leixa commited on
Commit
2fa7008
·
verified ·
1 Parent(s): cd96da7

Training in progress, step 81, 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:b38d7b6555d83a07d930ae602a5ac54b6d9afcd2ba67cd48c8ae06d6ca785af5
3
  size 402688040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bafff925e304e671a4ddc598bfe06cec5f8bcbe17b66fc1ff1bbcb7587306a94
3
  size 402688040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a40b8f1348a5aa857f26ee60d5d3f77f75d51cc0892c189ed06b43c3afc6f3c
3
  size 204773716
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a09f8541c24e6958cf92cd90b384f890f14926435c7e1d6351234050c81e72a4
3
  size 204773716
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c63140ddf559283cddcb5313678ca9c3d1182e1e697affce60f66dc4e18bd5b2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f1bcbc783ea307e9bf259e6fc8d6b97778e89b25d64a9a11dda62ea4d55bdf60
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.7346938775510204,
5
  "eval_steps": 9,
6
- "global_step": 72,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -247,6 +247,35 @@
247
  "eval_samples_per_second": 14.775,
248
  "eval_steps_per_second": 1.88,
249
  "step": 72
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
250
  }
251
  ],
252
  "logging_steps": 3,
@@ -266,7 +295,7 @@
266
  "attributes": {}
267
  }
268
  },
269
- "total_flos": 5.412096074317824e+16,
270
  "train_batch_size": 8,
271
  "trial_name": null,
272
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.826530612244898,
5
  "eval_steps": 9,
6
+ "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
247
  "eval_samples_per_second": 14.775,
248
  "eval_steps_per_second": 1.88,
249
  "step": 72
250
+ },
251
+ {
252
+ "epoch": 0.7653061224489796,
253
+ "grad_norm": 3.602689504623413,
254
+ "learning_rate": 1.7860619515673033e-05,
255
+ "loss": 6.447,
256
+ "step": 75
257
+ },
258
+ {
259
+ "epoch": 0.7959183673469388,
260
+ "grad_norm": 3.743265390396118,
261
+ "learning_rate": 1.4033009983067452e-05,
262
+ "loss": 6.4277,
263
+ "step": 78
264
+ },
265
+ {
266
+ "epoch": 0.826530612244898,
267
+ "grad_norm": 3.567052125930786,
268
+ "learning_rate": 1.0599462319663905e-05,
269
+ "loss": 6.7132,
270
+ "step": 81
271
+ },
272
+ {
273
+ "epoch": 0.826530612244898,
274
+ "eval_loss": 1.5810420513153076,
275
+ "eval_runtime": 11.1521,
276
+ "eval_samples_per_second": 14.795,
277
+ "eval_steps_per_second": 1.883,
278
+ "step": 81
279
  }
280
  ],
281
  "logging_steps": 3,
 
295
  "attributes": {}
296
  }
297
  },
298
+ "total_flos": 6.088608083607552e+16,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null