Hugging Face's logo

DmitryYarov
/
aristotle_full

Text Generation
Transformers
TensorBoard
Safetensors
gpt2
Generated from Trainer
text-generation-inference
Model card Files Metrics Community
DmitryYarov commited on
Commit
3603793
·
verified ·
1 Parent(s): 4e6985a

Upload folder using huggingface_hub

Browse files
Files changed (47) hide show
  1. README.md +62 -3
  2. all_results.json +16 -0
  3. checkpoint-10/config.json +41 -0
  4. checkpoint-10/generation_config.json +7 -0
  5. checkpoint-10/merges.txt +0 -0
  6. checkpoint-10/model.safetensors +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 +37 -0
  11. checkpoint-10/tokenizer.json +0 -0
  12. checkpoint-10/tokenizer_config.json +59 -0
  13. checkpoint-10/trainer_state.json +32 -0
  14. checkpoint-10/training_args.bin +3 -0
  15. checkpoint-10/vocab.json +0 -0
  16. checkpoint-30/config.json +41 -0
  17. checkpoint-30/generation_config.json +6 -0
  18. checkpoint-30/merges.txt +0 -0
  19. checkpoint-30/model.safetensors +3 -0
  20. checkpoint-30/optimizer.pt +3 -0
  21. checkpoint-30/rng_state.pth +3 -0
  22. checkpoint-30/scaler.pt +3 -0
  23. checkpoint-30/scheduler.pt +3 -0
  24. checkpoint-30/special_tokens_map.json +5 -0
  25. checkpoint-30/tokenizer.json +0 -0
  26. checkpoint-30/tokenizer_config.json +20 -0
  27. checkpoint-30/trainer_state.json +32 -0
  28. checkpoint-30/training_args.bin +3 -0
  29. checkpoint-30/vocab.json +0 -0
  30. config.json +41 -0
  31. eval_results.json +10 -0
  32. generation_config.json +6 -0
  33. merges.txt +0 -0
  34. model.safetensors +3 -0
  35. runs/Feb14_18-28-42_4cf0e8a4721b/events.out.tfevents.1739557738.4cf0e8a4721b.10495.0 +3 -0
  36. runs/Feb14_18-28-42_4cf0e8a4721b/events.out.tfevents.1739557819.4cf0e8a4721b.10495.1 +3 -0
  37. runs/Feb14_18-40-37_4cf0e8a4721b/events.out.tfevents.1739558443.4cf0e8a4721b.13623.0 +3 -0
  38. runs/Feb14_18-40-37_4cf0e8a4721b/events.out.tfevents.1739558668.4cf0e8a4721b.13623.1 +3 -0
  39. runs/Feb14_18-50-17_4cf0e8a4721b/events.out.tfevents.1739559036.4cf0e8a4721b.16147.0 +3 -0
  40. runs/Feb14_18-50-17_4cf0e8a4721b/events.out.tfevents.1739559290.4cf0e8a4721b.16147.1 +3 -0
  41. special_tokens_map.json +5 -0
  42. tokenizer.json +0 -0
  43. tokenizer_config.json +20 -0
  44. train_results.json +9 -0
  45. trainer_state.json +42 -0
  46. training_args.bin +3 -0
  47. vocab.json +0 -0
README.md CHANGED
@@ -1,3 +1,62 @@
1
- ---
2
- license: mit
3
- ---
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: gpt2-medium
5
+ tags:
6
+ - generated_from_trainer
7
+ metrics:
8
+ - accuracy
9
+ model-index:
10
+ - name: essays
11
+ results: []
12
+ ---
13
+
14
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
15
+ should probably proofread and complete it, then remove this comment. -->
16
+
17
+ # essays
18
+
19
+ This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on an unknown dataset.
