ardaspear commited on
Commit
466f44f
·
verified ·
1 Parent(s): 1eaf2f8

Training in progress, step 30, checkpoint

Browse files
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:90a2a726e05ae20a90cf9c53772c366b07862323166b9102d0b4ee5708bf7017
3
  size 639691872
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a22dc5933573d5ad0e2f0b88c8c0e4722f68fbee2dc78913b62afe5cdb963ee
3
  size 639691872
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3b7b217c592fd9476ea79ce5cb57ffdda20be7520b1b2f919d3a2c1d81b2506c
3
  size 325339796
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5590974220156f343bf17cd1dfea83c1eb69ca441840f889bdfb9ac844cbedc1
3
  size 325339796
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:295f0a621346f38e97a347d06bb9927816fe04926f6efca6f6b2fe56f30407d9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67ed692faf639600dadb63e47f782862b02e2b4f1c7bed5e0ed7d786d641b235
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
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": 0.14641288433382138,
5
  "eval_steps": 5,
6
- "global_step": 25,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -111,6 +111,28 @@
111
  "eval_samples_per_second": 15.601,
112
  "eval_steps_per_second": 1.95,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 3.32627164790784e+16,
134
  "train_batch_size": 8,
135
  "trial_name": null,
136
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.17569546120058566,
5
  "eval_steps": 5,
6
+ "global_step": 30,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
111
  "eval_samples_per_second": 15.601,
112
  "eval_steps_per_second": 1.95,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.1581259150805271,
117
+ "grad_norm": 10.735950469970703,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 2.6784,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.17569546120058566,
124
+ "grad_norm": 8.114375114440918,
125
+ "learning_rate": 5e-05,
126
+ "loss": 2.319,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.17569546120058566,
131
+ "eval_loss": 0.48306477069854736,
132
+ "eval_runtime": 18.4788,
133
+ "eval_samples_per_second": 15.585,
134
+ "eval_steps_per_second": 1.948,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 3.991525977489408e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null