auxyus commited on
Commit
b5f762b
·
verified ·
1 Parent(s): 9945bfb

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:f7388946537dc212b3617716a9131ce8da85283936c17738e6fdff8c77d0dded
3
  size 217931936
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca7d9a63df9f9fd467f0fc279009c89c3e960a665db8fdef86d689efc2447ee7
3
  size 217931936
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f43f1eeb605c4569cc6b7e111f42233d8d9cc9aaab31e48952c792d5826cf4e0
3
  size 111412180
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f8fc0d11ef6c34a739a596186855e6383971e7ec92b9ef06cefae34ddba8718f
3
  size 111412180
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5dc19870076a3cd22b0190add2deb01363f9d869716e763af6959ce3332cc326
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:29f06ac666ccb80cf862df33c085722e91c8899d64f85676a3f1501a8ce90745
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": 1.0909090909090908,
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": 11.069,
277
  "eval_steps_per_second": 1.417,
278
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
279
  }
280
  ],
281
  "logging_steps": 3,
@@ -295,7 +324,7 @@
295
  "attributes": {}
296
  }
297
  },
298
- "total_flos": 1.372501154117714e+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": 1.2121212121212122,
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": 11.069,
277
  "eval_steps_per_second": 1.417,
278
  "step": 81
279
+ },
280
+ {
281
+ "epoch": 1.1313131313131313,
282
+ "grad_norm": 0.0002512714418116957,
283
+ "learning_rate": 7.597595192178702e-06,
284
+ "loss": 0.0,
285
+ "step": 84
286
+ },
287
+ {
288
+ "epoch": 1.1717171717171717,
289
+ "grad_norm": 0.00025135595933534205,
290
+ "learning_rate": 5.060297685041659e-06,
291
+ "loss": 0.0,
292
+ "step": 87
293
+ },
294
+ {
295
+ "epoch": 1.2121212121212122,
296
+ "grad_norm": 0.00025588576681911945,
297
+ "learning_rate": 3.0153689607045845e-06,
298
+ "loss": 0.0,
299
+ "step": 90
300
+ },
301
+ {
302
+ "epoch": 1.2121212121212122,
303
+ "eval_loss": 7.283484137587948e-06,
304
+ "eval_runtime": 11.2861,
305
+ "eval_samples_per_second": 11.076,
306
+ "eval_steps_per_second": 1.418,
307
+ "step": 90
308
  }
309
  ],
310
  "logging_steps": 3,
 
324
  "attributes": {}
325
  }
326
  },
327
+ "total_flos": 1.5250601399864525e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null