Hugging Face's logo

fats-fme
/
a8285405-e96a-458b-8df5-55b8a6b1afe7

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
fats-fme commited on
Commit
8427a73
·
verified ·
1 Parent(s): 10a0af8

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 sha256:2018e4d3329707f505577873eb3d9aed0cae3d6fb2ef2e92ad69434f3069775c
3
  size 140815952
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e88a8f01f791aec7b720d16895e469efa22d6675f035597c74331bd48cd8d47
3
  size 140815952
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:9b78fa812c6984f3c612348c1478305fed3a76dde0b5116522dbd8599b62ee43
3
  size 71878612
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1903dc654aa8b89bf98c0511d722b5fccdca6f504aa8cce06c73e592baeee830
3
  size 71878612
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a5494b96b16fd60da243d7d87327fc5e454371d42ae0086d520a0eeb639746d7
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:235f7fe84fa30f854a3643f6ed1656321aa4b66f437bb424a1989d90e0d5ae17
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7708307d1b959a393541df6c657dca87476d08205aaca5feb82f751cfc227436
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93a4031351d40494c6fa2a2ab0690336e71553ec331e91c1b2ab832fe81468d8
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
- "best_metric": 0.17322567105293274,
3
- "best_model_checkpoint": "miner_id_24/checkpoint-100",
4
- "epoch": 0.06026819346090101,
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": 35.892,
94
  "eval_steps_per_second": 17.972,
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": 3873901818937344.0,
125
  "train_batch_size": 2,
126
  "trial_name": null,
127
  "trial_params": null
 
1
  {
2
+ "best_metric": 0.1569606214761734,
3
+ "best_model_checkpoint": "miner_id_24/checkpoint-200",
4
+ "epoch": 0.12053638692180202,
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": 35.892,
94
  "eval_steps_per_second": 17.972,
95
  "step": 100
96
+ },
97
+ {
98
+ "epoch": 0.06629501280699111,
99
+ "grad_norm": 2.4882545471191406,
100
+ "learning_rate": 2.7500000000000004e-05,
101
+ "loss": 0.5264,
102
+ "step": 110
103
+ },
104
+ {
105
+ "epoch": 0.07232183215308122,
106
+ "grad_norm": 0.6996169686317444,
107
+ "learning_rate": 3e-05,
108
+ "loss": 0.2292,
109
+ "step": 120
110
+ },
111
+ {
112
+ "epoch": 0.0783486514991713,
113
+ "grad_norm": 0.5811498165130615,
114
+ "learning_rate": 3.2500000000000004e-05,
115
+ "loss": 0.3182,
116
+ "step": 130
117
+ },
118
+ {
119
+ "epoch": 0.08437547084526141,
120
+ "grad_norm": 0.24197261035442352,
121
+ "learning_rate": 3.5e-05,
122
+ "loss": 0.2114,
123
+ "step": 140
124
+ },
125
+ {
126
+ "epoch": 0.09040229019135151,
127
+ "grad_norm": 0.4716508090496063,
128
+ "learning_rate": 3.7500000000000003e-05,
129
+ "loss": 0.1169,
130
+ "step": 150
131
+ },
132
+ {
133
+ "epoch": 0.09642910953744162,
134
+ "grad_norm": 0.48725882172584534,
135
+ "learning_rate": 4e-05,
136
+ "loss": 0.1013,
137
+ "step": 160
138
+ },
139
+ {
140
+ "epoch": 0.10245592888353172,
141
+ "grad_norm": 0.35950130224227905,
142
+ "learning_rate": 4.25e-05,
143
+ "loss": 0.2313,
144
+ "step": 170
145
+ },
146
+ {
147
+ "epoch": 0.10848274822962181,
148
+ "grad_norm": 0.43237921595573425,
149
+ "learning_rate": 4.5e-05,
150
+ "loss": 0.2109,
151
+ "step": 180
152
+ },
153
+ {
154
+ "epoch": 0.11450956757571192,
155
+ "grad_norm": 1.0144596099853516,
156
+ "learning_rate": 4.75e-05,
157
+ "loss": 0.3166,
158
+ "step": 190
159
+ },
160
+ {
161
+ "epoch": 0.12053638692180202,
162
+ "grad_norm": 0.6670956015586853,
163
+ "learning_rate": 5e-05,
164
+ "loss": 0.328,
165
+ "step": 200
166
+ },
167
+ {
168
+ "epoch": 0.12053638692180202,
169
+ "eval_loss": 0.1569606214761734,
170
+ "eval_runtime": 19.5861,
171
+ "eval_samples_per_second": 35.688,
172
+ "eval_steps_per_second": 17.87,
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": 7747803637874688.0,
203
  "train_batch_size": 2,
204
  "trial_name": null,
205
  "trial_params": null