Training in progress, step 22000
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:b0302dc19abcec156a7b2f17935a47c6b85162478f03f6da42eda8f1b2ddd704
|
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 sha256:0c431f67318e37ae2f39abd4e05340b4543e60abb3066a9325629237eaa4198f
|
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 sha256:9ff022473010c0df5ad37d9eb1d5da5c5588f400496bdf5e16f61bb2b07cea1a
|
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 sha256:00fc20b07457d2e67c7b293ab93cf0b2991ff2beeb6ad8da7e6a4999309dc031
|
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": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -226,11 +226,33 @@
|
|
226 |
"eval_samples_per_second": 77.077,
|
227 |
"eval_steps_per_second": 1.206,
|
228 |
"step": 20000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
229 |
}
|
230 |
],
|
231 |
"max_steps": 85840,
|
232 |
"num_train_epochs": 10,
|
233 |
-
"total_flos":
|
234 |
"trial_name": null,
|
235 |
"trial_params": null
|
236 |
}
|
|
|
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": 2.562907735321528,
|
5 |
+
"global_step": 22000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
226 |
"eval_samples_per_second": 77.077,
|
227 |
"eval_steps_per_second": 1.206,
|
228 |
"step": 20000
|
229 |
+
},
|
230 |
+
{
|
231 |
+
"epoch": 2.56,
|
232 |
+
"learning_rate": 0.000782851817334576,
|
233 |
+
"loss": 1.2499,
|
234 |
+
"step": 22000
|
235 |
+
},
|
236 |
+
{
|
237 |
+
"epoch": 2.56,
|
238 |
+
"eval_accuracy": null,
|
239 |
+
"eval_bertscore_f1": 0.931423125071294,
|
240 |
+
"eval_bleu": 0.3902916555092431,
|
241 |
+
"eval_f1": null,
|
242 |
+
"eval_loss": 1.8007221221923828,
|
243 |
+
"eval_rouge1": 0.6006911915544173,
|
244 |
+
"eval_rouge2": 0.39035654600491987,
|
245 |
+
"eval_rougeL": 0.5444104696749834,
|
246 |
+
"eval_rougeLsum": 0.5462500361747902,
|
247 |
+
"eval_runtime": 124.7647,
|
248 |
+
"eval_samples_per_second": 78.884,
|
249 |
+
"eval_steps_per_second": 1.234,
|
250 |
+
"step": 22000
|
251 |
}
|
252 |
],
|
253 |
"max_steps": 85840,
|
254 |
"num_train_epochs": 10,
|
255 |
+
"total_flos": 2.1972027488108544e+16,
|
256 |
"trial_name": null,
|
257 |
"trial_params": null
|
258 |
}
|
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 sha256:0c431f67318e37ae2f39abd4e05340b4543e60abb3066a9325629237eaa4198f
|
3 |
size 242071641
|