Training in progress, step 500, 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 sha256:0630567af254fb722f18f20962e2d292016e1db3059159a816c630e4a96ce700
|
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 21689885
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:71358ad5633616a9c137d5907d19443b0609ec1006caec3dae3ded9e58bf1000
|
3 |
size 21689885
|
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 sha256:1585068ae312cf1f7de20a3e0c887200b496bb2e3d71c9dc1ead2932e720ab9b
|
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 sha256:6194b84235fa1ddba212fdee3897fa9782daf71c2c06168668c130b773308785
|
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": 0.
|
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,
|
@@ -59,13 +59,26 @@
|
|
59 |
"eval_samples_per_second": 1.775,
|
60 |
"eval_steps_per_second": 0.222,
|
61 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 100,
|
65 |
"max_steps": 1686,
|
66 |
"num_train_epochs": 3,
|
67 |
"save_steps": 100,
|
68 |
-
"total_flos": 1.
|
69 |
"trial_name": null,
|
70 |
"trial_params": null
|
71 |
}
|
|
|
1 |
{
|
2 |
"best_metric": null,
|
3 |
"best_model_checkpoint": null,
|
4 |
+
"epoch": 0.8888888888888888,
|
5 |
"eval_steps": 100,
|
6 |
+
"global_step": 500,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 1.775,
|
60 |
"eval_steps_per_second": 0.222,
|
61 |
"step": 400
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.89,
|
65 |
+
"learning_rate": 0.0001,
|
66 |
+
"loss": 0.6019,
|
67 |
+
"step": 500
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.89,
|
71 |
+
"eval_runtime": 1403.5405,
|
72 |
+
"eval_samples_per_second": 1.781,
|
73 |
+
"eval_steps_per_second": 0.223,
|
74 |
+
"step": 500
|
75 |
}
|
76 |
],
|
77 |
"logging_steps": 100,
|
78 |
"max_steps": 1686,
|
79 |
"num_train_epochs": 3,
|
80 |
"save_steps": 100,
|
81 |
+
"total_flos": 1.598722915958784e+17,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|