Hugging Face's logo

bilkultheek
/
llama-2FineTuned

PEFT
TensorBoard
llama
4-bit precision
Model card Files Metrics Community
bilkultheek commited on
Commit
16fa3da
•
1 Parent(s): 0390074

Initial commit

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +32 -0
  2. adapter_config.json +21 -0
  3. adapter_model.bin +3 -0
  4. checkpoint-10/README.md +32 -0
  5. checkpoint-10/adapter_config.json +21 -0
  6. checkpoint-10/adapter_model.bin +3 -0
  7. checkpoint-10/optimizer.pt +3 -0
  8. checkpoint-10/rng_state.pth +3 -0
  9. checkpoint-10/scheduler.pt +3 -0
  10. checkpoint-10/special_tokens_map.json +24 -0
  11. checkpoint-10/tokenizer.json +0 -0
  12. checkpoint-10/tokenizer.model +3 -0
  13. checkpoint-10/tokenizer_config.json +32 -0
  14. checkpoint-10/trainer_state.json +76 -0
  15. checkpoint-10/training_args.bin +3 -0
  16. checkpoint-100/README.md +32 -0
  17. checkpoint-100/adapter_config.json +21 -0
  18. checkpoint-100/adapter_model.bin +3 -0
  19. checkpoint-100/optimizer.pt +3 -0
  20. checkpoint-100/rng_state.pth +3 -0
  21. checkpoint-100/scheduler.pt +3 -0
  22. checkpoint-100/special_tokens_map.json +24 -0
  23. checkpoint-100/tokenizer.json +0 -0
  24. checkpoint-100/tokenizer.model +3 -0
  25. checkpoint-100/tokenizer_config.json +32 -0
  26. checkpoint-100/trainer_state.json +616 -0
  27. checkpoint-100/training_args.bin +3 -0
  28. checkpoint-110/README.md +32 -0
  29. checkpoint-110/adapter_config.json +21 -0
  30. checkpoint-110/adapter_model.bin +3 -0
  31. checkpoint-110/optimizer.pt +3 -0
  32. checkpoint-110/rng_state.pth +3 -0
  33. checkpoint-110/scheduler.pt +3 -0
  34. checkpoint-110/special_tokens_map.json +24 -0
  35. checkpoint-110/tokenizer.json +0 -0
  36. checkpoint-110/tokenizer.model +3 -0
  37. checkpoint-110/tokenizer_config.json +32 -0
  38. checkpoint-110/trainer_state.json +676 -0
  39. checkpoint-110/training_args.bin +3 -0
  40. checkpoint-120/README.md +32 -0
  41. checkpoint-120/adapter_config.json +21 -0
  42. checkpoint-120/adapter_model.bin +3 -0
  43. checkpoint-120/optimizer.pt +3 -0
  44. checkpoint-120/rng_state.pth +3 -0
  45. checkpoint-120/scheduler.pt +3 -0
  46. checkpoint-120/special_tokens_map.json +24 -0
  47. checkpoint-120/tokenizer.json +0 -0
  48. checkpoint-120/tokenizer.model +3 -0
  49. checkpoint-120/tokenizer_config.json +32 -0
  50. checkpoint-120/trainer_state.json +736 -0
README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ddd1f51d53ea52493782b5890ae82655c081143f71afa40fa451c9c46907af5
3
+ size 134264202
checkpoint-10/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
checkpoint-10/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-10/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cbb4f27c39aec9f83d00c03302b114292847690cb3d604f507a1db83659f4a7
3
+ size 134264202
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27f90a1be67ec15b65b5db2191ff12be72ac806e81af5eb5bc75989c0fadb756
3
+ size 268514874
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2947a7ffa84ba75982b70f33d80e0e3415512d0cb88dcf5c92b10244c1ff928f
3
+ size 14244
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2faeb6bd0391cd9d4474312e78bfe7093dff96875879761063124470dcc35c7a
3
+ size 1064
checkpoint-10/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-10/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-10/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,76 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.05333333333333334,
5
+ "global_step": 10,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 1.1764705882352942e-05,
13
+ "loss": 1.9122,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 2.3529411764705884e-05,
19
+ "loss": 2.0707,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 3.529411764705883e-05,
25
+ "loss": 1.9703,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4.705882352941177e-05,
31
+ "loss": 2.015,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 5.882352941176471e-05,
37
+ "loss": 2.119,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 7.058823529411765e-05,
43
+ "loss": 2.0515,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 8.23529411764706e-05,
49
+ "loss": 1.7436,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 9.411764705882353e-05,
55
+ "loss": 1.9326,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 0.00010588235294117647,
61
+ "loss": 2.0819,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 0.00011764705882352942,
67
+ "loss": 1.9965,
68
+ "step": 10
69
+ }
70
+ ],
71
+ "max_steps": 561,
72
+ "num_train_epochs": 3,
73
+ "total_flos": 3333258509352960.0,
74
+ "trial_name": null,
75
+ "trial_params": null
76
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca476fdc79c35941e82478278237f98f92b013f5a509b33f355127ad4c6138c4
3
+ size 4408
checkpoint-100/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
checkpoint-100/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-100/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9141291504d87239f91084b18c66bd68daf04f03b48f723f57db46f8afe0c52
3
+ size 134264202
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef6b859cd0b6cdfd0473296f15be3f56e604ac5a032dec8263f254a6bc70cdae
3
+ size 268514874
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a91ed4b4f2cc2cebde59f7b92ff14f50e0610282d0e161293ed88422ed8fa903
3
+ size 14244
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d009ca03916fe40d05bc0e4fb43ea702d42b628abb299580906c2ed364dfb522
3
+ size 1064
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-100/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,616 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5333333333333333,
5
+ "global_step": 100,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 1.1764705882352942e-05,
13
+ "loss": 1.9122,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 2.3529411764705884e-05,
19
+ "loss": 2.0707,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 3.529411764705883e-05,
25
+ "loss": 1.9703,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4.705882352941177e-05,
31
+ "loss": 2.015,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 5.882352941176471e-05,
37
+ "loss": 2.119,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 7.058823529411765e-05,
43
+ "loss": 2.0515,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 8.23529411764706e-05,
49
+ "loss": 1.7436,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 9.411764705882353e-05,
