cvoffer commited on
Commit
5696dfd
·
verified ·
1 Parent(s): 8bd2464

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 sha256:5d81a5dbb7a5afc0f552ee9800ab19e54dedd8a8449e5e9602c61e1d4a7509e1
3
  size 159967880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:536270091c26545985f0b4a49f015a4d34d89e35628d561bb3c5daca719492bb
3
  size 159967880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9a5476c6959e8e1a76a1862150c0ce933fd3d5ef71a4362e98ce4fd341804d1b
3
  size 320194002
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:957090016edbdd4fc2bf7b8a540e97baf1b093de6b6094415f156f1deb72cff2
3
  size 320194002
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a45929d9a97dbe3e8f3b47feda09af466d725d8a7a4feef1dd76ddd7217823b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5afc85f5d22d31bbcb902635ba8c160003572d12eb86367ff5593ce490ad2af
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": 1.3295906782150269,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-10",
4
- "epoch": 0.0013667270304438446,
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": 3.726,
53
  "eval_steps_per_second": 1.863,
54
  "step": 10
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
55
  }
56
  ],
57
  "logging_steps": 3,
@@ -80,7 +117,7 @@
80
  "attributes": {}
81
  }
82
  },
83
- "total_flos": 6610941168844800.0,
84
  "train_batch_size": 2,
85
  "trial_name": null,
86
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.2255158424377441,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-20",
4
+ "epoch": 0.002733454060887689,
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": 3.726,
53
  "eval_steps_per_second": 1.863,
54
  "step": 10
55
+ },
56
+ {
57
+ "epoch": 0.0016400724365326135,
58
+ "grad_norm": 0.2799854874610901,
59
+ "learning_rate": 0.000163742398974869,
60
+ "loss": 0.8518,
61
+ "step": 12
62
+ },
63
+ {
64
+ "epoch": 0.002050090545665767,
65
+ "grad_norm": 0.2093087136745453,
66
+ "learning_rate": 0.00013090169943749476,
67
+ "loss": 0.9811,
68
+ "step": 15
69
+ },
70
+ {
71
+ "epoch": 0.002050090545665767,
72
+ "eval_loss": 1.2553142309188843,
73
+ "eval_runtime": 823.3936,
74
+ "eval_samples_per_second": 3.742,
75
+ "eval_steps_per_second": 1.872,
76
+ "step": 15
77
+ },
78
+ {
79
+ "epoch": 0.0024601086547989203,
80
+ "grad_norm": 0.217794269323349,
81
+ "learning_rate": 9.372094804706867e-05,
82
+ "loss": 0.883,
83
+ "step": 18
84
+ },
85
+ {
86
+ "epoch": 0.002733454060887689,
87
+ "eval_loss": 1.2255158424377441,
88
+ "eval_runtime": 825.0334,
89
+ "eval_samples_per_second": 3.734,
90
+ "eval_steps_per_second": 1.868,
91
+ "step": 20
92
  }
93
  ],
94
  "logging_steps": 3,
 
117
  "attributes": {}
118
  }
119
  },
120
+ "total_flos": 1.32218823376896e+16,
121
  "train_batch_size": 2,
122
  "trial_name": null,
123
  "trial_params": null