Training in progress, step 18000
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 sha256:9089a56861d266bd78768f133d8fd4f76ad9125b0e8a132d1ee57ec607c7b846
|
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 sha256:47141a4272f857b8347bb808de8bcaa16410a7fd8514d093a232810bccd44c67
|
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:a03a451e33b28ebcf0f7f7c3591624280db72e253ee1f74b711c1bac1a9d2627
|
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 sha256:62302b41ef27e8715d8b2f0e96943911ec884bb406e266f83a8ca9d79997b602
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -182,11 +182,33 @@
|
|
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.
|
190 |
"trial_name": null,
|
191 |
"trial_params": null
|
192 |
}
|
|
|
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": 2.096924510717614,
|
5 |
+
"global_step": 18000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
182 |
"eval_samples_per_second": 79.781,
|
183 |
"eval_steps_per_second": 1.248,
|
184 |
"step": 16000
|
185 |
+
},
|
186 |
+
{
|
187 |
+
"epoch": 2.1,
|
188 |
+
"learning_rate": 0.0008319026830823564,
|
189 |
+
"loss": 1.2811,
|
190 |
+
"step": 18000
|
191 |
+
},
|
192 |
+
{
|
193 |
+
"epoch": 2.1,
|
194 |
+
"eval_accuracy": null,
|
195 |
+
"eval_bertscore_f1": 0.9323258479783458,
|
196 |
+
"eval_bleu": 0.3945938807031178,
|
197 |
+
"eval_f1": null,
|
198 |
+
"eval_loss": 1.8054404258728027,
|
199 |
+
"eval_rouge1": 0.6125229180885745,
|
200 |
+
"eval_rouge2": 0.40770947555297465,
|
201 |
+
"eval_rougeL": 0.5571630795127507,
|
202 |
+
"eval_rougeLsum": 0.5593601401592401,
|
203 |
+
"eval_runtime": 130.5972,
|
204 |
+
"eval_samples_per_second": 75.361,
|
205 |
+
"eval_steps_per_second": 1.179,
|
206 |
+
"step": 18000
|
207 |
}
|
208 |
],
|
209 |
"max_steps": 85840,
|
210 |
"num_train_epochs": 10,
|
211 |
+
"total_flos": 1.7973692318121984e+16,
|
212 |
"trial_name": null,
|
213 |
"trial_params": null
|
214 |
}
|
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 sha256:47141a4272f857b8347bb808de8bcaa16410a7fd8514d093a232810bccd44c67
|
3 |
size 242071641
|