VERSIL91 commited on
Commit
9e80a1f
·
verified ·
1 Parent(s): 7dc6856

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:d0190f0a860c178dcef68065e740898b5376807206a4c478f7d1afada5eceb46
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0796bbf48e7054c2e895cfda167266e892e6b11108c9642c4c73676a0fdb3926
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bfb2b1af7e1ec0a9d79201e4d568c8c32b11a9e0c122282d343fc8bd791a688
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:31ab4a3f68a28a463f8ad072f3488d0eaa5ad70e70690d2f41839c158ffee572
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:de0a880b94d9b8f1377e86006043b94121eb1c447497937e3f4ae33277dae97f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f16f3b8874379bf8e1e039ef0bfa9f44be83be43b977ccd15b78395a275f501
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": 0.007557864903164856,
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": 5.108,
38
  "eval_steps_per_second": 2.554,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2532979444285440.0,
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": 0.015115729806329713,
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": 5.108,
38
  "eval_steps_per_second": 2.554,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.011336797354747285,
43
+ "grad_norm": 3.430900812149048,
44
+ "learning_rate": 3e-05,
45
+ "loss": 21.1357,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.015115729806329713,
50
+ "grad_norm": 3.2519538402557373,
51
+ "learning_rate": 4e-05,
52
+ "loss": 18.0472,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.015115729806329713,
57
+ "eval_loss": 1.3015305995941162,
58
+ "eval_runtime": 160.4481,
59
+ "eval_samples_per_second": 2.78,
60
+ "eval_steps_per_second": 1.39,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 5065958888570880.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null