Best000 commited on
Commit
509b9aa
·
verified ·
1 Parent(s): c5fd45d

Training in progress, step 39, 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:d6603b1deabdfa10aceb64769c25eef17d6e3c9e4a80ef1434a120308d474fff
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:80f6237f14f8737c6b0dfb719eadea636303ecafead1429774745fd3ed092687
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f5e85a34ba3c61c1b25f4e2db0d9ebe0c6b63b42f046483b2ab4e918e7bf72dc
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:375344c6990835c961cf955af5eef94d878e0d6d74612692af2df16f208c6333
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3fbfb2ebc436a787250427a55096ccac8da31c15076b6ad72f8489e64c6ccbd5
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3df234e5aaf8c4946e213550320cfa641d06d78d6188e95560495eed9123ce4
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:59af5f5d66ecb18e9abb84f5d5074a625502d490e59b29de1e9974286a967cbf
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
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": 0.11542730299667037,
5
  "eval_steps": 13,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -45,6 +45,21 @@
45
  "eval_samples_per_second": 33.854,
46
  "eval_steps_per_second": 17.105,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 4234706153373696.0,
68
  "train_batch_size": 2,
69
  "trial_name": null,
70
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.17314095449500555,
5
  "eval_steps": 13,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
45
  "eval_samples_per_second": 33.854,
46
  "eval_steps_per_second": 17.105,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.13318534961154274,
51
+ "grad_norm": 0.7843520045280457,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 0.2346,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.17314095449500555,
58
+ "eval_loss": 0.1703956425189972,
59
+ "eval_runtime": 2.8011,
60
+ "eval_samples_per_second": 33.915,
61
+ "eval_steps_per_second": 17.136,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 6352059230060544.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null