Muhammad Khalifa
commited on
Commit
·
5144cea
1
Parent(s):
f507001
add llama-2 13b plan model
Browse files- with_input/decomp_plan/llama-2-13b/best_model/adapter_config.json +21 -0
- with_input/decomp_plan/llama-2-13b/best_model/adapter_model.bin +3 -0
- with_input/decomp_plan/llama-2-13b/best_model/optimizer.pt +3 -0
- with_input/decomp_plan/llama-2-13b/best_model/rng_state.pth +3 -0
- with_input/decomp_plan/llama-2-13b/best_model/scheduler.pt +3 -0
- with_input/decomp_plan/llama-2-13b/best_model/trainer_state.json +2707 -0
- with_input/decomp_plan/llama-2-13b/best_model/training_args.bin +3 -0
with_input/decomp_plan/llama-2-13b/best_model/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"base_model_name_or_path": "NousResearch/Llama-2-13b-hf",
|
3 |
+
"bias": "none",
|
4 |
+
"enable_lora": null,
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"lora_alpha": 16,
|
9 |
+
"lora_dropout": 0.05,
|
10 |
+
"merge_weights": false,
|
11 |
+
"modules_to_save": null,
|
12 |
+
"peft_type": "LORA",
|
13 |
+
"r": 16,
|
14 |
+
"target_modules": [
|
15 |
+
"q_proj",
|
16 |
+
"k_proj",
|
17 |
+
"v_proj",
|
18 |
+
"o_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
with_input/decomp_plan/llama-2-13b/best_model/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4df4c37e29f48d13e71076397c361d796aff29eb70641871e1505192fb5b36b8
|
3 |
+
size 104973389
|
with_input/decomp_plan/llama-2-13b/best_model/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:402d37366953c60a16c122c91cc1fd60053b09b6fccaf16bc6d873c23a8eacd8
|
3 |
+
size 209984517
|
with_input/decomp_plan/llama-2-13b/best_model/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3a9eedb0e5a9bd306844dd23c2e8a2c80ae7ec69a838d6ffd25b4680665af411
|
3 |
+
size 14575
|
with_input/decomp_plan/llama-2-13b/best_model/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0ad33f45aefa5e68264ce2d2d7fc779dbf0d70e712368f1111eee883b5060e3
|
3 |
+
size 627
|
with_input/decomp_plan/llama-2-13b/best_model/trainer_state.json
ADDED
@@ -0,0 +1,2707 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": 0.7206348776817322,
|
3 |
+
"best_model_checkpoint": "checkpoints/instrucode/with_input/decomp_plan/llama-2-13b/checkpoint-4200",
|
4 |
+
"epoch": 2.7009646302250805,
|
5 |
+
"eval_steps": 200,
|
6 |
+
"global_step": 4200,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.01,
|
13 |
+
"learning_rate": 2.9999999999999997e-05,
|
14 |
+
"loss": 1.4995,
|
15 |
+
"step": 10
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.01,
|
19 |
+
"learning_rate": 5.9999999999999995e-05,
|
20 |
+
"loss": 1.4447,
|
21 |
+
"step": 20
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.02,
|
25 |
+
"learning_rate": 8.999999999999999e-05,
|
26 |
+
"loss": 1.2253,
|
27 |
+
"step": 30
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 0.03,
|
31 |
+
"learning_rate": 0.00011999999999999999,
|
32 |
+
"loss": 0.9599,
|
33 |
+
"step": 40
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 0.03,
|
37 |
+
"learning_rate": 0.00015,
|
38 |
+
"loss": 0.8987,
|
39 |
+
"step": 50
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 0.04,
|
43 |
+
"learning_rate": 0.00017999999999999998,
|
44 |
+
"loss": 0.8692,
|
45 |
+
"step": 60
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 0.05,
|
49 |
+
"learning_rate": 0.00020999999999999998,
|
50 |
+
"loss": 0.8347,
|
51 |
+
"step": 70
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 0.05,
|
55 |
+
"learning_rate": 0.00023999999999999998,
|
56 |
+
"loss": 0.8459,
|
57 |
+
"step": 80
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 0.06,
|
61 |
+
"learning_rate": 0.00027,
|
62 |
+
"loss": 0.835,
|
63 |
+
"step": 90
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 0.06,
|
67 |
+
"learning_rate": 0.0003,
|
68 |
+
"loss": 0.8249,
|
69 |
+
"step": 100
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 0.07,
|
73 |
+
"learning_rate": 0.00029960912052117263,
|
74 |
+
"loss": 0.8187,
|
75 |
+
"step": 110
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 0.08,
|
79 |
+
"learning_rate": 0.0002992182410423453,
|
80 |
+
"loss": 0.823,
|
81 |
+
"step": 120
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 0.08,
|
85 |
+
"learning_rate": 0.0002988273615635179,
|
86 |
+
"loss": 0.8365,
|
87 |
+
"step": 130
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 0.09,
|
91 |
+
"learning_rate": 0.00029843648208469054,
|
92 |
+
"loss": 0.8123,
|
93 |
+
"step": 140
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 0.1,
|
97 |
+
"learning_rate": 0.00029804560260586314,
|
98 |
+
"loss": 0.8179,
|
99 |
+
"step": 150
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 0.1,
|
103 |
+
"learning_rate": 0.0002976547231270358,
|
104 |
+
"loss": 0.8055,
|
105 |
+
"step": 160
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 0.11,
|
109 |
+
"learning_rate": 0.00029726384364820845,
|
110 |
+
"loss": 0.8009,
|
111 |
+
"step": 170
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 0.12,
|
115 |
+
"learning_rate": 0.00029687296416938105,
|
116 |
+
"loss": 0.8018,
|
117 |
+
"step": 180
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 0.12,
|
121 |
+
"learning_rate": 0.0002964820846905537,
|
122 |
+
"loss": 0.7961,
|
123 |
+
"step": 190
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 0.13,
|
127 |
+
"learning_rate": 0.00029609120521172636,
|
128 |
+
"loss": 0.8072,
|
129 |
+
"step": 200
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 0.13,
|
133 |
+
"eval_loss": 0.793488621711731,
|
134 |
+
"eval_runtime": 303.5091,
|
135 |
+
"eval_samples_per_second": 6.59,
|
136 |
+
"eval_steps_per_second": 0.824,
|
137 |
+
"step": 200
|
138 |
+
},
|
139 |
+
{
|
140 |
+
"epoch": 0.14,
|
141 |
+
"learning_rate": 0.000295700325732899,
|
142 |
+
"loss": 0.8007,
|
143 |
+
"step": 210
|
144 |
+
},
|
145 |
+
{
|
146 |
+
"epoch": 0.14,
|
147 |
+
"learning_rate": 0.0002953094462540716,
|
148 |
+
"loss": 0.8051,
|
149 |
+
"step": 220
|
150 |
+
},
|
151 |
+
{
|
152 |
+
"epoch": 0.15,
|
153 |
+
"learning_rate": 0.0002949185667752443,
|
154 |
+
"loss": 0.7764,
|
155 |
+
"step": 230
|
156 |
+
},
|
157 |
+
{
|
158 |
+
"epoch": 0.15,
|
159 |
+
"learning_rate": 0.00029452768729641693,
|
160 |
+
"loss": 0.8131,
|
161 |
+
"step": 240
|
162 |
+
},
|
163 |
+
{
|
164 |
+
"epoch": 0.16,
|
165 |
+
"learning_rate": 0.00029413680781758953,
|
166 |
+
"loss": 0.7833,
|
167 |
+
"step": 250
|
168 |
+
},
|
169 |
+
{
|
170 |
+
"epoch": 0.17,
|
171 |
+
"learning_rate": 0.0002937459283387622,
|
172 |
+
"loss": 0.779,
|
173 |
+
"step": 260
|
174 |
+
},
|
175 |
+
{
|
176 |
+
"epoch": 0.17,
|
177 |
+
"learning_rate": 0.00029335504885993484,
|
178 |
+
"loss": 0.7958,
|
179 |
+
"step": 270
|
180 |
+
},
|
181 |
+
{
|
182 |
+
"epoch": 0.18,
|
183 |
+
"learning_rate": 0.00029296416938110744,
|
184 |
+
"loss": 0.7782,
|
185 |
+
"step": 280
|
186 |
+
},
|
187 |
+
{
|
188 |
+
"epoch": 0.19,
|
189 |
+
"learning_rate": 0.0002925732899022801,
|
190 |
+
"loss": 0.7835,
|
191 |
+
"step": 290
|
192 |
+
},
|
193 |
+
{
|
194 |
+
"epoch": 0.19,
|
195 |
+
"learning_rate": 0.00029218241042345275,
|
196 |
+
"loss": 0.7805,
|
197 |
+
"step": 300
|
198 |
+
},
|
199 |
+
{
|
200 |
+
"epoch": 0.2,
|
201 |
+
"learning_rate": 0.0002917915309446254,
|
202 |
+
"loss": 0.7819,
|
203 |
+
"step": 310
|
204 |
+
},
|
205 |
+
{
|
206 |
+
"epoch": 0.21,
|
207 |
+
"learning_rate": 0.000291400651465798,
|
208 |
+
"loss": 0.7799,
|
209 |
+
"step": 320
|
210 |
+
},
|
211 |
+
{
|
212 |
+
"epoch": 0.21,
|
213 |
+
"learning_rate": 0.00029100977198697066,
|
214 |
+
"loss": 0.7681,
|
215 |
+
"step": 330
|
216 |
+
},
|
217 |
+
{
|
218 |
+
"epoch": 0.22,
|
219 |
+
"learning_rate": 0.00029061889250814327,
|
220 |
+
"loss": 0.8061,
|
221 |
+
"step": 340
|
222 |
+
},
|
223 |
+
{
|
224 |
+
"epoch": 0.23,
|
225 |
+
"learning_rate": 0.0002902280130293159,
|
226 |
+
"loss": 0.7578,
|
227 |
+
"step": 350
|
228 |
+
},
|
229 |
+
{
|
230 |
+
"epoch": 0.23,
|
231 |
+
"learning_rate": 0.0002898371335504886,
|
232 |
+
"loss": 0.7675,
|
233 |
+
"step": 360
|
234 |
+
},
|
235 |
+
{
|
236 |
+
"epoch": 0.24,
|
237 |
+
"learning_rate": 0.00028944625407166123,
|
238 |
+
"loss": 0.7766,
|
239 |
+
"step": 370
|
240 |
+
},
|
241 |
+
{
|
242 |
+
"epoch": 0.24,
|
243 |
+
"learning_rate": 0.0002890553745928339,
|
244 |
+
"loss": 0.7976,
|
245 |
+
"step": 380
|
246 |
+
},
|
247 |
+
{
|
248 |
+
"epoch": 0.25,
|
249 |
+
"learning_rate": 0.0002886644951140065,
|
250 |
+
"loss": 0.783,
|
251 |
+
"step": 390
|
252 |
+
},
|
253 |
+
{
|
254 |
+
"epoch": 0.26,
|
255 |
+
"learning_rate": 0.00028827361563517914,
|
256 |
+
"loss": 0.7746,
|
257 |
+
"step": 400
|
258 |
+
},
|
259 |
+
{
|
260 |
+
"epoch": 0.26,
|
261 |
+
"eval_loss": 0.7713018655776978,
|
262 |
+
"eval_runtime": 306.4904,
|
263 |
+
"eval_samples_per_second": 6.525,
|
264 |
+
"eval_steps_per_second": 0.816,
|
265 |
+
"step": 400
|
266 |
+
},
|
267 |
+
{
|
268 |
+
"epoch": 0.26,
|
269 |
+
"learning_rate": 0.00028788273615635174,
|
270 |
+
"loss": 0.7778,
|
271 |
+
"step": 410
|
272 |
+
},
|
273 |
+
{
|
274 |
+
"epoch": 0.27,
|
275 |
+
