Training in progress, step 300, 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 sha256:6aa601b0ed7c047c51629b4697bd9b3b3b253ab59baa8ef813f51dc07e8d0086
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd0b45306fb0f13046378c8ab10279a5a2c885b110a05502410a7df6f7edcd58
|
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:be07d38b1962fdec7f7532dd57d81c7db0d75acda55cc9decf5cd7b2ec8586ce
|
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 sha256:9218b00f81cdc7c95a459552cbf25b1fbc52bb38d9c85044830d891ce9d12f83
|
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": 60,
|
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": 1.916,
|
60 |
"eval_steps_per_second": 0.24,
|
61 |
"step": 240
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
62 |
}
|
63 |
],
|
64 |
"logging_steps": 60,
|
65 |
"max_steps": 1011,
|
66 |
"num_train_epochs": 3,
|
67 |
"save_steps": 60,
|
68 |
-
"total_flos":
|
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": 60,
|
6 |
+
"global_step": 300,
|
7 |
"is_hyper_param_search": false,
|
8 |
"is_local_process_zero": true,
|
9 |
"is_world_process_zero": true,
|
|
|
59 |
"eval_samples_per_second": 1.916,
|
60 |
"eval_steps_per_second": 0.24,
|
61 |
"step": 240
|
62 |
+
},
|
63 |
+
{
|
64 |
+
"epoch": 0.89,
|
65 |
+
"learning_rate": 0.0002,
|
66 |
+
"loss": 0.633,
|
67 |
+
"step": 300
|
68 |
+
},
|
69 |
+
{
|
70 |
+
"epoch": 0.89,
|
71 |
+
"eval_runtime": 312.6613,
|
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": 4.98303246532608e+16,
|
82 |
"trial_name": null,
|
83 |
"trial_params": null
|
84 |
}
|