55
+ "loss": 1.9326,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 0.00010588235294117647,
61
+ "loss": 2.0819,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 0.00011764705882352942,
67
+ "loss": 1.9965,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 0.00012941176470588237,
73
+ "loss": 2.0543,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.06,
78
+ "learning_rate": 0.0001411764705882353,
79
+ "loss": 2.0461,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 0.00015294117647058822,
85
+ "loss": 2.311,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "learning_rate": 0.0001647058823529412,
91
+ "loss": 1.8447,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 0.00017647058823529413,
97
+ "loss": 2.6263,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.09,
102
+ "learning_rate": 0.00018823529411764707,
103
+ "loss": 2.6179,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.09,
108
+ "learning_rate": 0.0002,
109
+ "loss": 2.535,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "learning_rate": 0.00019999833248118322,
115
+ "loss": 2.5924,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.1,
120
+ "learning_rate": 0.00019999332998034514,
121
+ "loss": 2.3562,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.11,
126
+ "learning_rate": 0.00019998499266432108,
127
+ "loss": 2.2352,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.11,
132
+ "learning_rate": 0.00019997332081116373,
133
+ "loss": 2.152,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.12,
138
+ "learning_rate": 0.00019995831481013374,
139
+ "loss": 2.1149,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.12,
144
+ "learning_rate": 0.00019993997516168689,
145
+ "loss": 2.1608,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.13,
150
+ "learning_rate": 0.0001999183024774573,
151
+ "loss": 2.1593,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.13,
156
+ "learning_rate": 0.00019989329748023725,
157
+ "loss": 2.2774,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.14,
162
+ "learning_rate": 0.00019986496100395275,
163
+ "loss": 2.0355,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.14,
168
+ "learning_rate": 0.00019983329399363598,
169
+ "loss": 1.9455,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "learning_rate": 0.0001997982975053936,
175
+ "loss": 2.5648,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.15,
180
+ "learning_rate": 0.0001997599727063717,
181
+ "loss": 2.3619,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.16,
186
+ "learning_rate": 0.00019971832087471676,
187
+ "loss": 2.0888,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.17,
192
+ "learning_rate": 0.000199673343399533,
193
+ "loss": 1.9363,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.17,
198
+ "learning_rate": 0.00019962504178083618,
199
+ "loss": 2.0259,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.18,
204
+ "learning_rate": 0.00019957341762950344,
205
+ "loss": 1.8482,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.18,
210
+ "learning_rate": 0.0001995184726672197,
211
+ "loss": 1.8542,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "learning_rate": 0.0001994602087264201,
217
+ "loss": 1.9435,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.19,
222
+ "learning_rate": 0.00019939862775022893,
223
+ "loss": 1.6559,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.2,
228
+ "learning_rate": 0.00019933373179239502,
229
+ "loss": 1.9478,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.2,
234
+ "learning_rate": 0.0001992655230172229,
235
+ "loss": 1.9417,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.21,
240
+ "learning_rate": 0.000199194003699501,
241
+ "loss": 1.9067,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.21,
246
+ "learning_rate": 0.00019911917622442537,
247
+ "loss": 1.6106,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.22,
252
+ "learning_rate": 0.0001990410430875205,
253
+ "loss": 1.2742,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.22,
258
+ "learning_rate": 0.00019895960689455598,
259
+ "loss": 1.3048,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.23,
264
+ "learning_rate": 0.0001988748703614594,
265
+ "loss": 1.1847,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.23,
270
+ "learning_rate": 0.00019878683631422605,
271
+ "loss": 1.1683,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.24,
276
+ "learning_rate": 0.00019869550768882455,
277
+ "loss": 1.1531,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.25,
282
+ "learning_rate": 0.00019860088753109896,
283
+ "loss": 1.1401,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.25,
288
+ "learning_rate": 0.0001985029789966671,
289
+ "loss": 1.8959,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.26,
294
+ "learning_rate": 0.00019840178535081545,
295
+ "loss": 1.897,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.26,
300
+ "learning_rate": 0.0001982973099683902,
301
+ "loss": 1.791,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.27,
306
+ "learning_rate": 0.00019818955633368464,
307
+ "loss": 1.7451,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.27,
312
+ "learning_rate": 0.00019807852804032305,
313
+ "loss": 1.8556,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.28,
318
+ "learning_rate": 0.00019796422879114084,
319
+ "loss": 1.7882,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.28,
324
+ "learning_rate": 0.0001978466623980609,
325
+ "loss": 1.8834,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.29,
330
+ "learning_rate": 0.00019772583278196678,
331
+ "loss": 1.7593,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.29,
336
+ "learning_rate": 0.00019760174397257156,
337
+ "loss": 1.8291,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.3,
342
+ "learning_rate": 0.00019747440010828383,
343
+ "loss": 1.808,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.3,
348
+ "learning_rate": 0.0001973438054360693,
349
+ "loss": 1.6324,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.31,
354
+ "learning_rate": 0.00019720996431130946,
355
+ "loss": 1.483,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.31,
360
+ "learning_rate": 0.00019707288119765623,
361
+ "loss": 1.9648,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.32,
366
+ "learning_rate": 0.000196932560666883,
367
