rizkyjun commited on
Commit
29e9925
1 Parent(s): 3e29ff6

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 sha256:4eb21b3d7a25488c2576bd971ed67a911c0d9b7b89195c14d2179bf6b7ceb743
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ed986a30c89a035286fcde611da36e9564116f693293ca4f7c507c62928ddaf
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d27667366c490ce36f7af5af3a82f5070d24e1851be4ddb43c9e5bb9cd172c84
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7389276df18e251c25a156be77e8b803cf65ffdac4a4785d223acc1767a0ad8a
3
  size 18902665
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:41425018b484575f28a5ea543894d6ee6cdc9e01846d0ddaa36b7e88cc98504f
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e1d9e3c6fddcf57fc2aabd22296e90ae548cdb72410388a1385f5736629c4e
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": 2.229428291320801,
3
- "best_model_checkpoint": "./outputs/checkpoint-1900",
4
- "epoch": 1.384335154826958,
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,
@@ -273,13 +273,27 @@
273
  "eval_samples_per_second": 30.257,
274
  "eval_steps_per_second": 3.786,
275
  "step": 1900
 
 
 
 
 
 
 
 
 
 
 
 
 
 
276
  }
277
  ],
278
  "logging_steps": 100,
279
  "max_steps": 4116,
280
  "num_train_epochs": 3,
281
  "save_steps": 100,
282
- "total_flos": 5.552186242885632e+16,
283
  "trial_name": null,
284
  "trial_params": null
285
  }
 
1
  {
2
+ "best_metric": 2.214716911315918,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2000",
4
+ "epoch": 1.4571948998178508,
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": 30.257,
274
  "eval_steps_per_second": 3.786,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 2.1939,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 2.214716911315918,
286
+ "eval_runtime": 207.5218,
287
+ "eval_samples_per_second": 30.233,
288
+ "eval_steps_per_second": 3.783,
289
+ "step": 2000
290
  }
291
  ],
292
  "logging_steps": 100,
293
  "max_steps": 4116,
294
  "num_train_epochs": 3,
295
  "save_steps": 100,
296
+ "total_flos": 5.844081922689024e+16,
297
  "trial_name": null,
298
  "trial_params": null
299
  }