Hugging Face's logo

Spaces:
SaviAnna
/
Extended_GPT_2
Sleeping

App Files Community
SaviAnna commited on
Commit
9177aa5
·
verified ·
1 Parent(s): b628870

Upload 25 files

Browse files

Fine-tuned model

Files changed (25) hide show
  1. rus_gpt2_tuned/README.md +66 -0
  2. rus_gpt2_tuned/checkpoint-10000/config.json +39 -0
  3. rus_gpt2_tuned/checkpoint-10000/generation_config.json +6 -0
  4. rus_gpt2_tuned/checkpoint-10000/optimizer.pt +3 -0
  5. rus_gpt2_tuned/checkpoint-10000/rng_state.pth +3 -0
  6. rus_gpt2_tuned/checkpoint-10000/scheduler.pt +3 -0
  7. rus_gpt2_tuned/checkpoint-10000/trainer_state.json +108 -0
  8. rus_gpt2_tuned/checkpoint-10000/training_args.bin +3 -0
  9. rus_gpt2_tuned/checkpoint-16594/config.json +39 -0
  10. rus_gpt2_tuned/checkpoint-16594/generation_config.json +6 -0
  11. rus_gpt2_tuned/checkpoint-16594/optimizer.pt +3 -0
  12. rus_gpt2_tuned/checkpoint-16594/rng_state.pth +3 -0
  13. rus_gpt2_tuned/checkpoint-16594/scheduler.pt +3 -0
  14. rus_gpt2_tuned/checkpoint-16594/trainer_state.json +153 -0
  15. rus_gpt2_tuned/checkpoint-16594/training_args.bin +3 -0
  16. rus_gpt2_tuned/config.json +39 -0
  17. rus_gpt2_tuned/generation_config.json +6 -0
  18. rus_gpt2_tuned/runs/Aug13_20-15-46_5da49f4c8fb7/events.out.tfevents.1723580147.5da49f4c8fb7.1074.2 +3 -0
  19. rus_gpt2_tuned/runs/Aug13_20-16-15_5da49f4c8fb7/events.out.tfevents.1723580176.5da49f4c8fb7.1074.3 +3 -0
  20. rus_gpt2_tuned/tokenizer/added_tokens.json +0 -0
  21. rus_gpt2_tuned/tokenizer/merges.txt +0 -0
  22. rus_gpt2_tuned/tokenizer/special_tokens_map.json +23 -0
  23. rus_gpt2_tuned/tokenizer/tokenizer_config.json +0 -0
  24. rus_gpt2_tuned/tokenizer/vocab.json +0 -0
  25. rus_gpt2_tuned/training_args.bin +3 -0
rus_gpt2_tuned/README.md ADDED
@@ -0,0 +1,66 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ base_model: gpt2
4
+ tags:
5
+ - generated_from_trainer
6
+ model-index:
7
+ - name: rus_gpt2_2_epoch
8
+ results: []
9
+ ---
10
+
11
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
12
+ should probably proofread and complete it, then remove this comment. -->
13
+
14
+ # rus_gpt2_2_epoch
15
+
16
+ This model is a fine-tuned version of [gpt2](https://huggingface.co/gpt2) on the None dataset.
17
+ It achieves the following results on the evaluation set:
18
+ - Loss: 2.7019
19
+
20
+ ## Model description
21
+
22
+ More information needed
23
+
24
+ ## Intended uses & limitations
25
+
26
+ More information needed
27
+
28
+ ## Training and evaluation data
29
+
30
+ More information needed
31
+
32
+ ## Training procedure
33
+
34
+ ### Training hyperparameters
35
+
36
+ The following hyperparameters were used during training:
37
+ - learning_rate: 0.005
38
+ - train_batch_size: 128
39
+ - eval_batch_size: 128
40
+ - seed: 42
41
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
42
+ - lr_scheduler_type: cosine
43
+ - lr_scheduler_warmup_steps: 50
44
+ - num_epochs: 2
45
+ - mixed_precision_training: Native AMP
46
+
47
+ ### Training results
48
+
49
+ | Training Loss | Epoch | Step | Validation Loss |
50
+ |:-------------:|:------:|:-----:|:---------------:|
51
+ | 4.2111 | 0.2411 | 2000 | 3.5603 |
52
+ | 3.5259 | 0.4821 | 4000 | 3.3412 |
53
+ | 3.3625 | 0.7232 | 6000 | 3.2120 |
54
+ | 3.2367 | 0.9642 | 8000 | 3.0991 |
55
+ | 3.1018 | 1.2053 | 10000 | 2.9778 |
56
+ | 2.9743 | 1.4463 | 12000 | 2.8497 |
57
+ | 2.8518 | 1.6874 | 14000 | 2.7453 |
58
+ | 2.7705 | 1.9284 | 16000 | 2.7019 |
59
+
60
+
61
+ ### Framework versions
62
+
63
+ - Transformers 4.42.4
64
+ - Pytorch 2.3.1+cu121
65
+ - Datasets 2.20.0
66
+ - Tokenizers 0.19.1
