sambitsingha commited on
Commit
544f8e9
·
verified ·
1 Parent(s): 10cc4b3

Upload fine-tuned Mr.Bully chatbot model

Browse files
Files changed (45) hide show
  1. checkpoint-100/chat_template.jinja +1 -0
  2. checkpoint-100/config.json +37 -0
  3. checkpoint-100/generation_config.json +6 -0
  4. checkpoint-100/merges.txt +0 -0
  5. checkpoint-100/model.safetensors +3 -0
  6. checkpoint-100/optimizer.pt +3 -0
  7. checkpoint-100/rng_state.pth +3 -0
  8. checkpoint-100/scaler.pt +3 -0
  9. checkpoint-100/scheduler.pt +3 -0
  10. checkpoint-100/special_tokens_map.json +24 -0
  11. checkpoint-100/tokenizer.json +0 -0
  12. checkpoint-100/tokenizer_config.json +23 -0
  13. checkpoint-100/trainer_state.json +129 -0
  14. checkpoint-100/training_args.bin +3 -0
  15. checkpoint-100/vocab.json +0 -0
  16. checkpoint-150/chat_template.jinja +1 -0
  17. checkpoint-150/config.json +37 -0
  18. checkpoint-150/generation_config.json +6 -0
  19. checkpoint-150/merges.txt +0 -0
  20. checkpoint-150/model.safetensors +3 -0
  21. checkpoint-150/optimizer.pt +3 -0
  22. checkpoint-150/rng_state.pth +3 -0
  23. checkpoint-150/scaler.pt +3 -0
  24. checkpoint-150/scheduler.pt +3 -0
  25. checkpoint-150/special_tokens_map.json +24 -0
  26. checkpoint-150/tokenizer.json +0 -0
  27. checkpoint-150/tokenizer_config.json +23 -0
  28. checkpoint-150/trainer_state.json +172 -0
  29. checkpoint-150/training_args.bin +3 -0
  30. checkpoint-150/vocab.json +0 -0
  31. checkpoint-200/chat_template.jinja +1 -0
  32. checkpoint-200/config.json +37 -0
  33. checkpoint-200/generation_config.json +6 -0
  34. checkpoint-200/merges.txt +0 -0
  35. checkpoint-200/model.safetensors +3 -0
  36. checkpoint-200/optimizer.pt +3 -0
  37. checkpoint-200/rng_state.pth +3 -0
  38. checkpoint-200/scaler.pt +3 -0
  39. checkpoint-200/scheduler.pt +3 -0
  40. checkpoint-200/special_tokens_map.json +24 -0
  41. checkpoint-200/tokenizer.json +0 -0
  42. checkpoint-200/tokenizer_config.json +23 -0
  43. checkpoint-200/trainer_state.json +215 -0
  44. checkpoint-200/training_args.bin +3 -0
  45. checkpoint-200/vocab.json +0 -0
checkpoint-100/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}
checkpoint-100/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 1024,
15
+ "n_head": 16,
16
+ "n_inner": null,
17
+ "n_layer": 24,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "conversational": {
30
+ "max_length": 1000
31
+ }
32
+ },
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.52.4",
35
+ "use_cache": true,
36
+ "vocab_size": 50257
37
+ }
checkpoint-100/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.52.4"
6
+ }
checkpoint-100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-100/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:57516a0793659476a7d76c2a5132b8e19d5545320dfe602b6b1ee8c890bf5127
3
+ size 1419322880
checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e973f6de8c0717270c643ab8d63f7c52335e38baed0e8d767aebdde453540bb7
3
+ size 2838829707
checkpoint-100/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a3916f36d462679f5a07b11856084a753a447301862ae2935e7364725d64148
3
+ size 14645
checkpoint-100/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:764d17dd4e070ebbd282c3e8cfa48c6fd4e8cdb343ba9f46b935824668f3af39
3
+ size 1383
checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ec0f9336a0a6fa0df1d9bea9374060599904f28351c431f3683bf8965133d53
3
+ size 1465
checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
