Training in progress, step 14000
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:bc32e1100521d3d21755b0985df06fa5a38de458d5e97394591015135c8d9452
|
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:fa77666cbc52dd799458b902c1fd7acd4162c4493243ae6d21cadadb9d387ac9
|
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 sha256:439d1b38531fc0bda6f808b6cacb2799778ce10a40ef67661a6dc5a64e4670d9
|
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 sha256:9a9379299cb036bee8563adb6a6941350bd1a2187d737827bca0ce7b889d9885
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.7958769798278809,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-10000",
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -138,11 +138,33 @@
|
|
138 |
"eval_samples_per_second": 79.721,
|
139 |
"eval_steps_per_second": 1.247,
|
140 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
}
|
142 |
],
|
143 |
"max_steps": 85840,
|
144 |
"num_train_epochs": 10,
|
145 |
-
"total_flos": 1.
|
146 |
"trial_name": null,
|
147 |
"trial_params": null
|
148 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7958769798278809,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/t5-small-e-snli-generation-explanation_only-selected-b64/checkpoint-10000",
|
4 |
+
"epoch": 1.6309412861136998,
|
5 |
+
"global_step": 14000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
138 |
"eval_samples_per_second": 79.721,
|
139 |
"eval_steps_per_second": 1.247,
|
140 |
"step": 12000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.63,
|
144 |
+
"learning_rate": 0.0008809535488301369,
|
145 |
+
"loss": 1.322,
|
146 |
+
"step": 14000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.63,
|
150 |
+
"eval_accuracy": null,
|
151 |
+
"eval_bertscore_f1": 0.9318598681253477,
|
152 |
+
"eval_bleu": 0.3901308120455454,
|
153 |
+
"eval_f1": null,
|
154 |
+
"eval_loss": 1.8139214515686035,
|
155 |
+
"eval_rouge1": 0.6077021217894953,
|
156 |
+
"eval_rouge2": 0.39737953301577167,
|
157 |
+
"eval_rougeL": 0.5487431215145148,
|
158 |
+
"eval_rougeLsum": 0.5508016845003574,
|
159 |
+
"eval_runtime": 128.2981,
|
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": 1.3969540358406144e+16,
|
168 |
"trial_name": null,
|
169 |
"trial_params": null
|
170 |
}
|
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:fa77666cbc52dd799458b902c1fd7acd4162c4493243ae6d21cadadb9d387ac9
|
3 |
size 242071641
|