sergioalves commited on
Commit
c7ddcf4
·
verified ·
1 Parent(s): 8eabe39

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:bd0c3ea5753b5a8094b40b9c0df40e021c0337fabb70857525e4e12734245657
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58eba2295aa59eaaaf1e8cab5a76df021e9d147fb75e3514f155e34a786c5a25
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:362138f2494739429759cbb57e607f9fe8cf7e6ac1ec3f85096ffd49cf02c228
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d294b7add7659ee47712ba99a93c40c294a0b70e00fc83a8109e2b8a913c2bc4
3
  size 118090
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21aa8370193657821b503919b759f89eb95410363c83bd1abe5823cc1ce9612a
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ef478262fdad1eef4d24ea689c7527a913041936810e0ef87a887ec073842b3
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": 10.376873970031738,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.01137009664582149,
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": 161.149,
53
  "eval_steps_per_second": 40.45,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -80,7 +117,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 536100077568.0,
84
  "train_batch_size": 4,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 10.375664710998535,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.02274019329164298,
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": 161.149,
53
  "eval_steps_per_second": 40.45,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.013644115974985787,
58
+ "grad_norm": 0.03667740151286125,
59
+ "learning_rate": 0.000163742398974869,
60
+ "loss": 10.377,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.017055144968732235,
65
+ "grad_norm": 0.03651963546872139,
66
+ "learning_rate": 0.00013090169943749476,
67
+ "loss": 10.376,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.017055144968732235,
72
+ "eval_loss": 10.376157760620117,
73
+ "eval_runtime": 4.6278,
74
+ "eval_samples_per_second": 160.119,
75
+ "eval_steps_per_second": 40.192,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.02046617396247868,
80
+ "grad_norm": 0.03485073149204254,
81
+ "learning_rate": 9.372094804706867e-05,
82
+ "loss": 10.3759,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.02274019329164298,
87
+ "eval_loss": 10.375664710998535,
88
+ "eval_runtime": 4.537,
89
+ "eval_samples_per_second": 163.323,
90
+ "eval_steps_per_second": 40.996,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 1059124543488.0,
121
  "train_batch_size": 4,
122
  "trial_name": null,
123
  "trial_params": null