trenden commited on
Commit
7cee539
·
verified ·
1 Parent(s): 9e1bae0

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 sha256:56e2a517b58e08a1620263aa41a05c98ed49d337d045ded30df656920a3d849b
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2851021cb7e2dc44a86a679dbd209c069caafefe02a8f7b546d66936780030
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e338a4083c27b030bac12ec258c20830aecc29584dea562f5380458e2b63b7f6
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:925654c0977eadca5a98ef9764e1e504537ac461b9dcc2efa451913bc8101525
3
  size 41459700
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fa55bb1211b966ee38680600e87c633649407947bf0fb7e8011fe6d5c3e8c50b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49311aa84f093855e564eba491f4fc5bbfe961780cd6ee624abc6a30cc246dde
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": 0.0020581425263699513,
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": 21.156,
74
  "eval_steps_per_second": 10.578,
75
  "step": 6
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
76
  }
77
  ],
78
  "logging_steps": 1,
@@ -92,7 +121,7 @@
92
  "attributes": {}
93
  }
94
  },
95
- "total_flos": 1873333749547008.0,
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": 0.0030872137895549268,
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": 21.156,
74
  "eval_steps_per_second": 10.578,
75
  "step": 6
76
+ },
77
+ {
78
+ "epoch": 0.002401166280764943,
79
+ "grad_norm": 1.7233264446258545,
80
+ "learning_rate": 0.00014,
81
+ "loss": 2.8047,
82
+ "step": 7
83
+ },
84
+ {
85
+ "epoch": 0.002744190035159935,
86
+ "grad_norm": 1.5937248468399048,
87
+ "learning_rate": 0.00016,
88
+ "loss": 2.5841,
89
+ "step": 8
90
+ },
91
+ {
92
+ "epoch": 0.0030872137895549268,
93
+ "grad_norm": 1.8650206327438354,
94
+ "learning_rate": 0.00018,
95
+ "loss": 2.9066,
96
+ "step": 9
97
+ },
98
+ {
99
+ "epoch": 0.0030872137895549268,
100
+ "eval_loss": 2.503354787826538,
101
+ "eval_runtime": 57.7567,
102
+ "eval_samples_per_second": 21.262,
103
+ "eval_steps_per_second": 10.631,
104
+ "step": 9
105
  }
106
  ],
107
  "logging_steps": 1,
 
121
  "attributes": {}
122
  }
123
  },
124
+ "total_flos": 2875349476048896.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null