"learning_rate": 0.0002874918566775244,
|
276 |
+
"loss": 0.7719,
|
277 |
+
"step": 420
|
278 |
+
},
|
279 |
+
{
|
280 |
+
"epoch": 0.28,
|
281 |
+
"learning_rate": 0.00028710097719869705,
|
282 |
+
"loss": 0.7835,
|
283 |
+
"step": 430
|
284 |
+
},
|
285 |
+
{
|
286 |
+
"epoch": 0.28,
|
287 |
+
"learning_rate": 0.00028671009771986966,
|
288 |
+
"loss": 0.749,
|
289 |
+
"step": 440
|
290 |
+
},
|
291 |
+
{
|
292 |
+
"epoch": 0.29,
|
293 |
+
"learning_rate": 0.0002863192182410423,
|
294 |
+
"loss": 0.7693,
|
295 |
+
"step": 450
|
296 |
+
},
|
297 |
+
{
|
298 |
+
"epoch": 0.3,
|
299 |
+
"learning_rate": 0.00028592833876221497,
|
300 |
+
"loss": 0.7759,
|
301 |
+
"step": 460
|
302 |
+
},
|
303 |
+
{
|
304 |
+
"epoch": 0.3,
|
305 |
+
"learning_rate": 0.0002855374592833876,
|
306 |
+
"loss": 0.7614,
|
307 |
+
"step": 470
|
308 |
+
},
|
309 |
+
{
|
310 |
+
"epoch": 0.31,
|
311 |
+
"learning_rate": 0.0002851465798045602,
|
312 |
+
"loss": 0.763,
|
313 |
+
"step": 480
|
314 |
+
},
|
315 |
+
{
|
316 |
+
"epoch": 0.32,
|
317 |
+
"learning_rate": 0.0002847557003257329,
|
318 |
+
"loss": 0.7713,
|
319 |
+
"step": 490
|
320 |
+
},
|
321 |
+
{
|
322 |
+
"epoch": 0.32,
|
323 |
+
"learning_rate": 0.0002843648208469055,
|
324 |
+
"loss": 0.774,
|
325 |
+
"step": 500
|
326 |
+
},
|
327 |
+
{
|
328 |
+
"epoch": 0.33,
|
329 |
+
"learning_rate": 0.00028397394136807813,
|
330 |
+
"loss": 0.7697,
|
331 |
+
"step": 510
|
332 |
+
},
|
333 |
+
{
|
334 |
+
"epoch": 0.33,
|
335 |
+
"learning_rate": 0.0002835830618892508,
|
336 |
+
"loss": 0.7683,
|
337 |
+
"step": 520
|
338 |
+
},
|
339 |
+
{
|
340 |
+
"epoch": 0.34,
|
341 |
+
"learning_rate": 0.00028319218241042344,
|
342 |
+
"loss": 0.7788,
|
343 |
+
"step": 530
|
344 |
+
},
|
345 |
+
{
|
346 |
+
"epoch": 0.35,
|
347 |
+
"learning_rate": 0.00028280130293159605,
|
348 |
+
"loss": 0.7551,
|
349 |
+
"step": 540
|
350 |
+
},
|
351 |
+
{
|
352 |
+
"epoch": 0.35,
|
353 |
+
"learning_rate": 0.0002824104234527687,
|
354 |
+
"loss": 0.7747,
|
355 |
+
"step": 550
|
356 |
+
},
|
357 |
+
{
|
358 |
+
"epoch": 0.36,
|
359 |
+
"learning_rate": 0.00028201954397394136,
|
360 |
+
"loss": 0.7494,
|
361 |
+
"step": 560
|
362 |
+
},
|
363 |
+
{
|
364 |
+
"epoch": 0.37,
|
365 |
+
"learning_rate": 0.000281628664495114,
|
366 |
+
"loss": 0.7749,
|
367 |
+
"step": 570
|
368 |
+
},
|
369 |
+
{
|
370 |
+
"epoch": 0.37,
|
371 |
+
"learning_rate": 0.0002812377850162866,
|
372 |
+
"loss": 0.7375,
|
373 |
+
"step": 580
|
374 |
+
},
|
375 |
+
{
|
376 |
+
"epoch": 0.38,
|
377 |
+
"learning_rate": 0.00028084690553745927,
|
378 |
+
"loss": 0.7558,
|
379 |
+
"step": 590
|
380 |
+
},
|
381 |
+
{
|
382 |
+
"epoch": 0.39,
|
383 |
+
"learning_rate": 0.00028045602605863187,
|
384 |
+
"loss": 0.7596,
|
385 |
+
"step": 600
|
386 |
+
},
|
387 |
+
{
|
388 |
+
"epoch": 0.39,
|
389 |
+
"eval_loss": 0.7580611109733582,
|
390 |
+
"eval_runtime": 303.7189,
|
391 |
+
"eval_samples_per_second": 6.585,
|
392 |
+
"eval_steps_per_second": 0.823,
|
393 |
+
"step": 600
|
394 |
+
},
|
395 |
+
{
|
396 |
+
"epoch": 0.39,
|
397 |
+
"learning_rate": 0.0002800651465798045,
|
398 |
+
"loss": 0.774,
|
399 |
+
"step": 610
|
400 |
+
},
|
401 |
+
{
|
402 |
+
"epoch": 0.4,
|
403 |
+
"learning_rate": 0.0002796742671009772,
|
404 |
+
"loss": 0.7443,
|
405 |
+
"step": 620
|
406 |
+
},
|
407 |
+
{
|
408 |
+
"epoch": 0.41,
|
409 |
+
"learning_rate": 0.00027928338762214983,
|
410 |
+
"loss": 0.7566,
|
411 |
+
"step": 630
|
412 |
+
},
|
413 |
+
{
|
414 |
+
"epoch": 0.41,
|
415 |
+
"learning_rate": 0.00027889250814332244,
|
416 |
+
"loss": 0.758,
|
417 |
+
"step": 640
|
418 |
+
},
|
419 |
+
{
|
420 |
+
"epoch": 0.42,
|
421 |
+
"learning_rate": 0.0002785016286644951,
|
422 |
+
"loss": 0.7766,
|
423 |
+
"step": 650
|
424 |
+
},
|
425 |
+
{
|
426 |
+
"epoch": 0.42,
|
427 |
+
"learning_rate": 0.00027811074918566775,
|
428 |
+
"loss": 0.7652,
|
429 |
+
"step": 660
|
430 |
+
},
|
431 |
+
{
|
432 |
+
"epoch": 0.43,
|
433 |
+
"learning_rate": 0.00027771986970684035,
|
434 |
+
"loss": 0.7578,
|
435 |
+
"step": 670
|
436 |
+
},
|
437 |
+
{
|
438 |
+
"epoch": 0.44,
|
439 |
+
"learning_rate": 0.000277328990228013,
|
440 |
+
"loss": 0.7619,
|
441 |
+
"step": 680
|
442 |
+
},
|
443 |
+
{
|
444 |
+
"epoch": 0.44,
|
445 |
+
"learning_rate": 0.00027693811074918566,
|
446 |
+
"loss": 0.7523,
|
447 |
+
"step": 690
|
448 |
+
},
|
449 |
+
{
|
450 |
+
"epoch": 0.45,
|
451 |
+
"learning_rate": 0.00027654723127035826,
|
452 |
+
"loss": 0.7486,
|
453 |
+
"step": 700
|
454 |
+
},
|
455 |
+
{
|
456 |
+
"epoch": 0.46,
|
457 |
+
"learning_rate": 0.0002761563517915309,
|
458 |
+
"loss": 0.7454,
|
459 |
+
"step": 710
|
460 |
+
},
|
461 |
+
{
|
462 |
+
"epoch": 0.46,
|
463 |
+
"learning_rate": 0.00027576547231270357,
|
464 |
+
"loss": 0.7639,
|
465 |
+
"step": 720
|
466 |
+
},
|
467 |
+
{
|
468 |
+
"epoch": 0.47,
|
469 |
+
"learning_rate": 0.0002753745928338762,
|
470 |
+
"loss": 0.7692,
|
471 |
+
"step": 730
|
472 |
+
},
|
473 |
+
{
|
474 |
+
"epoch": 0.48,
|
475 |
+
"learning_rate": 0.0002749837133550488,
|
476 |
+
"loss": 0.7609,
|
477 |
+
"step": 740
|
478 |
+
},
|
479 |
+
{
|
480 |
+
"epoch": 0.48,
|
481 |
+
"learning_rate": 0.0002745928338762215,
|
482 |
+
"loss": 0.7729,
|
483 |
+
"step": 750
|
484 |
+
},
|
485 |
+
{
|
486 |
+
"epoch": 0.49,
|
487 |
+
"learning_rate": 0.0002742019543973941,
|
488 |
+
"loss": 0.7515,
|
489 |
+
"step": 760
|
490 |
+
},
|
491 |
+
{
|
492 |
+
"epoch": 0.5,
|
493 |
+
"learning_rate": 0.00027381107491856674,
|
494 |
+
"loss": 0.746,
|
495 |
+
"step": 770
|
496 |
+
},
|
497 |
+
{
|
498 |
+
"epoch": 0.5,
|
499 |
+
"learning_rate": 0.0002734201954397394,
|
500 |
+
"loss": 0.7406,
|
501 |
+
"step": 780
|
502 |
+
},
|
503 |
+
{
|
504 |
+
"epoch": 0.51,
|
505 |
+
"learning_rate": 0.00027302931596091205,
|
506 |
+
"loss": 0.7529,
|
507 |
+
"step": 790
|
508 |
+
},
|
509 |
+
{
|
510 |
+
"epoch": 0.51,
|
511 |
+
"learning_rate": 0.00027263843648208465,
|
512 |
+
"loss": 0.7213,
|
513 |
+
"step": 800
|
514 |
+
},
|
515 |
+
{
|
516 |
+
"epoch": 0.51,
|
517 |
+
"eval_loss": 0.7531036138534546,
|
518 |
+
"eval_runtime": 304.2051,
|
519 |
+
"eval_samples_per_second": 6.575,
|
520 |
+
"eval_steps_per_second": 0.822,
|
521 |
+
"step": 800
|
522 |
+
},
|
523 |
+
{
|
524 |
+
"epoch": 0.52,
|
525 |
+
"learning_rate": 0.0002722475570032573,
|
526 |
+
"loss": 0.7395,
|
527 |
+
"step": 810
|
528 |
+
},
|
529 |
+
{
|
530 |
+
"epoch": 0.53,
|
531 |
+
"learning_rate": 0.00027185667752442996,
|
532 |
+
"loss": 0.7465,
|
533 |
+
"step": 820
|
534 |
+
},
|
535 |
+
{
|
536 |
+
"epoch": 0.53,
|
537 |
+
"learning_rate": 0.0002714657980456026,
|
538 |
+
"loss": 0.7671,
|
539 |
+
"step": 830
|
540 |
+
},
|
541 |
+
{
|
542 |
+
"epoch": 0.54,
|
543 |
+
"learning_rate": 0.0002710749185667752,
|
544 |
+
"loss": 0.7289,
|
545 |
+
"step": 840
|
546 |
+
},
|
547 |
+
{
|
548 |
+
"epoch": 0.55,
|
549 |
+
"learning_rate": 0.00027068403908794787,
|
550 |
+
"loss": 0.7453,
|
551 |
+
"step": 850
|
552 |
+
},
|
553 |
+
{
|
554 |
+
"epoch": 0.55,
|
555 |
+
"learning_rate": 0.00027029315960912047,
|
556 |
+
"loss": 0.7409,
|
557 |
+
"step": 860
|
558 |
+
},
|
559 |
+
{
|
560 |
+
"epoch": 0.56,
|
561 |
+
"learning_rate": 0.0002699022801302931,
|
562 |
+
"loss": 0.7635,
|
563 |
+
"step": 870
|
564 |
+
},
|
565 |
+
{
|
566 |
+
"epoch": 0.57,
|
567 |
+
"learning_rate": 0.0002695114006514658,
|
568 |
+
"loss": 0.7356,
|
569 |
+
"step": 880
|
570 |
+
},
|
571 |
+
{
|
572 |
+
"epoch": 0.57,
|
573 |
+
"learning_rate": 0.00026912052117263844,
|
574 |
+
"loss": 0.7526,
|
575 |
+
"step": 890
|
576 |
+
},
|
577 |
+
{
|
578 |
+
"epoch": 0.58,
|
579 |
+
"learning_rate": 0.00026872964169381104,
|
580 |
+
"loss": 0.7664,
|
581 |
+
"step": 900
|
582 |
+
},
|
583 |
+
{
|
584 |
+
"epoch": 0.59,
|
585 |
+
"learning_rate": 0.0002683387622149837,
|
586 |
+
"loss": 0.7509,
|
587 |
+
"step": 910
|
588 |
+
},
|
589 |
+
{
|
590 |
+
"epoch": 0.59,
|
591 |
+
"learning_rate": 0.00026794788273615635,
|
592 |
+
"loss": 0.7422,
|
593 |
+
"step": 920
|
594 |
+
},
|
595 |
+
{
|
596 |
+
"epoch": 0.6,
|
597 |
+
"learning_rate": 0.00026755700325732895,
|
598 |
+
"loss": 0.7612,
|
599 |
+
"step": 930
|
600 |
+
},
|
601 |
+
{
|
602 |
+
"epoch": 0.6,
|
603 |
+
"learning_rate": 0.0002671661237785016,
|
604 |
+
"loss": 0.7545,
|
605 |
+
"step": 940
|
606 |
+
},
|
607 |
+
{
|
608 |
+
"epoch": 0.61,
|
609 |
+
"learning_rate": 0.0002667752442996742,
|
610 |
+
"loss": 0.7318,
|
611 |
+
"step": 950
|
612 |
+
},
|
613 |
+
{
|
614 |
+
"epoch": 0.62,
|
615 |
+
"learning_rate": 0.00026638436482084686,
|
616 |
+
"loss": 0.7393,
|
617 |
+
"step": 960
|
618 |
+
},
|
619 |
+
{
|
620 |
+
"epoch": 0.62,
|
621 |
+
"learning_rate": 0.0002659934853420195,
|
622 |
+
"loss": 0.7543,
|
623 |
+
"step": 970
|
624 |
+
},
|
625 |
+
{
|
626 |
+
"epoch": 0.63,
|
627 |
+
"learning_rate": 0.00026560260586319217,
|
628 |
+
"loss": 0.7329,
|
629 |
+
"step": 980
|
630 |
+
},
|
631 |
+
{
|
632 |
+
"epoch": 0.64,
|
633 |
+
"learning_rate": 0.0002652117263843648,
|
634 |
+
"loss": 0.747,
|
635 |
+
"step": 990
|
636 |
+
},
|
637 |
+
{
