Hugging Face's logo

mllm-dev
/
merge_diff_data_IMDB

Text Classification
Transformers
TensorBoard
Safetensors
gpt2
Model card Files
xet
Metrics Community
mllm-dev commited on
Commit
f24f7b4
·
verified ·
1 Parent(s): df2b8b7

Upload folder using huggingface_hub

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. checkpoint-131/config.json +49 -0
  2. checkpoint-131/merges.txt +0 -0
  3. checkpoint-131/model.safetensors +3 -0
  4. checkpoint-131/optimizer.pt +3 -0
  5. checkpoint-131/rng_state.pth +3 -0
  6. checkpoint-131/scheduler.pt +3 -0
  7. checkpoint-131/special_tokens_map.json +6 -0
  8. checkpoint-131/tokenizer.json +0 -0
  9. checkpoint-131/tokenizer_config.json +20 -0
  10. checkpoint-131/trainer_state.json +30 -0
  11. checkpoint-131/training_args.bin +3 -0
  12. checkpoint-131/vocab.json +0 -0
  13. checkpoint-262/config.json +49 -0
  14. checkpoint-262/merges.txt +0 -0
  15. checkpoint-262/model.safetensors +3 -0
  16. checkpoint-262/optimizer.pt +3 -0
  17. checkpoint-262/rng_state.pth +3 -0
  18. checkpoint-262/scheduler.pt +3 -0
  19. checkpoint-262/special_tokens_map.json +6 -0
  20. checkpoint-262/tokenizer.json +0 -0
  21. checkpoint-262/tokenizer_config.json +20 -0
  22. checkpoint-262/trainer_state.json +39 -0
  23. checkpoint-262/training_args.bin +3 -0
  24. checkpoint-262/vocab.json +0 -0
  25. checkpoint-393/config.json +49 -0
  26. checkpoint-393/merges.txt +0 -0
  27. checkpoint-393/model.safetensors +3 -0
  28. checkpoint-393/optimizer.pt +3 -0
  29. checkpoint-393/rng_state.pth +3 -0
  30. checkpoint-393/scheduler.pt +3 -0
  31. checkpoint-393/special_tokens_map.json +6 -0
  32. checkpoint-393/tokenizer.json +0 -0
  33. checkpoint-393/tokenizer_config.json +20 -0
  34. checkpoint-393/trainer_state.json +48 -0
  35. checkpoint-393/training_args.bin +3 -0
  36. checkpoint-393/vocab.json +0 -0
  37. checkpoint-524/config.json +49 -0
  38. checkpoint-524/merges.txt +0 -0
  39. checkpoint-524/model.safetensors +3 -0
  40. checkpoint-524/optimizer.pt +3 -0
  41. checkpoint-524/rng_state.pth +3 -0
  42. checkpoint-524/scheduler.pt +3 -0
  43. checkpoint-524/special_tokens_map.json +6 -0
  44. checkpoint-524/tokenizer.json +0 -0
  45. checkpoint-524/tokenizer_config.json +20 -0
  46. checkpoint-524/trainer_state.json +64 -0
  47. checkpoint-524/training_args.bin +3 -0
  48. checkpoint-524/vocab.json +0 -0
  49. checkpoint-655/config.json +49 -0
  50. checkpoint-655/merges.txt +0 -0
checkpoint-131/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-131/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-131/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dec8db03fe73371edc0e09ebd97b6b25811c3d5e255424a5728ebd9f9e1df7f6
3
+ size 497780432
checkpoint-131/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:096e6444f18161de1439657b9fe8d49a5986e00e0cb2f2cdd04cea3fd62c48e8
3
+ size 995654981
checkpoint-131/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c9004150f8ada6a696b04eca38f3bf564e32a89917445a2ffe3d5e018c98b585
3
+ size 14575
checkpoint-131/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ddfa3345d20aff7800d98b17c3f35f70e2b37641caca26ed6d2cc11437aded6
3
+ size 627
checkpoint-131/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-131/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-131/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-131/trainer_state.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.21770058572292328,
3
+ "best_model_checkpoint": "imdb_full/checkpoint-131",
4
+ "epoch": 1.0,
5
+ "eval_steps": 500,
6
+ "global_step": 131,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9204,
14
+ "eval_loss": 0.21770058572292328,
15
+ "eval_runtime": 78.2774,
16
+ "eval_samples_per_second": 319.377,
17
+ "eval_steps_per_second": 1.674,
18
+ "step": 131
19
+ }
20
+ ],
21
+ "logging_steps": 500,
22
+ "max_steps": 655,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 5,
25
+ "save_steps": 500,
26
+ "total_flos": 1.30648375296e+16,
27
+ "train_batch_size": 192,
28
+ "trial_name": null,
29
+ "trial_params": null
30
+ }
checkpoint-131/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44e052061640a12a1c68cc309380de7e456987041221f8c311c1538cf1561d2
3
+ size 4539
