sara-nabhani
commited on
Commit
·
232080c
1
Parent(s):
b08d816
Training in progress, step 10000
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:d7a5e153b4a276c51311015ef7d32b4608d62762f7513236318a1ba50af8e70f
|
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 sha256:7e1f86e5ed9d088634a6c5c4549647aa229ec662b65d4a8392219025744cf3c1
|
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:c81298488a17e1b0ae49686ebcf93f90fd3c0a99ff00d5fb11e63f22f7814a35
|
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 sha256:9e2630ad918c61bc51cc3ab06f53d7b1174e5ad20efe090354e938c18819c227
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.748366355895996,
|
3 |
"best_model_checkpoint": "/home2/s5432073/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b48/checkpoint-2000",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -94,11 +94,33 @@
|
|
94 |
"eval_samples_per_second": 61.923,
|
95 |
"eval_steps_per_second": 1.296,
|
96 |
"step": 8000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
97 |
}
|
98 |
],
|
99 |
"max_steps": 114460,
|
100 |
"num_train_epochs": 10,
|
101 |
-
"total_flos":
|
102 |
"trial_name": null,
|
103 |
"trial_params": null
|
104 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.748366355895996,
|
3 |
"best_model_checkpoint": "/home2/s5432073/nlp-final-project/results/google-flan-t5-small-e-snli-generation-label_and_explanation-selected-b48/checkpoint-2000",
|
4 |
+
"epoch": 0.8736676568233444,
|
5 |
+
"global_step": 10000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
94 |
"eval_samples_per_second": 61.923,
|
95 |
"eval_steps_per_second": 1.296,
|
96 |
"step": 8000
|
97 |
+
},
|
98 |
+
{
|
99 |
+
"epoch": 0.87,
|
100 |
+
"learning_rate": 0.000960666562439648,
|
101 |
+
"loss": 1.1674,
|
102 |
+
"step": 10000
|
103 |
+
},
|
104 |
+
{
|
105 |
+
"epoch": 0.87,
|
106 |
+
"eval_accuracy": 0.8507417191627717,
|
107 |
+
"eval_bertscore_f1": 0.9309739923058087,
|
108 |
+
"eval_bleu": 0.38917736442742895,
|
109 |
+
"eval_f1": 0.8485245801942701,
|
110 |
+
"eval_loss": 1.8567092418670654,
|
111 |
+
"eval_rouge1": 0.5947498091541006,
|
112 |
+
"eval_rouge2": 0.38877870802357656,
|
113 |
+
"eval_rougeL": 0.5382707915260707,
|
114 |
+
"eval_rougeLsum": 0.5401697430632839,
|
115 |
+
"eval_runtime": 171.2441,
|
116 |
+
"eval_samples_per_second": 57.474,
|
117 |
+
"eval_steps_per_second": 1.203,
|
118 |
+
"step": 10000
|
119 |
}
|
120 |
],
|
121 |
"max_steps": 114460,
|
122 |
"num_train_epochs": 10,
|
123 |
+
"total_flos": 9877739266473984.0,
|
124 |
"trial_name": null,
|
125 |
"trial_params": null
|
126 |
}
|
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 sha256:7e1f86e5ed9d088634a6c5c4549647aa229ec662b65d4a8392219025744cf3c1
|
3 |
size 307910149
|