Training in progress, step 7500, checkpoint
Browse files
last-checkpoint/model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 242041896
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f5aeb1705eff30e408e7d69d68acf83742a837990575ea8909e1add1fd7430a
|
3 |
size 242041896
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 484163514
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:24530d6ce663eae131f1bfd7fc5bf2ec355b0ef342ab4768fae17fb20f93d1a9
|
3 |
size 484163514
|
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 sha256:9d8827135f388526a60488636968e475fb9d1d40fff7d295baf244173f4e4b38
|
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 sha256:5e942ee5aedceeb63e08a605ad1ad1eaaf1d5969d4deddb3cd371990891e61a2
|
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": 1.
|
5 |
"eval_steps": 500,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -101,13 +101,19 @@
|
|
101 |
"learning_rate": 0.0007852056476365869,
|
102 |
"loss": 0.5657,
|
103 |
"step": 7000
|
|
|
|
|
|
|
|
|
|
|
|
|
104 |
}
|
105 |
],
|
106 |
"logging_steps": 500,
|
107 |
"max_steps": 32580,
|
108 |
"num_train_epochs": 5,
|
109 |
"save_steps": 500,
|
110 |
-
"total_flos":
|
111 |
"trial_name": null,
|
112 |
"trial_params": null
|
113 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.1510128913443831,
|
5 |
"eval_steps": 500,
|
6 |
+
"global_step": 7500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
101 |
"learning_rate": 0.0007852056476365869,
|
102 |
"loss": 0.5657,
|
103 |
"step": 7000
|
104 |
+
},
|
105 |
+
{
|
106 |
+
"epoch": 1.15,
|
107 |
+
"learning_rate": 0.0007698588090853285,
|
108 |
+
"loss": 0.5623,
|
109 |
+
"step": 7500
|
110 |
}
|
111 |
],
|
112 |
"logging_steps": 500,
|
113 |
"max_steps": 32580,
|
114 |
"num_train_epochs": 5,
|
115 |
"save_steps": 500,
|
116 |
+
"total_flos": 3975931872411648.0,
|
117 |
"trial_name": null,
|
118 |
"trial_params": null
|
119 |
}
|