lesso18 commited on
Commit
06be073
·
verified ·
1 Parent(s): 01c5de7

Training in progress, step 400, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c460c795486334879fe7cf479e29c7cb2036d0f38277ddd3b7d880eafb7b340
3
  size 389074464
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3833cd0ac15cb58e965e1fe964f2d730c9bc22aa3217feb7a43c6f35fab45e95
3
  size 389074464
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b602487d2d0edbaee18d88ee52a377d0fb838b663687b0ce9b565652381fe1b0
3
  size 198011700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f0f75600a1bc88c0be9a59ff8d846b84467168078c722d628c0784b0ef7ca05c
3
  size 198011700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:bd60e931e8b1cd48273897c56fa931b9635d29b2d344c46bfe0ed5e5e81df16d
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9abda639c2cfa293d536cf66b24d39666c85f8fe12c5ec6b2e6c3f2d17980cd8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9aefa5c0989fb1076f44dee5ec81119730caab480902e567590e4c3defecd81d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4be7b38aa7a01f117ebb95bff4f596a12bcbebf1c53b704b1e44c42b56276682
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.5349125862121582,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.06582040432534085,
5
  "eval_steps": 50,
6
- "global_step": 350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -316,6 +316,49 @@
316
  "eval_samples_per_second": 20.328,
317
  "eval_steps_per_second": 5.084,
318
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
319
  }
320
  ],
321
  "logging_steps": 10,
@@ -344,7 +387,7 @@
344
  "attributes": {}
345
  }
346
  },
347
- "total_flos": 3.791008947398246e+16,
348
  "train_batch_size": 4,
349
  "trial_name": null,
350
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5289891362190247,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-400",
4
+ "epoch": 0.07522331922896097,
5
  "eval_steps": 50,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
316
  "eval_samples_per_second": 20.328,
317
  "eval_steps_per_second": 5.084,
318
  "step": 350
319
+ },
320
+ {
321
+ "epoch": 0.06770098730606489,
322
+ "grad_norm": 0.721478283405304,
323
+ "learning_rate": 4.804797352168861e-05,
324
+ "loss": 0.6473,
325
+ "step": 360
326
+ },
327
+ {
328
+ "epoch": 0.06958157028678891,
329
+ "grad_norm": 0.6118484735488892,
330
+ "learning_rate": 4.189289918950325e-05,
331
+ "loss": 0.5278,
332
+ "step": 370
333
+ },
334
+ {
335
+ "epoch": 0.07146215326751293,
336
+ "grad_norm": 0.6939198970794678,
337
+ "learning_rate": 3.606476390688449e-05,
338
+ "loss": 0.516,
339
+ "step": 380
340
+ },
341
+ {
342
+ "epoch": 0.07334273624823695,
343
+ "grad_norm": 0.6780189275741577,
344
+ "learning_rate": 3.0591961763087043e-05,
345
+ "loss": 0.5085,
346
+ "step": 390
347
+ },
348
+ {
349
+ "epoch": 0.07522331922896097,
350
+ "grad_norm": 0.786106288433075,
351
+ "learning_rate": 2.550115570003141e-05,
352
+ "loss": 0.4749,
353
+ "step": 400
354
+ },
355
+ {
356
+ "epoch": 0.07522331922896097,
357
+ "eval_loss": 0.5289891362190247,
358
+ "eval_runtime": 109.4848,
359
+ "eval_samples_per_second": 20.45,
360
+ "eval_steps_per_second": 5.115,
361
+ "step": 400
362
  }
363
  ],
364
  "logging_steps": 10,
 
387
  "attributes": {}
388
  }
389
  },
390
+ "total_flos": 4.339236139224269e+16,
391
  "train_batch_size": 4,
392
  "trial_name": null,
393
  "trial_params": null