+ "loss": 1.5742,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.33,
372
+ "learning_rate": 0.00019678900739873226,
373
+ "loss": 1.7066,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.33,
378
+ "learning_rate": 0.00019664222618075958,
379
+ "loss": 2.0719,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.34,
384
+ "learning_rate": 0.0001964922219081738,
385
+ "loss": 1.9432,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.34,
390
+ "learning_rate": 0.00019633899958367384,
391
+ "loss": 1.7979,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.35,
396
+ "learning_rate": 0.00019618256431728194,
397
+ "loss": 1.6286,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.35,
402
+ "learning_rate": 0.000196022921326173,
403
+ "loss": 1.6031,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.36,
408
+ "learning_rate": 0.00019586007593450097,
409
+ "loss": 1.5169,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.36,
414
+ "learning_rate": 0.0001956940335732209,
415
+ "loss": 1.5923,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.37,
420
+ "learning_rate": 0.000195524799779908,
421
+ "loss": 1.6123,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.37,
426
+ "learning_rate": 0.000195352380198573,
427
+ "loss": 1.7392,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.38,
432
+ "learning_rate": 0.00019517678057947384,
433
+ "loss": 1.6406,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.38,
438
+ "learning_rate": 0.00019499800677892385,
439
+ "loss": 1.5532,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.39,
444
+ "learning_rate": 0.0001948160647590966,
445
+ "loss": 1.816,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.39,
450
+ "learning_rate": 0.0001946309605878269,
451
+ "loss": 1.5759,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.4,
456
+ "learning_rate": 0.00019444270043840852,
457
+ "loss": 1.6726,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.41,
462
+ "learning_rate": 0.00019425129058938832,
463
+ "loss": 1.6134,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.41,
468
+ "learning_rate": 0.00019405673742435678,
469
+ "loss": 1.6285,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.42,
474
+ "learning_rate": 0.00019385904743173516,
475
+ "loss": 1.6023,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.42,
480
+ "learning_rate": 0.00019365822720455916,
481
+ "loss": 1.5177,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.43,
486
+ "learning_rate": 0.00019345428344025883,
487
+ "loss": 1.5413,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.43,
492
+ "learning_rate": 0.00019324722294043558,
493
+ "loss": 1.3404,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.44,
498
+ "learning_rate": 0.00019303705261063497,
499
+ "loss": 1.6409,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.44,
504
+ "learning_rate": 0.00019282377946011652,
505
+ "loss": 1.6361,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.45,
510
+ "learning_rate": 0.00019260741060162016,
511
+ "loss": 1.4902,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.45,
516
+ "learning_rate": 0.0001923879532511287,
517
+ "loss": 1.3232,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.46,
522
+ "learning_rate": 0.00019216541472762735,
523
+ "loss": 1.2438,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.46,
528
+ "learning_rate": 0.00019193980245285966,
529
+ "loss": 1.0828,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.47,
534
+ "learning_rate": 0.00019171112395107985,
535
+ "loss": 1.0696,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.47,
540
+ "learning_rate": 0.0001914793868488021,
541
+ "loss": 1.0179,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.48,
546
+ "learning_rate": 0.0001912445988745459,
547
+ "loss": 1.0012,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.49,
552
+ "learning_rate": 0.0001910067678585786,
553
+ "loss": 0.9423,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.49,
558
+ "learning_rate": 0.00019076590173265406,
559
+ "loss": 0.9173,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.5,
564
+ "learning_rate": 0.00019052200852974819,
565
+ "loss": 1.8901,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.5,
570
+ "learning_rate": 0.0001902750963837912,
571
+ "loss": 1.9665,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.51,
576
+ "learning_rate": 0.00019002517352939598,
577
+ "loss": 1.8323,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.51,
582
+ "learning_rate": 0.0001897722483015838,
583
+ "loss": 1.7828,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.52,
588
+ "learning_rate": 0.00018951632913550626,
589
+ "loss": 1.5083,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.52,
594
+ "learning_rate": 0.00018925742456616374,
595
+ "loss": 1.6924,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.53,
600
+ "learning_rate": 0.0001889955432281212,
601
+ "loss": 1.7446,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.53,
606
+ "learning_rate": 0.0001887306938552197,
607
+ "loss": 1.6143,
608
+ "step": 100
609
+ }
610
+ ],
611
+ "max_steps": 561,
612
+ "num_train_epochs": 3,
613
+ "total_flos": 1.932234765631488e+16,
614
+ "trial_name": null,
615
+ "trial_params": null
616
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca476fdc79c35941e82478278237f98f92b013f5a509b33f355127ad4c6138c4
3
+ size 4408
checkpoint-110/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
checkpoint-110/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-110/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ab160a4a76d4a34ffec9bbbcda7002e160774989aa00d679bd80bc9fd86dee0
3
+ size 134264202
checkpoint-110/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d265ef055c4e924feedbf425eea28fdb94b03453389e9b6cc5f9c08742dda1d
3
+ size 268514874
checkpoint-110/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f13f32f8aa164ffd1b7bde3b1300845eb4e5ff1261fa4d6b2a28fbbd9f352e72
3
+ size 14244
checkpoint-110/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ff9cebed4b84c4a10fa2a0b09dd590879ae33916425f0e7ff878ab3107234ceb
3
+ size 1064
checkpoint-110/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-110/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-110/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-110/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-110/trainer_state.json ADDED
@@ -0,0 +1,676 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.5866666666666667,
