Training in progress, step 12000
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 sha256:39e152eda147d2ecd5967adefd3a608fdb175fcbf859c981bb14657a55285502
|
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 sha256:54f4c8db04830c5a1cbf06c90cc84858329ae5ccefb52dc0fd78c2e9d38098df
|
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 sha256:8567cb85cd962d1aa81a0b740e7df2e6c65e5c12c6885cd8e7f30eb2ee7f99f3
|
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 sha256:7f07e5c87a13181fdd91b70430838fde915aa2178a6a09686f68923b2683ae87
|
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,
|
@@ -116,11 +116,33 @@
|
|
116 |
"eval_samples_per_second": 76.915,
|
117 |
"eval_steps_per_second": 1.204,
|
118 |
"step": 10000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
119 |
}
|
120 |
],
|
121 |
"max_steps": 85840,
|
122 |
"num_train_epochs": 10,
|
123 |
-
"total_flos":
|
124 |
"trial_name": null,
|
125 |
"trial_params": null
|
126 |
}
|
|
|
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": 1.3979496738117427,
|
5 |
+
"global_step": 12000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
116 |
"eval_samples_per_second": 76.915,
|
117 |
"eval_steps_per_second": 1.204,
|
118 |
"step": 10000
|
119 |
+
},
|
120 |
+
{
|
121 |
+
"epoch": 1.4,
|
122 |
+
"learning_rate": 0.0009054789817040271,
|
123 |
+
"loss": 1.3314,
|
124 |
+
"step": 12000
|
125 |
+
},
|
126 |
+
{
|
127 |
+
"epoch": 1.4,
|
128 |
+
"eval_accuracy": null,
|
129 |
+
"eval_bertscore_f1": 0.9321439913486325,
|
130 |
+
"eval_bleu": 0.40043826944150546,
|
131 |
+
"eval_f1": null,
|
132 |
+
"eval_loss": 1.8358908891677856,
|
133 |
+
"eval_rouge1": 0.6033740241419494,
|
134 |
+
"eval_rouge2": 0.3943871885637782,
|
135 |
+
"eval_rougeL": 0.5446854297032411,
|
136 |
+
"eval_rougeLsum": 0.5468056362503415,
|
137 |
+
"eval_runtime": 123.4557,
|
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": 1.1973265704419328e+16,
|
146 |
"trial_name": null,
|
147 |
"trial_params": null
|
148 |
}
|
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 sha256:54f4c8db04830c5a1cbf06c90cc84858329ae5ccefb52dc0fd78c2e9d38098df
|
3 |
size 242071641
|