Reza-Madani
commited on
Commit
•
25c1465
1
Parent(s):
1deae40
Training in progress, step 1250
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:a3fc164f30953e75b0614f9ab4278af13bf1713765e23d28adc52d465d162bdb
|
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 sha256:09a79e8e871e58d5d92c789eba016efa8e7df7b4e974401b53a47942e51c8ed4
|
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 sha256:77bfde002d97a4b05ffc411c3dcce1f9da80610f78f97b5e2224f883f365fdf8
|
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:d7fb040a33bb83412663862c33580f447382f04bbdfd3c7ca28962234e7c0c21
|
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":
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -74,11 +74,28 @@
|
|
74 |
"eval_samples_per_second": 3134.662,
|
75 |
"eval_steps_per_second": 6.37,
|
76 |
"step": 1000
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
77 |
}
|
78 |
],
|
79 |
"max_steps": 1524,
|
80 |
"num_train_epochs": 3,
|
81 |
-
"total_flos":
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
|
|
1 |
{
|
2 |
"best_metric": 0.32092705368995667,
|
3 |
"best_model_checkpoint": "./esnli-label-predictor-paraphrase-albert-small-v2/checkpoint-1000",
|
4 |
+
"epoch": 2.4606299212598426,
|
5 |
+
"global_step": 1250,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
74 |
"eval_samples_per_second": 3134.662,
|
75 |
"eval_steps_per_second": 6.37,
|
76 |
"step": 1000
|
77 |
+
},
|
78 |
+
{
|
79 |
+
"epoch": 2.46,
|
80 |
+
"learning_rate": 8.98950131233596e-06,
|
81 |
+
"loss": 0.2388,
|
82 |
+
"step": 1250
|
83 |
+
},
|
84 |
+
{
|
85 |
+
"epoch": 2.46,
|
86 |
+
"eval_Accuracy": {
|
87 |
+
"accuracy": 0.8709611867506605
|
88 |
+
},
|
89 |
+
"eval_loss": 0.34105175733566284,
|
90 |
+
"eval_runtime": 3.4947,
|
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": 238932192998112.0,
|
99 |
"trial_name": null,
|
100 |
"trial_params": null
|
101 |
}
|
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 sha256:09a79e8e871e58d5d92c789eba016efa8e7df7b4e974401b53a47942e51c8ed4
|
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 sha256:1181e26f4ce05499d88386d2119338d013c86d6e36f2e089c84af2b8ffdd16c3
|
3 |
+
size 6423
|