Training in progress, step 72000
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 839365
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:542f3ed811988104b9429f251b89c10386d14e5a21231f1b6a659a3705c2a602
|
3 |
size 839365
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242071641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:576ca4da26687f0f7b18afd0f65aa79de559df582f822fcd393e195465d6a856
|
3 |
size 242071641
|
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 sha256:2ecf8b5b81f52469ddb85f3a8b1af7713b402e9fcd9d628e93037739e7ea8fc9
|
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 sha256:6ce6383a0bf3ff0a48afe68b277cac51d233febacebd1aeb50695c2c049c5304
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.7131295204162598,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-52000",
|
4 |
-
"epoch": 8.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -776,11 +776,33 @@
|
|
776 |
"eval_samples_per_second": 68.844,
|
777 |
"eval_steps_per_second": 1.077,
|
778 |
"step": 70000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
779 |
}
|
780 |
],
|
781 |
"max_steps": 85840,
|
782 |
"num_train_epochs": 10,
|
783 |
-
"total_flos":
|
784 |
"trial_name": null,
|
785 |
"trial_params": null
|
786 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7131295204162598,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-52000",
|
4 |
+
"epoch": 8.387698042870456,
|
5 |
+
"global_step": 72000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
776 |
"eval_samples_per_second": 68.844,
|
777 |
"eval_steps_per_second": 1.077,
|
778 |
"step": 70000
|
779 |
+
},
|
780 |
+
{
|
781 |
+
"epoch": 8.39,
|
782 |
+
"learning_rate": 0.00016971599548732037,
|
783 |
+
"loss": 1.0488,
|
784 |
+
"step": 72000
|
785 |
+
},
|
786 |
+
{
|
787 |
+
"epoch": 8.39,
|
788 |
+
"eval_accuracy": null,
|
789 |
+
"eval_bertscore_f1": 0.9345181620816249,
|
790 |
+
"eval_bleu": 0.4124889872953633,
|
791 |
+
"eval_f1": null,
|
792 |
+
"eval_loss": 1.7536756992340088,
|
793 |
+
"eval_rouge1": 0.6217065929610754,
|
794 |
+
"eval_rouge2": 0.4146562066585521,
|
795 |
+
"eval_rougeL": 0.5638042099155474,
|
796 |
+
"eval_rougeLsum": 0.5658427165750861,
|
797 |
+
"eval_runtime": 141.3859,
|
798 |
+
"eval_samples_per_second": 69.611,
|
799 |
+
"eval_steps_per_second": 1.089,
|
800 |
+
"step": 72000
|
801 |
}
|
802 |
],
|
803 |
"max_steps": 85840,
|
804 |
"num_train_epochs": 10,
|
805 |
+
"total_flos": 7.189532808609792e+16,
|
806 |
"trial_name": null,
|
807 |
"trial_params": null
|
808 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242071641
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:576ca4da26687f0f7b18afd0f65aa79de559df582f822fcd393e195465d6a856
|
3 |
size 242071641
|