flytech commited on
Commit
78d7a97
1 Parent(s): c3aee9a

Training in progress, step 1800, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0137ef99c1a7b8626424c1ce04ccdf9189cb06acd6d38d5f7e43a46d039a7703
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9eb84eafa0c6521d28b95659b9f799b0bdb236789540a3e53980830daa6cb8ac
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:728eb538e59043c90e414bb1cc0d89ad5560107e49193b572a6ced9e91e48e35
3
  size 80630623
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c2722d27383dd5dbbd0ea822e3aa526a8022fa8bda2698a1da5faa4aae0256f
3
  size 80630623
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bc21fea72dc0791f4dc549e7c6b2f79ab236ae3c9b25f0eae4230835b22335ac
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a172b245a0e8ce0c232853c6220b0c93e78fb73bf7e2f5903fafe46e104c3685
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80bd1a19eefcf2faa72604d45a7e0dd3eaa509be69eeefba41933c85d5335a1a
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:479ba9f0f844678619258894f9811c2d42d65088287ecff3bea682ccb50a4f29
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 10.365853658536585,
5
  "eval_steps": 100,
6
- "global_step": 1700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -228,13 +228,26 @@
228
  "eval_samples_per_second": 1.856,
229
  "eval_steps_per_second": 0.242,
230
  "step": 1700
 
 
 
 
 
 
 
 
 
 
 
 
 
231
  }
232
  ],
233
  "logging_steps": 100,
234
  "max_steps": 1804,
235
  "num_train_epochs": 11,
236
  "save_steps": 100,
237
- "total_flos": 1.4212437116977152e+17,
238
  "trial_name": null,
239
  "trial_params": null
240
  }
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 10.975609756097562,
5
  "eval_steps": 100,
6
+ "global_step": 1800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
228
  "eval_samples_per_second": 1.856,
229
  "eval_steps_per_second": 0.242,
230
  "step": 1700
231
+ },
232
+ {
233
+ "epoch": 10.98,
234
+ "learning_rate": 0.0002,
235
+ "loss": 0.0201,
236
+ "step": 1800
237
+ },
238
+ {
239
+ "epoch": 10.98,
240
+ "eval_runtime": 36.3321,
241
+ "eval_samples_per_second": 1.899,
242
+ "eval_steps_per_second": 0.248,
243
+ "step": 1800
244
  }
245
  ],
246
  "logging_steps": 100,
247
  "max_steps": 1804,
248
  "num_train_epochs": 11,
249
  "save_steps": 100,
250
+ "total_flos": 1.5050311081132032e+17,
251
  "trial_name": null,
252
  "trial_params": null
253
  }