chauhoang commited on
Commit
6fce89c
·
verified ·
1 Parent(s): 3383213

Training in progress, step 39, 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:f456e6ae379bdee6a485dd85a85b5cf2c34da91a187bf941299cab9796a76fff
3
  size 17640136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dea13992fe5f2132a90eefac1b0e4b8a4fdf79063113045eea18d4f02a406b9e
3
  size 17640136
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:254bef4a9cce09d158bdab09a6e8f6d6a8c7dfd744271141bd3c95a1151b2de5
3
  size 9568884
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6d55306bebe75b76284562a5adc18e1b802564309bf28b844172a5228904f1a7
3
  size 9568884
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:93c0a2f298542422c4f57b584e3c4258688b62f2945feca91d54575c701b5435
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bec698543fc8efe1c42cfec18e55613892ce220f315dbecc631afb9ede0781a9
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
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": 0.0010436004214540164,
5
  "eval_steps": 10,
6
- "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -66,6 +66,28 @@
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.0411,
68
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
  }
70
  ],
71
  "logging_steps": 5,
@@ -85,7 +107,7 @@
85
  "attributes": {}
86
  }
87
  },
88
- "total_flos": 365056471597056.0,
89
  "train_batch_size": 2,
90
  "trial_name": null,
91
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0015654006321810245,
5
  "eval_steps": 10,
6
+ "global_step": 39,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
66
  "learning_rate": 6.91341716182545e-05,
67
  "loss": 0.0411,
68
  "step": 25
69
+ },
70
+ {
71
+ "epoch": 0.001204154332446942,
72
+ "grad_norm": 0.5554239749908447,
73
+ "learning_rate": 5e-05,
74
+ "loss": 0.0619,
75
+ "step": 30
76
+ },
77
+ {
78
+ "epoch": 0.001204154332446942,
79
+ "eval_loss": 0.058448392897844315,
80
+ "eval_runtime": 388.8644,
81
+ "eval_samples_per_second": 26.976,
82
+ "eval_steps_per_second": 13.488,
83
+ "step": 30
84
+ },
85
+ {
86
+ "epoch": 0.001404846721188099,
87
+ "grad_norm": 0.6090171933174133,
88
+ "learning_rate": 3.086582838174551e-05,
89
+ "loss": 0.0787,
90
+ "step": 35
91
  }
92
  ],
93
  "logging_steps": 5,
 
107
  "attributes": {}
108
  }
109
  },
110
+ "total_flos": 552036615585792.0,
111
  "train_batch_size": 2,
112
  "trial_name": null,
113
  "trial_params": null