rus_gpt2_tuned/checkpoint-10000/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
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": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.42.4",
37
+ "use_cache": true,
38
+ "vocab_size": 54848
39
+ }
rus_gpt2_tuned/checkpoint-10000/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": "4.42.4"
6
+ }
rus_gpt2_tuned/checkpoint-10000/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:201c4e516336829b1ff5c935bc8df8bae3962b76fc7f515ab93dcf098d86a078
3
+ size 1023849402
rus_gpt2_tuned/checkpoint-10000/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6254415d44977265b8e115a20e42243f65fd58405703b6238321812ac2703139
3
+ size 14244
rus_gpt2_tuned/checkpoint-10000/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d7f888ef3cafd5ec18efc026f3ff65cde7a6de88138414f6890e83b90fc26d6
3
+ size 1064
rus_gpt2_tuned/checkpoint-10000/trainer_state.json ADDED
@@ -0,0 +1,108 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 1.205254911413764,
5
+ "eval_steps": 2000,
6
+ "global_step": 10000,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2410509822827528,
13
+ "grad_norm": 0.20469364523887634,
14
+ "learning_rate": 0.004830554568302067,
15
+ "loss": 4.2111,
16
+ "step": 2000
17
+ },
18
+ {
19
+ "epoch": 0.2410509822827528,
20
+ "eval_loss": 3.560250997543335,
21
+ "eval_runtime": 106.0085,
22
+ "eval_samples_per_second": 1107.808,
23
+ "eval_steps_per_second": 8.66,
24
+ "step": 2000
25
+ },
26
+ {
27
+ "epoch": 0.4821019645655056,
28
+ "grad_norm": 0.19791439175605774,
29
+ "learning_rate": 0.004329089190438083,
30
+ "loss": 3.5259,
31
+ "step": 4000
32
+ },
33
+ {
34
+ "epoch": 0.4821019645655056,
35
+ "eval_loss": 3.341155529022217,
36
+ "eval_runtime": 106.3391,
37
+ "eval_samples_per_second": 1104.363,
38
+ "eval_steps_per_second": 8.633,
39
+ "step": 4000
40
+ },
41
+ {
42
+ "epoch": 0.7231529468482584,
43
+ "grad_norm": 0.17919738590717316,
44
+ "learning_rate": 0.003566956152862128,
45
+ "loss": 3.3625,
46
+ "step": 6000
47
+ },
48
+ {
49
+ "epoch": 0.7231529468482584,
50
+ "eval_loss": 3.212028741836548,
51
+ "eval_runtime": 105.9869,
52
+ "eval_samples_per_second": 1108.033,
53
+ "eval_steps_per_second": 8.661,
54
+ "step": 6000
55
+ },
56
+ {
57
+ "epoch": 0.9642039291310112,
58
+ "grad_norm": 0.1722663789987564,
59
+ "learning_rate": 0.0026527687677804354,
60
+ "loss": 3.2367,
61
+ "step": 8000
62
+ },
63
+ {
64
+ "epoch": 0.9642039291310112,
65
+ "eval_loss": 3.099142074584961,
66
+ "eval_runtime": 106.3519,
67
+ "eval_samples_per_second": 1104.231,
68
+ "eval_steps_per_second": 8.632,
69
+ "step": 8000
70
+ },
71
+ {
72
+ "epoch": 1.205254911413764,
73
+ "grad_norm": 0.1924629658460617,
74
+ "learning_rate": 0.0017168099582200536,
75
+ "loss": 3.1018,
76
+ "step": 10000
77
+ },
78
+ {
79
+ "epoch": 1.205254911413764,
80
+ "eval_loss": 2.9777753353118896,
81
+ "eval_runtime": 105.82,
82
+ "eval_samples_per_second": 1109.781,
83
+ "eval_steps_per_second": 8.675,
84
+ "step": 10000
85
+ }
86
+ ],
87
+ "logging_steps": 2000,
88
+ "max_steps": 16594,
89
+ "num_input_tokens_seen": 0,
90
+ "num_train_epochs": 2,
91
+ "save_steps": 10000,
92
+ "stateful_callbacks": {
93
+ "TrainerControl": {
94
+ "args": {
95
+ "should_epoch_stop": false,
96
+ "should_evaluate": false,
97
+ "should_log": false,
98
+ "should_save": true,
99
+ "should_training_stop": false
100
+ },
101
+ "attributes": {}
102
+ }
103
+ },
104
+ "total_flos": 8.3611621195776e+16,
105
+ "train_batch_size": 128,
106
+ "trial_name": null,
107
+ "trial_params": null
108
+ }
