auxyus commited on
Commit
f35d113
·
verified ·
1 Parent(s): 8d36074

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 sha256:7c6ece5925a10ac734022f49da070ad1738233acaa151bd4acc27be0a0010004
3
  size 19552
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:978fc3a36aa02ff4e4b8e582a8df18c0a8742fe4c260e8e3b70fede03d059ca4
3
  size 19552
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88d61c4a84177bbc5ccfcae31aa7c60c549f2f3d7ecc5340cbcbaa56b24e05fd
3
  size 44354
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e6e0123ed99a9c8333b0e2ffadcbffd712caaeb4a962515e69f46ce18b91a479
3
  size 44354
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:72ae2062f3aec7235be787aa3ef15f1a5a6178e412fee2637434cc95b287ec3d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c45e8509362c8946d16db39b13d549197b82acbaa6f5959a7e441bdaff0afef
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": 1.4464285714285714,
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": 44.129,
277
  "eval_steps_per_second": 5.574,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 165932433408.0,
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": 1.6071428571428572,
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": 44.129,
277
  "eval_steps_per_second": 5.574,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 1.5,
282
+ "grad_norm": 0.03833044692873955,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 12.428,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 1.5535714285714286,
289
+ "grad_norm": 0.039569344371557236,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 12.4315,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 1.6071428571428572,
296
+ "grad_norm": 0.038590870797634125,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 12.4301,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 1.6071428571428572,
303
+ "eval_loss": 12.429823875427246,
304
+ "eval_runtime": 2.1528,
305
+ "eval_samples_per_second": 44.129,
306
+ "eval_steps_per_second": 5.574,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 185354158080.0,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null