VERSIL91 commited on
Commit
92ef7cc
·
verified ·
1 Parent(s): d83073d

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:cee4bb2cbdb70aa73a3a24e68584fba0c0989dad1dff1eca838e2fc149b6cab0
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b329b74b28e9ba6d6989ddcc3cb02d5b9efe5d4448abcc271ed99c89b7902d9
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6d372db5205f9b50c010120b20a64998ed4b4fd670589ed65fb262033ca5e48f
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0e530648b8c66267c08062b31ed5e05188601700b63ee445052848f71c149828
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:b9b2b2595eca46aa10c15bef1c88e7ff2d9fdda1404bab559a5f739c48dff773
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30ac516c6d7fe9572355ad5c6fba833ac8668d2dd6eb2b3f24e1fba1da0be9d4
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": 0.0009178522257916476,
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": 26.114,
38
  "eval_steps_per_second": 13.057,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1343718124683264.0,
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": 0.0018357044515832951,
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": 26.114,
38
  "eval_steps_per_second": 13.057,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0013767783386874712,
43
+ "grad_norm": 4.031177520751953,
44
+ "learning_rate": 3e-05,
45
+ "loss": 4.4294,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0018357044515832951,
50
+ "grad_norm": 3.4328739643096924,
51
+ "learning_rate": 4e-05,
52
+ "loss": 4.1462,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0018357044515832951,
57
+ "eval_loss": 0.26450106501579285,
58
+ "eval_runtime": 483.9395,
59
+ "eval_samples_per_second": 7.584,
60
+ "eval_steps_per_second": 3.792,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2646717518315520.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null