Hugging Face's logo

fats-fme
/
e092f4f9-78d0-4011-8b1a-b75b3e980bc1

PEFT
Safetensors
llama
axolotl
Generated from Trainer
Model card Files
xet
 Community
fats-fme commited on
Commit
8a4f8b3
·
verified ·
1 Parent(s): e9f974c

Training in progress, step 200, checkpoint

Browse files
Files changed (4) hide show
  1. last-checkpoint/optimizer.pt +1 -1
  2. last-checkpoint/rng_state.pth +1 -1
  3. last-checkpoint/scheduler.pt +1 -1
  4. last-checkpoint/trainer_state.json +83 -5
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7bd9b75326e43ef632f144ed3db967683dffcb91a639a64f67d859901c06f531
3
  size 79866276
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c4d36d1d036014fdf29af8ce4a167163f9c585b10538c145dbae1f5deb1c3ae4
3
  size 79866276
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:84d16e5ade4b2c40b2b56cc1779d956f655c9c297e34f8b9d0398c8d3f38636e
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:330021ac70e91dee5090af7d2fab1900ffbc4e4d7fffc3a50e52877d126f757b
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:691263e55c7bb34b6e090bd89cf079f362100d7bd758be475bd3e7091c1a4ed6
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2d754412c61116546142914503e7369d0cc35d3c380a07e5218f595d76b6d96
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.0026970170990884084,
5
  "eval_steps": 100,
6
- "global_step": 100,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -93,6 +93,84 @@
93
  "eval_samples_per_second": 17.376,
94
  "eval_steps_per_second": 8.688,
95
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
  }
97
  ],
98
  "logging_steps": 10,
@@ -107,7 +185,7 @@
107
  "early_stopping_threshold": 0.0
108
  },
109
  "attributes": {
110
- "early_stopping_patience_counter": 0
111
  }
112
  },
113
  "TrainerControl": {
@@ -116,12 +194,12 @@
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": 1595961638387712.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
  "best_metric": NaN,
3
  "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
+ "epoch": 0.005394034198176817,
5
  "eval_steps": 100,
6
+ "global_step": 200,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
93
  "eval_samples_per_second": 17.376,
94
  "eval_steps_per_second": 8.688,
95
  "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.002966718808997249,
99
+ "grad_norm": NaN,
100
+ "learning_rate": 9.755282581475769e-05,
101
+ "loss": 0.0,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.00323642051890609,
106
+ "grad_norm": NaN,
107
+ "learning_rate": 9.045084971874738e-05,
108
+ "loss": 0.0,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.0035061222288149305,
113
+ "grad_norm": NaN,
114
+ "learning_rate": 7.938926261462366e-05,
115
+ "loss": 0.0,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.0037758239387237717,
120
+ "grad_norm": NaN,
121
+ "learning_rate": 6.545084971874738e-05,
122
+ "loss": 0.0,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.004045525648632612,
127
+ "grad_norm": NaN,
128
+ "learning_rate": 5e-05,
129
+ "loss": 0.0,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.004315227358541453,
134
+ "grad_norm": NaN,
135
+ "learning_rate": 3.4549150281252636e-05,
136
+ "loss": 0.0,
137
+ "step": 160
138
+ },
139
+ {
140
+ "epoch": 0.004584929068450294,
141
+ "grad_norm": NaN,
142
+ "learning_rate": 2.061073738537635e-05,
143
+ "loss": 0.0,
144
+ "step": 170
145
+ },
146
+ {
147
+ "epoch": 0.0048546307783591345,
148
+ "grad_norm": NaN,
149
+ "learning_rate": 9.549150281252633e-06,
150
+ "loss": 0.0,
151
+ "step": 180
152
+ },
153
+ {
154
+ "epoch": 0.005124332488267975,
155
+ "grad_norm": NaN,
156
+ "learning_rate": 2.4471741852423237e-06,
157
+ "loss": 0.0,
158
+ "step": 190
159
+ },
160
+ {
161
+ "epoch": 0.005394034198176817,
162
+ "grad_norm": NaN,
163
+ "learning_rate": 0.0,
164
+ "loss": 0.0,
165
+ "step": 200
166
+ },
167
+ {
168
+ "epoch": 0.005394034198176817,
169
+ "eval_loss": NaN,
170
+ "eval_runtime": 898.4753,
171
+ "eval_samples_per_second": 17.376,
172
+ "eval_steps_per_second": 8.688,
173
+ "step": 200
174
  }
175
  ],
176
  "logging_steps": 10,
 
185
  "early_stopping_threshold": 0.0
186
  },
187
  "attributes": {
188
+ "early_stopping_patience_counter": 1
189
  }
190
  },
191
  "TrainerControl": {
 
194
  "should_evaluate": false,
195
  "should_log": false,
196
  "should_save": true,
197
+ "should_training_stop": true
198
  },
199
  "attributes": {}
200
  }
201
  },
202
+ "total_flos": 3227627116560384.0,
203
  "train_batch_size": 2,
204
  "trial_name": null,
205
  "trial_params": null