great0001 commited on
Commit
581fd7f
·
verified ·
1 Parent(s): fb4248e

Training in progress, step 50, 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:e4c81f7d053d56d2ab1f38cccd123b20070aaf85767319b4d76a784a5c869a37
3
  size 190757752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d169a687320abd7201b5a2b106db87e9502e81e313a270420105bc110ea1cca4
3
  size 190757752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:30de5e6b12a8dcd9fd6bef6fe12147c25da16f5e99a73db092a71202418e935c
3
  size 97267892
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:23a66833c1633b832040da70e00b420e3155866cb97fa4c827326eb9653bd66d
3
  size 97267892
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:494086c651130cc3e2f89bcb64a15012216c62d147e8e5b7df1c3657929372c8
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2e49a4713024d996cbee5be53ad3c5b0014c56c6565e00d9107c8efcc22aa00f
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0030788663456224837,
5
  "eval_steps": 13,
6
- "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -60,6 +60,20 @@
60
  "eval_samples_per_second": 42.227,
61
  "eval_steps_per_second": 21.121,
62
  "step": 39
 
 
 
 
 
 
 
 
 
 
 
 
 
 
63
  }
64
  ],
65
  "logging_steps": 10,
@@ -74,12 +88,12 @@
74
  "should_evaluate": false,
75
  "should_log": false,
76
  "should_save": true,
77
- "should_training_stop": false
78
  },
79
  "attributes": {}
80
  }
81
  },
82
- "total_flos": 2014187693801472.0,
83
  "train_batch_size": 2,
84
  "trial_name": null,
85
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.003947264545669851,
5
  "eval_steps": 13,
6
+ "global_step": 50,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
60
  "eval_samples_per_second": 42.227,
61
  "eval_steps_per_second": 21.121,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.003157811636535881,
66
+ "grad_norm": 4.301798343658447,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 1.2228,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.003947264545669851,
73
+ "grad_norm": 5.790259838104248,
74
+ "learning_rate": 0.0,
75
+ "loss": 1.3358,
76
+ "step": 50
77
  }
78
  ],
79
  "logging_steps": 10,
 
88
  "should_evaluate": false,
89
  "should_log": false,
90
  "should_save": true,
91
+ "should_training_stop": true
92
  },
93
  "attributes": {}
94
  }
95
  },
96
+ "total_flos": 2553702254641152.0,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null