avsolatorio commited on
Commit
d59bdf2
1 Parent(s): 8d99c04

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 sha256:9524abf571f381ab467394332b60f92d8a68f46c1e26127034ed52a5bf5b7c6f
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e57af6d0264134e1a162bcfb3aa14cc30aa29fa31a292f9ff45b9499a1218c3f
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:12f564e11824fd13f47c0e8b598087bcb5bd2c2abcb35bd00154ba446a413a23
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:034a233bc1d79601e0eb13ff5bc45f0821be2f8026e4748c83964a8ac7a7afa7
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": 0.04293818399310112,
3
- "best_model_checkpoint": "doc-topic-model_eval-04_train-00/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": 565.238,
164
  "eval_steps_per_second": 2.229,
165
  "step": 6000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
166
  }
167
  ],
168
  "logging_steps": 500,
@@ -191,7 +217,7 @@
191
  "attributes": {}
192
  }
193
  },
194
- "total_flos": 135828564625332.0,
195
  "train_batch_size": 4,
196
  "trial_name": null,
197
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.041109804064035416,
3
+ "best_model_checkpoint": "doc-topic-model_eval-04_train-00/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": 565.238,
164
  "eval_steps_per_second": 2.229,
165
  "step": 6000
166
+ },
167
+ {
168
+ "epoch": 3.2051282051282053,
169
+ "grad_norm": 0.3562796711921692,
170
+ "learning_rate": 1.935897435897436e-05,
171
+ "loss": 0.0412,
172
+ "step": 6500
173
+ },
174
+ {
175
+ "epoch": 3.4516765285996054,
176
+ "grad_norm": 0.24857360124588013,
177
+ "learning_rate": 1.930966469428008e-05,
178
+ "loss": 0.0384,
179
+ "step": 7000
180
+ },
181
+ {
182
+ "epoch": 3.4516765285996054,
183
+ "eval_accuracy": 0.9867872054358622,
184
+ "eval_f1": 0.551246270811279,
185
+ "eval_loss": 0.041109804064035416,
186
+ "eval_precision": 0.7417767417767418,
187
+ "eval_recall": 0.43859111791730476,
188
+ "eval_runtime": 14.583,
189
+ "eval_samples_per_second": 556.331,
190
+ "eval_steps_per_second": 2.194,
191
+ "step": 7000
192
  }
193
  ],
194
  "logging_steps": 500,
 
217
  "attributes": {}
218
  }
219
  },
220
+ "total_flos": 158396435368380.0,
221
  "train_batch_size": 4,
222
  "trial_name": null,
223
  "trial_params": null