Training in progress, step 72, 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 72396376
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1e4365b0a96f195c7968ae88c43702fd4bfb2fed01bd8449e8a6095f5b7b8baf
|
3 |
size 72396376
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 37134420
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ded0f2b10056d51799dfa6d4d22e384e95bcaf2fc6e8b137eca4063a59132f14
|
3 |
size 37134420
|
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 sha256:73bc25759f78482fcfbccf20cd879d9d4d1a2cdc60e029432af1b682e3e8e7ff
|
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:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
|
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,
|
@@ -218,6 +218,35 @@
|
|
218 |
"eval_samples_per_second": 35.28,
|
219 |
"eval_steps_per_second": 4.501,
|
220 |
"step": 63
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 3,
|
@@ -237,7 +266,7 @@
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
-
"total_flos": 2.
|
241 |
"train_batch_size": 8,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.41799709724238027,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 72,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
218 |
"eval_samples_per_second": 35.28,
|
219 |
"eval_steps_per_second": 4.501,
|
220 |
"step": 63
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.38316400580551524,
|
224 |
+
"grad_norm": 0.3184368908405304,
|
225 |
+
"learning_rate": 1.56348351646022e-05,
|
226 |
+
"loss": 0.4958,
|
227 |
+
"step": 66
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.4005805515239477,
|
231 |
+
"grad_norm": 0.2603450417518616,
|
232 |
+
"learning_rate": 1.3263210930352737e-05,
|
233 |
+
"loss": 0.4831,
|
234 |
+
"step": 69
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.41799709724238027,
|
238 |
+
"grad_norm": 0.3131684362888336,
|
239 |
+
"learning_rate": 1.1020177413231334e-05,
|
240 |
+
"loss": 0.4193,
|
241 |
+
"step": 72
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.41799709724238027,
|
245 |
+
"eval_loss": 0.4739016890525818,
|
246 |
+
"eval_runtime": 8.222,
|
247 |
+
"eval_samples_per_second": 35.271,
|
248 |
+
"eval_steps_per_second": 4.5,
|
249 |
+
"step": 72
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 3,
|
|
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
+
"total_flos": 2.3056942444314624e+16,
|
270 |
"train_batch_size": 8,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|