Training in progress, step 25, 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 325339796
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c23f81e970b752cf424703e0fa7f797bd7a8a0ec7d857070058f693ac2a343b
|
3 |
size 325339796
|
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 sha256:344ce451d97f97388bb209454db3719af5ba7ec1a46d63e6682d4024475e0b69
|
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 sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
|
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": 5,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -89,6 +89,28 @@
|
|
89 |
"eval_samples_per_second": 13.382,
|
90 |
"eval_steps_per_second": 1.675,
|
91 |
"step": 20
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
92 |
}
|
93 |
],
|
94 |
"logging_steps": 3,
|
@@ -108,7 +130,7 @@
|
|
108 |
"attributes": {}
|
109 |
}
|
110 |
},
|
111 |
-
"total_flos":
|
112 |
"train_batch_size": 8,
|
113 |
"trial_name": null,
|
114 |
"trial_params": null
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.0074211502782931356,
|
5 |
"eval_steps": 5,
|
6 |
+
"global_step": 25,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
89 |
"eval_samples_per_second": 13.382,
|
90 |
"eval_steps_per_second": 1.675,
|
91 |
"step": 20
|
92 |
+
},
|
93 |
+
{
|
94 |
+
"epoch": 0.006233766233766234,
|
95 |
+
"grad_norm": NaN,
|
96 |
+
"learning_rate": 8.247240241650918e-05,
|
97 |
+
"loss": 0.0,
|
98 |
+
"step": 21
|
99 |
+
},
|
100 |
+
{
|
101 |
+
"epoch": 0.00712430426716141,
|
102 |
+
"grad_norm": NaN,
|
103 |
+
"learning_rate": 7.269952498697734e-05,
|
104 |
+
"loss": 0.0,
|
105 |
+
"step": 24
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.0074211502782931356,
|
109 |
+
"eval_loss": NaN,
|
110 |
+
"eval_runtime": 424.5104,
|
111 |
+
"eval_samples_per_second": 13.366,
|
112 |
+
"eval_steps_per_second": 1.673,
|
113 |
+
"step": 25
|
114 |
}
|
115 |
],
|
116 |
"logging_steps": 3,
|
|
|
130 |
"attributes": {}
|
131 |
}
|
132 |
},
|
133 |
+
"total_flos": 3.625636096219546e+16,
|
134 |
"train_batch_size": 8,
|
135 |
"trial_name": null,
|
136 |
"trial_params": null
|