Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- adapter_config.json +26 -0
- adapter_model.safetensors +3 -0
- checkpoint-3500/adapter_config.json +26 -0
- checkpoint-3500/adapter_model.safetensors +3 -0
- checkpoint-3500/optimizer.pt +3 -0
- checkpoint-3500/rng_state.pth +3 -0
- checkpoint-3500/scheduler.pt +3 -0
- checkpoint-3500/trainer_state.json +3043 -0
- checkpoint-3500/training_args.bin +3 -0
- git_hash.txt +1 -0
- preprocessor_config.json +40 -0
- results.json +1 -0
- special_tokens_map.json +39 -0
- tokenizer.json +3 -0
- tokenizer_config.json +0 -0
- training_config.yml +40 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "./models/colpaligemma-3b-mix-448-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": "gaussian",
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": "(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
| 23 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 24 |
+
"use_dora": false,
|
| 25 |
+
"use_rslora": false
|
| 26 |
+
}
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0cbdb6c0ebcb00260da3b1f6130f4a8892268f719b2d7be7e7ad07115abc1102
|
| 3 |
+
size 78625112
|
checkpoint-3500/adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "./models/colpaligemma-3b-mix-448-base",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": false,
|
| 8 |
+
"init_lora_weights": "gaussian",
|
| 9 |
+
"layer_replication": null,
|
| 10 |
+
"layers_pattern": null,
|
| 11 |
+
"layers_to_transform": null,
|
| 12 |
+
"loftq_config": {},
|
| 13 |
+
"lora_alpha": 32,
|
| 14 |
+
"lora_dropout": 0.1,
|
| 15 |
+
"megatron_config": null,
|
| 16 |
+
"megatron_core": "megatron.core",
|
| 17 |
+
"modules_to_save": null,
|
| 18 |
+
"peft_type": "LORA",
|
| 19 |
+
"r": 32,
|
| 20 |
+
"rank_pattern": {},
|
| 21 |
+
"revision": null,
|
| 22 |
+
"target_modules": "(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)",
|
| 23 |
+
"task_type": "FEATURE_EXTRACTION",
|
| 24 |
+
"use_dora": false,
|
| 25 |
+
"use_rslora": false
|
| 26 |
+
}
|
checkpoint-3500/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:948ed5e57c2eb866701430f59e28b3d8de670812cfcd932e1394b744031f1f26
|
| 3 |
+
size 78625112
|
checkpoint-3500/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bea68c5eabf40ec234adc42a4173115af50a1716e1827015da07d9088f71f052
|
| 3 |
+
size 157385722
|
checkpoint-3500/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0db386b438469df3ebf9750bd7c478ec4af19326ab81182cad3bd6f8baa775cd
|
| 3 |
+
size 14244
|
checkpoint-3500/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dec2a32bee5157051265785df8f5c2b01ebf99f431525907c20aae270b809aea
|
| 3 |
+
size 1064
|
checkpoint-3500/trainer_state.json
ADDED
|
@@ -0,0 +1,3043 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9474824038982134,
|
| 5 |
+
"eval_steps": 50,
|
| 6 |
+
"global_step": 3500,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0027070925825663237,
|
| 13 |
+
"grad_norm": 0.81640625,
|
| 14 |
+
"learning_rate": 5e-06,
|
| 15 |
+
"loss": 0.7309,
|
| 16 |
+
"step": 10
|
| 17 |
+
},
|
| 18 |
+
{
|
| 19 |
+
"epoch": 0.005414185165132647,
|
| 20 |
+
"grad_norm": 1.2578125,
|
| 21 |
+
"learning_rate": 1e-05,
|
| 22 |
+
"loss": 0.7211,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"epoch": 0.008121277747698972,
|
| 27 |
+
"grad_norm": 0.7265625,
|
| 28 |
+
"learning_rate": 1.5e-05,
|
| 29 |
+
"loss": 0.7223,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"epoch": 0.010828370330265295,
|
| 34 |
+
"grad_norm": 0.640625,
|
| 35 |
+
"learning_rate": 2e-05,
|
| 36 |
+
"loss": 0.7158,
|
| 37 |
+
"step": 40
|
| 38 |
+
},
|
| 39 |
+
{
|
| 40 |
+
"epoch": 0.01353546291283162,
|
| 41 |
+
"grad_norm": 0.427734375,
|
| 42 |
+
"learning_rate": 2.5e-05,
|
| 43 |
+
"loss": 0.7123,
|
| 44 |
+
"step": 50
|
| 45 |
+
},
|
| 46 |
+
{
|
| 47 |
+
"epoch": 0.01353546291283162,
|
| 48 |
+
"eval_loss": 0.711525022983551,
|
| 49 |
+
"eval_runtime": 105.29,
|
| 50 |
+
"eval_samples_per_second": 4.749,
|
| 51 |
+
"eval_steps_per_second": 0.152,
|
| 52 |
+
"step": 50
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.016242555495397944,
|
| 56 |
