tuantmdev commited on
Commit
5df1e9a
·
verified ·
1 Parent(s): 42ef765

Training in progress, step 150, 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:d1a037cfe70fe914206ad3b3e1cbfdb9c374500a378057ee570d928a6a28f6cf
3
  size 335604696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b6344a3f310b1b64011c55450a6088b385e11a27bd77add99ca504026d33a7a
3
  size 335604696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:816457b9f0c44be4dd4db650a44e9a8d86a6782bd44ec2362299d66cfb1389b6
3
  size 170920084
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6b8a536afce0209e12769c309d901c239791403adaf8469fdaa7eccf8fc32942
3
  size 170920084
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51b16b9760dc7e26f2ed467a5e9266923da5259cc1661dee821fd4505fdea8aa
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b7d50bf47367fbcf44bc68ab7161ecf92a7f0a67600c416dffffe09bb8f32596
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa172a67b17733f4f4576524fa7afa573b19fcbf0bf4ea9f180757ed71fc81e7
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:321052ad5e93c8a107bd6c10f372f50285d863120fc0088befc39ec2733238fb
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.7225255966186523,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-50",
4
- "epoch": 0.10601643254704479,
5
  "eval_steps": 50,
6
- "global_step": 100,
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": 14.526,
46
  "eval_steps_per_second": 7.272,
47
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  }
49
  ],
50
  "logging_steps": 40,
@@ -59,7 +74,7 @@
59
  "early_stopping_threshold": 0.0
60
  },
61
  "attributes": {
62
- "early_stopping_patience_counter": 1
63
  }
64
  },
65
  "TrainerControl": {
@@ -73,7 +88,7 @@
73
  "attributes": {}
74
  }
75
  },
76
- "total_flos": 3.5848869573033984e+16,
77
  "train_batch_size": 2,
78
  "trial_name": null,
79
  "trial_params": null
 
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,
 
45
  "eval_samples_per_second": 14.526,
46
  "eval_steps_per_second": 7.272,
47
  "step": 100
48
+ },
49
+ {
50
+ "epoch": 0.12721971905645374,
51
+ "grad_norm": 15.772492408752441,
52
+ "learning_rate": 9.619397662556435e-05,
53
+ "loss": 11.7626,
54
+ "step": 120
55
+ },
56
+ {
57
+ "epoch": 0.1590246488205672,
58
+ "eval_loss": 1.620514154434204,
59
+ "eval_runtime": 54.6402,
60
+ "eval_samples_per_second": 14.55,
61
+ "eval_steps_per_second": 7.284,
62
+ "step": 150
63
  }
64
  ],
65
  "logging_steps": 40,
 
74
  "early_stopping_threshold": 0.0
75
  },
76
  "attributes": {
77
+ "early_stopping_patience_counter": 0
78
  }
79
  },
80
  "TrainerControl": {
 
88
  "attributes": {}
89
  }
90
  },
91
+ "total_flos": 5.370699942199296e+16,
92
  "train_batch_size": 2,
93
  "trial_name": null,
94
  "trial_params": null