5
+ "global_step": 110,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 1.1764705882352942e-05,
13
+ "loss": 1.9122,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 2.3529411764705884e-05,
19
+ "loss": 2.0707,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 3.529411764705883e-05,
25
+ "loss": 1.9703,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4.705882352941177e-05,
31
+ "loss": 2.015,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 5.882352941176471e-05,
37
+ "loss": 2.119,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 7.058823529411765e-05,
43
+ "loss": 2.0515,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 8.23529411764706e-05,
49
+ "loss": 1.7436,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 9.411764705882353e-05,
55
+ "loss": 1.9326,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 0.00010588235294117647,
61
+ "loss": 2.0819,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 0.00011764705882352942,
67
+ "loss": 1.9965,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 0.00012941176470588237,
73
+ "loss": 2.0543,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.06,
78
+ "learning_rate": 0.0001411764705882353,
79
+ "loss": 2.0461,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 0.00015294117647058822,
85
+ "loss": 2.311,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "learning_rate": 0.0001647058823529412,
91
+ "loss": 1.8447,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 0.00017647058823529413,
97
+ "loss": 2.6263,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.09,
102
+ "learning_rate": 0.00018823529411764707,
103
+ "loss": 2.6179,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.09,
108
+ "learning_rate": 0.0002,
109
+ "loss": 2.535,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "learning_rate": 0.00019999833248118322,
115
+ "loss": 2.5924,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.1,
120
+ "learning_rate": 0.00019999332998034514,
121
+ "loss": 2.3562,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.11,
126
+ "learning_rate": 0.00019998499266432108,
127
+ "loss": 2.2352,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.11,
132
+ "learning_rate": 0.00019997332081116373,
133
+ "loss": 2.152,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.12,
138
+ "learning_rate": 0.00019995831481013374,
139
+ "loss": 2.1149,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.12,
144
+ "learning_rate": 0.00019993997516168689,
145
+ "loss": 2.1608,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.13,
150
+ "learning_rate": 0.0001999183024774573,
151
+ "loss": 2.1593,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.13,
156
+ "learning_rate": 0.00019989329748023725,
157
+ "loss": 2.2774,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.14,
162
+ "learning_rate": 0.00019986496100395275,
163
+ "loss": 2.0355,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.14,
168
+ "learning_rate": 0.00019983329399363598,
169
+ "loss": 1.9455,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "learning_rate": 0.0001997982975053936,
175
+ "loss": 2.5648,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.15,
180
+ "learning_rate": 0.0001997599727063717,
181
+ "loss": 2.3619,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.16,
186
+ "learning_rate": 0.00019971832087471676,
187
+ "loss": 2.0888,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.17,
192
+ "learning_rate": 0.000199673343399533,
193
+ "loss": 1.9363,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.17,
198
+ "learning_rate": 0.00019962504178083618,
199
+ "loss": 2.0259,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.18,
204
+ "learning_rate": 0.00019957341762950344,
205
+ "loss": 1.8482,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.18,
210
+ "learning_rate": 0.0001995184726672197,
211
+ "loss": 1.8542,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "learning_rate": 0.0001994602087264201,
217
+ "loss": 1.9435,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.19,
222
+ "learning_rate": 0.00019939862775022893,
223
+ "loss": 1.6559,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.2,
228
+ "learning_rate": 0.00019933373179239502,
229
+ "loss": 1.9478,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.2,
234
+ "learning_rate": 0.0001992655230172229,
235
+ "loss": 1.9417,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.21,
240
+ "learning_rate": 0.000199194003699501,
241
+ "loss": 1.9067,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.21,
246
+ "learning_rate": 0.00019911917622442537,
247
+ "loss": 1.6106,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.22,
252
+ "learning_rate": 0.0001990410430875205,
253
+ "loss": 1.2742,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.22,
258
+ "learning_rate": 0.00019895960689455598,
259
+ "loss": 1.3048,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.23,
264
+ "learning_rate": 0.0001988748703614594,
265
+ "loss": 1.1847,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.23,
270
+ "learning_rate": 0.00019878683631422605,
271
+ "loss": 1.1683,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.24,
276
+ "learning_rate": 0.00019869550768882455,
277
+ "loss": 1.1531,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.25,
282
+ "learning_rate": 0.00019860088753109896,
283
+ "loss": 1.1401,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.25,
288
+ "learning_rate": 0.0001985029789966671,
289
+ "loss": 1.8959,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.26,
294
+ "learning_rate": 0.00019840178535081545,
295
+ "loss": 1.897,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.26,
300
+ "learning_rate": 0.0001982973099683902,
301
+ "loss": 1.791,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.27,
306
+ "learning_rate": 0.00019818955633368464,
307
+ "loss": 1.7451,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.27,
312
+ "learning_rate": 0.00019807852804032305,
313
+ "loss": 1.8556,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.28,
318
+ "learning_rate": 0.00019796422879114084,
319
+ "loss": 1.7882,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.28,
324
+ "learning_rate": 0.0001978466623980609,
325
+ "loss": 1.8834,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.29,
330
+ "learning_rate": 0.00019772583278196678,
