brixeus commited on
Commit
af8c7fa
·
verified ·
1 Parent(s): fbdec12

Training in progress, step 99, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:157894532301c27df1dc68f43caf915ca1e93d6c3f93fb50ea8579ada468927b
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb4eeba702da0761b96103f15c1b5d00ee472965dd99e636192164b3978e5d5e
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:75a1f39676ab6e121cbb172abc3186759ab9cdf34c3975f2a6cd617889ad844a
3
  size 81730196
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e2d3c5ff8b58ea002c42a0a8bcae6ec28ce5ad14e5878c54cd852632ec5b67e
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:da19528665d7393dfd8135becd77f3e29c6e632c0d585c2ac21b37a3ccd854cc
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d657cb52b1d0da5353392589a89431a45005fe7acb1cf93575065a99de43df7
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5b64833e2721bfb57dae2a544bde34ace02492c2f80bfbff48034c9946dc6b4a
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": 0.05851755526657997,
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,
@@ -305,6 +305,35 @@
305
  "eval_samples_per_second": 15.217,
306
  "eval_steps_per_second": 1.903,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 1.1794920544351027e+17,
328
  "train_batch_size": 8,
329
  "trial_name": null,
330
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.06436931079323797,
5
  "eval_steps": 9,
6
+ "global_step": 99,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
305
  "eval_samples_per_second": 15.217,
306
  "eval_steps_per_second": 1.903,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 0.06046814044213264,
311
+ "grad_norm": 1.3437572717666626,
312
+ "learning_rate": 7.426068431000882e-07,
313
+ "loss": 2.7283,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 0.06241872561768531,
318
+ "grad_norm": 1.475144624710083,
319
+ "learning_rate": 2.4329828146074095e-07,
320
+ "loss": 2.8023,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 0.06436931079323797,
325
+ "grad_norm": 1.1647648811340332,
326
+ "learning_rate": 1.522932452260595e-08,
327
+ "loss": 2.8616,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 0.06436931079323797,
332
+ "eval_loss": 0.7154206037521362,
333
+ "eval_runtime": 170.168,
334
+ "eval_samples_per_second": 15.226,
335
+ "eval_steps_per_second": 1.904,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 1.2971145307776614e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null