hoang14 commited on
Commit
4ef05bf
·
verified ·
1 Parent(s): b786db6

Upload folder using huggingface_hub

Browse files
Files changed (50) hide show
  1. .gitattributes +1 -0
  2. 150/config.json +36 -0
  3. 150/generation_config.json +11 -0
  4. 150/latest +1 -0
  5. 150/model-00001-of-00030.safetensors +3 -0
  6. 150/model-00002-of-00030.safetensors +3 -0
  7. 150/model-00003-of-00030.safetensors +3 -0
  8. 150/model-00004-of-00030.safetensors +3 -0
  9. 150/model-00005-of-00030.safetensors +3 -0
  10. 150/model-00006-of-00030.safetensors +3 -0
  11. 150/model-00007-of-00030.safetensors +3 -0
  12. 150/model-00008-of-00030.safetensors +3 -0
  13. 150/model-00009-of-00030.safetensors +3 -0
  14. 150/model-00010-of-00030.safetensors +3 -0
  15. 150/model-00011-of-00030.safetensors +3 -0
  16. 150/model-00012-of-00030.safetensors +3 -0
  17. 150/model-00013-of-00030.safetensors +3 -0
  18. 150/model-00014-of-00030.safetensors +3 -0
  19. 150/model-00015-of-00030.safetensors +3 -0
  20. 150/model-00016-of-00030.safetensors +3 -0
  21. 150/model-00017-of-00030.safetensors +3 -0
  22. 150/model-00018-of-00030.safetensors +3 -0
  23. 150/model-00019-of-00030.safetensors +3 -0
  24. 150/model-00020-of-00030.safetensors +3 -0
  25. 150/model-00021-of-00030.safetensors +3 -0
  26. 150/model-00022-of-00030.safetensors +3 -0
  27. 150/model-00023-of-00030.safetensors +3 -0
  28. 150/model-00024-of-00030.safetensors +3 -0
  29. 150/model-00025-of-00030.safetensors +3 -0
  30. 150/model-00026-of-00030.safetensors +3 -0
  31. 150/model-00027-of-00030.safetensors +3 -0
  32. 150/model-00028-of-00030.safetensors +3 -0
  33. 150/model-00029-of-00030.safetensors +3 -0
  34. 150/model-00030-of-00030.safetensors +3 -0
  35. 150/model.safetensors.index.json +730 -0
  36. 150/rng_state_0.pth +3 -0
  37. 150/rng_state_1.pth +3 -0
  38. 150/rng_state_2.pth +3 -0
  39. 150/rng_state_3.pth +3 -0
  40. 150/rng_state_4.pth +3 -0
  41. 150/rng_state_5.pth +3 -0
  42. 150/rng_state_6.pth +3 -0
  43. 150/rng_state_7.pth +3 -0
  44. 150/scheduler.pt +3 -0
  45. 150/special_tokens_map.json +27 -0
  46. 150/tokenizer.json +3 -0
  47. 150/tokenizer_config.json +2070 -0
  48. 150/trainer_state.json +2112 -0
  49. 150/training_args.bin +3 -0
  50. 150/zero_to_fp32.py +674 -0
.gitattributes CHANGED
@@ -35,3 +35,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  050/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
  100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
37
  050/tokenizer.json filter=lfs diff=lfs merge=lfs -text
38
+ 150/tokenizer.json filter=lfs diff=lfs merge=lfs -text
150/config.json ADDED
@@ -0,0 +1,36 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "/raid/HUB_LLM/080225_vi_test_llama33_70b_instruct/checkpoint-2568/dpo32_epoch2/",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 128000,
9
+ "eos_token_id": 128009,
10
+ "head_dim": 128,
11
+ "hidden_act": "silu",
12
+ "hidden_size": 8192,
13
+ "initializer_range": 0.02,
14
+ "intermediate_size": 28672,
15
+ "max_position_embeddings": 16000,
16
+ "mlp_bias": false,
17
+ "model_type": "llama",
18
+ "num_attention_heads": 64,
19
+ "num_hidden_layers": 80,
20
+ "num_key_value_heads": 8,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": {
24
+ "factor": 8.0,
25
+ "high_freq_factor": 4.0,
26
+ "low_freq_factor": 1.0,
27
+ "original_max_position_embeddings": 8192,
28
+ "rope_type": "llama3"
29
+ },
30
+ "rope_theta": 500000.0,
31
+ "tie_word_embeddings": false,
32
+ "torch_dtype": "bfloat16",
33
+ "transformers_version": "4.46.3",
34
+ "use_cache": false,
35
+ "vocab_size": 128256
36
+ }
150/generation_config.json ADDED
@@ -0,0 +1,11 @@
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 128000,
4
+ "do_sample": true,
5
+ "eos_token_id": [
6
+ 128001,
7
+ 128008,
8
+ 128009
9
+ ],
10
+ "transformers_version": "4.46.3"
11
+ }
150/latest ADDED
@@ -0,0 +1 @@
 
 
1
+ global_step297
150/model-00001-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8bd8b50a77d5e52b5eddd2c1319a97c6d9633af77f2b1a1a43695c56350b0aa
3
+ size 4584408808
150/model-00002-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af30af56129342a9b7fc8d772c7bf35a761f8b15653de600eec13f5ae35bdc0a
3
+ size 4664167376
150/model-00003-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:77d737622fbe68a664afcf1f6d42252e056fb268030571805fab49fc13367ffe
3
+ size 4999711704
150/model-00004-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f5ef9fdf384c7557ce71739adb342da3b8c7b25d2f5666982766564638874bc
3
+ size 4966157032
150/model-00005-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26f8066e225268480e13605abe82c758fa4dcb34602dd96c2db2922b86607c85
3
+ size 4664134408
150/model-00006-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f441c060cc96c61cfa7101db178f22574eb89b410b91630c7a0c614fbe4e9ff4
3
+ size 4664167408
150/model-00007-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05346df513ec35072b152893adb50114678a2d5fa5e69ed8b3e4124c8a734ac2
3
+ size 4664167408
150/model-00008-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef06b476f47a7f819519fbaf10f886be24b94201075747c1166aee538b3d0240
3
+ size 4999711728
150/model-00009-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e5837cc0befc2921e99ec4df43515e913ada2f5f6d4a5e64b4a3aa5442fb642
3
+ size 4966157056
150/model-00010-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5d276379e41cf966b74448612ed5cf7b353e0a26c1c01aad2f51810ea3153376
3
+ size 4664134408
150/model-00011-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:92a5987e71d5ea99df8b1138394627b61a5a1d072ef1be4e7f9d5a86fe638d98
3
+ size 4664167408
150/model-00012-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:576c80a134b2536e880eb8c57c85182ebd431ee7f49c6d4f6e304df217dacf07
3
+ size 4664167408
150/model-00013-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:503cebc06bd7f947e94245505e4df1738753213d17f0b1813815787df2c26214
3
+ size 4999711728
150/model-00014-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:635c7698d4336d548bc33a73fe533ac80c037c3f7c726a93d7b46281feaa8e96
3
+ size 4966157056
150/model-00015-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c74d8c55ec49a8f8e0ec4e33fe5c3b6717103bef13b8a60931929df9ae0a31a
3
+ size 4664134408
150/model-00016-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34aeebdf5b8d3164d57925ef3d8c51c4ed0d6219b1f131cbb177ec9d2a2d4732
3
+ size 4664167408
150/model-00017-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:300be168b489f3b8e8efa17894a1b871ee4780ca333909319d01be61489a66fa
3
+ size 4664167408
150/model-00018-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e976c229c4fa6f4a521da06c4660b914573d33d3299c29a96444a4f36b53392d
3
+ size 4999711728
150/model-00019-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e27e16da30b347431570caae601492e53ea1b1a936e3dc2b381904c49a1b2dd
3
+ size 4966157056
150/model-00020-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ef4b96afb5c5eeb96d078cd6a6d18c538a70353003817fb31d8e1f4f1c22cb4
3
+ size 4664134408
150/model-00021-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b9ca30ee76cf01188e1abfddd85771686fca029f63d80d30c7d5f6f72714b2a9
3
+ size 4664167408
150/model-00022-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7c33b6e368f17c99e2b75f7c0c14e6d29bb756a883294f9ad0a7d5965f461e5c
3
+ size 4664167408
150/model-00023-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51d80c68884f091806e181cd9b8d3076f7f0e20c31cb11594745a890a27c791d
3
+ size 4999711728
150/model-00024-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43aed444d8ff89b5dc10b3d4e6cad8e9f047ef5404c44c2ab7fe20e8006976be
3
+ size 4966157056
150/model-00025-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4b2c71c79b766f177f76e3bc39fb15c4becb1cb8c59c13fe1d5984e8658b20e
3
+ size 4664134408
150/model-00026-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9f299314645cf2b31410e87fb4c815a2bf2c2cd121ed83417e3f9a991efed1a
3
+ size 4664167408
150/model-00027-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4171efa4c35a15f8ab9f3a890bc1e42f703bc56962438e06f09d430422d414d
3
+ size 4664167408
150/model-00028-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df8b315ffad891cc41ae8b1907f7c5c04999a20aa67655b2a38e665d97f93549
3
+ size 4999711728
150/model-00029-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee8f5428429b2a5a4f02e74414f9e12f62709c79eaa4e3d7678146cec7316fdc
3
+ size 4966173536
150/model-00030-of-00030.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c4494a5090f659874116494933fae691d2f8a806a6cfc666c29c2b06034d3b
3
+ size 2101346432
150/model.safetensors.index.json ADDED
@@ -0,0 +1,730 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 141107412992
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00030-of-00030.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00030.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00030.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00030.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00030.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00030.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00002-of-00030.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00030.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00030.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00030.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00030.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00030.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00005-of-00030.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00030.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00030.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00030.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00006-of-00030.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00030.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00030.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00030.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00030.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00030.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00030.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00030.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00030.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00030.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00030.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00030.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00007-of-00030.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00030.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00030.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00030.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00030.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00030.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00030.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00030.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00030.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00030.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00030.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00030.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00008-of-00030.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00030.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00030.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00030.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00030.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00030.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00030.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00030.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00030.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00030.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00030.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00030.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00030.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00009-of-00030.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00030.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00030.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00030.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00030.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00030.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00030.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00030.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00030.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00030.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00030.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00030.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00030.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00030.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00010-of-00030.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00030.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00030.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00030.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00011-of-00030.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00030.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00030.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00030.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00030.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00030.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00030.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00030.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00030.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00030.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00030.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00030.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00012-of-00030.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00030.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00030.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00030.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00030.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00030.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00030.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00030.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00030.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00030.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00030.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00030.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00030.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00030.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00030.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00030.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00030.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00013-of-00030.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00030.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00030.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00030.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00030.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00030.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00030.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00030.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00030.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00030.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00030.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00030.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00014-of-00030.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00030.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00030.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00030.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00030.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00014-of-00030.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00014-of-00030.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00030.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00030.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00030.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00030.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00030.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00030.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00030.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00015-of-00030.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00030.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00030.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00030.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00003-of-00030.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00030.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00030.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00030.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00030.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00016-of-00030.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00030.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00015-of-00030.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00030.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00030.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00030.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00030.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00030.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00016-of-00030.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00016-of-00030.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00016-of-00030.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00030.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00017-of-00030.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00030.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00030.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00030.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00030.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00030.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00030.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00017-of-00030.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00017-of-00030.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00030.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00017-of-00030.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00030.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00018-of-00030.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00030.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00030.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00030.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00030.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00030.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
395
+ "model.layers.48.input_layernorm.weight": "model-00018-of-00030.safetensors",
396
+ "model.layers.48.mlp.down_proj.weight": "model-00018-of-00030.safetensors",
397
+ "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00030.safetensors",
398
+ "model.layers.48.mlp.up_proj.weight": "model-00018-of-00030.safetensors",
399
+ "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00030.safetensors",
400
+ "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
401
+ "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00030.safetensors",
402
+ "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
403
+ "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
404
+ "model.layers.49.input_layernorm.weight": "model-00019-of-00030.safetensors",
405
+ "model.layers.49.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
406
+ "model.layers.49.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
407
+ "model.layers.49.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
408
+ "model.layers.49.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
409
+ "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00030.safetensors",
410
+ "model.layers.49.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
411
+ "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00030.safetensors",
412
+ "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00030.safetensors",
413
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00030.safetensors",
414
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
415
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
416
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
417
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
418
+ "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
419
+ "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
421
+ "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
422
+ "model.layers.50.input_layernorm.weight": "model-00019-of-00030.safetensors",
423
+ "model.layers.50.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
424
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
425
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
426
+ "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
427
+ "model.layers.50.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
428
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
429
+ "model.layers.50.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
430
+ "model.layers.50.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
431
+ "model.layers.51.input_layernorm.weight": "model-00019-of-00030.safetensors",
432
+ "model.layers.51.mlp.down_proj.weight": "model-00019-of-00030.safetensors",
433