|
638 |
+
"epoch": 0.64,
|
639 |
+
"learning_rate": 0.00026482084690553743,
|
640 |
+
"loss": 0.7519,
|
641 |
+
"step": 1000
|
642 |
+
},
|
643 |
+
{
|
644 |
+
"epoch": 0.64,
|
645 |
+
"eval_loss": 0.7442443370819092,
|
646 |
+
"eval_runtime": 308.0159,
|
647 |
+
"eval_samples_per_second": 6.493,
|
648 |
+
"eval_steps_per_second": 0.812,
|
649 |
+
"step": 1000
|
650 |
+
},
|
651 |
+
{
|
652 |
+
"epoch": 0.65,
|
653 |
+
"learning_rate": 0.0002644299674267101,
|
654 |
+
"loss": 0.738,
|
655 |
+
"step": 1010
|
656 |
+
},
|
657 |
+
{
|
658 |
+
"epoch": 0.66,
|
659 |
+
"learning_rate": 0.0002640390879478827,
|
660 |
+
"loss": 0.7544,
|
661 |
+
"step": 1020
|
662 |
+
},
|
663 |
+
{
|
664 |
+
"epoch": 0.66,
|
665 |
+
"learning_rate": 0.00026364820846905534,
|
666 |
+
"loss": 0.7336,
|
667 |
+
"step": 1030
|
668 |
+
},
|
669 |
+
{
|
670 |
+
"epoch": 0.67,
|
671 |
+
"learning_rate": 0.000263257328990228,
|
672 |
+
"loss": 0.7345,
|
673 |
+
"step": 1040
|
674 |
+
},
|
675 |
+
{
|
676 |
+
"epoch": 0.68,
|
677 |
+
"learning_rate": 0.0002628664495114006,
|
678 |
+
"loss": 0.7431,
|
679 |
+
"step": 1050
|
680 |
+
},
|
681 |
+
{
|
682 |
+
"epoch": 0.68,
|
683 |
+
"learning_rate": 0.00026247557003257325,
|
684 |
+
"loss": 0.7625,
|
685 |
+
"step": 1060
|
686 |
+
},
|
687 |
+
{
|
688 |
+
"epoch": 0.69,
|
689 |
+
"learning_rate": 0.0002620846905537459,
|
690 |
+
"loss": 0.7267,
|
691 |
+
"step": 1070
|
692 |
+
},
|
693 |
+
{
|
694 |
+
"epoch": 0.69,
|
695 |
+
"learning_rate": 0.00026169381107491856,
|
696 |
+
"loss": 0.7438,
|
697 |
+
"step": 1080
|
698 |
+
},
|
699 |
+
{
|
700 |
+
"epoch": 0.7,
|
701 |
+
"learning_rate": 0.0002613029315960912,
|
702 |
+
"loss": 0.7245,
|
703 |
+
"step": 1090
|
704 |
+
},
|
705 |
+
{
|
706 |
+
"epoch": 0.71,
|
707 |
+
"learning_rate": 0.0002609120521172638,
|
708 |
+
"loss": 0.7566,
|
709 |
+
"step": 1100
|
710 |
+
},
|
711 |
+
{
|
712 |
+
"epoch": 0.71,
|
713 |
+
"learning_rate": 0.0002605211726384365,
|
714 |
+
"loss": 0.7371,
|
715 |
+
"step": 1110
|
716 |
+
},
|
717 |
+
{
|
718 |
+
"epoch": 0.72,
|
719 |
+
"learning_rate": 0.0002601302931596091,
|
720 |
+
"loss": 0.7389,
|
721 |
+
"step": 1120
|
722 |
+
},
|
723 |
+
{
|
724 |
+
"epoch": 0.73,
|
725 |
+
"learning_rate": 0.00025973941368078173,
|
726 |
+
"loss": 0.7326,
|
727 |
+
"step": 1130
|
728 |
+
},
|
729 |
+
{
|
730 |
+
"epoch": 0.73,
|
731 |
+
"learning_rate": 0.0002593485342019544,
|
732 |
+
"loss": 0.7092,
|
733 |
+
"step": 1140
|
734 |
+
},
|
735 |
+
{
|
736 |
+
"epoch": 0.74,
|
737 |
+
"learning_rate": 0.00025895765472312704,
|
738 |
+
"loss": 0.7479,
|
739 |
+
"step": 1150
|
740 |
+
},
|
741 |
+
{
|
742 |
+
"epoch": 0.75,
|
743 |
+
"learning_rate": 0.00025856677524429964,
|
744 |
+
"loss": 0.7289,
|
745 |
+
"step": 1160
|
746 |
+
},
|
747 |
+
{
|
748 |
+
"epoch": 0.75,
|
749 |
+
"learning_rate": 0.0002581758957654723,
|
750 |
+
"loss": 0.7506,
|
751 |
+
"step": 1170
|
752 |
+
},
|
753 |
+
{
|
754 |
+
"epoch": 0.76,
|
755 |
+
"learning_rate": 0.00025778501628664495,
|
756 |
+
"loss": 0.7388,
|
757 |
+
"step": 1180
|
758 |
+
},
|
759 |
+
{
|
760 |
+
"epoch": 0.77,
|
761 |
+
"learning_rate": 0.00025739413680781755,
|
762 |
+
"loss": 0.756,
|
763 |
+
"step": 1190
|
764 |
+
},
|
765 |
+
{
|
766 |
+
"epoch": 0.77,
|
767 |
+
"learning_rate": 0.0002570032573289902,
|
768 |
+
"loss": 0.7269,
|
769 |
+
"step": 1200
|
770 |
+
},
|
771 |
+
{
|
772 |
+
"epoch": 0.77,
|
773 |
+
"eval_loss": 0.7402953505516052,
|
774 |
+
"eval_runtime": 304.0596,
|
775 |
+
"eval_samples_per_second": 6.578,
|
776 |
+
"eval_steps_per_second": 0.822,
|
777 |
+
"step": 1200
|
778 |
+
},
|
779 |
+
{
|
780 |
+
"epoch": 0.78,
|
781 |
+
"learning_rate": 0.0002566123778501628,
|
782 |
+
"loss": 0.729,
|
783 |
+
"step": 1210
|
784 |
+
},
|
785 |
+
{
|
786 |
+
"epoch": 0.78,
|
787 |
+
"learning_rate": 0.00025622149837133546,
|
788 |
+
"loss": 0.7473,
|
789 |
+
"step": 1220
|
790 |
+
},
|
791 |
+
{
|
792 |
+
"epoch": 0.79,
|
793 |
+
"learning_rate": 0.0002558306188925081,
|
794 |
+
"loss": 0.7174,
|
795 |
+
"step": 1230
|
796 |
+
},
|
797 |
+
{
|
798 |
+
"epoch": 0.8,
|
799 |
+
"learning_rate": 0.0002554397394136808,
|
800 |
+
"loss": 0.7526,
|
801 |
+
"step": 1240
|
802 |
+
},
|
803 |
+
{
|
804 |
+
"epoch": 0.8,
|
805 |
+
"learning_rate": 0.00025504885993485343,
|
806 |
+
"loss": 0.7502,
|
807 |
+
"step": 1250
|
808 |
+
},
|
809 |
+
{
|
810 |
+
"epoch": 0.81,
|
811 |
+
"learning_rate": 0.00025465798045602603,
|
812 |
+
"loss": 0.7335,
|
813 |
+
"step": 1260
|
814 |
+
},
|
815 |
+
{
|
816 |
+
"epoch": 0.82,
|
817 |
+
"learning_rate": 0.0002542671009771987,
|
818 |
+
"loss": 0.7452,
|
819 |
+
"step": 1270
|
820 |
+
},
|
821 |
+
{
|
822 |
+
"epoch": 0.82,
|
823 |
+
"learning_rate": 0.0002538762214983713,
|
824 |
+
"loss": 0.7534,
|
825 |
+
"step": 1280
|
826 |
+
},
|
827 |
+
{
|
828 |
+
"epoch": 0.83,
|
829 |
+
"learning_rate": 0.00025348534201954394,
|
830 |
+
"loss": 0.7408,
|
831 |
+
"step": 1290
|
832 |
+
},
|
833 |
+
{
|
834 |
+
"epoch": 0.84,
|
835 |
+
"learning_rate": 0.0002530944625407166,
|
836 |
+
"loss": 0.7582,
|
837 |
+
"step": 1300
|
838 |
+
},
|
839 |
+
{
|
840 |
+
"epoch": 0.84,
|
841 |
+
"learning_rate": 0.0002527035830618892,
|
842 |
+
"loss": 0.7575,
|
843 |
+
"step": 1310
|
844 |
+
},
|
845 |
+
{
|
846 |
+
"epoch": 0.85,
|
847 |
+
"learning_rate": 0.00025231270358306185,
|
848 |
+
"loss": 0.7391,
|
849 |
+
"step": 1320
|
850 |
+
},
|
851 |
+
{
|
852 |
+
"epoch": 0.86,
|
853 |
+
"learning_rate": 0.0002519218241042345,
|
854 |
+
"loss": 0.7486,
|
855 |
+
"step": 1330
|
856 |
+
},
|
857 |
+
{
|
858 |
+
"epoch": 0.86,
|
859 |
+
"learning_rate": 0.00025153094462540716,
|
860 |
+
"loss": 0.7227,
|
861 |
+
"step": 1340
|
862 |
+
},
|
863 |
+
{
|
864 |
+
"epoch": 0.87,
|
865 |
+
"learning_rate": 0.0002511400651465798,
|
866 |
+
"loss": 0.7511,
|
867 |
+
"step": 1350
|
868 |
+
},
|
869 |
+
{
|
870 |
+
"epoch": 0.87,
|
871 |
+
"learning_rate": 0.0002507491856677524,
|
872 |
+
"loss": 0.7442,
|
873 |
+
"step": 1360
|
874 |
+
},
|
875 |
+
{
|
876 |
+
"epoch": 0.88,
|
877 |
+
"learning_rate": 0.0002503583061889251,
|
878 |
+
"loss": 0.7544,
|
879 |
+
"step": 1370
|
880 |
+
},
|
881 |
+
{
|
882 |
+
"epoch": 0.89,
|
883 |
+
"learning_rate": 0.0002499674267100977,
|
884 |
+
"loss": 0.7456,
|
885 |
+
"step": 1380
|
886 |
+
},
|
887 |
+
{
|
888 |
+
"epoch": 0.89,
|
889 |
+
"learning_rate": 0.00024957654723127033,
|
890 |
+
"loss": 0.7363,
|
891 |
+
"step": 1390
|
892 |
+
},
|
893 |
+
{
|
894 |
+
"epoch": 0.9,
|
895 |
+
"learning_rate": 0.000249185667752443,
|
896 |
+
"loss": 0.7289,
|
897 |
+
"step": 1400
|
898 |
+
},
|
899 |
+
{
|
900 |
+
"epoch": 0.9,
|
901 |
+
"eval_loss": 0.7365428805351257,
|
902 |
+
"eval_runtime": 304.0198,
|
903 |
+
"eval_samples_per_second": 6.579,
|
904 |
+
"eval_steps_per_second": 0.822,
|
905 |
+
"step": 1400
|
906 |
+
},
|
907 |
+
{
|
908 |
+
"epoch": 0.91,
|
909 |
+
"learning_rate": 0.0002487947882736156,
|
910 |
+
"loss": 0.7376,
|
911 |
+
"step": 1410
|
912 |
+
},
|
913 |
+
{
|
914 |
+
"epoch": 0.91,
|
915 |
+
"learning_rate": 0.00024840390879478824,
|
916 |
+
"loss": 0.7535,
|
917 |
+
"step": 1420
|
918 |
+
},
|
919 |
+
{
|
920 |
+
"epoch": 0.92,
|
921 |
+
"learning_rate": 0.0002480130293159609,
|
922 |
+
"loss": 0.7152,
|
923 |
+
"step": 1430
|
924 |
+
},
|
925 |
+
{
|
926 |
+
"epoch": 0.93,
|
927 |
+
"learning_rate": 0.00024762214983713355,
|
928 |
+
"loss": 0.7264,
|
929 |
+
"step": 1440
|
930 |
+
},
|
931 |
+
{
|
932 |
+
"epoch": 0.93,
|
933 |
+
"learning_rate": 0.00024723127035830616,
|
934 |
+
"loss": 0.7113,
|
935 |
+
"step": 1450
|
936 |
+
},
|
937 |
+
{
|
938 |
+
"epoch": 0.94,
|
939 |
+
"learning_rate": 0.0002468403908794788,
|
940 |
+
"loss": 0.7281,
|
941 |
+
"step": 1460
|
942 |
+
},
|
943 |
+
{
|
944 |
+
"epoch": 0.95,
|
945 |
+
"learning_rate": 0.0002464495114006514,
|
946 |
+
"loss": 0.7356,
|
947 |
+
"step": 1470
|
948 |
+
},
|
949 |
+
{
|
950 |
+
"epoch": 0.95,
|
951 |
+
"learning_rate": 0.00024605863192182407,
|
952 |
+
"loss": 0.7212,
|
953 |
+
"step": 1480
|
954 |
+
},
|
955 |
+
{
|
956 |
+
"epoch": 0.96,
|
957 |
+
"learning_rate": 0.0002456677524429967,
|
958 |
+
"loss": 0.7294,
|
959 |
+
"step": 1490
|
960 |
+
},
|
961 |
+
{
|
962 |
+
"epoch": 0.96,
|
963 |
+
"learning_rate": 0.0002452768729641694,
|
964 |
+
"loss": 0.7432,
|
965 |
+
"step": 1500
|
966 |
+
},
|
967 |
+
{
|
968 |
+
"epoch": 0.97,
|
969 |
+
"learning_rate": 0.00024488599348534203,
|
970 |
+
"loss": 0.7416,
|
971 |
+
"step": 1510
|
972 |
+
},
|
973 |
+
{
|
974 |
+
"epoch": 0.98,
|
975 |
+
"learning_rate": 0.00024449511400651463,
|
976 |
+
"loss": 0.7371,
|
977 |
+
"step": 1520
|
978 |
+
},
|
979 |
+
{
|
980 |
+
"epoch": 0.98,
|
981 |
+
"learning_rate": 0.00024410423452768726,
|
982 |
+
"loss": 0.76,
|
983 |
+
"step": 1530
|
984 |
+
},
|
985 |
+
{
|
986 |
+
"epoch": 0.99,
|
987 |
+
"learning_rate": 0.00024371335504885992,
|
988 |
+
"loss": 0.7283,
|
989 |
+
"step": 1540
|
990 |
+
},
|
991 |
+
{
|
992 |
+
"epoch": 1.0,
|
993 |
+
"learning_rate": 0.00024332247557003257,
|
994 |
+
"loss": 0.7315,
|