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_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,129 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 100,
3
+ "best_metric": 1.5087827444076538,
4
+ "best_model_checkpoint": "./sambit-finetuned-model\\checkpoint-100",
5
+ "epoch": 2.511182108626198,
6
+ "eval_steps": 50,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.25559105431309903,
14
+ "grad_norm": 5.788098335266113,
15
+ "learning_rate": 1.2903225806451613e-05,
16
+ "loss": 8.2523,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.5111821086261981,
21
+ "grad_norm": 4.397591590881348,
22
+ "learning_rate": 2.9032258064516133e-05,
23
+ "loss": 6.5314,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7667731629392971,
28
+ "grad_norm": 4.693469524383545,
29
+ "learning_rate": 4.516129032258064e-05,
30
+ "loss": 4.2212,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "grad_norm": 14.251598358154297,
36
+ "learning_rate": 4.792899408284024e-05,
37
+ "loss": 2.7144,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.255591054313099,
42
+ "grad_norm": 2.6998775005340576,
43
+ "learning_rate": 4.4970414201183434e-05,
44
+ "loss": 2.1756,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.255591054313099,
49
+ "eval_loss": 2.1117615699768066,
50
+ "eval_runtime": 16.0334,
51
+ "eval_samples_per_second": 4.927,
52
+ "eval_steps_per_second": 4.927,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.511182108626198,
57
+ "grad_norm": 2.905092477798462,
58
+ "learning_rate": 4.201183431952663e-05,
59
+ "loss": 1.8235,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.766773162939297,
64
+ "grad_norm": 2.605362892150879,
65
+ "learning_rate": 3.905325443786982e-05,
66
+ "loss": 1.8472,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "grad_norm": 7.906912326812744,
72
+ "learning_rate": 3.609467455621302e-05,
73
+ "loss": 1.6125,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 2.255591054313099,
78
+ "grad_norm": 2.436338186264038,
79
+ "learning_rate": 3.3136094674556215e-05,
80
+ "loss": 1.4259,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 2.511182108626198,
85
+ "grad_norm": 3.1060962677001953,
86
+ "learning_rate": 3.017751479289941e-05,
87
+ "loss": 1.2312,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 2.511182108626198,
92
+ "eval_loss": 1.5087827444076538,
93
+ "eval_runtime": 16.0182,
94
+ "eval_samples_per_second": 4.932,
95
+ "eval_steps_per_second": 4.932,
96
+ "step": 100
97
+ }
98
+ ],
99
+ "logging_steps": 10,
100
+ "max_steps": 200,
101
+ "num_input_tokens_seen": 0,
102
+ "num_train_epochs": 5,
103
+ "save_steps": 50,
104
+ "stateful_callbacks": {
105
+ "EarlyStoppingCallback": {
106
+ "args": {
107
+ "early_stopping_patience": 3,
108
+ "early_stopping_threshold": 0.0
109
+ },
110
+ "attributes": {
111
+ "early_stopping_patience_counter": 0
112
+ }
113
+ },
114
+ "TrainerControl": {
115
+ "args": {
116
+ "should_epoch_stop": false,
117
+ "should_evaluate": false,
118
+ "should_log": false,
119
+ "should_save": true,
120
+ "should_training_stop": false
121
+ },
122
+ "attributes": {}
123
+ }
124
+ },
125
+ "total_flos": 68433632428032.0,
126
+ "train_batch_size": 1,
127
+ "trial_name": null,
128
+ "trial_params": null
129
+ }
checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981f5d17eb15f0405c1828809cb51d3b9d50ab094e9791745ac2661a6419d6a7
3
+ size 5649
checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}
checkpoint-150/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 1024,
15
+ "n_head": 16,
16
+ "n_inner": null,
17
+ "n_layer": 24,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "conversational": {
