Hugging Face's logo

Dmitriy007
/
Socrat_tmp

Text Generation
Transformers
PyTorch
TensorBoard
gpt2
Inference Endpoints
text-generation-inference
Model card Files Metrics Community
Dmitriy007 commited on
Commit
7c1ace1
•
1 Parent(s): 21d1895

Training in progress, step 7000

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/Mar25_07-47-44_6e686009e3a0/1679730482.1827366/events.out.tfevents.1679730482.6e686009e3a0.183.1 +3 -0
  11. runs/Mar25_07-47-44_6e686009e3a0/events.out.tfevents.1679730482.6e686009e3a0.183.0 +3 -0
  12. training_args.bin +1 -1
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "sberbank-ai/rugpt3medium_based_on_gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "/content/Socrat_tmp/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": "sberbank-ai/rugpt3medium_based_on_gpt2",
3
  "activation_function": "gelu_new",
4
  "architectures": [
5
  "GPT2LMHeadModel"
 
1
  {
2
+ "_name_or_path": "/content/Socrat_tmp/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 sha256:67978948fb3b549f5c65bac6be20371317a7760f6a1e185ee4429165340c2211
3
  size 2847145157
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c136ff0e9cb20c7463cf837c57a825a4e61457ecc99effe498b8cec7d902776
3
  size 2847145157
last-checkpoint/pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43af96f1ebc8edb6272710e8eded46b397b3566845920240e9b47c2c9d0eae77
3
  size 1524261149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e09ba7644b8ce1be54b5d151fb88c54f7af6e3f93b2834943e87018320b472
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:a8442c4ffbd50200b4bc943e03cf1d899ee87f53e137754e23543c2176c8b920
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89f2ea1099f73d4771d0adfcd2464d3b79ddc8be7baf6cb50692837d58a8a048
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:81baa9d1bbfebc8a9494097ebb00110cffda569e0baf3070d563ac3650b9b0ae
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14808219b4a7001cd7bd7967362505aa479b3e57cd0120b221d6370031f10450
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": 3.0015007503751874,
5
- "global_step": 6000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
@@ -126,11 +126,31 @@
126
  "eval_samples_per_second": 15.661,
127
  "eval_steps_per_second": 2.611,
128
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
129
  }
130
  ],
131
  "max_steps": 9995,
132
  "num_train_epochs": 5,
133
- "total_flos": 1.697780957184e+16,
134
  "trial_name": null,
135
  "trial_params": null
136
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 3.501750875437719,
5
+ "global_step": 7000,
6
  "is_hyper_param_search": false,
7
  "is_local_process_zero": true,
8
  "is_world_process_zero": true,
 
126
  "eval_samples_per_second": 15.661,
127
  "eval_steps_per_second": 2.611,
128
  "step": 6000
129
+ },
130
+ {
131
+ "epoch": 3.25,
132
+ "learning_rate": 6.9934967483741875e-06,
133
+ "loss": 2.8394,
134
+ "step": 6500
135
+ },
136
+ {
137
+ "epoch": 3.5,
138
+ "learning_rate": 5.992996498249125e-06,
139
+ "loss": 2.819,
140
+ "step": 7000
141
+ },
142
+ {
143
+ "epoch": 3.5,
144
+ "eval_loss": 3.090629816055298,
145
+ "eval_runtime": 133.0042,
146
+ "eval_samples_per_second": 15.917,
147
+ "eval_steps_per_second": 2.654,
148
+ "step": 7000
149
  }
150
  ],
151
  "max_steps": 9995,
152
  "num_train_epochs": 5,
153
+ "total_flos": 1.980744450048e+16,
154
  "trial_name": null,
155
  "trial_params": null
156
  }
last-checkpoint/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:175fa8453377bf4a0c9a3ff9526282460c0fde24b49844814ef9cd85c3698074
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7310e8acee49c640435d0d63ee639d9b8543c98942deb1f0453405499bf4acef
3
  size 3515
pytorch_model.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43af96f1ebc8edb6272710e8eded46b397b3566845920240e9b47c2c9d0eae77
3
  size 1524261149
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:89e09ba7644b8ce1be54b5d151fb88c54f7af6e3f93b2834943e87018320b472
3
  size 1524261149
runs/Mar25_07-47-44_6e686009e3a0/1679730482.1827366/events.out.tfevents.1679730482.6e686009e3a0.183.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:00f6c7ae6be349384a4f7a61c28fe5d4b861d59cb04560646f996698189df91c
3
+ size 5754
runs/Mar25_07-47-44_6e686009e3a0/events.out.tfevents.1679730482.6e686009e3a0.183.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:187a073febbce9d08c947a3283b5e8e473950f162a4dbd8c354fd7f957611812
3
+ size 4813
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:175fa8453377bf4a0c9a3ff9526282460c0fde24b49844814ef9cd85c3698074
3
  size 3515
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7310e8acee49c640435d0d63ee639d9b8543c98942deb1f0453405499bf4acef
3
  size 3515