VERSIL91 commited on
Commit
f393c08
·
verified ·
1 Parent(s): 94f6124

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:db78c5a02b4f3856db23c4499b69a6008da434613197ee3811ada5de1838a245
3
  size 100059752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9ed27d08cf4ddc316e3311848234adf9ef4bd6ea31909ce1c8551ecc6967a0
3
  size 100059752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3fe49f8a7101d0b3aaf177e7d3b4604ee3683fdefafc48b29f1e5f7e29b77d6
3
  size 51244020
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:11c9e2a129a56ee5225ca10669368841b2fcce5654cf3b069821108b22fd910f
3
  size 51244020
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
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": 0.022808267997148968,
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": 32.362,
38
  "eval_steps_per_second": 16.181,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1719982274641920.0,
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": 0.045616535994297935,
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,
 
37
  "eval_samples_per_second": 32.362,
38
  "eval_steps_per_second": 16.181,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.03421240199572345,
43
+ "grad_norm": 28.605438232421875,
44
+ "learning_rate": 3e-05,
45
+ "loss": 13.0542,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.045616535994297935,
50
+ "grad_norm": 27.959163665771484,
51
+ "learning_rate": 4e-05,
52
+ "loss": 14.1325,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.045616535994297935,
57
+ "eval_loss": 11.540223121643066,
58
+ "eval_runtime": 4.5932,
59
+ "eval_samples_per_second": 32.221,
60
+ "eval_steps_per_second": 16.111,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3774405547130880.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null