Hugging Face's logo

pharaouk
/
CodeLlama-34b-Python-hf_34bCodellama_unnatural-instructions_standardized

Model card Files Community
Farouk commited on
Commit
7f4b9fe
·
1 Parent(s): 2718f1f

Training in progress, step 5000

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. adapter_config.json +5 -5
  2. adapter_model.bin +1 -1
  3. all_results.json +9 -9
  4. checkpoint-2000/adapter_model.bin +0 -3
  5. checkpoint-2000/optimizer.pt +0 -3
  6. checkpoint-2000/rng_state.pth +0 -3
  7. checkpoint-2000/scheduler.pt +0 -3
  8. checkpoint-2000/trainer_state.json +0 -0
  9. checkpoint-2000/training_args.bin +0 -3
  10. checkpoint-2200/README.md +0 -20
  11. checkpoint-2200/adapter_config.json +0 -26
  12. checkpoint-2200/adapter_model/adapter_model/README.md +0 -80
  13. checkpoint-2200/adapter_model/adapter_model/adapter_config.json +0 -26
  14. checkpoint-2200/adapter_model/adapter_model/adapter_model.bin +0 -3
  15. checkpoint-2200/added_tokens.json +0 -3
  16. checkpoint-2200/optimizer.pt +0 -3
  17. checkpoint-2200/rng_state.pth +0 -3
  18. checkpoint-2200/scheduler.pt +0 -3
  19. checkpoint-2200/special_tokens_map.json +0 -6
  20. checkpoint-2200/tokenizer.model +0 -3
  21. checkpoint-2200/tokenizer_config.json +0 -35
  22. checkpoint-2200/trainer_state.json +0 -0
  23. checkpoint-2200/training_args.bin +0 -3
  24. checkpoint-2400/README.md +0 -20
  25. checkpoint-2400/adapter_config.json +0 -26
  26. checkpoint-2400/adapter_model.bin +0 -3
  27. checkpoint-2400/added_tokens.json +0 -3
  28. checkpoint-2400/optimizer.pt +0 -3
  29. checkpoint-2400/scheduler.pt +0 -3
  30. checkpoint-2400/special_tokens_map.json +0 -6
  31. checkpoint-2400/tokenizer.model +0 -3
  32. checkpoint-2400/tokenizer_config.json +0 -35
  33. checkpoint-2400/trainer_state.json +0 -0
  34. checkpoint-2600/README.md +0 -20
  35. checkpoint-2600/adapter_config.json +0 -26
  36. checkpoint-2600/adapter_model.bin +0 -3
  37. checkpoint-2600/added_tokens.json +0 -3
  38. checkpoint-2600/optimizer.pt +0 -3
  39. checkpoint-2600/rng_state.pth +0 -3
  40. checkpoint-2600/scheduler.pt +0 -3
  41. checkpoint-2600/special_tokens_map.json +0 -6
  42. checkpoint-2600/tokenizer.model +0 -3
  43. checkpoint-2600/tokenizer_config.json +0 -35
  44. checkpoint-2600/trainer_state.json +0 -0
  45. checkpoint-2600/training_args.bin +0 -3
  46. checkpoint-2800/README.md +0 -20
  47. checkpoint-2800/adapter_config.json +0 -26
  48. checkpoint-2800/adapter_model.bin +0 -3
  49. checkpoint-2800/added_tokens.json +0 -3
  50. checkpoint-2800/optimizer.pt +0 -3
adapter_config.json CHANGED
@@ -14,13 +14,13 @@
14
  "r": 64,
15
  "revision": null,
16
  "target_modules": [
17
- "k_proj",
18
- "down_proj",
19
- "up_proj",
20
- "o_proj",
21
  "v_proj",
 
 
22
  "gate_proj",
23
- "q_proj"
 
 
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
 
14
  "r": 64,
15
  "revision": null,
16
  "target_modules": [
 
 
 
 
17
  "v_proj",
18
+ "down_proj",
19
+ "q_proj",
20
  "gate_proj",
21
+ "o_proj",
22
+ "up_proj",
23
+ "k_proj"
24
  ],
25
  "task_type": "CAUSAL_LM"
26
  }
adapter_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5785e99f09d371ee2dfcf2a1379bc4856ae0eff4a8f0f90219dd0ddae67439e6
3
  size 871609293
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8c7b7177ebf043527303efc179b203f643a96dcbc5d00d10d809a5b270f2b361
3
  size 871609293
all_results.json CHANGED
@@ -1,11 +1,11 @@
1
  {
2
- "epoch": 0.03,
3
- "eval_loss": 6.423073768615723,
4
- "eval_runtime": 22.3351,
5
- "eval_samples_per_second": 2.239,
6
- "eval_steps_per_second": 1.119,
7
- "train_loss": 1.5118552861401908,
8
- "train_runtime": 2842.6735,
9
- "train_samples_per_second": 10.553,
10
- "train_steps_per_second": 10.553
11
  }
 
