ramdhanfirdaus commited on
Commit
9a278c6
1 Parent(s): d4149fb

Training in progress, step 2100, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e3c03df6bdc57583ce2a0b202fd2910f87efcf714826e731c9a3f379423fcd3
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ee445f42259eb708388e06a716c810a7efa682c6cbf2ba3e4b2a76cf3094c49
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b4bf684c11a2d0b3275af783a686d4f55bcbd0d676ab3fb7d3230f8bdf6e213a
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6450889938176d33a2c2905f2f7a13aef03aa0222e78e5871f21fe99bda36c83
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b844b6d05ca4a0d574e8b563577b5a55af86779b464ff872bc6a0d1764aa57d5
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2eac30a54a346eb77c88df167a4adbf13ea272bd1dd65fd9f0292631c36fab66
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.4579730033874512,
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,
@@ -287,13 +287,27 @@
287
  "eval_samples_per_second": 43.613,
288
  "eval_steps_per_second": 5.457,
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": 1.192408030183342e+17,
297
  "trial_name": null,
298
  "trial_params": null
299
  }
 
1
  {
2
+ "best_metric": 1.4419173002243042,
3
+ "best_model_checkpoint": "./outputs/checkpoint-2100",
4
+ "epoch": 1.530054644808743,
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,
 
287
  "eval_samples_per_second": 43.613,
288
  "eval_steps_per_second": 5.457,
289
  "step": 2000
290
+ },
291
+ {
292
+ "epoch": 1.53,
293
+ "learning_rate": 0.0002,
294
+ "loss": 1.437,
295
+ "step": 2100
296
+ },
297
+ {
298
+ "epoch": 1.53,
299
+ "eval_loss": 1.4419173002243042,
300
+ "eval_runtime": 143.8022,
301
+ "eval_samples_per_second": 43.629,
302
+ "eval_steps_per_second": 5.459,
303
+ "step": 2100
304
  }
305
  ],
306
  "logging_steps": 100,
307
  "max_steps": 4116,
308
  "num_train_epochs": 3,
309
  "save_steps": 100,
310
+ "total_flos": 1.2520111653502157e+17,
311
  "trial_name": null,
312
  "trial_params": null
313
  }