nathanialhunt commited on
Commit
592db68
·
verified ·
1 Parent(s): 599879d

Training in progress, step 9, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1c96074e1396e4b935f6f05057eeac05324bf13bc22e154efa2b606c8fa42c84
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b738a144c230daa4466fb992fbcd96981b47b4de1c42c9eebd9040e691f250bf
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:067c400eaf5af12e608f60a15addb991a0b15b3d2ad6add2ed648009264ed345
3
  size 43122580
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55d8b91b4e24d8383b4356cb06404ceb167fda68bb45e468478a5ef9f78f6d16
3
  size 43122580
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0ab4a38a5f8cb730ad7b7d6266876133f2bd3b82a7a3376ae62ebba181825498
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5bcc9dec470456049b85d58761d8b1cb7c00e042c845ac37d7d42f59480fe0bd
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0099cb7287625b29b67c4fcf42ff20fae623b429bfb10f5ac695bc54f2be54fd
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
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": 0.006577144423129624,
5
  "eval_steps": 3,
6
- "global_step": 6,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -73,6 +73,35 @@
73
  "eval_samples_per_second": 24.058,
74
  "eval_steps_per_second": 12.06,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1710846929534976.0,
96
  "train_batch_size": 2,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.009865716634694436,
5
  "eval_steps": 3,
6
+ "global_step": 9,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
73
  "eval_samples_per_second": 24.058,
74
  "eval_steps_per_second": 12.06,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.007673335160317895,
79
+ "grad_norm": 1.8144712448120117,
80
+ "learning_rate": 0.00014,
81
+ "loss": 0.6918,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.008769525897506167,
86
+ "grad_norm": 1.2779066562652588,
87
+ "learning_rate": 0.00016,
88
+ "loss": 0.2668,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.009865716634694436,
93
+ "grad_norm": 0.8901863098144531,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.0162,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.009865716634694436,
100
+ "eval_loss": 0.3736807703971863,
101
+ "eval_runtime": 16.037,
102
+ "eval_samples_per_second": 24.007,
103
+ "eval_steps_per_second": 12.035,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2358194416386048.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null