VERSIL91 commited on
Commit
a7f24f1
·
verified ·
1 Parent(s): 7643e09

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:b3175cde6908bb949795eb8a7b48a66e0793f183b0da88811f5f94c0ac980017
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a70ffe32f586b15d03a3a4e75d0c0d2e9cc3c2ce757514b1bc1ee1fa14b760c7
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:92be87594d303b6187e987af9c543f595f10fffabc354d7c4dc6a65cbfaea31e
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ddd23b9bcc52e0424715908d9c4673979a9469f5f9fc8658a7ee974da6e6cc09
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:557fadda68f81af2c774a79a4c369bd061cd88e6452778324e57a9edcd611ffb
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
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": 0.004967744161175699,
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": 707.26,
103
  "eval_steps_per_second": 353.63,
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": 4253810688.0,
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": 0.005519715734639666,
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": 707.26,
103
  "eval_steps_per_second": 353.63,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.005519715734639666,
108
+ "grad_norm": 0.0435008704662323,
109
+ "learning_rate": 0.0001,
110
+ "loss": 11.9317,
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": 4726456320.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null