avsolatorio commited on
Commit
1daf426
1 Parent(s): b404b99

Training in progress, step 7000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ab54cdd6804c1f69dcbb1927b975d5309301ea7f09f14368ff5cb936f54fbbe
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81f9391d1a3f7496c17b6f177cb61462c901e62e98a50edb8df8c02773379bd8
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f641ecb4950374542e19c7095a38f78489fe81cefbb63936c201a904573a2cdc
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a34883662b324dd1a0b9ef793b140ef0ea4d1cf9e31b8ec8a8255e7c14f6ee76
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5652cdeb5ebbadbe7a41c5bdef0e2c456fe9ce93c4c465bbbfd096c7a45e5ee6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f4902fcfb33d73ecfa5cb7dbd3cfd13500058abf1d6eae05ae197780b6416694
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40c676250ec219860d5697bba17ff8c0d4f32ee4dcb91bcc82789e7b28bcb701
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43495fd59fd541eb94253a07f3e011c2581153d25d7fa1816722e70a1a8e7f7f
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.044261422008275986,
3
- "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-6000",
4
- "epoch": 2.9585798816568047,
5
  "eval_steps": 1000,
6
- "global_step": 6000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -163,6 +163,32 @@
163
  "eval_samples_per_second": 561.645,
164
  "eval_steps_per_second": 2.216,
165
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  }
167
  ],
168
  "logging_steps": 500,
@@ -191,7 +217,7 @@
191
  "attributes": {}
192
  }
193
  },
194
- "total_flos": 135803170199520.0,
195
  "train_batch_size": 4,
196
  "trial_name": null,
197
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.04172312840819359,
3
+ "best_model_checkpoint": "doc-topic-model_eval-03_train-01/checkpoint-7000",
4
+ "epoch": 3.4516765285996054,
5
  "eval_steps": 1000,
6
+ "global_step": 7000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
163
  "eval_samples_per_second": 561.645,
164
  "eval_steps_per_second": 2.216,
165
  "step": 6000
166
+ },
167
+ {
168
+ "epoch": 3.2051282051282053,
169
+ "grad_norm": 0.3240315914154053,
170
+ "learning_rate": 1.935897435897436e-05,
171
+ "loss": 0.0424,
172
+ "step": 6500
173
+ },
174
+ {
175
+ "epoch": 3.4516765285996054,
176
+ "grad_norm": 0.39667147397994995,
177
+ "learning_rate": 1.930966469428008e-05,
178
+ "loss": 0.0389,
179
+ "step": 7000
180
+ },
181
+ {
182
+ "epoch": 3.4516765285996054,
183
+ "eval_accuracy": 0.9863174454696203,
184
+ "eval_f1": 0.5358653846153846,
185
+ "eval_loss": 0.04172312840819359,
186
+ "eval_precision": 0.7233904465212876,
187
+ "eval_recall": 0.42554978619425776,
188
+ "eval_runtime": 14.5013,
189
+ "eval_samples_per_second": 559.261,
190
+ "eval_steps_per_second": 2.207,
191
+ "step": 7000
192
  }
193
  ],
194
  "logging_steps": 500,
 
217
  "attributes": {}
218
  }
219
  },
220
+ "total_flos": 158408873454492.0,
221
  "train_batch_size": 4,
222
  "trial_name": null,
223
  "trial_params": null