+
"grad_norm": 0.8125,
|
| 57 |
+
"learning_rate": 3e-05,
|
| 58 |
+
"loss": 0.7142,
|
| 59 |
+
"step": 60
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.018949648077964266,
|
| 63 |
+
"grad_norm": 0.58203125,
|
| 64 |
+
"learning_rate": 3.5e-05,
|
| 65 |
+
"loss": 0.7052,
|
| 66 |
+
"step": 70
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02165674066053059,
|
| 70 |
+
"grad_norm": 0.62109375,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 0.7083,
|
| 73 |
+
"step": 80
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.024363833243096916,
|
| 77 |
+
"grad_norm": 0.98046875,
|
| 78 |
+
"learning_rate": 4.5e-05,
|
| 79 |
+
"loss": 0.7036,
|
| 80 |
+
"step": 90
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.02707092582566324,
|
| 84 |
+
"grad_norm": 0.6640625,
|
| 85 |
+
"learning_rate": 5e-05,
|
| 86 |
+
"loss": 0.6903,
|
| 87 |
+
"step": 100
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02707092582566324,
|
| 91 |
+
"eval_loss": 0.6922177672386169,
|
| 92 |
+
"eval_runtime": 63.6777,
|
| 93 |
+
"eval_samples_per_second": 7.852,
|
| 94 |
+
"eval_steps_per_second": 0.251,
|
| 95 |
+
"step": 100
|
| 96 |
+
},
|
| 97 |
+
{
|
| 98 |
+
"epoch": 0.02977801840822956,
|
| 99 |
+
"grad_norm": 0.96875,
|
| 100 |
+
"learning_rate": 4.986087924318308e-05,
|
| 101 |
+
"loss": 0.6695,
|
| 102 |
+
"step": 110
|
| 103 |
+
},
|
| 104 |
+
{
|
| 105 |
+
"epoch": 0.03248511099079589,
|
| 106 |
+
"grad_norm": 1.6484375,
|
| 107 |
+
"learning_rate": 4.972175848636616e-05,
|
| 108 |
+
"loss": 0.6261,
|
| 109 |
+
"step": 120
|
| 110 |
+
},
|
| 111 |
+
{
|
| 112 |
+
"epoch": 0.03519220357336221,
|
| 113 |
+
"grad_norm": 1.453125,
|
| 114 |
+
"learning_rate": 4.958263772954925e-05,
|
| 115 |
+
"loss": 0.5779,
|
| 116 |
+
"step": 130
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.03789929615592853,
|
| 120 |
+
"grad_norm": 3.09375,
|
| 121 |
+
"learning_rate": 4.944351697273234e-05,
|
| 122 |
+
"loss": 0.5185,
|
| 123 |
+
"step": 140
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.040606388738494856,
|
| 127 |
+
"grad_norm": 2.375,
|
| 128 |
+
"learning_rate": 4.930439621591542e-05,
|
| 129 |
+
"loss": 0.4695,
|
| 130 |
+
"step": 150
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.040606388738494856,
|
| 134 |
+
"eval_loss": 0.45527857542037964,
|
| 135 |
+
"eval_runtime": 64.9387,
|
| 136 |
+
"eval_samples_per_second": 7.7,
|
| 137 |
+
"eval_steps_per_second": 0.246,
|
| 138 |
+
"step": 150
|
| 139 |
+
},
|
| 140 |
+
{
|
| 141 |
+
"epoch": 0.04331348132106118,
|
| 142 |
+
"grad_norm": 3.984375,
|
| 143 |
+
"learning_rate": 4.91652754590985e-05,
|
| 144 |
+
"loss": 0.4536,
|
| 145 |
+
"step": 160
|
| 146 |
+
},
|
| 147 |
+
{
|
| 148 |
+
"epoch": 0.0460205739036275,
|
| 149 |
+
"grad_norm": 3.671875,
|
| 150 |
+
"learning_rate": 4.9026154702281585e-05,
|
| 151 |
+
"loss": 0.4113,
|
| 152 |
+
"step": 170
|
| 153 |
+
},
|
| 154 |
+
{
|
| 155 |
+
"epoch": 0.04872766648619383,
|
| 156 |
+
"grad_norm": 2.71875,
|
| 157 |
+
"learning_rate": 4.8887033945464666e-05,
|
| 158 |
+
"loss": 0.3874,
|
| 159 |
+
"step": 180
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.051434759068760154,
|
| 163 |
+
"grad_norm": 1.6640625,
|
| 164 |
+
"learning_rate": 4.8747913188647746e-05,
|
| 165 |
+
"loss": 0.3714,
|
| 166 |
+
"step": 190
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.05414185165132648,
|
| 170 |
+
"grad_norm": 4.1875,
|
| 171 |
+
"learning_rate": 4.8608792431830826e-05,
|
| 172 |
+
"loss": 0.294,
|
| 173 |
+
"step": 200
|
| 174 |
+
},
|
| 175 |
+
{
|
| 176 |
+
"epoch": 0.05414185165132648,
|
| 177 |
+
"eval_loss": 0.3422486186027527,
|
| 178 |
+
"eval_runtime": 64.2742,
|
| 179 |
+
"eval_samples_per_second": 7.779,
|
| 180 |
+
"eval_steps_per_second": 0.249,
|
| 181 |
+
"step": 200
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"epoch": 0.0568489442338928,
|
| 185 |
+
"grad_norm": 3.625,
|
| 186 |
+
"learning_rate": 4.8469671675013914e-05,
|
| 187 |
+
"loss": 0.4054,
|
| 188 |
+
"step": 210
|
| 189 |
+
},
|
| 190 |
+
{
|
| 191 |
+
"epoch": 0.05955603681645912,
|
| 192 |
+
