VERSIL91 commited on
Commit
dc73a5b
1 Parent(s): 42106ef

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 sha256:5a344df508c70129697a96a0db4184891f51d41306eca2564d1c1f31bb3fe0a1
3
  size 39256456
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2a218eb7865a2e3040998428c8400a2ed1558200081c13f110772b744759e73
3
  size 39256456
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d768999e03c7336785edf7ea938e45cb3d72c6dd9a68f7f1b4a7b6ad6b5097dd
3
  size 20632762
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:86f6b58c09fa4ed584ce8e0a15c8a83d70a020645cbb568b48b04db05d59fff9
3
  size 20632762
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": 0.006565449322938038,
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": 35.023,
38
  "eval_steps_per_second": 17.512,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 501714738216960.0,
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": 0.013130898645876077,
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": 35.023,
38
  "eval_steps_per_second": 17.512,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.009848173984407058,
43
+ "grad_norm": 0.9836621284484863,
44
+ "learning_rate": 3e-05,
45
+ "loss": 1.5016,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.013130898645876077,
50
+ "grad_norm": 1.1562381982803345,
51
+ "learning_rate": 4e-05,
52
+ "loss": 1.709,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.013130898645876077,
57
+ "eval_loss": 1.664827585220337,
58
+ "eval_runtime": 14.6498,
59
+ "eval_samples_per_second": 35.086,
60
+ "eval_steps_per_second": 17.543,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 1113561979944960.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null