+ "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00030.safetensors",
434
+ "model.layers.51.mlp.up_proj.weight": "model-00019-of-00030.safetensors",
435
+ "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00030.safetensors",
436
+ "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00030.safetensors",
437
+ "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00030.safetensors",
438
+ "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00030.safetensors",
439
+ "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00030.safetensors",
440
+ "model.layers.52.input_layernorm.weight": "model-00020-of-00030.safetensors",
441
+ "model.layers.52.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
442
+ "model.layers.52.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
443
+ "model.layers.52.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
444
+ "model.layers.52.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
445
+ "model.layers.52.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
446
+ "model.layers.52.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
447
+ "model.layers.52.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
448
+ "model.layers.52.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
449
+ "model.layers.53.input_layernorm.weight": "model-00020-of-00030.safetensors",
450
+ "model.layers.53.mlp.down_proj.weight": "model-00020-of-00030.safetensors",
451
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
452
+ "model.layers.53.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
453
+ "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00030.safetensors",
454
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
455
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
456
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
457
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
458
+ "model.layers.54.input_layernorm.weight": "model-00021-of-00030.safetensors",
459
+ "model.layers.54.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
460
+ "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00030.safetensors",
461
+ "model.layers.54.mlp.up_proj.weight": "model-00020-of-00030.safetensors",
462
+ "model.layers.54.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
463
+ "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00030.safetensors",
464
+ "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00030.safetensors",
465
+ "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00030.safetensors",
466
+ "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00030.safetensors",
467
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00030.safetensors",
468
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
469
+ "model.layers.55.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
470
+ "model.layers.55.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
471
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
472
+ "model.layers.55.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
473
+ "model.layers.55.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
474
+ "model.layers.55.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
475
+ "model.layers.55.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
476
+ "model.layers.56.input_layernorm.weight": "model-00021-of-00030.safetensors",
477
+ "model.layers.56.mlp.down_proj.weight": "model-00021-of-00030.safetensors",
478
+ "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
479
+ "model.layers.56.mlp.up_proj.weight": "model-00021-of-00030.safetensors",
480
+ "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00030.safetensors",
481
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
482
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
483
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
484
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
485
+ "model.layers.57.input_layernorm.weight": "model-00022-of-00030.safetensors",
486
+ "model.layers.57.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
487
+ "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00030.safetensors",
488
+ "model.layers.57.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
489
+ "model.layers.57.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
490
+ "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00030.safetensors",
491
+ "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00030.safetensors",
492
+ "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00030.safetensors",
493
+ "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00030.safetensors",
494
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00030.safetensors",
495
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
496
+ "model.layers.58.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
497
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
498
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
499
+ "model.layers.58.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
500
+ "model.layers.58.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
501
+ "model.layers.58.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
502
+ "model.layers.58.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
503
+ "model.layers.59.input_layernorm.weight": "model-00022-of-00030.safetensors",
504
+ "model.layers.59.mlp.down_proj.weight": "model-00022-of-00030.safetensors",
505
+ "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00030.safetensors",
506
+ "model.layers.59.mlp.up_proj.weight": "model-00022-of-00030.safetensors",
507
+ "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00030.safetensors",
508
+ "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
509
+ "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
510
+ "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
511
+ "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
512
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00030.safetensors",
513
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00030.safetensors",
514
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00030.safetensors",
515
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00030.safetensors",
516
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00030.safetensors",
517
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
518
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00030.safetensors",
519
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
520
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
521
+ "model.layers.60.input_layernorm.weight": "model-00023-of-00030.safetensors",
522
+ "model.layers.60.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
523
+ "model.layers.60.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
524
+ "model.layers.60.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
525
+ "model.layers.60.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
526
+ "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00030.safetensors",
527
+ "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00030.safetensors",
528
+ "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00030.safetensors",
529
+ "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00030.safetensors",
530
+ "model.layers.61.input_layernorm.weight": "model-00023-of-00030.safetensors",
531
+ "model.layers.61.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
532
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
533
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
534
+ "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
535
+ "model.layers.61.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
536
+ "model.layers.61.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
537
+ "model.layers.61.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
538
+ "model.layers.61.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
539
+ "model.layers.62.input_layernorm.weight": "model-00023-of-00030.safetensors",
540
+ "model.layers.62.mlp.down_proj.weight": "model-00023-of-00030.safetensors",
541
+ "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00030.safetensors",
542
+ "model.layers.62.mlp.up_proj.weight": "model-00023-of-00030.safetensors",
543
+ "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00030.safetensors",
544
+ "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
545
+ "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00030.safetensors",
546
+ "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
547
+ "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
548
+ "model.layers.63.input_layernorm.weight": "model-00024-of-00030.safetensors",
549
+ "model.layers.63.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
550
+ "model.layers.63.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
551
+ "model.layers.63.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
552
+ "model.layers.63.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
553
+ "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00030.safetensors",
554
+ "model.layers.63.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
555
+ "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00030.safetensors",
556
+ "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00030.safetensors",
557
+ "model.layers.64.input_layernorm.weight": "model-00024-of-00030.safetensors",
558
+ "model.layers.64.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
559
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
560
+ "model.layers.64.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
561
+ "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
562
+ "model.layers.64.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
563
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
564
+ "model.layers.64.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
565
+ "model.layers.64.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
566
+ "model.layers.65.input_layernorm.weight": "model-00024-of-00030.safetensors",
567
+ "model.layers.65.mlp.down_proj.weight": "model-00024-of-00030.safetensors",
568
+ "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00030.safetensors",
569
+ "model.layers.65.mlp.up_proj.weight": "model-00024-of-00030.safetensors",
570
+ "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00030.safetensors",
571
+ "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00030.safetensors",
572
+ "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00030.safetensors",
573
+ "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00030.safetensors",
574
+ "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00030.safetensors",
575
+ "model.layers.66.input_layernorm.weight": "model-00025-of-00030.safetensors",
576
+ "model.layers.66.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
577
+ "model.layers.66.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
578
+ "model.layers.66.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
579
+ "model.layers.66.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
580
+ "model.layers.66.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
581
+ "model.layers.66.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
582
+ "model.layers.66.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
583
+ "model.layers.66.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
584
+ "model.layers.67.input_layernorm.weight": "model-00025-of-00030.safetensors",
585
+ "model.layers.67.mlp.down_proj.weight": "model-00025-of-00030.safetensors",
586
+ "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
587
+ "model.layers.67.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
588
+ "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00030.safetensors",
589
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
590
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
591
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
592
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
593
+ "model.layers.68.input_layernorm.weight": "model-00026-of-00030.safetensors",
594
+ "model.layers.68.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
595
+ "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00030.safetensors",
596
+ "model.layers.68.mlp.up_proj.weight": "model-00025-of-00030.safetensors",
597
+ "model.layers.68.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
598
+ "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00030.safetensors",
599
+ "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00030.safetensors",
600
+ "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00030.safetensors",
601
+ "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00030.safetensors",
602
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00030.safetensors",
603
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
604
+ "model.layers.69.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
605
+ "model.layers.69.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
606
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
607
+ "model.layers.69.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
608
+ "model.layers.69.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
609
+ "model.layers.69.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
610
+ "model.layers.69.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
611
+ "model.layers.7.input_layernorm.weight": "model-00004-of-00030.safetensors",
612
+ "model.layers.7.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
613
+ "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
614
+ "model.layers.7.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
615
+ "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
616
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00030.safetensors",
617
+ "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
618
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00030.safetensors",
619
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00030.safetensors",
620
+ "model.layers.70.input_layernorm.weight": "model-00026-of-00030.safetensors",
621
+ "model.layers.70.mlp.down_proj.weight": "model-00026-of-00030.safetensors",
622
+ "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
623
+ "model.layers.70.mlp.up_proj.weight": "model-00026-of-00030.safetensors",
624
+ "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00030.safetensors",
625
+ "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
626
+ "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
627
+ "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
628
+ "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
629
+ "model.layers.71.input_layernorm.weight": "model-00027-of-00030.safetensors",
630
+ "model.layers.71.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
631
+ "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00030.safetensors",
632
+ "model.layers.71.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
633
+ "model.layers.71.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
634
+ "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00030.safetensors",
635
+ "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00030.safetensors",
636
+ "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00030.safetensors",
637
+ "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00030.safetensors",
638
+ "model.layers.72.input_layernorm.weight": "model-00027-of-00030.safetensors",
639
+ "model.layers.72.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
640
+ "model.layers.72.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
641
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
642
+ "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
643
+ "model.layers.72.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
644
+ "model.layers.72.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
645
+ "model.layers.72.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
646
+ "model.layers.72.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
647
+ "model.layers.73.input_layernorm.weight": "model-00027-of-00030.safetensors",
648
+ "model.layers.73.mlp.down_proj.weight": "model-00027-of-00030.safetensors",
649
+ "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00030.safetensors",
650
+ "model.layers.73.mlp.up_proj.weight": "model-00027-of-00030.safetensors",
651
+ "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00030.safetensors",
652
+ "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
653
+ "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
654
+ "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
655
+ "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
656
+ "model.layers.74.input_layernorm.weight": "model-00028-of-00030.safetensors",
657
+ "model.layers.74.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
658
+ "model.layers.74.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
659
+ "model.layers.74.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
660
+ "model.layers.74.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
661
+ "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00030.safetensors",
662
+ "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00030.safetensors",
663
+ "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00030.safetensors",
664
+ "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00030.safetensors",
665
+ "model.layers.75.input_layernorm.weight": "model-00028-of-00030.safetensors",
666
+ "model.layers.75.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
667
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
668
+ "model.layers.75.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
669
+ "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
670
+ "model.layers.75.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
671
+ "model.layers.75.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
672
+ "model.layers.75.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
673
+ "model.layers.75.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
674
+ "model.layers.76.input_layernorm.weight": "model-00028-of-00030.safetensors",
675
+ "model.layers.76.mlp.down_proj.weight": "model-00028-of-00030.safetensors",
676
+ "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00030.safetensors",
677
+ "model.layers.76.mlp.up_proj.weight": "model-00028-of-00030.safetensors",
678
+ "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00030.safetensors",
679
+ "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
680
+ "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00030.safetensors",
681
+ "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
682
+ "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
683
+ "model.layers.77.input_layernorm.weight": "model-00029-of-00030.safetensors",
684
+ "model.layers.77.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
685
+ "model.layers.77.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
686
+ "model.layers.77.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
687
+ "model.layers.77.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
688
+ "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00030.safetensors",
689
+ "model.layers.77.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
690
+ "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00030.safetensors",
691
+ "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00030.safetensors",
692
+ "model.layers.78.input_layernorm.weight": "model-00029-of-00030.safetensors",
693
+ "model.layers.78.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
694
+ "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
695
+ "model.layers.78.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
696
+ "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
697
+ "model.layers.78.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
698
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
699
+ "model.layers.78.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
700
+ "model.layers.78.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
701
+ "model.layers.79.input_layernorm.weight": "model-00029-of-00030.safetensors",
702
+ "model.layers.79.mlp.down_proj.weight": "model-00029-of-00030.safetensors",
703
+ "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00030.safetensors",
704
+ "model.layers.79.mlp.up_proj.weight": "model-00029-of-00030.safetensors",
705
+ "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00030.safetensors",
706
+ "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00030.safetensors",
707
+ "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00030.safetensors",
708
+ "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00030.safetensors",
709
+ "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00030.safetensors",
710
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00030.safetensors",
711
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
712
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
713
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
714
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
715
+ "model.layers.8.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
716
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
717
+ "model.layers.8.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
718
+ "model.layers.8.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
719