"grad_norm": 2.984375,
|
| 193 |
+
"learning_rate": 4.8330550918197e-05,
|
| 194 |
+
"loss": 0.3213,
|
| 195 |
+
"step": 220
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.062263129399025445,
|
| 199 |
+
"grad_norm": 3.46875,
|
| 200 |
+
"learning_rate": 4.819143016138008e-05,
|
| 201 |
+
"loss": 0.3261,
|
| 202 |
+
"step": 230
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.06497022198159177,
|
| 206 |
+
"grad_norm": 2.328125,
|
| 207 |
+
"learning_rate": 4.805230940456316e-05,
|
| 208 |
+
"loss": 0.2817,
|
| 209 |
+
"step": 240
|
| 210 |
+
},
|
| 211 |
+
{
|
| 212 |
+
"epoch": 0.0676773145641581,
|
| 213 |
+
"grad_norm": 2.59375,
|
| 214 |
+
"learning_rate": 4.791318864774624e-05,
|
| 215 |
+
"loss": 0.2502,
|
| 216 |
+
"step": 250
|
| 217 |
+
},
|
| 218 |
+
{
|
| 219 |
+
"epoch": 0.0676773145641581,
|
| 220 |
+
"eval_loss": 0.2796708643436432,
|
| 221 |
+
"eval_runtime": 63.6818,
|
| 222 |
+
"eval_samples_per_second": 7.852,
|
| 223 |
+
"eval_steps_per_second": 0.251,
|
| 224 |
+
"step": 250
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.07038440714672442,
|
| 228 |
+
"grad_norm": 3.765625,
|
| 229 |
+
"learning_rate": 4.777406789092933e-05,
|
| 230 |
+
"loss": 0.2768,
|
| 231 |
+
"step": 260
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.07309149972929074,
|
| 235 |
+
"grad_norm": 6.375,
|
| 236 |
+
"learning_rate": 4.763494713411241e-05,
|
| 237 |
+
"loss": 0.2615,
|
| 238 |
+
"step": 270
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.07579859231185707,
|
| 242 |
+
"grad_norm": 3.328125,
|
| 243 |
+
"learning_rate": 4.7495826377295496e-05,
|
| 244 |
+
"loss": 0.248,
|
| 245 |
+
"step": 280
|
| 246 |
+
},
|
| 247 |
+
{
|
| 248 |
+
"epoch": 0.07850568489442339,
|
| 249 |
+
"grad_norm": 2.109375,
|
| 250 |
+
"learning_rate": 4.735670562047858e-05,
|
| 251 |
+
"loss": 0.1904,
|
| 252 |
+
"step": 290
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"epoch": 0.08121277747698971,
|
| 256 |
+
"grad_norm": 1.7734375,
|
| 257 |
+
"learning_rate": 4.7217584863661664e-05,
|
| 258 |
+
"loss": 0.2066,
|
| 259 |
+
"step": 300
|
| 260 |
+
},
|
| 261 |
+
{
|
| 262 |
+
"epoch": 0.08121277747698971,
|
| 263 |
+
"eval_loss": 0.24386852979660034,
|
| 264 |
+
"eval_runtime": 63.7131,
|
| 265 |
+
"eval_samples_per_second": 7.848,
|
| 266 |
+
"eval_steps_per_second": 0.251,
|
| 267 |
+
"step": 300
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.08391987005955603,
|
| 271 |
+
"grad_norm": 2.515625,
|
| 272 |
+
"learning_rate": 4.7078464106844744e-05,
|
| 273 |
+
"loss": 0.2251,
|
| 274 |
+
"step": 310
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.08662696264212236,
|
| 278 |
+
"grad_norm": 1.9453125,
|
| 279 |
+
"learning_rate": 4.6939343350027825e-05,
|
| 280 |
+
"loss": 0.2066,
|
| 281 |
+
"step": 320
|
| 282 |
+
},
|
| 283 |
+
{
|
| 284 |
+
"epoch": 0.08933405522468868,
|
| 285 |
+
"grad_norm": 1.8515625,
|
| 286 |
+
"learning_rate": 4.6800222593210905e-05,
|
| 287 |
+
"loss": 0.1942,
|
| 288 |
+
"step": 330
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.092041147807255,
|
| 292 |
+
"grad_norm": 2.3125,
|
| 293 |
+
"learning_rate": 4.666110183639399e-05,
|
| 294 |
+
"loss": 0.2184,
|
| 295 |
+
"step": 340
|
| 296 |
+
},
|
| 297 |
+
{
|
| 298 |
+
"epoch": 0.09474824038982133,
|
| 299 |
+
"grad_norm": 2.265625,
|
| 300 |
+
"learning_rate": 4.652198107957708e-05,
|
| 301 |
+
"loss": 0.2343,
|
| 302 |
+
"step": 350
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.09474824038982133,
|
| 306 |
+
"eval_loss": 0.23647841811180115,
|
| 307 |
+
"eval_runtime": 63.9433,
|
| 308 |
+
"eval_samples_per_second": 7.819,
|
| 309 |
+
"eval_steps_per_second": 0.25,
|
| 310 |
+
"step": 350
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.09745533297238766,
|
| 314 |
+
"grad_norm": 2.09375,
|
| 315 |
+
"learning_rate": 4.638286032276016e-05,
|
| 316 |
+
"loss": 0.2554,
|
| 317 |
+
"step": 360
|
| 318 |
+
},
|
| 319 |
+
{
|
| 320 |
+
"epoch": 0.10016242555495398,
|
| 321 |
+
"grad_norm": 1.828125,
|
| 322 |
+
"learning_rate": 4.624373956594324e-05,
|
| 323 |
+
"loss": 0.2288,
|
| 324 |
+
