Hanzalwi commited on
Commit
d78927d
1 Parent(s): 438b956

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 sha256:46acb56ce81b9eaa130934ed581f496e538b7cca77114ea1be2f527e65ae8b45
3
  size 12595704
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a73e09e6cc72ba5d62b370d3a119ef23abf1462124e9ba7df16446c8c5d46bdc
3
  size 12595704
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13fcd684a8fbe2c7ab67a043a274177a1562c28e73742210c1567d468d3b4ee1
3
  size 25222341
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d323a7cad34c4b752cd3bdf60d11fdb3013978e1356244431064232f338d51b
3
  size 25222341
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c78706d744471c89dd06ac547d70d23cf235b0473edb572795996232735d747
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9cf68bdef8c75cb1972eb4442e671e85f5e6c9feb32427f2e8036e7ab01b09d0
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": 1.0725194215774536,
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": 10.326,
274
  "eval_steps_per_second": 1.295,
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": 2.6860284067270656e+17,
284
  "trial_name": null,
285
  "trial_params": null
286
  }
 
1
  {
2
  "best_metric": 1.0725194215774536,
3
  "best_model_checkpoint": "./outputs/checkpoint-1900",
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": 10.326,
274
  "eval_steps_per_second": 1.295,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 2.67,
279
+ "learning_rate": 0.0002,
280
+ "loss": 0.9309,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 2.67,
285
+ "eval_loss": 1.0725408792495728,
286
+ "eval_runtime": 186.323,
287
+ "eval_samples_per_second": 10.358,
288
+ "eval_steps_per_second": 1.299,
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": 2.8274374036682342e+17,
298
  "trial_name": null,
299
  "trial_params": null
300
  }