jssky commited on
Commit
ad465fc
1 Parent(s): fd42b2a

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 sha256:420cb6aa20d320182167714bd6585093a46231b1533b4e949ebca85ae718d6d5
3
  size 35237104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:363144cf38251484b629869983ed44f133019678ea2089ea9222edc61d94ea7e
3
  size 35237104
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fc5eaf0182a09660816ee42748119ba9ba47ac5ee7e20eda5c1bdae4142fa997
3
  size 18810036
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a9d2ac61f8efdc286da39761c5e2fc7609d9c7855d885bc1eda79163605a4d9d
3
  size 18810036
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc31493e63ecd538ed9797ce7f0b1f45e546239d1056d5181e4cff524b5c4118
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7567ae8a1ec33e28c23869de794452faaab4545ecafbc1b4920ceae179c9547
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": 0.00020951732446376658,
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": 16.887,
74
  "eval_steps_per_second": 16.887,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 216286290247680.0,
96
  "train_batch_size": 1,
97
  "trial_name": null,
98
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0003142759866956499,
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": 16.887,
74
  "eval_steps_per_second": 16.887,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.00024443687854106103,
79
+ "grad_norm": 1.8792164325714111,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.4839,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.00027935643261835545,
86
+ "grad_norm": 2.3412582874298096,
87
+ "learning_rate": 0.00016,
88
+ "loss": 1.5353,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0003142759866956499,
93
+ "grad_norm": 1.6153055429458618,
94
+ "learning_rate": 0.00018,
95
+ "loss": 1.6283,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0003142759866956499,
100
+ "eval_loss": 2.0233631134033203,
101
+ "eval_runtime": 358.2408,
102
+ "eval_samples_per_second": 16.829,
103
+ "eval_steps_per_second": 16.829,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 324429435371520.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null