995 |
+
"step": 1550
|
996 |
+
},
|
997 |
+
{
|
998 |
+
"epoch": 1.0,
|
999 |
+
"learning_rate": 0.0002429315960912052,
|
1000 |
+
"loss": 0.7212,
|
1001 |
+
"step": 1560
|
1002 |
+
},
|
1003 |
+
{
|
1004 |
+
"epoch": 1.01,
|
1005 |
+
"learning_rate": 0.00024254071661237783,
|
1006 |
+
"loss": 0.7209,
|
1007 |
+
"step": 1570
|
1008 |
+
},
|
1009 |
+
{
|
1010 |
+
"epoch": 1.02,
|
1011 |
+
"learning_rate": 0.00024214983713355046,
|
1012 |
+
"loss": 0.7333,
|
1013 |
+
"step": 1580
|
1014 |
+
},
|
1015 |
+
{
|
1016 |
+
"epoch": 1.02,
|
1017 |
+
"learning_rate": 0.0002417589576547231,
|
1018 |
+
"loss": 0.7179,
|
1019 |
+
"step": 1590
|
1020 |
+
},
|
1021 |
+
{
|
1022 |
+
"epoch": 1.03,
|
1023 |
+
"learning_rate": 0.00024136807817589574,
|
1024 |
+
"loss": 0.7051,
|
1025 |
+
"step": 1600
|
1026 |
+
},
|
1027 |
+
{
|
1028 |
+
"epoch": 1.03,
|
1029 |
+
"eval_loss": 0.7355972528457642,
|
1030 |
+
"eval_runtime": 304.1098,
|
1031 |
+
"eval_samples_per_second": 6.577,
|
1032 |
+
"eval_steps_per_second": 0.822,
|
1033 |
+
"step": 1600
|
1034 |
+
},
|
1035 |
+
{
|
1036 |
+
"epoch": 1.04,
|
1037 |
+
"learning_rate": 0.0002409771986970684,
|
1038 |
+
"loss": 0.6873,
|
1039 |
+
"step": 1610
|
1040 |
+
},
|
1041 |
+
{
|
1042 |
+
"epoch": 1.04,
|
1043 |
+
"learning_rate": 0.000240586319218241,
|
1044 |
+
"loss": 0.7022,
|
1045 |
+
"step": 1620
|
1046 |
+
},
|
1047 |
+
{
|
1048 |
+
"epoch": 1.05,
|
1049 |
+
"learning_rate": 0.00024019543973941365,
|
1050 |
+
"loss": 0.7307,
|
1051 |
+
"step": 1630
|
1052 |
+
},
|
1053 |
+
{
|
1054 |
+
"epoch": 1.05,
|
1055 |
+
"learning_rate": 0.0002398045602605863,
|
1056 |
+
"loss": 0.7194,
|
1057 |
+
"step": 1640
|
1058 |
+
},
|
1059 |
+
{
|
1060 |
+
"epoch": 1.06,
|
1061 |
+
"learning_rate": 0.00023941368078175893,
|
1062 |
+
"loss": 0.7111,
|
1063 |
+
"step": 1650
|
1064 |
+
},
|
1065 |
+
{
|
1066 |
+
"epoch": 1.07,
|
1067 |
+
"learning_rate": 0.0002390228013029316,
|
1068 |
+
"loss": 0.7039,
|
1069 |
+
"step": 1660
|
1070 |
+
},
|
1071 |
+
{
|
1072 |
+
"epoch": 1.07,
|
1073 |
+
"learning_rate": 0.0002386319218241042,
|
1074 |
+
"loss": 0.7046,
|
1075 |
+
"step": 1670
|
1076 |
+
},
|
1077 |
+
{
|
1078 |
+
"epoch": 1.08,
|
1079 |
+
"learning_rate": 0.00023824104234527685,
|
1080 |
+
"loss": 0.6964,
|
1081 |
+
"step": 1680
|
1082 |
+
},
|
1083 |
+
{
|
1084 |
+
"epoch": 1.09,
|
1085 |
+
"learning_rate": 0.0002378501628664495,
|
1086 |
+
"loss": 0.713,
|
1087 |
+
"step": 1690
|
1088 |
+
},
|
1089 |
+
{
|
1090 |
+
"epoch": 1.09,
|
1091 |
+
"learning_rate": 0.00023745928338762213,
|
1092 |
+
"loss": 0.6813,
|
1093 |
+
"step": 1700
|
1094 |
+
},
|
1095 |
+
{
|
1096 |
+
"epoch": 1.1,
|
1097 |
+
"learning_rate": 0.00023706840390879478,
|
1098 |
+
"loss": 0.7454,
|
1099 |
+
"step": 1710
|
1100 |
+
},
|
1101 |
+
{
|
1102 |
+
"epoch": 1.11,
|
1103 |
+
"learning_rate": 0.00023667752442996739,
|
1104 |
+
"loss": 0.7051,
|
1105 |
+
"step": 1720
|
1106 |
+
},
|
1107 |
+
{
|
1108 |
+
"epoch": 1.11,
|
1109 |
+
"learning_rate": 0.00023628664495114004,
|
1110 |
+
"loss": 0.7157,
|
1111 |
+
"step": 1730
|
1112 |
+
},
|
1113 |
+
{
|
1114 |
+
"epoch": 1.12,
|
1115 |
+
"learning_rate": 0.00023589576547231267,
|
1116 |
+
"loss": 0.7034,
|
1117 |
+
"step": 1740
|
1118 |
+
},
|
1119 |
+
{
|
1120 |
+
"epoch": 1.13,
|
1121 |
+
"learning_rate": 0.00023550488599348532,
|
1122 |
+
"loss": 0.6927,
|
1123 |
+
"step": 1750
|
1124 |
+
},
|
1125 |
+
{
|
1126 |
+
"epoch": 1.13,
|
1127 |
+
"learning_rate": 0.00023511400651465798,
|
1128 |
+
"loss": 0.7141,
|
1129 |
+
"step": 1760
|
1130 |
+
},
|
1131 |
+
{
|
1132 |
+
"epoch": 1.14,
|
1133 |
+
"learning_rate": 0.00023472312703583058,
|
1134 |
+
"loss": 0.7061,
|
1135 |
+
"step": 1770
|
1136 |
+
},
|
1137 |
+
{
|
1138 |
+
"epoch": 1.14,
|
1139 |
+
"learning_rate": 0.00023433224755700324,
|
1140 |
+
"loss": 0.7006,
|
1141 |
+
"step": 1780
|
1142 |
+
},
|
1143 |
+
{
|
1144 |
+
"epoch": 1.15,
|
1145 |
+
"learning_rate": 0.00023394136807817586,
|
1146 |
+
"loss": 0.6999,
|
1147 |
+
"step": 1790
|
1148 |
+
},
|
1149 |
+
{
|
1150 |
+
"epoch": 1.16,
|
1151 |
+
"learning_rate": 0.00023355048859934852,
|
1152 |
+
"loss": 0.6925,
|
1153 |
+
"step": 1800
|
1154 |
+
},
|
1155 |
+
{
|
1156 |
+
"epoch": 1.16,
|
1157 |
+
"eval_loss": 0.7322565913200378,
|
1158 |
+
"eval_runtime": 304.7894,
|
1159 |
+
"eval_samples_per_second": 6.562,
|
1160 |
+
"eval_steps_per_second": 0.82,
|
1161 |
+
"step": 1800
|
1162 |
+
},
|
1163 |
+
{
|
1164 |
+
"epoch": 1.16,
|
1165 |
+
"learning_rate": 0.00023315960912052117,
|
1166 |
+
"loss": 0.7099,
|
1167 |
+
"step": 1810
|
1168 |
+
},
|
1169 |
+
{
|
1170 |
+
"epoch": 1.17,
|
1171 |
+
"learning_rate": 0.00023276872964169378,
|
1172 |
+
"loss": 0.7004,
|
1173 |
+
"step": 1820
|
1174 |
+
},
|
1175 |
+
{
|
1176 |
+
"epoch": 1.18,
|
1177 |
+
"learning_rate": 0.00023237785016286643,
|
1178 |
+
"loss": 0.7131,
|
1179 |
+
"step": 1830
|
1180 |
+
},
|
1181 |
+
{
|
1182 |
+
"epoch": 1.18,
|
1183 |
+
"learning_rate": 0.00023198697068403906,
|
1184 |
+
"loss": 0.7261,
|
1185 |
+
"step": 1840
|
1186 |
+
},
|
1187 |
+
{
|
1188 |
+
"epoch": 1.19,
|
1189 |
+
"learning_rate": 0.00023159609120521171,
|
1190 |
+
"loss": 0.7246,
|
1191 |
+
"step": 1850
|
1192 |
+
},
|
1193 |
+
{
|
1194 |
+
"epoch": 1.2,
|
1195 |
+
"learning_rate": 0.00023120521172638434,
|
1196 |
+
"loss": 0.6893,
|
1197 |
+
"step": 1860
|
1198 |
+
},
|
1199 |
+
{
|
1200 |
+
"epoch": 1.2,
|
1201 |
+
"learning_rate": 0.000230814332247557,
|
1202 |
+
"loss": 0.7016,
|
1203 |
+
"step": 1870
|
1204 |
+
},
|
1205 |
+
{
|
1206 |
+
"epoch": 1.21,
|
1207 |
+
"learning_rate": 0.0002304234527687296,
|
1208 |
+
"loss": 0.7046,
|
1209 |
+
"step": 1880
|
1210 |
+
},
|
1211 |
+
{
|
1212 |
+
"epoch": 1.22,
|
1213 |
+
"learning_rate": 0.00023003257328990225,
|
1214 |
+
"loss": 0.7215,
|
1215 |
+
"step": 1890
|
1216 |
+
},
|
1217 |
+
{
|
1218 |
+
"epoch": 1.22,
|
1219 |
+
"learning_rate": 0.0002296416938110749,
|
1220 |
+
"loss": 0.6976,
|
1221 |
+
"step": 1900
|
1222 |
+
},
|
1223 |
+
{
|
1224 |
+
"epoch": 1.23,
|
1225 |
+
"learning_rate": 0.00022925081433224754,
|
1226 |
+
"loss": 0.7077,
|
1227 |
+
"step": 1910
|
1228 |
+
},
|
1229 |
+
{
|
1230 |
+
"epoch": 1.23,
|
1231 |
+
"learning_rate": 0.0002288599348534202,
|
1232 |
+
"loss": 0.7022,
|
1233 |
+
"step": 1920
|
1234 |
+
},
|
1235 |
+
{
|
1236 |
+
"epoch": 1.24,
|
1237 |
+
"learning_rate": 0.0002284690553745928,
|
1238 |
+
"loss": 0.7158,
|
1239 |
+
"step": 1930
|
1240 |
+
},
|
1241 |
+
{
|
1242 |
+
"epoch": 1.25,
|
1243 |
+
"learning_rate": 0.00022807817589576545,
|
1244 |
+
"loss": 0.7186,
|
1245 |
+
"step": 1940
|
1246 |
+
},
|
1247 |
+
{
|
1248 |
+
"epoch": 1.25,
|
1249 |
+
"learning_rate": 0.0002276872964169381,
|
1250 |
+
"loss": 0.7046,
|
1251 |
+
"step": 1950
|
1252 |
+
},
|
1253 |
+
{
|
1254 |
+
"epoch": 1.26,
|
1255 |
+
"learning_rate": 0.00022729641693811073,
|
1256 |
+
"loss": 0.729,
|
1257 |
+
"step": 1960
|
1258 |
+
},
|
1259 |
+
{
|
1260 |
+
"epoch": 1.27,
|
1261 |
+
"learning_rate": 0.0002269055374592834,
|
1262 |
+
"loss": 0.6897,
|
1263 |
+
"step": 1970
|
1264 |
+
},
|
1265 |
+
{
|
1266 |
+
"epoch": 1.27,
|
1267 |
+
"learning_rate": 0.000226514657980456,
|
1268 |
+
"loss": 0.6949,
|
1269 |
+
"step": 1980
|
1270 |
+
},
|
1271 |
+
{
|
1272 |
+
"epoch": 1.28,
|
1273 |
+
"learning_rate": 0.00022612377850162864,
|
1274 |
+
"loss": 0.6945,
|
1275 |
+
"step": 1990
|
1276 |
+
},
|
1277 |
+
{
|
1278 |
+
"epoch": 1.29,
|
1279 |
+
"learning_rate": 0.00022573289902280127,
|
1280 |
+
"loss": 0.7178,
|
1281 |
+
"step": 2000
|
1282 |
+
},
|
1283 |
+
{
|
1284 |
+
"epoch": 1.29,
|
1285 |
+
"eval_loss": 0.7295793294906616,
|
1286 |
+
"eval_runtime": 305.3011,
|
1287 |
+
"eval_samples_per_second": 6.551,
|
1288 |
+
"eval_steps_per_second": 0.819,
|
1289 |
+
"step": 2000
|
1290 |
+
},
|
1291 |
+
{
|
1292 |
+
"epoch": 1.29,
|
1293 |
+
"learning_rate": 0.00022534201954397393,
|
1294 |
+
"loss": 0.711,
|
1295 |
+
"step": 2010
|
1296 |
+
},
|
1297 |
+
{
|
1298 |
+
"epoch": 1.3,
|
1299 |
+
"learning_rate": 0.00022495114006514658,
|
1300 |
+
"loss": 0.74,
|
1301 |
+
"step": 2020
|
1302 |
+
},
|
1303 |
+
{
|
1304 |
+
"epoch": 1.31,
|
1305 |
+
"learning_rate": 0.00022456026058631918,
|
1306 |
+
"loss": 0.6866,
|
1307 |
+
"step": 2030
|
1308 |
+
},
|
1309 |
+
{
|
1310 |
+
"epoch": 1.31,
|
1311 |
+
"learning_rate": 0.00022416938110749184,
|
1312 |
+
"loss": 0.7241,
|
1313 |
+
"step": 2040
|
1314 |
+
},
|
1315 |
+
{
|
1316 |
+
"epoch": 1.32,
|
1317 |
+
"learning_rate": 0.00022377850162866447,
|
1318 |
+
"loss": 0.6936,
|
1319 |
+
"step": 2050
|
1320 |
+
},
|
1321 |
+
{
|
1322 |
+
"epoch": 1.32,
|
1323 |
+
"learning_rate": 0.00022338762214983712,
|
1324 |
+
"loss": 0.7024,
|
1325 |
+
"step": 2060
|
1326 |
+
},
|
1327 |
+
{
|
1328 |
+
"epoch": 1.33,
|
1329 |
+
"learning_rate": 0.00022299674267100978,
|
1330 |
+
"loss": 0.7133,
|
1331 |
+
"step": 2070
|
1332 |
+
},
|
1333 |
+
{
|
1334 |
+
"epoch": 1.34,
|
1335 |
+
"learning_rate": 0.00022260586319218238,
|
1336 |
+
"loss": 0.7113,
|
1337 |
+
"step": 2080
|
1338 |
+
},
|
1339 |
+
{
|
