Training in progress, step 8000
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:e352384b6f79720b1bbcc3d113d5ab897b96f6659224f695ee84f934fb3610ab
|
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 sha256:51d7b1ae3ed5c6db4e5b6b62f62a04d8ac4980311d48a19a7a53f4341141da10
|
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:c6ddd4db24f8162c6c29bb4b10ffd18c84b969981f90e81d7b10ed710ef908e4
|
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 sha256:0480a19c1bb0f1d4849d6f8498c92440ead5e7dc1264bee4fc839d9a71a6e7c3
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 1.7246909141540527,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-6000",
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -72,11 +72,33 @@
|
|
72 |
"eval_samples_per_second": 59.779,
|
73 |
"eval_steps_per_second": 0.935,
|
74 |
"step": 6000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
}
|
76 |
],
|
77 |
"max_steps": 85840,
|
78 |
"num_train_epochs": 10,
|
79 |
-
"total_flos":
|
80 |
"trial_name": null,
|
81 |
"trial_params": null
|
82 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 1.7246909141540527,
|
3 |
"best_model_checkpoint": "/home3/s5431786/nlp-final-project/results/google-flan-t5-small-e-snli-generation-explanation_use_prompt_label-selected-b64/checkpoint-6000",
|
4 |
+
"epoch": 0.9319664492078286,
|
5 |
+
"global_step": 8000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
72 |
"eval_samples_per_second": 59.779,
|
73 |
"eval_steps_per_second": 0.935,
|
74 |
"step": 6000
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 0.93,
|
78 |
+
"learning_rate": 0.0009545298474518076,
|
79 |
+
"loss": 1.3396,
|
80 |
+
"step": 8000
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 0.93,
|
84 |
+
"eval_accuracy": null,
|
85 |
+
"eval_bertscore_f1": 0.9358202236390555,
|
86 |
+
"eval_bleu": 0.41886081162261424,
|
87 |
+
"eval_f1": null,
|
88 |
+
"eval_loss": 1.7622839212417603,
|
89 |
+
"eval_rouge1": 0.6176280342703749,
|
90 |
+
"eval_rouge2": 0.4078573926320103,
|
91 |
+
"eval_rougeL": 0.5616472881864998,
|
92 |
+
"eval_rougeLsum": 0.563450597865839,
|
93 |
+
"eval_runtime": 154.9703,
|
94 |
+
"eval_samples_per_second": 63.509,
|
95 |
+
"eval_steps_per_second": 0.994,
|
96 |
+
"step": 8000
|
97 |
}
|
98 |
],
|
99 |
"max_steps": 85840,
|
100 |
"num_train_epochs": 10,
|
101 |
+
"total_flos": 1.208276662419456e+16,
|
102 |
"trial_name": null,
|
103 |
"trial_params": null
|
104 |
}
|
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 sha256:51d7b1ae3ed5c6db4e5b6b62f62a04d8ac4980311d48a19a7a53f4341141da10
|
3 |
size 307910149
|