VERSIL91 commited on
Commit
c8a2b0b
·
verified ·
1 Parent(s): fc5aa90

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 sha256:4e05c7cce21d5e1c605e66325528825f1a19c2734da908bb14462629a0638909
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9df653c152b2fb50aa95fa4333a7d29995454052e1b9a604251808178a926d22
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:681bb7aaaa6efea1a54803f0f90bd287b1fc7085646c919ec55f47460ad5cfb0
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6cab04a02616bc8ab15b48923f5a031d875006c183f7a5c47010d760d5743f2e
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5ff1a5a76862bbee56a9275ee6a5621dff6f0928cd044fcf7d46b0f5941256ac
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b8d6b9a0e9e9502751def1097143074ef257eab24506a0f12d159e188fa21987
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": 0.007948335817188276,
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": 8.887,
38
  "eval_steps_per_second": 4.444,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 1840305389174784.0,
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": 0.015896671634376552,
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": 8.887,
38
  "eval_steps_per_second": 4.444,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.011922503725782414,
43
+ "grad_norm": 30.4892578125,
44
+ "learning_rate": 3e-05,
45
+ "loss": 21.754,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.015896671634376552,
50
+ "grad_norm": 28.645517349243164,
51
+ "learning_rate": 4e-05,
52
+ "loss": 21.6039,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.015896671634376552,
57
+ "eval_loss": 1.388905644416809,
58
+ "eval_runtime": 48.2007,
59
+ "eval_samples_per_second": 8.797,
60
+ "eval_steps_per_second": 4.398,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 3680610778349568.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null