clarxus commited on
Commit
2ce30d1
·
verified ·
1 Parent(s): 4275042

Training in progress, step 100, 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:ef93c783fe7f0a703386cb69534b5df642a3c0d6062012a6dc5acc0a419c2243
3
  size 161533192
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc4af31e639a90bdde3e73636055e4f7a1677e4496acecaa5eb32563d8a9d3af
3
  size 161533192
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:96e27ccd1ac0b8310b5ac56224f08417b3796d6ff76c8b9966461f952b9bf5d0
3
  size 82460660
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a083de324e5522b98ccbe235e35114f73216e52e40fb43ba7e9fdb5c7c071eb
3
  size 82460660
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98ceeb98bc98a108f218bca849514ba73d1501e8edab441d125301a6929ed105
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:85d597bfce9ec1f79c3a3fdeb9aaca1b92767f4c56623506d9882dd3b721845d
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:43444b0a2aaeda40531bf13a694e8a3eeeb489f81435e9521c012609a5be4dc4
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
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": 1.4142857142857144,
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,
@@ -348,12 +348,12 @@
348
  "should_evaluate": false,
349
  "should_log": false,
350
  "should_save": true,
351
- "should_training_stop": false
352
  },
353
  "attributes": {}
354
  }
355
  },
356
- "total_flos": 2.72450330724139e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.4285714285714286,
5
  "eval_steps": 9,
6
+ "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
348
  "should_evaluate": false,
349
  "should_log": false,
350
  "should_save": true,
351
+ "should_training_stop": true
352
  },
353
  "attributes": {}
354
  }
355
  },
356
+ "total_flos": 2.752464854974464e+17,
357
  "train_batch_size": 8,
358
  "trial_name": null,
359
  "trial_params": null