Hugging Face's logo

Dmitriy007
/
rugpt2_test_gen_comments

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
Dmitriy007 commited on
Commit
eb7128d
•
1 Parent(s): 1f581d2

Training in progress, step 500

Browse files
Files changed (14) hide show
  1. .gitignore +1 -0
  2. config.json +34 -0
  3. last-checkpoint/config.json +34 -0
  4. last-checkpoint/generation_config.json +6 -0
  5. last-checkpoint/optimizer.pt +3 -0
  6. last-checkpoint/pytorch_model.bin +3 -0
  7. last-checkpoint/rng_state.pth +3 -0
  8. last-checkpoint/scheduler.pt +3 -0
  9. last-checkpoint/trainer_state.json +22 -0
  10. last-checkpoint/training_args.bin +3 -0
  11. pytorch_model.bin +3 -0
  12. runs/Feb20_09-01-29_18ffb5c4eaf2/1676883692.7105727/events.out.tfevents.1676883692.18ffb5c4eaf2.214.1 +3 -0
  13. runs/Feb20_09-01-29_18ffb5c4eaf2/events.out.tfevents.1676883692.18ffb5c4eaf2.214.0 +3 -0
  14. training_args.bin +3 -0
.gitignore ADDED
@@ -0,0 +1 @@
 
 
1
+ checkpoint-*/
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sberbank-ai/rugpt3large_based_on_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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 1536,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 2048,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.26.1",
32
+ "use_cache": true,
33
+ "vocab_size": 50257
34
+ }
last-checkpoint/config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "sberbank-ai/rugpt3large_based_on_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
+ "gradient_checkpointing": false,
12
+ "initializer_range": 0.02,
13
+ "layer_norm_epsilon": 1e-05,
14
+ "model_type": "gpt2",
15
+ "n_ctx": 2048,
16
+ "n_embd": 1536,
17
+ "n_head": 16,
18
+ "n_inner": null,
19
+ "n_layer": 24,
20
+ "n_positions": 2048,
21
+ "reorder_and_upcast_attn": false,
22
+ "resid_pdrop": 0.1,
23
+ "scale_attn_by_inverse_layer_idx": false,
24
+ "scale_attn_weights": true,
25
+ "summary_activation": null,
26
+ "summary_first_dropout": 0.1,
27
+ "summary_proj_to_labels": true,
28
+ "summary_type": "cls_index",
29
+ "summary_use_proj": true,
30
+ "torch_dtype": "float32",
31
+ "transformers_version": "4.26.1",
32
+ "use_cache": true,
33
+ "vocab_size": 50257
34
+ }
last-checkpoint/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": "4.26.1"
6
+ }
last-checkpoint/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a16aaeb9e71f9a745460d0a30166f67ae79f7804440538c7bf852a637af0aa2
3
+ size 6082574325
last-checkpoint/pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643c91bfbbfccac3781aafa2d565eac316b2da87840a0ed8a712f55263051155
3
+ size 3141974301
last-checkpoint/rng_state.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5f5f9d240b11d659a46df99501092e4ee7e232262b261930e9d28f1b05af61b
3
+ size 14575
last-checkpoint/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9be5816a88b81130845483cc0a19d8fdb928c4e821f9e77ede5abb9a307a0f70
3
+ size 627
last-checkpoint/trainer_state.json ADDED
@@ -0,0 +1,22 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_metric": null,
3
+ "best_model_checkpoint": null,
4
+ "epoch": 0.06999860002799944,
5
+ "global_step": 500,
6
+ "is_hyper_param_search": false,
7
+ "is_local_process_zero": true,
8
+ "is_world_process_zero": true,
9
+ "log_history": [
10
+ {
11
+ "epoch": 0.07,
12
+ "learning_rate": 1.982500349993e-05,
13
+ "loss": 3.4571,
14
+ "step": 500
15
+ }
16
+ ],
17
+ "max_steps": 57144,
18
+ "num_train_epochs": 8,
19
+ "total_flos": 509969664000000.0,
20
+ "trial_name": null,
21
+ "trial_params": null
22
+ }
last-checkpoint/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a57c3533dbce084c2f823b12b064346304af97fc9e4e15360061a955c8f7ea7
3
+ size 3515
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:643c91bfbbfccac3781aafa2d565eac316b2da87840a0ed8a712f55263051155
3
+ size 3141974301
runs/Feb20_09-01-29_18ffb5c4eaf2/1676883692.7105727/events.out.tfevents.1676883692.18ffb5c4eaf2.214.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdcf625d61f7d37ddfb8fda0f13b1eab10c24de2ba6b3543901908029cbdabbd
3
+ size 5691
runs/Feb20_09-01-29_18ffb5c4eaf2/events.out.tfevents.1676883692.18ffb5c4eaf2.214.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7bfd81f917de9d5fa4735e6a1d6b6c8cad2cb46bac63cc251ef8b720b0d43077
3
+ size 4178
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a57c3533dbce084c2f823b12b064346304af97fc9e4e15360061a955c8f7ea7
3
+ size 3515