1340 |
+
"epoch": 1.34,
|
1341 |
+
"learning_rate": 0.00022221498371335503,
|
1342 |
+
"loss": 0.7125,
|
1343 |
+
"step": 2090
|
1344 |
+
},
|
1345 |
+
{
|
1346 |
+
"epoch": 1.35,
|
1347 |
+
"learning_rate": 0.00022182410423452766,
|
1348 |
+
"loss": 0.7047,
|
1349 |
+
"step": 2100
|
1350 |
+
},
|
1351 |
+
{
|
1352 |
+
"epoch": 1.36,
|
1353 |
+
"learning_rate": 0.00022143322475570032,
|
1354 |
+
"loss": 0.7145,
|
1355 |
+
"step": 2110
|
1356 |
+
},
|
1357 |
+
{
|
1358 |
+
"epoch": 1.36,
|
1359 |
+
"learning_rate": 0.00022104234527687295,
|
1360 |
+
"loss": 0.7048,
|
1361 |
+
"step": 2120
|
1362 |
+
},
|
1363 |
+
{
|
1364 |
+
"epoch": 1.37,
|
1365 |
+
"learning_rate": 0.00022065146579804557,
|
1366 |
+
"loss": 0.7088,
|
1367 |
+
"step": 2130
|
1368 |
+
},
|
1369 |
+
{
|
1370 |
+
"epoch": 1.38,
|
1371 |
+
"learning_rate": 0.0002202605863192182,
|
1372 |
+
"loss": 0.6722,
|
1373 |
+
"step": 2140
|
1374 |
+
},
|
1375 |
+
{
|
1376 |
+
"epoch": 1.38,
|
1377 |
+
"learning_rate": 0.00021986970684039086,
|
1378 |
+
"loss": 0.7172,
|
1379 |
+
"step": 2150
|
1380 |
+
},
|
1381 |
+
{
|
1382 |
+
"epoch": 1.39,
|
1383 |
+
"learning_rate": 0.0002194788273615635,
|
1384 |
+
"loss": 0.7084,
|
1385 |
+
"step": 2160
|
1386 |
+
},
|
1387 |
+
{
|
1388 |
+
"epoch": 1.4,
|
1389 |
+
"learning_rate": 0.00021908794788273614,
|
1390 |
+
"loss": 0.7115,
|
1391 |
+
"step": 2170
|
1392 |
+
},
|
1393 |
+
{
|
1394 |
+
"epoch": 1.4,
|
1395 |
+
"learning_rate": 0.00021869706840390877,
|
1396 |
+
"loss": 0.711,
|
1397 |
+
"step": 2180
|
1398 |
+
},
|
1399 |
+
{
|
1400 |
+
"epoch": 1.41,
|
1401 |
+
"learning_rate": 0.0002183061889250814,
|
1402 |
+
"loss": 0.709,
|
1403 |
+
"step": 2190
|
1404 |
+
},
|
1405 |
+
{
|
1406 |
+
"epoch": 1.41,
|
1407 |
+
"learning_rate": 0.00021791530944625405,
|
1408 |
+
"loss": 0.7009,
|
1409 |
+
"step": 2200
|
1410 |
+
},
|
1411 |
+
{
|
1412 |
+
"epoch": 1.41,
|
1413 |
+
"eval_loss": 0.7283578515052795,
|
1414 |
+
"eval_runtime": 304.8952,
|
1415 |
+
"eval_samples_per_second": 6.56,
|
1416 |
+
"eval_steps_per_second": 0.82,
|
1417 |
+
"step": 2200
|
1418 |
+
},
|
1419 |
+
{
|
1420 |
+
"epoch": 1.42,
|
1421 |
+
"learning_rate": 0.0002175244299674267,
|
1422 |
+
"loss": 0.689,
|
1423 |
+
"step": 2210
|
1424 |
+
},
|
1425 |
+
{
|
1426 |
+
"epoch": 1.43,
|
1427 |
+
"learning_rate": 0.00021713355048859934,
|
1428 |
+
"loss": 0.7053,
|
1429 |
+
"step": 2220
|
1430 |
+
},
|
1431 |
+
{
|
1432 |
+
"epoch": 1.43,
|
1433 |
+
"learning_rate": 0.000216742671009772,
|
1434 |
+
"loss": 0.7083,
|
1435 |
+
"step": 2230
|
1436 |
+
},
|
1437 |
+
{
|
1438 |
+
"epoch": 1.44,
|
1439 |
+
"learning_rate": 0.0002163517915309446,
|
1440 |
+
"loss": 0.7243,
|
1441 |
+
"step": 2240
|
1442 |
+
},
|
1443 |
+
{
|
1444 |
+
"epoch": 1.45,
|
1445 |
+
"learning_rate": 0.00021596091205211725,
|
1446 |
+
"loss": 0.7015,
|
1447 |
+
"step": 2250
|
1448 |
+
},
|
1449 |
+
{
|
1450 |
+
"epoch": 1.45,
|
1451 |
+
"learning_rate": 0.00021557003257328987,
|
1452 |
+
"loss": 0.7003,
|
1453 |
+
"step": 2260
|
1454 |
+
},
|
1455 |
+
{
|
1456 |
+
"epoch": 1.46,
|
1457 |
+
"learning_rate": 0.00021517915309446253,
|
1458 |
+
"loss": 0.7082,
|
1459 |
+
"step": 2270
|
1460 |
+
},
|
1461 |
+
{
|
1462 |
+
"epoch": 1.47,
|
1463 |
+
"learning_rate": 0.00021478827361563519,
|
1464 |
+
"loss": 0.6813,
|
1465 |
+
"step": 2280
|
1466 |
+
},
|
1467 |
+
{
|
1468 |
+
"epoch": 1.47,
|
1469 |
+
"learning_rate": 0.00021439739413680779,
|
1470 |
+
"loss": 0.6653,
|
1471 |
+
"step": 2290
|
1472 |
+
},
|
1473 |
+
{
|
1474 |
+
"epoch": 1.48,
|
1475 |
+
"learning_rate": 0.00021400651465798044,
|
1476 |
+
"loss": 0.6942,
|
1477 |
+
"step": 2300
|
1478 |
+
},
|
1479 |
+
{
|
1480 |
+
"epoch": 1.49,
|
1481 |
+
"learning_rate": 0.00021361563517915307,
|
1482 |
+
"loss": 0.6831,
|
1483 |
+
"step": 2310
|
1484 |
+
},
|
1485 |
+
{
|
1486 |
+
"epoch": 1.49,
|
1487 |
+
"learning_rate": 0.00021322475570032572,
|
1488 |
+
"loss": 0.6975,
|
1489 |
+
"step": 2320
|
1490 |
+
},
|
1491 |
+
{
|
1492 |
+
"epoch": 1.5,
|
1493 |
+
"learning_rate": 0.00021283387622149838,
|
1494 |
+
"loss": 0.7188,
|
1495 |
+
"step": 2330
|
1496 |
+
},
|
1497 |
+
{
|
1498 |
+
"epoch": 1.5,
|
1499 |
+
"learning_rate": 0.00021244299674267098,
|
1500 |
+
"loss": 0.7015,
|
1501 |
+
"step": 2340
|
1502 |
+
},
|
1503 |
+
{
|
1504 |
+
"epoch": 1.51,
|
1505 |
+
"learning_rate": 0.00021205211726384364,
|
1506 |
+
"loss": 0.7035,
|
1507 |
+
"step": 2350
|
1508 |
+
},
|
1509 |
+
{
|
1510 |
+
"epoch": 1.52,
|
1511 |
+
"learning_rate": 0.00021166123778501626,
|
1512 |
+
"loss": 0.6914,
|
1513 |
+
"step": 2360
|
1514 |
+
},
|
1515 |
+
{
|
1516 |
+
"epoch": 1.52,
|
1517 |
+
"learning_rate": 0.00021127035830618892,
|
1518 |
+
"loss": 0.7002,
|
1519 |
+
"step": 2370
|
1520 |
+
},
|
1521 |
+
{
|
1522 |
+
"epoch": 1.53,
|
1523 |
+
"learning_rate": 0.00021087947882736155,
|
1524 |
+
"loss": 0.7263,
|
1525 |
+
"step": 2380
|
1526 |
+
},
|
1527 |
+
{
|
1528 |
+
"epoch": 1.54,
|
1529 |
+
"learning_rate": 0.00021048859934853418,
|
1530 |
+
"loss": 0.6828,
|
1531 |
+
"step": 2390
|
1532 |
+
},
|
1533 |
+
{
|
1534 |
+
"epoch": 1.54,
|
1535 |
+
"learning_rate": 0.0002100977198697068,
|
1536 |
+
"loss": 0.6953,
|
1537 |
+
"step": 2400
|
1538 |
+
},
|
1539 |
+
{
|
1540 |
+
"epoch": 1.54,
|
1541 |
+
"eval_loss": 0.7254114151000977,
|
1542 |
+
"eval_runtime": 305.3837,
|
1543 |
+
"eval_samples_per_second": 6.549,
|
1544 |
+
"eval_steps_per_second": 0.819,
|
1545 |
+
"step": 2400
|
1546 |
+
},
|
1547 |
+
{
|
1548 |
+
"epoch": 1.55,
|
1549 |
+
"learning_rate": 0.00020970684039087946,
|
1550 |
+
"loss": 0.6916,
|
1551 |
+
"step": 2410
|
1552 |
+
},
|
1553 |
+
{
|
1554 |
+
"epoch": 1.56,
|
1555 |
+
"learning_rate": 0.00020931596091205211,
|
1556 |
+
"loss": 0.6929,
|
1557 |
+
"step": 2420
|
1558 |
+
},
|
1559 |
+
{
|
1560 |
+
"epoch": 1.56,
|
1561 |
+
"learning_rate": 0.00020892508143322474,
|
1562 |
+
"loss": 0.6917,
|
1563 |
+
"step": 2430
|
1564 |
+
},
|
1565 |
+
{
|
1566 |
+
"epoch": 1.57,
|
1567 |
+
"learning_rate": 0.00020853420195439737,
|
1568 |
+
"loss": 0.7093,
|
1569 |
+
"step": 2440
|
1570 |
+
},
|
1571 |
+
{
|
1572 |
+
"epoch": 1.58,
|
1573 |
+
"learning_rate": 0.00020814332247557,
|
1574 |
+
"loss": 0.6587,
|
1575 |
+
"step": 2450
|
1576 |
+
},
|
1577 |
+
{
|
1578 |
+
"epoch": 1.58,
|
1579 |
+
"learning_rate": 0.00020775244299674265,
|
1580 |
+
"loss": 0.6849,
|
1581 |
+
"step": 2460
|
1582 |
+
},
|
1583 |
+
{
|
1584 |
+
"epoch": 1.59,
|
1585 |
+
"learning_rate": 0.0002073615635179153,
|
1586 |
+
"loss": 0.6868,
|
1587 |
+
"step": 2470
|
1588 |
+
},
|
1589 |
+
{
|
1590 |
+
"epoch": 1.59,
|
1591 |
+
"learning_rate": 0.00020697068403908794,
|
1592 |
+
"loss": 0.7033,
|
1593 |
+
"step": 2480
|
1594 |
+
},
|
1595 |
+
{
|
1596 |
+
"epoch": 1.6,
|
1597 |
+
"learning_rate": 0.00020657980456026057,
|
1598 |
+
"loss": 0.6981,
|
1599 |
+
"step": 2490
|
1600 |
+
},
|
1601 |
+
{
|
1602 |
+
"epoch": 1.61,
|
1603 |
+
"learning_rate": 0.0002061889250814332,
|
1604 |
+
"loss": 0.7093,
|
1605 |
+
"step": 2500
|
1606 |
+
},
|
1607 |
+
{
|
1608 |
+
"epoch": 1.61,
|
1609 |
+
"learning_rate": 0.00020579804560260585,
|
1610 |
+
"loss": 0.7087,
|
1611 |
+
"step": 2510
|
1612 |
+
},
|
1613 |
+
{
|
1614 |
+
"epoch": 1.62,
|
1615 |
+
"learning_rate": 0.00020540716612377848,
|
1616 |
+
"loss": 0.6819,
|
1617 |
+
"step": 2520
|
1618 |
+
},
|
1619 |
+
{
|
1620 |
+
"epoch": 1.63,
|
1621 |
+
"learning_rate": 0.00020501628664495113,
|
1622 |
+
"loss": 0.6874,
|
1623 |
+
"step": 2530
|
1624 |
+
},
|
1625 |
+
{
|
1626 |
+
"epoch": 1.63,
|
1627 |
+
"learning_rate": 0.00020462540716612373,
|
1628 |
+
"loss": 0.6895,
|
1629 |
+
"step": 2540
|
1630 |
+
},
|
1631 |
+
{
|
1632 |
+
"epoch": 1.64,
|
1633 |
+
"learning_rate": 0.0002042345276872964,
|
1634 |
+
"loss": 0.6954,
|
1635 |
+
"step": 2550
|
1636 |
+
},
|
1637 |
+
{
|
1638 |
+
"epoch": 1.65,
|
1639 |
+
"learning_rate": 0.00020384364820846904,
|
1640 |
+
"loss": 0.6676,
|
1641 |
+
"step": 2560
|
1642 |
+
},
|
1643 |
+
{
|
1644 |
+
"epoch": 1.65,
|
1645 |
+
"learning_rate": 0.00020345276872964167,
|
1646 |
+
"loss": 0.7144,
|
1647 |
+
"step": 2570
|
1648 |
+
},
|
1649 |
+
{
|
1650 |
+
"epoch": 1.66,
|
1651 |
+
"learning_rate": 0.00020306188925081433,
|
1652 |
+
"loss": 0.7194,
|
1653 |
+
"step": 2580
|
1654 |
+
},
|
1655 |
+
{
|
1656 |
+
"epoch": 1.67,
|
1657 |
+
"learning_rate": 0.00020267100977198693,
|
1658 |
+
"loss": 0.7016,
|
1659 |
+
"step": 2590
|
1660 |
+
},
|
1661 |
+
{
|
1662 |
+
"epoch": 1.67,
|
1663 |
+
"learning_rate": 0.00020228013029315958,
|
1664 |
+
"loss": 0.6849,
|
1665 |
+
"step": 2600
|
1666 |
+
},
|
1667 |
+
{
|
1668 |
+
"epoch": 1.67,
|
1669 |
+
"eval_loss": 0.7234678864479065,
|
1670 |
+
"eval_runtime": 305.414,
|
1671 |
+
"eval_samples_per_second": 6.548,
|
1672 |
+
"eval_steps_per_second": 0.819,
|
1673 |
+
"step": 2600
|
1674 |
+
},
|
1675 |
+
{
|
1676 |
+
"epoch": 1.68,
|
1677 |
+
"learning_rate": 0.00020188925081433224,
|
1678 |
+
"loss": 0.6993,
|
1679 |
+
"step": 2610
|
1680 |
+
},
|
1681 |
+
{
|
1682 |
+
"epoch": 1.68,
|
1683 |
+
