Training in progress, epoch 4
Browse files
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 997319877
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5c01506ef657a5cfe82e6d5c93387b32d58a71063bbbb9197676d07bc9df237
|
| 3 |
size 997319877
|
last-checkpoint/pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498674357
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6168d3ea6ea415ac5d4b8f9268699d58544bd98aa79aeabeb94e0511fee359c9
|
| 3 |
size 498674357
|
last-checkpoint/rng_state.pth
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 14575
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b13cc8b183bab9e3f2965176c88613417f4bdc40431893a4eaf37d5e24d0725c
|
| 3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 627
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d93a7f55b88f81f3a8daa77a3fd516f0eb2469d9d57b82f0d4c87ab8988d61ea
|
| 3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5226846644169478,
|
| 3 |
"best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-316",
|
| 4 |
-
"epoch":
|
| 5 |
-
"global_step":
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
@@ -54,11 +54,27 @@
|
|
| 54 |
"eval_samples_per_second": 352.616,
|
| 55 |
"eval_steps_per_second": 24.745,
|
| 56 |
"step": 316
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 57 |
}
|
| 58 |
],
|
| 59 |
"max_steps": 1050,
|
| 60 |
"num_train_epochs": 10,
|
| 61 |
-
"total_flos":
|
| 62 |
"trial_name": null,
|
| 63 |
"trial_params": null
|
| 64 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": 0.5226846644169478,
|
| 3 |
"best_model_checkpoint": "citation_intent_classification_roberta_dapt/checkpoint-316",
|
| 4 |
+
"epoch": 4.0,
|
| 5 |
+
"global_step": 422,
|
| 6 |
"is_hyper_param_search": false,
|
| 7 |
"is_local_process_zero": true,
|
| 8 |
"is_world_process_zero": true,
|
|
|
|
| 54 |
"eval_samples_per_second": 352.616,
|
| 55 |
"eval_steps_per_second": 24.745,
|
| 56 |
"step": 316
|
| 57 |
+
},
|
| 58 |
+
{
|
| 59 |
+
"epoch": 3.79,
|
| 60 |
+
"learning_rate": 1.3171225937183386e-05,
|
| 61 |
+
"loss": 0.5604,
|
| 62 |
+
"step": 400
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"epoch": 4.0,
|
| 66 |
+
"eval_accuracy": 0.7280701754385965,
|
| 67 |
+
"eval_f1_macro": 0.4904761087856539,
|
| 68 |
+
"eval_loss": 0.7902174592018127,
|
| 69 |
+
"eval_runtime": 0.3265,
|
| 70 |
+
"eval_samples_per_second": 349.161,
|
| 71 |
+
"eval_steps_per_second": 24.502,
|
| 72 |
+
"step": 422
|
| 73 |
}
|
| 74 |
],
|
| 75 |
"max_steps": 1050,
|
| 76 |
"num_train_epochs": 10,
|
| 77 |
+
"total_flos": 352832263206048.0,
|
| 78 |
"trial_name": null,
|
| 79 |
"trial_params": null
|
| 80 |
}
|
pytorch_model.bin
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 498674357
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6168d3ea6ea415ac5d4b8f9268699d58544bd98aa79aeabeb94e0511fee359c9
|
| 3 |
size 498674357
|
runs/Apr21_16-08-32_jupyter/events.out.tfevents.1713715716.jupyter.2714651.4
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe8c6664a48bec5c6a4d02ee0e662f952ddf62bd3b29b12a693eb39911d77fe7
|
| 3 |
+
size 6508
|