30
+ "max_length": 1000
31
+ }
32
+ },
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.52.4",
35
+ "use_cache": true,
36
+ "vocab_size": 50257
37
+ }
checkpoint-150/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.52.4"
6
+ }
checkpoint-150/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ad513e75d67f555c65f84f2025f196c12106cee378b4bd0abe39804667d61ed5
3
+ size 1419322880
checkpoint-150/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816d52b0da5b1b1cd82a7b01b4c33da167b954733f172078dd0f2f0f265352de
3
+ size 2838829707
checkpoint-150/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dc1e005e1c01cd986c6b271798fe0067356df13083c8ca62cc16820511255c77
3
+ size 14645
checkpoint-150/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba74cd06f5329d289f9094ed92217a11711aded322f4beca5e274d03a2607521
3
+ size 1383
checkpoint-150/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f20618700eab268cc9d3979c906c7974ae853ba6c8c32fd2ce726ce79332cce3
3
+ size 1465
checkpoint-150/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-150/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-150/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
checkpoint-150/trainer_state.json ADDED
@@ -0,0 +1,172 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 150,
3
+ "best_metric": 1.2683324813842773,
4
+ "best_model_checkpoint": "./sambit-finetuned-model\\checkpoint-150",
5
+ "epoch": 3.7667731629392973,
6
+ "eval_steps": 50,
7
+ "global_step": 150,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.25559105431309903,
14
+ "grad_norm": 5.788098335266113,
15
+ "learning_rate": 1.2903225806451613e-05,
16
+ "loss": 8.2523,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.5111821086261981,
21
+ "grad_norm": 4.397591590881348,
22
+ "learning_rate": 2.9032258064516133e-05,
23
+ "loss": 6.5314,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7667731629392971,
28
+ "grad_norm": 4.693469524383545,
29
+ "learning_rate": 4.516129032258064e-05,
30
+ "loss": 4.2212,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "grad_norm": 14.251598358154297,
36
+ "learning_rate": 4.792899408284024e-05,
37
+ "loss": 2.7144,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.255591054313099,
42
+ "grad_norm": 2.6998775005340576,
43
+ "learning_rate": 4.4970414201183434e-05,
44
+ "loss": 2.1756,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.255591054313099,
49
+ "eval_loss": 2.1117615699768066,
50
+ "eval_runtime": 16.0334,
51
+ "eval_samples_per_second": 4.927,
52
+ "eval_steps_per_second": 4.927,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.511182108626198,
57
+ "grad_norm": 2.905092477798462,
58
+ "learning_rate": 4.201183431952663e-05,
59
+ "loss": 1.8235,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.766773162939297,
64
+ "grad_norm": 2.605362892150879,
65
+ "learning_rate": 3.905325443786982e-05,
66
+ "loss": 1.8472,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "grad_norm": 7.906912326812744,
72
+ "learning_rate": 3.609467455621302e-05,
73
+ "loss": 1.6125,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 2.255591054313099,
78
+ "grad_norm": 2.436338186264038,
79
+ "learning_rate": 3.3136094674556215e-05,
80
+ "loss": 1.4259,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 2.511182108626198,
85
+ "grad_norm": 3.1060962677001953,
86
+ "learning_rate": 3.017751479289941e-05,
87
+ "loss": 1.2312,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 2.511182108626198,
92
+ "eval_loss": 1.5087827444076538,
93