331
+ "loss": 1.7593,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.29,
336
+ "learning_rate": 0.00019760174397257156,
337
+ "loss": 1.8291,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.3,
342
+ "learning_rate": 0.00019747440010828383,
343
+ "loss": 1.808,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.3,
348
+ "learning_rate": 0.0001973438054360693,
349
+ "loss": 1.6324,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.31,
354
+ "learning_rate": 0.00019720996431130946,
355
+ "loss": 1.483,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.31,
360
+ "learning_rate": 0.00019707288119765623,
361
+ "loss": 1.9648,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.32,
366
+ "learning_rate": 0.000196932560666883,
367
+ "loss": 1.5742,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.33,
372
+ "learning_rate": 0.00019678900739873226,
373
+ "loss": 1.7066,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.33,
378
+ "learning_rate": 0.00019664222618075958,
379
+ "loss": 2.0719,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.34,
384
+ "learning_rate": 0.0001964922219081738,
385
+ "loss": 1.9432,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.34,
390
+ "learning_rate": 0.00019633899958367384,
391
+ "loss": 1.7979,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.35,
396
+ "learning_rate": 0.00019618256431728194,
397
+ "loss": 1.6286,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.35,
402
+ "learning_rate": 0.000196022921326173,
403
+ "loss": 1.6031,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.36,
408
+ "learning_rate": 0.00019586007593450097,
409
+ "loss": 1.5169,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.36,
414
+ "learning_rate": 0.0001956940335732209,
415
+ "loss": 1.5923,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.37,
420
+ "learning_rate": 0.000195524799779908,
421
+ "loss": 1.6123,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.37,
426
+ "learning_rate": 0.000195352380198573,
427
+ "loss": 1.7392,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.38,
432
+ "learning_rate": 0.00019517678057947384,
433
+ "loss": 1.6406,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.38,
438
+ "learning_rate": 0.00019499800677892385,
439
+ "loss": 1.5532,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.39,
444
+ "learning_rate": 0.0001948160647590966,
445
+ "loss": 1.816,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.39,
450
+ "learning_rate": 0.0001946309605878269,
451
+ "loss": 1.5759,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.4,
456
+ "learning_rate": 0.00019444270043840852,
457
+ "loss": 1.6726,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.41,
462
+ "learning_rate": 0.00019425129058938832,
463
+ "loss": 1.6134,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.41,
468
+ "learning_rate": 0.00019405673742435678,
469
+ "loss": 1.6285,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.42,
474
+ "learning_rate": 0.00019385904743173516,
475
+ "loss": 1.6023,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.42,
480
+ "learning_rate": 0.00019365822720455916,
481
+ "loss": 1.5177,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.43,
486
+ "learning_rate": 0.00019345428344025883,
487
+ "loss": 1.5413,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.43,
492
+ "learning_rate": 0.00019324722294043558,
493
+ "loss": 1.3404,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.44,
498
+ "learning_rate": 0.00019303705261063497,
499
+ "loss": 1.6409,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.44,
504
+ "learning_rate": 0.00019282377946011652,
505
+ "loss": 1.6361,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.45,
510
+ "learning_rate": 0.00019260741060162016,
511
+ "loss": 1.4902,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.45,
516
+ "learning_rate": 0.0001923879532511287,
517
+ "loss": 1.3232,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.46,
522
+ "learning_rate": 0.00019216541472762735,
523
+ "loss": 1.2438,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.46,
528
+ "learning_rate": 0.00019193980245285966,
529
+ "loss": 1.0828,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.47,
534
+ "learning_rate": 0.00019171112395107985,
535
+ "loss": 1.0696,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.47,
540
+ "learning_rate": 0.0001914793868488021,
541
+ "loss": 1.0179,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.48,
546
+ "learning_rate": 0.0001912445988745459,
547
+ "loss": 1.0012,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.49,
552
+ "learning_rate": 0.0001910067678585786,
553
+ "loss": 0.9423,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.49,
558
+ "learning_rate": 0.00019076590173265406,
559
+ "loss": 0.9173,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.5,
564
+ "learning_rate": 0.00019052200852974819,
565
+ "loss": 1.8901,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.5,
570
+ "learning_rate": 0.0001902750963837912,
571
+ "loss": 1.9665,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.51,
576
+ "learning_rate": 0.00019002517352939598,
577
+ "loss": 1.8323,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.51,
582
+ "learning_rate": 0.0001897722483015838,
583
+ "loss": 1.7828,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.52,
588
+ "learning_rate": 0.00018951632913550626,
589
+ "loss": 1.5083,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.52,
594
+ "learning_rate": 0.00018925742456616374,
595
+ "loss": 1.6924,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.53,
600
+ "learning_rate": 0.0001889955432281212,
601
+ "loss": 1.7446,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.53,
606
+ "learning_rate": 0.0001887306938552197,
607
+ "loss": 1.6143,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.54,
612
+ "learning_rate": 0.00018846288528028555,
613
+ "loss": 1.5013,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.54,
618
+ "learning_rate": 0.0001881921264348355,
619
+ "loss": 1.6335,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.55,
624
+ "learning_rate": 0.00018791842634877898,
625
+ "loss": 1.5852,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.55,
630
+ "learning_rate": 0.00018764179415011682,
631
+ "loss": 1.4358,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.56,
636
