mamung commited on
Commit
9005d54
·
verified ·
1 Parent(s): 5888329

Training in progress, step 81, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:117e138d442add83d89cc88f627fd24d5f8db7ffb432d4a6c70faf0d4fc9ad2c
3
  size 4628218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21154256a977650e0f741b040e34e73fa2f16d280482259df83a4466d5b0cc61
3
  size 4628218
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ebc356da7830c54c054fafbcc62e661641ed179b2053ebeee944a97351b0a94e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5add46d4d28bcb535d1631fb310b8516b9bf2635f833c5c8df60d5713872d3ee
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d43bd90ad476e419738deb9472ad85fd5991005a147e1627aa99867bdfc5655
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09ab64d5ace66796aa9c2fa2fc4e0206d69a1eb4ef03f574f85ee8eb16a64b71
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.1304938830992297,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -177,6 +177,28 @@
177
  "eval_samples_per_second": 284.921,
178
  "eval_steps_per_second": 35.724,
179
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
180
  }
181
  ],
182
  "logging_steps": 5,
@@ -196,7 +218,7 @@
196
  "attributes": {}
197
  }
198
  },
199
- "total_flos": 1287527281459200.0,
200
  "train_batch_size": 8,
201
  "trial_name": null,
202
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.14680561848663343,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
177
  "eval_samples_per_second": 284.921,
178
  "eval_steps_per_second": 35.724,
179
  "step": 72
180
+ },
181
+ {
182
+ "epoch": 0.13593112822836428,
183
+ "grad_norm": NaN,
184
+ "learning_rate": 3.333223252352985e-05,
185
+ "loss": 0.0,
186
+ "step": 75
187
+ },
188
+ {
189
+ "epoch": 0.14499320344358857,
190
+ "grad_norm": NaN,
191
+ "learning_rate": 2.1966991411008938e-05,
192
+ "loss": 0.0,
193
+ "step": 80
194
+ },
195
+ {
196
+ "epoch": 0.14680561848663343,
197
+ "eval_loss": NaN,
198
+ "eval_runtime": 6.8785,
199
+ "eval_samples_per_second": 285.236,
200
+ "eval_steps_per_second": 35.764,
201
+ "step": 81
202
  }
203
  ],
204
  "logging_steps": 5,
 
218
  "attributes": {}
219
  }
220
  },
221
+ "total_flos": 1449310814208000.0,
222
  "train_batch_size": 8,
223
  "trial_name": null,
224
  "trial_params": null