dixedus commited on
Commit
5caddd4
·
verified ·
1 Parent(s): b381244

Training in progress, step 90, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6f2a793ec2910f712bcf16365ea9c3505bcf1a2cb5032e5a76d055ed84fb6091
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ac004e32736b382d7db7b4cc7513153031fe4f925be20185d1412efc9e8c238e
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:eac729fe5ba8dd2f54b1bfa655b168e0fd5a8cb1d9782b709e9d12ef4dadc08e
3
  size 111142
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474bf252fb832c440025dd77bdebfe81c5d01507c659a7712bf6bd11d405d395
3
  size 111142
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:be622379442f4c64d8348dba7b9c8f3e2c7f0248e9290c8bd054cb94a5fb513d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:caf3df79d32802077abb14f00f426d66e8451b2d6bb5137f21895e49735502ae
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
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": 0.05924300603400987,
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,
@@ -276,6 +276,35 @@
276
  "eval_samples_per_second": 387.442,
277
  "eval_steps_per_second": 48.451,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 12160318832640.0,
299
  "train_batch_size": 8,
300
  "trial_name": null,
301
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06582556226001098,
5
  "eval_steps": 9,
6
+ "global_step": 90,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
276
  "eval_samples_per_second": 387.442,
277
  "eval_steps_per_second": 48.451,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.061437191442676904,
282
+ "grad_norm": 0.05520528927445412,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 10.3517,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.06363137685134394,
289
+ "grad_norm": 0.058600787073373795,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 10.358,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.06582556226001098,
296
+ "grad_norm": 0.05863627418875694,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 10.359,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.06582556226001098,
303
+ "eval_loss": 10.355664253234863,
304
+ "eval_runtime": 5.9304,
305
+ "eval_samples_per_second": 388.34,
306
+ "eval_steps_per_second": 48.564,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 13415577550848.0,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null