+ "learning_rate": 0.00018736223906463696,
637
+ "loss": 1.7103,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.57,
642
+ "learning_rate": 0.0001870797704156067,
643
+ "loss": 1.3361,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.57,
648
+ "learning_rate": 0.00018679439762346185,
649
+ "loss": 1.7021,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.58,
654
+ "learning_rate": 0.00018650613020549232,
655
+ "loss": 2.3076,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.58,
660
+ "learning_rate": 0.00018621497777552507,
661
+ "loss": 1.6109,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.59,
666
+ "learning_rate": 0.00018592095004360318,
667
+ "loss": 1.8032,
668
+ "step": 110
669
+ }
670
+ ],
671
+ "max_steps": 561,
672
+ "num_train_epochs": 3,
673
+ "total_flos": 2.197088917291008e+16,
674
+ "trial_name": null,
675
+ "trial_params": null
676
+ }
checkpoint-110/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca476fdc79c35941e82478278237f98f92b013f5a509b33f355127ad4c6138c4
3
+ size 4408
checkpoint-120/README.md ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: peft
3
+ ---
4
+ ## Training procedure
5
+
6
+
7
+ The following `bitsandbytes` quantization config was used during training:
8
+ - load_in_8bit: False
9
+ - load_in_4bit: True
10
+ - llm_int8_threshold: 6.0
11
+ - llm_int8_skip_modules: None
12
+ - llm_int8_enable_fp32_cpu_offload: False
13
+ - llm_int8_has_fp16_weight: False
14
+ - bnb_4bit_quant_type: nf4
15
+ - bnb_4bit_use_double_quant: False
16
+ - bnb_4bit_compute_dtype: float16
17
+
18
+ The following `bitsandbytes` quantization config was used during training:
19
+ - load_in_8bit: False
20
+ - load_in_4bit: True
21
+ - llm_int8_threshold: 6.0
22
+ - llm_int8_skip_modules: None
23
+ - llm_int8_enable_fp32_cpu_offload: False
24
+ - llm_int8_has_fp16_weight: False
25
+ - bnb_4bit_quant_type: nf4
26
+ - bnb_4bit_use_double_quant: False
27
+ - bnb_4bit_compute_dtype: float16
28
+ ### Framework versions
29
+
30
+ - PEFT 0.4.0
31
+
32
+ - PEFT 0.4.0
checkpoint-120/adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "auto_mapping": null,
3
+ "base_model_name_or_path": "NousResearch/Llama-2-7b-hf",
4
+ "bias": "none",
5
+ "fan_in_fan_out": false,
6
+ "inference_mode": true,
7
+ "init_lora_weights": true,
8
+ "layers_pattern": null,
9
+ "layers_to_transform": null,
10
+ "lora_alpha": 16,
11
+ "lora_dropout": 0.1,
12
+ "modules_to_save": null,
13
+ "peft_type": "LORA",
14
+ "r": 64,
15
+ "revision": null,
16
+ "target_modules": [
17
+ "q_proj",
18
+ "v_proj"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
checkpoint-120/adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5f63b18c360ef434241c46077438e856ee40767edea3f3ef136502e81622c7e8
3
+ size 134264202
checkpoint-120/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:743ae5cb13f6c4bc0acf827c572b3f52dbcf3261520bc97b97f7415248d7143b
3
+ size 268514874
checkpoint-120/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69f9463e63f630e9d19e9e943967b483f6ad7d8148528460ee5eef8b57e4837
3
+ size 14244
checkpoint-120/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38bdced6aea30e4a2fbc6689e1d6c5e654c04a709c3628d0ddc81f78f9902682
3
+ size 1064
checkpoint-120/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "</s>",
17
+ "unk_token": {
18
+ "content": "<unk>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-120/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-120/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
checkpoint-120/tokenizer_config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "__type": "AddedToken",
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": {
12
+ "__type": "AddedToken",
13
+ "content": "</s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "legacy": false,
20
+ "model_max_length": 1000000000000000019884624838656,
21
+ "pad_token": null,
22
+ "sp_model_kwargs": {},
23
+ "tokenizer_class": "LlamaTokenizer",
24
+ "unk_token": {
25
+ "__type": "AddedToken",
26
+ "content": "<unk>",
27
+ "lstrip": false,
28
+ "normalized": true,
29
+ "rstrip": false,
30
+ "single_word": false
31
+ }
32
+ }
checkpoint-120/trainer_state.json ADDED
@@ -0,0 +1,736 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.64,
5
+ "global_step": 120,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.01,
12
+ "learning_rate": 1.1764705882352942e-05,
13
+ "loss": 1.9122,
14
+ "step": 1
15
+ },
16
+ {
17
+ "epoch": 0.01,
18
+ "learning_rate": 2.3529411764705884e-05,
19
+ "loss": 2.0707,
20
+ "step": 2
21
+ },
22
+ {
23
+ "epoch": 0.02,
24
+ "learning_rate": 3.529411764705883e-05,
25
+ "loss": 1.9703,
26
+ "step": 3
27
+ },
28
+ {
29
+ "epoch": 0.02,
30
+ "learning_rate": 4.705882352941177e-05,
31
+ "loss": 2.015,
32
+ "step": 4
33
+ },
34
+ {
35
+ "epoch": 0.03,
36
+ "learning_rate": 5.882352941176471e-05,
37
+ "loss": 2.119,
38
+ "step": 5
39
+ },
40
+ {
41
+ "epoch": 0.03,
42
+ "learning_rate": 7.058823529411765e-05,
43
+ "loss": 2.0515,
44
+ "step": 6
45
+ },
46
+ {
47
+ "epoch": 0.04,
48
+ "learning_rate": 8.23529411764706e-05,
49
+ "loss": 1.7436,
50
+ "step": 7
51
+ },
52
+ {
53
+ "epoch": 0.04,
54
+ "learning_rate": 9.411764705882353e-05,
55
+ "loss": 1.9326,
56
+ "step": 8
57
+ },
58
+ {
59
+ "epoch": 0.05,
60
+ "learning_rate": 0.00010588235294117647,
61
+ "loss": 2.0819,
62
+ "step": 9
63
+ },
64
+ {
65
+ "epoch": 0.05,
66
+ "learning_rate": 0.00011764705882352942,
67
+ "loss": 1.9965,
68
+ "step": 10
69
+ },
70
+ {
71
+ "epoch": 0.06,
72
+ "learning_rate": 0.00012941176470588237,
73
+ "loss": 2.0543,
74
+ "step": 11
75
+ },
76
+ {
77
+ "epoch": 0.06,
78
+ "learning_rate": 0.0001411764705882353,
79
+ "loss": 2.0461,
80
+ "step": 12
81
+ },
82
+ {
83
+ "epoch": 0.07,
84
+ "learning_rate": 0.00015294117647058822,
85
+ "loss": 2.311,
86
+ "step": 13
87
+ },
88
+ {
89
+ "epoch": 0.07,
90
+ "learning_rate": 0.0001647058823529412,
91
+ "loss": 1.8447,
92
+ "step": 14
93
+ },
94
+ {
95
+ "epoch": 0.08,
96
+ "learning_rate": 0.00017647058823529413,
97
+ "loss": 2.6263,
98
+ "step": 15
99
+ },
100
+ {
101
+ "epoch": 0.09,
102
+ "learning_rate": 0.00018823529411764707,
103
+ "loss": 2.6179,
104
+ "step": 16
105
+ },
106
+ {
107
+ "epoch": 0.09,
108
+ "learning_rate": 0.0002,
109
+ "loss": 2.535,
110
+ "step": 17
111
+ },
112
+ {
113
+ "epoch": 0.1,
114
+ "learning_rate": 0.00019999833248118322,
115
+ "loss": 2.5924,
116
+ "step": 18
117
+ },
118
+ {
119
