leixa commited on
Commit
6bcb383
·
verified ·
1 Parent(s): 6f4e0d4

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 sha256:204a6b7f21410c79c0c6b123e8a711467bcb358d99d91a0bb4e02e6e8b35ee89
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da9a045aedd9878d5ea110ae1d1d5c4295379424a4b3b337bf1bcf854370f825
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1cc7c6d10a053145fc2e3d6682932545f8dfb5dfde232c9671872e4fde4d58f1
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e63b04a46a7d7ab9efad126266195741e9984877090de922ff0e7512ba77ff4c
3
  size 18810036
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1b4713dea5ab961e62ed6cdc4a0e82f3f4e67dbf8b87455d689d16a8cb61300f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:310d39d9221666853737008bb796bf66212225b90483a0c6cd0d8c20cb9be521
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f7d03f1dba06dbe949e0b7294b5a80e81e1c97413b12e930c7d1d62b4e569ba
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
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": 1.135646687697161,
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": 59.663,
306
  "eval_steps_per_second": 7.569,
307
  "step": 90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
308
  }
309
  ],
310
  "logging_steps": 3,
@@ -324,7 +353,7 @@
324
  "attributes": {}
325
  }
326
  },
327
- "total_flos": 7081123023421440.0,
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": 1.249211356466877,
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": 59.663,
306
  "eval_steps_per_second": 7.569,
307
  "step": 90
308
+ },
309
+ {
310
+ "epoch": 1.1735015772870663,
311
+ "grad_norm": 0.800684928894043,
312
+ "learning_rate": 1.4852136862001764e-06,
313
+ "loss": 1.6495,
314
+ "step": 93
315
+ },
316
+ {
317
+ "epoch": 1.2113564668769716,
318
+ "grad_norm": 0.615403950214386,
319
+ "learning_rate": 4.865965629214819e-07,
320
+ "loss": 1.5472,
321
+ "step": 96
322
+ },
323
+ {
324
+ "epoch": 1.249211356466877,
325
+ "grad_norm": 0.7376525402069092,
326
+ "learning_rate": 3.04586490452119e-08,
327
+ "loss": 1.3958,
328
+ "step": 99
329
+ },
330
+ {
331
+ "epoch": 1.249211356466877,
332
+ "eval_loss": 1.6302069425582886,
333
+ "eval_runtime": 2.2327,
334
+ "eval_samples_per_second": 60.017,
335
+ "eval_steps_per_second": 7.614,
336
+ "step": 99
337
  }
338
  ],
339
  "logging_steps": 3,
 
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 7802077324247040.0,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null