VERSIL91 commited on
Commit
6f11ce6
·
verified ·
1 Parent(s): ee17805

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 sha256:677040385177e88d9f1ff1de1e473e7b88a0423d775056eec1304ff0754ff431
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:812f5748fa88b1d1bda81ee2d1235c7dec481519ae637598b81e2eb50238edcd
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b276c45f310ea119da95b8202741f6f07652de3ad74ebb4bea7019d1bc90a5ce
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:13b460eb7d805a55c6d92a9bf57c5735b2cf23f71e3958167b35c5f8a0134b5d
3
  size 64219860
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e941fe70220f4b7b2456db35764bb0c5162ce06d79a4be42b68666748dacd01
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:28903fd1aac92e346442663b9f2b5539c4576c035a060f8b841d0ff180c806d1
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": 0.002484279170871827,
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": 3.192,
38
  "eval_steps_per_second": 1.596,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 4749336458035200.0,
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": 0.004968558341743654,
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": 3.192,
38
  "eval_steps_per_second": 1.596,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.00372641875630774,
43
+ "grad_norm": 0.730056881904602,
44
+ "learning_rate": 3e-05,
45
+ "loss": 2.825,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.004968558341743654,
50
+ "grad_norm": 0.619186282157898,
51
+ "learning_rate": 4e-05,
52
+ "loss": 3.5916,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.004968558341743654,
57
+ "eval_loss": 0.16779856383800507,
58
+ "eval_runtime": 377.7079,
59
+ "eval_samples_per_second": 3.59,
60
+ "eval_steps_per_second": 1.795,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 9419517308436480.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null