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 25191576
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c943bb9a943634621468e46c64ea459e5ce06abd54049694b3bb85b13059d57
|
3 |
size 25191576
|
last-checkpoint/optimizer.pt
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 50444805
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:058939e5f0d9ca64017411b6049b141a73228f398e75219ccadd2efac4824409
|
3 |
size 50444805
|
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:bd8a24a385cb71560f44319d7f96b3f5db0ea1776994de824c1079951b7246d9
|
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 sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
|
3 |
size 627
|
last-checkpoint/trainer_state.json
CHANGED
@@ -1,9 +1,9 @@
|
|
1 |
{
|
2 |
-
"best_metric": 1.
|
3 |
-
"best_model_checkpoint": "./outputs/checkpoint-
|
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,
|
@@ -63,6 +63,20 @@
|
|
63 |
"eval_samples_per_second": 5.454,
|
64 |
"eval_steps_per_second": 0.684,
|
65 |
"step": 400
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
66 |
}
|
67 |
],
|
68 |
"logging_steps": 100,
|
@@ -70,7 +84,7 @@
|
|
70 |
"num_input_tokens_seen": 0,
|
71 |
"num_train_epochs": 3,
|
72 |
"save_steps": 100,
|
73 |
-
"total_flos": 1.
|
74 |
"trial_name": null,
|
75 |
"trial_params": null
|
76 |
}
|
|
|
1 |
{
|
2 |
+
"best_metric": 1.0268442630767822,
|
3 |
+
"best_model_checkpoint": "./outputs/checkpoint-500",
|
4 |
+
"epoch": 0.6666666666666666,
|
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,
|
|
|
63 |
"eval_samples_per_second": 5.454,
|
64 |
"eval_steps_per_second": 0.684,
|
65 |
"step": 400
|
66 |
+
},
|
67 |
+
{
|
68 |
+
"epoch": 0.67,
|
69 |
+
"learning_rate": 0.0002,
|
70 |
+
"loss": 0.881,
|
71 |
+
"step": 500
|
72 |
+
},
|
73 |
+
{
|
74 |
+
"epoch": 0.67,
|
75 |
+
"eval_loss": 1.0268442630767822,
|
76 |
+
"eval_runtime": 352.5818,
|
77 |
+
"eval_samples_per_second": 5.474,
|
78 |
+
"eval_steps_per_second": 0.686,
|
79 |
+
"step": 500
|
80 |
}
|
81 |
],
|
82 |
"logging_steps": 100,
|
|
|
84 |
"num_input_tokens_seen": 0,
|
85 |
"num_train_epochs": 3,
|
86 |
"save_steps": 100,
|
87 |
+
"total_flos": 1.4137479027061555e+17,
|
88 |
"trial_name": null,
|
89 |
"trial_params": null
|
90 |
}
|