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00030.safetensors",
720
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00030.safetensors",
721
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00030.safetensors",
722
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00030.safetensors",
723
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00030.safetensors",
724
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00030.safetensors",
725
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00030.safetensors",
726
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00030.safetensors",
727
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00030.safetensors",
728
+ "model.norm.weight": "model-00029-of-00030.safetensors"
729
+ }
730
+ }
150/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
3
+ size 15984
150/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
3
+ size 15984
150/rng_state_2.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
3
+ size 15984
150/rng_state_3.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
3
+ size 15984
150/rng_state_4.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
3
+ size 15984
150/rng_state_5.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
3
+ size 15984
150/rng_state_6.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
3
+ size 15984
150/rng_state_7.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
3
+ size 15984
150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8ee6bb45db64a238048801013c8cfa9bbe1bc3c20b31f2d4cc5db65568b0cb46
3
+ size 1064
150/special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|eot_id|>",
4
+ "<|eom_id|>"
5
+ ],
6
+ "bos_token": {
7
+ "content": "<|begin_of_text|>",
8
+ "lstrip": false,
9
+ "normalized": false,
10
+ "rstrip": false,
11
+ "single_word": false
12
+ },
13
+ "eos_token": {
14
+ "content": "<|eot_id|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false
19
+ },
20
+ "pad_token": {
21
+ "content": "<|end_of_text|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
150/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
3
+ size 17209920
150/tokenizer_config.json ADDED
@@ -0,0 +1,2070 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "128000": {
4
+ "content": "<|begin_of_text|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "128001": {
12
+ "content": "<|end_of_text|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "128002": {
20
+ "content": "<|reserved_special_token_0|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "128003": {
28
+ "content": "<|reserved_special_token_1|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "128004": {
36
+ "content": "<|finetune_right_pad_id|>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "128005": {
44
+ "content": "<|reserved_special_token_2|>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "128006": {
52
+ "content": "<|start_header_id|>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "128007": {
60
+ "content": "<|end_header_id|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "128008": {
68
+ "content": "<|eom_id|>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "128009": {
76
+ "content": "<|eot_id|>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "128010": {
84
+ "content": "<|python_tag|>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "128011": {
92
+ "content": "<|reserved_special_token_3|>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "128012": {
100
+ "content": "<|reserved_special_token_4|>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "128013": {
108
+ "content": "<|reserved_special_token_5|>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "128014": {
116
+ "content": "<|reserved_special_token_6|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "128015": {
124
+ "content": "<|reserved_special_token_7|>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "128016": {
132
+ "content": "<|reserved_special_token_8|>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "128017": {
140
+ "content": "<|reserved_special_token_9|>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "128018": {
148
+ "content": "<|reserved_special_token_10|>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "128019": {
156
+ "content": "<|reserved_special_token_11|>",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "128020": {
164
+ "content": "<|reserved_special_token_12|>",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "128021": {
172
+ "content": "<|reserved_special_token_13|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "128022": {
180
+ "content": "<|reserved_special_token_14|>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "128023": {
188
+ "content": "<|reserved_special_token_15|>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "128024": {
196
+ "content": "<|reserved_special_token_16|>",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "128025": {
204
+ "content": "<|reserved_special_token_17|>",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "128026": {
212
+ "content": "<|reserved_special_token_18|>",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "128027": {
220
+ "content": "<|reserved_special_token_19|>",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "128028": {
228
+ "content": "<|reserved_special_token_20|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "128029": {
236
+ "content": "<|reserved_special_token_21|>",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "128030": {
244
+ "content": "<|reserved_special_token_22|>",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "128031": {
252
+ "content": "<|reserved_special_token_23|>",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "128032": {
260
+ "content": "<|reserved_special_token_24|>",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "128033": {
268
+ "content": "<|reserved_special_token_25|>",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "128034": {
276
+ "content": "<|reserved_special_token_26|>",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "128035": {
284
+ "content": "<|reserved_special_token_27|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "128036": {
292
+ "content": "<|reserved_special_token_28|>",
293
+ "lstrip": false,
294
+ "normalized": false,
295
+ "rstrip": false,
296
+ "single_word": false,
297
+ "special": true
298
+ },
299
+ "128037": {
300
+ "content": "<|reserved_special_token_29|>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "128038": {
308
+ "content": "<|reserved_special_token_30|>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "128039": {
316
+ "content": "<|reserved_special_token_31|>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "128040": {
324
+ "content": "<|reserved_special_token_32|>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "128041": {
332
+ "content": "<|reserved_special_token_33|>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "128042": {
340
+ "content": "<|reserved_special_token_34|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "128043": {
348
+ "content": "<|reserved_special_token_35|>",
349
+ "lstrip": false,
350
+ "normalized": false,
351
+ "rstrip": false,
352
+ "single_word": false,
353
+ "special": true
354
+ },
355
+ "128044": {
356
+ "content": "<|reserved_special_token_36|>",
357
+ "lstrip": false,
358
+ "normalized": false,
359
+ "rstrip": false,
360
+ "single_word": false,
361
+ "special": true
362
+ },
363
+ "128045": {
364
+ "content": "<|reserved_special_token_37|>",
365
+ "lstrip": false,
366
+ "normalized": false,
367
+ "rstrip": false,
368
+ "single_word": false,
369
+ "special": true
370
+ },
371
+ "128046": {
372
+ "content": "<|reserved_special_token_38|>",
373
+ "lstrip": false,
374
+ "normalized": false,
375
+ "rstrip": false,
376
+ "single_word": false,
377
+ "special": true
378
+ },
379
+ "128047": {
380
+ "content": "<|reserved_special_token_39|>",
381
+ "lstrip": false,
382
+ "normalized": false,
383
+ "rstrip": false,
384
+ "single_word": false,
385
+ "special": true
386
+ },
387
+ "128048": {
388
+ "content": "<|reserved_special_token_40|>",
389
+ "lstrip": false,
390
+ "normalized": false,
391
+ "rstrip": false,
392
+ "single_word": false,
393
+ "special": true
394
+ },
395
+ "128049": {
396
+ "content": "<|reserved_special_token_41|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false,
401
+ "special": true
402
+ },
403
+ "128050": {
404
+ "content": "<|reserved_special_token_42|>",
405
+ "lstrip": false,
406
+ "normalized": false,
407
+ "rstrip": false,
408
+ "single_word": false,
409
+ "special": true
410
+ },
411
+ "128051": {
412
+ "content": "<|reserved_special_token_43|>",
413
+ "lstrip": false,
414
+ "normalized": false,
415
+ "rstrip": false,
416
+ "single_word": false,
417
+ "special": true
418
+ },
419
+ "128052": {
420
+ "content": "<|reserved_special_token_44|>",
421
+ "lstrip": false,
422
+ "normalized": false,
423
+ "rstrip": false,
424
+ "single_word": false,
425
+ "special": true
426
+ },
427
+ "128053": {
428
+ "content": "<|reserved_special_token_45|>",
429
+ "lstrip": false,
430
+ "normalized": false,
431
+ "rstrip": false,
432
+ "single_word": false,
433
+ "special": true
434
+ },
435
+ "128054": {
436
+ "content": "<|reserved_special_token_46|>",
437
+ "lstrip": false,
438
+ "normalized": false,
439
+ "rstrip": false,
440
+ "single_word": false,
441
+ "special": true
442
+ },
443
+ "128055": {
444
+ "content": "<|reserved_special_token_47|>",
445
+ "lstrip": false,
446
+ "normalized": false,
447
+ "rstrip": false,
448
+ "single_word": false,
449
+ "special": true
450
+ },
451
+ "128056": {
452
+ "content": "<|reserved_special_token_48|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false,
457
+ "special": true
458
+ },
459
+ "128057": {
460
+ "content": "<|reserved_special_token_49|>",
461
+ "lstrip": false,
462
+ "normalized": false,
463
+ "rstrip": false,
464
+ "single_word": false,
465
+ "special": true
466
+ },
467
+ "128058": {
468
+ "content": "<|reserved_special_token_50|>",
469
+ "lstrip": false,
470
+ "normalized": false,
471
+ "rstrip": false,
472
+ "single_word": false,
473
+ "special": true
474
+ },
475
+ "128059": {
476
+ "content": "<|reserved_special_token_51|>",
477
+ "lstrip": false,
478
+ "normalized": false,
479
+ "rstrip": false,
480
+ "single_word": false,
481
+ "special": true
482
+ },
483
+ "128060": {
484
+ "content": "<|reserved_special_token_52|>",
485
+ "lstrip": false,
486
+ "normalized": false,
487
+ "rstrip": false,
488
+ "single_word": false,
489
+ "special": true
490
+ },
491
+ "128061": {
492
+ "content": "<|reserved_special_token_53|>",
493
+ "lstrip": false,
494
+ "normalized": false,
495
+ "rstrip": false,
496
+ "single_word": false,
497
+ "special": true
498
+ },
499
+ "128062": {
500
+ "content": "<|reserved_special_token_54|>",
501
+ "lstrip": false,
502
+ "normalized": false,
503
+ "rstrip": false,
504
+ "single_word": false,
505
+ "special": true
506
+ },
507
+ "128063": {
508
+ "content": "<|reserved_special_token_55|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false,
513
+ "special": true
514
+ },
515
+ "128064": {
516
+ "content": "<|reserved_special_token_56|>",
517
+ "lstrip": false,
518
+ "normalized": false,
519
+ "rstrip": false,
520
+ "single_word": false,
521
+ "special": true
522
+ },
523
+ "128065": {
524
+ "content": "<|reserved_special_token_57|>",
525
+ "lstrip": false,
526
+ "normalized": false,
527
+ "rstrip": false,
528
+ "single_word": false,
529
+ "special": true
530
+ },
531
+ "128066": {
532
+ "content": "<|reserved_special_token_58|>",
533
+ "lstrip": false,
534
+ "normalized": false,
535
+ "rstrip": false,
536
+ "single_word": false,
537
+ "special": true
538
+ },
539
+ "128067": {
540
+ "content": "<|reserved_special_token_59|>",
541
+ "lstrip": false,
542
+ "normalized": false,
543
+ "rstrip": false,
544
+ "single_word": false,
545
+ "special": true
546
+ },
547
+ "128068": {
548
+ "content": "<|reserved_special_token_60|>",
549
+ "lstrip": false,
550
+ "normalized": false,
551
+ "rstrip": false,
552
+ "single_word": false,
553
+ "special": true
554
+ },
555
+ "128069": {
556
+ "content": "<|reserved_special_token_61|>",
557
+ "lstrip": false,
558
+ "normalized": false,
559
+ "rstrip": false,
560
+ "single_word": false,
561
+ "special": true
562
+ },
563
+ "128070": {
564
+ "content": "<|reserved_special_token_62|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false,
569
+ "special": true
570
+ },
571
+ "128071": {
572
+ "content": "<|reserved_special_token_63|>",
573
+ "lstrip": false,
574
+ "normalized": false,
575
+ "rstrip": false,
576
+ "single_word": false,
577
+ "special": true
578
+ },
579
+ "128072": {
580
+ "content": "<|reserved_special_token_64|>",
581
+ "lstrip": false,
582
+ "normalized": false,
583
+ "rstrip": false,
584
+ "single_word": false,
585
+ "special": true
586
+ },
587
+ "128073": {
588
+ "content": "<|reserved_special_token_65|>",
589
+ "lstrip": false,
590
+ "normalized": false,
591
+ "rstrip": false,
592
+ "single_word": false,
593
+ "special": true
594
+ },
595
+ "128074": {
596
+ "content": "<|reserved_special_token_66|>",
597
+ "lstrip": false,
598
+ "normalized": false,
599
+ "rstrip": false,
600
+ "single_word": false,
601
+ "special": true
602
+ },
603
+ "128075": {
604
+ "content": "<|reserved_special_token_67|>",
605
+ "lstrip": false,
606
+ "normalized": false,
607
+ "rstrip": false,
608
+ "single_word": false,
609
+ "special": true
610
+ },
611
+ "128076": {
612
+ "content": "<|reserved_special_token_68|>",
613
+ "lstrip": false,
614
+ "normalized": false,
615
+ "rstrip": false,
616
+ "single_word": false,
617
+ "special": true
618
+ },
619
+ "128077": {
620
+ "content": "<|reserved_special_token_69|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false,
625
+ "special": true
626
+ },
627
+ "128078": {
628
+ "content": "<|reserved_special_token_70|>",
629
+ "lstrip": false,
630
+ "normalized": false,
631
+ "rstrip": false,
632
+ "single_word": false,
633
+ "special": true
634
+ },
635
+ "128079": {
636
+ "content": "<|reserved_special_token_71|>",
637
+ "lstrip": false,
638
+ "normalized": false,
639
+ "rstrip": false,
640
+ "single_word": false,
641
+ "special": true
642
+ },
643
+ "128080": {
644
+ "content": "<|reserved_special_token_72|>",
645
+ "lstrip": false,
646
+ "normalized": false,
647
+ "rstrip": false,
648
+ "single_word": false,
649
+ "special": true
650
+ },
651
+ "128081": {
652
+ "content": "<|reserved_special_token_73|>",
653
+ "lstrip": false,
654
+ "normalized": false,
655
+ "rstrip": false,
656
+ "single_word": false,
657
+ "special": true
658
+ },
659
+ "128082": {
660
+ "content": "<|reserved_special_token_74|>",
661
+ "lstrip": false,
662
+ "normalized": false,
663
+ "rstrip": false,
664
+ "single_word": false,
665
+ "special": true
666
+ },
667
+ "128083": {
668
+ "content": "<|reserved_special_token_75|>",
669
+ "lstrip": false,
670
+ "normalized": false,
671
+ "rstrip": false,
672
+ "single_word": false,
673
+ "special": true
674
+ },
675
+ "128084": {
676
+ "content": "<|reserved_special_token_76|>",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false,
681
+ "special": true
682
+ },
683
+ "128085": {
684
+ "content": "<|reserved_special_token_77|>",
685
+ "lstrip": false,
686
+ "normalized": false,
687
+ "rstrip": false,
688
+ "single_word": false,
689
+ "special": true
690
+ },
691
+ "128086": {
692
+ "content": "<|reserved_special_token_78|>",
693
+ "lstrip": false,
694
+ "normalized": false,
695
+ "rstrip": false,
696
+ "single_word": false,
697
+ "special": true
698
+ },
699
+ "128087": {
700
+ "content": "<|reserved_special_token_79|>",
701
+ "lstrip": false,
702
+ "normalized": false,
703
+ "rstrip": false,
704
+ "single_word": false,
705
+ "special": true
706
+ },
707
+ "128088": {
708
+ "content": "<|reserved_special_token_80|>",
709
+ "lstrip": false,
710
+ "normalized": false,
711
+ "rstrip": false,
712
+ "single_word": false,
713
+ "special": true
714
+ },
715
+ "128089": {
716
+ "content": "<|reserved_special_token_81|>",
717
+ "lstrip": false,
718
+ "normalized": false,
719
+ "rstrip": false,
720
+ "single_word": false,
721
+ "special": true
722
+ },
723
+ "128090": {
724
+ "content": "<|reserved_special_token_82|>",
725
+ "lstrip": false,
726
+ "normalized": false,
727
+ "rstrip": false,
728
+ "single_word": false,
729
+ "special": true
730
+ },
731
+ "128091": {
732
+ "content": "<|reserved_special_token_83|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false,
737
+ "special": true
738
+ },
739
+ "128092": {
740
+ "content": "<|reserved_special_token_84|>",
741
+ "lstrip": false,
742
+ "normalized": false,
743
+ "rstrip": false,
744
+ "single_word": false,
745
+ "special": true
746
+ },
747
+ "128093": {
748
+ "content": "<|reserved_special_token_85|>",
749
+ "lstrip": false,
750
+ "normalized": false,
751
+ "rstrip": false,
752
+ "single_word": false,
753
+ "special": true
754
+ },
755
+ "128094": {
756
+ "content": "<|reserved_special_token_86|>",
757
+ "lstrip": false,
758
+ "normalized": false,
759
+ "rstrip": false,
760
+ "single_word": false,
761
+ "special": true
762
+ },
763
+ "128095": {
764
+ "content": "<|reserved_special_token_87|>",
765
+ "lstrip": false,
766
+ "normalized": false,
767
+ "rstrip": false,
768
+ "single_word": false,
769
+ "special": true
770
+ },
771
+ "128096": {
772
+ "content": "<|reserved_special_token_88|>",
773
+ "lstrip": false,
774
+ "normalized": false,
775
+ "rstrip": false,
776
+ "single_word": false,
777
+ "special": true
778
+ },
779
+ "128097": {
780
+ "content": "<|reserved_special_token_89|>",
781
+ "lstrip": false,
782
+ "normalized": false,
783
+ "rstrip": false,
784
+ "single_word": false,
785
+ "special": true
786
+ },
787
+ "128098": {
788
+ "content": "<|reserved_special_token_90|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false,
793
+ "special": true
794
+ },
795
+ "128099": {
796
+ "content": "<|reserved_special_token_91|>",
797
+ "lstrip": false,
798
+ "normalized": false,
799
+ "rstrip": false,
800
+ "single_word": false,
801
+ "special": true
802
+ },
803
+ "128100": {
804
+ "content": "<|reserved_special_token_92|>",
805
+ "lstrip": false,
806
+ "normalized": false,
807
+ "rstrip": false,
808
+ "single_word": false,
809
+ "special": true
810
+ },
811
+ "128101": {
812
+ "content": "<|reserved_special_token_93|>",
813
+ "lstrip": false,
814
+ "normalized": false,
815
+ "rstrip": false,
816
+ "single_word": false,
817
+ "special": true
818
+ },
819
+ "128102": {
820
+ "content": "<|reserved_special_token_94|>",
821
+ "lstrip": false,
822
+ "normalized": false,
823
+ "rstrip": false,
824
+ "single_word": false,
825
+ "special": true
826
+ },
827
+ "128103": {
828
+ "content": "<|reserved_special_token_95|>",
829
+ "lstrip": false,
830
+ "normalized": false,
831
+ "rstrip": false,
832
+ "single_word": false,
833
+ "special": true
834
+ },
835
+ "128104": {
836
+ "content": "<|reserved_special_token_96|>",
837
+ "lstrip": false,
838
+ "normalized": false,
839
+ "rstrip": false,
840
+ "single_word": false,
841
+ "special": true
842
+ },
843
+ "128105": {
844
+ "content": "<|reserved_special_token_97|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false,
849
+ "special": true
850
+ },
851
+ "128106": {
852
+ "content": "<|reserved_special_token_98|>",
853
+ "lstrip": false,
854
+ "normalized": false,
855
+ "rstrip": false,
856
+ "single_word": false,
857
+ "special": true
858
+ },
859
+ "128107": {
860
+ "content": "<|reserved_special_token_99|>",
861
+ "lstrip": false,
862
+ "normalized": false,
863
+ "rstrip": false,
864
+ "single_word": false,
865
+ "special": true
866
+ },
867
+ "128108": {
868
+ "content": "<|reserved_special_token_100|>",
869
+ "lstrip": false,
870
+ "normalized": false,
871
+ "rstrip": false,
872
+ "single_word": false,
873
+ "special": true
874
+ },
875
+ "128109": {
876
+ "content": "<|reserved_special_token_101|>",
877
+ "lstrip": false,
878
+ "normalized": false,
879
+ "rstrip": false,
880
+ "single_word": false,
881
+ "special": true
882
+ },
883
+ "128110": {
884
+ "content": "<|reserved_special_token_102|>",
885
+ "lstrip": false,
886
+ "normalized": false,
887
+ "rstrip": false,
888
+ "single_word": false,
889
+ "special": true
890
+ },
891
+ "128111": {
892
+ "content": "<|reserved_special_token_103|>",
893
+ "lstrip": false,
894
+ "normalized": false,
895
+ "rstrip": false,
896
+ "single_word": false,
897
+ "special": true
898
+ },
899
+ "128112": {
900
+ "content": "<|reserved_special_token_104|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false,
905
+ "special": true
906
+ },
907
+ "128113": {
908
+ "content": "<|reserved_special_token_105|>",
909
+ "lstrip": false,
910
+ "normalized": false,
911
+ "rstrip": false,
912
+ "single_word": false,
913
+ "special": true
914
+ },
915
+ "128114": {
916
+ "content": "<|reserved_special_token_106|>",
917
+ "lstrip": false,
918
+ "normalized": false,
919
+ "rstrip": false,
920
+ "single_word": false,
921
+ "special": true
922
+ },
923
+ "128115": {
924
+ "content": "<|reserved_special_token_107|>",
925
+ "lstrip": false,
926
+ "normalized": false,
927
+ "rstrip": false,
928
+ "single_word": false,
929
+ "special": true
930
+ },
931
+ "128116": {
932
+ "content": "<|reserved_special_token_108|>",
933
+ "lstrip": false,
934
+ "normalized": false,
935
+ "rstrip": false,
936
+ "single_word": false,
937
+ "special": true
938
+ },
939
+ "128117": {
940
