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 73911112
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7d8f14473fe7e2d52d16fffbf31168d48f0574a07b89d539e2c32de04838913e
|
3 |
size 73911112
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37965300
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c9fda77b31f29a2dd5f585bd1343a183ea61a997d8732924e05e26f0190f1dee
|
3 |
size 37965300
|
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 sha256:3dd691ba07c28a646751ed666917ad41c5e4defab12b08b7a97b013371c94da8
|
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":
|
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": 36.344,
|
161 |
"eval_steps_per_second": 4.759,
|
162 |
"step": 45
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
}
|
164 |
],
|
165 |
"logging_steps": 3,
|
@@ -179,7 +208,7 @@
|
|
179 |
"attributes": {}
|
180 |
}
|
181 |
},
|
182 |
-
"total_flos": 1.
|
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": 1.0909090909090908,
|
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": 36.344,
|
161 |
"eval_steps_per_second": 4.759,
|
162 |
"step": 45
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 0.9696969696969697,
|
166 |
+
"grad_norm": 1.132219672203064,
|
167 |
+
"learning_rate": 3.104804738999169e-05,
|
168 |
+
"loss": 2.4134,
|
169 |
+
"step": 48
|
170 |
+
},
|
171 |
+
{
|
172 |
+
"epoch": 1.0303030303030303,
|
173 |
+
"grad_norm": 1.2697609663009644,
|
174 |
+
"learning_rate": 2.8479327524001636e-05,
|
175 |
+
"loss": 2.9878,
|
176 |
+
"step": 51
|
177 |
+
},
|
178 |
+
{
|
179 |
+
"epoch": 1.0909090909090908,
|
180 |
+
"grad_norm": 0.9924309849739075,
|
181 |
+
"learning_rate": 2.587248741756253e-05,
|
182 |
+
"loss": 2.2329,
|
183 |
+
"step": 54
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 1.0909090909090908,
|
187 |
+
"eval_loss": 2.328364372253418,
|
188 |
+
"eval_runtime": 2.3181,
|
189 |
+
"eval_samples_per_second": 36.237,
|
190 |
+
"eval_steps_per_second": 4.745,
|
191 |
+
"step": 54
|
192 |
}
|
193 |
],
|
194 |
"logging_steps": 3,
|
|
|
208 |
"attributes": {}
|
209 |
}
|
210 |
},
|
211 |
+
"total_flos": 1.4099539257458688e+16,
|
212 |
"train_batch_size": 8,
|
213 |
"trial_name": null,
|
214 |
"trial_params": null
|