dixedus commited on
Commit
a390f90
·
verified ·
1 Parent(s): 6a8cc15

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 sha256:1a71b2f86053a13a4b914267a59fbaa9ad5d8e8efae67814ddc0cb0e36c43969
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9647adb27981853b26d82eeddc723e36144f864d61580d416f699ea91dcaefa
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6dc7954c9972a46c7bd05461331372430cccceebaea6f1d3c28d720fa1c763b1
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e47f36ad78f6f7604e3268f59728911c1aa62156f46a6c659ac6efcfed066dc7
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d473c2d08bf20f94f4fab65a52b5ac470f09ea13e785d77bab188afec69c558
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7e8c1b8811cba42117d1c35bab2d6e9ca27ecfe61350e3c045dcd0814b8dbb5
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": 2.1315789473684212,
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": 14.249,
277
  "eval_steps_per_second": 1.781,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 1.132918702300201e+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": 2.3684210526315788,
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": 14.249,
277
  "eval_steps_per_second": 1.781,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 2.2105263157894735,
282
+ "grad_norm": 7.621229648590088,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 1.5441,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 2.2894736842105265,
289
+ "grad_norm": 6.870114803314209,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 1.5711,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 2.3684210526315788,
296
+ "grad_norm": 7.845399379730225,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 1.504,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 2.3684210526315788,
303
+ "eval_loss": 0.7961782217025757,
304
+ "eval_runtime": 4.497,
305
+ "eval_samples_per_second": 14.232,
306
+ "eval_steps_per_second": 1.779,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 1.2594821570179891e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null