Reza-Madani
commited on
Commit
•
f963ca5
1
Parent(s):
25c1465
Training in progress, step 1500
Browse files- last-checkpoint/optimizer.pt +1 -1
- last-checkpoint/pytorch_model.bin +1 -1
- last-checkpoint/rng_state.pth +1 -1
- last-checkpoint/scheduler.pt +1 -1
- last-checkpoint/trainer_state.json +20 -3
- pytorch_model.bin +1 -1
- runs/Feb06_00-09-26_7b2c5a261d79/events.out.tfevents.1675642174.7b2c5a261d79.156.12 +2 -2
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 93502963
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bbd65b2910dfe53def7025ef51fea4d5f7484d3cd682e4874f019ae891fff975
|
3 |
size 93502963
|
last-checkpoint/pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46757253
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:154b3577f719c5dda0de2f408518a2b15fcd9c62776e556892d416f80c2c552e
|
3 |
size 46757253
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14575
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69539607f448b1412bfe6fdd85dee449a8882b18d3ae1c1e9b9033dfd59077a8
|
3 |
size 14575
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 627
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:11136fcd46eec730857bbc14c4e6166f25c84e1400e212dbacd1092858622907
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
"best_metric": 0.32092705368995667,
|
3 |
"best_model_checkpoint": "./esnli-label-predictor-paraphrase-albert-small-v2/checkpoint-1000",
|
4 |
-
"epoch": 2.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -91,11 +91,28 @@
|
|
91 |
"eval_samples_per_second": 2816.303,
|
92 |
"eval_steps_per_second": 5.723,
|
93 |
"step": 1250
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
94 |
}
|
95 |
],
|
96 |
"max_steps": 1524,
|
97 |
"num_train_epochs": 3,
|
98 |
-
"total_flos":
|
99 |
"trial_name": null,
|
100 |
"trial_params": null
|
101 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.32092705368995667,
|
3 |
"best_model_checkpoint": "./esnli-label-predictor-paraphrase-albert-small-v2/checkpoint-1000",
|
4 |
+
"epoch": 2.952755905511811,
|
5 |
+
"global_step": 1500,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
91 |
"eval_samples_per_second": 2816.303,
|
92 |
"eval_steps_per_second": 5.723,
|
93 |
"step": 1250
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 2.95,
|
97 |
+
"learning_rate": 7.874015748031496e-07,
|
98 |
+
"loss": 0.2333,
|
99 |
+
"step": 1500
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 2.95,
|
103 |
+
"eval_Accuracy": {
|
104 |
+
"accuracy": 0.8686242633611054
|
105 |
+
},
|
106 |
+
"eval_loss": 0.34050989151000977,
|
107 |
+
"eval_runtime": 3.3893,
|
108 |
+
"eval_samples_per_second": 2903.839,
|
109 |
+
"eval_steps_per_second": 5.901,
|
110 |
+
"step": 1500
|
111 |
}
|
112 |
],
|
113 |
"max_steps": 1524,
|
114 |
"num_train_epochs": 3,
|
115 |
+
"total_flos": 286733121254112.0,
|
116 |
"trial_name": null,
|
117 |
"trial_params": null
|
118 |
}
|
pytorch_model.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 46757253
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:154b3577f719c5dda0de2f408518a2b15fcd9c62776e556892d416f80c2c552e
|
3 |
size 46757253
|
runs/Feb06_00-09-26_7b2c5a261d79/events.out.tfevents.1675642174.7b2c5a261d79.156.12
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1efb68300424559ee97e9e0fae46584b1df05ca4452e80c7506c078c7f0d468d
|
3 |
+
size 6851
|