nathanialhunt commited on
Commit
e116b72
·
verified ·
1 Parent(s): 93445d8

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:e193218bd73e781c03e78372f1ee703345a8fe097968f25583a7d361e73c9695
3
  size 80013120
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2743d313c97b59386e2e29605490f702d89eb6bae5d733fa761a8f1ccdc2d56
3
  size 80013120
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:587a86ac0ed47aa95cdd31710e708f763e40ea8ec66c3aefa7c192f949aebd06
3
  size 41119636
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f9509f3b0e4a60b6ce1838c9b26e464a79ce03066610b88af985ab01dc4ea643
3
  size 41119636
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b9abf883c2e9c09674e212674962f98f5fa416abc3e528367d43967e85b78711
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f6772af577974c8afd4f01c292dee37aefb71155f4658c2cd442b9995c16c293
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": 0.05239294710327456,
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": 14.345,
46
  "eval_steps_per_second": 7.207,
47
  "step": 26
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 10,
@@ -64,7 +79,7 @@
64
  "attributes": {}
65
  }
66
  },
67
- "total_flos": 8469496058609664.0,
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": 0.07858942065491184,
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": 14.345,
46
  "eval_steps_per_second": 7.207,
47
  "step": 26
48
+ },
49
+ {
50
+ "epoch": 0.060453400503778336,
51
+ "grad_norm": 0.22602833807468414,
52
+ "learning_rate": 8.263518223330697e-05,
53
+ "loss": 0.1853,
54
+ "step": 30
55
+ },
56
+ {
57
+ "epoch": 0.07858942065491184,
58
+ "eval_loss": 0.05225418880581856,
59
+ "eval_runtime": 14.5852,
60
+ "eval_samples_per_second": 14.33,
61
+ "eval_steps_per_second": 7.199,
62
+ "step": 39
63
  }
64
  ],
65
  "logging_steps": 10,
 
79
  "attributes": {}
80
  }
81
  },
82
+ "total_flos": 1.2704244087914496e+16,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null