Training in progress, step 17000, 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 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5adfa46e3ddfd088ddcff8e2b4d5d2e22b5262134efabf88908d983013cadef2
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:55c58829c4bcf80e72ccd1f5def21e54e28ca040dc00cc84a75d3765eef60d58
|
3 |
size 484163514
|
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:a515644a1536d58bc151d4772fbcb30c6719059de1dca0ac69481684fdd622ee
|
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 sha256:8030e4de81bed9438f1213c20e98e00469ffeac6ae1e0ae6de34e5da948dd505
|
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": 2.
|
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,
|
@@ -225,13 +225,19 @@
|
|
225 |
"learning_rate": 0.0004937384898710866,
|
226 |
"loss": 0.5295,
|
227 |
"step": 16500
|
|
|
|
|
|
|
|
|
|
|
|
|
228 |
}
|
229 |
],
|
230 |
"logging_steps": 500,
|
231 |
"max_steps": 32580,
|
232 |
"num_train_epochs": 5,
|
233 |
"save_steps": 500,
|
234 |
-
"total_flos":
|
235 |
"trial_name": null,
|
236 |
"trial_params": null
|
237 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 2.608962553713935,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 17000,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
225 |
"learning_rate": 0.0004937384898710866,
|
226 |
"loss": 0.5295,
|
227 |
"step": 16500
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 2.61,
|
231 |
+
"learning_rate": 0.00047839165131982814,
|
232 |
+
"loss": 0.524,
|
233 |
+
"step": 17000
|
234 |
}
|
235 |
],
|
236 |
"logging_steps": 500,
|
237 |
"max_steps": 32580,
|
238 |
"num_train_epochs": 5,
|
239 |
"save_steps": 500,
|
240 |
+
"total_flos": 9011746539307008.0,
|
241 |
"trial_name": null,
|
242 |
"trial_params": null
|
243 |
}
|