"step": 370
|
| 325 |
+
},
|
| 326 |
+
{
|
| 327 |
+
"epoch": 0.10286951813752031,
|
| 328 |
+
"grad_norm": 2.328125,
|
| 329 |
+
"learning_rate": 4.610461880912633e-05,
|
| 330 |
+
"loss": 0.2159,
|
| 331 |
+
"step": 380
|
| 332 |
+
},
|
| 333 |
+
{
|
| 334 |
+
"epoch": 0.10557661072008663,
|
| 335 |
+
"grad_norm": 2.1875,
|
| 336 |
+
"learning_rate": 4.596549805230941e-05,
|
| 337 |
+
"loss": 0.1825,
|
| 338 |
+
"step": 390
|
| 339 |
+
},
|
| 340 |
+
{
|
| 341 |
+
"epoch": 0.10828370330265295,
|
| 342 |
+
"grad_norm": 2.4375,
|
| 343 |
+
"learning_rate": 4.582637729549249e-05,
|
| 344 |
+
"loss": 0.2525,
|
| 345 |
+
"step": 400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.10828370330265295,
|
| 349 |
+
"eval_loss": 0.21003711223602295,
|
| 350 |
+
"eval_runtime": 64.3464,
|
| 351 |
+
"eval_samples_per_second": 7.77,
|
| 352 |
+
"eval_steps_per_second": 0.249,
|
| 353 |
+
"step": 400
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.11099079588521928,
|
| 357 |
+
"grad_norm": 2.4375,
|
| 358 |
+
"learning_rate": 4.568725653867557e-05,
|
| 359 |
+
"loss": 0.1708,
|
| 360 |
+
"step": 410
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.1136978884677856,
|
| 364 |
+
"grad_norm": 3.140625,
|
| 365 |
+
"learning_rate": 4.5548135781858655e-05,
|
| 366 |
+
"loss": 0.1939,
|
| 367 |
+
"step": 420
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.11640498105035192,
|
| 371 |
+
"grad_norm": 2.5625,
|
| 372 |
+
"learning_rate": 4.540901502504174e-05,
|
| 373 |
+
"loss": 0.1732,
|
| 374 |
+
"step": 430
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.11911207363291824,
|
| 378 |
+
"grad_norm": 1.3984375,
|
| 379 |
+
"learning_rate": 4.526989426822482e-05,
|
| 380 |
+
"loss": 0.2078,
|
| 381 |
+
"step": 440
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.12181916621548457,
|
| 385 |
+
"grad_norm": 7.5,
|
| 386 |
+
"learning_rate": 4.51307735114079e-05,
|
| 387 |
+
"loss": 0.1984,
|
| 388 |
+
"step": 450
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.12181916621548457,
|
| 392 |
+
"eval_loss": 0.2016001045703888,
|
| 393 |
+
"eval_runtime": 98.9371,
|
| 394 |
+
"eval_samples_per_second": 5.054,
|
| 395 |
+
"eval_steps_per_second": 0.162,
|
| 396 |
+
"step": 450
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.12452625879805089,
|
| 400 |
+
"grad_norm": 2.78125,
|
| 401 |
+
"learning_rate": 4.4991652754590984e-05,
|
| 402 |
+
"loss": 0.1846,
|
| 403 |
+
"step": 460
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.12723335138061723,
|
| 407 |
+
"grad_norm": 1.0,
|
| 408 |
+
"learning_rate": 4.485253199777407e-05,
|
| 409 |
+
"loss": 0.1628,
|
| 410 |
+
"step": 470
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.12994044396318355,
|
| 414 |
+
"grad_norm": 0.65625,
|
| 415 |
+
"learning_rate": 4.471341124095715e-05,
|
| 416 |
+
"loss": 0.1627,
|
| 417 |
+
"step": 480
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.13264753654574987,
|
| 421 |
+
"grad_norm": 1.1953125,
|
| 422 |
+
"learning_rate": 4.457429048414024e-05,
|
| 423 |
+
"loss": 0.1694,
|
| 424 |
+
"step": 490
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.1353546291283162,
|
| 428 |
+
"grad_norm": 1.5078125,
|
| 429 |
+
"learning_rate": 4.443516972732332e-05,
|
| 430 |
+
"loss": 0.2156,
|
| 431 |
+
"step": 500
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.1353546291283162,
|
| 435 |
+
"eval_loss": 0.19197307527065277,
|
| 436 |
+
"eval_runtime": 72.4725,
|
| 437 |
+
"eval_samples_per_second": 6.899,
|
| 438 |
+
"eval_steps_per_second": 0.221,
|
| 439 |
+
"step": 500
|
| 440 |
+
},
|
| 441 |
+
{
|
| 442 |
+
"epoch": 0.13806172171088252,
|
| 443 |
+
"grad_norm": 3.140625,
|
| 444 |
+
"learning_rate": 4.4296048970506406e-05,
|
| 445 |
+
"loss": 0.1641,
|
| 446 |
+
"step": 510
|
| 447 |
+
},
|
| 448 |
+
{
|
| 449 |
+
"epoch": 0.14076881429344884,
|
| 450 |
+
"grad_norm": 2.359375,
|
| 451 |
+
"learning_rate": 4.4156928213689486e-05,
|
| 452 |
+
"loss": 0.1925,
|
| 453 |
+
"step": 520
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.14347590687601516,
|
| 457 |
+
"grad_norm": 1.375,
|
| 458 |
+