20
+ It achieves the following results on the evaluation set:
21
+ - Loss: 1.9714
22
+ - Accuracy: 0.4092
23
+
24
+ ## Model description
25
+
26
+ More information needed
27
+
28
+ ## Intended uses & limitations
29
+
30
+ More information needed
31
+
32
+ ## Training and evaluation data
33
+
34
+ More information needed
35
+
36
+ ## Training procedure
37
+
38
+ ### Training hyperparameters
39
+
40
+ The following hyperparameters were used during training:
41
+ - learning_rate: 3e-05
42
+ - train_batch_size: 8
43
+ - eval_batch_size: 8
44
+ - seed: 42
45
+ - gradient_accumulation_steps: 8
46
+ - total_train_batch_size: 64
47
+ - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
48
+ - lr_scheduler_type: linear
49
+ - lr_scheduler_warmup_steps: 500
50
+ - num_epochs: 30.0
51
+ - mixed_precision_training: Native AMP
52
+
53
+ ### Training results
54
+
55
+
56
+
57
+ ### Framework versions
58
+
59
+ - Transformers 4.49.0.dev0
60
+ - Pytorch 2.5.1+cu124
61
+ - Datasets 3.3.0
62
+ - Tokenizers 0.21.0
all_results.json ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.4091607317413769,
4
+ "eval_loss": 1.9713736772537231,
5
+ "eval_runtime": 0.7104,
6
+ "eval_samples": 7,
7
+ "eval_samples_per_second": 9.854,
8
+ "eval_steps_per_second": 1.408,
9
+ "perplexity": 7.180533452125931,
10
+ "total_flos": 1114440833433600.0,
11
+ "train_loss": 2.3499191284179686,
12
+ "train_runtime": 228.8073,
13
+ "train_samples": 20,
14
+ "train_samples_per_second": 2.622,
15
+ "train_steps_per_second": 0.131
16
+ }
checkpoint-10/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "ai-forever/rugpt3small_based_on_gpt2",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 1,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 2,
11
+ "gradient_checkpointing": false,
12
+ "id2label": {
13
+ "0": "LABEL_0"
14
+ },
15
+ "initializer_range": 0.02,
16
+ "label2id": {
17
+ "LABEL_0": 0
18
+ },
19
+ "layer_norm_epsilon": 1e-05,
20
+ "model_type": "gpt2",
21
+ "n_ctx": 2048,
22
+ "n_embd": 768,
23
+ "n_head": 12,
24
+ "n_inner": null,
25
+ "n_layer": 12,
26
+ "n_positions": 2048,
27
+ "pad_token_id": 0,
28
+ "reorder_and_upcast_attn": false,
29
+ "resid_pdrop": 0.1,
30
+ "scale_attn_by_inverse_layer_idx": false,
31
+ "scale_attn_weights": true,
32
+ "summary_activation": null,
33
+ "summary_first_dropout": 0.1,
34
+ "summary_proj_to_labels": true,
35
+ "summary_type": "cls_index",
36
+ "summary_use_proj": true,
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.49.0.dev0",
39
+ "use_cache": true,
40
+ "vocab_size": 50264
41
+ }
checkpoint-10/generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.49.0.dev0"
7
+ }
checkpoint-10/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e70697afa9b1d369be1e8b5c7dc5f43a1961659fe623ce16df18ceeb360d4a0
3
+ size 500941440
checkpoint-10/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6f85aabf3043f8f2143bdf960eff3bb232a9c155ea312d977e1aff912f0f9ba
3
+ size 1001976762
checkpoint-10/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fab923fbe45feef8307938f04fdccf97d99920477f68ebc570d6f9f24b0d77f5
3
+ size 14244
checkpoint-10/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fcbd984600c98bdcc78383a5987627eb4a3d08762dc110427741c7205bf80bb
3
+ size 1064
checkpoint-10/special_tokens_map.json ADDED
@@ -0,0 +1,37 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "mask_token": {
17
+ "content": "<mask>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "pad_token": {
24
+ "content": "<pad>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ },
30
+ "unk_token": {
31
+ "content": "<unk>",
32
+ "lstrip": false,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ }
37
+ }
checkpoint-10/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-10/tokenizer_config.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<pad>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "3": {
30
+ "content": "<unk>",
31
+ "lstrip": false,
32
+ "normalized": true,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "4": {
38
+ "content": "<mask>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ }
45
+ },
46
+ "bos_token": "<s>",
47
+ "clean_up_tokenization_spaces": true,
48
+ "eos_token": "</s>",
49
+ "errors": "replace",
50
+ "extra_special_tokens": {},
51
+ "mask_token": "<mask>",
52
+ "model_max_length": 2048,
53
+ "pad_token": "<pad>",
54
+ "padding_side": "left",
55
+ "tokenizer_class": "GPT2Tokenizer",
56
+ "truncation_side": "left",
57
+ "trust_remote_code": false,
58
+ "unk_token": "<unk>"
59
+ }
checkpoint-10/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 10.0,
5
+ "eval_steps": 500,
6
+ "global_step": 10,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 100,
12
+ "max_steps": 10,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 10,
15
+ "save_steps": 500,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": true
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 41806725120000.0,
29
+ "train_batch_size": 2,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-10/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97781035a5b9c520285bb0c2a90034c4754231466e836045b9125ae30cb5d601
3
+ size 5304
checkpoint-10/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-30/config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.49.0.dev0",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
checkpoint-30/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": "4.49.0.dev0"
6
+ }
checkpoint-30/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-30/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953fc556a56496f269fa2110b1a2388ecb83d8d577d6eafff9cb265807ccfed4
3
+ size 1419322880
checkpoint-30/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26915e89a96418c720b6885563c9bc9ade12cb8cd63251257ef5d0d8a372ca38
3
+ size 2838829242
checkpoint-30/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3ada27ab76b41d357d159114098e11d553d210935b5a7bc36dc0332636c27e1
3
+ size 14244
checkpoint-30/scaler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d4314535dadffef7d30ee715abc65f2f9f176180c1b1e847e26c55d1e86d02d3
3
+ size 988
checkpoint-30/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:44fb68e8d634fb3a2293b64b50e74ac629a030fd75df7276e04e7d960f950a53
3
+ size 1064
checkpoint-30/special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
checkpoint-30/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
checkpoint-30/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": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
checkpoint-30/trainer_state.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 30.0,
5
+ "eval_steps": 1000,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [],
11
+ "logging_steps": 100,
12
+ "max_steps": 30,
13
+ "num_input_tokens_seen": 0,
14
+ "num_train_epochs": 30,
15
+ "save_steps": 1000,
16
+ "stateful_callbacks": {
17
+ "TrainerControl": {
18
+ "args": {
19
+ "should_epoch_stop": false,
20
+ "should_evaluate": false,
21
+ "should_log": false,
22
+ "should_save": true,
23
+ "should_training_stop": true
24
+ },
25
+ "attributes": {}
26
+ }
27
+ },
28
+ "total_flos": 1114440833433600.0,
29
+ "train_batch_size": 8,
30
+ "trial_name": null,
31
+ "trial_params": null
32
+ }
checkpoint-30/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f04d98084e7a6280e0a6c91911fe431004d48212b3a67f01aab63ab9bd2674
3
+ size 5304
checkpoint-30/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2-medium",
3
+ "activation_function": "gelu_new",
4
+ "architectures": [
5
+ "GPT2LMHeadModel"
6
+ ],
7
+ "attn_pdrop": 0.1,
8
+ "bos_token_id": 50256,
9
+ "embd_pdrop": 0.1,
10
+ "eos_token_id": 50256,
11
+ "initializer_range": 0.02,
12
+ "layer_norm_epsilon": 1e-05,
13
+ "model_type": "gpt2",
14
+ "n_ctx": 1024,
15
+ "n_embd": 1024,
16
+ "n_head": 16,
17
+ "n_inner": null,
18
+ "n_layer": 24,
19
+ "n_positions": 1024,
20
+ "n_special": 0,
21
+ "predict_special_tokens": true,
22
+ "reorder_and_upcast_attn": false,
23
+ "resid_pdrop": 0.1,
24
+ "scale_attn_by_inverse_layer_idx": false,
25
+ "scale_attn_weights": true,
26
+ "summary_activation": null,
27
+ "summary_first_dropout": 0.1,
28