checkpoint-131/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-262/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-262/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-262/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e478bc15e007bb1c988f5604abebbc20faf9f56b660e1d1815eb0267e054286
3
+ size 497780432
checkpoint-262/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44e839bc4d38ec138fdad0307c0ada35b9d5d11e8d32d7a4ddc7e1538a0738e0
3
+ size 995654981
checkpoint-262/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d40edca14de5b4a30a989e4a774aff37f6e06a1e46148103de52936c6ed7874b
3
+ size 14575
checkpoint-262/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a2fad01f66d8c9b6b48a923b69fdbc3745a4a758206fb7214d9140234df6ab7c
3
+ size 627
checkpoint-262/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-262/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-262/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-262/trainer_state.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.19915565848350525,
3
+ "best_model_checkpoint": "imdb_full/checkpoint-262",
4
+ "epoch": 2.0,
5
+ "eval_steps": 500,
6
+ "global_step": 262,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9204,
14
+ "eval_loss": 0.21770058572292328,
15
+ "eval_runtime": 78.2774,
16
+ "eval_samples_per_second": 319.377,
17
+ "eval_steps_per_second": 1.674,
18
+ "step": 131
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.92204,
23
+ "eval_loss": 0.19915565848350525,
24
+ "eval_runtime": 78.1566,
25
+ "eval_samples_per_second": 319.871,
26
+ "eval_steps_per_second": 1.676,
27
+ "step": 262
28
+ }
29
+ ],
30
+ "logging_steps": 500,
31
+ "max_steps": 655,
32
+ "num_input_tokens_seen": 0,
33
+ "num_train_epochs": 5,
34
+ "save_steps": 500,
35
+ "total_flos": 2.61296750592e+16,
36
+ "train_batch_size": 192,
37
+ "trial_name": null,
38
+ "trial_params": null
39
+ }
checkpoint-262/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44e052061640a12a1c68cc309380de7e456987041221f8c311c1538cf1561d2
3
+ size 4539
checkpoint-262/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-393/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-393/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-393/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50230968ca29b09eebae846acf7a4281caaa9e62dafb7ae34d151e3534498c20
3
+ size 497780432
checkpoint-393/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b56aaf162459488ecf2d164ca92763ed5c07d9d0ded7b319cb187f159ba3be81
3
+ size 995654981
checkpoint-393/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9027bd1205a572d40b0333171e0692a8c2265f9ea47403ae3c412d873ee16064
3
+ size 14575
checkpoint-393/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:247e6c287fbd7e78eff360f31061e5471826f2b84cf356fba5dcb9844f00ba82
3
+ size 627
checkpoint-393/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-393/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-393/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-393/trainer_state.json ADDED
@@ -0,0 +1,48 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.1659126728773117,
3
+ "best_model_checkpoint": "imdb_full/checkpoint-393",
4
+ "epoch": 3.0,
5
+ "eval_steps": 500,
6
+ "global_step": 393,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9204,
14
+ "eval_loss": 0.21770058572292328,
15
+ "eval_runtime": 78.2774,
16
+ "eval_samples_per_second": 319.377,
17
+ "eval_steps_per_second": 1.674,
18
+ "step": 131
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.92204,
23
+ "eval_loss": 0.19915565848350525,
24
+ "eval_runtime": 78.1566,
25
+ "eval_samples_per_second": 319.871,
26
+ "eval_steps_per_second": 1.676,
27
+ "step": 262
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.93932,
32
+ "eval_loss": 0.1659126728773117,
33
+ "eval_runtime": 78.3631,
34
+ "eval_samples_per_second": 319.028,
35
+ "eval_steps_per_second": 1.672,
36
+ "step": 393
37
+ }
38
+ ],
39
+ "logging_steps": 500,
40
+ "max_steps": 655,
41
+ "num_input_tokens_seen": 0,
42
+ "num_train_epochs": 5,
43
+ "save_steps": 500,
44
+ "total_flos": 3.917961459125453e+16,
45
+ "train_batch_size": 192,
46
+ "trial_name": null,
47
+ "trial_params": null
48
+ }
checkpoint-393/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44e052061640a12a1c68cc309380de7e456987041221f8c311c1538cf1561d2
3
+ size 4539
