Training in progress, step 27, 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 645975704
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:558766315c932764fd3f29a9e6de086a56f6052c99a9afadf45c33ed746c659a
|
3 |
size 645975704
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 328468404
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9452c05fabdc701d9e29627f014fd4c92b615244a7f799bb4ce7936a4f56b94c
|
3 |
size 328468404
|
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 sha256:3d06b862671e761d6edc600580aa7af29e9ee4b8075baec4ac513026a16f5aca
|
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 sha256:3f4cb172acc239bdfcb1321474587dd4513dd004b0281034cdef9d5bfde0d5ff
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 1.940207600593567,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
-
"epoch": 0
|
5 |
"eval_steps": 25,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -198,6 +198,20 @@
|
|
198 |
"eval_samples_per_second": 15.602,
|
199 |
"eval_steps_per_second": 2.035,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +235,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos": 2.
|
230 |
"train_batch_size": 8,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 1.940207600593567,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 1.0,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 27,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 15.602,
|
199 |
"eval_steps_per_second": 2.035,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 0.9629629629629629,
|
204 |
+
"grad_norm": 1.2259421348571777,
|
205 |
+
"learning_rate": 5.089279059533658e-07,
|
206 |
+
"loss": 1.9491,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 1.0,
|
211 |
+
"grad_norm": 1.2239744663238525,
|
212 |
+
"learning_rate": 0.0,
|
213 |
+
"loss": 1.9371,
|
214 |
+
"step": 27
|
215 |
}
|
216 |
],
|
217 |
"logging_steps": 1,
|
|
|
235 |
"should_evaluate": false,
|
236 |
"should_log": false,
|
237 |
"should_save": true,
|
238 |
+
"should_training_stop": true
|
239 |
},
|
240 |
"attributes": {}
|
241 |
}
|
242 |
},
|
243 |
+
"total_flos": 2.468309889712128e+16,
|
244 |
"train_batch_size": 8,
|
245 |
"trial_name": null,
|
246 |
"trial_params": null
|