lesso commited on
Commit
8ed021e
1 Parent(s): 0d870d1

Training in progress, step 10, 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:af392bdd238c7dec56a878f8e7a9f703dbb092e68deb6d265e6f3e13c056d929
3
  size 83945296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:73a8c2c36dffffb8ebd203b89578b740ec248b53ca4912e9d49ff8561e422512
3
  size 83945296
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e37860f528a0b494fd027d21f377b5256fc4b346b9b870685ca5ccdca75fbc06
3
  size 168037178
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb50fc47723b0761c460e50c5c6811f93f4a5c44bb0a6a3253944dde47d41195
3
  size 168037178
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b90a19943f8ef28f7f3c1abafd8de7b24ff68c3eda11dffdc748b1a1d989fcb2
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:574c700717b33f47ad8a70b47083271e5db120d9e87ae1c83258d7702c5eeb81
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8bdda546a1390be3b85a90dd4ef31050dfb7b691765ffc12ed691b6786ed6e3d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:26a93b2a1f4b5368650119fe6e0d6eec6d19cda6badeba4d21943ab48964fa00
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": 0.02702702702702703,
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,
@@ -102,6 +102,13 @@
102
  "eval_samples_per_second": 14.169,
103
  "eval_steps_per_second": 14.169,
104
  "step": 9
 
 
 
 
 
 
 
105
  }
106
  ],
107
  "logging_steps": 1,
@@ -116,12 +123,12 @@
116
  "should_evaluate": false,
117
  "should_log": false,
118
  "should_save": true,
119
- "should_training_stop": false
120
  },
121
  "attributes": {}
122
  }
123
  },
124
- "total_flos": 1664607823331328.0,
125
  "train_batch_size": 1,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.03003003003003003,
5
  "eval_steps": 3,
6
+ "global_step": 10,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
102
  "eval_samples_per_second": 14.169,
103
  "eval_steps_per_second": 14.169,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.03003003003003003,
108
+ "grad_norm": 3.6290924549102783,
109
+ "learning_rate": 0.00016,
110
+ "loss": 2.4698,
111
+ "step": 10
112
  }
113
  ],
114
  "logging_steps": 1,
 
123
  "should_evaluate": false,
124
  "should_log": false,
125
  "should_save": true,
126
+ "should_training_stop": true
127
  },
128
  "attributes": {}
129
  }
130
  },
131
+ "total_flos": 1849564248145920.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null