VERSIL91 commited on
Commit
0099da3
·
verified ·
1 Parent(s): 608561a

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 sha256:4ae58378910e3e96e2604ede0783916d766e072f3888393b58b6d1c9dff7fca3
3
  size 125040
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ef7bda73e42f788b81c6b158133c05b3dc8fa43f291ed4530fea6c685bb213a1
3
  size 125040
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7351faf53c7a6d66d038f69543c4d12c36a2050708ccc0b0169aca108b0f597
3
  size 162868
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ea2e0d34eb8c13ac0cdfeb26337ee9392d99bb0adac548e9cd43fd02b91bb0ad
3
  size 162868
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": 0.03121951219512195,
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": 518.024,
38
  "eval_steps_per_second": 259.012,
39
  "step": 2
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
40
  }
41
  ],
42
  "logging_steps": 1,
@@ -56,7 +78,7 @@
56
  "attributes": {}
57
  }
58
  },
59
- "total_flos": 96448020480.0,
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": 0.0624390243902439,
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": 518.024,
38
  "eval_steps_per_second": 259.012,
39
  "step": 2
40
+ },
41
+ {
42
+ "epoch": 0.04682926829268293,
43
+ "grad_norm": 2.388425588607788,
44
+ "learning_rate": 3e-05,
45
+ "loss": 178.0,
46
+ "step": 3
47
+ },
48
+ {
49
+ "epoch": 0.0624390243902439,
50
+ "grad_norm": 2.5343129634857178,
51
+ "learning_rate": 4e-05,
52
+ "loss": 177.9375,
53
+ "step": 4
54
+ },
55
+ {
56
+ "epoch": 0.0624390243902439,
57
+ "eval_loss": 11.115740776062012,
58
+ "eval_runtime": 0.2282,
59
+ "eval_samples_per_second": 473.198,
60
+ "eval_steps_per_second": 236.599,
61
+ "step": 4
62
  }
63
  ],
64
  "logging_steps": 1,
 
78
  "attributes": {}
79
  }
80
  },
81
+ "total_flos": 183251238912.0,
82
  "train_batch_size": 2,
83
  "trial_name": null,
84
  "trial_params": null