Training in progress, step 29, checkpoint
Browse files- last-checkpoint/adapter_model.safetensors +1 -1
- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/rng_state_0.pth +1 -1
- last-checkpoint/rng_state_1.pth +1 -1
- last-checkpoint/rng_state_2.pth +1 -1
- last-checkpoint/rng_state_3.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +32 -4
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 239536272
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e4fdb7067849a4c464668852c635bc461c590a24325a406d7d9fb1945ce921e
|
3 |
size 239536272
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 479362682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a4d24bf17d5ab97591019b37cb44f79afe3e47dfd02162862a8bda0860138074
|
3 |
size 479362682
|
last-checkpoint/rng_state_0.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14960
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:614714b3e86980d626ed5bb91ec370b5c4c594311cc1a24f20a23f4bd23df084
|
3 |
size 14960
|
last-checkpoint/rng_state_1.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01468a262529a447c856ce160b15a9647a19c8d96a43698fdfc8e1ddc8447661
|
3 |
size 15024
|
last-checkpoint/rng_state_2.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d416fd5646fea1d436dfdb19b6e134890b1c9b3625ef41b6e8cc540bff208d80
|
3 |
size 15024
|
last-checkpoint/rng_state_3.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 15024
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:116635eab115b8ddfa54680c0f6d827b6ed844f1290ac05b52a40223acf16528
|
3 |
size 15024
|
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 sha256:77b1cd5ec232ad7fc4a8bf29290c170002b5e29b256da7fe912039052d43ab0b
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": 0.7201225757598877,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
-
"epoch":
|
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 +198,34 @@
|
|
198 |
"eval_samples_per_second": 22.319,
|
199 |
"eval_steps_per_second": 3.09,
|
200 |
"step": 25
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
201 |
}
|
202 |
],
|
203 |
"logging_steps": 1,
|
@@ -221,12 +249,12 @@
|
|
221 |
"should_evaluate": false,
|
222 |
"should_log": false,
|
223 |
"should_save": true,
|
224 |
-
"should_training_stop":
|
225 |
},
|
226 |
"attributes": {}
|
227 |
}
|
228 |
},
|
229 |
-
"total_flos": 1.
|
230 |
"train_batch_size": 2,
|
231 |
"trial_name": null,
|
232 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": 0.7201225757598877,
|
3 |
"best_model_checkpoint": "miner_id_24/checkpoint-25",
|
4 |
+
"epoch": 3.1870967741935483,
|
5 |
"eval_steps": 25,
|
6 |
+
"global_step": 29,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
198 |
"eval_samples_per_second": 22.319,
|
199 |
"eval_steps_per_second": 3.09,
|
200 |
"step": 25
|
201 |
+
},
|
202 |
+
{
|
203 |
+
"epoch": 2.8129032258064517,
|
204 |
+
"grad_norm": 1.8182753324508667,
|
205 |
+
"learning_rate": 3.0153689607045845e-06,
|
206 |
+
"loss": 0.7967,
|
207 |
+
"step": 26
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 2.9161290322580644,
|
211 |
+
"grad_norm": 1.4322144985198975,
|
212 |
+
"learning_rate": 1.3477564710088098e-06,
|
213 |
+
"loss": 0.7748,
|
214 |
+
"step": 27
|
215 |
+
},
|
216 |
+
{
|
217 |
+
"epoch": 3.0838709677419356,
|
218 |
+
"grad_norm": 3.2206716537475586,
|
219 |
+
"learning_rate": 3.380821129028489e-07,
|
220 |
+
"loss": 1.3338,
|
221 |
+
"step": 28
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 3.1870967741935483,
|
225 |
+
"grad_norm": 2.47102427482605,
|
226 |
+
"learning_rate": 0.0,
|
227 |
+
"loss": 0.8182,
|
228 |
+
"step": 29
|
229 |
}
|
230 |
],
|
231 |
"logging_steps": 1,
|
|
|
249 |
"should_evaluate": false,
|
250 |
"should_log": false,
|
251 |
"should_save": true,
|
252 |
+
"should_training_stop": true
|
253 |
},
|
254 |
"attributes": {}
|
255 |
}
|
256 |
},
|
257 |
+
"total_flos": 1.2929663392913818e+17,
|
258 |
"train_batch_size": 2,
|
259 |
"trial_name": null,
|
260 |
"trial_params": null
|