VERSIL91 commited on
Commit
e60b807
·
verified ·
1 Parent(s): 14b9345

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 sha256:771d96678a28b2a81ef4f89724229808a5b2fe844833369b0bfb805ac723914b
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df3dec194597d2557c392468c3488c45db32c8281ba7401a58975476a6bf00d5
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6d4442e668f7f9c3c2ef00feeab87da1cde7eeb113d040b9e09105ebc9f78d4
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1ffcadb7aad7efd24c634b594f3fd738c2419b4e41dd0df1a14da7dc1a0b1d3
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:ac53eac6999c0ee8d3b0b8c91f614ff6a7474b92186a011bb25104ab766ee8a2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1062f79177d2635d7d8b560b420014391b57cb1f30c0a2cf7f9ac503015703de
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": 0.0006360690930052277,
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": 9.088,
38
  "eval_steps_per_second": 4.544,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4331643391180800.0,
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": 0.0012721381860104554,
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": 9.088,
38
  "eval_steps_per_second": 4.544,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0009541036395078415,
43
+ "grad_norm": 5.136423587799072,
44
+ "learning_rate": 3e-05,
45
+ "loss": 15.3937,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0012721381860104554,
50
+ "grad_norm": 1.8153798580169678,
51
+ "learning_rate": 4e-05,
52
+ "loss": 14.8549,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0012721381860104554,
57
+ "eval_loss": 1.1653506755828857,
58
+ "eval_runtime": 623.0984,
59
+ "eval_samples_per_second": 8.499,
60
+ "eval_steps_per_second": 4.25,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 8663286782361600.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null