avsolatorio commited on
Commit
a3d8c2b
1 Parent(s): 1716517

Training in progress, step 11000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a29bdd6dd99b89c77d6304028688587d1b8726526a52d214cd23379fdecaebbe
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:75cff0201fb04f7e432cdd3591c2fd402738370e09f6d8455d837e5c3cba220d
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1f09c406b05c324524d6a329f73f7a6945c206dde699341114fe910ad244dee5
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca2ba0f1a59da394029688bd7f74cc19e6fd0e3ce1ba6f4ac6132838494c2786
3
  size 1135783354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b7e320b5a2475507aebb5f1ef7a9c98d12600ef0165cc1de949f181761d986b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef6b86d20d6ecc4df3a0c586eaefe72e249b74f60cbccfafd813b5495f54c4f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d33ebaa07fbbf9d04ea7e6a7b80d3a50929ab3c541f194d4f807567dfec05d5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f575d719835851124a9879abd7b08dea2c333d05d2e7d3bcd4c9a0a05b509d
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.038497649133205414,
3
- "best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-10000",
4
- "epoch": 4.928536224741252,
5
  "eval_steps": 1000,
6
- "global_step": 10000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -267,6 +267,32 @@
267
  "eval_samples_per_second": 564.067,
268
  "eval_steps_per_second": 2.226,
269
  "step": 10000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
270
  }
271
  ],
272
  "logging_steps": 500,
@@ -295,7 +321,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 226752528864816.0,
299
  "train_batch_size": 4,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.037736039608716965,
3
+ "best_model_checkpoint": "doc-topic-model_eval-01_train-04/checkpoint-11000",
4
+ "epoch": 5.421389847215377,
5
  "eval_steps": 1000,
6
+ "global_step": 11000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
267
  "eval_samples_per_second": 564.067,
268
  "eval_steps_per_second": 2.226,
269
  "step": 10000
270
+ },
271
+ {
272
+ "epoch": 5.1749630359783145,
273
+ "grad_norm": 0.3740977942943573,
274
+ "learning_rate": 1.8965007392804338e-05,
275
+ "loss": 0.0303,
276
+ "step": 10500
277
+ },
278
+ {
279
+ "epoch": 5.421389847215377,
280
+ "grad_norm": 0.37522149085998535,
281
+ "learning_rate": 1.891582060128142e-05,
282
+ "loss": 0.0295,
283
+ "step": 11000
284
+ },
285
+ {
286
+ "epoch": 5.421389847215377,
287
+ "eval_accuracy": 0.9871380585909265,
288
+ "eval_f1": 0.6012916831422169,
289
+ "eval_loss": 0.037736039608716965,
290
+ "eval_precision": 0.7108871805526699,
291
+ "eval_recall": 0.520974495622383,
292
+ "eval_runtime": 14.3748,
293
+ "eval_samples_per_second": 564.184,
294
+ "eval_steps_per_second": 2.226,
295
+ "step": 11000
296
  }
297
  ],
298
  "logging_steps": 500,
 
321
  "attributes": {}
322
  }
323
  },
324
+ "total_flos": 249475098303882.0,
325
  "train_batch_size": 4,
326
  "trial_name": null,
327
  "trial_params": null