mamung commited on
Commit
5888329
·
verified ·
1 Parent(s): db3af8c

Training in progress, step 72, checkpoint

Browse files
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b49e9ead3f21d202ff67fa2fb22fda92ce88919bafea33839ea997b143b774f
3
  size 4628218
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:117e138d442add83d89cc88f627fd24d5f8db7ffb432d4a6c70faf0d4fc9ad2c
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:b7ad175a076a7fd8f329187fe43465860040056030380e6abc5d9d77f2dda140
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ebc356da7830c54c054fafbcc62e661641ed179b2053ebeee944a97351b0a94e
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d85eac2daddfe8e3f78a5d6ef1e9ba13c04651694635a9ed76369a20726389db
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8d43bd90ad476e419738deb9472ad85fd5991005a147e1627aa99867bdfc5655
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": 0.11418214771182601,
5
  "eval_steps": 9,
6
- "global_step": 63,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -155,6 +155,28 @@
155
  "eval_samples_per_second": 285.551,
156
  "eval_steps_per_second": 35.803,
157
  "step": 63
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
158
  }
159
  ],
160
  "logging_steps": 5,
@@ -174,7 +196,7 @@
174
  "attributes": {}
175
  }
176
  },
177
- "total_flos": 1130237735731200.0,
178
  "train_batch_size": 8,
179
  "trial_name": null,
180
  "trial_params": null
 
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,
 
155
  "eval_samples_per_second": 285.551,
156
  "eval_steps_per_second": 35.803,
157
  "step": 63
158
+ },
159
+ {
160
+ "epoch": 0.11780697779791573,
161
+ "grad_norm": NaN,
162
+ "learning_rate": 6.036822584879038e-05,
163
+ "loss": 0.0,
164
+ "step": 65
165
+ },
166
+ {
167
+ "epoch": 0.12686905301314,
168
+ "grad_norm": NaN,
169
+ "learning_rate": 4.6298742572618266e-05,
170
+ "loss": 0.0,
171
+ "step": 70
172
+ },
173
+ {
174
+ "epoch": 0.1304938830992297,
175
+ "eval_loss": NaN,
176
+ "eval_runtime": 6.8861,
177
+ "eval_samples_per_second": 284.921,
178
+ "eval_steps_per_second": 35.724,
179
+ "step": 72
180
  }
181
  ],
182
  "logging_steps": 5,
 
196
  "attributes": {}
197
  }
198
  },
199
+ "total_flos": 1287527281459200.0,
200
  "train_batch_size": 8,
201
  "trial_name": null,
202
  "trial_params": null