Hanzalwi commited on
Commit
fd04067
1 Parent(s): 239d39e

Training in progress, step 2200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:077213219e8b8677999bcb2593f6400f44ad43e7392cc494ad1fc5c13084077e
3
  size 6298560
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3371f13b66c969eb7ee06a87886d59c9177868b32e16052618f0ce92c817396c
3
  size 6298560
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eb2c775ed3ea7c96df0449c20bca12ac19d6c8a9ae24fdc13c21b40f8e36a895
3
  size 12611145
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67a38367f875f76bdb14f97bdb7183e64dc5d9b1267531c75f45bca500baca9d
3
  size 12611145
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a8cfcaec1f5911fc7c2b7c4eeaf66555768023f53d9ed79d8ed6b38d001dcf35
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3438fe6cf014af3dcfd560104641977a705ec397c5ca3c2f83734a38605b07ea
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f10a983aa914555fea6e5c0db8d7ddbaebbe7e28546c78ee0e93ac76cbc28436
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.1806031465530396,
3
- "best_model_checkpoint": "./outputs/checkpoint-2100",
4
- "epoch": 2.8,
5
  "eval_steps": 100,
6
- "global_step": 2100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -301,6 +301,20 @@
301
  "eval_samples_per_second": 3.92,
302
  "eval_steps_per_second": 0.491,
303
  "step": 2100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
304
  }
305
  ],
306
  "logging_steps": 100,
@@ -308,7 +322,7 @@
308
  "num_input_tokens_seen": 0,
309
  "num_train_epochs": 3,
310
  "save_steps": 100,
311
- "total_flos": 6.987573836110234e+16,
312
  "trial_name": null,
313
  "trial_params": null
314
  }
 
1
  {
2
+ "best_metric": 1.1772046089172363,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2200",
4
+ "epoch": 2.9333333333333336,
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,
 
301
  "eval_samples_per_second": 3.92,
302
  "eval_steps_per_second": 0.491,
303
  "step": 2100
304
+ },
305
+ {
306
+ "epoch": 2.93,
307
+ "learning_rate": 0.0002,
308
+ "loss": 0.9663,
309
+ "step": 2200
310
+ },
311
+ {
312
+ "epoch": 2.93,
313
+ "eval_loss": 1.1772046089172363,
314
+ "eval_runtime": 491.1926,
315
+ "eval_samples_per_second": 3.929,
316
+ "eval_steps_per_second": 0.493,
317
+ "step": 2200
318
  }
319
  ],
320
  "logging_steps": 100,
 
322
  "num_input_tokens_seen": 0,
323
  "num_train_epochs": 3,
324
  "save_steps": 100,
325
+ "total_flos": 7.321308131141222e+16,
326
  "trial_name": null,
327
  "trial_params": null
328
  }