VERSIL91 commited on
Commit
b5ae6d3
·
verified ·
1 Parent(s): c801073

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 sha256:4793a33e04f93b79c0501f8eeff23cd4dc0fb93e61811f2b708b867aa33d091d
3
  size 111454040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb6e5bb63c85901b1feb0d5b708351e81c5fd5dbc08c349aa5760adb16976f98
3
  size 111454040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33e3294bddeaa4005a8e67e8762b9c93def6e556520ec5c0c9e032a9e1ea3935
3
  size 56950676
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8280829507377bc7e176a90a8ddc684518fa234c081ef4a2fa058a946596df26
3
  size 56950676
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e300bddb0d7e7d6e026d32cddc3203212379cd7e7d4945e7775d35a028e0ce1f
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:94eb3af0be59b8022e591483a56634de67b6ec709d4a7976205940027b927a1a
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": 0.000313541054281795,
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": 6.511,
38
  "eval_steps_per_second": 3.256,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 2717893892505600.0,
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": 0.00062708210856359,
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": 6.511,
38
  "eval_steps_per_second": 3.256,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.00047031158142269255,
43
+ "grad_norm": 16.65349769592285,
44
+ "learning_rate": 3e-05,
45
+ "loss": 108.6886,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.00062708210856359,
50
+ "grad_norm": 18.71934700012207,
51
+ "learning_rate": 4e-05,
52
+ "loss": 99.0921,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.00062708210856359,
57
+ "eval_loss": 6.895726680755615,
58
+ "eval_runtime": 1652.4436,
59
+ "eval_samples_per_second": 6.502,
60
+ "eval_steps_per_second": 3.251,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 5435787785011200.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null