nathanialhunt commited on
Commit
6357cda
·
verified ·
1 Parent(s): 87b5040

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:f108bf778242b1c0d7befa5636ef545b6278c2bd398b9166c3f07b2a853c8c52
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ed79e6edd5f9f34aed13084950156d85cfd9f7e522ea3d75b18f69e135e2845a
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:98f4353fe907b9499ab1263eaedb96a102a7e5beb15eab95cfc5ec649bdc138d
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d088d1e38346e4ea79f3a646ae2444d241a80085fc58c28a92b7c6a320ff8a6f
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c73b88f5a325402ade8b631cbde07f764e38136b3a98cd5bf088404635b73f25
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c3b386391a624b1bd584d01969e845897c710c297088eab7a1800fd97b3f3de
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": 0.010853683990816114,
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": 59.577,
46
  "eval_steps_per_second": 29.818,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 244854950461440.0,
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": 0.01628052598622417,
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": 59.577,
46
  "eval_steps_per_second": 29.818,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.012523481527864746,
51
+ "grad_norm": 1.0281912088394165,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 2.8738,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.01628052598622417,
58
+ "eval_loss": 2.912461757659912,
59
+ "eval_runtime": 16.7721,
60
+ "eval_samples_per_second": 60.159,
61
+ "eval_steps_per_second": 30.11,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 365056471597056.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null