tuantmdev commited on
Commit
630b732
·
verified ·
1 Parent(s): 4b25d6d

Training in progress, step 200, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b6344a3f310b1b64011c55450a6088b385e11a27bd77add99ca504026d33a7a
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ec730630dd47ffcebec478577b0e29ac7ce5b94a93b5ddfadf8f8e2e05913a74
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6b8a536afce0209e12769c309d901c239791403adaf8469fdaa7eccf8fc32942
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c1be83eee156b64ccaa6715a3d74b963b801b2e16737814a4ba3c1b06bd3e964
3
  size 170920084
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b7d50bf47367fbcf44bc68ab7161ecf92a7f0a67600c416dffffe09bb8f32596
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5aab15a6bfd3da33b5a55e0d0c415be6212b4d8d069f7e06df29dcd13fa3a33
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:530505d607699f384741067a5f9139d72f043713adb680898a3f1b5714170c97
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.620514154434204,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-150",
4
- "epoch": 0.1590246488205672,
5
  "eval_steps": 50,
6
- "global_step": 150,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,28 @@
60
  "eval_samples_per_second": 14.55,
61
  "eval_steps_per_second": 7.284,
62
  "step": 150
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 40,
@@ -88,7 +110,7 @@
88
  "attributes": {}
89
  }
90
  },
91
- "total_flos": 5.370699942199296e+16,
92
  "train_batch_size": 2,
93
  "trial_name": null,
94
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.6030395030975342,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.21203286509408958,
5
  "eval_steps": 50,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 14.55,
61
  "eval_steps_per_second": 7.284,
62
  "step": 150
63
+ },
64
+ {
65
+ "epoch": 0.16962629207527166,
66
+ "grad_norm": 13.623527526855469,
67
+ "learning_rate": 8.535533905932738e-05,
68
+ "loss": 11.3132,
69
+ "step": 160
70
+ },
71
+ {
72
+ "epoch": 0.21203286509408958,
73
+ "grad_norm": 36.52813720703125,
74
+ "learning_rate": 6.91341716182545e-05,
75
+ "loss": 11.344,
76
+ "step": 200
77
+ },
78
+ {
79
+ "epoch": 0.21203286509408958,
80
+ "eval_loss": 1.6030395030975342,
81
+ "eval_runtime": 54.8289,
82
+ "eval_samples_per_second": 14.5,
83
+ "eval_steps_per_second": 7.259,
84
+ "step": 200
85
  }
86
  ],
87
  "logging_steps": 40,
 
110
  "attributes": {}
111
  }
112
  },
113
+ "total_flos": 7.156512927095194e+16,
114
  "train_batch_size": 2,
115
  "trial_name": null,
116
  "trial_params": null