+ "content": "<|reserved_special_token_109|>",
941
+ "lstrip": false,
942
+ "normalized": false,
943
+ "rstrip": false,
944
+ "single_word": false,
945
+ "special": true
946
+ },
947
+ "128118": {
948
+ "content": "<|reserved_special_token_110|>",
949
+ "lstrip": false,
950
+ "normalized": false,
951
+ "rstrip": false,
952
+ "single_word": false,
953
+ "special": true
954
+ },
955
+ "128119": {
956
+ "content": "<|reserved_special_token_111|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false,
961
+ "special": true
962
+ },
963
+ "128120": {
964
+ "content": "<|reserved_special_token_112|>",
965
+ "lstrip": false,
966
+ "normalized": false,
967
+ "rstrip": false,
968
+ "single_word": false,
969
+ "special": true
970
+ },
971
+ "128121": {
972
+ "content": "<|reserved_special_token_113|>",
973
+ "lstrip": false,
974
+ "normalized": false,
975
+ "rstrip": false,
976
+ "single_word": false,
977
+ "special": true
978
+ },
979
+ "128122": {
980
+ "content": "<|reserved_special_token_114|>",
981
+ "lstrip": false,
982
+ "normalized": false,
983
+ "rstrip": false,
984
+ "single_word": false,
985
+ "special": true
986
+ },
987
+ "128123": {
988
+ "content": "<|reserved_special_token_115|>",
989
+ "lstrip": false,
990
+ "normalized": false,
991
+ "rstrip": false,
992
+ "single_word": false,
993
+ "special": true
994
+ },
995
+ "128124": {
996
+ "content": "<|reserved_special_token_116|>",
997
+ "lstrip": false,
998
+ "normalized": false,
999
+ "rstrip": false,
1000
+ "single_word": false,
1001
+ "special": true
1002
+ },
1003
+ "128125": {
1004
+ "content": "<|reserved_special_token_117|>",
1005
+ "lstrip": false,
1006
+ "normalized": false,
1007
+ "rstrip": false,
1008
+ "single_word": false,
1009
+ "special": true
1010
+ },
1011
+ "128126": {
1012
+ "content": "<|reserved_special_token_118|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false,
1017
+ "special": true
1018
+ },
1019
+ "128127": {
1020
+ "content": "<|reserved_special_token_119|>",
1021
+ "lstrip": false,
1022
+ "normalized": false,
1023
+ "rstrip": false,
1024
+ "single_word": false,
1025
+ "special": true
1026
+ },
1027
+ "128128": {
1028
+ "content": "<|reserved_special_token_120|>",
1029
+ "lstrip": false,
1030
+ "normalized": false,
1031
+ "rstrip": false,
1032
+ "single_word": false,
1033
+ "special": true
1034
+ },
1035
+ "128129": {
1036
+ "content": "<|reserved_special_token_121|>",
1037
+ "lstrip": false,
1038
+ "normalized": false,
1039
+ "rstrip": false,
1040
+ "single_word": false,
1041
+ "special": true
1042
+ },
1043
+ "128130": {
1044
+ "content": "<|reserved_special_token_122|>",
1045
+ "lstrip": false,
1046
+ "normalized": false,
1047
+ "rstrip": false,
1048
+ "single_word": false,
1049
+ "special": true
1050
+ },
1051
+ "128131": {
1052
+ "content": "<|reserved_special_token_123|>",
1053
+ "lstrip": false,
1054
+ "normalized": false,
1055
+ "rstrip": false,
1056
+ "single_word": false,
1057
+ "special": true
1058
+ },
1059
+ "128132": {
1060
+ "content": "<|reserved_special_token_124|>",
1061
+ "lstrip": false,
1062
+ "normalized": false,
1063
+ "rstrip": false,
1064
+ "single_word": false,
1065
+ "special": true
1066
+ },
1067
+ "128133": {
1068
+ "content": "<|reserved_special_token_125|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false,
1073
+ "special": true
1074
+ },
1075
+ "128134": {
1076
+ "content": "<|reserved_special_token_126|>",
1077
+ "lstrip": false,
1078
+ "normalized": false,
1079
+ "rstrip": false,
1080
+ "single_word": false,
1081
+ "special": true
1082
+ },
1083
+ "128135": {
1084
+ "content": "<|reserved_special_token_127|>",
1085
+ "lstrip": false,
1086
+ "normalized": false,
1087
+ "rstrip": false,
1088
+ "single_word": false,
1089
+ "special": true
1090
+ },
1091
+ "128136": {
1092
+ "content": "<|reserved_special_token_128|>",
1093
+ "lstrip": false,
1094
+ "normalized": false,
1095
+ "rstrip": false,
1096
+ "single_word": false,
1097
+ "special": true
1098
+ },
1099
+ "128137": {
1100
+ "content": "<|reserved_special_token_129|>",
1101
+ "lstrip": false,
1102
+ "normalized": false,
1103
+ "rstrip": false,
1104
+ "single_word": false,
1105
+ "special": true
1106
+ },
1107
+ "128138": {
1108
+ "content": "<|reserved_special_token_130|>",
1109
+ "lstrip": false,
1110
+ "normalized": false,
1111
+ "rstrip": false,
1112
+ "single_word": false,
1113
+ "special": true
1114
+ },
1115
+ "128139": {
1116
+ "content": "<|reserved_special_token_131|>",
1117
+ "lstrip": false,
1118
+ "normalized": false,
1119
+ "rstrip": false,
1120
+ "single_word": false,
1121
+ "special": true
1122
+ },
1123
+ "128140": {
1124
+ "content": "<|reserved_special_token_132|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false,
1129
+ "special": true
1130
+ },
1131
+ "128141": {
1132
+ "content": "<|reserved_special_token_133|>",
1133
+ "lstrip": false,
1134
+ "normalized": false,
1135
+ "rstrip": false,
1136
+ "single_word": false,
1137
+ "special": true
1138
+ },
1139
+ "128142": {
1140
+ "content": "<|reserved_special_token_134|>",
1141
+ "lstrip": false,
1142
+ "normalized": false,
1143
+ "rstrip": false,
1144
+ "single_word": false,
1145
+ "special": true
1146
+ },
1147
+ "128143": {
1148
+ "content": "<|reserved_special_token_135|>",
1149
+ "lstrip": false,
1150
+ "normalized": false,
1151
+ "rstrip": false,
1152
+ "single_word": false,
1153
+ "special": true
1154
+ },
1155
+ "128144": {
1156
+ "content": "<|reserved_special_token_136|>",
1157
+ "lstrip": false,
1158
+ "normalized": false,
1159
+ "rstrip": false,
1160
+ "single_word": false,
1161
+ "special": true
1162
+ },
1163
+ "128145": {
1164
+ "content": "<|reserved_special_token_137|>",
1165
+ "lstrip": false,
1166
+ "normalized": false,
1167
+ "rstrip": false,
1168
+ "single_word": false,
1169
+ "special": true
1170
+ },
1171
+ "128146": {
1172
+ "content": "<|reserved_special_token_138|>",
1173
+ "lstrip": false,
1174
+ "normalized": false,
1175
+ "rstrip": false,
1176
+ "single_word": false,
1177
+ "special": true
1178
+ },
1179
+ "128147": {
1180
+ "content": "<|reserved_special_token_139|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false,
1185
+ "special": true
1186
+ },
1187
+ "128148": {
1188
+ "content": "<|reserved_special_token_140|>",
1189
+ "lstrip": false,
1190
+ "normalized": false,
1191
+ "rstrip": false,
1192
+ "single_word": false,
1193
+ "special": true
1194
+ },
1195
+ "128149": {
1196
+ "content": "<|reserved_special_token_141|>",
1197
+ "lstrip": false,
1198
+ "normalized": false,
1199
+ "rstrip": false,
1200
+ "single_word": false,
1201
+ "special": true
1202
+ },
1203
+ "128150": {
1204
+ "content": "<|reserved_special_token_142|>",
1205
+ "lstrip": false,
1206
+ "normalized": false,
1207
+ "rstrip": false,
1208
+ "single_word": false,
1209
+ "special": true
1210
+ },
1211
+ "128151": {
1212
+ "content": "<|reserved_special_token_143|>",
1213
+ "lstrip": false,
1214
+ "normalized": false,
1215
+ "rstrip": false,
1216
+ "single_word": false,
1217
+ "special": true
1218
+ },
1219
+ "128152": {
1220
+ "content": "<|reserved_special_token_144|>",
1221
+ "lstrip": false,
1222
+ "normalized": false,
1223
+ "rstrip": false,
1224
+ "single_word": false,
1225
+ "special": true
1226
+ },
1227
+ "128153": {
1228
+ "content": "<|reserved_special_token_145|>",
1229
+ "lstrip": false,
1230
+ "normalized": false,
1231
+ "rstrip": false,
1232
+ "single_word": false,
1233
+ "special": true
1234
+ },
1235
+ "128154": {
1236
+ "content": "<|reserved_special_token_146|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false,
1241
+ "special": true
1242
+ },
1243
+ "128155": {
1244
+ "content": "<|reserved_special_token_147|>",
1245
+ "lstrip": false,
1246
+ "normalized": false,
1247
+ "rstrip": false,
1248
+ "single_word": false,
1249
+ "special": true
1250
+ },
1251
+ "128156": {
1252
+ "content": "<|reserved_special_token_148|>",
1253
+ "lstrip": false,
1254
+ "normalized": false,
1255
+ "rstrip": false,
1256
+ "single_word": false,
1257
+ "special": true
1258
+ },
1259
+ "128157": {
1260
+ "content": "<|reserved_special_token_149|>",
1261
+ "lstrip": false,
1262
+ "normalized": false,
1263
+ "rstrip": false,
1264
+ "single_word": false,
1265
+ "special": true
1266
+ },
1267
+ "128158": {
1268
+ "content": "<|reserved_special_token_150|>",
1269
+ "lstrip": false,
1270
+ "normalized": false,
1271
+ "rstrip": false,
1272
+ "single_word": false,
1273
+ "special": true
1274
+ },
1275
+ "128159": {
1276
+ "content": "<|reserved_special_token_151|>",
1277
+ "lstrip": false,
1278
+ "normalized": false,
1279
+ "rstrip": false,
1280
+ "single_word": false,
1281
+ "special": true
1282
+ },
1283
+ "128160": {
1284
+ "content": "<|reserved_special_token_152|>",
1285
+ "lstrip": false,
1286
+ "normalized": false,
1287
+ "rstrip": false,
1288
+ "single_word": false,
1289
+ "special": true
1290
+ },
1291
+ "128161": {
1292
+ "content": "<|reserved_special_token_153|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false,
1297
+ "special": true
1298
+ },
1299
+ "128162": {
1300
+ "content": "<|reserved_special_token_154|>",
1301
+ "lstrip": false,
1302
+ "normalized": false,
1303
+ "rstrip": false,
1304
+ "single_word": false,
1305
+ "special": true
1306
+ },
1307
+ "128163": {
1308
+ "content": "<|reserved_special_token_155|>",
1309
+ "lstrip": false,
1310
+ "normalized": false,
1311
+ "rstrip": false,
1312
+ "single_word": false,
1313
+ "special": true
1314
+ },
1315
+ "128164": {
1316
+ "content": "<|reserved_special_token_156|>",
1317
+ "lstrip": false,
1318
+ "normalized": false,
1319
+ "rstrip": false,
1320
+ "single_word": false,
1321
+ "special": true
1322
+ },
1323
+ "128165": {
1324
+ "content": "<|reserved_special_token_157|>",
1325
+ "lstrip": false,
1326
+ "normalized": false,
1327
+ "rstrip": false,
1328
+ "single_word": false,
1329
+ "special": true
1330
+ },
1331
+ "128166": {
1332
+ "content": "<|reserved_special_token_158|>",
1333
+ "lstrip": false,
1334
+ "normalized": false,
1335
+ "rstrip": false,
1336
+ "single_word": false,
1337
+ "special": true
1338
+ },
1339
+ "128167": {
1340
+ "content": "<|reserved_special_token_159|>",
1341
+ "lstrip": false,
1342
+ "normalized": false,
1343
+ "rstrip": false,
1344
+ "single_word": false,
1345
+ "special": true
1346
+ },
1347
+ "128168": {
1348
+ "content": "<|reserved_special_token_160|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false,
1353
+ "special": true
1354
+ },
1355
+ "128169": {
1356
+ "content": "<|reserved_special_token_161|>",
1357
+ "lstrip": false,
1358
+ "normalized": false,
1359
+ "rstrip": false,
1360
+ "single_word": false,
1361
+ "special": true
1362
+ },
1363
+ "128170": {
1364
+ "content": "<|reserved_special_token_162|>",
1365
+ "lstrip": false,
1366
+ "normalized": false,
1367
+ "rstrip": false,
1368
+ "single_word": false,
1369
+ "special": true
1370
+ },
1371
+ "128171": {
1372
+ "content": "<|reserved_special_token_163|>",
1373
+ "lstrip": false,
1374
+ "normalized": false,
1375
+ "rstrip": false,
1376
+ "single_word": false,
1377
+ "special": true
1378
+ },
1379
+ "128172": {
1380
+ "content": "<|reserved_special_token_164|>",
1381
+ "lstrip": false,
1382
+ "normalized": false,
1383
+ "rstrip": false,
1384
+ "single_word": false,
1385
+ "special": true
1386
+ },
1387
+ "128173": {
1388
+ "content": "<|reserved_special_token_165|>",
1389
+ "lstrip": false,
1390
+ "normalized": false,
1391
+ "rstrip": false,
1392
+ "single_word": false,
1393
+ "special": true
1394
+ },
1395
+ "128174": {
1396
+ "content": "<|reserved_special_token_166|>",
1397
+ "lstrip": false,
1398
+ "normalized": false,
1399
+ "rstrip": false,
1400
+ "single_word": false,
1401
+ "special": true
1402
+ },
1403
+ "128175": {
1404
+ "content": "<|reserved_special_token_167|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false,
1409
+ "special": true
1410
+ },
1411
+ "128176": {
1412
+ "content": "<|reserved_special_token_168|>",
1413
+ "lstrip": false,
1414
+ "normalized": false,
1415
+ "rstrip": false,
1416
+ "single_word": false,
1417
+ "special": true
1418
+ },
1419
+ "128177": {
1420
+ "content": "<|reserved_special_token_169|>",
1421
+ "lstrip": false,
1422
+ "normalized": false,
1423
+ "rstrip": false,
1424
+ "single_word": false,
1425
+ "special": true
1426
+ },
1427
+ "128178": {
1428
+ "content": "<|reserved_special_token_170|>",
1429
+ "lstrip": false,
1430
+ "normalized": false,
1431
+ "rstrip": false,
1432
+ "single_word": false,
1433
+ "special": true
1434
+ },
1435
+ "128179": {
1436
+ "content": "<|reserved_special_token_171|>",
1437
+ "lstrip": false,
1438
+ "normalized": false,
1439
+ "rstrip": false,
1440
+ "single_word": false,
1441
+ "special": true
1442
+ },
1443
+ "128180": {
1444
+ "content": "<|reserved_special_token_172|>",
1445
+ "lstrip": false,
1446
+ "normalized": false,
1447
+ "rstrip": false,
1448
+ "single_word": false,
1449
+ "special": true
1450
+ },
1451
+ "128181": {
1452
+ "content": "<|reserved_special_token_173|>",
1453
+ "lstrip": false,
1454
+ "normalized": false,
1455
+ "rstrip": false,
1456
+ "single_word": false,
1457
+ "special": true
1458
+ },
1459
+ "128182": {
1460
+ "content": "<|reserved_special_token_174|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false,
1465
+ "special": true
1466
+ },
1467
+ "128183": {
1468
+ "content": "<|reserved_special_token_175|>",
1469
+ "lstrip": false,
1470
+ "normalized": false,
1471
+ "rstrip": false,
1472
+ "single_word": false,
1473
+ "special": true
1474
+ },
1475
+ "128184": {
1476
+ "content": "<|reserved_special_token_176|>",
1477
+ "lstrip": false,
1478
+ "normalized": false,
1479
+ "rstrip": false,
1480
+ "single_word": false,
1481
+ "special": true
1482
+ },
1483
+ "128185": {
1484
+ "content": "<|reserved_special_token_177|>",
1485
+ "lstrip": false,
1486
+ "normalized": false,
1487
+ "rstrip": false,
1488
+ "single_word": false,
1489
+ "special": true
1490
+ },
1491
+ "128186": {
1492
+ "content": "<|reserved_special_token_178|>",
1493
+ "lstrip": false,
1494
+ "normalized": false,
1495
+ "rstrip": false,
1496
+ "single_word": false,
1497
+ "special": true
1498
+ },
1499
+ "128187": {
1500
+ "content": "<|reserved_special_token_179|>",
1501
+ "lstrip": false,
1502
+ "normalized": false,
1503
+ "rstrip": false,
1504
+ "single_word": false,
1505
+ "special": true
1506
+ },
1507
+ "128188": {
1508
+ "content": "<|reserved_special_token_180|>",
1509
+ "lstrip": false,
1510
+ "normalized": false,
1511
+ "rstrip": false,
1512
+ "single_word": false,
1513
+ "special": true
1514
+ },
1515
+ "128189": {
1516
+ "content": "<|reserved_special_token_181|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false,
1521
+ "special": true
1522
+ },
1523
+ "128190": {
1524
+ "content": "<|reserved_special_token_182|>",
1525
+ "lstrip": false,
1526
+ "normalized": false,
1527
+ "rstrip": false,
1528
+ "single_word": false,
1529
+ "special": true
1530
+ },
1531
+ "128191": {
1532
+ "content": "<|reserved_special_token_183|>",
1533
+ "lstrip": false,
1534
+ "normalized": false,
1535
+ "rstrip": false,
1536
+ "single_word": false,
1537
+ "special": true
1538
+ },
1539
+ "128192": {
1540
+ "content": "<|reserved_special_token_184|>",
1541
+ "lstrip": false,
1542
+ "normalized": false,
1543
+ "rstrip": false,
1544
+ "single_word": false,
1545
+ "special": true
1546
+ },
1547
+ "128193": {
1548
+ "content": "<|reserved_special_token_185|>",
1549
+ "lstrip": false,
1550
+ "normalized": false,
1551
+ "rstrip": false,
1552
+ "single_word": false,
1553
+ "special": true
1554
+ },
1555
+ "128194": {
1556
+ "content": "<|reserved_special_token_186|>",
1557
+ "lstrip": false,
1558
+ "normalized": false,
1559
+ "rstrip": false,
1560
+ "single_word": false,
1561
+ "special": true
1562
+ },
1563
+ "128195": {
1564
+ "content": "<|reserved_special_token_187|>",
1565
+ "lstrip": false,
1566
+ "normalized": false,
1567
+ "rstrip": false,
1568
+ "single_word": false,
1569
+ "special": true
1570
+ },
1571
+ "128196": {
1572
+ "content": "<|reserved_special_token_188|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false,
1577
+ "special": true
1578
+ },
1579
+ "128197": {
1580
+ "content": "<|reserved_special_token_189|>",
1581
+ "lstrip": false,
1582
+ "normalized": false,
1583
+ "rstrip": false,
1584
+ "single_word": false,
1585
+ "special": true
1586
+ },
1587
+ "128198": {
1588
+ "content": "<|reserved_special_token_190|>",
1589
+ "lstrip": false,
1590
+ "normalized": false,
1591
+ "rstrip": false,
1592
+ "single_word": false,
1593
+ "special": true
1594
+ },
1595
+ "128199": {
1596
+ "content": "<|reserved_special_token_191|>",
1597
+ "lstrip": false,
1598
+ "normalized": false,
1599
+ "rstrip": false,
1600
+ "single_word": false,
1601
+ "special": true
1602
+ },
1603
+ "128200": {
1604
+ "content": "<|reserved_special_token_192|>",
1605
+ "lstrip": false,
1606
+ "normalized": false,
1607
+ "rstrip": false,
1608
+ "single_word": false,
1609
+ "special": true
1610
+ },
1611
+ "128201": {
1612
+ "content": "<|reserved_special_token_193|>",
1613
+ "lstrip": false,
1614
+ "normalized": false,
1615
+ "rstrip": false,
1616
+ "single_word": false,
1617
+ "special": true
1618
+ },
1619
+ "128202": {
1620
+ "content": "<|reserved_special_token_194|>",
1621
+ "lstrip": false,
1622
+ "normalized": false,
1623
+ "rstrip": false,
1624
+ "single_word": false,
1625
+ "special": true
1626
+ },
1627
+ "128203": {
1628
+ "content": "<|reserved_special_token_195|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false,
1633
+ "special": true
1634
+ },
1635
+ "128204": {
1636
+ "content": "<|reserved_special_token_196|>",
1637
+ "lstrip": false,
1638
+ "normalized": false,
1639
+ "rstrip": false,
1640
+ "single_word": false,
1641
+ "special": true
1642
+ },
1643
+ "128205": {
1644
+ "content": "<|reserved_special_token_197|>",
1645
+ "lstrip": false,
1646
+ "normalized": false,
1647
+ "rstrip": false,
1648
+ "single_word": false,
1649
+ "special": true
1650
+ },
1651
+ "128206": {
1652
+ "content": "<|reserved_special_token_198|>",
1653
+ "lstrip": false,
1654
+ "normalized": false,
1655
+ "rstrip": false,
1656
+ "single_word": false,
1657
+ "special": true
1658
+ },
1659
+ "128207": {
1660
+ "content": "<|reserved_special_token_199|>",
1661
+ "lstrip": false,
1662
+ "normalized": false,
1663
+ "rstrip": false,
1664
+ "single_word": false,
1665
+ "special": true
1666
+ },
1667
+ "128208": {
1668
+ "content": "<|reserved_special_token_200|>",
1669
+ "lstrip": false,
1670
+ "normalized": false,
1671
+ "rstrip": false,
1672
+ "single_word": false,
1673
+ "special": true
1674
+ },
1675
+ "128209": {
1676
+ "content": "<|reserved_special_token_201|>",
1677
+ "lstrip": false,
1678
+ "normalized": false,
1679
+ "rstrip": false,
1680
+ "single_word": false,
1681
+ "special": true
1682
+ },
1683
+ "128210": {
1684
+ "content": "<|reserved_special_token_202|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false,
1689
+ "special": true
1690
+ },
1691
+ "128211": {
1692
+ "content": "<|reserved_special_token_203|>",
1693
+ "lstrip": false,
1694
+ "normalized": false,
1695
+ "rstrip": false,
1696
+ "single_word": false,
1697
+ "special": true
1698
+ },
1699
+ "128212": {
1700
+ "content": "<|reserved_special_token_204|>",
1701
+ "lstrip": false,
1702
+ "normalized": false,
1703
+ "rstrip": false,
1704
+ "single_word": false,
1705
+ "special": true
1706
+ },
1707
+ "128213": {
1708
+ "content": "<|reserved_special_token_205|>",
1709
+ "lstrip": false,
1710
+ "normalized": false,
1711
+ "rstrip": false,
1712
+ "single_word": false,
1713
+ "special": true
1714
+ },
1715
+ "128214": {
1716
+ "content": "<|reserved_special_token_206|>",
1717
+ "lstrip": false,
1718
+ "normalized": false,
1719
+ "rstrip": false,
1720
+ "single_word": false,
1721
+ "special": true
1722
+ },
1723
+ "128215": {
1724
+ "content": "<|reserved_special_token_207|>",
1725
+ "lstrip": false,
1726
+ "normalized": false,
1727
+ "rstrip": false,
1728
+ "single_word": false,
1729
+ "special": true
1730
+ },
1731
+ "128216": {
1732
+ "content": "<|reserved_special_token_208|>",
1733
+ "lstrip": false,
1734
+ "normalized": false,
1735
+ "rstrip": false,
1736
+ "single_word": false,
1737
+ "special": true
1738
+ },
1739
+ "128217": {
1740
+ "content": "<|reserved_special_token_209|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false,
1745
+ "special": true
1746
+ },
1747
+ "128218": {
1748
+ "content": "<|reserved_special_token_210|>",
1749
+ "lstrip": false,
1750
+ "normalized": false,
1751
+ "rstrip": false,
1752
+ "single_word": false,
1753
+ "special": true
1754
+ },
1755
+ "128219": {
1756
+ "content": "<|reserved_special_token_211|>",
1757
+ "lstrip": false,
1758
+ "normalized": false,
1759
+ "rstrip": false,
1760
+ "single_word": false,
1761
+ "special": true
1762
+ },
1763
+ "128220": {
1764
+ "content": "<|reserved_special_token_212|>",
1765
+ "lstrip": false,
1766
+ "normalized": false,
1767
+ "rstrip": false,
1768
+ "single_word": false,
1769
+ "special": true
1770
+ },
1771
+ "128221": {
1772
+ "content": "<|reserved_special_token_213|>",
1773
+ "lstrip": false,
1774
+ "normalized": false,
1775
+ "rstrip": false,
1776
+ "single_word": false,
1777
+ "special": true
1778
+ },
1779
+ "128222": {
1780
+ "content": "<|reserved_special_token_214|>",
1781
+ "lstrip": false,
1782
+ "normalized": false,
1783
+ "rstrip": false,
1784
+ "single_word": false,
1785
+ "special": true
1786
+ },
1787
+ "128223": {
1788
