Hugging Face's logo

tuantmdev
/
6860d41c-54b0-429a-b48d-4e896b5c9961

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
tuantmdev commited on
Commit
e624b04
·
verified ·
1 Parent(s): 3677905

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 +29 -7
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e7486d601c6a18aacfdfeed2bd2b54565c661839b313247cd4bc7278b0704927
3
  size 2436967616
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd6dbc1f821864e783e661fa12e693eb76d6a4a233c3e27511b251c8f1d2cf9d
3
  size 2436967616
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a9c9d50313bdd1f25ae62148e0793e8d6b47ca8137ec2284a8926c1c89d09a7f
3
  size 170920532
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a28ce728be1e6cb27a1eafb8b00c46205718b05b9a7e8cc0fefc752ca88abd3
3
  size 170920532
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:33eb612e08d19c1cbd851b37d45e5358a268bbf325344a2480d41bdd2efcb680
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58711118e625284fcf8a641d26aad0f4433bc612bf26fbc21dd25f8986746391
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": 1.5710722208023071,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-300",
4
- "epoch": 0.02157996146435453,
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": 13.107,
128
  "eval_steps_per_second": 6.554,
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": 1
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": 1.4318745844658995e+17,
159
  "train_batch_size": 2,
160
  "trial_name": null,
161
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.5678154230117798,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-400",
4
+ "epoch": 0.02466281310211946,
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": 13.107,
128
  "eval_steps_per_second": 6.554,
129
  "step": 350
130
+ },
131
+ {
132
+ "epoch": 0.022196531791907514,
133
+ "grad_norm": 0.8112738728523254,
134
+ "learning_rate": 3.8060233744356633e-06,
135
+ "loss": 1.6334,
136
+ "step": 360
137
+ },
138
+ {
139
+ "epoch": 0.02466281310211946,
140
+ "grad_norm": 1.1077427864074707,
141
+ "learning_rate": 0.0,
142
+ "loss": 1.6116,
143
+ "step": 400
144
+ },
145
+ {
146
+ "epoch": 0.02466281310211946,
147
+ "eval_loss": 1.5678154230117798,
148
+ "eval_runtime": 1040.5356,
149
+ "eval_samples_per_second": 13.126,
150
+ "eval_steps_per_second": 6.563,
151
+ "step": 400
152
  }
153
  ],
154
  "logging_steps": 40,
 
163
  "early_stopping_threshold": 0.0
164
  },
165
  "attributes": {
166
+ "early_stopping_patience_counter": 0
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": 1.635628799188009e+17,
181
  "train_batch_size": 2,
182
  "trial_name": null,
183
  "trial_params": null