Training in progress, step 2500
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 sha256:7067dfa1d865beb320fd151fbfec80c2679ff5f9742b4a59758dd2cab91979db
|
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 sha256:8861ece90fa3df483275c3049986a20e7084f56252b3e1f127ec89dcb5f41e49
|
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 sha256:0c2a1e35b0ca15cfd1e4ca76c86e2c2838e12da4c0f1bd154bd2ddd0c46d0927
|
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 sha256:5d7b70dca843c46e01703cb818c79be798fc8fa62b2ae2d70baff27e6b0f3498
|
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 sha256:57a60f57dc0d94ead31d499287d0db8ad4c9668cf5fc529c7699985dcd646f76
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric":
|
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,
|
@@ -82,11 +82,30 @@
|
|
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":
|
90 |
"trial_name": null,
|
91 |
"trial_params": null
|
92 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9908952116966248,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-2500",
|
4 |
+
"epoch": 0.8,
|
5 |
+
"global_step": 2500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
82 |
"eval_samples_per_second": 56.631,
|
83 |
"eval_steps_per_second": 1.784,
|
84 |
"step": 2000
|
85 |
+
},
|
86 |
+
{
|
87 |
+
"epoch": 0.8,
|
88 |
+
"learning_rate": 0.00039952,
|
89 |
+
"loss": 1.0062,
|
90 |
+
"step": 2500
|
91 |
+
},
|
92 |
+
{
|
93 |
+
"epoch": 0.8,
|
94 |
+
"eval_bleu": 0.0525791651130599,
|
95 |
+
"eval_exact_match": 0.0815,
|
96 |
+
"eval_loss": 0.9908952116966248,
|
97 |
+
"eval_rouge1": 0.46270763973625095,
|
98 |
+
"eval_rouge2": 0.2836027818482203,
|
99 |
+
"eval_rougeL": 0.4457626023912316,
|
100 |
+
"eval_runtime": 35.2306,
|
101 |
+
"eval_samples_per_second": 56.769,
|
102 |
+
"eval_steps_per_second": 1.788,
|
103 |
+
"step": 2500
|
104 |
}
|
105 |
],
|
106 |
"max_steps": 62500,
|
107 |
"num_train_epochs": 20,
|
108 |
+
"total_flos": 1.0477773162283008e+16,
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
111 |
}
|
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 sha256:8861ece90fa3df483275c3049986a20e7084f56252b3e1f127ec89dcb5f41e49
|
3 |
size 242031355
|