dougtrajano
commited on
Commit
•
ffb90ee
1
Parent(s):
0f31868
Training in progress, epoch 4
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 2675416477
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0e6ea6cfafe708a028924c28cc19f7dcd6a5c3004ec5cc3422203245a05bf072
|
3 |
size 2675416477
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1337729837
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c983c6bf26b67f2c0eb7ff97382c87d6e4e1524f8a9b8e86abdbf4f481a34192
|
3 |
size 1337729837
|
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:f806152ad64e8898453899042bd69ab8cd8cda7df40e6f3fa4b727ea90c75eaf
|
3 |
size 14503
|
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 sha256:5a9a007030c4f96fbaeed29d3595a7874042a37dd20fba571f613e56b64d9989
|
3 |
size 623
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.8549217425622928,
|
3 |
"best_model_checkpoint": "/opt/ml/checkpoints/toxic-comment-classification-2023-02-26-22-07-06-968/model/checkpoint-1408",
|
4 |
-
"epoch":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -90,11 +90,41 @@
|
|
90 |
"eval_samples_per_second": 273.94,
|
91 |
"eval_steps_per_second": 34.274,
|
92 |
"step": 4224
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
93 |
}
|
94 |
],
|
95 |
"max_steps": 42240,
|
96 |
"num_train_epochs": 30,
|
97 |
-
"total_flos":
|
98 |
"trial_name": null,
|
99 |
"trial_params": null
|
100 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.8549217425622928,
|
3 |
"best_model_checkpoint": "/opt/ml/checkpoints/toxic-comment-classification-2023-02-26-22-07-06-968/model/checkpoint-1408",
|
4 |
+
"epoch": 4.0,
|
5 |
+
"global_step": 5632,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
90 |
"eval_samples_per_second": 273.94,
|
91 |
"eval_steps_per_second": 34.274,
|
92 |
"step": 4224
|
93 |
+
},
|
94 |
+
{
|
95 |
+
"epoch": 3.2,
|
96 |
+
"learning_rate": 2.9089362530568417e-05,
|
97 |
+
"loss": 0.3607,
|
98 |
+
"step": 4500
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 3.55,
|
102 |
+
"learning_rate": 2.8703970870121032e-05,
|
103 |
+
"loss": 0.345,
|
104 |
+
"step": 5000
|
105 |
+
},
|
106 |
+
{
|
107 |
+
"epoch": 3.91,
|
108 |
+
"learning_rate": 2.831857920967365e-05,
|
109 |
+
"loss": 0.3643,
|
110 |
+
"step": 5500
|
111 |
+
},
|
112 |
+
{
|
113 |
+
"epoch": 4.0,
|
114 |
+
"eval_accuracy": 0.8247743541861189,
|
115 |
+
"eval_f1": 0.8210678650289922,
|
116 |
+
"eval_loss": 0.49613112211227417,
|
117 |
+
"eval_precision": 0.8348592222910702,
|
118 |
+
"eval_recall": 0.8247743541861189,
|
119 |
+
"eval_runtime": 11.9823,
|
120 |
+
"eval_samples_per_second": 268.146,
|
121 |
+
"eval_steps_per_second": 33.55,
|
122 |
+
"step": 5632
|
123 |
}
|
124 |
],
|
125 |
"max_steps": 42240,
|
126 |
"num_train_epochs": 30,
|
127 |
+
"total_flos": 6189585965602872.0,
|
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 1337729837
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c983c6bf26b67f2c0eb7ff97382c87d6e4e1524f8a9b8e86abdbf4f481a34192
|
3 |
size 1337729837
|