fats-fme commited on
Commit
309c012
1 Parent(s): 22165a2

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 sha256:4887da4add908014cd983f4445d2b947544b120bff63f066248572301af9eb42
3
  size 50624
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2bceb52bf33dfa0a2bb6e6658dc71198c0307001dddccd64e0569cb4b5e4acd0
3
  size 50624
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2590de21df2c71616d6c80ea30cafee07f8b78aa4f6eb5fe0bc948b73937c0c0
3
  size 118090
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:72bec9af03f6adaf88471cea7962894903cae150919a698b931e674a2509c063
3
  size 118090
last-checkpoint/rng_state_0.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d15fe51fa3cbb901bfb2befbf96bc2ec7c0ffec4192ee59ce440bc34867e1a44
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b178972a0bc48550c2fac19712e1b235453f958232c8b0df94bce3618b54a88d
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:f69d5ba6761ac9f26960ae6afbdbf7137bc92600b7a5d4043e27216619dd3479
3
  size 14512
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:df8a060ebfb59cf9323e12c4330b97d75adfae456873b34b1865281e71386a3d
3
  size 14512
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:621519582414cbcc961b30cff113e8b1e10923f26e46ef8e0ad7c29a35554318
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b31a829d59ebd39c9acc251fad364f0269b01d5c00f5b496056b99c740c21da1
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": 0.0025517436915225406,
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": 154.377,
103
  "eval_steps_per_second": 38.62,
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": 1882888077312.0,
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": 0.002835270768358378,
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": 154.377,
103
  "eval_steps_per_second": 38.62,
104
  "step": 9
105
+ },
106
+ {
107
+ "epoch": 0.002835270768358378,
108
+ "grad_norm": 0.12301714718341827,
109
+ "learning_rate": 0.0001,
110
+ "loss": 10.3881,
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": 2092097863680.0,
132
  "train_batch_size": 2,
133
  "trial_name": null,
134
  "trial_params": null