Training in progress, step 90, 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 671149168
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:602d49ff4825aa25f81d8bdad5fd8ee21294b826f26ed0b622fdb59a57eb2981
|
3 |
size 671149168
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1342555602
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c33a1e7c88c0c38111b6dfb1d5bbbd559073488f179b51fb5bbd604013eb384
|
3 |
size 1342555602
|
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:d0f4c520bdbbb3a94697b2862fd0c9032953c1d5738ee32bb212e1a1a1576476
|
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 sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
|
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,
|
@@ -199,6 +199,28 @@
|
|
199 |
"eval_samples_per_second": 19.375,
|
200 |
"eval_steps_per_second": 2.422,
|
201 |
"step": 81
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
202 |
}
|
203 |
],
|
204 |
"logging_steps": 5,
|
@@ -218,7 +240,7 @@
|
|
218 |
"attributes": {}
|
219 |
}
|
220 |
},
|
221 |
-
"total_flos": 1.
|
222 |
"train_batch_size": 8,
|
223 |
"trial_name": null,
|
224 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.07068525427056745,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 90,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
199 |
"eval_samples_per_second": 19.375,
|
200 |
"eval_steps_per_second": 2.422,
|
201 |
"step": 81
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 0.06675829569998036,
|
205 |
+
"grad_norm": 5.313036918640137,
|
206 |
+
"learning_rate": 1.2639779077309098e-05,
|
207 |
+
"loss": 3.3791,
|
208 |
+
"step": 85
|
209 |
+
},
|
210 |
+
{
|
211 |
+
"epoch": 0.07068525427056745,
|
212 |
+
"grad_norm": 4.830722332000732,
|
213 |
+
"learning_rate": 5.709035061653494e-06,
|
214 |
+
"loss": 3.0172,
|
215 |
+
"step": 90
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.07068525427056745,
|
219 |
+
"eval_loss": 3.3156657218933105,
|
220 |
+
"eval_runtime": 233.6444,
|
221 |
+
"eval_samples_per_second": 19.38,
|
222 |
+
"eval_steps_per_second": 2.422,
|
223 |
+
"step": 90
|
224 |
}
|
225 |
],
|
226 |
"logging_steps": 5,
|
|
|
240 |
"attributes": {}
|
241 |
}
|
242 |
},
|
243 |
+
"total_flos": 1.3576622208712704e+17,
|
244 |
"train_batch_size": 8,
|
245 |
"trial_name": null,
|
246 |
"trial_params": null
|