lesso01 commited on
Commit
33ea90c
1 Parent(s): 14790e7

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 sha256:5723f64577d26d3cd2c64bb53c04f630a62b20122a504ed659a411b18ba3081e
3
  size 27024
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5703a9ae9e07f074beafcfdc30908e890f60eb4f68da459821534304131244cf
3
  size 27024
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:63c84dc8b985440b5960d8dd6c9a3931ddc106d51573d3e3b614ab08f725faa2
3
  size 63974
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4af2bb72532d2022babccfa9bdb77b6b835bd223c147497b1adb9debfca9e2bf
3
  size 63974
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:56e4c605570ee3c73fe8ff5167e52a53ea3100415d1bfd842431b5b9a62a411e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12066a9c624fe38430ff3feea2dc6451e9f1a920255c11680c737a33d2c53a0
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
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": 0.0003793266951161688,
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": 222.142,
103
  "eval_steps_per_second": 111.071,
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": 723619381248.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.000421474105684632,
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": 222.142,
103
  "eval_steps_per_second": 111.071,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.000421474105684632,
108
+ "grad_norm": 0.015935491770505905,
109
+ "learning_rate": 0.0002,
110
+ "loss": 11.7665,
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": 812484919296.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null