VERSIL91 commited on
Commit
7d2ae61
·
verified ·
1 Parent(s): 53419db

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:a9d322765424c562a8d5989a130bc60577141fa0752767229dd7f347fa350929
3
  size 125248064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cfa9aaf0d3cbf6a455ad798436f2b4617df52a98fedbf7f49bb6981d8e870d0
3
  size 125248064
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd44d36f574660684da8c5342744b422bc6cd8f7a0c55fef421820528bc91ca5
3
  size 64219860
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6f6e0396869827426534cd1740cee0867b7f09f45122fed1af7505e28b8d1f9
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:a813ad05e79ee2c7ae28e32bed6004a753ef0f900655fb68cd3e73236f86a86a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:af93c27c5bde1ecbb7889f2aeca50c50c9fe4237cbad3fb13649f213484bc331
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": 0.0006876544536370474,
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": 6.246,
38
  "eval_steps_per_second": 3.124,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2612135051919360.0,
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": 0.0013753089072740948,
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": 6.246,
38
  "eval_steps_per_second": 3.124,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.0010314816804555711,
43
+ "grad_norm": 7.610560417175293,
44
+ "learning_rate": 3e-05,
45
+ "loss": 60.8528,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0013753089072740948,
50
+ "grad_norm": 7.584437847137451,
51
+ "learning_rate": 4e-05,
52
+ "loss": 59.9693,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0013753089072740948,
57
+ "eval_loss": 3.6589016914367676,
58
+ "eval_runtime": 899.3134,
59
+ "eval_samples_per_second": 5.447,
60
+ "eval_steps_per_second": 2.724,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 5461736926740480.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null