trenden commited on
Commit
ea47b87
·
verified ·
1 Parent(s): bba548b

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 sha256:1ddea9fead2f96758b8f57d938ba0fce87c54ac5847d44e07da6a371e55cbe9a
3
  size 109009752
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8516f5a19f50f442409b54acf3a33212f17a0d1576a4c93ab22bf874a751a6ce
3
  size 109009752
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9709ae65c4b48f0fa29ccd31ade70b35192a3a0ad4d41c21c768b583e5aaf8c7
3
  size 56088148
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cddde3476367efd67d905218083bca08d400fa2a6f243ce04e3bec1aa0f30f17
3
  size 56088148
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c08b4a49f49241773a60a024c1b9c1584ca824ef6695a0c84b1e802f41c8b8e3
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8761e80a67a0e3a5e4214ac9d8140801abe498f969e7741ed8234c2fea0d7e7
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": 0.006957762811649793,
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": 20.178,
61
  "eval_steps_per_second": 10.093,
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": 1.066652267446272e+16,
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": 0.00892020873288435,
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": 20.178,
61
  "eval_steps_per_second": 10.093,
62
  "step": 39
63
+ },
64
+ {
65
+ "epoch": 0.0071361669863074795,
66
+ "grad_norm": 0.5293271541595459,
67
+ "learning_rate": 2.339555568810221e-05,
68
+ "loss": 2.4498,
69
+ "step": 40
70
+ },
71
+ {
72
+ "epoch": 0.00892020873288435,
73
+ "grad_norm": 0.5129912495613098,
74
+ "learning_rate": 0.0,
75
+ "loss": 2.5075,
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": 1.383479673618432e+16,
97
  "train_batch_size": 2,
98
  "trial_name": null,
99
  "trial_params": null