JacksonBrune commited on
Commit
ed82f0c
·
verified ·
1 Parent(s): b55acf3

Training in progress, step 108, 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:d5d9f6b98cc9f048e5169746ef789fc8480759447b2d5c6f5aaa1fb14ef8f2a7
3
  size 80792096
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a72ed405bab8cd14c6318ccbbb673e5e5a585c39d292417874f1881956c142d
3
  size 80792096
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5c0301a139bb8a85ad7acb7fcf314bfe162380ecc3eb4096c9178f7508aea9a0
3
  size 41459700
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:942c3196f785c6bf9f133c4213d77e393c946533c81c4bf4464759717269e81a
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:fd0720e792ecac2f254067a0dc257b8adbd58dfec0fa4539951aec0dd9a21bbe
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce66bcf37e6cf86178fb8345a22aed6f1309223896733e7455bba91587271e36
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5b8a8d75d7676c575e259c493c54103f7a2b90d3a7c875dd35fc40f677facad
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12d04027c11c32a353bd331b1c11424d837519f6887b6896322960683ea2c6db
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": 0.75,
5
  "eval_steps": 27,
6
- "global_step": 81,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -95,6 +95,28 @@
95
  "eval_samples_per_second": 24.45,
96
  "eval_steps_per_second": 12.225,
97
  "step": 81
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
98
  }
99
  ],
100
  "logging_steps": 10,
@@ -109,12 +131,12 @@
109
  "should_evaluate": false,
110
  "should_log": false,
111
  "should_save": true,
112
- "should_training_stop": false
113
  },
114
  "attributes": {}
115
  }
116
  },
117
- "total_flos": 2.078093484962611e+16,
118
  "train_batch_size": 2,
119
  "trial_name": null,
120
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 1.0,
5
  "eval_steps": 27,
6
+ "global_step": 108,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
95
  "eval_samples_per_second": 24.45,
96
  "eval_steps_per_second": 12.225,
97
  "step": 81
98
+ },
99
+ {
100
+ "epoch": 0.8333333333333334,
101
+ "grad_norm": 1.6890088319778442,
102
+ "learning_rate": 1.4696166665835853e-05,
103
+ "loss": 1.8259,
104
+ "step": 90
105
+ },
106
+ {
107
+ "epoch": 0.9259259259259259,
108
+ "grad_norm": 1.789994478225708,
109
+ "learning_rate": 2.9622342385589254e-06,
110
+ "loss": 1.8186,
111
+ "step": 100
112
+ },
113
+ {
114
+ "epoch": 1.0,
115
+ "eval_loss": 1.9264085292816162,
116
+ "eval_runtime": 1.8765,
117
+ "eval_samples_per_second": 24.514,
118
+ "eval_steps_per_second": 12.257,
119
+ "step": 108
120
  }
121
  ],
122
  "logging_steps": 10,
 
131
  "should_evaluate": false,
132
  "should_log": false,
133
  "should_save": true,
134
+ "should_training_stop": true
135
  },
136
  "attributes": {}
137
  }
138
  },
139
+ "total_flos": 2.766434723168256e+16,
140
  "train_batch_size": 2,
141
  "trial_name": null,
142
  "trial_params": null