ardaspear commited on
Commit
89d2698
·
verified ·
1 Parent(s): e539324

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:e416cc4d888cdf12b210413de5a8578762010edc20b842a44d11953f187ca270
3
  size 201892112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22cac41c482c8faca513db9f7db53b24749d07cb82eec510352f41af2e784ba5
3
  size 201892112
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2c95c32c3431613e08d510bda797066196c4a3571a3abdec03a9024fa03d2911
3
  size 102864548
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb1f53a378f949f188dd08f454444580c1f8c28c90388060c6c2568d80cba068
3
  size 102864548
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:66d8f2e10bd118fdac9d025c1b83156fdd4f01028217426d46dea10b07adc4c1
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e5b0cb815397e3c92225b2dab264a7d448e514e16e7690c2e9a5cf6380cd5479
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": 0.004376559149196902,
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": 23.683,
112
  "eval_steps_per_second": 2.961,
113
  "step": 25
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
114
  }
115
  ],
116
  "logging_steps": 3,
@@ -130,7 +152,7 @@
130
  "attributes": {}
131
  }
132
  },
133
- "total_flos": 1.0612410566049792e+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": 0.005251870979036281,
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": 23.683,
112
  "eval_steps_per_second": 2.961,
113
  "step": 25
114
+ },
115
+ {
116
+ "epoch": 0.004726683881132654,
117
+ "grad_norm": 5.901070594787598,
118
+ "learning_rate": 6.167226819279528e-05,
119
+ "loss": 1.0971,
120
+ "step": 27
121
+ },
122
+ {
123
+ "epoch": 0.005251870979036281,
124
+ "grad_norm": 6.64203405380249,
125
+ "learning_rate": 5e-05,
126
+ "loss": 1.0402,
127
+ "step": 30
128
+ },
129
+ {
130
+ "epoch": 0.005251870979036281,
131
+ "eval_loss": 1.1571475267410278,
132
+ "eval_runtime": 406.5337,
133
+ "eval_samples_per_second": 23.666,
134
+ "eval_steps_per_second": 2.959,
135
+ "step": 30
136
  }
137
  ],
138
  "logging_steps": 3,
 
152
  "attributes": {}
153
  }
154
  },
155
+ "total_flos": 1.2745558418522112e+16,
156
  "train_batch_size": 8,
157
  "trial_name": null,
158
  "trial_params": null