dixedus commited on
Commit
eb20851
·
verified ·
1 Parent(s): 95033f8

Training in progress, step 36, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0cfb84e66e6d7e6ac9cb1fba4e7fe0194263d9a4f3624128ea2c3e7b48ca92a2
3
  size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:430d1b2713445a662ccf110f86e8833b748e732cac421189ebe75ad3c4887379
3
  size 167832240
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:807363c14a34f42629792a1dcd97052ae3445965d99cfce3b7ced0835245fa04
3
  size 85723284
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1134086ee4a1ff2a80530a4d0036fe055170285fca67039bbdd3dc88101a32d1
3
  size 85723284
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:cc3af19de247348acb313345a43a4aa9e3e74629a4910adb275427735ab53b92
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87c522dcd1e4b502aba9b066a9d8ab7c80ee5dcffa17dfeef57048e2b65b6eba
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95e5b5e126f269e3dd52e13e2ce68743557810f4e2bb59a1eda63231c7828066
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
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": 0.19424460431654678,
5
  "eval_steps": 9,
6
- "global_step": 27,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -102,6 +102,35 @@
102
  "eval_samples_per_second": 12.072,
103
  "eval_steps_per_second": 1.548,
104
  "step": 27
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 3,
@@ -121,7 +150,7 @@
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 4.605498216362803e+16,
125
  "train_batch_size": 8,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.2589928057553957,
5
  "eval_steps": 9,
6
+ "global_step": 36,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 12.072,
103
  "eval_steps_per_second": 1.548,
104
  "step": 27
105
+ },
106
+ {
107
+ "epoch": 0.2158273381294964,
108
+ "grad_norm": 2.0901005268096924,
109
+ "learning_rate": 4.415111107797445e-05,
110
+ "loss": 4.397,
111
+ "step": 30
112
+ },
113
+ {
114
+ "epoch": 0.23741007194244604,
115
+ "grad_norm": 3.103538751602173,
116
+ "learning_rate": 4.2366459261474933e-05,
117
+ "loss": 4.2221,
118
+ "step": 33
119
+ },
120
+ {
121
+ "epoch": 0.2589928057553957,
122
+ "grad_norm": 1.9494324922561646,
123
+ "learning_rate": 4.039153688314145e-05,
124
+ "loss": 4.3688,
125
+ "step": 36
126
+ },
127
+ {
128
+ "epoch": 0.2589928057553957,
129
+ "eval_loss": 1.0416053533554077,
130
+ "eval_runtime": 19.3673,
131
+ "eval_samples_per_second": 12.082,
132
+ "eval_steps_per_second": 1.549,
133
+ "step": 36
134
  }
135
  ],
136
  "logging_steps": 3,
 
150
  "attributes": {}
151
  }
152
  },
153
+ "total_flos": 6.082070163593626e+16,
154
  "train_batch_size": 8,
155
  "trial_name": null,
156
  "trial_params": null