"learning_rate": 0.00020149837133550487,
|
1684 |
+
"loss": 0.7068,
|
1685 |
+
"step": 2620
|
1686 |
+
},
|
1687 |
+
{
|
1688 |
+
"epoch": 1.69,
|
1689 |
+
"learning_rate": 0.00020110749185667752,
|
1690 |
+
"loss": 0.7013,
|
1691 |
+
"step": 2630
|
1692 |
+
},
|
1693 |
+
{
|
1694 |
+
"epoch": 1.7,
|
1695 |
+
"learning_rate": 0.00020071661237785015,
|
1696 |
+
"loss": 0.7064,
|
1697 |
+
"step": 2640
|
1698 |
+
},
|
1699 |
+
{
|
1700 |
+
"epoch": 1.7,
|
1701 |
+
"learning_rate": 0.00020032573289902278,
|
1702 |
+
"loss": 0.6916,
|
1703 |
+
"step": 2650
|
1704 |
+
},
|
1705 |
+
{
|
1706 |
+
"epoch": 1.71,
|
1707 |
+
"learning_rate": 0.0001999348534201954,
|
1708 |
+
"loss": 0.6717,
|
1709 |
+
"step": 2660
|
1710 |
+
},
|
1711 |
+
{
|
1712 |
+
"epoch": 1.72,
|
1713 |
+
"learning_rate": 0.00019954397394136806,
|
1714 |
+
"loss": 0.6969,
|
1715 |
+
"step": 2670
|
1716 |
+
},
|
1717 |
+
{
|
1718 |
+
"epoch": 1.72,
|
1719 |
+
"learning_rate": 0.00019915309446254072,
|
1720 |
+
"loss": 0.685,
|
1721 |
+
"step": 2680
|
1722 |
+
},
|
1723 |
+
{
|
1724 |
+
"epoch": 1.73,
|
1725 |
+
"learning_rate": 0.00019876221498371335,
|
1726 |
+
"loss": 0.7093,
|
1727 |
+
"step": 2690
|
1728 |
+
},
|
1729 |
+
{
|
1730 |
+
"epoch": 1.74,
|
1731 |
+
"learning_rate": 0.00019837133550488597,
|
1732 |
+
"loss": 0.6936,
|
1733 |
+
"step": 2700
|
1734 |
+
},
|
1735 |
+
{
|
1736 |
+
"epoch": 1.74,
|
1737 |
+
"learning_rate": 0.0001979804560260586,
|
1738 |
+
"loss": 0.6898,
|
1739 |
+
"step": 2710
|
1740 |
+
},
|
1741 |
+
{
|
1742 |
+
"epoch": 1.75,
|
1743 |
+
"learning_rate": 0.00019758957654723126,
|
1744 |
+
"loss": 0.6914,
|
1745 |
+
"step": 2720
|
1746 |
+
},
|
1747 |
+
{
|
1748 |
+
"epoch": 1.76,
|
1749 |
+
"learning_rate": 0.0001971986970684039,
|
1750 |
+
"loss": 0.6863,
|
1751 |
+
"step": 2730
|
1752 |
+
},
|
1753 |
+
{
|
1754 |
+
"epoch": 1.76,
|
1755 |
+
"learning_rate": 0.00019680781758957654,
|
1756 |
+
"loss": 0.6974,
|
1757 |
+
"step": 2740
|
1758 |
+
},
|
1759 |
+
{
|
1760 |
+
"epoch": 1.77,
|
1761 |
+
"learning_rate": 0.00019641693811074917,
|
1762 |
+
"loss": 0.7073,
|
1763 |
+
"step": 2750
|
1764 |
+
},
|
1765 |
+
{
|
1766 |
+
"epoch": 1.77,
|
1767 |
+
"learning_rate": 0.0001960260586319218,
|
1768 |
+
"loss": 0.6874,
|
1769 |
+
"step": 2760
|
1770 |
+
},
|
1771 |
+
{
|
1772 |
+
"epoch": 1.78,
|
1773 |
+
"learning_rate": 0.00019563517915309445,
|
1774 |
+
"loss": 0.6847,
|
1775 |
+
"step": 2770
|
1776 |
+
},
|
1777 |
+
{
|
1778 |
+
"epoch": 1.79,
|
1779 |
+
"learning_rate": 0.00019524429967426708,
|
1780 |
+
"loss": 0.6989,
|
1781 |
+
"step": 2780
|
1782 |
+
},
|
1783 |
+
{
|
1784 |
+
"epoch": 1.79,
|
1785 |
+
"learning_rate": 0.00019485342019543974,
|
1786 |
+
"loss": 0.6953,
|
1787 |
+
"step": 2790
|
1788 |
+
},
|
1789 |
+
{
|
1790 |
+
"epoch": 1.8,
|
1791 |
+
"learning_rate": 0.00019446254071661234,
|
1792 |
+
"loss": 0.6855,
|
1793 |
+
"step": 2800
|
1794 |
+
},
|
1795 |
+
{
|
1796 |
+
"epoch": 1.8,
|
1797 |
+
"eval_loss": 0.7221594452857971,
|
1798 |
+
"eval_runtime": 304.2851,
|
1799 |
+
"eval_samples_per_second": 6.573,
|
1800 |
+
"eval_steps_per_second": 0.822,
|
1801 |
+
"step": 2800
|
1802 |
+
},
|
1803 |
+
{
|
1804 |
+
"epoch": 1.81,
|
1805 |
+
"learning_rate": 0.000194071661237785,
|
1806 |
+
"loss": 0.7001,
|
1807 |
+
"step": 2810
|
1808 |
+
},
|
1809 |
+
{
|
1810 |
+
"epoch": 1.81,
|
1811 |
+
"learning_rate": 0.00019368078175895765,
|
1812 |
+
"loss": 0.7271,
|
1813 |
+
"step": 2820
|
1814 |
+
},
|
1815 |
+
{
|
1816 |
+
"epoch": 1.82,
|
1817 |
+
"learning_rate": 0.00019328990228013028,
|
1818 |
+
"loss": 0.6892,
|
1819 |
+
"step": 2830
|
1820 |
+
},
|
1821 |
+
{
|
1822 |
+
"epoch": 1.83,
|
1823 |
+
"learning_rate": 0.00019289902280130293,
|
1824 |
+
"loss": 0.7021,
|
1825 |
+
"step": 2840
|
1826 |
+
},
|
1827 |
+
{
|
1828 |
+
"epoch": 1.83,
|
1829 |
+
"learning_rate": 0.00019250814332247553,
|
1830 |
+
"loss": 0.713,
|
1831 |
+
"step": 2850
|
1832 |
+
},
|
1833 |
+
{
|
1834 |
+
"epoch": 1.84,
|
1835 |
+
"learning_rate": 0.0001921172638436482,
|
1836 |
+
"loss": 0.7011,
|
1837 |
+
"step": 2860
|
1838 |
+
},
|
1839 |
+
{
|
1840 |
+
"epoch": 1.85,
|
1841 |
+
"learning_rate": 0.00019172638436482084,
|
1842 |
+
"loss": 0.6932,
|
1843 |
+
"step": 2870
|
1844 |
+
},
|
1845 |
+
{
|
1846 |
+
"epoch": 1.85,
|
1847 |
+
"learning_rate": 0.00019133550488599347,
|
1848 |
+
"loss": 0.6895,
|
1849 |
+
"step": 2880
|
1850 |
+
},
|
1851 |
+
{
|
1852 |
+
"epoch": 1.86,
|
1853 |
+
"learning_rate": 0.00019094462540716613,
|
1854 |
+
"loss": 0.6971,
|
1855 |
+
"step": 2890
|
1856 |
+
},
|
1857 |
+
{
|
1858 |
+
"epoch": 1.86,
|
1859 |
+
"learning_rate": 0.00019055374592833873,
|
1860 |
+
"loss": 0.6949,
|
1861 |
+
"step": 2900
|
1862 |
+
},
|
1863 |
+
{
|
1864 |
+
"epoch": 1.87,
|
1865 |
+
"learning_rate": 0.00019016286644951138,
|
1866 |
+
"loss": 0.6767,
|
1867 |
+
"step": 2910
|
1868 |
+
},
|
1869 |
+
{
|
1870 |
+
"epoch": 1.88,
|
1871 |
+
"learning_rate": 0.000189771986970684,
|
1872 |
+
"loss": 0.693,
|
1873 |
+
"step": 2920
|
1874 |
+
},
|
1875 |
+
{
|
1876 |
+
"epoch": 1.88,
|
1877 |
+
"learning_rate": 0.00018938110749185666,
|
1878 |
+
"loss": 0.7048,
|
1879 |
+
"step": 2930
|
1880 |
+
},
|
1881 |
+
{
|
1882 |
+
"epoch": 1.89,
|
1883 |
+
"learning_rate": 0.00018899022801302932,
|
1884 |
+
"loss": 0.7007,
|
1885 |
+
"step": 2940
|
1886 |
+
},
|
1887 |
+
{
|
1888 |
+
"epoch": 1.9,
|
1889 |
+
"learning_rate": 0.00018859934853420192,
|
1890 |
+
"loss": 0.6677,
|
1891 |
+
"step": 2950
|
1892 |
+
},
|
1893 |
+
{
|
1894 |
+
"epoch": 1.9,
|
1895 |
+
"learning_rate": 0.00018820846905537458,
|
1896 |
+
"loss": 0.7071,
|
1897 |
+
"step": 2960
|
1898 |
+
},
|
1899 |
+
{
|
1900 |
+
"epoch": 1.91,
|
1901 |
+
"learning_rate": 0.0001878175895765472,
|
1902 |
+
"loss": 0.7014,
|
1903 |
+
"step": 2970
|
1904 |
+
},
|
1905 |
+
{
|
1906 |
+
"epoch": 1.92,
|
1907 |
+
"learning_rate": 0.00018742671009771986,
|
1908 |
+
"loss": 0.7017,
|
1909 |
+
"step": 2980
|
1910 |
+
},
|
1911 |
+
{
|
1912 |
+
"epoch": 1.92,
|
1913 |
+
"learning_rate": 0.00018703583061889252,
|
1914 |
+
"loss": 0.6962,
|
1915 |
+
"step": 2990
|
1916 |
+
},
|
1917 |
+
{
|
1918 |
+
"epoch": 1.93,
|
1919 |
+
"learning_rate": 0.00018664495114006514,
|
1920 |
+
"loss": 0.6785,
|
1921 |
+
"step": 3000
|
1922 |
+
},
|
1923 |
+
{
|
1924 |
+
"epoch": 1.93,
|
1925 |
+
"eval_loss": 0.7213538289070129,
|
1926 |
+
"eval_runtime": 304.1305,
|
1927 |
+
"eval_samples_per_second": 6.576,
|
1928 |
+
"eval_steps_per_second": 0.822,
|
1929 |
+
"step": 3000
|
1930 |
+
},
|
1931 |
+
{
|
1932 |
+
"epoch": 1.94,
|
1933 |
+
"learning_rate": 0.00018625407166123777,
|
1934 |
+
"loss": 0.68,
|
1935 |
+
"step": 3010
|
1936 |
+
},
|
1937 |
+
{
|
1938 |
+
"epoch": 1.94,
|
1939 |
+
"learning_rate": 0.0001858631921824104,
|
1940 |
+
"loss": 0.6839,
|
1941 |
+
"step": 3020
|
1942 |
+
},
|
1943 |
+
{
|
1944 |
+
"epoch": 1.95,
|
1945 |
+
"learning_rate": 0.00018547231270358305,
|
1946 |
+
"loss": 0.6739,
|
1947 |
+
"step": 3030
|
1948 |
+
},
|
1949 |
+
{
|
1950 |
+
"epoch": 1.95,
|
1951 |
+
"learning_rate": 0.00018508143322475568,
|
1952 |
+
"loss": 0.6944,
|
1953 |
+
"step": 3040
|
1954 |
+
},
|
1955 |
+
{
|
1956 |
+
"epoch": 1.96,
|
1957 |
+
"learning_rate": 0.00018469055374592834,
|
1958 |
+
"loss": 0.7065,
|
1959 |
+
"step": 3050
|
1960 |
+
},
|
1961 |
+
{
|
1962 |
+
"epoch": 1.97,
|
1963 |
+
"learning_rate": 0.00018429967426710094,
|
1964 |
+
"loss": 0.7103,
|
1965 |
+
"step": 3060
|
1966 |
+
},
|
1967 |
+
{
|
1968 |
+
"epoch": 1.97,
|
1969 |
+
"learning_rate": 0.0001839087947882736,
|
1970 |
+
"loss": 0.7001,
|
1971 |
+
"step": 3070
|
1972 |
+
},
|
1973 |
+
{
|
1974 |
+
"epoch": 1.98,
|
1975 |
+
"learning_rate": 0.00018351791530944625,
|
1976 |
+
"loss": 0.6892,
|
1977 |
+
"step": 3080
|
1978 |
+
},
|
1979 |
+
{
|
1980 |
+
"epoch": 1.99,
|
1981 |
+
"learning_rate": 0.00018312703583061888,
|
1982 |
+
"loss": 0.7009,
|
1983 |
+
"step": 3090
|
1984 |
+
},
|
1985 |
+
{
|
1986 |
+
"epoch": 1.99,
|
1987 |
+
"learning_rate": 0.00018273615635179153,
|
1988 |
+
"loss": 0.714,
|
1989 |
+
"step": 3100
|
1990 |
+
},
|
1991 |
+
{
|
1992 |
+
"epoch": 2.0,
|
1993 |
+
"learning_rate": 0.00018234527687296413,
|
1994 |
+
"loss": 0.7133,
|
1995 |
+
"step": 3110
|
1996 |
+
},
|
1997 |
+
{
|
1998 |
+
"epoch": 2.01,
|
1999 |
+
"learning_rate": 0.0001819543973941368,
|
2000 |
+
"loss": 0.6702,
|
2001 |
+
"step": 3120
|
2002 |
+
},
|
2003 |
+
{
|
2004 |
+
"epoch": 2.01,
|
2005 |
+
"learning_rate": 0.00018156351791530944,
|
2006 |
+
"loss": 0.6416,
|
2007 |
+
"step": 3130
|
2008 |
+
},
|
2009 |
+
{
|
2010 |
+
"epoch": 2.02,
|
2011 |
+
"learning_rate": 0.00018117263843648207,
|
2012 |
+
"loss": 0.6654,
|
2013 |
+
"step": 3140
|
2014 |
+
},
|
2015 |
+
{
|
2016 |
+
"epoch": 2.03,
|
2017 |
+
"learning_rate": 0.00018078175895765473,
|
2018 |
+
"loss": 0.6678,
|
2019 |
+
"step": 3150
|
2020 |
+
},
|
2021 |
+
{
|
2022 |
+
"epoch": 2.03,
|
2023 |
+
"learning_rate": 0.00018039087947882733,
|
2024 |
+
"loss": 0.6657,
|
2025 |
+
"step": 3160
|
2026 |
+
},
|
2027 |
+
{
|
2028 |
+
"epoch": 2.04,
