VERSIL91 commited on
Commit
cacc47c
1 Parent(s): 3ca65bc

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 sha256:30a17fe195425bc8a6492e36a40c74297974115c2b3d33293b2787fd9eef42d6
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ebbac6e2cdca5d6da805566e1321fac58f3c22e2a54ff3abb6647cb6372a730
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b502f8f8c2dd88643027d4e8e0f8219354c099096b3ea015b2154baef35ae358
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:009abae2f384755621f50389cf8958ed7fcfce280031ca95f6cea15bd5777e3c
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:abaa9373bbe156c59363a08f9fb6a81f0701ec05adf8ddebf0a95d11c5c0d35c
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4338e60828af3efb3dbfac479ffbce4cf22f201f32dd76c072dd2215e2af458f
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": 8.98485210091112e-05,
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": 28.723,
38
  "eval_steps_per_second": 14.361,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1302986508730368.0,
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": 0.0001796970420182224,
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": 28.723,
38
  "eval_steps_per_second": 14.361,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0001347727815136668,
43
+ "grad_norm": 15.355352401733398,
44
+ "learning_rate": 3e-05,
45
+ "loss": 34.2527,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0001796970420182224,
50
+ "grad_norm": 13.506675720214844,
51
+ "learning_rate": 4e-05,
52
+ "loss": 33.2262,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0001796970420182224,
57
+ "eval_loss": 2.224916696548462,
58
+ "eval_runtime": 1242.049,
59
+ "eval_samples_per_second": 30.184,
60
+ "eval_steps_per_second": 15.092,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2605973017460736.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null