dimasik1987 commited on
Commit
9556562
·
verified ·
1 Parent(s): fb9a413

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 sha256:0b7876aa7dbffa3f5a1a49a6df48e31223aee9573ec8d5db9ce9256e594c0f9d
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e8b9b4fa8f6a98856be2095fac98bf717c5e34b75d9e7a3aa69d2ffc069b853f
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5eeac84050b487a1e63d27fed18c00a2c641767e7acc2dc5d5d68734a7b203e
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb43dd5888ac4bd6ea7cbc370ef770fe7253c3ab1560212d702fa60351fac1c9
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9433274712604a43304fac8e76440a4135a61285e183672abe9afea6683f5c35
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1982d72f3f4f446cae04689c9ac92d3b920848c175c7208e6263b5cff7f25011
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": 0.8010535836219788,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.021197668256491786,
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": 3.317,
53
  "eval_steps_per_second": 0.833,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -80,7 +117,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 1.306929288708096e+16,
84
  "train_batch_size": 4,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.5995034575462341,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.04239533651298357,
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": 3.317,
53
  "eval_steps_per_second": 0.833,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.025437201907790145,
58
+ "grad_norm": 0.9566070437431335,
59
+ "learning_rate": 0.000163742398974869,
60
+ "loss": 2.9623,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.03179650238473768,
65
+ "grad_norm": 0.7144882678985596,
66
+ "learning_rate": 0.00013090169943749476,
67
+ "loss": 2.6517,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.03179650238473768,
72
+ "eval_loss": 0.6578609347343445,
73
+ "eval_runtime": 118.7794,
74
+ "eval_samples_per_second": 3.351,
75
+ "eval_steps_per_second": 0.842,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.03815580286168521,
80
+ "grad_norm": 0.6463198065757751,
81
+ "learning_rate": 9.372094804706867e-05,
82
+ "loss": 2.3795,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.04239533651298357,
87
+ "eval_loss": 0.5995034575462341,
88
+ "eval_runtime": 120.2682,
89
+ "eval_samples_per_second": 3.309,
90
+ "eval_steps_per_second": 0.831,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 2.613858577416192e+16,
121
  "train_batch_size": 4,
122
  "trial_name": null,
123
  "trial_params": null