|
2029 |
+
"learning_rate": 0.00017999999999999998,
|
2030 |
+
"loss": 0.6588,
|
2031 |
+
"step": 3170
|
2032 |
+
},
|
2033 |
+
{
|
2034 |
+
"epoch": 2.05,
|
2035 |
+
"learning_rate": 0.0001796091205211726,
|
2036 |
+
"loss": 0.6545,
|
2037 |
+
"step": 3180
|
2038 |
+
},
|
2039 |
+
{
|
2040 |
+
"epoch": 2.05,
|
2041 |
+
"learning_rate": 0.00017921824104234527,
|
2042 |
+
"loss": 0.6266,
|
2043 |
+
"step": 3190
|
2044 |
+
},
|
2045 |
+
{
|
2046 |
+
"epoch": 2.06,
|
2047 |
+
"learning_rate": 0.00017882736156351792,
|
2048 |
+
"loss": 0.6608,
|
2049 |
+
"step": 3200
|
2050 |
+
},
|
2051 |
+
{
|
2052 |
+
"epoch": 2.06,
|
2053 |
+
"eval_loss": 0.7244688868522644,
|
2054 |
+
"eval_runtime": 301.8449,
|
2055 |
+
"eval_samples_per_second": 6.626,
|
2056 |
+
"eval_steps_per_second": 0.828,
|
2057 |
+
"step": 3200
|
2058 |
+
},
|
2059 |
+
{
|
2060 |
+
"epoch": 2.06,
|
2061 |
+
"learning_rate": 0.00017843648208469052,
|
2062 |
+
"loss": 0.6472,
|
2063 |
+
"step": 3210
|
2064 |
+
},
|
2065 |
+
{
|
2066 |
+
"epoch": 2.07,
|
2067 |
+
"learning_rate": 0.00017804560260586318,
|
2068 |
+
"loss": 0.6375,
|
2069 |
+
"step": 3220
|
2070 |
+
},
|
2071 |
+
{
|
2072 |
+
"epoch": 2.08,
|
2073 |
+
"learning_rate": 0.0001776547231270358,
|
2074 |
+
"loss": 0.6715,
|
2075 |
+
"step": 3230
|
2076 |
+
},
|
2077 |
+
{
|
2078 |
+
"epoch": 2.08,
|
2079 |
+
"learning_rate": 0.00017726384364820846,
|
2080 |
+
"loss": 0.6541,
|
2081 |
+
"step": 3240
|
2082 |
+
},
|
2083 |
+
{
|
2084 |
+
"epoch": 2.09,
|
2085 |
+
"learning_rate": 0.0001768729641693811,
|
2086 |
+
"loss": 0.6707,
|
2087 |
+
"step": 3250
|
2088 |
+
},
|
2089 |
+
{
|
2090 |
+
"epoch": 2.1,
|
2091 |
+
"learning_rate": 0.00017648208469055372,
|
2092 |
+
"loss": 0.6634,
|
2093 |
+
"step": 3260
|
2094 |
+
},
|
2095 |
+
{
|
2096 |
+
"epoch": 2.1,
|
2097 |
+
"learning_rate": 0.00017609120521172637,
|
2098 |
+
"loss": 0.6558,
|
2099 |
+
"step": 3270
|
2100 |
+
},
|
2101 |
+
{
|
2102 |
+
"epoch": 2.11,
|
2103 |
+
"learning_rate": 0.000175700325732899,
|
2104 |
+
"loss": 0.6741,
|
2105 |
+
"step": 3280
|
2106 |
+
},
|
2107 |
+
{
|
2108 |
+
"epoch": 2.12,
|
2109 |
+
"learning_rate": 0.00017530944625407166,
|
2110 |
+
"loss": 0.6454,
|
2111 |
+
"step": 3290
|
2112 |
+
},
|
2113 |
+
{
|
2114 |
+
"epoch": 2.12,
|
2115 |
+
"learning_rate": 0.00017491856677524429,
|
2116 |
+
"loss": 0.6619,
|
2117 |
+
"step": 3300
|
2118 |
+
},
|
2119 |
+
{
|
2120 |
+
"epoch": 2.13,
|
2121 |
+
"learning_rate": 0.00017452768729641691,
|
2122 |
+
"loss": 0.6417,
|
2123 |
+
"step": 3310
|
2124 |
+
},
|
2125 |
+
{
|
2126 |
+
"epoch": 2.14,
|
2127 |
+
"learning_rate": 0.00017413680781758954,
|
2128 |
+
"loss": 0.6485,
|
2129 |
+
"step": 3320
|
2130 |
+
},
|
2131 |
+
{
|
2132 |
+
"epoch": 2.14,
|
2133 |
+
"learning_rate": 0.0001737459283387622,
|
2134 |
+
"loss": 0.6326,
|
2135 |
+
"step": 3330
|
2136 |
+
},
|
2137 |
+
{
|
2138 |
+
"epoch": 2.15,
|
2139 |
+
"learning_rate": 0.00017335504885993485,
|
2140 |
+
"loss": 0.663,
|
2141 |
+
"step": 3340
|
2142 |
+
},
|
2143 |
+
{
|
2144 |
+
"epoch": 2.15,
|
2145 |
+
"learning_rate": 0.00017296416938110748,
|
2146 |
+
"loss": 0.6529,
|
2147 |
+
"step": 3350
|
2148 |
+
},
|
2149 |
+
{
|
2150 |
+
"epoch": 2.16,
|
2151 |
+
"learning_rate": 0.0001725732899022801,
|
2152 |
+
"loss": 0.6619,
|
2153 |
+
"step": 3360
|
2154 |
+
},
|
2155 |
+
{
|
2156 |
+
"epoch": 2.17,
|
2157 |
+
"learning_rate": 0.00017218241042345274,
|
2158 |
+
"loss": 0.6553,
|
2159 |
+
"step": 3370
|
2160 |
+
},
|
2161 |
+
{
|
2162 |
+
"epoch": 2.17,
|
2163 |
+
"learning_rate": 0.0001717915309446254,
|
2164 |
+
"loss": 0.6514,
|
2165 |
+
"step": 3380
|
2166 |
+
},
|
2167 |
+
{
|
2168 |
+
"epoch": 2.18,
|
2169 |
+
"learning_rate": 0.00017140065146579802,
|
2170 |
+
"loss": 0.6634,
|
2171 |
+
"step": 3390
|
2172 |
+
},
|
2173 |
+
{
|
2174 |
+
"epoch": 2.19,
|
2175 |
+
"learning_rate": 0.00017100977198697068,
|
2176 |
+
"loss": 0.6438,
|
2177 |
+
"step": 3400
|
2178 |
+
},
|
2179 |
+
{
|
2180 |
+
"epoch": 2.19,
|
2181 |
+
"eval_loss": 0.7247596979141235,
|
2182 |
+
"eval_runtime": 304.03,
|
2183 |
+
"eval_samples_per_second": 6.578,
|
2184 |
+
"eval_steps_per_second": 0.822,
|
2185 |
+
"step": 3400
|
2186 |
+
},
|
2187 |
+
{
|
2188 |
+
"epoch": 2.19,
|
2189 |
+
"learning_rate": 0.00017061889250814333,
|
2190 |
+
"loss": 0.6592,
|
2191 |
+
"step": 3410
|
2192 |
+
},
|
2193 |
+
{
|
2194 |
+
"epoch": 2.2,
|
2195 |
+
"learning_rate": 0.00017022801302931593,
|
2196 |
+
"loss": 0.6478,
|
2197 |
+
"step": 3420
|
2198 |
+
},
|
2199 |
+
{
|
2200 |
+
"epoch": 2.21,
|
2201 |
+
"learning_rate": 0.0001698371335504886,
|
2202 |
+
"loss": 0.6475,
|
2203 |
+
"step": 3430
|
2204 |
+
},
|
2205 |
+
{
|
2206 |
+
"epoch": 2.21,
|
2207 |
+
"learning_rate": 0.00016944625407166122,
|
2208 |
+
"loss": 0.6559,
|
2209 |
+
"step": 3440
|
2210 |
+
},
|
2211 |
+
{
|
2212 |
+
"epoch": 2.22,
|
2213 |
+
"learning_rate": 0.00016905537459283387,
|
2214 |
+
"loss": 0.6635,
|
2215 |
+
"step": 3450
|
2216 |
+
},
|
2217 |
+
{
|
2218 |
+
"epoch": 2.23,
|
2219 |
+
"learning_rate": 0.00016866449511400653,
|
2220 |
+
"loss": 0.667,
|
2221 |
+
"step": 3460
|
2222 |
+
},
|
2223 |
+
{
|
2224 |
+
"epoch": 2.23,
|
2225 |
+
"learning_rate": 0.00016827361563517913,
|
2226 |
+
"loss": 0.6781,
|
2227 |
+
"step": 3470
|
2228 |
+
},
|
2229 |
+
{
|
2230 |
+
"epoch": 2.24,
|
2231 |
+
"learning_rate": 0.00016788273615635178,
|
2232 |
+
"loss": 0.6446,
|
2233 |
+
"step": 3480
|
2234 |
+
},
|
2235 |
+
{
|
2236 |
+
"epoch": 2.24,
|
2237 |
+
"learning_rate": 0.0001674918566775244,
|
2238 |
+
"loss": 0.6617,
|
2239 |
+
"step": 3490
|
2240 |
+
},
|
2241 |
+
{
|
2242 |
+
"epoch": 2.25,
|
2243 |
+
"learning_rate": 0.00016710097719869707,
|
2244 |
+
"loss": 0.6497,
|
2245 |
+
"step": 3500
|
2246 |
+
},
|
2247 |
+
{
|
2248 |
+
"epoch": 2.26,
|
2249 |
+
"learning_rate": 0.0001667100977198697,
|
2250 |
+
"loss": 0.6473,
|
2251 |
+
"step": 3510
|
2252 |
+
},
|
2253 |
+
{
|
2254 |
+
"epoch": 2.26,
|
2255 |
+
"learning_rate": 0.00016631921824104232,
|
2256 |
+
"loss": 0.6497,
|
2257 |
+
"step": 3520
|
2258 |
+
},
|
2259 |
+
{
|
2260 |
+
"epoch": 2.27,
|
2261 |
+
"learning_rate": 0.00016592833876221495,
|
2262 |
+
"loss": 0.6599,
|
2263 |
+
"step": 3530
|
2264 |
+
},
|
2265 |
+
{
|
2266 |
+
"epoch": 2.28,
|
2267 |
+
"learning_rate": 0.0001655374592833876,
|
2268 |
+
"loss": 0.6581,
|
2269 |
+
"step": 3540
|
2270 |
+
},
|
2271 |
+
{
|
2272 |
+
"epoch": 2.28,
|
2273 |
+
"learning_rate": 0.00016514657980456026,
|
2274 |
+
"loss": 0.6265,
|
2275 |
+
"step": 3550
|
2276 |
+
},
|
2277 |
+
{
|
2278 |
+
"epoch": 2.29,
|
2279 |
+
"learning_rate": 0.0001647557003257329,
|
2280 |
+
"loss": 0.6648,
|
2281 |
+
"step": 3560
|
2282 |
+
},
|
2283 |
+
{
|
2284 |
+
"epoch": 2.3,
|
2285 |
+
"learning_rate": 0.00016436482084690552,
|
2286 |
+
"loss": 0.6568,
|
2287 |
+
"step": 3570
|
2288 |
+
},
|
2289 |
+
{
|
2290 |
+
"epoch": 2.3,
|
2291 |
+
"learning_rate": 0.00016397394136807814,
|
2292 |
+
"loss": 0.6629,
|
2293 |
+
"step": 3580
|
2294 |
+
},
|
2295 |
+
{
|
2296 |
+
"epoch": 2.31,
|
2297 |
+
"learning_rate": 0.0001635830618892508,
|
2298 |
+
"loss": 0.6526,
|
2299 |
+
"step": 3590
|
2300 |
+
},
|
2301 |
+
{
|
2302 |
+
"epoch": 2.32,
|
2303 |
+
"learning_rate": 0.00016319218241042346,
|
2304 |
+
"loss": 0.6362,
|
2305 |
+
"step": 3600
|
2306 |
+
},
|
2307 |
+
{
|
2308 |
+
"epoch": 2.32,
|
2309 |
+
"eval_loss": 0.7260497808456421,
|
2310 |
+
"eval_runtime": 304.4517,
|
2311 |
+
"eval_samples_per_second": 6.569,
|
2312 |
+
"eval_steps_per_second": 0.821,
|
2313 |
+
"step": 3600
|
2314 |
+
},
|
2315 |
+
{
|
2316 |
+
"epoch": 2.32,
|
2317 |
+
"learning_rate": 0.00016280130293159608,
|
2318 |
+
"loss": 0.6525,
|
2319 |
+
"step": 3610
|
2320 |
+
},
|
2321 |
+
{
|
2322 |
+
"epoch": 2.33,
|
2323 |
+
"learning_rate": 0.0001624104234527687,
|
2324 |
+
"loss": 0.6389,
|
2325 |
+
"step": 3620
|
2326 |
+
},
|
2327 |
+
{
|
2328 |
+
"epoch": 2.33,
|
2329 |
+
"learning_rate": 0.00016201954397394134,
|
2330 |
+
"loss": 0.6672,
|
2331 |
+
"step": 3630
|
2332 |
+
},
|
2333 |
+
{
|
2334 |
+
"epoch": 2.34,
|
2335 |
+
"learning_rate": 0.000161628664495114,
|
2336 |
+
"loss": 0.686,
|
2337 |
+
"step": 3640
|
2338 |
+
},
|
2339 |
+
{
|
2340 |
+
"epoch": 2.35,
|
2341 |
+
"learning_rate": 0.00016123778501628662,
|
2342 |
+
"loss": 0.6508,
|
2343 |
+
"step": 3650
|
2344 |
+
},
|
2345 |
+
{
|
2346 |
+
"epoch": 2.35,
|
2347 |
+
"learning_rate": 0.00016084690553745928,
|
2348 |
+
"loss": 0.6449,
|
2349 |
+
"step": 3660
|
2350 |
+
},
|
2351 |
+
{
|
2352 |
+
"epoch": 2.36,
|
2353 |
+
"learning_rate": 0.00016045602605863188,
|
2354 |
+
"loss": 0.6482,
|
2355 |
+
"step": 3670
|
2356 |
+
},
|
2357 |
+
{
|
2358 |
+
"epoch": 2.37,
|
2359 |
+
"learning_rate": 0.00016006514657980453,
|
2360 |
+
"loss": 0.6607,
|
2361 |
+
"step": 3680
|
2362 |
+
},
|
2363 |
+
{
|
2364 |
+
"epoch": 2.37,
|
2365 |
+
"learning_rate": 0.0001596742671009772,
|
2366 |
+
"loss": 0.6656,
|
2367 |
+
"step": 3690
|
2368 |
+
},
|
2369 |
+
{
|
2370 |
+
"epoch": 2.38,
|
2371 |
+
"learning_rate": 0.00015928338762214982,