"learning_rate": 4.4017807456872566e-05,
|
| 459 |
+
"loss": 0.1794,
|
| 460 |
+
"step": 530
|
| 461 |
+
},
|
| 462 |
+
{
|
| 463 |
+
"epoch": 0.1461829994585815,
|
| 464 |
+
"grad_norm": 4.96875,
|
| 465 |
+
"learning_rate": 4.387868670005565e-05,
|
| 466 |
+
"loss": 0.197,
|
| 467 |
+
"step": 540
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.1488900920411478,
|
| 471 |
+
"grad_norm": 1.1015625,
|
| 472 |
+
"learning_rate": 4.373956594323873e-05,
|
| 473 |
+
"loss": 0.1423,
|
| 474 |
+
"step": 550
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.1488900920411478,
|
| 478 |
+
"eval_loss": 0.19690875709056854,
|
| 479 |
+
"eval_runtime": 62.7419,
|
| 480 |
+
"eval_samples_per_second": 7.969,
|
| 481 |
+
"eval_steps_per_second": 0.255,
|
| 482 |
+
"step": 550
|
| 483 |
+
},
|
| 484 |
+
{
|
| 485 |
+
"epoch": 0.15159718462371413,
|
| 486 |
+
"grad_norm": 1.5234375,
|
| 487 |
+
"learning_rate": 4.360044518642182e-05,
|
| 488 |
+
"loss": 0.1976,
|
| 489 |
+
"step": 560
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.15430427720628045,
|
| 493 |
+
"grad_norm": 0.57421875,
|
| 494 |
+
"learning_rate": 4.34613244296049e-05,
|
| 495 |
+
"loss": 0.14,
|
| 496 |
+
"step": 570
|
| 497 |
+
},
|
| 498 |
+
{
|
| 499 |
+
"epoch": 0.15701136978884678,
|
| 500 |
+
"grad_norm": 2.890625,
|
| 501 |
+
"learning_rate": 4.332220367278798e-05,
|
| 502 |
+
"loss": 0.2063,
|
| 503 |
+
"step": 580
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.1597184623714131,
|
| 507 |
+
"grad_norm": 2.15625,
|
| 508 |
+
"learning_rate": 4.318308291597106e-05,
|
| 509 |
+
"loss": 0.2194,
|
| 510 |
+
"step": 590
|
| 511 |
+
},
|
| 512 |
+
{
|
| 513 |
+
"epoch": 0.16242555495397942,
|
| 514 |
+
"grad_norm": 1.40625,
|
| 515 |
+
"learning_rate": 4.304396215915415e-05,
|
| 516 |
+
"loss": 0.1308,
|
| 517 |
+
"step": 600
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"epoch": 0.16242555495397942,
|
| 521 |
+
"eval_loss": 0.1980336606502533,
|
| 522 |
+
"eval_runtime": 62.7479,
|
| 523 |
+
"eval_samples_per_second": 7.968,
|
| 524 |
+
"eval_steps_per_second": 0.255,
|
| 525 |
+
"step": 600
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.16513264753654575,
|
| 529 |
+
"grad_norm": 0.8046875,
|
| 530 |
+
"learning_rate": 4.290484140233723e-05,
|
| 531 |
+
"loss": 0.1557,
|
| 532 |
+
"step": 610
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.16783974011911207,
|
| 536 |
+
"grad_norm": 2.21875,
|
| 537 |
+
"learning_rate": 4.276572064552031e-05,
|
| 538 |
+
"loss": 0.1923,
|
| 539 |
+
"step": 620
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.1705468327016784,
|
| 543 |
+
"grad_norm": 0.73828125,
|
| 544 |
+
"learning_rate": 4.26265998887034e-05,
|
| 545 |
+
"loss": 0.1714,
|
| 546 |
+
"step": 630
|
| 547 |
+
},
|
| 548 |
+
{
|
| 549 |
+
"epoch": 0.17325392528424471,
|
| 550 |
+
"grad_norm": 3.578125,
|
| 551 |
+
"learning_rate": 4.2487479131886484e-05,
|
| 552 |
+
"loss": 0.184,
|
| 553 |
+
"step": 640
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"epoch": 0.17596101786681104,
|
| 557 |
+
"grad_norm": 1.8125,
|
| 558 |
+
"learning_rate": 4.2348358375069565e-05,
|
| 559 |
+
"loss": 0.2067,
|
| 560 |
+
"step": 650
|
| 561 |
+
},
|
| 562 |
+
{
|
| 563 |
+
"epoch": 0.17596101786681104,
|
| 564 |
+
"eval_loss": 0.19718270003795624,
|
| 565 |
+
"eval_runtime": 62.7349,
|
| 566 |
+
"eval_samples_per_second": 7.97,
|
| 567 |
+
"eval_steps_per_second": 0.255,
|
| 568 |
+
"step": 650
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"epoch": 0.17866811044937736,
|
| 572 |
+
"grad_norm": 2.734375,
|
| 573 |
+
"learning_rate": 4.2209237618252645e-05,
|
| 574 |
+
"loss": 0.156,
|
| 575 |
+
"step": 660
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.18137520303194368,
|
| 579 |
+
"grad_norm": 1.6328125,
|
| 580 |
+
"learning_rate": 4.2070116861435725e-05,
|
| 581 |
+
"loss": 0.1309,
|
| 582 |
+
"step": 670
|
| 583 |
+
},
|
| 584 |
+
{
|
| 585 |
+
"epoch": 0.18408229561451,
|
| 586 |
+
"grad_norm": 3.28125,
|
| 587 |
+
"learning_rate": 4.193099610461881e-05,
|
| 588 |
+
"loss": 0.1983,
|
| 589 |
+
"step": 680
