auxyus commited on
Commit
dea6f47
·
verified ·
1 Parent(s): 94c89bf

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 sha256:17f43c4e908fa649a6e0b950bee7fe730e9026abb57ef9987595f257953777d9
3
  size 73911112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb3ae4af331d3d46eff187dd0973f7c9cb15a64172396d8230cba38f5036f7aa
3
  size 73911112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b5dd0bb4b4e8b7983cdc0750220729df0689f1dfff0b58882450f989ac05d31
3
  size 37965300
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ff46d57480b6d02a5ec601a398957f6d6d40027cf3f4327871b035d8e122cb5
3
  size 37965300
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:18a55733c512b33a1d8d4cc1387f7f6f5a8dcc0f715abbe53c564c0d6e191dc6
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ee30e1de861cb5d531a3ca06c5b85c789d099fe249b46222ebbd707f4f8516c0
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": 0.050590219224283306,
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": 18.178,
306
  "eval_steps_per_second": 2.275,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 4.702567812562944e+16,
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": 0.05564924114671164,
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": 18.178,
306
  "eval_steps_per_second": 2.275,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.05227655986509275,
311
+ "grad_norm": 0.1683541089296341,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 0.6752,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.05396290050590219,
318
+ "grad_norm": 0.16768647730350494,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 0.7573,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.05564924114671164,
325
+ "grad_norm": 0.15775783360004425,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 0.6528,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.05564924114671164,
332
+ "eval_loss": 0.7322031259536743,
333
+ "eval_runtime": 164.8241,
334
+ "eval_samples_per_second": 18.183,
335
+ "eval_steps_per_second": 2.275,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 5.172824593819238e+16,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null