+ "eval_runtime": 16.0182,
94
+ "eval_samples_per_second": 4.932,
95
+ "eval_steps_per_second": 4.932,
96
+ "step": 100
97
+ },
98
+ {
99
+ "epoch": 2.7667731629392973,
100
+ "grad_norm": 2.785402536392212,
101
+ "learning_rate": 2.7218934911242606e-05,
102
+ "loss": 1.1941,
103
+ "step": 110
104
+ },
105
+ {
106
+ "epoch": 3.0,
107
+ "grad_norm": 8.138482093811035,
108
+ "learning_rate": 2.42603550295858e-05,
109
+ "loss": 1.2012,
110
+ "step": 120
111
+ },
112
+ {
113
+ "epoch": 3.255591054313099,
114
+ "grad_norm": 3.094937562942505,
115
+ "learning_rate": 2.1301775147928997e-05,
116
+ "loss": 1.0695,
117
+ "step": 130
118
+ },
119
+ {
120
+ "epoch": 3.511182108626198,
121
+ "grad_norm": 2.8744637966156006,
122
+ "learning_rate": 1.834319526627219e-05,
123
+ "loss": 0.9515,
124
+ "step": 140
125
+ },
126
+ {
127
+ "epoch": 3.7667731629392973,
128
+ "grad_norm": 3.282501220703125,
129
+ "learning_rate": 1.5384615384615387e-05,
130
+ "loss": 0.9726,
131
+ "step": 150
132
+ },
133
+ {
134
+ "epoch": 3.7667731629392973,
135
+ "eval_loss": 1.2683324813842773,
136
+ "eval_runtime": 16.0056,
137
+ "eval_samples_per_second": 4.936,
138
+ "eval_steps_per_second": 4.936,
139
+ "step": 150
140
+ }
141
+ ],
142
+ "logging_steps": 10,
143
+ "max_steps": 200,
144
+ "num_input_tokens_seen": 0,
145
+ "num_train_epochs": 5,
146
+ "save_steps": 50,
147
+ "stateful_callbacks": {
148
+ "EarlyStoppingCallback": {
149
+ "args": {
150
+ "early_stopping_patience": 3,
151
+ "early_stopping_threshold": 0.0
152
+ },
153
+ "attributes": {
154
+ "early_stopping_patience_counter": 0
155
+ }
156
+ },
157
+ "TrainerControl": {
158
+ "args": {
159
+ "should_epoch_stop": false,
160
+ "should_evaluate": false,
161
+ "should_log": false,
162
+ "should_save": true,
163
+ "should_training_stop": false
164
+ },
165
+ "attributes": {}
166
+ }
167
+ },
168
+ "total_flos": 102650448642048.0,
169
+ "train_batch_size": 1,
170
+ "trial_name": null,
171
+ "trial_params": null
172
+ }
checkpoint-150/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981f5d17eb15f0405c1828809cb51d3b9d50ab094e9791745ac2661a6419d6a7
3
+ size 5649
checkpoint-150/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/chat_template.jinja ADDED
@@ -0,0 +1 @@
 
 
1
+ {% for message in messages %}{{ message.content }}{{ eos_token }}{% endfor %}
checkpoint-200/config.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "activation_function": "gelu_new",
3
+ "architectures": [
4
+ "GPT2LMHeadModel"
5
+ ],
6
+ "attn_pdrop": 0.1,
7
+ "bos_token_id": 50256,
8
+ "embd_pdrop": 0.1,
9
+ "eos_token_id": 50256,
10
+ "initializer_range": 0.02,
11
+ "layer_norm_epsilon": 1e-05,
12
+ "model_type": "gpt2",
13
+ "n_ctx": 1024,
14
+ "n_embd": 1024,
15
+ "n_head": 16,
16
+ "n_inner": null,
17
+ "n_layer": 24,
18
+ "n_positions": 1024,
19
+ "reorder_and_upcast_attn": false,
20
+ "resid_pdrop": 0.1,
21
+ "scale_attn_by_inverse_layer_idx": false,
22
+ "scale_attn_weights": true,
23
+ "summary_activation": null,
24
+ "summary_first_dropout": 0.1,
25
+ "summary_proj_to_labels": true,
26
+ "summary_type": "cls_index",
27
+ "summary_use_proj": true,
28
+ "task_specific_params": {
29
+ "conversational": {
30
+ "max_length": 1000
31
+ }
32
+ },
33
+ "torch_dtype": "float32",
34
+ "transformers_version": "4.52.4",
35
+ "use_cache": true,
36
+ "vocab_size": 50257
37
+ }
checkpoint-200/generation_config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 50256,
4
+ "eos_token_id": 50256,
5
+ "transformers_version": "4.52.4"
6
+ }