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"epoch": 0.18678938819707633,
|
| 593 |
+
"grad_norm": 1.765625,
|
| 594 |
+
"learning_rate": 4.179187534780189e-05,
|
| 595 |
+
"loss": 0.159,
|
| 596 |
+
"step": 690
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.18949648077964265,
|
| 600 |
+
"grad_norm": 0.62109375,
|
| 601 |
+
"learning_rate": 4.165275459098498e-05,
|
| 602 |
+
"loss": 0.1481,
|
| 603 |
+
"step": 700
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.18949648077964265,
|
| 607 |
+
"eval_loss": 0.1895207166671753,
|
| 608 |
+
"eval_runtime": 62.6131,
|
| 609 |
+
"eval_samples_per_second": 7.986,
|
| 610 |
+
"eval_steps_per_second": 0.256,
|
| 611 |
+
"step": 700
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.19220357336220897,
|
| 615 |
+
"grad_norm": 1.984375,
|
| 616 |
+
"learning_rate": 4.151363383416806e-05,
|
| 617 |
+
"loss": 0.2162,
|
| 618 |
+
"step": 710
|
| 619 |
+
},
|
| 620 |
+
{
|
| 621 |
+
"epoch": 0.19491066594477532,
|
| 622 |
+
"grad_norm": 1.1875,
|
| 623 |
+
"learning_rate": 4.137451307735114e-05,
|
| 624 |
+
"loss": 0.1278,
|
| 625 |
+
"step": 720
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"epoch": 0.19761775852734165,
|
| 629 |
+
"grad_norm": 0.7734375,
|
| 630 |
+
"learning_rate": 4.123539232053423e-05,
|
| 631 |
+
"loss": 0.1714,
|
| 632 |
+
"step": 730
|
| 633 |
+
},
|
| 634 |
+
{
|
| 635 |
+
"epoch": 0.20032485110990797,
|
| 636 |
+
"grad_norm": 1.90625,
|
| 637 |
+
"learning_rate": 4.109627156371731e-05,
|
| 638 |
+
"loss": 0.1764,
|
| 639 |
+
"step": 740
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.2030319436924743,
|
| 643 |
+
"grad_norm": 1.9765625,
|
| 644 |
+
"learning_rate": 4.095715080690039e-05,
|
| 645 |
+
"loss": 0.161,
|
| 646 |
+
"step": 750
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.2030319436924743,
|
| 650 |
+
"eval_loss": 0.18931728601455688,
|
| 651 |
+
"eval_runtime": 63.0862,
|
| 652 |
+
"eval_samples_per_second": 7.926,
|
| 653 |
+
"eval_steps_per_second": 0.254,
|
| 654 |
+
"step": 750
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.20573903627504062,
|
| 658 |
+
"grad_norm": 0.859375,
|
| 659 |
+
"learning_rate": 4.081803005008347e-05,
|
| 660 |
+
"loss": 0.1913,
|
| 661 |
+
"step": 760
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.20844612885760694,
|
| 665 |
+
"grad_norm": 1.0234375,
|
| 666 |
+
"learning_rate": 4.0678909293266556e-05,
|
| 667 |
+
"loss": 0.1447,
|
| 668 |
+
"step": 770
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.21115322144017326,
|
| 672 |
+
"grad_norm": 1.265625,
|
| 673 |
+
"learning_rate": 4.053978853644964e-05,
|
| 674 |
+
"loss": 0.1265,
|
| 675 |
+
"step": 780
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.21386031402273958,
|
| 679 |
+
"grad_norm": 3.5,
|
| 680 |
+
"learning_rate": 4.0400667779632724e-05,
|
| 681 |
+
"loss": 0.1812,
|
| 682 |
+
"step": 790
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.2165674066053059,
|
| 686 |
+
"grad_norm": 1.484375,
|
| 687 |
+
"learning_rate": 4.0261547022815804e-05,
|
| 688 |
+
"loss": 0.1352,
|
| 689 |
+
"step": 800
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.2165674066053059,
|
| 693 |
+
"eval_loss": 0.1901209056377411,
|
| 694 |
+
"eval_runtime": 63.1622,
|
| 695 |
+
"eval_samples_per_second": 7.916,
|
| 696 |
+
"eval_steps_per_second": 0.253,
|
| 697 |
+
"step": 800
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.21927449918787223,
|
| 701 |
+
"grad_norm": 2.390625,
|
| 702 |
+
"learning_rate": 4.012242626599889e-05,
|
| 703 |
+
"loss": 0.1266,
|
| 704 |
+
"step": 810
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.22198159177043855,
|
| 708 |
+
"grad_norm": 2.71875,
|
| 709 |
+
"learning_rate": 3.998330550918197e-05,
|
| 710 |
+
"loss": 0.1408,
|
| 711 |
+
"step": 820
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.22468868435300487,
|
| 715 |
+
"grad_norm": 1.6875,
|
| 716 |
+
"learning_rate": 3.984418475236505e-05,
|
| 717 |
+
"loss": 0.1268,
|
| 718 |
+
"step": 830
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.2273957769355712,
|
| 722 |
+
"grad_norm": 1.5234375,
