Training in progress, step 54, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3e7d0fac5a39e398089bf5f53a56312d336d01b3f5d7684197e7eb83427c578
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e712febab3a44a4e3b2977edacee6ab2f1c05118dc1ab3bcfbfb70af6699d35a
|
3 |
size 640009682
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cea0571e03c42072c2619a6841806791c3454e943bf747e8a4e1158abf717848
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6f68b4a4ba4603d307a8be653dd70e693a9f3506ea1af5f24d2d241dc54cfcb1
|
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.
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -160,6 +160,35 @@
|
|
160 |
"eval_samples_per_second": 5.921,
|
161 |
"eval_steps_per_second": 2.961,
|
162 |
"step": 45
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
@@ -179,7 +208,7 @@
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
-
"total_flos": 2.
|
183 |
"train_batch_size": 2,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.63646408839779,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 54,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
160 |
"eval_samples_per_second": 5.921,
|
161 |
"eval_steps_per_second": 2.961,
|
162 |
"step": 45
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.5657458563535912,
|
166 |
+
"grad_norm": 27.746295928955078,
|
167 |
+
"learning_rate": 0.00010904928748046599,
|
168 |
+
"loss": 57.6997,
|
169 |
+
"step": 48
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.6011049723756906,
|
173 |
+
"grad_norm": 26.590911865234375,
|
174 |
+
"learning_rate": 0.00010095877928081196,
|
175 |
+
"loss": 57.611,
|
176 |
+
"step": 51
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.63646408839779,
|
180 |
+
"grad_norm": 24.721492767333984,
|
181 |
+
"learning_rate": 9.25084022891929e-05,
|
182 |
+
"loss": 54.3467,
|
183 |
+
"step": 54
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.63646408839779,
|
187 |
+
"eval_loss": 1.7132052183151245,
|
188 |
+
"eval_runtime": 48.2964,
|
189 |
+
"eval_samples_per_second": 5.922,
|
190 |
+
"eval_steps_per_second": 2.961,
|
191 |
+
"step": 54
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
+
"total_flos": 2.839944410337116e+17,
|
212 |
"train_batch_size": 2,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|