checkpoint-393/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-524/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-524/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-524/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8649ab5dc3b752ee3d6981d4c0b12089ef230a56a528819eacd42393c8ef318
3
+ size 497780432
checkpoint-524/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ae63434f0ba9d6695aaa16b1678b6fe9f2be1e63a32a59990f8924519f8b3014
3
+ size 995654981
checkpoint-524/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8095c613c9533ba72a3ed7bcc837d9023f21db5bcb6041badf6c3403d3a5c9d
3
+ size 14575
checkpoint-524/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:38d86af8a89790751628f8f7e3e6e0ff6f1e0b43a39e6f38dd6c45ee28873ba6
3
+ size 627
checkpoint-524/special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|endoftext|>",
5
+ "unk_token": "<|endoftext|>"
6
+ }
checkpoint-524/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-524/tokenizer_config.json ADDED
@@ -0,0 +1,20 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "50256": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ }
12
+ },
13
+ "bos_token": "<|endoftext|>",
14
+ "clean_up_tokenization_spaces": true,
15
+ "eos_token": "<|endoftext|>",
16
+ "model_max_length": 1024,
17
+ "pad_token": "<|endoftext|>",
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-524/trainer_state.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": 0.15741272270679474,
3
+ "best_model_checkpoint": "imdb_full/checkpoint-524",
4
+ "epoch": 4.0,
5
+ "eval_steps": 500,
6
+ "global_step": 524,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 1.0,
13
+ "eval_accuracy": 0.9204,
14
+ "eval_loss": 0.21770058572292328,
15
+ "eval_runtime": 78.2774,
16
+ "eval_samples_per_second": 319.377,
17
+ "eval_steps_per_second": 1.674,
18
+ "step": 131
19
+ },
20
+ {
21
+ "epoch": 2.0,
22
+ "eval_accuracy": 0.92204,
23
+ "eval_loss": 0.19915565848350525,
24
+ "eval_runtime": 78.1566,
25
+ "eval_samples_per_second": 319.871,
26
+ "eval_steps_per_second": 1.676,
27
+ "step": 262
28
+ },
29
+ {
30
+ "epoch": 3.0,
31
+ "eval_accuracy": 0.93932,
32
+ "eval_loss": 0.1659126728773117,
33
+ "eval_runtime": 78.3631,
34
+ "eval_samples_per_second": 319.028,
35
+ "eval_steps_per_second": 1.672,
36
+ "step": 393
37
+ },
38
+ {
39
+ "epoch": 3.82,
40
+ "grad_norm": 2.5449366569519043,
41
+ "learning_rate": 1.4198473282442749e-05,
42
+ "loss": 0.1895,
43
+ "step": 500
44
+ },
45
+ {
46
+ "epoch": 4.0,
47
+ "eval_accuracy": 0.94728,
48
+ "eval_loss": 0.15741272270679474,
49
+ "eval_runtime": 78.2398,
50
+ "eval_samples_per_second": 319.53,
51
+ "eval_steps_per_second": 1.674,
52
+ "step": 524
53
+ }
54
+ ],
55
+ "logging_steps": 500,
56
+ "max_steps": 655,
57
+ "num_input_tokens_seen": 0,
58
+ "num_train_epochs": 5,
59
+ "save_steps": 500,
60
+ "total_flos": 5.22274025078784e+16,
61
+ "train_batch_size": 192,
62
+ "trial_name": null,
63
+ "trial_params": null
64
+ }
checkpoint-524/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44e052061640a12a1c68cc309380de7e456987041221f8c311c1538cf1561d2
3
+ size 4539
checkpoint-524/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-655/config.json ADDED
@@ -0,0 +1,49 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "openai-community/gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2ForSequenceClassification"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "id2label": {
12
+ "0": "NEGATIVE",
13
+ "1": "POSITIVE"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "NEGATIVE": 0,
18
+ "POSITIVE": 1
19
+ },
20
+ "layer_norm_epsilon": 1e-05,
21
+ "model_type": "gpt2",
22
+ "n_ctx": 1024,
23
+ "n_embd": 768,
24
+ "n_head": 12,
25
+ "n_inner": null,
26
+ "n_layer": 12,
27
+ "n_positions": 1024,
28
+ "pad_token_id": 50256,
29
+ "problem_type": "single_label_classification",
30
+ "reorder_and_upcast_attn": false,
31
+ "resid_pdrop": 0.1,
32
+ "scale_attn_by_inverse_layer_idx": false,
33
+ "scale_attn_weights": true,
34
+ "summary_activation": null,
35
+ "summary_first_dropout": 0.1,
36
+ "summary_proj_to_labels": true,
37
+ "summary_type": "cls_index",
38
+ "summary_use_proj": true,
39
+ "task_specific_params": {
40
+ "text-generation": {
41
+ "do_sample": true,
42
+ "max_length": 50
43
+ }
44
+ },
45
+ "torch_dtype": "float32",
46
+ "transformers_version": "4.38.2",
47
+ "use_cache": true,
48
+ "vocab_size": 50257
49
+ }
checkpoint-655/merges.txt ADDED
The diff for this file is too large to render. See raw diff