VERSIL91 commited on
Commit
313570f
·
verified ·
1 Parent(s): fe2a967

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:cf143679b4f97aa1407fe0ad8c8e1763ffe3b2d252d995a071ceaeee071df472
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2f07fa9665dfdc9cf29dd3cbbcf0db54529007584a139741be61a68bc028ab8
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a18628809e523cc196e05e7ac2859cd587dd3563b7933e135ab47e2c8587bf3b
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1dae634952151106eef3943bf2a088afda2a9b48c6b8d4c8211ba2e1dd7b7394
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": 0.029547553093259463,
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": 27.787,
38
  "eval_steps_per_second": 13.893,
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": 0.05909510618651893,
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": 27.787,
38
  "eval_steps_per_second": 13.893,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0443213296398892,
43
+ "grad_norm": 25.863922119140625,
44
+ "learning_rate": 3e-05,
45
+ "loss": 55.8648,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.05909510618651893,
50
+ "grad_norm": 20.992795944213867,
51
+ "learning_rate": 4e-05,
52
+ "loss": 57.1646,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.05909510618651893,
57
+ "eval_loss": 3.442988872528076,
58
+ "eval_runtime": 4.1559,
59
+ "eval_samples_per_second": 27.431,
60
+ "eval_steps_per_second": 13.716,
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