Training in progress, step 72, 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 319876032
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cfd8957fc076960c30b730496f2c8be0968e87df245ba83540c8fe45c8ce1b5c
|
3 |
size 319876032
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 640009682
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23991589a9558d35301f754221fb75eb5d034a6e6a21b3ffbef0e6f1636637df
|
3 |
size 640009682
|
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 sha256:54695bae591aceb2574c0570650d7a15033601e879a5235bc5ef9cc452369efd
|
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 sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
|
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": 1.
|
5 |
"eval_steps": 9,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -218,6 +218,35 @@
|
|
218 |
"eval_samples_per_second": 2.763,
|
219 |
"eval_steps_per_second": 1.382,
|
220 |
"step": 63
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 3,
|
@@ -237,7 +266,7 @@
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
-
"total_flos": 3.
|
241 |
"train_batch_size": 2,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.2108843537414966,
|
5 |
"eval_steps": 9,
|
6 |
+
"global_step": 72,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
218 |
"eval_samples_per_second": 2.763,
|
219 |
"eval_steps_per_second": 1.382,
|
220 |
"step": 63
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 1.1104133961276819,
|
224 |
+
"grad_norm": 5.304825782775879,
|
225 |
+
"learning_rate": 7.66554636144095e-05,
|
226 |
+
"loss": 1.6933,
|
227 |
+
"step": 66
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 1.1606488749345891,
|
231 |
+
"grad_norm": 5.396218776702881,
|
232 |
+
"learning_rate": 6.538829429225069e-05,
|
233 |
+
"loss": 1.6576,
|
234 |
+
"step": 69
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 1.2108843537414966,
|
238 |
+
"grad_norm": 7.664739608764648,
|
239 |
+
"learning_rate": 5.4600950026045326e-05,
|
240 |
+
"loss": 1.566,
|
241 |
+
"step": 72
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 1.2108843537414966,
|
245 |
+
"eval_loss": 0.05733713135123253,
|
246 |
+
"eval_runtime": 73.1797,
|
247 |
+
"eval_samples_per_second": 2.76,
|
248 |
+
"eval_steps_per_second": 1.38,
|
249 |
+
"step": 72
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 3,
|
|
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
+
"total_flos": 3.7865554385987174e+17,
|
270 |
"train_batch_size": 2,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|