VERSIL91 commited on
Commit
eb1b739
1 Parent(s): ae103c7

Training in progress, step 5, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c9ed27d08cf4ddc316e3311848234adf9ef4bd6ea31909ce1c8551ecc6967a0
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e857d0b539b0e06d7345915ce205e6332916054b63cc6904ffab55fb42f375f
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11c9e2a129a56ee5225ca10669368841b2fcce5654cf3b069821108b22fd910f
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e993ffa77c25f03cff6b3c3a75b7e4bfc75ecd45d75b3717badd6fbe7c558f8f
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:572c5653b97399d6dc550389d4e48df5479adab7c80147f357d4d04c0f7252da
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d63217b923cb177f669d6bc2174b89abdc6a56d968d279b505491b37976d9bb
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": 0.045616535994297935,
5
  "eval_steps": 2,
6
- "global_step": 4,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -59,6 +59,13 @@
59
  "eval_samples_per_second": 32.221,
60
  "eval_steps_per_second": 16.111,
61
  "step": 4
 
 
 
 
 
 
 
62
  }
63
  ],
64
  "logging_steps": 1,
@@ -73,12 +80,12 @@
73
  "should_evaluate": false,
74
  "should_log": false,
75
  "should_save": true,
76
- "should_training_stop": false
77
  },
78
  "attributes": {}
79
  }
80
  },
81
- "total_flos": 3774405547130880.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.05702066999287242,
5
  "eval_steps": 2,
6
+ "global_step": 5,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
59
  "eval_samples_per_second": 32.221,
60
  "eval_steps_per_second": 16.111,
61
  "step": 4
62
+ },
63
+ {
64
+ "epoch": 0.05702066999287242,
65
+ "grad_norm": 29.26180076599121,
66
+ "learning_rate": 5e-05,
67
+ "loss": 13.0918,
68
+ "step": 5
69
  }
70
  ],
71
  "logging_steps": 1,
 
80
  "should_evaluate": false,
81
  "should_log": false,
82
  "should_save": true,
83
+ "should_training_stop": true
84
  },
85
  "attributes": {}
86
  }
87
  },
88
+ "total_flos": 4873283111485440.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null