Training in progress, step 16000
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 839109
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:56d6d24eba954687e02fb2c80851e2d5be2aec336b2ebb8f6a455e4b84b93109
|
3 |
size 839109
|
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 sha256:89cedab307f06025168521c80e60ea525573bc523455ae3e165e4034e682a576
|
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 sha256:705825e2a86c915f1014e328cd9c306c18f9c735917a383cf9e37dd633a62b92
|
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:a3c7bfd871284a6faa92f94aee9c5ea71a9bdcdd13ee2b820e7d8b41939b332d
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -160,11 +160,33 @@
|
|
160 |
"eval_samples_per_second": 76.712,
|
161 |
"eval_steps_per_second": 1.2,
|
162 |
"step": 14000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
163 |
}
|
164 |
],
|
165 |
"max_steps": 85840,
|
166 |
"num_train_epochs": 10,
|
167 |
-
"total_flos": 1.
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|
170 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.7547861337661743,
|
3 |
+
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-16000",
|
4 |
+
"epoch": 1.8639328984156571,
|
5 |
+
"global_step": 16000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
160 |
"eval_samples_per_second": 76.712,
|
161 |
"eval_steps_per_second": 1.2,
|
162 |
"step": 14000
|
163 |
+
},
|
164 |
+
{
|
165 |
+
"epoch": 1.86,
|
166 |
+
"learning_rate": 0.0008564281159562467,
|
167 |
+
"loss": 1.3046,
|
168 |
+
"step": 16000
|
169 |
+
},
|
170 |
+
{
|
171 |
+
"epoch": 1.86,
|
172 |
+
"eval_accuracy": null,
|
173 |
+
"eval_bertscore_f1": 0.9335851898597426,
|
174 |
+
"eval_bleu": 0.4074581189783245,
|
175 |
+
"eval_f1": null,
|
176 |
+
"eval_loss": 1.7547861337661743,
|
177 |
+
"eval_rouge1": 0.6106875900448452,
|
178 |
+
"eval_rouge2": 0.40481219032920934,
|
179 |
+
"eval_rougeL": 0.5549309353470346,
|
180 |
+
"eval_rougeLsum": 0.5570675429924621,
|
181 |
+
"eval_runtime": 123.362,
|
182 |
+
"eval_samples_per_second": 79.781,
|
183 |
+
"eval_steps_per_second": 1.248,
|
184 |
+
"step": 16000
|
185 |
}
|
186 |
],
|
187 |
"max_steps": 85840,
|
188 |
"num_train_epochs": 10,
|
189 |
+
"total_flos": 1.5969080133353472e+16,
|
190 |
"trial_name": null,
|
191 |
"trial_params": null
|
192 |
}
|
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 sha256:89cedab307f06025168521c80e60ea525573bc523455ae3e165e4034e682a576
|
3 |
size 242071641
|