VERSIL91 commited on
Commit
25aa36c
·
verified ·
1 Parent(s): aa9a360

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:cc3ee02335905c86075bf3e0ac2021c4a4ec19644740f5d6d17aa9aea4312b15
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:56fd5730c8a1472036127e9ef9442e86e22e67284b7877eec3176d25e881ab4d
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321e0f958af7c51e63b60f49087c301e1830ed0ec4f6c699f8ce1b5edc2a8d19
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a975efdc7ed41ba2eef57283e2a66750bb79d633b75bc9c1f96cb8d92b1af36f
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
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": 0.0050809780882819944,
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": 40.293,
38
  "eval_steps_per_second": 20.177,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1572129610924032.0,
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": 0.010161956176563989,
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": 40.293,
38
  "eval_steps_per_second": 20.177,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.007621467132422992,
43
+ "grad_norm": 1.0568405389785767,
44
+ "learning_rate": 3e-05,
45
+ "loss": 0.5769,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.010161956176563989,
50
+ "grad_norm": 1.1675392389297485,
51
+ "learning_rate": 4e-05,
52
+ "loss": 0.8007,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.010161956176563989,
57
+ "eval_loss": 0.6899632215499878,
58
+ "eval_runtime": 16.5009,
59
+ "eval_samples_per_second": 40.18,
60
+ "eval_steps_per_second": 20.12,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3098020115644416.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null