Hanzalwi commited on
Commit
57927de
1 Parent(s): 6782719

Training in progress, step 2000, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bb21fc38b6e1a61b8c8cbf28a1ad57f09b3e5737d24f28b2a452d471ca5ca2e
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:734330beaad492891ff5f7fc9df9a2e1b069f2c4211ce697c6855f1a02cdfc32
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f16eb2dede13e2fdb04313cbb52f7e91a89c8d596d36cbaa70ec17303c83ff4c
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df4a54290fafb95c4a6d1e942a73c358bc2ff92a9bc5868ee328e710dde0905
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a5633f06ee7068396712f7cccd0b526b2f848878b47f6580e5d95109e7a8e98
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72f0bd9d86319639dfe9833d26a1acc00818f50c46f354bc07ae5eca24846d97
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b2d4b4cadcabd3e17adcc39c43d8312038a1f5c7f53125f288ba4de5ed25396b
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2911254167556763,
3
- "best_model_checkpoint": "./outputs/checkpoint-1900",
4
- "epoch": 2.533333333333333,
5
  "eval_steps": 100,
6
- "global_step": 1900,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -273,6 +273,20 @@
273
  "eval_samples_per_second": 12.716,
274
  "eval_steps_per_second": 1.595,
275
  "step": 1900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
276
  }
277
  ],
278
  "logging_steps": 100,
@@ -280,7 +294,7 @@
280
  "num_input_tokens_seen": 0,
281
  "num_train_epochs": 3,
282
  "save_steps": 100,
283
- "total_flos": 1.2108220870201344e+17,
284
  "trial_name": null,
285
  "trial_params": null
286
  }
 
1
  {
2
+ "best_metric": 1.2876315116882324,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2000",
4
+ "epoch": 2.6666666666666665,
5
  "eval_steps": 100,
6
+ "global_step": 2000,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
273
  "eval_samples_per_second": 12.716,
274
  "eval_steps_per_second": 1.595,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 2.67,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.0341,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 2.67,
285
+ "eval_loss": 1.2876315116882324,
286
+ "eval_runtime": 151.8147,
287
+ "eval_samples_per_second": 12.713,
288
+ "eval_steps_per_second": 1.594,
289
+ "step": 2000
290
  }
291
  ],
292
  "logging_steps": 100,
 
294
  "num_input_tokens_seen": 0,
295
  "num_train_epochs": 3,
296
  "save_steps": 100,
297
+ "total_flos": 1.2745693497470976e+17,
298
  "trial_name": null,
299
  "trial_params": null
300
  }