Training in progress, step 3500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scaler.pt +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +24 -5
- pytorch_model.bin +1 -1
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484083951
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:12dc8791bfa2147598bcc50adbc21ee3a76e43368392c15e23995c2743d0fb79
|
3 |
size 484083951
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a92c7c453300be3539a50737e2144a5eae2cb1fddc078ced32786788bbdeb54
|
3 |
size 242031355
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14503
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1c0ca3d86e7c8df38990a333c730b9ec8059ce6ab1aa1c8ca472fd47534ab31
|
3 |
size 14503
|
last-checkpoint/scaler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 559
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:93eb9e64cb70109e8f24ce054cb2686796a877ca28c7ab0a7311addb9529200a
|
3 |
size 559
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 623
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8256adaefb0d04a2c31981797ab33c62d768acc4b6aa9346d47d584bcdb617eb
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -120,11 +120,30 @@
|
|
120 |
"eval_samples_per_second": 53.783,
|
121 |
"eval_steps_per_second": 1.694,
|
122 |
"step": 3000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
123 |
}
|
124 |
],
|
125 |
"max_steps": 62500,
|
126 |
"num_train_epochs": 20,
|
127 |
-
"total_flos": 1.
|
128 |
"trial_name": null,
|
129 |
"trial_params": null
|
130 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.8949318528175354,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-3500",
|
4 |
+
"epoch": 1.12,
|
5 |
+
"global_step": 3500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
120 |
"eval_samples_per_second": 53.783,
|
121 |
"eval_steps_per_second": 1.694,
|
122 |
"step": 3000
|
123 |
+
},
|
124 |
+
{
|
125 |
+
"epoch": 1.12,
|
126 |
+
"learning_rate": 0.0004968673684210526,
|
127 |
+
"loss": 0.8581,
|
128 |
+
"step": 3500
|
129 |
+
},
|
130 |
+
{
|
131 |
+
"epoch": 1.12,
|
132 |
+
"eval_bleu": 0.05920053067894586,
|
133 |
+
"eval_exact_match": 0.0855,
|
134 |
+
"eval_loss": 0.8949318528175354,
|
135 |
+
"eval_rouge1": 0.475736898014815,
|
136 |
+
"eval_rouge2": 0.30127214832048377,
|
137 |
+
"eval_rougeL": 0.45988834774964316,
|
138 |
+
"eval_runtime": 35.9797,
|
139 |
+
"eval_samples_per_second": 55.587,
|
140 |
+
"eval_steps_per_second": 1.751,
|
141 |
+
"step": 3500
|
142 |
}
|
143 |
],
|
144 |
"max_steps": 62500,
|
145 |
"num_train_epochs": 20,
|
146 |
+
"total_flos": 1.4670281523068928e+16,
|
147 |
"trial_name": null,
|
148 |
"trial_params": null
|
149 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242031355
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9a92c7c453300be3539a50737e2144a5eae2cb1fddc078ced32786788bbdeb54
|
3 |
size 242031355
|