Training in progress, step 360, checkpoint
Browse files
last-checkpoint/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 40036040
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:281f2bb8ec37e1a497bb964267b9226b673aee794da31245de90e101585bc643
|
3 |
size 40036040
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 20524127
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:28e5076a26141edbfbbc85535f6acf5eb70e3ba8a51a9acf0496ebfcb7c0cc9f
|
3 |
size 20524127
|
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:d76006f795613301e629caaf1b5b74581e7f909e5940ad6e56c63203d03fea2a
|
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:ca62326b8ce4f54e20ff333143deee78dde2b7aae63a05f72ba09c1e1be44bee
|
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": 60,
|
6 |
-
"global_step":
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
@@ -72,13 +72,26 @@
|
|
72 |
"eval_samples_per_second": 1.919,
|
73 |
"eval_steps_per_second": 0.24,
|
74 |
"step": 300
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 60,
|
78 |
"max_steps": 1011,
|
79 |
"num_train_epochs": 3,
|
80 |
"save_steps": 60,
|
81 |
-
"total_flos":
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 1.0666666666666667,
|
5 |
"eval_steps": 60,
|
6 |
+
"global_step": 360,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
72 |
"eval_samples_per_second": 1.919,
|
73 |
"eval_steps_per_second": 0.24,
|
74 |
"step": 300
|
75 |
+
},
|
76 |
+
{
|
77 |
+
"epoch": 1.07,
|
78 |
+
"learning_rate": 0.0002,
|
79 |
+
"loss": 0.5895,
|
80 |
+
"step": 360
|
81 |
+
},
|
82 |
+
{
|
83 |
+
"epoch": 1.07,
|
84 |
+
"eval_runtime": 313.3051,
|
85 |
+
"eval_samples_per_second": 1.915,
|
86 |
+
"eval_steps_per_second": 0.239,
|
87 |
+
"step": 360
|
88 |
}
|
89 |
],
|
90 |
"logging_steps": 60,
|
91 |
"max_steps": 1011,
|
92 |
"num_train_epochs": 3,
|
93 |
"save_steps": 60,
|
94 |
+
"total_flos": 5.979638958391296e+16,
|
95 |
"trial_name": null,
|
96 |
"trial_params": null
|
97 |
}
|