Training in progress, step 12000, 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 891558696
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0426db5bf32594814a8c37e618d6398246b9271f06265c61e6b718a3b1d4b11f
|
3 |
size 891558696
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1783272762
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:109669df17b5f6b02118f596a85fbd94dfbe94bfa26ddbed9e0a32a469bb37b2
|
3 |
size 1783272762
|
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:d0ddcf15b11b5d2f3a427728cce5454c9ef039ba8bfd4e438abdef47917e7a39
|
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:ff57c48e4ef354be063370e4a408d39b39e1d0cde79b3adacb1e6416a8aedc46
|
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": 4.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -200,6 +200,13 @@
|
|
200 |
"learning_rate": 8.89443059019119e-07,
|
201 |
"loss": 0.3117,
|
202 |
"step": 11500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
203 |
}
|
204 |
],
|
205 |
"logging_steps": 500,
|
@@ -219,7 +226,7 @@
|
|
219 |
"attributes": {}
|
220 |
}
|
221 |
},
|
222 |
-
"total_flos": 2.
|
223 |
"train_batch_size": 4,
|
224 |
"trial_name": null,
|
225 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 4.987531172069826,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 12000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
200 |
"learning_rate": 8.89443059019119e-07,
|
201 |
"loss": 0.3117,
|
202 |
"step": 11500
|
203 |
+
},
|
204 |
+
{
|
205 |
+
"epoch": 4.987531172069826,
|
206 |
+
"grad_norm": 0.9830431342124939,
|
207 |
+
"learning_rate": 5.8187863674147975e-08,
|
208 |
+
"loss": 0.3083,
|
209 |
+
"step": 12000
|
210 |
}
|
211 |
],
|
212 |
"logging_steps": 500,
|
|
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
+
"total_flos": 2.922754291531776e+16,
|
230 |
"train_batch_size": 4,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|