+ "epoch": 0.1,
120
+ "learning_rate": 0.00019999332998034514,
121
+ "loss": 2.3562,
122
+ "step": 19
123
+ },
124
+ {
125
+ "epoch": 0.11,
126
+ "learning_rate": 0.00019998499266432108,
127
+ "loss": 2.2352,
128
+ "step": 20
129
+ },
130
+ {
131
+ "epoch": 0.11,
132
+ "learning_rate": 0.00019997332081116373,
133
+ "loss": 2.152,
134
+ "step": 21
135
+ },
136
+ {
137
+ "epoch": 0.12,
138
+ "learning_rate": 0.00019995831481013374,
139
+ "loss": 2.1149,
140
+ "step": 22
141
+ },
142
+ {
143
+ "epoch": 0.12,
144
+ "learning_rate": 0.00019993997516168689,
145
+ "loss": 2.1608,
146
+ "step": 23
147
+ },
148
+ {
149
+ "epoch": 0.13,
150
+ "learning_rate": 0.0001999183024774573,
151
+ "loss": 2.1593,
152
+ "step": 24
153
+ },
154
+ {
155
+ "epoch": 0.13,
156
+ "learning_rate": 0.00019989329748023725,
157
+ "loss": 2.2774,
158
+ "step": 25
159
+ },
160
+ {
161
+ "epoch": 0.14,
162
+ "learning_rate": 0.00019986496100395275,
163
+ "loss": 2.0355,
164
+ "step": 26
165
+ },
166
+ {
167
+ "epoch": 0.14,
168
+ "learning_rate": 0.00019983329399363598,
169
+ "loss": 1.9455,
170
+ "step": 27
171
+ },
172
+ {
173
+ "epoch": 0.15,
174
+ "learning_rate": 0.0001997982975053936,
175
+ "loss": 2.5648,
176
+ "step": 28
177
+ },
178
+ {
179
+ "epoch": 0.15,
180
+ "learning_rate": 0.0001997599727063717,
181
+ "loss": 2.3619,
182
+ "step": 29
183
+ },
184
+ {
185
+ "epoch": 0.16,
186
+ "learning_rate": 0.00019971832087471676,
187
+ "loss": 2.0888,
188
+ "step": 30
189
+ },
190
+ {
191
+ "epoch": 0.17,
192
+ "learning_rate": 0.000199673343399533,
193
+ "loss": 1.9363,
194
+ "step": 31
195
+ },
196
+ {
197
+ "epoch": 0.17,
198
+ "learning_rate": 0.00019962504178083618,
199
+ "loss": 2.0259,
200
+ "step": 32
201
+ },
202
+ {
203
+ "epoch": 0.18,
204
+ "learning_rate": 0.00019957341762950344,
205
+ "loss": 1.8482,
206
+ "step": 33
207
+ },
208
+ {
209
+ "epoch": 0.18,
210
+ "learning_rate": 0.0001995184726672197,
211
+ "loss": 1.8542,
212
+ "step": 34
213
+ },
214
+ {
215
+ "epoch": 0.19,
216
+ "learning_rate": 0.0001994602087264201,
217
+ "loss": 1.9435,
218
+ "step": 35
219
+ },
220
+ {
221
+ "epoch": 0.19,
222
+ "learning_rate": 0.00019939862775022893,
223
+ "loss": 1.6559,
224
+ "step": 36
225
+ },
226
+ {
227
+ "epoch": 0.2,
228
+ "learning_rate": 0.00019933373179239502,
229
+ "loss": 1.9478,
230
+ "step": 37
231
+ },
232
+ {
233
+ "epoch": 0.2,
234
+ "learning_rate": 0.0001992655230172229,
235
+ "loss": 1.9417,
236
+ "step": 38
237
+ },
238
+ {
239
+ "epoch": 0.21,
240
+ "learning_rate": 0.000199194003699501,
241
+ "loss": 1.9067,
242
+ "step": 39
243
+ },
244
+ {
245
+ "epoch": 0.21,
246
+ "learning_rate": 0.00019911917622442537,
247
+ "loss": 1.6106,
248
+ "step": 40
249
+ },
250
+ {
251
+ "epoch": 0.22,
252
+ "learning_rate": 0.0001990410430875205,
253
+ "loss": 1.2742,
254
+ "step": 41
255
+ },
256
+ {
257
+ "epoch": 0.22,
258
+ "learning_rate": 0.00019895960689455598,
259
+ "loss": 1.3048,
260
+ "step": 42
261
+ },
262
+ {
263
+ "epoch": 0.23,
264
+ "learning_rate": 0.0001988748703614594,
265
+ "loss": 1.1847,
266
+ "step": 43
267
+ },
268
+ {
269
+ "epoch": 0.23,
270
+ "learning_rate": 0.00019878683631422605,
271
+ "loss": 1.1683,
272
+ "step": 44
273
+ },
274
+ {
275
+ "epoch": 0.24,
276
+ "learning_rate": 0.00019869550768882455,
277
+ "loss": 1.1531,
278
+ "step": 45
279
+ },
280
+ {
281
+ "epoch": 0.25,
282
+ "learning_rate": 0.00019860088753109896,
283
+ "loss": 1.1401,
284
+ "step": 46
285
+ },
286
+ {
287
+ "epoch": 0.25,
288
+ "learning_rate": 0.0001985029789966671,
289
+ "loss": 1.8959,
290
+ "step": 47
291
+ },
292
+ {
293
+ "epoch": 0.26,
294
+ "learning_rate": 0.00019840178535081545,
295
+ "loss": 1.897,
296
+ "step": 48
297
+ },
298
+ {
299
+ "epoch": 0.26,
300
+ "learning_rate": 0.0001982973099683902,
301
+ "loss": 1.791,
302
+ "step": 49
303
+ },
304
+ {
305
+ "epoch": 0.27,
306
+ "learning_rate": 0.00019818955633368464,
307
+ "loss": 1.7451,
308
+ "step": 50
309
+ },
310
+ {
311
+ "epoch": 0.27,
312
+ "learning_rate": 0.00019807852804032305,
313
+ "loss": 1.8556,
314
+ "step": 51
315
+ },
316
+ {
317
+ "epoch": 0.28,
318
+ "learning_rate": 0.00019796422879114084,
319
+ "loss": 1.7882,
320
+ "step": 52
321
+ },
322
+ {
323
+ "epoch": 0.28,
324
+ "learning_rate": 0.0001978466623980609,
325
+ "loss": 1.8834,
326
+ "step": 53
327
+ },
328
+ {
329
+ "epoch": 0.29,
330
+ "learning_rate": 0.00019772583278196678,
331
+ "loss": 1.7593,
332
+ "step": 54
333
+ },
334
+ {
335
+ "epoch": 0.29,
336
+ "learning_rate": 0.00019760174397257156,
337
+ "loss": 1.8291,
338
+ "step": 55
339
+ },
340
+ {
341
+ "epoch": 0.3,
342
+ "learning_rate": 0.00019747440010828383,
343
+ "loss": 1.808,
344
+ "step": 56
345
+ },
346
+ {
347
+ "epoch": 0.3,
348
+ "learning_rate": 0.0001973438054360693,
349
+ "loss": 1.6324,
350
+ "step": 57
351
+ },
352
+ {
353
+ "epoch": 0.31,
354
+ "learning_rate": 0.00019720996431130946,
355
+ "loss": 1.483,
356
+ "step": 58
357
+ },
358
+ {
359
+ "epoch": 0.31,
360
+ "learning_rate": 0.00019707288119765623,
361
+ "loss": 1.9648,
362
+ "step": 59
363
+ },
364
+ {
365
+ "epoch": 0.32,
366
+ "learning_rate": 0.000196932560666883,
367
+ "loss": 1.5742,
368
+ "step": 60
369
+ },
370
+ {
371
+ "epoch": 0.33,
372
+ "learning_rate": 0.00019678900739873226,
373
+ "loss": 1.7066,
374
+ "step": 61
375
+ },
376
+ {
377
+ "epoch": 0.33,
378
+ "learning_rate": 0.00019664222618075958,
379
+ "loss": 2.0719,
380
+ "step": 62
381
+ },
382
+ {
383
+ "epoch": 0.34,
384
+ "learning_rate": 0.0001964922219081738,
385
+ "loss": 1.9432,
386
+ "step": 63
387
+ },
388
+ {
389
+ "epoch": 0.34,
390
+ "learning_rate": 0.00019633899958367384,
391
+ "loss": 1.7979,
392
+ "step": 64
393
+ },
394
+ {
395
+ "epoch": 0.35,
396
+ "learning_rate": 0.00019618256431728194,
397
+ "loss": 1.6286,
398
+ "step": 65
399
+ },
400
+ {
401
+ "epoch": 0.35,
402
+ "learning_rate": 0.000196022921326173,
403
+ "loss": 1.6031,
404
+ "step": 66
405
+ },
406
+ {
407
+ "epoch": 0.36,
408
+ "learning_rate": 0.00019586007593450097,
409
+ "loss": 1.5169,
410
+ "step": 67
411
+ },
412
+ {
413
+ "epoch": 0.36,
414
+ "learning_rate": 0.0001956940335732209,
415
+ "loss": 1.5923,
416
+ "step": 68
417
+ },
418
+ {
419
+ "epoch": 0.37,
420
+ "learning_rate": 0.000195524799779908,
421
+ "loss": 1.6123,
422
+ "step": 69
423
+ },
424
+ {
425
+ "epoch": 0.37,
426
+ "learning_rate": 0.000195352380198573,
427
+ "loss": 1.7392,
428