+ "content": "<|reserved_special_token_215|>",
1789
+ "lstrip": false,
1790
+ "normalized": false,
1791
+ "rstrip": false,
1792
+ "single_word": false,
1793
+ "special": true
1794
+ },
1795
+ "128224": {
1796
+ "content": "<|reserved_special_token_216|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false,
1801
+ "special": true
1802
+ },
1803
+ "128225": {
1804
+ "content": "<|reserved_special_token_217|>",
1805
+ "lstrip": false,
1806
+ "normalized": false,
1807
+ "rstrip": false,
1808
+ "single_word": false,
1809
+ "special": true
1810
+ },
1811
+ "128226": {
1812
+ "content": "<|reserved_special_token_218|>",
1813
+ "lstrip": false,
1814
+ "normalized": false,
1815
+ "rstrip": false,
1816
+ "single_word": false,
1817
+ "special": true
1818
+ },
1819
+ "128227": {
1820
+ "content": "<|reserved_special_token_219|>",
1821
+ "lstrip": false,
1822
+ "normalized": false,
1823
+ "rstrip": false,
1824
+ "single_word": false,
1825
+ "special": true
1826
+ },
1827
+ "128228": {
1828
+ "content": "<|reserved_special_token_220|>",
1829
+ "lstrip": false,
1830
+ "normalized": false,
1831
+ "rstrip": false,
1832
+ "single_word": false,
1833
+ "special": true
1834
+ },
1835
+ "128229": {
1836
+ "content": "<|reserved_special_token_221|>",
1837
+ "lstrip": false,
1838
+ "normalized": false,
1839
+ "rstrip": false,
1840
+ "single_word": false,
1841
+ "special": true
1842
+ },
1843
+ "128230": {
1844
+ "content": "<|reserved_special_token_222|>",
1845
+ "lstrip": false,
1846
+ "normalized": false,
1847
+ "rstrip": false,
1848
+ "single_word": false,
1849
+ "special": true
1850
+ },
1851
+ "128231": {
1852
+ "content": "<|reserved_special_token_223|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false,
1857
+ "special": true
1858
+ },
1859
+ "128232": {
1860
+ "content": "<|reserved_special_token_224|>",
1861
+ "lstrip": false,
1862
+ "normalized": false,
1863
+ "rstrip": false,
1864
+ "single_word": false,
1865
+ "special": true
1866
+ },
1867
+ "128233": {
1868
+ "content": "<|reserved_special_token_225|>",
1869
+ "lstrip": false,
1870
+ "normalized": false,
1871
+ "rstrip": false,
1872
+ "single_word": false,
1873
+ "special": true
1874
+ },
1875
+ "128234": {
1876
+ "content": "<|reserved_special_token_226|>",
1877
+ "lstrip": false,
1878
+ "normalized": false,
1879
+ "rstrip": false,
1880
+ "single_word": false,
1881
+ "special": true
1882
+ },
1883
+ "128235": {
1884
+ "content": "<|reserved_special_token_227|>",
1885
+ "lstrip": false,
1886
+ "normalized": false,
1887
+ "rstrip": false,
1888
+ "single_word": false,
1889
+ "special": true
1890
+ },
1891
+ "128236": {
1892
+ "content": "<|reserved_special_token_228|>",
1893
+ "lstrip": false,
1894
+ "normalized": false,
1895
+ "rstrip": false,
1896
+ "single_word": false,
1897
+ "special": true
1898
+ },
1899
+ "128237": {
1900
+ "content": "<|reserved_special_token_229|>",
1901
+ "lstrip": false,
1902
+ "normalized": false,
1903
+ "rstrip": false,
1904
+ "single_word": false,
1905
+ "special": true
1906
+ },
1907
+ "128238": {
1908
+ "content": "<|reserved_special_token_230|>",
1909
+ "lstrip": false,
1910
+ "normalized": false,
1911
+ "rstrip": false,
1912
+ "single_word": false,
1913
+ "special": true
1914
+ },
1915
+ "128239": {
1916
+ "content": "<|reserved_special_token_231|>",
1917
+ "lstrip": false,
1918
+ "normalized": false,
1919
+ "rstrip": false,
1920
+ "single_word": false,
1921
+ "special": true
1922
+ },
1923
+ "128240": {
1924
+ "content": "<|reserved_special_token_232|>",
1925
+ "lstrip": false,
1926
+ "normalized": false,
1927
+ "rstrip": false,
1928
+ "single_word": false,
1929
+ "special": true
1930
+ },
1931
+ "128241": {
1932
+ "content": "<|reserved_special_token_233|>",
1933
+ "lstrip": false,
1934
+ "normalized": false,
1935
+ "rstrip": false,
1936
+ "single_word": false,
1937
+ "special": true
1938
+ },
1939
+ "128242": {
1940
+ "content": "<|reserved_special_token_234|>",
1941
+ "lstrip": false,
1942
+ "normalized": false,
1943
+ "rstrip": false,
1944
+ "single_word": false,
1945
+ "special": true
1946
+ },
1947
+ "128243": {
1948
+ "content": "<|reserved_special_token_235|>",
1949
+ "lstrip": false,
1950
+ "normalized": false,
1951
+ "rstrip": false,
1952
+ "single_word": false,
1953
+ "special": true
1954
+ },
1955
+ "128244": {
1956
+ "content": "<|reserved_special_token_236|>",
1957
+ "lstrip": false,
1958
+ "normalized": false,
1959
+ "rstrip": false,
1960
+ "single_word": false,
1961
+ "special": true
1962
+ },
1963
+ "128245": {
1964
+ "content": "<|reserved_special_token_237|>",
1965
+ "lstrip": false,
1966
+ "normalized": false,
1967
+ "rstrip": false,
1968
+ "single_word": false,
1969
+ "special": true
1970
+ },
1971
+ "128246": {
1972
+ "content": "<|reserved_special_token_238|>",
1973
+ "lstrip": false,
1974
+ "normalized": false,
1975
+ "rstrip": false,
1976
+ "single_word": false,
1977
+ "special": true
1978
+ },
1979
+ "128247": {
1980
+ "content": "<|reserved_special_token_239|>",
1981
+ "lstrip": false,
1982
+ "normalized": false,
1983
+ "rstrip": false,
1984
+ "single_word": false,
1985
+ "special": true
1986
+ },
1987
+ "128248": {
1988
+ "content": "<|reserved_special_token_240|>",
1989
+ "lstrip": false,
1990
+ "normalized": false,
1991
+ "rstrip": false,
1992
+ "single_word": false,
1993
+ "special": true
1994
+ },
1995
+ "128249": {
1996
+ "content": "<|reserved_special_token_241|>",
1997
+ "lstrip": false,
1998
+ "normalized": false,
1999
+ "rstrip": false,
2000
+ "single_word": false,
2001
+ "special": true
2002
+ },
2003
+ "128250": {
2004
+ "content": "<|reserved_special_token_242|>",
2005
+ "lstrip": false,
2006
+ "normalized": false,
2007
+ "rstrip": false,
2008
+ "single_word": false,
2009
+ "special": true
2010
+ },
2011
+ "128251": {
2012
+ "content": "<|reserved_special_token_243|>",
2013
+ "lstrip": false,
2014
+ "normalized": false,
2015
+ "rstrip": false,
2016
+ "single_word": false,
2017
+ "special": true
2018
+ },
2019
+ "128252": {
2020
+ "content": "<|reserved_special_token_244|>",
2021
+ "lstrip": false,
2022
+ "normalized": false,
2023
+ "rstrip": false,
2024
+ "single_word": false,
2025
+ "special": true
2026
+ },
2027
+ "128253": {
2028
+ "content": "<|reserved_special_token_245|>",
2029
+ "lstrip": false,
2030
+ "normalized": false,
2031
+ "rstrip": false,
2032
+ "single_word": false,
2033
+ "special": true
2034
+ },
2035
+ "128254": {
2036
+ "content": "<|reserved_special_token_246|>",
2037
+ "lstrip": false,
2038
+ "normalized": false,
2039
+ "rstrip": false,
2040
+ "single_word": false,
2041
+ "special": true
2042
+ },
2043
+ "128255": {
2044
+ "content": "<|reserved_special_token_247|>",
2045
+ "lstrip": false,
2046
+ "normalized": false,
2047
+ "rstrip": false,
2048
+ "single_word": false,
2049
+ "special": true
2050
+ }
2051
+ },
2052
+ "additional_special_tokens": [
2053
+ "<|eot_id|>",
2054
+ "<|eom_id|>"
2055
+ ],
2056
+ "bos_token": "<|begin_of_text|>",
2057
+ "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n {%- set system_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n{%- else %}\n {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n {#- Extract the first user message so we can plug it in here #}\n {%- if messages | length != 0 %}\n {%- set first_user_message = messages[0]['content']|trim %}\n {%- set messages = messages[1:] %}\n {%- else %}\n {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n {{- \"Do not use variables.\\n\\n\" }}\n {%- for t in tools %}\n {{- t | tojson(indent=4) }}\n {{- \"\\n\\n\" }}\n {%- endfor %}\n {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n {%- elif 'tool_calls' in message %}\n {%- if not message.tool_calls|length == 1 %}\n {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n {%- endif %}\n {%- set tool_call = message.tool_calls[0].function %}\n {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n {%- for arg_name, arg_val in tool_call.arguments | items %}\n {{- arg_name + '=\"' + arg_val + '\"' }}\n {%- if not loop.last %}\n {{- \", \" }}\n {%- endif %}\n {%- endfor %}\n {{- \")\" }}\n {%- else %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n {{- '\"parameters\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- \"}\" }}\n {%- endif %}\n {%- if builtin_tools is defined %}\n {#- This means we're in ipython mode #}\n {{- \"<|eom_id|>\" }}\n {%- else %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n {%- if message.content is mapping or message.content is iterable %}\n {{- message.content | tojson }}\n {%- else %}\n {{- message.content }}\n {%- endif %}\n {{- \"<|eot_id|>\" }}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
2058
+ "clean_up_tokenization_spaces": true,
2059
+ "eos_token": "<|eot_id|>",
2060
+ "extra_special_tokens": {},
2061
+ "model_input_names": [
2062
+ "input_ids",
2063
+ "attention_mask"
2064
+ ],
2065
+ "model_max_length": 131072,
2066
+ "pad_token": "<|end_of_text|>",
2067
+ "padding_side": "left",
2068
+ "split_special_tokens": false,
2069
+ "tokenizer_class": "PreTrainedTokenizerFast"
2070
+ }
150/trainer_state.json ADDED
@@ -0,0 +1,2112 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.4963733837906024,
5
+ "eval_steps": 500,
6
+ "global_step": 297,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.005045726900031536,
13
+ "grad_norm": 0.16816571847556824,
14
+ "learning_rate": 2.9999839160139495e-06,
15
+ "loss": 0.7782,
16
+ "step": 1
17
+ },
18
+ {
19
+ "epoch": 0.010091453800063072,
20
+ "grad_norm": 0.1469143977253523,
21
+ "learning_rate": 2.9999356645057024e-06,
22
+ "loss": 0.6817,
23
+ "step": 2
24
+ },
25
+ {
26
+ "epoch": 0.015137180700094607,
27
+ "grad_norm": 0.07996774677933757,
28
+ "learning_rate": 2.9998552468249567e-06,
29
+ "loss": 0.6735,
30
+ "step": 3
31
+ },
32
+ {
33
+ "epoch": 0.020182907600126143,
34
+ "grad_norm": 0.0800127664777818,
35
+ "learning_rate": 2.999742665221167e-06,
36
+ "loss": 0.6569,
37
+ "step": 4
38
+ },
39
+ {
40
+ "epoch": 0.02522863450015768,
41
+ "grad_norm": 0.08070188267575489,
42
+ "learning_rate": 2.999597922843484e-06,
43
+ "loss": 0.6283,
44
+ "step": 5
45
+ },
46
+ {
47
+ "epoch": 0.030274361400189215,
48
+ "grad_norm": 0.06839180655145351,
49
+ "learning_rate": 2.999421023740663e-06,
50
+ "loss": 0.6446,
51
+ "step": 6
52
+ },
53
+ {
54
+ "epoch": 0.03532008830022075,
55
+ "grad_norm": 0.05534188923028301,
56
+ "learning_rate": 2.9992119728609516e-06,
57
+ "loss": 0.6371,
58
+ "step": 7
59
+ },
60
+ {
61
+ "epoch": 0.040365815200252286,
62
+ "grad_norm": 0.07094943987370793,
63
+ "learning_rate": 2.9989707760519526e-06,
64
+ "loss": 0.6111,
65
+ "step": 8
66
+ },
67
+ {
68
+ "epoch": 0.04541154210028382,
69
+ "grad_norm": 0.06436005389698786,
70
+ "learning_rate": 2.9986974400604593e-06,
71
+ "loss": 0.588,
72
+ "step": 9
73
+ },
74
+ {
75
+ "epoch": 0.05045726900031536,
76
+ "grad_norm": 0.05699223365274786,
77
+ "learning_rate": 2.9983919725322667e-06,
78
+ "loss": 0.6101,
79
+ "step": 10
80
+ },
81
+ {
82
+ "epoch": 0.055502995900346894,
83
+ "grad_norm": 0.058843386030182285,
84
+ "learning_rate": 2.9980543820119585e-06,
85
+ "loss": 0.6047,
86
+ "step": 11
87
+ },
88
+ {
89
+ "epoch": 0.06054872280037843,
90
+ "grad_norm": 0.047228554008764044,
91
+ "learning_rate": 2.997684677942667e-06,
92
+ "loss": 0.5937,
93
+ "step": 12
94
+ },
95
+ {
96
+ "epoch": 0.06559444970040997,
97
+ "grad_norm": 0.04830399085917525,
98
+ "learning_rate": 2.9972828706658102e-06,
99
+ "loss": 0.6448,
100
+ "step": 13
101
+ },
102
+ {
103
+ "epoch": 0.0706401766004415,
104
+ "grad_norm": 0.04469640349332499,
105
+ "learning_rate": 2.996848971420801e-06,
106
+ "loss": 0.6145,
107
+ "step": 14
108
+ },
109
+ {
110
+ "epoch": 0.07568590350047304,
111
+ "grad_norm": 0.048907003957727534,
112
+ "learning_rate": 2.996382992344734e-06,
113
+ "loss": 0.5755,
114
+ "step": 15
115
+ },
116
+ {
117
+ "epoch": 0.08073163040050457,
118
+ "grad_norm": 0.04502223888969105,
119
+ "learning_rate": 2.9958849464720457e-06,
120
+ "loss": 0.5765,
121
+ "step": 16
122
+ },
123
+ {
124
+ "epoch": 0.08577735730053611,
125
+ "grad_norm": 0.04485565875842678,
126
+ "learning_rate": 2.9953548477341497e-06,
127
+ "loss": 0.6364,
128
+ "step": 17
129
+ },
130
+ {
131
+ "epoch": 0.09082308420056764,
132
+ "grad_norm": 0.04319237430058616,
133
+ "learning_rate": 2.9947927109590477e-06,
134
+ "loss": 0.568,
135
+ "step": 18
136
+ },
137
+ {
138
+ "epoch": 0.09586881110059918,
139
+ "grad_norm": 0.042093297202993624,
140
+ "learning_rate": 2.994198551870913e-06,
141
+ "loss": 0.6184,
142
+ "step": 19
143
+ },
144
+ {
145
+ "epoch": 0.10091453800063072,
146
+ "grad_norm": 0.04087623899598573,
147
+ "learning_rate": 2.993572387089653e-06,
148
+ "loss": 0.5822,
149
+ "step": 20
150
+ },
151
+ {
152
+ "epoch": 0.10596026490066225,
153
+ "grad_norm": 0.042619877493329586,
154
+ "learning_rate": 2.992914234130442e-06,
155
+ "loss": 0.5983,
156
+ "step": 21
157
+ },
158
+ {
159
+ "epoch": 0.11100599180069379,
160
+ "grad_norm": 0.04314774114784986,
161
+ "learning_rate": 2.9922241114032345e-06,
162
+ "loss": 0.6058,
163
+ "step": 22
164
+ },
165
+ {
166
+ "epoch": 0.11605171870072532,
167
+ "grad_norm": 0.04125496902035363,
168
+ "learning_rate": 2.9915020382122458e-06,
169
+ "loss": 0.5741,
170
+ "step": 23
171
+ },
172
+ {
173
+ "epoch": 0.12109744560075686,
174
+ "grad_norm": 0.03985368427853683,
175
+ "learning_rate": 2.990748034755415e-06,
176
+ "loss": 0.6002,
177
+ "step": 24
178
+ },
179
+ {
180
+ "epoch": 0.1261431725007884,
181
+ "grad_norm": 0.04603566805698703,
182
+ "learning_rate": 2.9899621221238394e-06,
183
+ "loss": 0.5616,
184
+ "step": 25
185
+ },
186
+ {
187
+ "epoch": 0.13118889940081993,
188
+ "grad_norm": 0.033944581121186666,
189
+ "learning_rate": 2.989144322301186e-06,
190
+ "loss": 0.591,
191
+ "step": 26
192
+ },
193
+ {
194
+ "epoch": 0.13623462630085148,
195
+ "grad_norm": 0.0352127486146018,
196
+ "learning_rate": 2.988294658163073e-06,
197
+ "loss": 0.575,
198
+ "step": 27
199
+ },
200
+ {
201
+ "epoch": 0.141280353200883,
202
+ "grad_norm": 0.04026082684896548,
203
+ "learning_rate": 2.9874131534764325e-06,
204
+ "loss": 0.5783,
205
+ "step": 28
206
+ },
207
+ {
208
+ "epoch": 0.14632608010091455,
209
+ "grad_norm": 0.038584952671910096,
210
+ "learning_rate": 2.9864998328988463e-06,
211
+ "loss": 0.5814,
212
+ "step": 29
213
+ },
214
+ {
215
+ "epoch": 0.15137180700094607,
216
+ "grad_norm": 0.03294755370363045,
217
+ "learning_rate": 2.985554721977853e-06,
218
+ "loss": 0.5688,
219
+ "step": 30
220
+ },
221
+ {
222
+ "epoch": 0.15641753390097762,
223
+ "grad_norm": 0.035774614388450525,
224
+ "learning_rate": 2.984577847150239e-06,
225
+ "loss": 0.5914,
226
+ "step": 31
227
+ },
228
+ {
229
+ "epoch": 0.16146326080100915,
230
+ "grad_norm": 0.04512017281393784,
231
+ "learning_rate": 2.983569235741291e-06,
232
+ "loss": 0.557,
233
+ "step": 32
234
+ },
235
+ {
236
+ "epoch": 0.1665089877010407,
237
+ "grad_norm": 0.03447545680264101,
238
+ "learning_rate": 2.9825289159640397e-06,
239
+ "loss": 0.568,
240
+ "step": 33
241
+ },
242
+ {
243
+ "epoch": 0.17155471460107222,
244
+ "grad_norm": 0.033658505681229516,
245
+ "learning_rate": 2.9814569169184642e-06,
246
+ "loss": 0.5868,
247
+ "step": 34
248
+ },
249
+ {
250
+ "epoch": 0.17660044150110377,
251
+ "grad_norm": 0.03071546221735757,
252
+ "learning_rate": 2.980353268590683e-06,
253
+ "loss": 0.5487,
254
+ "step": 35
255
+ },
256
+ {
257
+ "epoch": 0.1816461684011353,
258
+ "grad_norm": 0.07417860742940319,
259
+ "learning_rate": 2.9792180018521128e-06,
260
+ "loss": 0.6099,
261
+ "step": 36
262
+ },
263
+ {
264
+ "epoch": 0.18669189530116684,
265
+ "grad_norm": 0.032180325133544276,
266
+ "learning_rate": 2.978051148458604e-06,
267
+ "loss": 0.5939,
268
+ "step": 37
269
+ },
270
+ {
271
+ "epoch": 0.19173762220119836,
272
+ "grad_norm": 0.031347752245340116,
273
+ "learning_rate": 2.976852741049554e-06,
274
+ "loss": 0.5764,
275
+ "step": 38
276
+ },
277
+ {
278
+ "epoch": 0.1967833491012299,
279
+ "grad_norm": 0.035873383222778825,
280
+ "learning_rate": 2.975622813146996e-06,
281
+ "loss": 0.57,
282
+ "step": 39
283
+ },
284
+ {
285
+ "epoch": 0.20182907600126143,
286
+ "grad_norm": 0.03130302787258777,
287
+ "learning_rate": 2.9743613991546548e-06,
288
+ "loss": 0.5503,
289
+ "step": 40
290
+ },
291
+ {
292
+ "epoch": 0.20687480290129298,
293
+ "grad_norm": 0.04111552220221803,
294
+ "learning_rate": 2.9730685343569934e-06,
295
+ "loss": 0.6028,
296
+ "step": 41
297
+ },
298
+ {
299
+ "epoch": 0.2119205298013245,
300
+ "grad_norm": 0.031561335436647305,
301
+ "learning_rate": 2.971744254918218e-06,
302
+ "loss": 0.5682,
303
+ "step": 42
304
+ },
305
+ {
306
+ "epoch": 0.21696625670135605,
307
+ "grad_norm": 0.03466870924962832,
308
+ "learning_rate": 2.9703885978812726e-06,
309
+ "loss": 0.55,
310
+ "step": 43
311
+ },
312
+ {
313
+ "epoch": 0.22201198360138757,
314
+ "grad_norm": 0.03396258277418921,
315
+ "learning_rate": 2.9690016011667974e-06,
316
+ "loss": 0.5953,
317
+ "step": 44
318
+ },
319
+ {
320
+ "epoch": 0.22705771050141912,
321
+ "grad_norm": 0.033463552224919146,
322
+ "learning_rate": 2.967583303572073e-06,
323
+ "loss": 0.6231,
324
+ "step": 45
325
+ },
326
+ {
327
+ "epoch": 0.23210343740145065,
328
+ "grad_norm": 0.03747113039368738,
329
+ "learning_rate": 2.9661337447699316e-06,
330
+ "loss": 0.5742,
331
+ "step": 46
332
+ },
333
+ {
334
+ "epoch": 0.2371491643014822,
335
+ "grad_norm": 0.04159182229285405,
336
+ "learning_rate": 2.9646529653076493e-06,
337
+ "loss": 0.5681,
338
+ "step": 47
339
+ },
340
+ {
341
+ "epoch": 0.24219489120151372,
342
+ "grad_norm": 0.032311171301265075,
343
+ "learning_rate": 2.9631410066058098e-06,
344
+ "loss": 0.5464,
345
+ "step": 48
346
+ },
347
+ {
348
+ "epoch": 0.24724061810154527,
349
+ "grad_norm": 0.035494911254562625,
350
+ "learning_rate": 2.9615979109571493e-06,
351
+ "loss": 0.5377,
352
+ "step": 49
353
+ },
354
+ {
355
+ "epoch": 0.2522863450015768,
356
+ "grad_norm": 0.032401750473671755,
357
+ "learning_rate": 2.9600237215253696e-06,
358
+ "loss": 0.6043,
359
+ "step": 50
360
+ },
361
+ {
362
+ "epoch": 0.25733207190160834,
363
+ "grad_norm": 0.03477400444401883,
364
+ "learning_rate": 2.9584184823439337e-06,
365
+ "loss": 0.6078,
366
+ "step": 51
367
+ },
368
+ {
369
+ "epoch": 0.26237779880163986,
370
+ "grad_norm": 0.03586539534553979,
371
+ "learning_rate": 2.9567822383148315e-06,
372
+ "loss": 0.5857,
373
+ "step": 52
374
+ },
375
+ {
376
+ "epoch": 0.2674235257016714,
377
+ "grad_norm": 0.034776366845092124,
378
+ "learning_rate": 2.955115035207326e-06,
379
+ "loss": 0.5652,
380
+ "step": 53
381
+ },
382
+ {
383
+ "epoch": 0.27246925260170296,
384
+ "grad_norm": 0.047916672806890825,
385
+ "learning_rate": 2.953416919656672e-06,
386
+ "loss": 0.529,
387
+ "step": 54
388
+ },
389
+ {
390
+ "epoch": 0.2775149795017345,
391
+ "grad_norm": 0.035512253032401846,
392
+ "learning_rate": 2.9516879391628125e-06,
393
+ "loss": 0.6018,
394
+ "step": 55
395
+ },
396
+ {
397
+ "epoch": 0.282560706401766,
398
+ "grad_norm": 0.0669654595534551,
399
+ "learning_rate": 2.9499281420890474e-06,
400
+ "loss": 0.5832,
401
+ "step": 56
402
+ },
403
+ {
404
+ "epoch": 0.2876064333017975,
405
+ "grad_norm": 0.04009377576904152,
406
+ "learning_rate": 2.948137577660685e-06,
407
+ "loss": 0.5376,
408
+ "step": 57
409
+ },
410
+ {
411
+ "epoch": 0.2926521602018291,
412
+ "grad_norm": 0.05517678453435375,
413
+ "learning_rate": 2.946316295963661e-06,
414
+ "loss": 0.5725,
415
+ "step": 58
416
+ },
417
+ {
418
+ "epoch": 0.2976978871018606,
419
+ "grad_norm": 0.040682905696082294,
420
+ "learning_rate": 2.9444643479431393e-06,
421
+ "loss": 0.5887,
422
+ "step": 59
423
+ },
424
+ {
425
+ "epoch": 0.30274361400189215,
426
+ "grad_norm": 0.044774454426992336,
427
+ "learning_rate": 2.9425817854020873e-06,
428
+ "loss": 0.5756,
429
+ "step": 60
430
+ },
431
+ {
432
+ "epoch": 0.30778934090192367,
433
+ "grad_norm": 0.03263011910584542,
434
+ "learning_rate": 2.940668660999826e-06,
435
+ "loss": 0.5693,
436
+ "step": 61
437
+ },
438
+ {
439
+ "epoch": 0.31283506780195525,
440
+ "grad_norm": 0.032496230797448664,
441
+ "learning_rate": 2.9387250282505583e-06,
442
+ "loss": 0.586,
443
+ "step": 62
444
+ },
445
+ {
446
+ "epoch": 0.31788079470198677,
447
+ "grad_norm": 0.03310861754959189,
448
+ "learning_rate": 2.9367509415218687e-06,
449
+ "loss": 0.5548,
450
+ "step": 63
451
+ },
452
+ {
453
+ "epoch": 0.3229265216020183,
454
+ "grad_norm": 0.031816229512850104,
455
+ "learning_rate": 2.9347464560332084e-06,
456
+ "loss": 0.6,
457
+ "step": 64
458
+ },
459
+ {
460
+ "epoch": 0.3279722485020498,
461
+ "grad_norm": 0.036465675122600016,
462
+ "learning_rate": 2.932711627854344e-06,
463
+ "loss": 0.5613,
464
+ "step": 65
465
+ },
466
+ {
467
+ "epoch": 0.3330179754020814,
468
+ "grad_norm": 0.03107217546123426,
469
+ "learning_rate": 2.9306465139037947e-06,
470
+ "loss": 0.5421,
471
+ "step": 66
472
+ },
473
+ {
474
+ "epoch": 0.3380637023021129,
475
+ "grad_norm": 0.031633841290591734,
476
+ "learning_rate": 2.9285511719472367e-06,
477
+ "loss": 0.58,
478
+ "step": 67
479
+ },
480
+ {
481
+ "epoch": 0.34310942920214443,
482
+ "grad_norm": 0.030853855883844275,
483
+ "learning_rate": 2.9264256605958885e-06,
484
+ "loss": 0.5496,
485
+ "step": 68
486
+ },
487
+ {
488
+ "epoch": 0.34815515610217596,
489
+ "grad_norm": 0.036265638918391636,
490
+ "learning_rate": 2.924270039304873e-06,
