Training in progress, step 42, checkpoint
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 43122580
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2c29feb93714190670b2fb92ef70a723f460c9f0f0870090b889f1096cf82463
|
3 |
size 43122580
|
last-checkpoint/rng_state.pth
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 14244
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a2b3f6b12e0aa9c777494137b728f08bc96c5e3af997823b308e5dae78db59ee
|
3 |
size 14244
|
last-checkpoint/scheduler.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1064
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
|
3 |
size 1064
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch": 0.
|
5 |
"eval_steps": 14,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -45,6 +45,28 @@
|
|
45 |
"eval_samples_per_second": 30.178,
|
46 |
"eval_steps_per_second": 15.089,
|
47 |
"step": 28
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
48 |
}
|
49 |
],
|
50 |
"logging_steps": 10,
|
@@ -64,7 +86,7 @@
|
|
64 |
"attributes": {}
|
65 |
}
|
66 |
},
|
67 |
-
"total_flos":
|
68 |
"train_batch_size": 2,
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0018329805573133742,
|
5 |
"eval_steps": 14,
|
6 |
+
"global_step": 42,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
45 |
"eval_samples_per_second": 30.178,
|
46 |
"eval_steps_per_second": 15.089,
|
47 |
"step": 28
|
48 |
+
},
|
49 |
+
{
|
50 |
+
"epoch": 0.0013092718266524102,
|
51 |
+
"grad_norm": NaN,
|
52 |
+
"learning_rate": 0.0001,
|
53 |
+
"loss": 722.4505,
|
54 |
+
"step": 30
|
55 |
+
},
|
56 |
+
{
|
57 |
+
"epoch": 0.00174569576886988,
|
58 |
+
"grad_norm": NaN,
|
59 |
+
"learning_rate": 4.12214747707527e-05,
|
60 |
+
"loss": 0.0,
|
61 |
+
"step": 40
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.0018329805573133742,
|
65 |
+
"eval_loss": NaN,
|
66 |
+
"eval_runtime": 319.7007,
|
67 |
+
"eval_samples_per_second": 30.178,
|
68 |
+
"eval_steps_per_second": 15.089,
|
69 |
+
"step": 42
|
70 |
}
|
71 |
],
|
72 |
"logging_steps": 10,
|
|
|
86 |
"attributes": {}
|
87 |
}
|
88 |
},
|
89 |
+
"total_flos": 7887027626311680.0,
|
90 |
"train_batch_size": 2,
|
91 |
"trial_name": null,
|
92 |
"trial_params": null
|