rus_gpt2_tuned/checkpoint-10000/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b6ff58a9bf1e982d206470594d4dd04f3cb47b910b0fe24b44cdbb92457b09
3
+ size 5176
rus_gpt2_tuned/checkpoint-16594/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
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": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.42.4",
37
+ "use_cache": true,
38
+ "vocab_size": 54848
39
+ }
rus_gpt2_tuned/checkpoint-16594/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": "4.42.4"
6
+ }
rus_gpt2_tuned/checkpoint-16594/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27614eb638f7b197bb14b1b66b856490b95ed558fb9e51bfb18be86bb32598aa
3
+ size 1023849402
rus_gpt2_tuned/checkpoint-16594/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c02fc671d71cbd43e31ba23967276720e1f3fd626c006a72c270ac6308b8ec7
3
+ size 14244
rus_gpt2_tuned/checkpoint-16594/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef2c61684b7606044cd5fca5cac6e222f4199e225e2a0f986b334e15ead0d8df
3
+ size 1064
rus_gpt2_tuned/checkpoint-16594/trainer_state.json ADDED
@@ -0,0 +1,153 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 2.0,
5
+ "eval_steps": 2000,
6
+ "global_step": 16594,
7
+ "is_hyper_param_search": false,
8
+ "is_local_process_zero": true,
9
+ "is_world_process_zero": true,
10
+ "log_history": [
11
+ {
12
+ "epoch": 0.2410509822827528,
13
+ "grad_norm": 0.20469364523887634,
14
+ "learning_rate": 0.004830554568302067,
15
+ "loss": 4.2111,
16
+ "step": 2000
17
+ },
18
+ {
19
+ "epoch": 0.2410509822827528,
20
+ "eval_loss": 3.560250997543335,
21
+ "eval_runtime": 106.0085,
22
+ "eval_samples_per_second": 1107.808,
23
+ "eval_steps_per_second": 8.66,
24
+ "step": 2000
25
+ },
26
+ {
27
+ "epoch": 0.4821019645655056,
28
+ "grad_norm": 0.19791439175605774,
29
+ "learning_rate": 0.004329089190438083,
30
+ "loss": 3.5259,
31
+ "step": 4000
32
+ },
33
+ {
34
+ "epoch": 0.4821019645655056,
35
+ "eval_loss": 3.341155529022217,
36
+ "eval_runtime": 106.3391,
37
+ "eval_samples_per_second": 1104.363,
38
+ "eval_steps_per_second": 8.633,
39
+ "step": 4000
40
+ },
41
+ {
42
+ "epoch": 0.7231529468482584,
43
+ "grad_norm": 0.17919738590717316,
44
+ "learning_rate": 0.003566956152862128,
45
+ "loss": 3.3625,
46
+ "step": 6000
47
+ },
48
+ {
49
+ "epoch": 0.7231529468482584,
50
+ "eval_loss": 3.212028741836548,
51
+ "eval_runtime": 105.9869,
52
+ "eval_samples_per_second": 1108.033,
53
+ "eval_steps_per_second": 8.661,
54
+ "step": 6000
55
+ },
56
+ {
57
+ "epoch": 0.9642039291310112,
58
+ "grad_norm": 0.1722663789987564,
59
+ "learning_rate": 0.0026527687677804354,
60
+ "loss": 3.2367,
61
+ "step": 8000
62
+ },
63
+ {
64
+ "epoch": 0.9642039291310112,
65
+ "eval_loss": 3.099142074584961,
66
+ "eval_runtime": 106.3519,
67
+ "eval_samples_per_second": 1104.231,
68
+ "eval_steps_per_second": 8.632,
69
+ "step": 8000
70
+ },
71
+ {
72
+ "epoch": 1.205254911413764,
73
+ "grad_norm": 0.1924629658460617,
74
+ "learning_rate": 0.0017168099582200536,
75
+ "loss": 3.1018,
76
+ "step": 10000
77
+ },
78
+ {
79
+ "epoch": 1.205254911413764,
80
+ "eval_loss": 2.9777753353118896,
81
+ "eval_runtime": 105.82,
82
+ "eval_samples_per_second": 1109.781,
83
+ "eval_steps_per_second": 8.675,
84
+ "step": 10000
85
+ },
86
+ {
87
+ "epoch": 1.4463058936965167,
88
+ "grad_norm": 0.19710072875022888,
89
+ "learning_rate": 0.0008928289477681187,
90
+ "loss": 2.9743,
91
+ "step": 12000
92
+ },
93
+ {
94
+ "epoch": 1.4463058936965167,
95
+ "eval_loss": 2.849729537963867,
96
+ "eval_runtime": 106.2665,
97
+ "eval_samples_per_second": 1105.118,
98
+ "eval_steps_per_second": 8.639,
99
+ "step": 12000
