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 313820248
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a69d4b13e965a3c836107b9098733b9a91c9a3f0b464cd9a9cc7321aa806efdb
|
3 |
size 313820248
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 159641092
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bfadffdc10f43bbdd3c0cebd302f1e75d95eaaf101eb405c45f31b7addf36c68
|
3 |
size 159641092
|
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:b858b78f36c65303cc43c5895026eba72df7985e2a9ad8127cc9604564de326b
|
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 sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
|
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": 0.
|
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": 27.586,
|
219 |
"eval_steps_per_second": 6.897,
|
220 |
"step": 63
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
221 |
}
|
222 |
],
|
223 |
"logging_steps": 3,
|
@@ -237,7 +266,7 @@
|
|
237 |
"attributes": {}
|
238 |
}
|
239 |
},
|
240 |
-
"total_flos": 1.
|
241 |
"train_batch_size": 4,
|
242 |
"trial_name": null,
|
243 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0028269383668541475,
|
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": 27.586,
|
219 |
"eval_steps_per_second": 6.897,
|
220 |
"step": 63
|
221 |
+
},
|
222 |
+
{
|
223 |
+
"epoch": 0.002591360169616302,
|
224 |
+
"grad_norm": 3.213492163922638e-05,
|
225 |
+
"learning_rate": 3.12696703292044e-05,
|
226 |
+
"loss": 0.0,
|
227 |
+
"step": 66
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.002709149268235225,
|
231 |
+
"grad_norm": 2.8474241844378412e-05,
|
232 |
+
"learning_rate": 2.6526421860705473e-05,
|
233 |
+
"loss": 0.0,
|
234 |
+
"step": 69
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 0.0028269383668541475,
|
238 |
+
"grad_norm": 3.170351919834502e-05,
|
239 |
+
"learning_rate": 2.2040354826462668e-05,
|
240 |
+
"loss": 0.0,
|
241 |
+
"step": 72
|
242 |
+
},
|
243 |
+
{
|
244 |
+
"epoch": 0.0028269383668541475,
|
245 |
+
"eval_loss": 0.0005312738940119743,
|
246 |
+
"eval_runtime": 777.5031,
|
247 |
+
"eval_samples_per_second": 27.586,
|
248 |
+
"eval_steps_per_second": 6.896,
|
249 |
+
"step": 72
|
250 |
}
|
251 |
],
|
252 |
"logging_steps": 3,
|
|
|
266 |
"attributes": {}
|
267 |
}
|
268 |
},
|
269 |
+
"total_flos": 1.4582792117551104e+16,
|
270 |
"train_batch_size": 4,
|
271 |
"trial_name": null,
|
272 |
"trial_params": null
|