VERSIL91 commited on
Commit
a6f131a
·
verified ·
1 Parent(s): 92b593d

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:dd180c3a5bc0d0cffec97783960f72a8187c431d284185fdc85cb184d9400064
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:64a876ea02df00a403be7837a866b25309ad78f24949eb21e1f1222fbd239c7f
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:46330f943e03aec3205d44be8b9c1728013a6ce55b0821b32b7510750f6adaa5
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16c260ce7147be25127ca7c4542e4da7f205aa0126f91ba5628d99c61dad622a
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e4bbba064701c6c5641a803b1cc6ad3663ec5a37b46a361f1a3f2ad360548d26
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39dd70f78833b407302ec7a08a5ddbe1954a321879cf7446f5acb83d55b840c1
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": 0.007207207207207207,
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": 91.935,
38
  "eval_steps_per_second": 45.967,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 142461062086656.0,
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": 0.014414414414414415,
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": 91.935,
38
  "eval_steps_per_second": 45.967,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.010810810810810811,
43
+ "grad_norm": 4.124750137329102,
44
+ "learning_rate": 3e-05,
45
+ "loss": 3.235,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.014414414414414415,
50
+ "grad_norm": 4.565180778503418,
51
+ "learning_rate": 4e-05,
52
+ "loss": 3.4669,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.014414414414414415,
57
+ "eval_loss": 3.972473621368408,
58
+ "eval_runtime": 5.1083,
59
+ "eval_samples_per_second": 91.616,
60
+ "eval_steps_per_second": 45.808,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 282696170078208.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null