1
  {
2
+ "epoch": 0.04,
3
+ "eval_loss": 6.335043907165527,
4
+ "eval_runtime": 21.5795,
5
+ "eval_samples_per_second": 2.317,
6
+ "eval_steps_per_second": 1.159,
7
+ "train_loss": 1.2399261393149694,
8
+ "train_runtime": 2886.6567,
9
+ "train_samples_per_second": 10.393,
10
+ "train_steps_per_second": 10.393
11
  }
checkpoint-2000/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:ca7fae775be00cb7e472a75158d8ab72644b8579a83e290f3c7c2b2bc675e8dc
3
- size 871609293
 
 
 
 
checkpoint-2000/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:642bf4673b8142a63843a17e79e1f902522cc016a4c4d10c09a6183594d7f16a
3
- size 873873439
 
 
 
 
checkpoint-2000/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:b145ff169e72f737f06951054bbd14e171358b3bb7a8261a702439d3bfaed29b
3
- size 14511
 
 
 
 
checkpoint-2000/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:37938855094cecb443a20382ff199f051b8482dee28568306481bf327258d4cf
3
- size 627
 
 
 
 
checkpoint-2000/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-2000/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2493c95326c359fb00f88976162bc7966690beaaca22964b91c1db649a04988f
3
- size 6011
 
 
 
 
checkpoint-2200/README.md DELETED
@@ -1,20 +0,0 @@
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: True
16
- - bnb_4bit_compute_dtype: bfloat16
17
- ### Framework versions
18
-
19
-
20
- - PEFT 0.4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2200/adapter_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "auto_mapping": null,
3
- "base_model_name_or_path": "codellama/CodeLlama-34b-Python-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": 16.0,
11
- "lora_dropout": 0.1,
12
- "modules_to_save": null,
13
- "peft_type": "LORA",
14
- "r": 64,
15
- "revision": null,
16
- "target_modules": [
17
- "down_proj",
18
- "up_proj",
19
- "q_proj",
20
- "gate_proj",
21
- "o_proj",
22
- "v_proj",
23
- "k_proj"
24
- ],
25
- "task_type": "CAUSAL_LM"
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2200/adapter_model/adapter_model/README.md DELETED
@@ -1,80 +0,0 @@
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: True
16
- - bnb_4bit_compute_dtype: bfloat16
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: True
27
- - bnb_4bit_compute_dtype: bfloat16
28
-
29
- The following `bitsandbytes` quantization config was used during training:
30
- - load_in_8bit: False
31
- - load_in_4bit: True
32
- - llm_int8_threshold: 6.0
33
- - llm_int8_skip_modules: None
34
- - llm_int8_enable_fp32_cpu_offload: False
35
- - llm_int8_has_fp16_weight: False
36
- - bnb_4bit_quant_type: nf4
37
- - bnb_4bit_use_double_quant: True
38
- - bnb_4bit_compute_dtype: bfloat16
39
-
40
- The following `bitsandbytes` quantization config was used during training:
41
- - load_in_8bit: False
42
- - load_in_4bit: True
43
- - llm_int8_threshold: 6.0
44
- - llm_int8_skip_modules: None
45
- - llm_int8_enable_fp32_cpu_offload: False
46
- - llm_int8_has_fp16_weight: False
47
- - bnb_4bit_quant_type: nf4
48
- - bnb_4bit_use_double_quant: True
49
- - bnb_4bit_compute_dtype: bfloat16
50
-
51
- The following `bitsandbytes` quantization config was used during training:
52
- - load_in_8bit: False
53
- - load_in_4bit: True
54
- - llm_int8_threshold: 6.0
55
- - llm_int8_skip_modules: None
56
- - llm_int8_enable_fp32_cpu_offload: False
57
- - llm_int8_has_fp16_weight: False
58
- - bnb_4bit_quant_type: nf4
59
- - bnb_4bit_use_double_quant: True
60
- - bnb_4bit_compute_dtype: bfloat16
61
-
62
- The following `bitsandbytes` quantization config was used during training:
63
- - load_in_8bit: False
64
- - load_in_4bit: True
65
- - llm_int8_threshold: 6.0
66
- - llm_int8_skip_modules: None
67
- - llm_int8_enable_fp32_cpu_offload: False
68
- - llm_int8_has_fp16_weight: False
69
- - bnb_4bit_quant_type: nf4
70
- - bnb_4bit_use_double_quant: True
71
- - bnb_4bit_compute_dtype: bfloat16
72
- ### Framework versions
73
-
74
- - PEFT 0.4.0
75
- - PEFT 0.4.0
76
- - PEFT 0.4.0
77
- - PEFT 0.4.0
78
- - PEFT 0.4.0
79
-
80
- - PEFT 0.4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2200/adapter_model/adapter_model/adapter_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "auto_mapping": null,
3
- "base_model_name_or_path": "codellama/CodeLlama-34b-Python-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": 16.0,
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
- "o_proj",
19
- "k_proj",
20
- "gate_proj",
21
- "down_proj",
22
- "v_proj",
23
- "up_proj"
24
- ],
25
- "task_type": "CAUSAL_LM"
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2200/adapter_model/adapter_model/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:8300649a3cb3257506bd84a299764cdbbadb65ebf8c06576deb99c0b813044d3
3
- size 871609293
 
