VERSIL91 commited on
Commit
ef2feb2
·
verified ·
1 Parent(s): 1479d4a

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 sha256:34bcebdff3bc2f9199d761169a8b5c592b2ddf3ab7025cd49d9e4bc0bbaf0911
3
  size 65309632
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c7d8a0aa3e6d9371732513ecc6106999a92c28a5dd10b3ae7c0ac689cc7bdf18
3
  size 65309632
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c68f93008bdac243f517ca28e9cd116b4d2c52a2a41812d9c4ec1ee1957f3bd1
3
  size 33424212
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a642b4a05bd74aa128f92eb2c316e7c01f7deb790610779b835b61f197c3e44f
3
  size 33424212
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8f9e07e820f54feaba0cfa662932b655c782efb642a1de96126d3203420eaf62
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0f7de842be5b823c5352a6f4d4c24b0c158a91304726e478c62968d6920c3c78
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": 0.005321802760685182,
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": 52.203,
38
  "eval_steps_per_second": 26.143,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1305982424580096.0,
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": 0.010643605521370364,
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": 52.203,
38
  "eval_steps_per_second": 26.143,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.007982704141027773,
43
+ "grad_norm": 22.730106353759766,
44
+ "learning_rate": 3e-05,
45
+ "loss": 58.9688,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.010643605521370364,
50
+ "grad_norm": 24.190460205078125,
51
+ "learning_rate": 4e-05,
52
+ "loss": 57.6406,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.010643605521370364,
57
+ "eval_loss": 3.5928120613098145,
58
+ "eval_runtime": 12.1417,
59
+ "eval_samples_per_second": 52.134,
60
+ "eval_steps_per_second": 26.108,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 2611964849160192.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null