Hugging Face's logo

fats-fme
/
28ca8254-6e22-4fef-b3ac-882bfa93b3e8

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
1
fats-fme commited on
Commit
478e149
·
verified ·
1 Parent(s): 9b24fdd

Training in progress, step 200, 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 +84 -6
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2939777b0e4a8b0876924c5310e0fccff18e050f20b74abb540d4a63614ae625
3
  size 281587880
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b5576b1a75896f65c336d83650e30d2050ffd7c9becb4a5c80ea5f28bbf0eaae
3
  size 281587880
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:734681681c8035878e8c361e5aaf890db76ea10d42af9349e85de8093e87ed17
3
  size 143365780
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b4df2d15dc120b344d1c40ef30ad4b539d21831629742369ca24da5176890976
3
  size 143365780
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21a421b3448c24398a3047080c91284d9c5142d3766e9f839cb32bd56b4a2727
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b162baf04e073922232119dbf7ea8452bb637e4cc77c6392e39765246368dcc
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": 1.4834803342819214,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.015355675841682983,
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": 28.955,
94
  "eval_steps_per_second": 14.477,
95
  "step": 100
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
96
  }
97
  ],
98
  "logging_steps": 10,
@@ -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": 4210200831590400.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
+ "best_metric": 1.3910435438156128,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.030711351683365966,
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": 28.955,
94
  "eval_steps_per_second": 14.477,
95
  "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.01689124342585128,
99
+ "grad_norm": 2.0391786098480225,
100
+ "learning_rate": 9.755282581475769e-05,
101
+ "loss": 1.4156,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.01842681101001958,
106
+ "grad_norm": 2.2521729469299316,
107
+ "learning_rate": 9.045084971874738e-05,
108
+ "loss": 1.4366,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.019962378594187875,
113
+ "grad_norm": 1.8232300281524658,
114
+ "learning_rate": 7.938926261462366e-05,
115
+ "loss": 1.4997,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.021497946178356174,
120
+ "grad_norm": 1.88625967502594,
121
+ "learning_rate": 6.545084971874738e-05,
122
+ "loss": 1.4474,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.023033513762524473,
127
+ "grad_norm": 1.6772247552871704,
128
+ "learning_rate": 5e-05,
129
+ "loss": 1.3546,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.02456908134669277,
134
+ "grad_norm": 1.6294618844985962,
135
+ "learning_rate": 3.4549150281252636e-05,
136
+ "loss": 1.297,
137
+ "step": 160
138
+ },
139
+ {
140
+ "epoch": 0.02610464893086107,
141
+ "grad_norm": 2.385097026824951,
142
+ "learning_rate": 2.061073738537635e-05,
143
+ "loss": 1.4471,
144
+ "step": 170
145
+ },
146
+ {
147
+ "epoch": 0.02764021651502937,
148
+ "grad_norm": 1.7222036123275757,
149
+ "learning_rate": 9.549150281252633e-06,
150
+ "loss": 1.4381,
151
+ "step": 180
152
+ },
153
+ {
154
+ "epoch": 0.029175784099197667,
155
+ "grad_norm": 1.7840774059295654,
156
+ "learning_rate": 2.4471741852423237e-06,
157
+ "loss": 1.4755,
158
+ "step": 190
159
+ },
160
+ {
161
+ "epoch": 0.030711351683365966,
162
+ "grad_norm": 1.845508098602295,
163
+ "learning_rate": 0.0,
164
+ "loss": 1.357,
165
+ "step": 200
166
+ },
167
+ {
168
+ "epoch": 0.030711351683365966,
169
+ "eval_loss": 1.3910435438156128,
170
+ "eval_runtime": 94.6349,
171
+ "eval_samples_per_second": 28.975,
172
+ "eval_steps_per_second": 14.487,
173
+ "step": 200
174
  }
175
  ],
176
  "logging_steps": 10,
 
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": 8420401663180800.0,
203
  "train_batch_size": 2,
204
  "trial_name": null,
205
  "trial_params": null