oldiday commited on
Commit
dca477d
·
verified ·
1 Parent(s): 7eced85

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 sha256:32da9f0d8803a172a33cc227c473a879d4ec2cf423d9aa889615c261d5962737
3
  size 262219392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b5123933b671618fe324f2014250792bc9096c20ff4691b821cf76c453ea55c
3
  size 262219392
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:523242a28b3ac3ee211467a4f5ddce7d76936eb6e69ae5c2c4c05696a1d7831f
3
  size 133777940
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e42b15cd57d56067f566978fcbbc0a536e4bb7bdfd85bed22fe60bafee3cfbf
3
  size 133777940
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:80a4b5751ba235d313a582d09297cb16fc8bcd065bbcdd466a3cc4df6c93c4e0
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0e0b1e6af3f27328b492c5dcc4a7d3c3624cc21184947dce7ecf3056b63a6dd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
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": 0.33707865168539325,
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": 9.2,
306
  "eval_steps_per_second": 1.165,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 2.643543629758464e+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": 0.3707865168539326,
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": 9.2,
306
  "eval_steps_per_second": 1.165,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.34831460674157305,
311
+ "grad_norm": 3.245680093765259,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 6.1023,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.3595505617977528,
318
+ "grad_norm": 2.9969637393951416,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 5.7552,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.3707865168539326,
325
+ "grad_norm": 3.160747766494751,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 5.9094,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.3707865168539326,
332
+ "eval_loss": 1.3485381603240967,
333
+ "eval_runtime": 48.9177,
334
+ "eval_samples_per_second": 9.199,
335
+ "eval_steps_per_second": 1.165,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.916073900867584e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null