dimasik1987 commited on
Commit
62070b2
·
verified ·
1 Parent(s): 4049774

Training in progress, step 20, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:15d04485dec98896d23511093f19e4fc6b96f38b9ee2e36a3e6a5f934bb5a344
3
  size 250422888
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aef85ea856781702c5f3e48711c54409b8d37ae027403ff7d3e7c77a79f33bde
3
  size 250422888
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f22be1d6a20b5b01df47a2e88850b4187823d86c93873b3d15fd98e68051f764
3
  size 501168482
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51cab14804b20c31dae170a7b571bc90d8c428f5fdd588dd3bb032acf5b5b4c7
3
  size 501168482
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:31aa55e34fc596b72654d1cf3260e6de6d6534847670471bd93bd0732f004433
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fcb382ea71cd423bab21d617c20f9064b0a5efca9aeec8b9e69fc4f286ae1a39
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c188a6a4749e6ca627bb6d536eb7443f499d5b1b88d98a78f9c713443e010d9c
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:015707cb16790250630febca682498cb5d3456d5a13443b953687f19dc7d59ed
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 2.2999963760375977,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.18691588785046728,
5
  "eval_steps": 5,
6
- "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -52,6 +52,43 @@
52
  "eval_samples_per_second": 5.068,
53
  "eval_steps_per_second": 1.351,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -80,7 +117,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 1.26955844272128e+16,
84
  "train_batch_size": 4,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5361648797988892,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.37383177570093457,
5
  "eval_steps": 5,
6
+ "global_step": 20,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
52
  "eval_samples_per_second": 5.068,
53
  "eval_steps_per_second": 1.351,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.22429906542056074,
58
+ "grad_norm": 1.5405913591384888,
59
+ "learning_rate": 0.000163742398974869,
60
+ "loss": 2.3672,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.2803738317757009,
65
+ "grad_norm": 1.4216840267181396,
66
+ "learning_rate": 0.00013090169943749476,
67
+ "loss": 1.8806,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.2803738317757009,
72
+ "eval_loss": 1.7696713209152222,
73
+ "eval_runtime": 8.8922,
74
+ "eval_samples_per_second": 5.061,
75
+ "eval_steps_per_second": 1.35,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.3364485981308411,
80
+ "grad_norm": 1.701966404914856,
81
+ "learning_rate": 9.372094804706867e-05,
82
+ "loss": 1.6274,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.37383177570093457,
87
+ "eval_loss": 1.5361648797988892,
88
+ "eval_runtime": 8.9088,
89
+ "eval_samples_per_second": 5.051,
90
+ "eval_steps_per_second": 1.347,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 2.53911688544256e+16,
121
  "train_batch_size": 4,
122
  "trial_name": null,
123
  "trial_params": null