491
+ "loss": 0.5939,
492
+ "step": 69
493
+ },
494
+ {
495
+ "epoch": 0.35320088300220753,
496
+ "grad_norm": 0.03703293289195566,
497
+ "learning_rate": 2.9220843683715497e-06,
498
+ "loss": 0.5311,
499
+ "step": 70
500
+ },
501
+ {
502
+ "epoch": 0.35824660990223905,
503
+ "grad_norm": 0.07682301940151573,
504
+ "learning_rate": 2.9198687089338345e-06,
505
+ "loss": 0.5655,
506
+ "step": 71
507
+ },
508
+ {
509
+ "epoch": 0.3632923368022706,
510
+ "grad_norm": 0.03240731857642153,
511
+ "learning_rate": 2.9176231229684835e-06,
512
+ "loss": 0.5436,
513
+ "step": 72
514
+ },
515
+ {
516
+ "epoch": 0.3683380637023021,
517
+ "grad_norm": 0.03550209155305971,
518
+ "learning_rate": 2.9153476732893646e-06,
519
+ "loss": 0.5529,
520
+ "step": 73
521
+ },
522
+ {
523
+ "epoch": 0.3733837906023337,
524
+ "grad_norm": 0.03572110732287988,
525
+ "learning_rate": 2.913042423545696e-06,
526
+ "loss": 0.5601,
527
+ "step": 74
528
+ },
529
+ {
530
+ "epoch": 0.3784295175023652,
531
+ "grad_norm": 0.030318267187340705,
532
+ "learning_rate": 2.910707438220269e-06,
533
+ "loss": 0.5827,
534
+ "step": 75
535
+ },
536
+ {
537
+ "epoch": 0.3834752444023967,
538
+ "grad_norm": 0.030779462298936085,
539
+ "learning_rate": 2.9083427826276414e-06,
540
+ "loss": 0.5366,
541
+ "step": 76
542
+ },
543
+ {
544
+ "epoch": 0.38852097130242824,
545
+ "grad_norm": 0.033078267956613755,
546
+ "learning_rate": 2.905948522912315e-06,
547
+ "loss": 0.5769,
548
+ "step": 77
549
+ },
550
+ {
551
+ "epoch": 0.3935666982024598,
552
+ "grad_norm": 0.032022182515529865,
553
+ "learning_rate": 2.90352472604688e-06,
554
+ "loss": 0.6059,
555
+ "step": 78
556
+ },
557
+ {
558
+ "epoch": 0.39861242510249134,
559
+ "grad_norm": 0.032572741826790486,
560
+ "learning_rate": 2.901071459830145e-06,
561
+ "loss": 0.5325,
562
+ "step": 79
563
+ },
564
+ {
565
+ "epoch": 0.40365815200252286,
566
+ "grad_norm": 0.03322477222052267,
567
+ "learning_rate": 2.89858879288524e-06,
568
+ "loss": 0.6102,
569
+ "step": 80
570
+ },
571
+ {
572
+ "epoch": 0.4087038789025544,
573
+ "grad_norm": 0.03290381540817977,
574
+ "learning_rate": 2.896076794657696e-06,
575
+ "loss": 0.5297,
576
+ "step": 81
577
+ },
578
+ {
579
+ "epoch": 0.41374960580258596,
580
+ "grad_norm": 0.02986308712893659,
581
+ "learning_rate": 2.893535535413504e-06,
582
+ "loss": 0.6016,
583
+ "step": 82
584
+ },
585
+ {
586
+ "epoch": 0.4187953327026175,
587
+ "grad_norm": 0.03708195442407903,
588
+ "learning_rate": 2.8909650862371465e-06,
589
+ "loss": 0.5644,
590
+ "step": 83
591
+ },
592
+ {
593
+ "epoch": 0.423841059602649,
594
+ "grad_norm": 0.05585756602200335,
595
+ "learning_rate": 2.888365519029615e-06,
596
+ "loss": 0.5645,
597
+ "step": 84
598
+ },
599
+ {
600
+ "epoch": 0.42888678650268053,
601
+ "grad_norm": 0.03232081336561299,
602
+ "learning_rate": 2.8857369065063893e-06,
603
+ "loss": 0.5492,
604
+ "step": 85
605
+ },
606
+ {
607
+ "epoch": 0.4339325134027121,
608
+ "grad_norm": 0.03807439954613977,
609
+ "learning_rate": 2.883079322195415e-06,
610
+ "loss": 0.5694,
611
+ "step": 86
612
+ },
613
+ {
614
+ "epoch": 0.4389782403027436,
615
+ "grad_norm": 0.03718669059491054,
616
+ "learning_rate": 2.880392840435036e-06,
617
+ "loss": 0.5603,
618
+ "step": 87
619
+ },
620
+ {
621
+ "epoch": 0.44402396720277515,
622
+ "grad_norm": 0.02993361885707706,
623
+ "learning_rate": 2.8776775363719244e-06,
624
+ "loss": 0.5193,
625
+ "step": 88
626
+ },
627
+ {
628
+ "epoch": 0.44906969410280667,
629
+ "grad_norm": 0.03471859873605538,
630
+ "learning_rate": 2.8749334859589696e-06,
631
+ "loss": 0.5195,
632
+ "step": 89
633
+ },
634
+ {
635
+ "epoch": 0.45411542100283825,
636
+ "grad_norm": 0.03468783264087511,
637
+ "learning_rate": 2.872160765953162e-06,
638
+ "loss": 0.5685,
639
+ "step": 90
640
+ },
641
+ {
642
+ "epoch": 0.45916114790286977,
643
+ "grad_norm": 0.06028818099354049,
644
+ "learning_rate": 2.86935945391344e-06,
645
+ "loss": 0.5875,
646
+ "step": 91
647
+ },
648
+ {
649
+ "epoch": 0.4642068748029013,
650
+ "grad_norm": 0.03189592063110031,
651
+ "learning_rate": 2.8665296281985232e-06,
652
+ "loss": 0.5627,
653
+ "step": 92
654
+ },
655
+ {
656
+ "epoch": 0.4692526017029328,
657
+ "grad_norm": 0.032489964455779306,
658
+ "learning_rate": 2.8636713679647195e-06,
659
+ "loss": 0.5398,
660
+ "step": 93
661
+ },
662
+ {
663
+ "epoch": 0.4742983286029644,
664
+ "grad_norm": 0.03300509062363307,
665
+ "learning_rate": 2.8607847531637127e-06,
666
+ "loss": 0.5675,
667
+ "step": 94
668
+ },
669
+ {
670
+ "epoch": 0.4793440555029959,
671
+ "grad_norm": 0.034805575232998785,
672
+ "learning_rate": 2.857869864540323e-06,
673
+ "loss": 0.5526,
674
+ "step": 95
675
+ },
676
+ {
677
+ "epoch": 0.48438978240302744,
678
+ "grad_norm": 0.03304213276713402,
679
+ "learning_rate": 2.854926783630253e-06,
680
+ "loss": 0.5475,
681
+ "step": 96
682
+ },
683
+ {
684
+ "epoch": 0.48943550930305896,
685
+ "grad_norm": 0.03753659611183512,
686
+ "learning_rate": 2.851955592757801e-06,
687
+ "loss": 0.5511,
688
+ "step": 97
689
+ },
690
+ {
691
+ "epoch": 0.49448123620309054,
692
+ "grad_norm": 0.033892234979303396,
693
+ "learning_rate": 2.848956375033562e-06,
694
+ "loss": 0.5232,
695
+ "step": 98
696
+ },
697
+ {
698
+ "epoch": 0.49952696310312206,
699
+ "grad_norm": 0.037074509268233,
700
+ "learning_rate": 2.845929214352105e-06,
701
+ "loss": 0.5655,
702
+ "step": 99
703
+ },
704
+ {
705
+ "epoch": 0.5045726900031536,
706
+ "grad_norm": 0.03224402404614455,
707
+ "learning_rate": 2.8428741953896195e-06,
708
+ "loss": 0.5556,
709
+ "step": 100
710
+ },
711
+ {
712
+ "epoch": 0.5096184169031851,
713
+ "grad_norm": 0.03072821069928307,
714
+ "learning_rate": 2.839791403601555e-06,
715
+ "loss": 0.5472,
716
+ "step": 101
717
+ },
718
+ {
719
+ "epoch": 0.5146641438032167,
720
+ "grad_norm": 0.03380249813156003,
721
+ "learning_rate": 2.8366809252202235e-06,
722
+ "loss": 0.5413,
723
+ "step": 102
724
+ },
725
+ {
726
+ "epoch": 0.5197098707032481,
727
+ "grad_norm": 0.0335216929092493,
728
+ "learning_rate": 2.8335428472523927e-06,
729
+ "loss": 0.5479,
730
+ "step": 103
731
+ },
732
+ {
733
+ "epoch": 0.5247555976032797,
734
+ "grad_norm": 0.030808915999862914,
735
+ "learning_rate": 2.8303772574768482e-06,
736
+ "loss": 0.548,
737
+ "step": 104
738
+ },
739
+ {
740
+ "epoch": 0.5298013245033113,
741
+ "grad_norm": 0.02912454306651085,
742
+ "learning_rate": 2.8271842444419414e-06,
743
+ "loss": 0.548,
744
+ "step": 105
745
+ },
746
+ {
747
+ "epoch": 0.5348470514033428,
748
+ "grad_norm": 0.05012632142858796,
749
+ "learning_rate": 2.8239638974631112e-06,
750
+ "loss": 0.5152,
751
+ "step": 106
752
+ },
753
+ {
754
+ "epoch": 0.5398927783033743,
755
+ "grad_norm": 0.0344361048789296,
756
+ "learning_rate": 2.8207163066203843e-06,
757
+ "loss": 0.5698,
758
+ "step": 107
759
+ },
760
+ {
761
+ "epoch": 0.5449385052034059,
762
+ "grad_norm": 0.10550189124699653,
763
+ "learning_rate": 2.8174415627558584e-06,
764
+ "loss": 0.522,
765
+ "step": 108
766
+ },
767
+ {
768
+ "epoch": 0.5499842321034374,
769
+ "grad_norm": 0.0323910546595259,
770
+ "learning_rate": 2.8141397574711587e-06,
771
+ "loss": 0.5518,
772
+ "step": 109
773
+ },
774
+ {
775
+ "epoch": 0.555029959003469,
776
+ "grad_norm": 0.032448012717327133,
777
+ "learning_rate": 2.810810983124877e-06,
778
+ "loss": 0.5839,
779
+ "step": 110
780
+ },
781
+ {
782
+ "epoch": 0.5600756859035004,
783
+ "grad_norm": 0.03112632332891334,
784
+ "learning_rate": 2.807455332829987e-06,
785
+ "loss": 0.5635,
786
+ "step": 111
787
+ },
788
+ {
789
+ "epoch": 0.565121412803532,
790
+ "grad_norm": 0.035282498495490644,
791
+ "learning_rate": 2.8040729004512415e-06,
792
+ "loss": 0.535,
793
+ "step": 112
794
+ },
795
+ {
796
+ "epoch": 0.5701671397035636,
797
+ "grad_norm": 0.02966255382156268,
798
+ "learning_rate": 2.800663780602545e-06,
799
+ "loss": 0.5492,
800
+ "step": 113
801
+ },
802
+ {
803
+ "epoch": 0.575212866603595,
804
+ "grad_norm": 0.03707668859813438,
805
+ "learning_rate": 2.7972280686443077e-06,
806
+ "loss": 0.5663,
807
+ "step": 114
808
+ },
809
+ {
810
+ "epoch": 0.5802585935036266,
811
+ "grad_norm": 0.03659428904439035,
812
+ "learning_rate": 2.793765860680779e-06,
813
+ "loss": 0.542,
814
+ "step": 115
815
+ },
816
+ {
817
+ "epoch": 0.5853043204036582,
818
+ "grad_norm": 0.035159210590374,
819
+ "learning_rate": 2.790277253557359e-06,
820
+ "loss": 0.5738,
821
+ "step": 116
822
+ },
823
+ {
824
+ "epoch": 0.5903500473036897,
825
+ "grad_norm": 0.030990014790480254,
826
+ "learning_rate": 2.7867623448578863e-06,
827
+ "loss": 0.5892,
828
+ "step": 117
829
+ },
830
+ {
831
+ "epoch": 0.5953957742037213,
832
+ "grad_norm": 0.03399071129755366,
833
+ "learning_rate": 2.783221232901914e-06,
834
+ "loss": 0.5677,
835
+ "step": 118
836
+ },
837
+ {
838
+ "epoch": 0.6004415011037527,
839
+ "grad_norm": 0.03247591991435437,
840
+ "learning_rate": 2.7796540167419567e-06,
841
+ "loss": 0.5412,
842
+ "step": 119
843
+ },
844
+ {
845
+ "epoch": 0.6054872280037843,
846
+ "grad_norm": 0.032370031907677656,
847
+ "learning_rate": 2.7760607961607174e-06,
848
+ "loss": 0.5556,
849
+ "step": 120
850
+ },
851
+ {
852
+ "epoch": 0.6105329549038159,
853
+ "grad_norm": 0.033174635710333106,
854
+ "learning_rate": 2.7724416716683005e-06,
855
+ "loss": 0.5668,
856
+ "step": 121
857
+ },
858
+ {
859
+ "epoch": 0.6155786818038473,
860
+ "grad_norm": 0.03148435780507138,
861
+ "learning_rate": 2.7687967444993976e-06,
862
+ "loss": 0.5205,
863
+ "step": 122
864
+ },
865
+ {
866
+ "epoch": 0.6206244087038789,
867
+ "grad_norm": 0.03187378459330813,
868
+ "learning_rate": 2.7651261166104574e-06,
869
+ "loss": 0.5563,
870
+ "step": 123
871
+ },
872
+ {
873
+ "epoch": 0.6256701356039105,
874
+ "grad_norm": 0.03429711811644175,
875
+ "learning_rate": 2.7614298906768316e-06,
876
+ "loss": 0.5167,
877
+ "step": 124
878
+ },
879
+ {
880
+ "epoch": 0.630715862503942,
881
+ "grad_norm": 0.03859718827910278,
882
+ "learning_rate": 2.757708170089906e-06,
883
+ "loss": 0.559,
884
+ "step": 125
885
+ },
886
+ {
887
+ "epoch": 0.6357615894039735,
888
+ "grad_norm": 0.03623858619383074,
889
+ "learning_rate": 2.7539610589542057e-06,
890
+ "loss": 0.5795,
891
+ "step": 126
892
+ },
893
+ {
894
+ "epoch": 0.640807316304005,
895
+ "grad_norm": 0.03263585179382894,
896
+ "learning_rate": 2.750188662084484e-06,
897
+ "loss": 0.5566,
898
+ "step": 127
899
+ },
900
+ {
901
+ "epoch": 0.6458530432040366,
902
+ "grad_norm": 0.03877113662246629,
903
+ "learning_rate": 2.746391085002791e-06,
904
+ "loss": 0.6018,
905
+ "step": 128
906
+ },
907
+ {
908
+ "epoch": 0.6508987701040682,
909
+ "grad_norm": 0.03400954730094289,
910
+ "learning_rate": 2.7425684339355203e-06,
911
+ "loss": 0.5438,
912
+ "step": 129
913
+ },
914
+ {
915
+ "epoch": 0.6559444970040996,
916
+ "grad_norm": 0.03140528838198611,
917
+ "learning_rate": 2.7387208158104406e-06,
918
+ "loss": 0.5554,
919
+ "step": 130
920
+ },
921
+ {
922
+ "epoch": 0.6609902239041312,
923
+ "grad_norm": 0.037206585802644396,
924
+ "learning_rate": 2.7348483382537015e-06,
925
+ "loss": 0.5634,
926
+ "step": 131
927
+ },
928
+ {
929
+ "epoch": 0.6660359508041628,
930
+ "grad_norm": 0.03211586967766076,
931
+ "learning_rate": 2.7309511095868246e-06,
932
+ "loss": 0.5391,
933
+ "step": 132
934
+ },
935
+ {
936
+ "epoch": 0.6710816777041942,
937
+ "grad_norm": 0.03396187095971342,
938
+ "learning_rate": 2.727029238823674e-06,
939
+ "loss": 0.5406,
940
+ "step": 133
941
+ },
942
+ {
943
+ "epoch": 0.6761274046042258,
944
+ "grad_norm": 0.03502286862929664,
945
+ "learning_rate": 2.7230828356674047e-06,
946
+ "loss": 0.5753,
947
+ "step": 134
948
+ },
949
+ {
950
+ "epoch": 0.6811731315042573,
951
+ "grad_norm": 0.03214739270222773,
952
+ "learning_rate": 2.7191120105073974e-06,
953
+ "loss": 0.5245,
954
+ "step": 135
955
+ },
956
+ {
957
+ "epoch": 0.6862188584042889,
958
+ "grad_norm": 0.03387635714681519,
959
+ "learning_rate": 2.7151168744161664e-06,
960
+ "loss": 0.54,
961
+ "step": 136
962
+ },
963
+ {
964
+ "epoch": 0.6912645853043204,
965
+ "grad_norm": 0.032951263305626276,
966
+ "learning_rate": 2.7110975391462574e-06,
967
+ "loss": 0.5259,
968
+ "step": 137
969
+ },
970
+ {
971
+ "epoch": 0.6963103122043519,
972
+ "grad_norm": 0.05015537211126262,
973
+ "learning_rate": 2.707054117127118e-06,
974
+ "loss": 0.5267,
975
+ "step": 138
976
+ },
977
+ {
978
+ "epoch": 0.7013560391043835,
979
+ "grad_norm": 0.035135429069184716,
980
+ "learning_rate": 2.7029867214619533e-06,
981
+ "loss": 0.5518,
982
+ "step": 139
983
+ },
984
+ {
985
+ "epoch": 0.7064017660044151,
986
+ "grad_norm": 0.0320337788657044,
987
+ "learning_rate": 2.698895465924565e-06,
988
+ "loss": 0.5555,
989
+ "step": 140
990
+ },
991
+ {
992
+ "epoch": 0.7114474929044465,
993
+ "grad_norm": 0.03645990761972981,
994
+ "learning_rate": 2.6947804649561633e-06,
995
+ "loss": 0.572,
996
+ "step": 141
997
+ },
998
+ {
999
+ "epoch": 0.7164932198044781,
1000
+ "grad_norm": 0.03470519450277183,
1001
+ "learning_rate": 2.6906418336621724e-06,
1002
+ "loss": 0.5505,
1003
+ "step": 142
1004
+ },
1005
+ {
1006
+ "epoch": 0.7215389467045096,
1007
+ "grad_norm": 0.031235480044832488,
1008
+ "learning_rate": 2.686479687809006e-06,
1009
+ "loss": 0.5377,
1010
+ "step": 143
1011
+ },
1012
+ {
1013
+ "epoch": 0.7265846736045412,
1014
+ "grad_norm": 0.029941451042590675,
1015
+ "learning_rate": 2.6822941438208306e-06,
1016
+ "loss": 0.5381,
1017
+ "step": 144
1018
+ },
1019
+ {
1020
+ "epoch": 0.7316304005045727,
1021
+ "grad_norm": 0.035617952049989555,
1022
+ "learning_rate": 2.6780853187763096e-06,
1023
+ "loss": 0.5546,
1024
+ "step": 145
1025
+ },
1026
+ {
1027
+ "epoch": 0.7366761274046042,
1028
+ "grad_norm": 0.03343536591046196,
1029
+ "learning_rate": 2.673853330405326e-06,
1030
+ "loss": 0.5519,
1031
+ "step": 146
1032
+ },
1033
+ {
1034
+ "epoch": 0.7417218543046358,
1035
+ "grad_norm": 0.03110711029893078,
1036
+ "learning_rate": 2.6695982970856925e-06,
1037
+ "loss": 0.5744,
1038
+ "step": 147
1039
+ },
1040
+ {
1041
+ "epoch": 0.7467675812046674,
1042
+ "grad_norm": 0.030535258085941947,
1043
+ "learning_rate": 2.6653203378398375e-06,
1044
+ "loss": 0.5239,
1045
+ "step": 148
1046
+ },
1047
+ {
1048
+ "epoch": 0.7518133081046988,
1049
+ "grad_norm": 0.06889481171001853,
1050
+ "learning_rate": 2.661019572331478e-06,
1051
+ "loss": 0.5445,
1052
+ "step": 149
1053
+ },
1054
+ {
1055
+ "epoch": 0.7568590350047304,
1056
+ "grad_norm": 0.034136168134648794,
1057
+ "learning_rate": 2.6566961208622696e-06,
1058
+ "loss": 0.5403,
1059
+ "step": 150
1060
+ },
1061
+ {
1062
+ "epoch": 0.7619047619047619,
1063
+ "grad_norm": 0.03361146386829785,
1064
+ "learning_rate": 2.652350104368444e-06,
1065
+ "loss": 0.5252,
1066
+ "step": 151
1067
+ },
1068
+ {
1069
+ "epoch": 0.7669504888047934,
1070
+ "grad_norm": 0.03232558697340943,
1071
+ "learning_rate": 2.6479816444174253e-06,
1072
+ "loss": 0.5537,
1073
+ "step": 152
1074
+ },
1075
+ {
1076
+ "epoch": 0.771996215704825,
1077
+ "grad_norm": 0.031246440682898686,
1078
+ "learning_rate": 2.643590863204429e-06,
1079
+ "loss": 0.5358,
1080
+ "step": 153
1081
+ },
1082
+ {
1083
+ "epoch": 0.7770419426048565,
1084
+ "grad_norm": 0.03123193076665316,
1085
+ "learning_rate": 2.6391778835490438e-06,
1086
+ "loss": 0.5162,
1087
+ "step": 154
1088
+ },
1089
+ {
1090
+ "epoch": 0.7820876695048881,
1091
+ "grad_norm": 0.042414916882850415,
1092
+ "learning_rate": 2.6347428288917972e-06,
1093
+ "loss": 0.5522,
1094
+ "step": 155
1095
+ },
1096
+ {
1097
+ "epoch": 0.7871333964049196,
1098
+ "grad_norm": 0.03663820317771632,
1099
+ "learning_rate": 2.630285823290702e-06,
1100
+ "loss": 0.5395,
1101
+ "step": 156
1102
+ },
1103
+ {
1104
+ "epoch": 0.7921791233049511,
1105
+ "grad_norm": 0.0323447950510978,
1106
+ "learning_rate": 2.625806991417786e-06,
1107
+ "loss": 0.5471,
1108
+ "step": 157
1109
+ },
1110
+ {
1111
+ "epoch": 0.7972248502049827,
1112
+ "grad_norm": 0.03301071769705723,
1113
+ "learning_rate": 2.621306458555604e-06,
1114
+ "loss": 0.5529,
1115
+ "step": 158
1116
+ },
1117
+ {
1118
+ "epoch": 0.8022705771050141,
1119
+ "grad_norm": 0.03261309640826233,
1120
+ "learning_rate": 2.6167843505937356e-06,
1121
+ "loss": 0.5507,
1122
+ "step": 159
1123
+ },
1124
+ {
1125
+ "epoch": 0.8073163040050457,
1126
+ "grad_norm": 0.03240576468524181,
1127
+ "learning_rate": 2.6122407940252608e-06,
1128
+ "loss": 0.5468,
1129
+ "step": 160
1130
+ },
1131
+ {
1132
+ "epoch": 0.8123620309050773,
1133
+ "grad_norm": 0.03018210963467149,
1134
+ "learning_rate": 2.6076759159432237e-06,
1135
+ "loss": 0.5583,
1136
+ "step": 161
1137
+ },
1138
+ {
1139
+ "epoch": 0.8174077578051088,
1140
+ "grad_norm": 0.031036132663069035,
1141
+ "learning_rate": 2.603089844037078e-06,
1142
+ "loss": 0.5226,
1143
+ "step": 162
1144
+ },
1145
+ {
1146
+ "epoch": 0.8224534847051403,
1147
+ "grad_norm": 0.0347386534073021,
1148
+ "learning_rate": 2.5984827065891126e-06,
1149
+ "loss": 0.5529,
1150
+ "step": 163
1151
+ },
1152
+ {
1153
+ "epoch": 0.8274992116051719,
1154
+ "grad_norm": 0.044827581860260125,
1155
+ "learning_rate": 2.593854632470866e-06,
1156
+ "loss": 0.6117,
1157
+ "step": 164
1158
+ },
1159
+ {
1160
+ "epoch": 0.8325449385052034,
1161
+ "grad_norm": 0.030210519399600917,
1162
+ "learning_rate": 2.5892057511395202e-06,
1163
+ "loss": 0.5436,
1164
+ "step": 165
1165
+ },
1166
+ {
1167
+ "epoch": 0.837590665405235,
1168
+ "grad_norm": 0.031447473869825514,
1169
+ "learning_rate": 2.5845361926342794e-06,
1170
+ "loss": 0.5228,
1171
+ "step": 166
1172
+ },
1173
+ {
1174
+ "epoch": 0.8426363923052664,
1175
+ "grad_norm": 0.035332567006398724,
1176
+ "learning_rate": 2.5798460875727326e-06,
1177
+ "loss": 0.5478,
1178
+ "step": 167
1179
+ },
1180
+ {
1181
+ "epoch": 0.847682119205298,
1182
+ "grad_norm": 0.02886367248116525,
1183
+ "learning_rate": 2.575135567147201e-06,
1184
+ "loss": 0.5114,
1185
+ "step": 168
1186
+ },
1187
+ {
1188
+ "epoch": 0.8527278461053296,
1189
+ "grad_norm": 0.031532384271644245,
1190
+ "learning_rate": 2.5704047631210664e-06,
1191
+ "loss": 0.5623,
1192
+ "step": 169
1193
+ },
1194
+ {
1195
+ "epoch": 0.8577735730053611,
1196
+ "grad_norm": 0.034567108800704585,
1197
+ "learning_rate": 2.5656538078250873e-06,
1198
+ "loss": 0.5657,
1199
+ "step": 170
1200
+ },
1201
+ {
1202
+ "epoch": 0.8628192999053926,
1203
+ "grad_norm": 0.03160145253530057,
1204
+ "learning_rate": 2.560882834153696e-06,
1205
+ "loss": 0.5136,
1206
+ "step": 171
1207
+ },
1208
+ {
1209
+ "epoch": 0.8678650268054242,
1210
+ "grad_norm": 0.03135869657202659,
1211
+ "learning_rate": 2.5560919755612823e-06,
1212
+ "loss": 0.544,
1213
+ "step": 172
1214
+ },
1215
+ {
1216
+ "epoch": 0.8729107537054557,
1217
+ "grad_norm": 0.03597121576219098,
1218
+ "learning_rate": 2.5512813660584597e-06,
1219
+ "loss": 0.5152,
1220
+ "step": 173
1221
+ },
1222
+ {
1223
+ "epoch": 0.8779564806054873,
1224
+ "grad_norm": 0.030221173382051915,
1225
+ "learning_rate": 2.5464511402083166e-06,
1226
+ "loss": 0.5251,
1227
+ "step": 174
1228
+ },
1229
+ {
1230
+ "epoch": 0.8830022075055187,
1231
+ "grad_norm": 0.030000072996604673,
1232
+ "learning_rate": 2.541601433122654e-06,
1233
+ "loss": 0.5186,
1234
+ "step": 175
1235
+ },
1236
+ {
1237
+ "epoch": 0.8880479344055503,
1238
+ "grad_norm": 0.03376922343601561,
1239
+ "learning_rate": 2.536732380458204e-06,
1240
+ "loss": 0.5164,
1241
+ "step": 176
1242
+ },
1243
+ {
1244
+ "epoch": 0.8930936613055819,
1245
+ "grad_norm": 0.03156034083736404,
1246
+ "learning_rate": 2.531844118412837e-06,
1247
+ "loss": 0.5316,
1248
+ "step": 177
1249
+ },
1250
+ {
1251
+ "epoch": 0.8981393882056133,
1252
+ "grad_norm": 0.03377666641180589,
1253
+ "learning_rate": 2.5269367837217488e-06,
1254
+ "loss": 0.5054,
1255
+ "step": 178
1256
+ },
1257
+ {
1258
+ "epoch": 0.9031851151056449,
1259
+ "grad_norm": 0.030954166615192916,
1260
+ "learning_rate": 2.522010513653642e-06,
1261
+ "loss": 0.5256,
1262
+ "step": 179
1263
+ },
1264
+ {
1265
+ "epoch": 0.9082308420056765,
1266
+ "grad_norm": 0.03484714660203487,
1267
+ "learning_rate": 2.517065446006878e-06,
1268
+ "loss": 0.5225,
1269
+ "step": 180
1270
+ },
1271
+ {
1272
+ "epoch": 0.913276568905708,
1273
+ "grad_norm": 0.06223673456920668,
1274
+ "learning_rate": 2.5121017191056306e-06,
1275
+ "loss": 0.5207,
1276
+ "step": 181
1277
+ },
1278
+ {
1279
+ "epoch": 0.9183222958057395,
1280
+ "grad_norm": 0.04079770792332633,
1281
+ "learning_rate": 2.507119471796011e-06,
1282
+ "loss": 0.555,
1283
+ "step": 182
1284
+ },
1285
+ {
1286
+ "epoch": 0.923368022705771,
1287
+ "grad_norm": 0.030029925631475055,
1288
+ "learning_rate": 2.5021188434421863e-06,
1289
+ "loss": 0.5435,
1290
+ "step": 183
1291
+ },
1292
+ {
1293
+ "epoch": 0.9284137496058026,
1294
+ "grad_norm": 0.03519161994895625,
1295
+ "learning_rate": 2.4970999739224816e-06,
1296
+ "loss": 0.5817,
1297
+ "step": 184
1298
+ },
1299
+ {
1300
+ "epoch": 0.9334594765058342,
1301
+ "grad_norm": 0.03194895322649527,
1302
+ "learning_rate": 2.492063003625466e-06,
1303
+ "loss": 0.5288,
1304
+ "step": 185
1305
+ },
1306
+ {
1307
+ "epoch": 0.9385052034058656,
1308
+ "grad_norm": 0.03862824281648028,
1309
+ "learning_rate": 2.487008073446027e-06,
1310
+ "loss": 0.5428,
1311
+ "step": 186
1312
+ },
1313
+ {
1314
+ "epoch": 0.9435509303058972,
1315
+ "grad_norm": 0.040703435887500077,
1316