+ "step": 70
429
+ },
430
+ {
431
+ "epoch": 0.38,
432
+ "learning_rate": 0.00019517678057947384,
433
+ "loss": 1.6406,
434
+ "step": 71
435
+ },
436
+ {
437
+ "epoch": 0.38,
438
+ "learning_rate": 0.00019499800677892385,
439
+ "loss": 1.5532,
440
+ "step": 72
441
+ },
442
+ {
443
+ "epoch": 0.39,
444
+ "learning_rate": 0.0001948160647590966,
445
+ "loss": 1.816,
446
+ "step": 73
447
+ },
448
+ {
449
+ "epoch": 0.39,
450
+ "learning_rate": 0.0001946309605878269,
451
+ "loss": 1.5759,
452
+ "step": 74
453
+ },
454
+ {
455
+ "epoch": 0.4,
456
+ "learning_rate": 0.00019444270043840852,
457
+ "loss": 1.6726,
458
+ "step": 75
459
+ },
460
+ {
461
+ "epoch": 0.41,
462
+ "learning_rate": 0.00019425129058938832,
463
+ "loss": 1.6134,
464
+ "step": 76
465
+ },
466
+ {
467
+ "epoch": 0.41,
468
+ "learning_rate": 0.00019405673742435678,
469
+ "loss": 1.6285,
470
+ "step": 77
471
+ },
472
+ {
473
+ "epoch": 0.42,
474
+ "learning_rate": 0.00019385904743173516,
475
+ "loss": 1.6023,
476
+ "step": 78
477
+ },
478
+ {
479
+ "epoch": 0.42,
480
+ "learning_rate": 0.00019365822720455916,
481
+ "loss": 1.5177,
482
+ "step": 79
483
+ },
484
+ {
485
+ "epoch": 0.43,
486
+ "learning_rate": 0.00019345428344025883,
487
+ "loss": 1.5413,
488
+ "step": 80
489
+ },
490
+ {
491
+ "epoch": 0.43,
492
+ "learning_rate": 0.00019324722294043558,
493
+ "loss": 1.3404,
494
+ "step": 81
495
+ },
496
+ {
497
+ "epoch": 0.44,
498
+ "learning_rate": 0.00019303705261063497,
499
+ "loss": 1.6409,
500
+ "step": 82
501
+ },
502
+ {
503
+ "epoch": 0.44,
504
+ "learning_rate": 0.00019282377946011652,
505
+ "loss": 1.6361,
506
+ "step": 83
507
+ },
508
+ {
509
+ "epoch": 0.45,
510
+ "learning_rate": 0.00019260741060162016,
511
+ "loss": 1.4902,
512
+ "step": 84
513
+ },
514
+ {
515
+ "epoch": 0.45,
516
+ "learning_rate": 0.0001923879532511287,
517
+ "loss": 1.3232,
518
+ "step": 85
519
+ },
520
+ {
521
+ "epoch": 0.46,
522
+ "learning_rate": 0.00019216541472762735,
523
+ "loss": 1.2438,
524
+ "step": 86
525
+ },
526
+ {
527
+ "epoch": 0.46,
528
+ "learning_rate": 0.00019193980245285966,
529
+ "loss": 1.0828,
530
+ "step": 87
531
+ },
532
+ {
533
+ "epoch": 0.47,
534
+ "learning_rate": 0.00019171112395107985,
535
+ "loss": 1.0696,
536
+ "step": 88
537
+ },
538
+ {
539
+ "epoch": 0.47,
540
+ "learning_rate": 0.0001914793868488021,
541
+ "loss": 1.0179,
542
+ "step": 89
543
+ },
544
+ {
545
+ "epoch": 0.48,
546
+ "learning_rate": 0.0001912445988745459,
547
+ "loss": 1.0012,
548
+ "step": 90
549
+ },
550
+ {
551
+ "epoch": 0.49,
552
+ "learning_rate": 0.0001910067678585786,
553
+ "loss": 0.9423,
554
+ "step": 91
555
+ },
556
+ {
557
+ "epoch": 0.49,
558
+ "learning_rate": 0.00019076590173265406,
559
+ "loss": 0.9173,
560
+ "step": 92
561
+ },
562
+ {
563
+ "epoch": 0.5,
564
+ "learning_rate": 0.00019052200852974819,
565
+ "loss": 1.8901,
566
+ "step": 93
567
+ },
568
+ {
569
+ "epoch": 0.5,
570
+ "learning_rate": 0.0001902750963837912,
571
+ "loss": 1.9665,
572
+ "step": 94
573
+ },
574
+ {
575
+ "epoch": 0.51,
576
+ "learning_rate": 0.00019002517352939598,
577
+ "loss": 1.8323,
578
+ "step": 95
579
+ },
580
+ {
581
+ "epoch": 0.51,
582
+ "learning_rate": 0.0001897722483015838,
583
+ "loss": 1.7828,
584
+ "step": 96
585
+ },
586
+ {
587
+ "epoch": 0.52,
588
+ "learning_rate": 0.00018951632913550626,
589
+ "loss": 1.5083,
590
+ "step": 97
591
+ },
592
+ {
593
+ "epoch": 0.52,
594
+ "learning_rate": 0.00018925742456616374,
595
+ "loss": 1.6924,
596
+ "step": 98
597
+ },
598
+ {
599
+ "epoch": 0.53,
600
+ "learning_rate": 0.0001889955432281212,
601
+ "loss": 1.7446,
602
+ "step": 99
603
+ },
604
+ {
605
+ "epoch": 0.53,
606
+ "learning_rate": 0.0001887306938552197,
607
+ "loss": 1.6143,
608
+ "step": 100
609
+ },
610
+ {
611
+ "epoch": 0.54,
612
+ "learning_rate": 0.00018846288528028555,
613
+ "loss": 1.5013,
614
+ "step": 101
615
+ },
616
+ {
617
+ "epoch": 0.54,
618
+ "learning_rate": 0.0001881921264348355,
619
+ "loss": 1.6335,
620
+ "step": 102
621
+ },
622
+ {
623
+ "epoch": 0.55,
624
+ "learning_rate": 0.00018791842634877898,
625
+ "loss": 1.5852,
626
+ "step": 103
627
+ },
628
+ {
629
+ "epoch": 0.55,
630
+ "learning_rate": 0.00018764179415011682,
631
+ "loss": 1.4358,
632
+ "step": 104
633
+ },
634
+ {
635
+ "epoch": 0.56,
636
+ "learning_rate": 0.00018736223906463696,
637
+ "loss": 1.7103,
638
+ "step": 105
639
+ },
640
+ {
641
+ "epoch": 0.57,
642
+ "learning_rate": 0.0001870797704156067,
643
+ "loss": 1.3361,
644
+ "step": 106
645
+ },
646
+ {
647
+ "epoch": 0.57,
648
+ "learning_rate": 0.00018679439762346185,
649
+ "loss": 1.7021,
650
+ "step": 107
651
+ },
652
+ {
653
+ "epoch": 0.58,
654
+ "learning_rate": 0.00018650613020549232,
655
+ "loss": 2.3076,
656
+ "step": 108
657
+ },
658
+ {
659
+ "epoch": 0.58,
660
+ "learning_rate": 0.00018621497777552507,
661
+ "loss": 1.6109,
662
+ "step": 109
663
+ },
664
+ {
665
+ "epoch": 0.59,
666
+ "learning_rate": 0.00018592095004360318,
667
+ "loss": 1.8032,
668
+ "step": 110
669
+ },
670
+ {
671
+ "epoch": 0.59,
672
+ "learning_rate": 0.00018562405681566216,
673
+ "loss": 1.6432,
674
+ "step": 111
675
+ },
676
+ {
677
+ "epoch": 0.6,
678
+ "learning_rate": 0.0001853243079932029,
679
+ "loss": 1.4159,
680
+ "step": 112
681
+ },
682
+ {
683
+ "epoch": 0.6,
684
+ "learning_rate": 0.00018502171357296144,
685
+ "loss": 1.4869,
686
+ "step": 113
687
+ },
688
+ {
689
+ "epoch": 0.61,
690
+ "learning_rate": 0.00018471628364657555,
691
+ "loss": 1.419,
692
+ "step": 114
693
+ },
694
+ {
695
+ "epoch": 0.61,
696
+ "learning_rate": 0.00018440802840024822,
697
+ "loss": 1.3616,
698
+ "step": 115
699
+ },
700
+ {
701
+ "epoch": 0.62,
702
+ "learning_rate": 0.00018409695811440796,
703
+ "loss": 1.4805,
704
+ "step": 116
705
+ },
706
+ {
707
+ "epoch": 0.62,
708
+ "learning_rate": 0.00018378308316336584,
709
+ "loss": 1.5585,
710
+ "step": 117
711
+ },
712
+ {
713
+ "epoch": 0.63,
714
+ "learning_rate": 0.0001834664140149696,
715
+ "loss": 1.4302,
716
+ "step": 118
717
+ },
718
+ {
719
+ "epoch": 0.63,
720
+ "learning_rate": 0.00018314696123025454,
721
+ "loss": 1.3596,
722
+ "step": 119
723
+ },
724
+ {
725
+ "epoch": 0.64,
726
+ "learning_rate": 0.0001828247354630912,
727
+ "loss": 1.5605,
728
+ "step": 120
729
+ }
730
+ ],
731
+ "max_steps": 561,
732
+ "num_train_epochs": 3,
733
+ "total_flos": 2.36947687391232e+16,
734
+ "trial_name": null,
735
+ "trial_params": null
736
+ }