ramdhanfirdaus commited on
Commit
1143987
1 Parent(s): e8fa512

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 sha256:8d0fddb20473efac1286eda903a7514b7d159a3db2c500a2598036838e125f99
3
  size 50338848
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:81527ea9e608599fe95a6448599fa180cd55477fb1291875bdc1a547880a7ca1
3
  size 50338848
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c9f5b6eaea4479fa0199aac028fed659f7828b4b456558aac671ac5f404d448a
3
  size 100693001
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9b1c840d7e2335a61e732e072cb0dccd604349c37336d989f068f3908ba67fa4
3
  size 100693001
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:4b260e5aa5c575d02f510db3424cb2898335e8d38fcdc4bec564683729218a6b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c134cfa86adc7fd0d893de0ed5f1d042c69cb03ed5bb956e86d5d878b172fe1
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:496140aa30b21578f6775ba5236d745f834471c83d84a366a20359624c56b122
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d466bcdc36eef33e32dd1288944b590d249986f908ba4cdb9b0a666ab8a33427
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.5939785242080688,
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": 43.706,
274
  "eval_steps_per_second": 5.468,
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": 1.1315157627172454e+17,
283
  "trial_name": null,
284
  "trial_params": null
285
  }
 
1
  {
2
+ "best_metric": 1.5781009197235107,
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": 43.706,
274
  "eval_steps_per_second": 5.468,
275
  "step": 1900
276
+ },
277
+ {
278
+ "epoch": 1.46,
279
+ "learning_rate": 0.0002,
280
+ "loss": 1.5723,
281
+ "step": 2000
282
+ },
283
+ {
284
+ "epoch": 1.46,
285
+ "eval_loss": 1.5781009197235107,
286
+ "eval_runtime": 143.4468,
287
+ "eval_samples_per_second": 43.737,
288
+ "eval_steps_per_second": 5.472,
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": 1.1910623325700915e+17,
297
  "trial_name": null,
298
  "trial_params": null
299
  }