brixeus commited on
Commit
ca6e7b1
·
verified ·
1 Parent(s): a22d8e2

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:256d7b0364ce08d05ce7e7fa030997236dd61c9eeab760c183296bac80be173c
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b6afdeb786156a4ca5f1f8608a742108c5ae455a4d70dfc9f82a5f3d5f81921
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:412121c10f738a940c3d1638e6f4d589cdcc31908f3d7530e4a2e16a3644b624
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33a628eb4008f5e04cf3e87a261d90f60d654247fe031fdac3e87f32d5c8e9fe
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:dc035f9a226a227cf75c9503cec9ab273f9add4d937ca11d5a322e17d720ce7a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a78116a1a3cc61ec4cd22d66a4d69d6de853ed4df4f21995f474568d06c3153
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 2.3684210526315788,
5
  "eval_steps": 9,
6
- "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 14.027,
306
  "eval_steps_per_second": 1.753,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.2594821570179891e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 2.6052631578947367,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 14.027,
306
  "eval_steps_per_second": 1.753,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 2.4473684210526314,
311
+ "grad_norm": 6.9743523597717285,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.5261,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 2.526315789473684,
318
+ "grad_norm": 7.8254241943359375,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.4583,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 2.6052631578947367,
325
+ "grad_norm": 7.711915016174316,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.4774,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 2.6052631578947367,
332
+ "eval_loss": 0.7982271313667297,
333
+ "eval_runtime": 4.5631,
334
+ "eval_samples_per_second": 14.025,
335
+ "eval_steps_per_second": 1.753,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.3860456117357773e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null