lesso commited on
Commit
ba22f3d
1 Parent(s): fa233ad

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 sha256:0d1dd18c9b3cefa077921600611dc4202347d245406263ac6b50b4437ccbccf9
3
  size 25271744
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c84cf75488a609edf773d9a267f1dc419b258283686d47acd9633b02e601275d
3
  size 25271744
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e907b2cba4d632db7cbe93f905b8e4c9868f50ee7533a02d89880c2465e0266e
3
  size 50644602
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa34c8178a84a20dec938fcaf6a48aeade7c672c1cf35f4b65ca98f46ac4d111
3
  size 50644602
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:88476cca778895e8f6fc0ce62e75c4eb34e2a6753b0330ed367b1810fb7506cc
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8553e6b7b203230de04c46abc800a9d1637993cf953706fd74e7852ad2a4bd7b
3
  size 14512
last-checkpoint/rng_state_1.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c67987ed9e4b714a7c9a3a18204371980574e6e97487d2f71430eac95201f642
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12ed487d7299cf554fa6782ea8f956d0ccbd0651e650a6ac9d43496d520112be
3
  size 14512
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": 0.024759284731774415,
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": 29.643,
103
  "eval_steps_per_second": 14.918,
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": 920851121700864.0,
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": 0.027510316368638238,
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": 29.643,
103
  "eval_steps_per_second": 14.918,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.027510316368638238,
108
+ "grad_norm": 0.9675346612930298,
109
+ "learning_rate": 0.00016,
110
+ "loss": 0.9712,
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": 1023167913000960.0,
132
  "train_batch_size": 1,
133
  "trial_name": null,
134
  "trial_params": null