ramdhanfirdaus commited on
Commit
2c49f60
1 Parent(s): 42256be

Training in progress, step 2300, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:557525ab6ebf99073c6638ccd8f4e685491ddbca038630e83e2ed6fb924b97a7
3
  size 75507072
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b224bb2144b166ed0f3223f5de34c9a9ae294eff60b66b723c7a6b541a045cf
3
  size 75507072
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abca4028050388bba9551352fb284a9b11c16805490da76ac91ccb3ae62cf5ca
3
  size 151034501
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:20d523a25eb3995eb7b033b67953af8ff66244daec4522a6d2b2f5c78796dd36
3
  size 151034501
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:01bdbeb5937e67c48029bfb76c4643cade36da9398930f69b0a6221a6ee4eb33
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0ecaa372dca690ec2f6181df8c7b03d3248836d0042c5e635eada8af4366c91
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58c098aa199ff890a6444b804a3fbc89c9468b8e4fb7f53db1b50396e4ed0c2d
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.259511113166809,
3
- "best_model_checkpoint": "./outputs/checkpoint-2200",
4
- "epoch": 1.6029143897996359,
5
  "eval_steps": 100,
6
- "global_step": 2200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -315,13 +315,27 @@
315
  "eval_samples_per_second": 15.022,
316
  "eval_steps_per_second": 1.88,
317
  "step": 2200
 
 
 
 
 
 
 
 
 
 
 
 
 
 
318
  }
319
  ],
320
  "logging_steps": 100,
321
  "max_steps": 4116,
322
  "num_train_epochs": 3,
323
  "save_steps": 100,
324
- "total_flos": 7.133138222904146e+17,
325
  "trial_name": null,
326
  "trial_params": null
327
  }
 
1
  {
2
+ "best_metric": 1.2497906684875488,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2300",
4
+ "epoch": 1.6757741347905282,
5
  "eval_steps": 100,
6
+ "global_step": 2300,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
315
  "eval_samples_per_second": 15.022,
316
  "eval_steps_per_second": 1.88,
317
  "step": 2200
318
+ },
319
+ {
320
+ "epoch": 1.68,
321
+ "learning_rate": 0.0002,
322
+ "loss": 1.2436,
323
+ "step": 2300
324
+ },
325
+ {
326
+ "epoch": 1.68,
327
+ "eval_loss": 1.2497906684875488,
328
+ "eval_runtime": 417.7302,
329
+ "eval_samples_per_second": 15.019,
330
+ "eval_steps_per_second": 1.879,
331
+ "step": 2300
332
  }
333
  ],
334
  "logging_steps": 100,
335
  "max_steps": 4116,
336
  "num_train_epochs": 3,
337
  "save_steps": 100,
338
+ "total_flos": 7.457059409239757e+17,
339
  "trial_name": null,
340
  "trial_params": null
341
  }