brixeus commited on
Commit
23dc777
·
verified ·
1 Parent(s): acfde0a

Training in progress, step 90, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:514624e8caa7138b89314ee0f940cd757882c866b8affecbb6b0c7ea3f8b1da4
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b45806395e9da2ebf0a7065a5560c457e522d26c8d2a4f258b7095a0559ea892
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:79f27a7441303a26dbf11c4d29cfdb0c36a996dee976afa4496f431272a5a2d6
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e804bf5c8501502bf11dd61d26aef9b28af8f8f0a0b7cba07ce1ba4d7b9bb83
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eaef23ad6b9358048cfa2eb81866d8f39693a1c7df686b619cd9d9ea3051d3a5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b202cc35d4d82828b46ac25c2aa3b0d5b24c9fdd644bb03957f013b307cbc71d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
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": 0.0934795152914022,
5
  "eval_steps": 9,
6
- "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -276,6 +276,35 @@
276
  "eval_samples_per_second": 13.969,
277
  "eval_steps_per_second": 1.751,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 1.1357313258907238e+17,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.10386612810155799,
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,
 
276
  "eval_samples_per_second": 13.969,
277
  "eval_steps_per_second": 1.751,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.09694171956145413,
282
+ "grad_norm": 3.5582807064056396,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 7.6637,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.10040392383150606,
289
+ "grad_norm": 4.048159122467041,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 7.3083,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.10386612810155799,
296
+ "grad_norm": 3.8467483520507812,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 7.7565,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.10386612810155799,
303
+ "eval_loss": 1.91769278049469,
304
+ "eval_runtime": 104.4893,
305
+ "eval_samples_per_second": 13.973,
306
+ "eval_steps_per_second": 1.751,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 1.2619236954341376e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null