Hanzalwi commited on
Commit
ced4e2a
1 Parent(s): ab9298d

Training in progress, step 1800, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6157273021e0ff19574630eee80b638867f923006bf5ef26df6a0f45536d8a9b
3
  size 9444296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e59e9d66c6abe3766a4795909850028ef3eecad1e36266bb406469eadcac77a
3
  size 9444296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b27e98f9ad862a2b7b5bebd6b6b36aaa531a06e1cc4d392a6fad11843326a611
3
  size 18902665
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:47d8db54698873fb17c6207f0160eb623a648b156acdac11c8477660eccbd519
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:e9e557b1e77c85fe07b1ec3d978d1fe6eca72d96d47ae9e1632080936f73f36b
3
  size 14575
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d72d4610256ec3210e9ec5e1eee2b9b0106afc774d4eee7e345554af1a495e2b
3
  size 14575
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
3
  size 627
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
3
  size 627
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.2983750104904175,
3
- "best_model_checkpoint": "./outputs/checkpoint-1700",
4
- "epoch": 2.2666666666666666,
5
  "eval_steps": 100,
6
- "global_step": 1700,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -245,6 +245,20 @@
245
  "eval_samples_per_second": 12.901,
246
  "eval_steps_per_second": 1.618,
247
  "step": 1700
 
 
 
 
 
 
 
 
 
 
 
 
 
 
248
  }
249
  ],
250
  "logging_steps": 100,
@@ -252,7 +266,7 @@
252
  "num_input_tokens_seen": 0,
253
  "num_train_epochs": 3,
254
  "save_steps": 100,
255
- "total_flos": 1.0816203102437376e+17,
256
  "trial_name": null,
257
  "trial_params": null
258
  }
 
1
  {
2
+ "best_metric": 1.29191255569458,
3
+ "best_model_checkpoint": "./outputs/checkpoint-1800",
4
+ "epoch": 2.4,
5
  "eval_steps": 100,
6
+ "global_step": 1800,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
245
  "eval_samples_per_second": 12.901,
246
  "eval_steps_per_second": 1.618,
247
  "step": 1700
248
+ },
249
+ {
250
+ "epoch": 2.4,
251
+ "learning_rate": 0.0002,
252
+ "loss": 1.0441,
253
+ "step": 1800
254
+ },
255
+ {
256
+ "epoch": 2.4,
257
+ "eval_loss": 1.29191255569458,
258
+ "eval_runtime": 112.4345,
259
+ "eval_samples_per_second": 12.905,
260
+ "eval_steps_per_second": 1.619,
261
+ "step": 1800
262
  }
263
  ],
264
  "logging_steps": 100,
 
266
  "num_input_tokens_seen": 0,
267
  "num_train_epochs": 3,
268
  "save_steps": 100,
269
+ "total_flos": 1.1450811615215616e+17,
270
  "trial_name": null,
271
  "trial_params": null
272
  }