Hugging Face's logo

adammandic87
/
6af1ed4c-21cc-45df-8e37-236b857c9285

PEFT
Safetensors
qwen2
axolotl
Generated from Trainer
Model card Files
xet
 Community
adammandic87 commited on
Commit
9cf0b24
·
verified ·
1 Parent(s): 4ac5d1b

Training in progress, step 26, 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 +102 -3
last-checkpoint/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b3dad1e57cbd56dd157e632c924b65380717259f1622e2a51cee3e398d5a02f7
3
  size 14696
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2b58d3eb1217eed19f2e4e6102060b04b13f02dac1dfd9c93bdab8fac3eef1a5
3
  size 14696
last-checkpoint/optimizer.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3bc8385834e0aadf16373d8ac2aa3006a912d55656cbf0e15f3a67702e9ff2e1
3
  size 39398
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4322d34611a6658e45fb8dde4b68db66aacf8f907484f721dd2f6875a4299c54
3
  size 39398
last-checkpoint/rng_state.pth CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02c5fd8138c740194f70b268d048773555e70d025e165ecc026d15ff4300315b
3
  size 14244
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4ce9ec22e0051f976ac081d26951edb3de92acba5c29f4c684fe32b805e5bc15
3
  size 14244
last-checkpoint/scheduler.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ea3a68034a6fca5f7c1565a9344e41aadbdff3752a8799ae94336c8c84c6d63d
3
  size 1064
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa0fde01e60897f55f4ebaca5a490a1a483a2c53b2ae8e7543860a62c5b3298c
3
  size 1064
last-checkpoint/trainer_state.json CHANGED
@@ -1,9 +1,9 @@
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
- "epoch": 0.0009021199819576004,
5
  "eval_steps": 13,
6
- "global_step": 13,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
@@ -114,6 +114,105 @@
114
  "eval_samples_per_second": 181.847,
115
  "eval_steps_per_second": 90.923,
116
  "step": 13
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
117
  }
118
  ],
119
  "logging_steps": 1,
@@ -133,7 +232,7 @@
133
  "attributes": {}
134
  }
135
  },
136
- "total_flos": 2894954496.0,
137
  "train_batch_size": 2,
138
  "trial_name": null,
139
  "trial_params": null
 
1
  {
2
  "best_metric": null,
3
  "best_model_checkpoint": null,
4
+ "epoch": 0.0018042399639152007,
5
  "eval_steps": 13,
6
+ "global_step": 26,
7
  "is_hyper_param_search": false,
8
  "is_local_process_zero": true,
9
  "is_world_process_zero": true,
 
114
  "eval_samples_per_second": 181.847,
115
  "eval_steps_per_second": 90.923,
116
  "step": 13
117
+ },
118
+ {
119
+ "epoch": 0.0009715138267235696,
120
+ "grad_norm": 0.010756623931229115,
121
+ "learning_rate": 4.877641290737884e-05,
122
+ "loss": 11.9327,
123
+ "step": 14
124
+ },
125
+ {
126
+ "epoch": 0.0010409076714895389,
127
+ "grad_norm": 0.006050897296518087,
128
+ "learning_rate": 4.8096988312782174e-05,
129
+ "loss": 11.9318,
130
+ "step": 15
131
+ },
132
+ {
133
+ "epoch": 0.0011103015162555081,
134
+ "grad_norm": 0.007868759334087372,
135
+ "learning_rate": 4.72751631047092e-05,
136
+ "loss": 11.9321,
137
+ "step": 16
138
+ },
139
+ {
140
+ "epoch": 0.0011796953610214774,
141
+ "grad_norm": 0.007864049635827541,
142
+ "learning_rate": 4.6316004108852305e-05,
143
+ "loss": 11.9311,
144
+ "step": 17
145
+ },
146
+ {
147
+ "epoch": 0.0012490892057874466,
148
+ "grad_norm": 0.008323868736624718,
149
+ "learning_rate": 4.522542485937369e-05,
150
+ "loss": 11.9347,
151
+ "step": 18
152
+ },
153
+ {
154
+ "epoch": 0.001318483050553416,
155
+ "grad_norm": 0.00886128842830658,
156
+ "learning_rate": 4.401014914000078e-05,
157
+ "loss": 11.9329,
158
+ "step": 19
159
+ },
160
+ {
161
+ "epoch": 0.0013878768953193852,
162
+ "grad_norm": 0.005215478595346212,
163
+ "learning_rate": 4.267766952966369e-05,
164
+ "loss": 11.9303,
165
+ "step": 20
166
+ },
167
+ {
168
+ "epoch": 0.0014572707400853544,
169
+ "grad_norm": 0.005890417378395796,
170
+ "learning_rate": 4.123620120825459e-05,
171
+ "loss": 11.934,
172
+ "step": 21
173
+ },
174
+ {
175
+ "epoch": 0.0015266645848513237,
176
+ "grad_norm": 0.007370072416961193,
177
+ "learning_rate": 3.969463130731183e-05,
178
+ "loss": 11.9309,
179
+ "step": 22
180
+ },
181
+ {
182
+ "epoch": 0.001596058429617293,
183
+ "grad_norm": 0.006254307925701141,
184
+ "learning_rate": 3.8062464117898724e-05,
185
+ "loss": 11.9322,
186
+ "step": 23
187
+ },
188
+ {
189
+ "epoch": 0.0016654522743832622,
190
+ "grad_norm": 0.007640794385224581,
191
+ "learning_rate": 3.634976249348867e-05,
192
+ "loss": 11.9338,
193
+ "step": 24
194
+ },
195
+ {
196
+ "epoch": 0.0017348461191492315,
197
+ "grad_norm": 0.00681285047903657,
198
+ "learning_rate": 3.456708580912725e-05,
199
+ "loss": 11.9325,
200
+ "step": 25
201
+ },
202
+ {
203
+ "epoch": 0.0018042399639152007,
204
+ "grad_norm": 0.006646146532148123,
205
+ "learning_rate": 3.272542485937369e-05,
206
+ "loss": 11.9355,
207
+ "step": 26
208
+ },
209
+ {
210
+ "epoch": 0.0018042399639152007,
211
+ "eval_loss": 11.931816101074219,
212
+ "eval_runtime": 33.7496,
213
+ "eval_samples_per_second": 179.795,
214
+ "eval_steps_per_second": 89.897,
215
+ "step": 26
216
  }
217
  ],
218
  "logging_steps": 1,
 
232
  "attributes": {}
233
  }
234
  },
235
+ "total_flos": 5848989696.0,
236
  "train_batch_size": 2,
237
  "trial_name": null,
238
  "trial_params": null