Training in progress, step 2125, 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 479005064
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65e5504061500ef7c4d8e7b72b76e3b6be0d719dcd518e9c46b23160aece9f85
|
| 3 |
size 479005064
|
last-checkpoint/optimizer.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 958299770
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d8bec8fb05cb894f67ecd78d5402233076a7866cb7ac37b429f0b4197d8cf40
|
| 3 |
size 958299770
|
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 sha256:89cc12b6ef889dd8c54df79f287f1c2fe76ea7edebf8cf05913b800380e92f69
|
| 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 sha256:823f545a614848455ef557579867553ca1e0ed28d34695c57c4a484f3da883fe
|
| 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": 0.
|
| 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,
|
|
@@ -2527,6 +2527,30 @@
|
|
| 2527 |
"reward_std": 0.4077802121639252,
|
| 2528 |
"rewards/custom_reward_logic_v4_batch_streak_dblog": 0.9238749846816063,
|
| 2529 |
"step": 2100
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2530 |
}
|
| 2531 |
],
|
| 2532 |
"logging_steps": 10,
|
|
|
|
| 1 |
{
|
| 2 |
"best_metric": null,
|
| 3 |
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.016924044886549167,
|
| 5 |
"eval_steps": 500,
|
| 6 |
+
"global_step": 2125,
|
| 7 |
"is_hyper_param_search": false,
|
| 8 |
"is_local_process_zero": true,
|
| 9 |
"is_world_process_zero": true,
|
|
|
|
| 2527 |
"reward_std": 0.4077802121639252,
|
| 2528 |
"rewards/custom_reward_logic_v4_batch_streak_dblog": 0.9238749846816063,
|
| 2529 |
"step": 2100
|
| 2530 |
+
},
|
| 2531 |
+
{
|
| 2532 |
+
"completion_length": 752.3625,
|
| 2533 |
+
"epoch": 0.016804581040291172,
|
| 2534 |
+
"grad_norm": 0.3764999210834503,
|
| 2535 |
+
"kl": 2.637471490353346,
|
| 2536 |
+
"learning_rate": 2.1910388661746495e-07,
|
| 2537 |
+
"loss": 0.1055,
|
| 2538 |
+
"reward": 1.1242249839007854,
|
| 2539 |
+
"reward_std": 0.5460393548011779,
|
| 2540 |
+
"rewards/custom_reward_logic_v4_batch_streak_dblog": 1.1242249839007854,
|
| 2541 |
+
"step": 2110
|
| 2542 |
+
},
|
| 2543 |
+
{
|
| 2544 |
+
"completion_length": 780.86875,
|
| 2545 |
+
"epoch": 0.01688422360446317,
|
| 2546 |
+
"grad_norm": 0.512827455997467,
|
| 2547 |
+
"kl": 2.5999191406182947,
|
| 2548 |
+
"learning_rate": 2.044597327993153e-07,
|
| 2549 |
+
"loss": 0.104,
|
| 2550 |
+
"reward": 1.0923499889671802,
|
| 2551 |
+
"reward_std": 0.4055012479424477,
|
| 2552 |
+
"rewards/custom_reward_logic_v4_batch_streak_dblog": 1.0923499889671802,
|
| 2553 |
+
"step": 2120
|
| 2554 |
}
|
| 2555 |
],
|
| 2556 |
"logging_steps": 10,
|