|
| 723 |
+
"learning_rate": 3.970506399554814e-05,
|
| 724 |
+
"loss": 0.1397,
|
| 725 |
+
"step": 840
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.23010286951813752,
|
| 729 |
+
"grad_norm": 1.421875,
|
| 730 |
+
"learning_rate": 3.956594323873122e-05,
|
| 731 |
+
"loss": 0.2107,
|
| 732 |
+
"step": 850
|
| 733 |
+
},
|
| 734 |
+
{
|
| 735 |
+
"epoch": 0.23010286951813752,
|
| 736 |
+
"eval_loss": 0.18407949805259705,
|
| 737 |
+
"eval_runtime": 62.4768,
|
| 738 |
+
"eval_samples_per_second": 8.003,
|
| 739 |
+
"eval_steps_per_second": 0.256,
|
| 740 |
+
"step": 850
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.23280996210070384,
|
| 744 |
+
"grad_norm": 2.515625,
|
| 745 |
+
"learning_rate": 3.9426822481914307e-05,
|
| 746 |
+
"loss": 0.1519,
|
| 747 |
+
"step": 860
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.23551705468327017,
|
| 751 |
+
"grad_norm": 2.3125,
|
| 752 |
+
"learning_rate": 3.928770172509739e-05,
|
| 753 |
+
"loss": 0.1877,
|
| 754 |
+
"step": 870
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.2382241472658365,
|
| 758 |
+
"grad_norm": 1.453125,
|
| 759 |
+
"learning_rate": 3.914858096828047e-05,
|
| 760 |
+
"loss": 0.099,
|
| 761 |
+
"step": 880
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.2409312398484028,
|
| 765 |
+
"grad_norm": 1.171875,
|
| 766 |
+
"learning_rate": 3.900946021146355e-05,
|
| 767 |
+
"loss": 0.1565,
|
| 768 |
+
"step": 890
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.24363833243096913,
|
| 772 |
+
"grad_norm": 0.44921875,
|
| 773 |
+
"learning_rate": 3.8870339454646635e-05,
|
| 774 |
+
"loss": 0.1352,
|
| 775 |
+
"step": 900
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.24363833243096913,
|
| 779 |
+
"eval_loss": 0.18001192808151245,
|
| 780 |
+
"eval_runtime": 62.7885,
|
| 781 |
+
"eval_samples_per_second": 7.963,
|
| 782 |
+
"eval_steps_per_second": 0.255,
|
| 783 |
+
"step": 900
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.24634542501353546,
|
| 787 |
+
"grad_norm": 2.140625,
|
| 788 |
+
"learning_rate": 3.873121869782972e-05,
|
| 789 |
+
"loss": 0.1469,
|
| 790 |
+
"step": 910
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 0.24905251759610178,
|
| 794 |
+
"grad_norm": 1.453125,
|
| 795 |
+
"learning_rate": 3.85920979410128e-05,
|
| 796 |
+
"loss": 0.1918,
|
| 797 |
+
"step": 920
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.2517596101786681,
|
| 801 |
+
"grad_norm": 1.4609375,
|
| 802 |
+
"learning_rate": 3.845297718419588e-05,
|
| 803 |
+
"loss": 0.1836,
|
| 804 |
+
"step": 930
|
| 805 |
+
},
|
| 806 |
+
{
|
| 807 |
+
"epoch": 0.25446670276123445,
|
| 808 |
+
"grad_norm": 2.625,
|
| 809 |
+
"learning_rate": 3.831385642737897e-05,
|
| 810 |
+
"loss": 0.1588,
|
| 811 |
+
"step": 940
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"epoch": 0.25717379534380075,
|
| 815 |
+
"grad_norm": 0.6953125,
|
| 816 |
+
"learning_rate": 3.817473567056205e-05,
|
| 817 |
+
"loss": 0.1503,
|
| 818 |
+
"step": 950
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"epoch": 0.25717379534380075,
|
| 822 |
+
"eval_loss": 0.17602640390396118,
|
| 823 |
+
"eval_runtime": 63.175,
|
| 824 |
+
"eval_samples_per_second": 7.915,
|
| 825 |
+
"eval_steps_per_second": 0.253,
|
| 826 |
+
"step": 950
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.2598808879263671,
|
| 830 |
+
"grad_norm": 2.0,
|
| 831 |
+
"learning_rate": 3.803561491374513e-05,
|
| 832 |
+
"loss": 0.1356,
|
| 833 |
+
"step": 960
|
| 834 |
+
},
|
| 835 |
+
{
|
| 836 |
+
"epoch": 0.2625879805089334,
|
| 837 |
+
"grad_norm": 0.9375,
|
| 838 |
+
"learning_rate": 3.789649415692821e-05,
|
| 839 |
+
"loss": 0.1702,
|
| 840 |
+
"step": 970
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.26529507309149974,
|
| 844 |
+
"grad_norm": 0.92578125,
|
| 845 |
+
"learning_rate": 3.77573734001113e-05,
|
| 846 |
+
"loss": 0.1545,
|
| 847 |
+
"step": 980
|
| 848 |
+
},
|
| 849 |
+
{
|
| 850 |
+
"epoch": 0.26800216567406604,
|
| 851 |
+
"grad_norm": 0.6640625,
|
| 852 |
+
"learning_rate": 3.7618252643294385e-05,
|
| 853 |
+
"loss": 0.1421,
|
| 854 |
+
"step": 990