+ "learning_rate": 2.481935324781427e-06,
1317
+ "loss": 0.5407,
1318
+ "step": 187
1319
+ },
1320
+ {
1321
+ "epoch": 0.9485966572059288,
1322
+ "grad_norm": 0.03251789567309417,
1323
+ "learning_rate": 2.4768448995273514e-06,
1324
+ "loss": 0.5305,
1325
+ "step": 188
1326
+ },
1327
+ {
1328
+ "epoch": 0.9536423841059603,
1329
+ "grad_norm": 0.031182531135357086,
1330
+ "learning_rate": 2.4717369400739372e-06,
1331
+ "loss": 0.5436,
1332
+ "step": 189
1333
+ },
1334
+ {
1335
+ "epoch": 0.9586881110059918,
1336
+ "grad_norm": 0.033544076361382125,
1337
+ "learning_rate": 2.466611589301791e-06,
1338
+ "loss": 0.5849,
1339
+ "step": 190
1340
+ },
1341
+ {
1342
+ "epoch": 0.9637338379060233,
1343
+ "grad_norm": 0.03146239237618079,
1344
+ "learning_rate": 2.4614689905779907e-06,
1345
+ "loss": 0.5424,
1346
+ "step": 191
1347
+ },
1348
+ {
1349
+ "epoch": 0.9687795648060549,
1350
+ "grad_norm": 0.031938896005507596,
1351
+ "learning_rate": 2.4563092877520776e-06,
1352
+ "loss": 0.5541,
1353
+ "step": 192
1354
+ },
1355
+ {
1356
+ "epoch": 0.9738252917060864,
1357
+ "grad_norm": 0.031136299616893074,
1358
+ "learning_rate": 2.4511326251520325e-06,
1359
+ "loss": 0.58,
1360
+ "step": 193
1361
+ },
1362
+ {
1363
+ "epoch": 0.9788710186061179,
1364
+ "grad_norm": 0.03323472651029714,
1365
+ "learning_rate": 2.445939147580235e-06,
1366
+ "loss": 0.5073,
1367
+ "step": 194
1368
+ },
1369
+ {
1370
+ "epoch": 0.9839167455061495,
1371
+ "grad_norm": 0.03213726601057571,
1372
+ "learning_rate": 2.4407290003094177e-06,
1373
+ "loss": 0.5758,
1374
+ "step": 195
1375
+ },
1376
+ {
1377
+ "epoch": 0.9889624724061811,
1378
+ "grad_norm": 0.032768188978415214,
1379
+ "learning_rate": 2.4355023290785993e-06,
1380
+ "loss": 0.5354,
1381
+ "step": 196
1382
+ },
1383
+ {
1384
+ "epoch": 0.9940081993062125,
1385
+ "grad_norm": 0.10156434597935675,
1386
+ "learning_rate": 2.4302592800890095e-06,
1387
+ "loss": 0.5784,
1388
+ "step": 197
1389
+ },
1390
+ {
1391
+ "epoch": 0.9990539262062441,
1392
+ "grad_norm": 0.03993430739998164,
1393
+ "learning_rate": 2.425e-06,
1394
+ "loss": 0.532,
1395
+ "step": 198
1396
+ },
1397
+ {
1398
+ "epoch": 1.0018921475875118,
1399
+ "grad_norm": 0.14663213929873462,
1400
+ "learning_rate": 2.4197246359249405e-06,
1401
+ "loss": 0.7106,
1402
+ "step": 199
1403
+ },
1404
+ {
1405
+ "epoch": 1.0069378744875435,
1406
+ "grad_norm": 0.03682337094632227,
1407
+ "learning_rate": 2.4144333354271033e-06,
1408
+ "loss": 0.4702,
1409
+ "step": 200
1410
+ },
1411
+ {
1412
+ "epoch": 1.011983601387575,
1413
+ "grad_norm": 0.04044872570852846,
1414
+ "learning_rate": 2.4091262465155386e-06,
1415
+ "loss": 0.5213,
1416
+ "step": 201
1417
+ },
1418
+ {
1419
+ "epoch": 1.0170293282876064,
1420
+ "grad_norm": 0.03956345299513896,
1421
+ "learning_rate": 2.403803517640932e-06,
1422
+ "loss": 0.488,
1423
+ "step": 202
1424
+ },
1425
+ {
1426
+ "epoch": 1.022075055187638,
1427
+ "grad_norm": 0.035011481501724055,
1428
+ "learning_rate": 2.398465297691452e-06,
1429
+ "loss": 0.4754,
1430
+ "step": 203
1431
+ },
1432
+ {
1433
+ "epoch": 1.0271207820876695,
1434
+ "grad_norm": 0.033861610990122235,
1435
+ "learning_rate": 2.393111735988585e-06,
1436
+ "loss": 0.4782,
1437
+ "step": 204
1438
+ },
1439
+ {
1440
+ "epoch": 1.032166508987701,
1441
+ "grad_norm": 0.055350616536286666,
1442
+ "learning_rate": 2.387742982282961e-06,
1443
+ "loss": 0.479,
1444
+ "step": 205
1445
+ },
1446
+ {
1447
+ "epoch": 1.0372122358877325,
1448
+ "grad_norm": 0.031693846556977066,
1449
+ "learning_rate": 2.3823591867501623e-06,
1450
+ "loss": 0.4708,
1451
+ "step": 206
1452
+ },
1453
+ {
1454
+ "epoch": 1.0422579627877642,
1455
+ "grad_norm": 0.03527666796296507,
1456
+ "learning_rate": 2.376960499986522e-06,
1457
+ "loss": 0.504,
1458
+ "step": 207
1459
+ },
1460
+ {
1461
+ "epoch": 1.0473036896877956,
1462
+ "grad_norm": 0.03114715236687362,
1463
+ "learning_rate": 2.3715470730049154e-06,
1464
+ "loss": 0.4656,
1465
+ "step": 208
1466
+ },
1467
+ {
1468
+ "epoch": 1.052349416587827,
1469
+ "grad_norm": 0.03195304059581202,
1470
+ "learning_rate": 2.3661190572305315e-06,
1471
+ "loss": 0.5021,
1472
+ "step": 209
1473
+ },
1474
+ {
1475
+ "epoch": 1.0573951434878588,
1476
+ "grad_norm": 0.041909938570619656,
1477
+ "learning_rate": 2.3606766044966404e-06,
1478
+ "loss": 0.4477,
1479
+ "step": 210
1480
+ },
1481
+ {
1482
+ "epoch": 1.0624408703878903,
1483
+ "grad_norm": 0.031765017759599695,
1484
+ "learning_rate": 2.355219867040344e-06,
1485
+ "loss": 0.4852,
1486
+ "step": 211
1487
+ },
1488
+ {
1489
+ "epoch": 1.0674865972879217,
1490
+ "grad_norm": 0.03226173748335202,
1491
+ "learning_rate": 2.3497489974983195e-06,
1492
+ "loss": 0.4499,
1493
+ "step": 212
1494
+ },
1495
+ {
1496
+ "epoch": 1.0725323241879534,
1497
+ "grad_norm": 0.04089170994785027,
1498
+ "learning_rate": 2.3442641489025476e-06,
1499
+ "loss": 0.4763,
1500
+ "step": 213
1501
+ },
1502
+ {
1503
+ "epoch": 1.0775780510879849,
1504
+ "grad_norm": 0.03266826231646906,
1505
+ "learning_rate": 2.3387654746760346e-06,
1506
+ "loss": 0.5058,
1507
+ "step": 214
1508
+ },
1509
+ {
1510
+ "epoch": 1.0826237779880163,
1511
+ "grad_norm": 0.031198910926951966,
1512
+ "learning_rate": 2.333253128628519e-06,
1513
+ "loss": 0.4761,
1514
+ "step": 215
1515
+ },
1516
+ {
1517
+ "epoch": 1.087669504888048,
1518
+ "grad_norm": 0.03390455032734163,
1519
+ "learning_rate": 2.3277272649521696e-06,
1520
+ "loss": 0.5087,
1521
+ "step": 216
1522
+ },
1523
+ {
1524
+ "epoch": 1.0927152317880795,
1525
+ "grad_norm": 0.03890356772507247,
1526
+ "learning_rate": 2.3221880382172716e-06,
1527
+ "loss": 0.4581,
1528
+ "step": 217
1529
+ },
1530
+ {
1531
+ "epoch": 1.097760958688111,
1532
+ "grad_norm": 0.03659037349548446,
1533
+ "learning_rate": 2.3166356033679037e-06,
1534
+ "loss": 0.4924,
1535
+ "step": 218
1536
+ },
1537
+ {
1538
+ "epoch": 1.1028066855881424,
1539
+ "grad_norm": 0.03393150371468798,
1540
+ "learning_rate": 2.3110701157176058e-06,
1541
+ "loss": 0.467,
1542
+ "step": 219
1543
+ },
1544
+ {
1545
+ "epoch": 1.1078524124881741,
1546
+ "grad_norm": 0.03457204743267538,
1547
+ "learning_rate": 2.3054917309450305e-06,
1548
+ "loss": 0.4769,
1549
+ "step": 220
1550
+ },
1551
+ {
1552
+ "epoch": 1.1128981393882056,
1553
+ "grad_norm": 0.032520047837292926,
1554
+ "learning_rate": 2.2999006050895913e-06,
1555
+ "loss": 0.5045,
1556
+ "step": 221
1557
+ },
1558
+ {
1559
+ "epoch": 1.117943866288237,
1560
+ "grad_norm": 0.031699959269331585,
1561
+ "learning_rate": 2.2942968945470975e-06,
1562
+ "loss": 0.4459,
1563
+ "step": 222
1564
+ },
1565
+ {
1566
+ "epoch": 1.1229895931882687,
1567
+ "grad_norm": 0.03425055841117851,
1568
+ "learning_rate": 2.28868075606538e-06,
1569
+ "loss": 0.45,
1570
+ "step": 223
1571
+ },
1572
+ {
1573
+ "epoch": 1.1280353200883002,
1574
+ "grad_norm": 0.031848100692100624,
1575
+ "learning_rate": 2.2830523467399035e-06,
1576
+ "loss": 0.483,
1577
+ "step": 224
1578
+ },
1579
+ {
1580
+ "epoch": 1.1330810469883317,
1581
+ "grad_norm": 0.030558054743067897,
1582
+ "learning_rate": 2.2774118240093768e-06,
1583
+ "loss": 0.4711,
1584
+ "step": 225
1585
+ },
1586
+ {
1587
+ "epoch": 1.1381267738883634,
1588
+ "grad_norm": 0.0348970127065318,
1589
+ "learning_rate": 2.2717593456513453e-06,
1590
+ "loss": 0.4469,
1591
+ "step": 226
1592
+ },
1593
+ {
1594
+ "epoch": 1.1431725007883948,
1595
+ "grad_norm": 0.0374572663863973,
1596
+ "learning_rate": 2.26609506977778e-06,
1597
+ "loss": 0.4781,
1598
+ "step": 227
1599
+ },
1600
+ {
1601
+ "epoch": 1.1482182276884263,
1602
+ "grad_norm": 0.03510434827876549,
1603
+ "learning_rate": 2.2604191548306524e-06,
1604
+ "loss": 0.4833,
1605
+ "step": 228
1606
+ },
1607
+ {
1608
+ "epoch": 1.153263954588458,
1609
+ "grad_norm": 0.030172104427951332,
1610
+ "learning_rate": 2.2547317595775065e-06,
1611
+ "loss": 0.4599,
1612
+ "step": 229
1613
+ },
1614
+ {
1615
+ "epoch": 1.1583096814884895,
1616
+ "grad_norm": 0.046734886663062365,
1617
+ "learning_rate": 2.2490330431070117e-06,
1618
+ "loss": 0.4527,
1619
+ "step": 230
1620
+ },
1621
+ {
1622
+ "epoch": 1.163355408388521,
1623
+ "grad_norm": 0.03666142541656924,
1624
+ "learning_rate": 2.243323164824519e-06,
1625
+ "loss": 0.5086,
1626
+ "step": 231
1627
+ },
1628
+ {
1629
+ "epoch": 1.1684011352885526,
1630
+ "grad_norm": 0.03333582987080111,
1631
+ "learning_rate": 2.2376022844475983e-06,
1632
+ "loss": 0.4892,
1633
+ "step": 232
1634
+ },
1635
+ {
1636
+ "epoch": 1.173446862188584,
1637
+ "grad_norm": 0.044806971398086565,
1638
+ "learning_rate": 2.2318705620015707e-06,
1639
+ "loss": 0.5171,
1640
+ "step": 233
1641
+ },
1642
+ {
1643
+ "epoch": 1.1784925890886155,
1644
+ "grad_norm": 0.02976391238091838,
1645
+ "learning_rate": 2.226128157815035e-06,
1646
+ "loss": 0.473,
1647
+ "step": 234
1648
+ },
1649
+ {
1650
+ "epoch": 1.1835383159886472,
1651
+ "grad_norm": 0.032855191116779925,
1652
+ "learning_rate": 2.2203752325153805e-06,
1653
+ "loss": 0.4622,
1654
+ "step": 235
1655
+ },
1656
+ {
1657
+ "epoch": 1.1885840428886787,
1658
+ "grad_norm": 0.030746957757418838,
1659
+ "learning_rate": 2.214611947024294e-06,
1660
+ "loss": 0.5058,
1661
+ "step": 236
1662
+ },
1663
+ {
1664
+ "epoch": 1.1936297697887102,
1665
+ "grad_norm": 0.04025604127464795,
1666
+ "learning_rate": 2.20883846255326e-06,
1667
+ "loss": 0.4532,
1668
+ "step": 237
1669
+ },
1670
+ {
1671
+ "epoch": 1.1986754966887416,
1672
+ "grad_norm": 0.038162603936688196,
1673
+ "learning_rate": 2.2030549405990507e-06,
1674
+ "loss": 0.4807,
1675
+ "step": 238
1676
+ },
1677
+ {
1678
+ "epoch": 1.2037212235887733,
1679
+ "grad_norm": 0.032258710879740395,
1680
+ "learning_rate": 2.1972615429392072e-06,
1681
+ "loss": 0.4641,
1682
+ "step": 239
1683
+ },
1684
+ {
1685
+ "epoch": 1.2087669504888048,
1686
+ "grad_norm": 0.04981629781222614,
1687
+ "learning_rate": 2.1914584316275165e-06,
1688
+ "loss": 0.5017,
1689
+ "step": 240
1690
+ },
1691
+ {
1692
+ "epoch": 1.2138126773888362,
1693
+ "grad_norm": 0.04243199718669605,
1694
+ "learning_rate": 2.1856457689894754e-06,
1695
+ "loss": 0.4902,
1696
+ "step": 241
1697
+ },
1698
+ {
1699
+ "epoch": 1.218858404288868,
1700
+ "grad_norm": 0.0342114934326818,
1701
+ "learning_rate": 2.179823717617754e-06,
1702
+ "loss": 0.5117,
1703
+ "step": 242
1704
+ },
1705
+ {
1706
+ "epoch": 1.2239041311888994,
1707
+ "grad_norm": 0.035548749332123104,
1708
+ "learning_rate": 2.1739924403676444e-06,
1709
+ "loss": 0.4381,
1710
+ "step": 243
1711
+ },
1712
+ {
1713
+ "epoch": 1.2289498580889309,
1714
+ "grad_norm": 0.034760487487630214,
1715
+ "learning_rate": 2.168152100352506e-06,
1716
+ "loss": 0.4591,
1717
+ "step": 244
1718
+ },
1719
+ {
1720
+ "epoch": 1.2339955849889626,
1721
+ "grad_norm": 0.03546769169516817,
1722
+ "learning_rate": 2.1623028609392048e-06,
1723
+ "loss": 0.5399,
1724
+ "step": 245
1725
+ },
1726
+ {
1727
+ "epoch": 1.239041311888994,
1728
+ "grad_norm": 0.030499056297799327,
1729
+ "learning_rate": 2.1564448857435402e-06,
1730
+ "loss": 0.4359,
1731
+ "step": 246
1732
+ },
1733
+ {
1734
+ "epoch": 1.2440870387890255,
1735
+ "grad_norm": 0.0347599990737736,
1736
+ "learning_rate": 2.1505783386256712e-06,
1737
+ "loss": 0.4812,
1738
+ "step": 247
1739
+ },
1740
+ {
1741
+ "epoch": 1.249132765689057,
1742
+ "grad_norm": 0.033702971243902105,
1743
+ "learning_rate": 2.1447033836855322e-06,
1744
+ "loss": 0.4722,
1745
+ "step": 248
1746
+ },
1747
+ {
1748
+ "epoch": 1.2541784925890886,
1749
+ "grad_norm": 0.032222809178112814,
1750
+ "learning_rate": 2.1388201852582413e-06,
1751
+ "loss": 0.4685,
1752
+ "step": 249
1753
+ },
1754
+ {
1755
+ "epoch": 1.2592242194891201,
1756
+ "grad_norm": 0.03251536305035892,
1757
+ "learning_rate": 2.1329289079095053e-06,
1758
+ "loss": 0.4863,
1759
+ "step": 250
1760
+ },
1761
+ {
1762
+ "epoch": 1.2642699463891516,
1763
+ "grad_norm": 0.03032333505076748,
1764
+ "learning_rate": 2.127029716431017e-06,
1765
+ "loss": 0.4904,
1766
+ "step": 251
1767
+ },
1768
+ {
1769
+ "epoch": 1.2693156732891833,
1770
+ "grad_norm": 0.03243078647811712,
1771
+ "learning_rate": 2.1211227758358416e-06,
1772
+ "loss": 0.4489,
1773
+ "step": 252
1774
+ },
1775
+ {
1776
+ "epoch": 1.2743614001892147,
1777
+ "grad_norm": 0.029896600919276654,
1778
+ "learning_rate": 2.115208251353806e-06,
1779
+ "loss": 0.44,
1780
+ "step": 253
1781
+ },
1782
+ {
1783
+ "epoch": 1.2794071270892462,
1784
+ "grad_norm": 0.03513886472785278,
1785
+ "learning_rate": 2.109286308426875e-06,
1786
+ "loss": 0.4469,
1787
+ "step": 254
1788
+ },
1789
+ {
1790
+ "epoch": 1.2844528539892779,
1791
+ "grad_norm": 0.034551710763168,
1792
+ "learning_rate": 2.103357112704522e-06,
1793
+ "loss": 0.4679,
1794
+ "step": 255
1795
+ },
1796
+ {
1797
+ "epoch": 1.2894985808893094,
1798
+ "grad_norm": 0.03318123641296534,
1799
+ "learning_rate": 2.0974208300390965e-06,
1800
+ "loss": 0.5459,
1801
+ "step": 256
1802
+ },
1803
+ {
1804
+ "epoch": 1.2945443077893408,
1805
+ "grad_norm": 0.03692313739508695,
1806
+ "learning_rate": 2.0914776264811856e-06,
1807
+ "loss": 0.4515,
1808
+ "step": 257
1809
+ },
1810
+ {
1811
+ "epoch": 1.2995900346893725,
1812
+ "grad_norm": 0.045176468474857956,
1813
+ "learning_rate": 2.0855276682749695e-06,
1814
+ "loss": 0.5145,
1815
+ "step": 258
1816
+ },
1817
+ {
1818
+ "epoch": 1.304635761589404,
1819
+ "grad_norm": 0.031189748556156745,
1820
+ "learning_rate": 2.0795711218535688e-06,
1821
+ "loss": 0.4604,
1822
+ "step": 259
1823
+ },
1824
+ {
1825
+ "epoch": 1.3096814884894354,
1826
+ "grad_norm": 0.03325438648076318,
1827
+ "learning_rate": 2.0736081538343916e-06,
1828
+ "loss": 0.4993,
1829
+ "step": 260
1830
+ },
1831
+ {
1832
+ "epoch": 1.3147272153894671,
1833
+ "grad_norm": 0.031199262961620483,
1834
+ "learning_rate": 2.0676389310144718e-06,
1835
+ "loss": 0.4362,
1836
+ "step": 261
1837
+ },
1838
+ {
1839
+ "epoch": 1.3197729422894986,
1840
+ "grad_norm": 0.031944131266326836,
1841
+ "learning_rate": 2.0616636203658033e-06,
1842
+ "loss": 0.4564,
1843
+ "step": 262
1844
+ },
1845
+ {
1846
+ "epoch": 1.32481866918953,
1847
+ "grad_norm": 0.03473404208713477,
1848
+ "learning_rate": 2.0556823890306702e-06,
1849
+ "loss": 0.4812,
1850
+ "step": 263
1851
+ },
1852
+ {
1853
+ "epoch": 1.3298643960895618,
1854
+ "grad_norm": 0.036841604651030695,
1855
+ "learning_rate": 2.04969540431697e-06,
1856
+ "loss": 0.473,
1857
+ "step": 264
1858
+ },
1859
+ {
1860
+ "epoch": 1.3349101229895932,
1861
+ "grad_norm": 0.033301870334618816,
1862
+ "learning_rate": 2.0437028336935354e-06,
1863
+ "loss": 0.5129,
1864
+ "step": 265
1865
+ },
1866
+ {
1867
+ "epoch": 1.3399558498896247,
1868
+ "grad_norm": 0.03157054955686288,
1869
+ "learning_rate": 2.0377048447854483e-06,
1870
+ "loss": 0.4497,
1871
+ "step": 266
1872
+ },
1873
+ {
1874
+ "epoch": 1.3450015767896564,
1875
+ "grad_norm": 0.031056401843407105,
1876
+ "learning_rate": 2.0317016053693527e-06,
1877
+ "loss": 0.4971,
1878
+ "step": 267
1879
+ },
1880
+ {
1881
+ "epoch": 1.3500473036896878,
1882
+ "grad_norm": 0.031039315725744067,
1883
+ "learning_rate": 2.0256932833687594e-06,
1884
+ "loss": 0.4729,
1885
+ "step": 268
1886
+ },
1887
+ {
1888
+ "epoch": 1.3550930305897193,
1889
+ "grad_norm": 0.030343085739004155,
1890
+ "learning_rate": 2.01968004684935e-06,
1891
+ "loss": 0.4571,
1892
+ "step": 269
1893
+ },
1894
+ {
1895
+ "epoch": 1.360138757489751,
1896
+ "grad_norm": 0.03216221791171112,
1897
+ "learning_rate": 2.013662064014278e-06,
1898
+ "loss": 0.4892,
1899
+ "step": 270
1900
+ },
1901
+ {
1902
+ "epoch": 1.3651844843897825,
1903
+ "grad_norm": 0.030997748793028454,
1904
+ "learning_rate": 2.0076395031994588e-06,
1905
+ "loss": 0.4853,
1906
+ "step": 271
1907
+ },
1908
+ {
1909
+ "epoch": 1.370230211289814,
1910
+ "grad_norm": 0.03051181164140716,
1911
+ "learning_rate": 2.0016125328688645e-06,
1912
+ "loss": 0.4712,
1913
+ "step": 272
1914
+ },
1915
+ {
1916
+ "epoch": 1.3752759381898454,
1917
+ "grad_norm": 0.033819677864526616,
1918
+ "learning_rate": 1.995581321609812e-06,
1919
+ "loss": 0.4936,
1920
+ "step": 273
1921
+ },
1922
+ {
1923
+ "epoch": 1.380321665089877,
1924
+ "grad_norm": 0.03283516748621975,
1925
+ "learning_rate": 1.9895460381282443e-06,
1926
+ "loss": 0.4671,
1927
+ "step": 274
1928
+ },
1929
+ {
1930
+ "epoch": 1.3853673919899085,
1931
+ "grad_norm": 0.0360523107800218,
1932
+ "learning_rate": 1.983506851244015e-06,
1933
+ "loss": 0.4313,
1934
+ "step": 275
1935
+ },
1936
+ {
1937
+ "epoch": 1.39041311888994,
1938
+ "grad_norm": 0.033433849463724505,
1939
+ "learning_rate": 1.9774639298861625e-06,
1940
+ "loss": 0.4823,
1941
+ "step": 276
1942
+ },
1943
+ {
1944
+ "epoch": 1.3954588457899715,
1945
+ "grad_norm": 0.03465852287263857,
1946
+ "learning_rate": 1.9714174430881886e-06,
1947
+ "loss": 0.4619,
1948
+ "step": 277
1949
+ },
1950
+ {
1951
+ "epoch": 1.4005045726900032,
1952
+ "grad_norm": 0.036080701809884305,
1953
+ "learning_rate": 1.9653675599833256e-06,
1954
+ "loss": 0.4878,
1955
+ "step": 278
1956
+ },
1957
+ {
1958
+ "epoch": 1.4055502995900346,
1959
+ "grad_norm": 0.030820007521684834,
1960
+ "learning_rate": 1.95931444979981e-06,
1961
+ "loss": 0.4698,
1962
+ "step": 279
1963
+ },
1964
+ {
1965
+ "epoch": 1.410596026490066,
1966
+ "grad_norm": 0.04113205730752187,
1967
+ "learning_rate": 1.9532582818561455e-06,
1968
+ "loss": 0.4728,
1969
+ "step": 280
1970
+ },
1971
+ {
1972
+ "epoch": 1.4156417533900978,
1973
+ "grad_norm": 0.04806829892661083,
1974
+ "learning_rate": 1.9471992255563675e-06,
1975
+ "loss": 0.4906,
1976
+ "step": 281
1977
+ },
1978
+ {
1979
+ "epoch": 1.4206874802901293,
1980
+ "grad_norm": 0.03503516935353285,
1981
+ "learning_rate": 1.941137450385307e-06,
1982
+ "loss": 0.4356,
1983
+ "step": 282
1984
+ },
1985
+ {
1986
+ "epoch": 1.4257332071901607,
1987
+ "grad_norm": 0.030864677107393407,
1988
+ "learning_rate": 1.935073125903845e-06,
1989
+ "loss": 0.4418,
1990
+ "step": 283
1991
+ },
1992
+ {
1993
+ "epoch": 1.4307789340901924,
1994
+ "grad_norm": 0.031871510937479065,
1995
+ "learning_rate": 1.929006421744173e-06,
1996
+ "loss": 0.4897,
1997
+ "step": 284
1998
+ },
1999
+ {
2000
+ "epoch": 1.4358246609902239,
2001
+ "grad_norm": 0.040994048526582366,
2002
+ "learning_rate": 1.9229375076050492e-06,
2003
+ "loss": 0.4109,
2004
+ "step": 285
2005
+ },
2006
+ {
2007
+ "epoch": 1.4408703878902553,
2008
+ "grad_norm": 0.04141601982962323,
2009
+ "learning_rate": 1.9168665532470472e-06,
2010
+ "loss": 0.466,
2011
+ "step": 286
2012
+ },
2013
+ {
2014
+ "epoch": 1.445916114790287,
2015
+ "grad_norm": 0.03049794074820137,
2016
+ "learning_rate": 1.910793728487811e-06,
2017
+ "loss": 0.4316,
2018
+ "step": 287
2019
+ },
2020
+ {
2021
+ "epoch": 1.4509618416903185,
2022
+ "grad_norm": 0.031744519891624884,
2023
+ "learning_rate": 1.904719203197304e-06,
2024
+ "loss": 0.479,
2025
+ "step": 288
2026
+ },
2027
+ {
2028
+ "epoch": 1.45600756859035,
2029
+ "grad_norm": 0.029790700550052368,
2030
+ "learning_rate": 1.8986431472930554e-06,
2031
+ "loss": 0.4379,
2032
+ "step": 289
2033
+ },
2034
+ {
2035
+ "epoch": 1.4610532954903817,
2036
+ "grad_norm": 0.029483006697427174,
2037
+ "learning_rate": 1.8925657307354117e-06,
2038
+ "loss": 0.4747,
2039
+ "step": 290
2040
+ },
2041
+ {
2042
+ "epoch": 1.4660990223904131,
2043
+ "grad_norm": 0.0324936518347741,
2044
+ "learning_rate": 1.886487123522778e-06,
2045
+ "loss": 0.4777,
2046
+ "step": 291
2047
+ },
2048
+ {
2049
+ "epoch": 1.4711447492904446,
2050
+ "grad_norm": 0.033649363452982924,
2051
+ "learning_rate": 1.8804074956868647e-06,
2052
+ "loss": 0.4891,
2053
+ "step": 292
2054
+ },
2055
+ {
2056
+ "epoch": 1.4761904761904763,
2057
+ "grad_norm": 0.029439747594352722,
2058
+ "learning_rate": 1.874327017287931e-06,
2059
+ "loss": 0.4393,
2060
+ "step": 293
2061
+ },
2062
+ {
2063
+ "epoch": 1.4812362030905077,
2064
+ "grad_norm": 0.03233846484977382,
2065
+ "learning_rate": 1.8682458584100292e-06,
2066
+ "loss": 0.4841,
2067
+ "step": 294
2068
+ },
2069
+ {
2070
+ "epoch": 1.4862819299905392,
2071
+ "grad_norm": 0.03555793172558539,
2072
+ "learning_rate": 1.8621641891562458e-06,
2073
+ "loss": 0.4718,
2074
+ "step": 295
2075
+ },
2076
+ {
2077
+ "epoch": 1.491327656890571,
2078
+ "grad_norm": 0.03769744501026416,
2079
+ "learning_rate": 1.8560821796439423e-06,
2080
+ "loss": 0.457,
2081
+ "step": 296
2082
+ },
2083
+ {
2084
+ "epoch": 1.4963733837906024,
2085
+ "grad_norm": 0.031502776602075996,
2086
+ "learning_rate": 1.85e-06,
2087
+ "loss": 0.4982,
2088
+ "step": 297
2089
+ }
2090
+ ],
2091
+ "logging_steps": 1,
2092
+ "max_steps": 594,
2093
+ "num_input_tokens_seen": 0,
2094
+ "num_train_epochs": 3,
2095
+ "save_steps": 99,
2096
+ "stateful_callbacks": {
2097
+ "TrainerControl": {
2098
+ "args": {
2099
+ "should_epoch_stop": false,
2100
+ "should_evaluate": false,
2101
+ "should_log": false,
2102
+ "should_save": true,
2103
+ "should_training_stop": false
2104
+ },
2105
+ "attributes": {}
2106
+ }
2107
+ },
2108
+ "total_flos": 1231975398506496.0,
2109
+ "train_batch_size": 1,
2110
+ "trial_name": null,
2111
+ "trial_params": null
2112
+ }
150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df0968b7e60c915735f9ede99196db9a2d6628333f8558d1383b92bb4d4706f8
3
+ size 8376
150/zero_to_fp32.py ADDED
@@ -0,0 +1,674 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ #!/usr/bin/env python
2
+
3
+ # Copyright (c) Microsoft Corporation.
