VERSIL91 commited on
Commit
71534e1
·
verified ·
1 Parent(s): 4886e7a

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:a386f713d8e32f18a37793b2e1735d09996d366275fc3af74de1035e73f19095
3
  size 125040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1d24c97f1cc72f846730a4e0cf883dbadab8081bce0a9c37659066bcaf825db0
3
  size 125040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:49ddaa9ee81cebb8ef5d0fc686a4ca5eecfc08a7ed35914b499cc87256f0c88a
3
  size 162868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:79ce9f09111b7581412efa450f95017a3e81aedff56354462e66df6917bf6973
3
  size 162868
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": 0.011531531531531532,
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": 814.736,
38
  "eval_steps_per_second": 408.758,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 77158416384.0,
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": 0.023063063063063063,
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": 814.736,
38
  "eval_steps_per_second": 408.758,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.017297297297297298,
43
+ "grad_norm": 2.545091152191162,
44
+ "learning_rate": 3e-05,
45
+ "loss": 177.875,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.023063063063063063,
50
+ "grad_norm": 2.5474777221679688,
51
+ "learning_rate": 4e-05,
52
+ "loss": 177.875,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.023063063063063063,
57
+ "eval_loss": 11.113054275512695,
58
+ "eval_runtime": 0.3638,
59
+ "eval_samples_per_second": 805.291,
60
+ "eval_steps_per_second": 404.02,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 154316832768.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null