Hugging Face's logo

Dmitriy007
/
Socrat_batch3_epochs5

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
1
Dmitriy007 commited on
Commit
d424cb7
•
1 Parent(s): aa22b54

Training in progress, step 11000

Browse files
Files changed (12) hide show
  1. config.json +1 -1
  2. last-checkpoint/config.json +1 -1
  3. last-checkpoint/optimizer.pt +1 -1
  4. last-checkpoint/pytorch_model.bin +1 -1
  5. last-checkpoint/rng_state.pth +1 -1
  6. last-checkpoint/scheduler.pt +1 -1
  7. last-checkpoint/trainer_state.json +23 -3
  8. last-checkpoint/training_args.bin +1 -1
  9. pytorch_model.bin +1 -1
  10. runs/Mar21_22-11-09_493485ec0ec3/1679436700.0595562/events.out.tfevents.1679436700.493485ec0ec3.312.1 +3 -0
  11. runs/Mar21_22-11-09_493485ec0ec3/events.out.tfevents.1679436700.493485ec0ec3.312.0 +3 -0
  12. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/Socrat_4",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "/content/Socrat/last-checkpoint",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
last-checkpoint/config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "/content/Socrat_4",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "/content/Socrat/last-checkpoint",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d43d75d9a69cab6bbdc5d807e2bb46ff6cdc4a8d041a08ec646f4a6e3cd2db85
3
  size 2847145157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8720595d9cd147ba8bd6abc76e18e81c63e203a5b44ecc616282800b286e6f36
3
  size 2847145157
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddbae1252128d10be81c8573c827bec76386fb0202a5c3196a13dad3d7c56f87
3
  size 1524261149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f3de48b1b73850c149cde38909a25b776fb76e72c1a1c7caf5503c22ed001a
3
  size 1524261149
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4726f886967d0edea6aba4d768b4e7e6c5f2c77453e08bd258b36ebd6bbf0054
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8a0709b6819bc1359d68b27147b21e79a4b0ab08155c73633b9b5980d48b775
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d83ea694a86cc0c579d479f8a93d9e180abe564de49dd67c75124cdac727a14a
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f8f9ac5225a5e9f7fe84cd20e2b56b961f452f409f1ca512b75e655587f5d09
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,8 +1,8 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 2.5012506253126565,
5
- "global_step": 10000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -206,11 +206,31 @@
206
  "eval_samples_per_second": 15.532,
207
  "eval_steps_per_second": 5.18,
208
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
209
  }
210
  ],
211
  "max_steps": 19990,
212
  "num_train_epochs": 5,
213
- "total_flos": 1.41481746432e+16,
214
  "trial_name": null,
215
  "trial_params": null
216
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.7513756878439217,
5
+ "global_step": 11000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
206
  "eval_samples_per_second": 15.532,
207
  "eval_steps_per_second": 5.18,
208
  "step": 10000
209
+ },
210
+ {
211
+ "epoch": 2.63,
212
+ "learning_rate": 9.494747373686844e-06,
213
+ "loss": 2.6173,
214
+ "step": 10500
215
+ },
216
+ {
217
+ "epoch": 2.75,
218
+ "learning_rate": 8.994497248624313e-06,
219
+ "loss": 2.6314,
220
+ "step": 11000
221
+ },
222
+ {
223
+ "epoch": 2.75,
224
+ "eval_loss": 3.12784481048584,
225
+ "eval_runtime": 143.6305,
226
+ "eval_samples_per_second": 14.739,
227
+ "eval_steps_per_second": 4.915,
228
+ "step": 11000
229
  }
230
  ],
231
  "max_steps": 19990,
232
  "num_train_epochs": 5,
233
+ "total_flos": 1.556299210752e+16,
234
  "trial_name": null,
235
  "trial_params": null
236
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:918b854d4ced36747513144ebd0eebe9f265f3dbaedccdbeea45c88b4a5aac6b
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c73f1a75e190362ef7c8240bf1c1babc7762c20322487413673a3acb504d42b
3
  size 3515
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ddbae1252128d10be81c8573c827bec76386fb0202a5c3196a13dad3d7c56f87
3
  size 1524261149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36f3de48b1b73850c149cde38909a25b776fb76e72c1a1c7caf5503c22ed001a
3
  size 1524261149
runs/Mar21_22-11-09_493485ec0ec3/1679436700.0595562/events.out.tfevents.1679436700.493485ec0ec3.312.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:95c09fdcaef4701b0ca04894990682343b2e558f5ca942a5b7a1e2cac5b158c6
3
+ size 5742
runs/Mar21_22-11-09_493485ec0ec3/events.out.tfevents.1679436700.493485ec0ec3.312.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e45471f0b2e945d7dfe440a410866c7d81dced0c30e01d0ec457a92a32e67ed5
3
+ size 4797
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:918b854d4ced36747513144ebd0eebe9f265f3dbaedccdbeea45c88b4a5aac6b
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c73f1a75e190362ef7c8240bf1c1babc7762c20322487413673a3acb504d42b
3
  size 3515