Training in progress, step 700, 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 160285149
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dd03b0f621ace53dbb41365520e9d264fbf7b64c28301f32b12ea29ec6f3458
|
3 |
size 160285149
|
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 sha256:9e3465e167409675f6fa80c05bb553328847f7fae6e8fb2bf8345054d99a3074
|
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:f9c1417b81bbf5bb143eea752aa484a07d2d358bf6e2d354641b4850ccd6daf8
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
-
"epoch":
|
5 |
"eval_steps": 100,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -85,13 +85,26 @@
|
|
85 |
"eval_samples_per_second": 1.905,
|
86 |
"eval_steps_per_second": 0.239,
|
87 |
"step": 600
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 100,
|
91 |
"max_steps": 2025,
|
92 |
"num_train_epochs": 3,
|
93 |
"save_steps": 100,
|
94 |
-
"total_flos": 1.
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
97 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.037037037037037,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 700,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
85 |
"eval_samples_per_second": 1.905,
|
86 |
"eval_steps_per_second": 0.239,
|
87 |
"step": 600
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 1.04,
|
91 |
+
"learning_rate": 0.0,
|
92 |
+
"loss": 8.4979,
|
93 |
+
"step": 700
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 1.04,
|
97 |
+
"eval_runtime": 788.4314,
|
98 |
+
"eval_samples_per_second": 1.903,
|
99 |
+
"eval_steps_per_second": 0.238,
|
100 |
+
"step": 700
|
101 |
}
|
102 |
],
|
103 |
"logging_steps": 100,
|
104 |
"max_steps": 2025,
|
105 |
"num_train_epochs": 3,
|
106 |
"save_steps": 100,
|
107 |
+
"total_flos": 1.45768279179264e+17,
|
108 |
"trial_name": null,
|
109 |
"trial_params": null
|
110 |
}
|