 
 
 
checkpoint-2200/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "[PAD]": 32000
3
- }
 
 
 
 
checkpoint-2200/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:782517fcce8ab1d24acc99ecafbd35461a60b67479b118a71921b13139c6347d
3
- size 873873439
 
 
 
 
checkpoint-2200/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f1fc4b7401fd0efa3a43831682cea6e692f653e982f2004f30e952d611992a90
3
- size 14511
 
 
 
 
checkpoint-2200/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:092acf798ddb85605a10300c434ed87828e2ee5daceee07a115b3c1278ee199e
3
- size 627
 
 
 
 
checkpoint-2200/special_tokens_map.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "<unk>"
6
- }
 
 
 
 
 
 
 
checkpoint-2200/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
checkpoint-2200/tokenizer_config.json DELETED
@@ -1,35 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "legacy": null,
22
- "model_max_length": 1000000000000000019884624838656,
23
- "pad_token": null,
24
- "padding_side": "right",
25
- "sp_model_kwargs": {},
26
- "tokenizer_class": "LlamaTokenizer",
27
- "unk_token": {
28
- "__type": "AddedToken",
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2200/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-2200/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2493c95326c359fb00f88976162bc7966690beaaca22964b91c1db649a04988f
3
- size 6011
 
 
 
 
checkpoint-2400/README.md DELETED
@@ -1,20 +0,0 @@
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: True
16
- - bnb_4bit_compute_dtype: bfloat16
17
- ### Framework versions
18
-
19
-
20
- - PEFT 0.4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2400/adapter_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "auto_mapping": null,
3
- "base_model_name_or_path": "codellama/CodeLlama-34b-Python-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": 16.0,
11
- "lora_dropout": 0.1,
12
- "modules_to_save": null,
13
- "peft_type": "LORA",
14
- "r": 64,
15
- "revision": null,
16
- "target_modules": [
17
- "down_proj",
18
- "up_proj",
19
- "q_proj",
20
- "gate_proj",
21
- "o_proj",
22
- "v_proj",
23
- "k_proj"
24
- ],
25
- "task_type": "CAUSAL_LM"
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2400/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:23824721820d37d6fe44fee9306d0e71a5826aebaf3eb2f970cab6872288b55a
3
- size 871609293
 
 
 
 
checkpoint-2400/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "[PAD]": 32000
3
- }
 
 
 
 
checkpoint-2400/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:0e124e64b77531d5f98edc3d5e51a56228b9c1bccf94fbc775628676a06fb976
3
- size 873873439
 
 
 
 
checkpoint-2400/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cf2acca1029437820e5d9cd9f7ccc6efd7468e812d0f38078e4079d268163c1
3
- size 627
 
 
 
 
checkpoint-2400/special_tokens_map.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "<unk>"
6
- }
 
 
 
 
 
 
 
checkpoint-2400/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
checkpoint-2400/tokenizer_config.json DELETED
@@ -1,35 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "legacy": null,
22
- "model_max_length": 1000000000000000019884624838656,
23
- "pad_token": null,
24
- "padding_side": "right",
25
- "sp_model_kwargs": {},
26
- "tokenizer_class": "LlamaTokenizer",
27
- "unk_token": {
28
- "__type": "AddedToken",
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2400/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-2600/README.md DELETED
@@ -1,20 +0,0 @@
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: True
16
- - bnb_4bit_compute_dtype: bfloat16
17
- ### Framework versions
18
-
19
-
20
- - PEFT 0.4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2600/adapter_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "auto_mapping": null,
3
- "base_model_name_or_path": "codellama/CodeLlama-34b-Python-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": 16.0,
11
- "lora_dropout": 0.1,
12
- "modules_to_save": null,
13
- "peft_type": "LORA",
14
- "r": 64,
15
- "revision": null,
16
- "target_modules": [
17
- "down_proj",
18
- "up_proj",
19
- "q_proj",
20
- "gate_proj",
21
- "o_proj",
22
- "v_proj",
23
- "k_proj"
24
- ],
25
- "task_type": "CAUSAL_LM"
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2600/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5c5c24c518432dc2a92978262de3604250bfd1be5847484ad75d2cbbe9a78b0
3
- size 871609293
 
