clarxus commited on
Commit
147bb7b
·
verified ·
1 Parent(s): da9120e

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:db512f1b45379144d6d80eeae2c5d36ebe3194838652e3d66da47c1ec1912ea0
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ef19d9f243399c3d2c941fc985949d6a3e2e61a1246433bd2697e170137baca
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c4c9deaad46766ff8e4caabdcb4fd357606a69a76210fb23feb9eaab1da305e9
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:930d3e468372e83b6d0bb5b88765915033ac06b5fe0ca618a2a79ddd3e4ea9f4
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a6ab9b9869e601adf44834e3a12d4a18fbed8343468019356d2f3491dc62e15c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a5051a0e31a9165b3b43ecaf91c64aba598ba8800af01edf71cd1ee48db7cb7f
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": 0.04428044280442804,
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": 7.29,
277
  "eval_steps_per_second": 0.913,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 2.1188066446147584e+17,
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": 0.04920049200492005,
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": 7.29,
277
  "eval_steps_per_second": 0.913,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.04592045920459205,
282
+ "grad_norm": 0.1903477907180786,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 0.6178,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.04756047560475605,
289
+ "grad_norm": 0.19779753684997559,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 0.5633,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.04920049200492005,
296
+ "grad_norm": 0.20657652616500854,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 0.6083,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.04920049200492005,
303
+ "eval_loss": 0.6009935736656189,
304
+ "eval_runtime": 422.6386,
305
+ "eval_samples_per_second": 7.29,
306
+ "eval_steps_per_second": 0.913,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 2.3568005266931712e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null