Hugging Face's logo

tuantmdev
/
05b3a41e-7187-4f77-bfcc-d205d0a2e951

PEFT
Safetensors
mistral
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
721bdb2
·
verified ·
1 Parent(s): fb73f10

Training in progress, step 400, checkpoint

Browse files
Files changed (5) hide show
  1. last-checkpoint/adapter_model.safetensors +1 -1
  2. last-checkpoint/optimizer.pt +1 -1
  3. last-checkpoint/rng_state.pth +1 -1
  4. last-checkpoint/scheduler.pt +1 -1
  5. last-checkpoint/trainer_state.json +27 -5
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b21751edd89464bdf2eda160884932f912c0b4bd483658f7997b32a58b857fdf
3
  size 113864
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a43763f1e4ca82ee5cf79697a7cfb0109d8d5bd711e45d3a202082e33cf245d2
3
  size 113864
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9b55320816417799d4a5fe7edfee650c6613ccd413c9c6e2ced20d6856847bd
3
  size 237606
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0db63aac13cd520792f76dde75007c08a3e328c1de0edac395e034e976a18eaf
3
  size 237606
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9181240285511a2677d7c7992dbbc017afe432ed39dc02ff18385ff52020e055
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc16dfe9ccbcac541ede0af34b40df2a8b8435993d487eead390884edb8371f2
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": 10.315242767333984,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
- "epoch": 0.3757884847671453,
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": 315.061,
128
  "eval_steps_per_second": 157.731,
129
  "step": 350
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
130
  }
131
  ],
132
  "logging_steps": 40,
@@ -141,7 +163,7 @@
141
  "early_stopping_threshold": 0.0
142
  },
143
  "attributes": {
144
- "early_stopping_patience_counter": 0
145
  }
146
  },
147
  "TrainerControl": {
@@ -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": 18504483078144.0,
159
  "train_batch_size": 2,
160
  "trial_name": null,
161
  "trial_params": null
 
1
  {
2
  "best_metric": 10.315242767333984,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-350",
4
+ "epoch": 0.42947255401959467,
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": 315.061,
128
  "eval_steps_per_second": 157.731,
129
  "step": 350
130
+ },
131
+ {
132
+ "epoch": 0.38652529861763524,
133
+ "grad_norm": 0.7442543506622314,
134
+ "learning_rate": 3.8060233744356633e-06,
135
+ "loss": 82.5153,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.42947255401959467,
140
+ "grad_norm": 1.5092549324035645,
141
+ "learning_rate": 0.0,
142
+ "loss": 82.4893,
143
+ "step": 400
144
+ },
145
+ {
146
+ "epoch": 0.42947255401959467,
147
+ "eval_loss": 10.315845489501953,
148
+ "eval_runtime": 2.4735,
149
+ "eval_samples_per_second": 317.358,
150
+ "eval_steps_per_second": 158.881,
151
+ "step": 400
152
  }
153
  ],
154
  "logging_steps": 40,
 
163
  "early_stopping_threshold": 0.0
164
  },
165
  "attributes": {
166
+ "early_stopping_patience_counter": 1
167
  }
168
  },
169
  "TrainerControl": {
 
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": 21134894039040.0,
181
  "train_batch_size": 2,
182
  "trial_name": null,
183
  "trial_params": null