Training in progress, step 3000
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:d2e0f4bc6098f5fa36b06e85afa4c85d494237c1160681326f697f29caf9cb26
|
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:a5f818863e1366c6b155186b36b018d809dadcd0e7115839d6fba96086ef03cd
|
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 sha256:969602af4fc3b140873606fdda6dd2ae12cd2305646785b559a5fbd9c6199203
|
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:f8ec6882b7592c0ac7b9cd7d7fe3da25ac3c6fd19100a89c73fb078e31a1ddc3
|
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 sha256:4359ecbcc02f21ec2731460ada3d69cd156e923f4b38d3522bdd336b05d00497
|
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": 0.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -101,11 +101,30 @@
|
|
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.
|
109 |
"trial_name": null,
|
110 |
"trial_params": null
|
111 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.9375063180923462,
|
3 |
+
"best_model_checkpoint": "/home2/s5431786/jb-internship/results/t5-small-CodeXGLUE-CONCODE-faster/checkpoint-3000",
|
4 |
+
"epoch": 0.96,
|
5 |
+
"global_step": 3000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
101 |
"eval_samples_per_second": 56.769,
|
102 |
"eval_steps_per_second": 1.788,
|
103 |
"step": 2500
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 0.96,
|
107 |
+
"learning_rate": 0.00047952,
|
108 |
+
"loss": 0.9314,
|
109 |
+
"step": 3000
|
110 |
+
},
|
111 |
+
{
|
112 |
+
"epoch": 0.96,
|
113 |
+
"eval_bleu": 0.056618620209005335,
|
114 |
+
"eval_exact_match": 0.0845,
|
115 |
+
"eval_loss": 0.9375063180923462,
|
116 |
+
"eval_rouge1": 0.4688436524948581,
|
117 |
+
"eval_rouge2": 0.2932255323307211,
|
118 |
+
"eval_rougeL": 0.45301193641551707,
|
119 |
+
"eval_runtime": 37.1868,
|
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": 1.2580663320379392e+16,
|
128 |
"trial_name": null,
|
129 |
"trial_params": null
|
130 |
}
|
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:a5f818863e1366c6b155186b36b018d809dadcd0e7115839d6fba96086ef03cd
|
3 |
size 242031355
|