4
+ # SPDX-License-Identifier: Apache-2.0
5
+
6
+ # DeepSpeed Team
7
+
8
+ # This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
9
+ # copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
10
+ # the future. Once extracted, the weights don't require DeepSpeed and can be used in any
11
+ # application.
12
+ #
13
+ # example:
14
+ # python zero_to_fp32.py . output_dir/
15
+ # or
16
+ # python zero_to_fp32.py . output_dir/ --safe_serialization
17
+
18
+ import argparse
19
+ import torch
20
+ import glob
21
+ import math
22
+ import os
23
+ import re
24
+ import json
25
+ from tqdm import tqdm
26
+ from collections import OrderedDict
27
+ from dataclasses import dataclass
28
+
29
+ # while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
30
+ # DeepSpeed data structures it has to be available in the current python environment.
31
+ from deepspeed.utils import logger
32
+ from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
33
+ FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
34
+ FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
35
+
36
+
37
+ @dataclass
38
+ class zero_model_state:
39
+ buffers: dict()
40
+ param_shapes: dict()
41
+ shared_params: list
42
+ ds_version: int
43
+ frozen_param_shapes: dict()
44
+ frozen_param_fragments: dict()
45
+
46
+
47
+ debug = 0
48
+
49
+ # load to cpu
50
+ device = torch.device('cpu')
51
+
52
+
53
+ def atoi(text):
54
+ return int(text) if text.isdigit() else text
55
+
56
+
57
+ def natural_keys(text):
58
+ '''
59
+ alist.sort(key=natural_keys) sorts in human order
60
+ http://nedbatchelder.com/blog/200712/human_sorting.html
61
+ (See Toothy's implementation in the comments)
62
+ '''
63
+ return [atoi(c) for c in re.split(r'(\d+)', text)]
64
+
65
+
66
+ def get_model_state_file(checkpoint_dir, zero_stage):
67
+ if not os.path.isdir(checkpoint_dir):
68
+ raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
69
+
70
+ # there should be only one file
71
+ if zero_stage <= 2:
72
+ file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
73
+ elif zero_stage == 3:
74
+ file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
75
+
76
+ if not os.path.exists(file):
77
+ raise FileNotFoundError(f"can't find model states file at '{file}'")
78
+
79
+ return file
80
+
81
+
82
+ def get_checkpoint_files(checkpoint_dir, glob_pattern):
83
+ # XXX: need to test that this simple glob rule works for multi-node setup too
84
+ ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
85
+
86
+ if len(ckpt_files) == 0:
87
+ raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
88
+
89
+ return ckpt_files
90
+
91
+
92
+ def get_optim_files(checkpoint_dir):
93
+ return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
94
+
95
+
96
+ def get_model_state_files(checkpoint_dir):
97
+ return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
98
+
99
+
100
+ def parse_model_states(files):
101
+ zero_model_states = []
102
+ for file in files:
103
+ state_dict = torch.load(file, map_location=device)
104
+
105
+ if BUFFER_NAMES not in state_dict:
106
+ raise ValueError(f"{file} is not a model state checkpoint")
107
+ buffer_names = state_dict[BUFFER_NAMES]
108
+ if debug:
109
+ print("Found buffers:", buffer_names)
110
+
111
+ # recover just the buffers while restoring them to fp32 if they were saved in fp16
112
+ buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
113
+ param_shapes = state_dict[PARAM_SHAPES]
114
+
115
+ # collect parameters that are included in param_shapes
116
+ param_names = []
117
+ for s in param_shapes:
118
+ for name in s.keys():
119
+ param_names.append(name)
120
+
121
+ # update with frozen parameters
122
+ frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
123
+ if frozen_param_shapes is not None:
124
+ if debug:
125
+ print(f"Found frozen_param_shapes: {frozen_param_shapes}")
126
+ param_names += list(frozen_param_shapes.keys())
127
+
128
+ # handle shared params
129
+ shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
130
+
131
+ ds_version = state_dict.get(DS_VERSION, None)
132
+
133
+ frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
134
+
135
+ z_model_state = zero_model_state(buffers=buffers,
136
+ param_shapes=param_shapes,
137
+ shared_params=shared_params,
138
+ ds_version=ds_version,
139
+ frozen_param_shapes=frozen_param_shapes,
140
+ frozen_param_fragments=frozen_param_fragments)
141
+ zero_model_states.append(z_model_state)
142
+
143
+ return zero_model_states
144
+
145
+
146
+ def parse_optim_states(files, ds_checkpoint_dir):
147
+ total_files = len(files)
148
+ state_dicts = []
149
+ for f in files:
150
+ state_dict = torch.load(f, map_location=device)
151
+ # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
152
+ # and also handle the case where it was already removed by another helper script
153
+ state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
154
+ state_dicts.append(state_dict)
155
+
156
+ if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
157
+ raise ValueError(f"{files[0]} is not a zero checkpoint")
158
+ zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
159
+ world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
160
+
161
+ # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
162
+ # parameters can be different from data parallelism for non-expert parameters. So we can just
163
+ # use the max of the partition_count to get the dp world_size.
164
+
165
+ if type(world_size) is list:
166
+ world_size = max(world_size)
167
+
168
+ if world_size != total_files:
169
+ raise ValueError(
170
+ f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
171
+ "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
172
+ )
173
+
174
+ # the groups are named differently in each stage
175
+ if zero_stage <= 2:
176
+ fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
177
+ elif zero_stage == 3:
178
+ fp32_groups_key = FP32_FLAT_GROUPS
179
+ else:
180
+ raise ValueError(f"unknown zero stage {zero_stage}")
181
+
182
+ if zero_stage <= 2:
183
+ fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
184
+ elif zero_stage == 3:
185
+ # if there is more than one param group, there will be multiple flattened tensors - one
186
+ # flattened tensor per group - for simplicity merge them into a single tensor
187
+ #
188
+ # XXX: could make the script more memory efficient for when there are multiple groups - it
189
+ # will require matching the sub-lists of param_shapes for each param group flattened tensor
190
+
191
+ fp32_flat_groups = [
192
+ torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
193
+ ]
194
+
195
+ return zero_stage, world_size, fp32_flat_groups
196
+
197
+
198
+ def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
199
+ """
200
+ Returns fp32 state_dict reconstructed from ds checkpoint
201
+
202
+ Args:
203
+ - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
204
+
205
+ """
206
+ print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
207
+
208
+ optim_files = get_optim_files(ds_checkpoint_dir)
209
+ zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
210
+ print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
211
+
212
+ model_files = get_model_state_files(ds_checkpoint_dir)
213
+
214
+ zero_model_states = parse_model_states(model_files)
215
+ print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
216
+
217
+ if zero_stage <= 2:
218
+ return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
219
+ exclude_frozen_parameters)
220
+ elif zero_stage == 3:
221
+ return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
222
+ exclude_frozen_parameters)
223
+
224
+
225
+ def _zero2_merge_frozen_params(state_dict, zero_model_states):
226
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
227
+ return
228
+
229
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
230
+ frozen_param_fragments = zero_model_states[0].frozen_param_fragments
231
+
232
+ if debug:
233
+ num_elem = sum(s.numel() for s in frozen_param_shapes.values())
234
+ print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
235
+
236
+ wanted_params = len(frozen_param_shapes)
237
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
238
+ avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
239
+ print(f'Frozen params: Have {avail_numel} numels to process.')
240
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
241
+
242
+ total_params = 0
243
+ total_numel = 0
244
+ for name, shape in frozen_param_shapes.items():
245
+ total_params += 1
246
+ unpartitioned_numel = shape.numel()
247
+ total_numel += unpartitioned_numel
248
+
249
+ state_dict[name] = frozen_param_fragments[name]
250
+
251
+ if debug:
252
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
253
+
254
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
255
+
256
+
257
+ def _has_callable(obj, fn):
258
+ attr = getattr(obj, fn, None)
259
+ return callable(attr)
260
+
261
+
262
+ def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
263
+ param_shapes = zero_model_states[0].param_shapes
264
+
265
+ # Reconstruction protocol:
266
+ #
267
+ # XXX: document this
268
+
269
+ if debug:
270
+ for i in range(world_size):
271
+ for j in range(len(fp32_flat_groups[0])):
272
+ print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
273
+
274
+ # XXX: memory usage doubles here (zero2)
275
+ num_param_groups = len(fp32_flat_groups[0])
276
+ merged_single_partition_of_fp32_groups = []
277
+ for i in range(num_param_groups):
278
+ merged_partitions = [sd[i] for sd in fp32_flat_groups]
279
+ full_single_fp32_vector = torch.cat(merged_partitions, 0)
280
+ merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
281
+ avail_numel = sum(
282
+ [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
283
+
284
+ if debug:
285
+ wanted_params = sum([len(shapes) for shapes in param_shapes])
286
+ wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
287
+ # not asserting if there is a mismatch due to possible padding
288
+ print(f"Have {avail_numel} numels to process.")
289
+ print(f"Need {wanted_numel} numels in {wanted_params} params.")
290
+
291
+ # params
292
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
293
+ # out-of-core computing solution
294
+ total_numel = 0
295
+ total_params = 0
296
+ for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
297
+ offset = 0
298
+ avail_numel = full_single_fp32_vector.numel()
299
+ for name, shape in shapes.items():
300
+
301
+ unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
302
+ total_numel += unpartitioned_numel
303
+ total_params += 1
304
+
305
+ if debug:
306
+ print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
307
+ state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
308
+ offset += unpartitioned_numel
309
+
310
+ # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
311
+ # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
312
+ # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
313
+ # live optimizer object, so we are checking that the numbers are within the right range
314
+ align_to = 2 * world_size
315
+
316
+ def zero2_align(x):
317
+ return align_to * math.ceil(x / align_to)
318
+
319
+ if debug:
320
+ print(f"original offset={offset}, avail_numel={avail_numel}")
321
+
322
+ offset = zero2_align(offset)
323
+ avail_numel = zero2_align(avail_numel)
324
+
325
+ if debug:
326
+ print(f"aligned offset={offset}, avail_numel={avail_numel}")
327
+
328
+ # Sanity check
329
+ if offset != avail_numel:
330
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
331
+
332
+ print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
333
+
334
+
335
+ def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
336
+ exclude_frozen_parameters):
337
+ state_dict = OrderedDict()
338
+
339
+ # buffers
340
+ buffers = zero_model_states[0].buffers
341
+ state_dict.update(buffers)
342
+ if debug:
343
+ print(f"added {len(buffers)} buffers")
344
+
345
+ if not exclude_frozen_parameters:
346
+ _zero2_merge_frozen_params(state_dict, zero_model_states)
347
+
348
+ _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
349
+
350
+ # recover shared parameters
351
+ for pair in zero_model_states[0].shared_params:
352
+ if pair[1] in state_dict:
353
+ state_dict[pair[0]] = state_dict[pair[1]]
354
+
355
+ return state_dict
356
+
357
+
358
+ def zero3_partitioned_param_info(unpartitioned_numel, world_size):
359
+ remainder = unpartitioned_numel % world_size
360
+ padding_numel = (world_size - remainder) if remainder else 0
361
+ partitioned_numel = math.ceil(unpartitioned_numel / world_size)
362
+ return partitioned_numel, padding_numel
363
+
364
+
365
+ def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
366
+ if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
367
+ return
368
+
369
+ if debug:
370
+ for i in range(world_size):
371
+ num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
372
+ print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
373
+
374
+ frozen_param_shapes = zero_model_states[0].frozen_param_shapes
375
+ wanted_params = len(frozen_param_shapes)
376
+ wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
377
+ avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
378
+ print(f'Frozen params: Have {avail_numel} numels to process.')
379
+ print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
380
+
381
+ total_params = 0
382
+ total_numel = 0
383
+ for name, shape in zero_model_states[0].frozen_param_shapes.items():
384
+ total_params += 1
385
+ unpartitioned_numel = shape.numel()
386
+ total_numel += unpartitioned_numel
387
+
388
+ param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
389
+ state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
390
+
391
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
392
+
393
+ if debug:
394
+ print(
395
+ f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
396
+ )
397
+
398
+ print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
399
+
400
+
401
+ def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
402
+ param_shapes = zero_model_states[0].param_shapes
403
+ avail_numel = fp32_flat_groups[0].numel() * world_size
404
+ # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
405
+ # param, re-consolidating each param, while dealing with padding if any
406
+
407
+ # merge list of dicts, preserving order
408
+ param_shapes = {k: v for d in param_shapes for k, v in d.items()}
409
+
410
+ if debug:
411
+ for i in range(world_size):
412
+ print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
413
+
414
+ wanted_params = len(param_shapes)
415
+ wanted_numel = sum(shape.numel() for shape in param_shapes.values())
416
+ # not asserting if there is a mismatch due to possible padding
417
+ avail_numel = fp32_flat_groups[0].numel() * world_size
418
+ print(f"Trainable params: Have {avail_numel} numels to process.")
419
+ print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
420
+
421
+ # params
422
+ # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
423
+ # out-of-core computing solution
424
+ offset = 0
425
+ total_numel = 0
426
+ total_params = 0
427
+ for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
428
+ unpartitioned_numel = shape.numel()
429
+ total_numel += unpartitioned_numel
430
+ total_params += 1
431
+ partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
432
+
433
+ if debug:
434
+ print(
435
+ f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
436
+ )
437
+
438
+ # XXX: memory usage doubles here
439
+ state_dict[name] = torch.cat(
440
+ tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
441
+ 0).narrow(0, 0, unpartitioned_numel).view(shape)
442
+ offset += partitioned_numel
443
+
444
+ offset *= world_size
445
+
446
+ # Sanity check
447
+ if offset != avail_numel:
448
+ raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
449
+
450
+ print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
451
+
452
+
453
+ def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
454
+ exclude_frozen_parameters):
455
+ state_dict = OrderedDict()
456
+
457
+ # buffers
458
+ buffers = zero_model_states[0].buffers
459
+ state_dict.update(buffers)
460
+ if debug:
461
+ print(f"added {len(buffers)} buffers")
462
+
463
+ if not exclude_frozen_parameters:
464
+ _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
465
+
466
+ _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
467
+
468
+ # recover shared parameters
469
+ for pair in zero_model_states[0].shared_params:
470
+ if pair[1] in state_dict:
471
+ state_dict[pair[0]] = state_dict[pair[1]]
472
+
473
+ return state_dict
474
+
475
+
476
+ def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
477
+ """
478
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
479
+ ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
480
+ via a model hub.
481
+
482
+ Args:
483
+ - ``checkpoint_dir``: path to the desired checkpoint folder
484
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
485
+ - ``exclude_frozen_parameters``: exclude frozen parameters
486
+
487
+ Returns:
488
+ - pytorch ``state_dict``
489
+
490
+ Note: this approach may not work if your application doesn't have sufficient free CPU memory and
491
+ you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
492
+ the checkpoint.
493
+
494
+ A typical usage might be ::
495
+
496
+ from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
497
+ # do the training and checkpoint saving
498
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
499
+ model = model.cpu() # move to cpu
500
+ model.load_state_dict(state_dict)
501
+ # submit to model hub or save the model to share with others
502
+
503
+ In this example the ``model`` will no longer be usable in the deepspeed context of the same
504
+ application. i.e. you will need to re-initialize the deepspeed engine, since
505
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
506
+
507
+ If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
508
+
509
+ """
510
+ if tag is None:
511
+ latest_path = os.path.join(checkpoint_dir, 'latest')
512
+ if os.path.isfile(latest_path):
513
+ with open(latest_path, 'r') as fd:
514
+ tag = fd.read().strip()
515
+ else:
516
+ raise ValueError(f"Unable to find 'latest' file at {latest_path}")
517
+
518
+ ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
519
+
520
+ if not os.path.isdir(ds_checkpoint_dir):
521
+ raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
522
+
523
+ return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
524
+
525
+
526
+ def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
527
+ output_dir,
528
+ max_shard_size="5GB",
529
+ safe_serialization=False,
530
+ tag=None,
531
+ exclude_frozen_parameters=False):
532
+ """
533
+ Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
534
+ loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
535
+
536
+ Args:
537
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
538
+ - ``output_dir``: directory to the pytorch fp32 state_dict output files
539
+ - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
540
+ - ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
541
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
542
+ - ``exclude_frozen_parameters``: exclude frozen parameters
543
+ """
544
+ # Dependency pre-check
545
+ if safe_serialization:
546
+ try:
547
+ from safetensors.torch import save_file
548
+ except ImportError:
549
+ print('If you want to use `safe_serialization`, please `pip install safetensors`')
550
+ raise
551
+ if max_shard_size is not None:
552
+ try:
553
+ from huggingface_hub import split_torch_state_dict_into_shards
554
+ except ImportError:
555
+ print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
556
+ raise
557
+
558
+ # Convert zero checkpoint to state_dict
559
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
560
+
561
+ # Shard the model if it is too big.
562
+ weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
563
+ if max_shard_size is not None:
564
+ filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
565
+ state_dict_split = split_torch_state_dict_into_shards(state_dict,
566
+ filename_pattern=filename_pattern,
567
+ max_shard_size=max_shard_size)
568
+ else:
569
+ from collections import namedtuple
570
+ StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
571
+ state_dict_split = StateDictSplit(is_sharded=False,
572
+ filename_to_tensors={weights_name: list(state_dict.keys())})
573
+
574
+ # Save the model
575
+ filename_to_tensors = state_dict_split.filename_to_tensors.items()
576
+ for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
577
+ shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
578
+ output_path = os.path.join(output_dir, shard_file)
579
+ if safe_serialization:
580
+ save_file(shard, output_path, metadata={"format": "pt"})
581
+ else:
582
+ torch.save(shard, output_path)
583
+
584
+ # Save index if sharded
585
+ if state_dict_split.is_sharded:
586
+ index = {
587
+ "metadata": state_dict_split.metadata,
588
+ "weight_map": state_dict_split.tensor_to_filename,
589
+ }
590
+ save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
591
+ save_index_file = os.path.join(output_dir, save_index_file)
592
+ with open(save_index_file, "w", encoding="utf-8") as f:
593
+ content = json.dumps(index, indent=2, sort_keys=True) + "\n"
594
+ f.write(content)
595
+
596
+
597
+ def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
598
+ """
599
+ 1. Put the provided model to cpu
600
+ 2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
601
+ 3. Load it into the provided model
602
+
603
+ Args:
604
+ - ``model``: the model object to update
605
+ - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
606
+ - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
607
+
608
+ Returns:
609
+ - ``model`: modified model
610
+
611
+ Make sure you have plenty of CPU memory available before you call this function. If you don't
612
+ have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
613
+ conveniently placed for you in the checkpoint folder.
614
+
615
+ A typical usage might be ::
616
+
617
+ from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
618
+ model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
619
+ # submit to model hub or save the model to share with others
620
+
621
+ Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
622
+ of the same application. i.e. you will need to re-initialize the deepspeed engine, since
623
+ ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
624
+
625
+ """
626
+ logger.info(f"Extracting fp32 weights")
627
+ state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
628
+
629
+ logger.info(f"Overwriting model with fp32 weights")
630
+ model = model.cpu()
631
+ model.load_state_dict(state_dict, strict=False)
632
+
633
+ return model
634
+
635
+
636
+ if __name__ == "__main__":
637
+ parser = argparse.ArgumentParser()
638
+ parser.add_argument("checkpoint_dir",
639
+ type=str,
640
+ help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
641
+ parser.add_argument("output_dir",
642
+ type=str,
643
+ help="directory to the pytorch fp32 state_dict output files"
644
+ "(e.g. path/checkpoint-12-output/)")
645
+ parser.add_argument(
646
+ "--max_shard_size",
647
+ type=str,
648
+ default="5GB",
649
+ help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
650
+ "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
651
+ "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
652
+ "without CPU OOM issues.")
653
+ parser.add_argument(
654
+ "--safe_serialization",
655
+ default=False,
656
+ action='store_true',
657
+ help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
658
+ parser.add_argument("-t",
659
+ "--tag",
660
+ type=str,
661
+ default=None,
662
+ help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
663
+ parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
664
+ parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
665
+ args = parser.parse_args()
666
+
667
+ debug = args.debug
668
+
669
+ convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
670
+ args.output_dir,
671
+ max_shard_size=args.max_shard_size,
672
+ safe_serialization=args.safe_serialization,
673
+ tag=args.tag,
674
+ exclude_frozen_parameters=args.exclude_frozen_parameters)