|
2372 |
+
"loss": 0.6624,
|
2373 |
+
"step": 3700
|
2374 |
+
},
|
2375 |
+
{
|
2376 |
+
"epoch": 2.39,
|
2377 |
+
"learning_rate": 0.00015889250814332247,
|
2378 |
+
"loss": 0.6436,
|
2379 |
+
"step": 3710
|
2380 |
+
},
|
2381 |
+
{
|
2382 |
+
"epoch": 2.39,
|
2383 |
+
"learning_rate": 0.00015850162866449507,
|
2384 |
+
"loss": 0.6792,
|
2385 |
+
"step": 3720
|
2386 |
+
},
|
2387 |
+
{
|
2388 |
+
"epoch": 2.4,
|
2389 |
+
"learning_rate": 0.00015811074918566773,
|
2390 |
+
"loss": 0.6549,
|
2391 |
+
"step": 3730
|
2392 |
+
},
|
2393 |
+
{
|
2394 |
+
"epoch": 2.41,
|
2395 |
+
"learning_rate": 0.00015771986970684038,
|
2396 |
+
"loss": 0.655,
|
2397 |
+
"step": 3740
|
2398 |
+
},
|
2399 |
+
{
|
2400 |
+
"epoch": 2.41,
|
2401 |
+
"learning_rate": 0.000157328990228013,
|
2402 |
+
"loss": 0.6468,
|
2403 |
+
"step": 3750
|
2404 |
+
},
|
2405 |
+
{
|
2406 |
+
"epoch": 2.42,
|
2407 |
+
"learning_rate": 0.00015693811074918567,
|
2408 |
+
"loss": 0.6489,
|
2409 |
+
"step": 3760
|
2410 |
+
},
|
2411 |
+
{
|
2412 |
+
"epoch": 2.42,
|
2413 |
+
"learning_rate": 0.0001565472312703583,
|
2414 |
+
"loss": 0.6587,
|
2415 |
+
"step": 3770
|
2416 |
+
},
|
2417 |
+
{
|
2418 |
+
"epoch": 2.43,
|
2419 |
+
"learning_rate": 0.00015615635179153092,
|
2420 |
+
"loss": 0.6506,
|
2421 |
+
"step": 3780
|
2422 |
+
},
|
2423 |
+
{
|
2424 |
+
"epoch": 2.44,
|
2425 |
+
"learning_rate": 0.00015576547231270355,
|
2426 |
+
"loss": 0.6525,
|
2427 |
+
"step": 3790
|
2428 |
+
},
|
2429 |
+
{
|
2430 |
+
"epoch": 2.44,
|
2431 |
+
"learning_rate": 0.0001553745928338762,
|
2432 |
+
"loss": 0.6554,
|
2433 |
+
"step": 3800
|
2434 |
+
},
|
2435 |
+
{
|
2436 |
+
"epoch": 2.44,
|
2437 |
+
"eval_loss": 0.7240291833877563,
|
2438 |
+
"eval_runtime": 304.5938,
|
2439 |
+
"eval_samples_per_second": 6.566,
|
2440 |
+
"eval_steps_per_second": 0.821,
|
2441 |
+
"step": 3800
|
2442 |
+
},
|
2443 |
+
{
|
2444 |
+
"epoch": 2.45,
|
2445 |
+
"learning_rate": 0.00015498371335504886,
|
2446 |
+
"loss": 0.6404,
|
2447 |
+
"step": 3810
|
2448 |
+
},
|
2449 |
+
{
|
2450 |
+
"epoch": 2.46,
|
2451 |
+
"learning_rate": 0.0001545928338762215,
|
2452 |
+
"loss": 0.6856,
|
2453 |
+
"step": 3820
|
2454 |
+
},
|
2455 |
+
{
|
2456 |
+
"epoch": 2.46,
|
2457 |
+
"learning_rate": 0.00015420195439739412,
|
2458 |
+
"loss": 0.6508,
|
2459 |
+
"step": 3830
|
2460 |
+
},
|
2461 |
+
{
|
2462 |
+
"epoch": 2.47,
|
2463 |
+
"learning_rate": 0.00015381107491856675,
|
2464 |
+
"loss": 0.6485,
|
2465 |
+
"step": 3840
|
2466 |
+
},
|
2467 |
+
{
|
2468 |
+
"epoch": 2.48,
|
2469 |
+
"learning_rate": 0.0001534201954397394,
|
2470 |
+
"loss": 0.626,
|
2471 |
+
"step": 3850
|
2472 |
+
},
|
2473 |
+
{
|
2474 |
+
"epoch": 2.48,
|
2475 |
+
"learning_rate": 0.00015302931596091206,
|
2476 |
+
"loss": 0.6595,
|
2477 |
+
"step": 3860
|
2478 |
+
},
|
2479 |
+
{
|
2480 |
+
"epoch": 2.49,
|
2481 |
+
"learning_rate": 0.00015263843648208469,
|
2482 |
+
"loss": 0.6737,
|
2483 |
+
"step": 3870
|
2484 |
+
},
|
2485 |
+
{
|
2486 |
+
"epoch": 2.5,
|
2487 |
+
"learning_rate": 0.00015224755700325731,
|
2488 |
+
"loss": 0.634,
|
2489 |
+
"step": 3880
|
2490 |
+
},
|
2491 |
+
{
|
2492 |
+
"epoch": 2.5,
|
2493 |
+
"learning_rate": 0.00015185667752442994,
|
2494 |
+
"loss": 0.6691,
|
2495 |
+
"step": 3890
|
2496 |
+
},
|
2497 |
+
{
|
2498 |
+
"epoch": 2.51,
|
2499 |
+
"learning_rate": 0.0001514657980456026,
|
2500 |
+
"loss": 0.6507,
|
2501 |
+
"step": 3900
|
2502 |
+
},
|
2503 |
+
{
|
2504 |
+
"epoch": 2.51,
|
2505 |
+
"learning_rate": 0.00015107491856677523,
|
2506 |
+
"loss": 0.6438,
|
2507 |
+
"step": 3910
|
2508 |
+
},
|
2509 |
+
{
|
2510 |
+
"epoch": 2.52,
|
2511 |
+
"learning_rate": 0.00015068403908794788,
|
2512 |
+
"loss": 0.6553,
|
2513 |
+
"step": 3920
|
2514 |
+
},
|
2515 |
+
{
|
2516 |
+
"epoch": 2.53,
|
2517 |
+
"learning_rate": 0.00015029315960912048,
|
2518 |
+
"loss": 0.6753,
|
2519 |
+
"step": 3930
|
2520 |
+
},
|
2521 |
+
{
|
2522 |
+
"epoch": 2.53,
|
2523 |
+
"learning_rate": 0.00014990228013029314,
|
2524 |
+
"loss": 0.6727,
|
2525 |
+
"step": 3940
|
2526 |
+
},
|
2527 |
+
{
|
2528 |
+
"epoch": 2.54,
|
2529 |
+
"learning_rate": 0.0001495114006514658,
|
2530 |
+
"loss": 0.6462,
|
2531 |
+
"step": 3950
|
2532 |
+
},
|
2533 |
+
{
|
2534 |
+
"epoch": 2.55,
|
2535 |
+
"learning_rate": 0.00014912052117263842,
|
2536 |
+
"loss": 0.6605,
|
2537 |
+
"step": 3960
|
2538 |
+
},
|
2539 |
+
{
|
2540 |
+
"epoch": 2.55,
|
2541 |
+
"learning_rate": 0.00014872964169381105,
|
2542 |
+
"loss": 0.651,
|
2543 |
+
"step": 3970
|
2544 |
+
},
|
2545 |
+
{
|
2546 |
+
"epoch": 2.56,
|
2547 |
+
"learning_rate": 0.0001483387622149837,
|
2548 |
+
"loss": 0.668,
|
2549 |
+
"step": 3980
|
2550 |
+
},
|
2551 |
+
{
|
2552 |
+
"epoch": 2.57,
|
2553 |
+
"learning_rate": 0.00014794788273615633,
|
2554 |
+
"loss": 0.6631,
|
2555 |
+
"step": 3990
|
2556 |
+
},
|
2557 |
+
{
|
2558 |
+
"epoch": 2.57,
|
2559 |
+
"learning_rate": 0.000147557003257329,
|
2560 |
+
"loss": 0.6676,
|
2561 |
+
"step": 4000
|
2562 |
+
},
|
2563 |
+
{
|
2564 |
+
"epoch": 2.57,
|
2565 |
+
"eval_loss": 0.7227743268013,
|
2566 |
+
"eval_runtime": 305.0392,
|
2567 |
+
"eval_samples_per_second": 6.557,
|
2568 |
+
"eval_steps_per_second": 0.82,
|
2569 |
+
"step": 4000
|
2570 |
+
},
|
2571 |
+
{
|
2572 |
+
"epoch": 2.58,
|
2573 |
+
"learning_rate": 0.00014716612377850162,
|
2574 |
+
"loss": 0.6438,
|
2575 |
+
"step": 4010
|
2576 |
+
},
|
2577 |
+
{
|
2578 |
+
"epoch": 2.59,
|
2579 |
+
"learning_rate": 0.00014677524429967424,
|
2580 |
+
"loss": 0.6503,
|
2581 |
+
"step": 4020
|
2582 |
+
},
|
2583 |
+
{
|
2584 |
+
"epoch": 2.59,
|
2585 |
+
"learning_rate": 0.0001463843648208469,
|
2586 |
+
"loss": 0.6534,
|
2587 |
+
"step": 4030
|
2588 |
+
},
|
2589 |
+
{
|
2590 |
+
"epoch": 2.6,
|
2591 |
+
"learning_rate": 0.00014599348534201953,
|
2592 |
+
"loss": 0.6497,
|
2593 |
+
"step": 4040
|
2594 |
+
},
|
2595 |
+
{
|
2596 |
+
"epoch": 2.6,
|
2597 |
+
"learning_rate": 0.00014560260586319216,
|
2598 |
+
"loss": 0.6633,
|
2599 |
+
"step": 4050
|
2600 |
+
},
|
2601 |
+
{
|
2602 |
+
"epoch": 2.61,
|
2603 |
+
"learning_rate": 0.0001452117263843648,
|
2604 |
+
"loss": 0.6473,
|
2605 |
+
"step": 4060
|
2606 |
+
},
|
2607 |
+
{
|
2608 |
+
"epoch": 2.62,
|
2609 |
+
"learning_rate": 0.00014482084690553744,
|
2610 |
+
"loss": 0.6532,
|
2611 |
+
"step": 4070
|
2612 |
+
},
|
2613 |
+
{
|
2614 |
+
"epoch": 2.62,
|
2615 |
+
"learning_rate": 0.0001444299674267101,
|
2616 |
+
"loss": 0.6687,
|
2617 |
+
"step": 4080
|
2618 |
+
},
|
2619 |
+
{
|
2620 |
+
"epoch": 2.63,
|
2621 |
+
"learning_rate": 0.00014403908794788272,
|
2622 |
+
"loss": 0.6582,
|
2623 |
+
"step": 4090
|
2624 |
+
},
|
2625 |
+
{
|
2626 |
+
"epoch": 2.64,
|
2627 |
+
"learning_rate": 0.00014364820846905535,
|
2628 |
+
"loss": 0.6498,
|
2629 |
+
"step": 4100
|
2630 |
+
},
|
2631 |
+
{
|
2632 |
+
"epoch": 2.64,
|
2633 |
+
"learning_rate": 0.000143257328990228,
|
2634 |
+
"loss": 0.6665,
|
2635 |
+
"step": 4110
|
2636 |
+
},
|
2637 |
+
{
|
2638 |
+
"epoch": 2.65,
|
2639 |
+
"learning_rate": 0.00014286644951140063,
|
2640 |
+
"loss": 0.6519,
|
2641 |
+
"step": 4120
|
2642 |
+
},
|
2643 |
+
{
|
2644 |
+
"epoch": 2.66,
|
2645 |
+
"learning_rate": 0.0001424755700325733,
|
2646 |
+
"loss": 0.6597,
|
2647 |
+
"step": 4130
|
2648 |
+
},
|
2649 |
+
{
|
2650 |
+
"epoch": 2.66,
|
2651 |
+
"learning_rate": 0.00014208469055374592,
|
2652 |
+
"loss": 0.6585,
|
2653 |
+
"step": 4140
|
2654 |
+
},
|
2655 |
+
{
|
2656 |
+
"epoch": 2.67,
|
2657 |
+
"learning_rate": 0.00014169381107491854,
|
2658 |
+
"loss": 0.6614,
|
2659 |
+
"step": 4150
|
2660 |
+
},
|
2661 |
+
{
|
2662 |
+
"epoch": 2.68,
|
2663 |
+
"learning_rate": 0.0001413029315960912,
|
2664 |
+
"loss": 0.641,
|
2665 |
+
"step": 4160
|
2666 |
+
},
|
2667 |
+
{
|
2668 |
+
"epoch": 2.68,
|
2669 |
+
"learning_rate": 0.00014091205211726383,
|
2670 |
+
"loss": 0.6417,
|
2671 |
+
"step": 4170
|
2672 |
+
},
|
2673 |
+
{
|
2674 |
+
"epoch": 2.69,
|
2675 |
+
"learning_rate": 0.00014052117263843646,
|
2676 |
+
"loss": 0.6844,
|
2677 |
+
"step": 4180
|
2678 |
+
},
|
2679 |
+
{
|
2680 |
+
"epoch": 2.69,
|
2681 |
+
"learning_rate": 0.0001401302931596091,
|
2682 |
+
"loss": 0.6464,
|
2683 |
+
"step": 4190
|
2684 |
+
},
|
2685 |
+
{
|
2686 |
+
"epoch": 2.7,
|
2687 |
+
"learning_rate": 0.00013973941368078174,
|
2688 |
+
"loss": 0.6689,
|
2689 |
+
"step": 4200
|
2690 |
+
},
|
2691 |
+
{
|
2692 |
+
"epoch": 2.7,
|
2693 |
+
"eval_loss": 0.7206348776817322,
|
2694 |
+
"eval_runtime": 302.1995,
|
2695 |
+
"eval_samples_per_second": 6.618,
|
2696 |
+
"eval_steps_per_second": 0.827,
|
2697 |
+
"step": 4200
|
2698 |
+
}
|
2699 |
+
],
|
2700 |
+
"logging_steps": 10,
|
2701 |
+
"max_steps": 7775,
|
2702 |
+
"num_train_epochs": 5,
|
2703 |
+
"save_steps": 200,
|
2704 |
+
"total_flos": 3.0362368185357926e+18,
|
2705 |
+
"trial_name": null,
|
2706 |
+
"trial_params": null
|
2707 |
+
}
|
with_input/decomp_plan/llama-2-13b/best_model/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c539647211831005ee13a101575d3f7569fecb194ab8e42d373a484c2c5d357
|
3 |
+
size 4091
|