VERSIL91 commited on
Commit
3333d12
·
verified ·
1 Parent(s): 1347f4f

Training in progress, step 4, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:10e318942da198647aa14f941b815181acb1b19ed6ba22305e3f3519c58504f8
3
  size 32856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:abf02b78de543d024f08db799a0405af5385fffd625bda969b401ddad2cca4fb
3
  size 32856
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c6f73dacafea018b124a09ad60b6707a22de1bd14865f7c0e14e3ef356ba3490
3
  size 71358
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dbad11938f08006bada5e11e5d2e723f9e532d0de52607c9ed16b987e617ab66
3
  size 71358
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:29742e4ebd31c1909fecf2e302c876ad3db12d429dcfb2bc20afaf4180743e9c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18797824dc0375cb657b51b8e87aff809ea47d39704d989e1b1c3a76a7a70a6b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:60f8f27a9d76e31d3721bb37f2f4c76e866b8dedf8d4315f175dac906a4a966d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7adb031dc938779259a07e684ea318126e92e52b40c256b93ef474d2ac57a5b
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": 0.0006418871482157543,
5
  "eval_steps": 2,
6
- "global_step": 2,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -37,6 +37,28 @@
37
  "eval_samples_per_second": 774.239,
38
  "eval_steps_per_second": 387.119,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 5976883200.0,
60
  "train_batch_size": 2,
61
  "trial_name": null,
62
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0012837742964315086,
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,
 
37
  "eval_samples_per_second": 774.239,
38
  "eval_steps_per_second": 387.119,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0009628307223236315,
43
+ "grad_norm": 12.251354217529297,
44
+ "learning_rate": 3e-05,
45
+ "loss": 177.75,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0012837742964315086,
50
+ "grad_norm": 11.125019073486328,
51
+ "learning_rate": 4e-05,
52
+ "loss": 178.25,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0012837742964315086,
57
+ "eval_loss": 11.111065864562988,
58
+ "eval_runtime": 6.861,
59
+ "eval_samples_per_second": 764.901,
60
+ "eval_steps_per_second": 382.451,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 11953766400.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null