Commit
•
c42d3a8
1
Parent(s):
6f336e8
Training in progress, step 8000, 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 sha256:78c9e820e6f2b34afef294ea03b9806ca31e36f8873e0df7c298ce3b6bdee8fd
|
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 sha256:611e8a5f53f98861b9122353f39089365a355506c0f560578945807b4e4b391f
|
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 sha256:40c6f4b43aefb772d54e56c245109d4d777d2195b3fa9ce39aa759919ebd5a69
|
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 sha256:82489f346a442f6da6a913d4059284e68bce2bb5b3b04d85ed6e18e1fb87da9f
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "training_dir/checkpoint-
|
4 |
-
"epoch": 0.
|
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,
|
@@ -140,6 +140,25 @@
|
|
140 |
"eval_samples_per_second": 87.878,
|
141 |
"eval_steps_per_second": 10.985,
|
142 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
143 |
}
|
144 |
],
|
145 |
"logging_steps": 1000,
|
@@ -159,7 +178,7 @@
|
|
159 |
"attributes": {}
|
160 |
}
|
161 |
},
|
162 |
-
"total_flos":
|
163 |
"train_batch_size": 8,
|
164 |
"trial_name": null,
|
165 |
"trial_params": null
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.7183207652218417,
|
3 |
+
"best_model_checkpoint": "training_dir/checkpoint-8000",
|
4 |
+
"epoch": 0.8477270318957296,
|
5 |
"eval_steps": 1000,
|
6 |
+
"global_step": 8000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
140 |
"eval_samples_per_second": 87.878,
|
141 |
"eval_steps_per_second": 10.985,
|
142 |
"step": 7000
|
143 |
+
},
|
144 |
+
{
|
145 |
+
"epoch": 0.8477270318957296,
|
146 |
+
"grad_norm": 7.15505838394165,
|
147 |
+
"learning_rate": 9.201022690955577e-06,
|
148 |
+
"loss": 0.4598,
|
149 |
+
"step": 8000
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.8477270318957296,
|
153 |
+
"eval_accuracy": 0.7263986013986014,
|
154 |
+
"eval_f1": 0.7183207652218417,
|
155 |
+
"eval_loss": 0.782526969909668,
|
156 |
+
"eval_precision": 0.7270872567100993,
|
157 |
+
"eval_recall": 0.7263986013986014,
|
158 |
+
"eval_runtime": 26.0044,
|
159 |
+
"eval_samples_per_second": 87.985,
|
160 |
+
"eval_steps_per_second": 10.998,
|
161 |
+
"step": 8000
|
162 |
}
|
163 |
],
|
164 |
"logging_steps": 1000,
|
|
|
178 |
"attributes": {}
|
179 |
}
|
180 |
},
|
181 |
+
"total_flos": 7765358762666736.0,
|
182 |
"train_batch_size": 8,
|
183 |
"trial_name": null,
|
184 |
"trial_params": null
|