Reza-Madani
commited on
Commit
•
1deae40
1
Parent(s):
b1e061e
Training in progress, step 1000
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 +22 -5
- 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:b0389c7f32215f9f903f4bfabee38ce155031094d66e799e1eb39446015f15c8
|
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 sha256:7a0a70f093d89b0e0fdf76276042d9c5aa2d7a84940b8d0466c94d09df031e81
|
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 sha256:4699a0eae985b31ef8a24595e931e39a899b80f0dbe6f548151088ee9e305ff8
|
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:d7903e1198dd123058ac75e597fb8933a13a62864a1f6aa9a968fc9ea106b6b8
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,8 +1,8 @@
|
|
1 |
{
|
2 |
-
"best_metric": 0.
|
3 |
-
"best_model_checkpoint": "./esnli-label-predictor-paraphrase-albert-small-v2/checkpoint-
|
4 |
-
"epoch": 1.
|
5 |
-
"global_step":
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
@@ -57,11 +57,28 @@
|
|
57 |
"eval_samples_per_second": 3190.679,
|
58 |
"eval_steps_per_second": 6.484,
|
59 |
"step": 750
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
60 |
}
|
61 |
],
|
62 |
"max_steps": 1524,
|
63 |
"num_train_epochs": 3,
|
64 |
-
"total_flos":
|
65 |
"trial_name": null,
|
66 |
"trial_params": null
|
67 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 0.32092705368995667,
|
3 |
+
"best_model_checkpoint": "./esnli-label-predictor-paraphrase-albert-small-v2/checkpoint-1000",
|
4 |
+
"epoch": 1.968503937007874,
|
5 |
+
"global_step": 1000,
|
6 |
"is_hyper_param_search": false,
|
7 |
"is_local_process_zero": true,
|
8 |
"is_world_process_zero": true,
|
|
|
57 |
"eval_samples_per_second": 3190.679,
|
58 |
"eval_steps_per_second": 6.484,
|
59 |
"step": 750
|
60 |
+
},
|
61 |
+
{
|
62 |
+
"epoch": 1.97,
|
63 |
+
"learning_rate": 1.7191601049868766e-05,
|
64 |
+
"loss": 0.295,
|
65 |
+
"step": 1000
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 1.97,
|
69 |
+
"eval_Accuracy": {
|
70 |
+
"accuracy": 0.8718756350335297
|
71 |
+
},
|
72 |
+
"eval_loss": 0.32092705368995667,
|
73 |
+
"eval_runtime": 3.1397,
|
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": 191167488883056.0,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
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 sha256:7a0a70f093d89b0e0fdf76276042d9c5aa2d7a84940b8d0466c94d09df031e81
|
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 sha256:0c86263ec761b6959224f9f77fd47326f58323e4e2990683efe63dc3589fb813
|
3 |
+
size 5995
|