tuantmdev commited on
Commit
49bd259
·
verified ·
1 Parent(s): c715913

Training in progress, step 400, 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:b41c6d0a5d962252c16a0664bf29f69eccb3c7c2bb9eab6f738b6490ffaeafc0
3
  size 18887640
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3eb4ac26a10b81b7739c1b29d323cb9f4dd43739cd2189f1363fe30a1edfd6c1
3
  size 18887640
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d5f8c5f881347e2070b05d31cd1ead46d493c15bfe2ee35b57c08aa1ef3aa668
3
  size 9699194
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27ec274ce9200771106450cff687ec2970a138d311fd96872c7032b2b62bcce6
3
  size 9699194
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1785e7476b6984485a124d2a02b6295a3b332843cf7cfba46d734823f7107dc9
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f87929ca513841f05993ac6ea480753fbcd7752f236474ee78ae410959ab04c8
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1a982b0cf4aa3113be3ccf8c7c44abbcbdbc330e78e6392b70eb543df2118de5
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:705cabf5cbc3a6ab0feb67c77b9b453d59efcc939ce90d310af96e621810f990
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 1.8631290197372437,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.22241639526570817,
5
  "eval_steps": 50,
6
- "global_step": 350,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -127,6 +127,28 @@
127
  "eval_samples_per_second": 138.618,
128
  "eval_steps_per_second": 69.309,
129
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  }
131
  ],
132
  "logging_steps": 40,
@@ -150,12 +172,12 @@
150
  "should_evaluate": false,
151
  "should_log": false,
152
  "should_save": true,
153
- "should_training_stop": false
154
  },
155
  "attributes": {}
156
  }
157
  },
158
- "total_flos": 2313958512918528.0,
159
  "train_batch_size": 2,
160
  "trial_name": null,
161
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.842798113822937,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-400",
4
+ "epoch": 0.2541901660179522,
5
  "eval_steps": 50,
6
+ "global_step": 400,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
127
  "eval_samples_per_second": 138.618,
128
  "eval_steps_per_second": 69.309,
129
  "step": 350
130
+ },
131
+ {
132
+ "epoch": 0.22877114941615695,
133
+ "grad_norm": 4149.703125,
134
+ "learning_rate": 3.8060233744356633e-06,
135
+ "loss": 15.2292,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.2541901660179522,
140
+ "grad_norm": 2392.755126953125,
141
+ "learning_rate": 0.0,
142
+ "loss": 14.769,
143
+ "step": 400
144
+ },
145
+ {
146
+ "epoch": 0.2541901660179522,
147
+ "eval_loss": 1.842798113822937,
148
+ "eval_runtime": 9.6006,
149
+ "eval_samples_per_second": 138.116,
150
+ "eval_steps_per_second": 69.058,
151
+ "step": 400
152
  }
153
  ],
154
  "logging_steps": 40,
 
172
  "should_evaluate": false,
173
  "should_log": false,
174
  "should_save": true,
175
+ "should_training_stop": true
176
  },
177
  "attributes": {}
178
  }
179
  },
180
+ "total_flos": 2647679771344896.0,
181
  "train_batch_size": 2,
182
  "trial_name": null,
183
  "trial_params": null