avsolatorio commited on
Commit
14632c9
1 Parent(s): 14ec2fb

Training in progress, step 15000, checkpoint

Browse files
last-checkpoint/model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8872fada1a981cf6b5a3b4e8ccf8c61843bbeb383d907f5afdf234ab3625087d
3
  size 567860028
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e92461c0a337d1dd2bff405603253f8264e3af53e9d34c5802a4e32340a674d
3
  size 567860028
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9d3d3afd06995d892904de019bc49182323dd2135abf4e4a204ebe2485e31f61
3
  size 1135783354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eeb4a0be311b1e98139917e61cafec146b95b94d710cbcf004fe9cd4dc0274a7
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:b3067b28aa64de4757065dd8a01a67d3704c9818184e3b87673b274005079225
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2ade8cbdb5c0dd1f6c03e792fe42b4b1893a6c42ae7b8ee252e85a63008e936
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33ec0c6c7881febe86af83de0fd1c05de3d6b8cdacbf1d5a88958d9ee8777f33
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3bf1b4a06cfcf7ffbad3f6e707792c1da71ddc3c6fe8d02ca200ee95016b033
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": 0.03739364445209503,
3
  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-11000",
4
- "epoch": 6.903353057199211,
5
  "eval_steps": 1000,
6
- "global_step": 14000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -371,6 +371,32 @@
371
  "eval_samples_per_second": 571.184,
372
  "eval_steps_per_second": 2.254,
373
  "step": 14000
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
374
  }
375
  ],
376
  "logging_steps": 500,
@@ -399,7 +425,7 @@
399
  "attributes": {}
400
  }
401
  },
402
- "total_flos": 316297938560220.0,
403
  "train_batch_size": 4,
404
  "trial_name": null,
405
  "trial_params": null
 
1
  {
2
  "best_metric": 0.03739364445209503,
3
  "best_model_checkpoint": "doc-topic-model_eval-01_train-02/checkpoint-11000",
4
+ "epoch": 7.396449704142012,
5
  "eval_steps": 1000,
6
+ "global_step": 15000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
371
  "eval_samples_per_second": 571.184,
372
  "eval_steps_per_second": 2.254,
373
  "step": 14000
374
+ },
375
+ {
376
+ "epoch": 7.149901380670611,
377
+ "grad_norm": 0.21536009013652802,
378
+ "learning_rate": 1.8570315581854045e-05,
379
+ "loss": 0.0253,
380
+ "step": 14500
381
+ },
382
+ {
383
+ "epoch": 7.396449704142012,
384
+ "grad_norm": 0.20045433938503265,
385
+ "learning_rate": 1.8521005917159765e-05,
386
+ "loss": 0.0234,
387
+ "step": 15000
388
+ },
389
+ {
390
+ "epoch": 7.396449704142012,
391
+ "eval_accuracy": 0.9876213557832674,
392
+ "eval_f1": 0.6177680525164114,
393
+ "eval_loss": 0.03792005032300949,
394
+ "eval_precision": 0.7265054040144107,
395
+ "eval_recall": 0.5373429767795965,
396
+ "eval_runtime": 14.2941,
397
+ "eval_samples_per_second": 567.368,
398
+ "eval_steps_per_second": 2.239,
399
+ "step": 15000
400
  }
401
  ],
402
  "logging_steps": 500,
 
425
  "attributes": {}
426
  }
427
  },
428
+ "total_flos": 338806210140648.0,
429
  "train_batch_size": 4,
430
  "trial_name": null,
431
  "trial_params": null