100
+ },
101
+ {
102
+ "epoch": 1.6873568759792696,
103
+ "grad_norm": 0.19068941473960876,
104
+ "learning_rate": 0.0002976633104314971,
105
+ "loss": 2.8518,
106
+ "step": 14000
107
+ },
108
+ {
109
+ "epoch": 1.6873568759792696,
110
+ "eval_loss": 2.7452616691589355,
111
+ "eval_runtime": 106.1447,
112
+ "eval_samples_per_second": 1106.386,
113
+ "eval_steps_per_second": 8.649,
114
+ "step": 14000
115
+ },
116
+ {
117
+ "epoch": 1.9284078582620223,
118
+ "grad_norm": 0.20230965316295624,
119
+ "learning_rate": 1.610142628396982e-05,
120
+ "loss": 2.7705,
121
+ "step": 16000
122
+ },
123
+ {
124
+ "epoch": 1.9284078582620223,
125
+ "eval_loss": 2.7018611431121826,
126
+ "eval_runtime": 106.1155,
127
+ "eval_samples_per_second": 1106.69,
128
+ "eval_steps_per_second": 8.651,
129
+ "step": 16000
130
+ }
131
+ ],
132
+ "logging_steps": 2000,
133
+ "max_steps": 16594,
134
+ "num_input_tokens_seen": 0,
135
+ "num_train_epochs": 2,
136
+ "save_steps": 10000,
137
+ "stateful_callbacks": {
138
+ "TrainerControl": {
139
+ "args": {
140
+ "should_epoch_stop": false,
141
+ "should_evaluate": false,
142
+ "should_log": false,
143
+ "should_save": true,
144
+ "should_training_stop": true
145
+ },
146
+ "attributes": {}
147
+ }
148
+ },
149
+ "total_flos": 1.38744501239808e+17,
150
+ "train_batch_size": 128,
151
+ "trial_name": null,
152
+ "trial_params": null
153
+ }
rus_gpt2_tuned/checkpoint-16594/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b6ff58a9bf1e982d206470594d4dd04f3cb47b910b0fe24b44cdbb92457b09
3
+ size 5176
rus_gpt2_tuned/config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "gpt2",
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": 768,
16
+ "n_head": 12,
17
+ "n_inner": null,
18
+ "n_layer": 12,
19
+ "n_positions": 1024,
20
+ "reorder_and_upcast_attn": false,
21
+ "resid_pdrop": 0.1,
22
+ "scale_attn_by_inverse_layer_idx": false,
23
+ "scale_attn_weights": true,
24
+ "summary_activation": null,
25
+ "summary_first_dropout": 0.1,
26
+ "summary_proj_to_labels": true,
27
+ "summary_type": "cls_index",
28
+ "summary_use_proj": true,
29
+ "task_specific_params": {
30
+ "text-generation": {
31
+ "do_sample": true,
32
+ "max_length": 50
33
+ }
34
+ },
35
+ "torch_dtype": "float32",
36
+ "transformers_version": "4.42.4",
37
+ "use_cache": true,
38
+ "vocab_size": 54848
39
+ }
rus_gpt2_tuned/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": "4.42.4"
6
+ }
rus_gpt2_tuned/runs/Aug13_20-15-46_5da49f4c8fb7/events.out.tfevents.1723580147.5da49f4c8fb7.1074.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:898b283f0b4a8bac7aada262eeae7eaa9c4ab80fbf144f6af9f4238c0255a308
3
+ size 5159
rus_gpt2_tuned/runs/Aug13_20-16-15_5da49f4c8fb7/events.out.tfevents.1723580176.5da49f4c8fb7.1074.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1319b65ae8fc7d1877b25c6ed5a450f601b8372766ec8aff67de65e0f9af03a6
3
+ size 9375
rus_gpt2_tuned/tokenizer/added_tokens.json ADDED
The diff for this file is too large to render. See raw diff
 
rus_gpt2_tuned/tokenizer/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
rus_gpt2_tuned/tokenizer/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
+ "unk_token": {
17
+ "content": "<|endoftext|>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
rus_gpt2_tuned/tokenizer/tokenizer_config.json ADDED
The diff for this file is too large to render. See raw diff
 
rus_gpt2_tuned/tokenizer/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
rus_gpt2_tuned/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d3b6ff58a9bf1e982d206470594d4dd04f3cb47b910b0fe24b44cdbb92457b09
3
+ size 5176