VERSIL91 commited on
Commit
136b5a4
·
verified ·
1 Parent(s): e43df8c

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:bf1c4a264cac05bff3b6d00f24f5b1673749b59c244c110b22573c69bf340c71
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6dfe98581114617518830b6703f65d61ea43ce051d78d9416d909d0617681ec7
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:657cf6670593be17b746ee3b9fe61d39ef012ee65b462ed282d39ee7ab8164a1
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb2a1cd53b90d56b9d922e736e52a7a519667c2be6b46905ec333d3316363610
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5045e6b5041e0d82aaa1f35e39116d9580228034dda2b0205d3a7a9d6f6a181a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0a3fd2aaf2311cd9d97d6239a6c81d74833efc2f7447be6d7e57848f15b0f961
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": 0.004614940871070089,
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": 2.893,
38
  "eval_steps_per_second": 1.446,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 3227498997350400.0,
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": 0.009229881742140178,
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": 2.893,
38
  "eval_steps_per_second": 1.446,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.006922411306605134,
43
+ "grad_norm": 4.4841837882995605,
44
+ "learning_rate": 3e-05,
45
+ "loss": 17.613,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.009229881742140178,
50
+ "grad_norm": 7.501538276672363,
51
+ "learning_rate": 4e-05,
52
+ "loss": 21.325,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.009229881742140178,
57
+ "eval_loss": 1.3067024946212769,
58
+ "eval_runtime": 252.7273,
59
+ "eval_samples_per_second": 2.888,
60
+ "eval_steps_per_second": 1.444,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 6200195442278400.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null