dixedus commited on
Commit
a108bd8
·
verified ·
1 Parent(s): d6d7d1e

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:fb11a2b7915357d44fcf0b568553daeb139aabe03f2a1582e3c5258b38b8054b
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33116f53cd2af9d2453ad151a9cb859b87d2920e96cd5c9a5b32fe5427efdf52
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d26bfe3b6dcf2986bd1e99015575904eff176446c711436daa55c12327d6bec
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a061a58ac6d3c360b3986c8cf928c53ee385dec3c173e39a371a89c430a68013
3
  size 81730196
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5b28d32e44f1b86535ab5c43f746f36446a2f15908fbf88502e3cd1ccb9dd7ad
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e17e59518a33349d3e7ccb2a3d6202e23618632431c2022d3d7024a72198bc7
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": 0.00875131674904789,
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": 6.927,
277
  "eval_steps_per_second": 0.866,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 2.135908571550843e+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": 0.009723685276719877,
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": 6.927,
277
  "eval_steps_per_second": 0.866,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 0.009075439591605219,
282
+ "grad_norm": 0.8182294964790344,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 1.7684,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 0.009399562434162548,
289
+ "grad_norm": 0.8671604990959167,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 1.8174,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 0.009723685276719877,
296
+ "grad_norm": 0.8588350415229797,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 1.7666,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 0.009723685276719877,
303
+ "eval_loss": 1.7697868347167969,
304
+ "eval_runtime": 2249.367,
305
+ "eval_samples_per_second": 6.93,
306
+ "eval_steps_per_second": 0.866,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 2.3732317461676032e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null