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 1135685
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b67a585ad731edfd3190139c2048716d1ef0cd5c4e23c5d039753733beb85292
|
3 |
size 1135685
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:593e18bc3c456f313a1af17bb6a97030aabe3dfbde4c59f3e4ae0a040049cb77
|
3 |
size 307910149
|
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 sha256:82960f07cae3e568bb93b45888fd2b6a63f1fd9b319bf6f6dda39789df0fc6a6
|
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": 1.7180376052856445,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-12000",
|
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": 61.053,
|
139 |
"eval_steps_per_second": 0.955,
|
140 |
"step": 12000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
141 |
}
|
142 |
],
|
143 |
"max_steps": 85840,
|
144 |
"num_train_epochs": 10,
|
145 |
-
"total_flos":
|
146 |
"trial_name": null,
|
147 |
"trial_params": null
|
148 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7180376052856445,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-12000",
|
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": 61.053,
|
139 |
"eval_steps_per_second": 0.955,
|
140 |
"step": 12000
|
141 |
+
},
|
142 |
+
{
|
143 |
+
"epoch": 1.63,
|
144 |
+
"learning_rate": 0.0008809535488301369,
|
145 |
+
"loss": 1.2527,
|
146 |
+
"step": 14000
|
147 |
+
},
|
148 |
+
{
|
149 |
+
"epoch": 1.63,
|
150 |
+
"eval_accuracy": null,
|
151 |
+
"eval_bertscore_f1": 0.9347525270301088,
|
152 |
+
"eval_bleu": 0.4103575347376984,
|
153 |
+
"eval_f1": null,
|
154 |
+
"eval_loss": 1.7438157796859741,
|
155 |
+
"eval_rouge1": 0.6163196253092696,
|
156 |
+
"eval_rouge2": 0.40951276436422024,
|
157 |
+
"eval_rougeL": 0.561512744919562,
|
158 |
+
"eval_rougeLsum": 0.5636171995683823,
|
159 |
+
"eval_runtime": 163.0281,
|
160 |
+
"eval_samples_per_second": 60.37,
|
161 |
+
"eval_steps_per_second": 0.945,
|
162 |
+
"step": 14000
|
163 |
}
|
164 |
],
|
165 |
"max_steps": 85840,
|
166 |
"num_train_epochs": 10,
|
167 |
+
"total_flos": 2.1150083559346176e+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 307910149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:593e18bc3c456f313a1af17bb6a97030aabe3dfbde4c59f3e4ae0a040049cb77
|
3 |
size 307910149
|