checkpoint-200/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04450db790fec7db93d8265202b6038374157a69282609e2a6a91f92d687571
3
+ size 1419322880
checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38b201aaf3389ece2e6f13781074e8466162cad2a42c15d358b911cccb53a5a0
3
+ size 2838829707
checkpoint-200/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ccb9fc4ea26244e1248a10fd516b70b0aa873869b2413d3737ae2b376d547e5a
3
+ size 14645
checkpoint-200/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b02095b6537db94208a875b9c1e539d1e086b4529b03ff6f22a36ddd29827f
3
+ size 1383
checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9a613502b3af7a9ce322ebc8895c54cffa72acac822baccebc0e449a0d72848e
3
+ size 1465
checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,24 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<|endoftext|>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "<|endoftext|>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": "<|endoftext|>",
17
+ "unk_token": {
18
+ "content": "<|endoftext|>",
19
+ "lstrip": false,
20
+ "normalized": true,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ }
24
+ }
checkpoint-200/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "50256": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ }
13
+ },
14
+ "bos_token": "<|endoftext|>",
15
+ "clean_up_tokenization_spaces": true,
16
+ "eos_token": "<|endoftext|>",
17
+ "errors": "replace",
18
+ "extra_special_tokens": {},
19
+ "model_max_length": 1024,
20
+ "pad_token": "<|endoftext|>",
21
+ "tokenizer_class": "GPT2Tokenizer",
22
+ "unk_token": "<|endoftext|>"
23
+ }
checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,215 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": 200,
3
+ "best_metric": 1.1922019720077515,
4
+ "best_model_checkpoint": "./sambit-finetuned-model\\checkpoint-200",
5
+ "epoch": 5.0,
6
+ "eval_steps": 50,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "epoch": 0.25559105431309903,
14
+ "grad_norm": 5.788098335266113,
15
+ "learning_rate": 1.2903225806451613e-05,
16
+ "loss": 8.2523,
17
+ "step": 10
18
+ },
19
+ {
20
+ "epoch": 0.5111821086261981,
21
+ "grad_norm": 4.397591590881348,
22
+ "learning_rate": 2.9032258064516133e-05,
23
+ "loss": 6.5314,
24
+ "step": 20
25
+ },
26
+ {
27
+ "epoch": 0.7667731629392971,
28
+ "grad_norm": 4.693469524383545,
29
+ "learning_rate": 4.516129032258064e-05,
30
+ "loss": 4.2212,
31
+ "step": 30
32
+ },
33
+ {
34
+ "epoch": 1.0,
35
+ "grad_norm": 14.251598358154297,
36
+ "learning_rate": 4.792899408284024e-05,
37
+ "loss": 2.7144,
38
+ "step": 40
39
+ },
40
+ {
41
+ "epoch": 1.255591054313099,
42
+ "grad_norm": 2.6998775005340576,
43
+ "learning_rate": 4.4970414201183434e-05,
44
+ "loss": 2.1756,
45
+ "step": 50
46
+ },
47
+ {
48
+ "epoch": 1.255591054313099,
49
+ "eval_loss": 2.1117615699768066,
50
+ "eval_runtime": 16.0334,
51
+ "eval_samples_per_second": 4.927,
52
+ "eval_steps_per_second": 4.927,
53
+ "step": 50
54
+ },
55
+ {
56
+ "epoch": 1.511182108626198,
57
+ "grad_norm": 2.905092477798462,
58
+ "learning_rate": 4.201183431952663e-05,
59
+ "loss": 1.8235,
60
+ "step": 60
61
+ },
62
+ {
63
+ "epoch": 1.766773162939297,
64
+ "grad_norm": 2.605362892150879,
65
+ "learning_rate": 3.905325443786982e-05,
66
+ "loss": 1.8472,
67
+ "step": 70
68
+ },
69
+ {
70
+ "epoch": 2.0,
71
+ "grad_norm": 7.906912326812744,
72
+ "learning_rate": 3.609467455621302e-05,
73
+ "loss": 1.6125,
74
+ "step": 80
75
+ },
76
+ {
77
+ "epoch": 2.255591054313099,
78
+ "grad_norm": 2.436338186264038,
79
+ "learning_rate": 3.3136094674556215e-05,
80