+ "summary_proj_to_labels": true,
29
+ "summary_type": "cls_index",
30
+ "summary_use_proj": true,
31
+ "task_specific_params": {
32
+ "text-generation": {
33
+ "do_sample": true,
34
+ "max_length": 50
35
+ }
36
+ },
37
+ "torch_dtype": "float32",
38
+ "transformers_version": "4.49.0.dev0",
39
+ "use_cache": true,
40
+ "vocab_size": 50257
41
+ }
eval_results.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "eval_accuracy": 0.4091607317413769,
4
+ "eval_loss": 1.9713736772537231,
5
+ "eval_runtime": 0.7104,
6
+ "eval_samples": 7,
7
+ "eval_samples_per_second": 9.854,
8
+ "eval_steps_per_second": 1.408,
9
+ "perplexity": 7.180533452125931
10
+ }
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": "4.49.0.dev0"
6
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953fc556a56496f269fa2110b1a2388ecb83d8d577d6eafff9cb265807ccfed4
3
+ size 1419322880
runs/Feb14_18-28-42_4cf0e8a4721b/events.out.tfevents.1739557738.4cf0e8a4721b.10495.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b7e7e34364789396989b95e76c2fd3878c7c2e8c7e4a3bc27d2f1fe74852e62
3
+ size 5703
runs/Feb14_18-28-42_4cf0e8a4721b/events.out.tfevents.1739557819.4cf0e8a4721b.10495.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3c9d6a89c6d6944041a427ddd0fc83fc7799ae164864241a515e3d92e998f37e
3
+ size 405
runs/Feb14_18-40-37_4cf0e8a4721b/events.out.tfevents.1739558443.4cf0e8a4721b.13623.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e005dc0ce78078bb705850a846e3f6394e728812323ff936711f8e7e7fa5f45
3
+ size 5703
runs/Feb14_18-40-37_4cf0e8a4721b/events.out.tfevents.1739558668.4cf0e8a4721b.13623.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aac0e42e5114465b5c138fb4487d574150ae7169326525a3cc25fd3453739520
3
+ size 405
runs/Feb14_18-50-17_4cf0e8a4721b/events.out.tfevents.1739559036.4cf0e8a4721b.16147.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eb729ae0af1def1ac4225ffe35cf3a51ce72df47524d2aa4a3bd3ff43af1c4b
3
+ size 5721
runs/Feb14_18-50-17_4cf0e8a4721b/events.out.tfevents.1739559290.4cf0e8a4721b.16147.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1fbbb4e13b6642880a600ad787b82781dd15958ac945d70979b76d0a78e4eeb3
3
+ size 405
special_tokens_map.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|endoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "unk_token": "<|endoftext|>"
5
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
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": false,
15
+ "eos_token": "<|endoftext|>",
16
+ "extra_special_tokens": {},
17
+ "model_max_length": 1024,
18
+ "tokenizer_class": "GPT2Tokenizer",
19
+ "unk_token": "<|endoftext|>"
20
+ }
train_results.json ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "epoch": 30.0,
3
+ "total_flos": 1114440833433600.0,
4
+ "train_loss": 2.3499191284179686,
5
+ "train_runtime": 228.8073,
6
+ "train_samples": 20,
7
+ "train_samples_per_second": 2.622,
8
+ "train_steps_per_second": 0.131
9
+ }
trainer_state.json ADDED
@@ -0,0 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 30.0,
5
+ "eval_steps": 1000,
6
+ "global_step": 30,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 30.0,
13
+ "step": 30,
14
+ "total_flos": 1114440833433600.0,
15
+ "train_loss": 2.3499191284179686,
16
+ "train_runtime": 228.8073,
17
+ "train_samples_per_second": 2.622,
18
+ "train_steps_per_second": 0.131
19
+ }
20
+ ],
21
+ "logging_steps": 100,
22
+ "max_steps": 30,
23
+ "num_input_tokens_seen": 0,
24
+ "num_train_epochs": 30,
25
+ "save_steps": 1000,
26
+ "stateful_callbacks": {
27
+ "TrainerControl": {
28
+ "args": {
29
+ "should_epoch_stop": false,
30
+ "should_evaluate": false,
31
+ "should_log": false,
32
+ "should_save": true,
33
+ "should_training_stop": true
34
+ },
35
+ "attributes": {}
36
+ }
37
+ },
38
+ "total_flos": 1114440833433600.0,
39
+ "train_batch_size": 8,
40
+ "trial_name": null,
41
+ "trial_params": null
42
+ }
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2f04d98084e7a6280e0a6c91911fe431004d48212b3a67f01aab63ab9bd2674
3
+ size 5304
vocab.json ADDED
The diff for this file is too large to render. See raw diff