Training in progress, step 2000
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 sha256:579fa724661366bf79930b1774db39ef896467595fe276ba6872bd3d115cb386
|
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:cfc1304a617e228df65bbeb484bfdff5002bdb04b6f9b26a9f020d691d17574e
|
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:c5c1723cf0ae27acb08d4bc7722be5995496e74a0a3f581f3fd06b8c40d9cfd0
|
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 sha256:8d5dbc29b7b73bb6aed001c30726ee5465aa95d807330c1e0307d129e92eb7dc
|
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:ef39c185b26e11042cf07c78b07c454716078f0195a99401d7c43ccc71697be0
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-
|
4 |
-
"epoch": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -63,11 +63,30 @@
|
|
63 |
"eval_samples_per_second": 57.239,
|
64 |
"eval_steps_per_second": 1.803,
|
65 |
"step": 1500
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
],
|
68 |
"max_steps": 62500,
|
69 |
"num_train_epochs": 20,
|
70 |
-
"total_flos":
|
71 |
"trial_name": null,
|
72 |
"trial_params": null
|
73 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0715276002883911,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-2000",
|
4 |
+
"epoch": 0.64,
|
5 |
+
"global_step": 2000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
63 |
"eval_samples_per_second": 57.239,
|
64 |
"eval_steps_per_second": 1.803,
|
65 |
"step": 1500
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.64,
|
69 |
+
"learning_rate": 0.00031952000000000006,
|
70 |
+
"loss": 1.1187,
|
71 |
+
"step": 2000
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.64,
|
75 |
+
"eval_bleu": 0.05024016948621801,
|
76 |
+
"eval_exact_match": 0.0735,
|
77 |
+
"eval_loss": 1.0715276002883911,
|
78 |
+
"eval_rouge1": 0.44133744346838355,
|
79 |
+
"eval_rouge2": 0.25777725613931946,
|
80 |
+
"eval_rougeL": 0.4219959477894215,
|
81 |
+
"eval_runtime": 35.3166,
|
82 |
+
"eval_samples_per_second": 56.631,
|
83 |
+
"eval_steps_per_second": 1.784,
|
84 |
+
"step": 2000
|
85 |
}
|
86 |
],
|
87 |
"max_steps": 62500,
|
88 |
"num_train_epochs": 20,
|
89 |
+
"total_flos": 8378790998704128.0,
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|
92 |
}
|
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:cfc1304a617e228df65bbeb484bfdff5002bdb04b6f9b26a9f020d691d17574e
|
3 |
size 242031355
|