+ "loss": 1.4259,
81
+ "step": 90
82
+ },
83
+ {
84
+ "epoch": 2.511182108626198,
85
+ "grad_norm": 3.1060962677001953,
86
+ "learning_rate": 3.017751479289941e-05,
87
+ "loss": 1.2312,
88
+ "step": 100
89
+ },
90
+ {
91
+ "epoch": 2.511182108626198,
92
+ "eval_loss": 1.5087827444076538,
93
+ "eval_runtime": 16.0182,
94
+ "eval_samples_per_second": 4.932,
95
+ "eval_steps_per_second": 4.932,
96
+ "step": 100
97
+ },
98
+ {
99
+ "epoch": 2.7667731629392973,
100
+ "grad_norm": 2.785402536392212,
101
+ "learning_rate": 2.7218934911242606e-05,
102
+ "loss": 1.1941,
103
+ "step": 110
104
+ },
105
+ {
106
+ "epoch": 3.0,
107
+ "grad_norm": 8.138482093811035,
108
+ "learning_rate": 2.42603550295858e-05,
109
+ "loss": 1.2012,
110
+ "step": 120
111
+ },
112
+ {
113
+ "epoch": 3.255591054313099,
114
+ "grad_norm": 3.094937562942505,
115
+ "learning_rate": 2.1301775147928997e-05,
116
+ "loss": 1.0695,
117
+ "step": 130
118
+ },
119
+ {
120
+ "epoch": 3.511182108626198,
121
+ "grad_norm": 2.8744637966156006,
122
+ "learning_rate": 1.834319526627219e-05,
123
+ "loss": 0.9515,
124
+ "step": 140
125
+ },
126
+ {
127
+ "epoch": 3.7667731629392973,
128
+ "grad_norm": 3.282501220703125,
129
+ "learning_rate": 1.5384615384615387e-05,
130
+ "loss": 0.9726,
131
+ "step": 150
132
+ },
133
+ {
134
+ "epoch": 3.7667731629392973,
135
+ "eval_loss": 1.2683324813842773,
136
+ "eval_runtime": 16.0056,
137
+ "eval_samples_per_second": 4.936,
138
+ "eval_steps_per_second": 4.936,
139
+ "step": 150
140
+ },
141
+ {
142
+ "epoch": 4.0,
143
+ "grad_norm": 7.329628944396973,
144
+ "learning_rate": 1.242603550295858e-05,
145
+ "loss": 0.893,
146
+ "step": 160
147
+ },
148
+ {
149
+ "epoch": 4.255591054313099,
150
+ "grad_norm": 3.342067003250122,
151
+ "learning_rate": 9.467455621301776e-06,
152
+ "loss": 0.9067,
153
+ "step": 170
154
+ },
155
+ {
156
+ "epoch": 4.511182108626198,
157
+ "grad_norm": 3.3412821292877197,
158
+ "learning_rate": 6.5088757396449705e-06,
159
+ "loss": 0.7669,
160
+ "step": 180
161
+ },
162
+ {
163
+ "epoch": 4.766773162939297,
164
+ "grad_norm": 3.615647792816162,
165
+ "learning_rate": 3.550295857988166e-06,
166
+ "loss": 0.786,
167
+ "step": 190
168
+ },
169
+ {
170
+ "epoch": 5.0,
171
+ "grad_norm": 5.327714920043945,
172
+ "learning_rate": 5.91715976331361e-07,
173
+ "loss": 0.7928,
174
+ "step": 200
175
+ },
176
+ {
177
+ "epoch": 5.0,
178
+ "eval_loss": 1.1922019720077515,
179
+ "eval_runtime": 16.0469,
180
+ "eval_samples_per_second": 4.923,
181
+ "eval_steps_per_second": 4.923,
182
+ "step": 200
183
+ }
184
+ ],
185
+ "logging_steps": 10,
186
+ "max_steps": 200,
187
+ "num_input_tokens_seen": 0,
188
+ "num_train_epochs": 5,
189
+ "save_steps": 50,
190
+ "stateful_callbacks": {
191
+ "EarlyStoppingCallback": {
192
+ "args": {
193
+ "early_stopping_patience": 3,
194
+ "early_stopping_threshold": 0.0
195
+ },
196
+ "attributes": {
197
+ "early_stopping_patience_counter": 0
198
+ }
199
+ },
200
+ "TrainerControl": {
201
+ "args": {
202
+ "should_epoch_stop": false,
203
+ "should_evaluate": false,
204
+ "should_log": false,
205
+ "should_save": true,
206
+ "should_training_stop": true
207
+ },
208
+ "attributes": {}
209
+ }
210
+ },
211
+ "total_flos": 136257805025280.0,
212
+ "train_batch_size": 1,
213
+ "trial_name": null,
214
+ "trial_params": null
215
+ }
checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:981f5d17eb15f0405c1828809cb51d3b9d50ab094e9791745ac2661a6419d6a7
3
+ size 5649
checkpoint-200/vocab.json ADDED
The diff for this file is too large to render. See raw diff