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 167832240
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b5bc3665eb969d55941f958da6a3d13c244b9eb8ee809445f4a65b52931f858c
|
3 |
size 167832240
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 85723284
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c52c5a3f256efcce06dadccc2702edeef3814a5c812633b60970144030ebb435
|
3 |
size 85723284
|
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 sha256:87951bd1d28cfc789427636c05788fc21db0e7e40be21589b4278413c44c66bd
|
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:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
|
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": 12.937,
|
161 |
"eval_steps_per_second": 1.617,
|
162 |
"step": 45
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
@@ -179,7 +208,7 @@
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
-
"total_flos":
|
183 |
"train_batch_size": 8,
|
184 |
"trial_name": null,
|
185 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.004886214541012532,
|
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": 12.937,
|
161 |
"eval_steps_per_second": 1.617,
|
162 |
"step": 45
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.004343301814233362,
|
166 |
+
"grad_norm": 2.69805645942688,
|
167 |
+
"learning_rate": 3.104804738999169e-05,
|
168 |
+
"loss": 0.4621,
|
169 |
+
"step": 48
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 0.004614758177622947,
|
173 |
+
"grad_norm": 1.981372594833374,
|
174 |
+
"learning_rate": 2.8479327524001636e-05,
|
175 |
+
"loss": 0.6349,
|
176 |
+
"step": 51
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 0.004886214541012532,
|
180 |
+
"grad_norm": 2.258195161819458,
|
181 |
+
"learning_rate": 2.587248741756253e-05,
|
182 |
+
"loss": 0.5486,
|
183 |
+
"step": 54
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 0.004886214541012532,
|
187 |
+
"eval_loss": 0.5081658363342285,
|
188 |
+
"eval_runtime": 1439.3002,
|
189 |
+
"eval_samples_per_second": 12.932,
|
190 |
+
"eval_steps_per_second": 1.617,
|
191 |
+
"step": 54
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
+
"total_flos": 7.798615858741248e+16,
|
212 |
"train_batch_size": 8,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|