Francesco0101
commited on
Commit
•
f316e2c
1
Parent(s):
3054246
Training in progress, step 11000, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 267835644
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b84a63e05cf7e61ff14b5ea5d202d907a95ae5d688f07eba6dbb3a5cf9831ea3
|
3 |
size 267835644
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 535733434
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b6a9740009265e4015f0bd0b724d04ed7cdb3386fadf9ea4c0cb954fd748f74
|
3 |
size 535733434
|
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 sha256:7ec7ae411f17ee5368e427345b1ed8acea7cd6ccd42454b74ac83350e2af9f53
|
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:d02561f05f92ec38469dcdbeea658727d1c42867b8c61448e75168ac1ada02d6
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7302118007837902,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-9000",
|
4 |
-
"epoch": 1.
|
5 |
"eval_steps": 1000,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -197,6 +197,25 @@
|
|
197 |
"eval_samples_per_second": 89.363,
|
198 |
"eval_steps_per_second": 11.17,
|
199 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
200 |
}
|
201 |
],
|
202 |
"logging_steps": 1000,
|
@@ -216,7 +235,7 @@
|
|
216 |
"attributes": {}
|
217 |
}
|
218 |
},
|
219 |
-
"total_flos": 1.
|
220 |
"train_batch_size": 8,
|
221 |
"trial_name": null,
|
222 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7302118007837902,
|
3 |
"best_model_checkpoint": "training_dir/checkpoint-9000",
|
4 |
+
"epoch": 1.5856998702609197,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 11000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
197 |
"eval_samples_per_second": 89.363,
|
198 |
"eval_steps_per_second": 11.17,
|
199 |
"step": 10000
|
200 |
+
},
|
201 |
+
{
|
202 |
+
"epoch": 1.5856998702609197,
|
203 |
+
"grad_norm": 0.9291965961456299,
|
204 |
+
"learning_rate": 8.475388412951939e-06,
|
205 |
+
"loss": 0.382,
|
206 |
+
"step": 11000
|
207 |
+
},
|
208 |
+
{
|
209 |
+
"epoch": 1.5856998702609197,
|
210 |
+
"eval_accuracy": 0.7233391608391608,
|
211 |
+
"eval_f1": 0.7111261766120992,
|
212 |
+
"eval_loss": 0.9670953154563904,
|
213 |
+
"eval_precision": 0.7298151319032911,
|
214 |
+
"eval_recall": 0.7233391608391608,
|
215 |
+
"eval_runtime": 25.491,
|
216 |
+
"eval_samples_per_second": 89.757,
|
217 |
+
"eval_steps_per_second": 11.22,
|
218 |
+
"step": 11000
|
219 |
}
|
220 |
],
|
221 |
"logging_steps": 1000,
|
|
|
235 |
"attributes": {}
|
236 |
}
|
237 |
},
|
238 |
+
"total_flos": 1.101747897676584e+16,
|
239 |
"train_batch_size": 8,
|
240 |
"trial_name": null,
|
241 |
"trial_params": null
|