 
 
 
checkpoint-2600/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "[PAD]": 32000
3
- }
 
 
 
 
checkpoint-2600/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e399286bddf29fae9880c0806ad5c3a545182e5671745d250d09887d0e6488e1
3
- size 873873439
 
 
 
 
checkpoint-2600/rng_state.pth DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:93c31a76c4022e28a921261e573692176e89a3efea64621cc9f63e1fc4fe3e45
3
- size 14511
 
 
 
 
checkpoint-2600/scheduler.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:e1d4f35a64d8e8e44f3eee69a5887f0a83a9d2c1424e925461278b8523e04e0f
3
- size 627
 
 
 
 
checkpoint-2600/special_tokens_map.json DELETED
@@ -1,6 +0,0 @@
1
- {
2
- "bos_token": "<s>",
3
- "eos_token": "</s>",
4
- "pad_token": "[PAD]",
5
- "unk_token": "<unk>"
6
- }
 
 
 
 
 
 
 
checkpoint-2600/tokenizer.model DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
- size 499723
 
 
 
 
checkpoint-2600/tokenizer_config.json DELETED
@@ -1,35 +0,0 @@
1
- {
2
- "add_bos_token": true,
3
- "add_eos_token": false,
4
- "bos_token": {
5
- "__type": "AddedToken",
6
- "content": "<s>",
7
- "lstrip": false,
8
- "normalized": true,
9
- "rstrip": false,
10
- "single_word": false
11
- },
12
- "clean_up_tokenization_spaces": false,
13
- "eos_token": {
14
- "__type": "AddedToken",
15
- "content": "</s>",
16
- "lstrip": false,
17
- "normalized": true,
18
- "rstrip": false,
19
- "single_word": false
20
- },
21
- "legacy": null,
22
- "model_max_length": 1000000000000000019884624838656,
23
- "pad_token": null,
24
- "padding_side": "right",
25
- "sp_model_kwargs": {},
26
- "tokenizer_class": "LlamaTokenizer",
27
- "unk_token": {
28
- "__type": "AddedToken",
29
- "content": "<unk>",
30
- "lstrip": false,
31
- "normalized": true,
32
- "rstrip": false,
33
- "single_word": false
34
- }
35
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2600/trainer_state.json DELETED
The diff for this file is too large to render. See raw diff
 
checkpoint-2600/training_args.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:2493c95326c359fb00f88976162bc7966690beaaca22964b91c1db649a04988f
3
- size 6011
 
 
 
 
checkpoint-2800/README.md DELETED
@@ -1,20 +0,0 @@
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: True
16
- - bnb_4bit_compute_dtype: bfloat16
17
- ### Framework versions
18
-
19
-
20
- - PEFT 0.4.0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2800/adapter_config.json DELETED
@@ -1,26 +0,0 @@
1
- {
2
- "auto_mapping": null,
3
- "base_model_name_or_path": "codellama/CodeLlama-34b-Python-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": 16.0,
11
- "lora_dropout": 0.1,
12
- "modules_to_save": null,
13
- "peft_type": "LORA",
14
- "r": 64,
15
- "revision": null,
16
- "target_modules": [
17
- "down_proj",
18
- "up_proj",
19
- "q_proj",
20
- "gate_proj",
21
- "o_proj",
22
- "v_proj",
23
- "k_proj"
24
- ],
25
- "task_type": "CAUSAL_LM"
26
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
checkpoint-2800/adapter_model.bin DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:f225cf9428443345e7ae8d074f6c79ee61a6dba536cd308e438af491df396828
3
- size 871609293
 
 
 
 
checkpoint-2800/added_tokens.json DELETED
@@ -1,3 +0,0 @@
1
- {
2
- "[PAD]": 32000
3
- }
 
 
 
 
checkpoint-2800/optimizer.pt DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:79fcc33a32a377baf845df2980411ec64b9e5c19908b53d5583187466dcc4980
3
- size 873873439