|
| 855 |
+
},
|
| 856 |
+
{
|
| 857 |
+
"epoch": 0.2707092582566324,
|
| 858 |
+
"grad_norm": 3.96875,
|
| 859 |
+
"learning_rate": 3.7479131886477466e-05,
|
| 860 |
+
"loss": 0.1255,
|
| 861 |
+
"step": 1000
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.2707092582566324,
|
| 865 |
+
"eval_loss": 0.18262001872062683,
|
| 866 |
+
"eval_runtime": 78.6472,
|
| 867 |
+
"eval_samples_per_second": 6.358,
|
| 868 |
+
"eval_steps_per_second": 0.203,
|
| 869 |
+
"step": 1000
|
| 870 |
+
},
|
| 871 |
+
{
|
| 872 |
+
"epoch": 0.2734163508391987,
|
| 873 |
+
"grad_norm": 1.2734375,
|
| 874 |
+
"learning_rate": 3.7340011129660546e-05,
|
| 875 |
+
"loss": 0.144,
|
| 876 |
+
"step": 1010
|
| 877 |
+
},
|
| 878 |
+
{
|
| 879 |
+
"epoch": 0.27612344342176504,
|
| 880 |
+
"grad_norm": 1.7109375,
|
| 881 |
+
"learning_rate": 3.7200890372843626e-05,
|
| 882 |
+
"loss": 0.108,
|
| 883 |
+
"step": 1020
|
| 884 |
+
},
|
| 885 |
+
{
|
| 886 |
+
"epoch": 0.27883053600433133,
|
| 887 |
+
"grad_norm": 2.9375,
|
| 888 |
+
"learning_rate": 3.7061769616026713e-05,
|
| 889 |
+
"loss": 0.1255,
|
| 890 |
+
"step": 1030
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.2815376285868977,
|
| 894 |
+
"grad_norm": 1.25,
|
| 895 |
+
"learning_rate": 3.6922648859209794e-05,
|
| 896 |
+
"loss": 0.1421,
|
| 897 |
+
"step": 1040
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.284244721169464,
|
| 901 |
+
"grad_norm": 4.625,
|
| 902 |
+
"learning_rate": 3.678352810239288e-05,
|
| 903 |
+
"loss": 0.1686,
|
| 904 |
+
"step": 1050
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.284244721169464,
|
| 908 |
+
"eval_loss": 0.18178632855415344,
|
| 909 |
+
"eval_runtime": 62.9144,
|
| 910 |
+
"eval_samples_per_second": 7.947,
|
| 911 |
+
"eval_steps_per_second": 0.254,
|
| 912 |
+
"step": 1050
|
| 913 |
+
},
|
| 914 |
+
{
|
| 915 |
+
"epoch": 0.2869518137520303,
|
| 916 |
+
"grad_norm": 1.1328125,
|
| 917 |
+
"learning_rate": 3.664440734557596e-05,
|
| 918 |
+
"loss": 0.1147,
|
| 919 |
+
"step": 1060
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"epoch": 0.2896589063345966,
|
| 923 |
+
"grad_norm": 1.703125,
|
| 924 |
+
"learning_rate": 3.650528658875905e-05,
|
| 925 |
+
"loss": 0.1517,
|
| 926 |
+
"step": 1070
|
| 927 |
+
},
|
| 928 |
+
{
|
| 929 |
+
"epoch": 0.292365998917163,
|
| 930 |
+
"grad_norm": 2.328125,
|
| 931 |
+
"learning_rate": 3.636616583194213e-05,
|
| 932 |
+
"loss": 0.1545,
|
| 933 |
+
"step": 1080
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 0.29507309149972927,
|
| 937 |
+
"grad_norm": 1.984375,
|
| 938 |
+
"learning_rate": 3.622704507512521e-05,
|
| 939 |
+
"loss": 0.1471,
|
| 940 |
+
"step": 1090
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"epoch": 0.2977801840822956,
|
| 944 |
+
"grad_norm": 2.515625,
|
| 945 |
+
"learning_rate": 3.608792431830829e-05,
|
| 946 |
+
"loss": 0.1522,
|
| 947 |
+
"step": 1100
|
| 948 |
+
},
|
| 949 |
+
{
|
| 950 |
+
"epoch": 0.2977801840822956,
|
| 951 |
+
"eval_loss": 0.17702646553516388,
|
| 952 |
+
"eval_runtime": 63.2535,
|
| 953 |
+
"eval_samples_per_second": 7.905,
|
| 954 |
+
"eval_steps_per_second": 0.253,
|
| 955 |
+
"step": 1100
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.3004872766648619,
|
| 959 |
+
"grad_norm": 1.5859375,
|
| 960 |
+
"learning_rate": 3.594880356149138e-05,
|
| 961 |
+
"loss": 0.1772,
|
| 962 |
+
"step": 1110
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.30319436924742826,
|
| 966 |
+
"grad_norm": 0.77734375,
|
| 967 |
+
"learning_rate": 3.580968280467446e-05,
|
| 968 |
+
"loss": 0.1361,
|
| 969 |
+
"step": 1120
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.30590146182999456,
|
| 973 |
+
"grad_norm": 0.427734375,
|
| 974 |
+
"learning_rate": 3.5670562047857544e-05,
|
| 975 |
+
"loss": 0.128,
|
| 976 |
+
"step": 1130
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.3086085544125609,
|
| 980 |
+
"grad_norm": 2.328125,
|
| 981 |
+
"learning_rate": 3.5531441291040625e-05,
|
| 982 |
+
"loss": 0.1313,
|
| 983 |
+
"step": 1140
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.31131564699512726,
|
| 987 |
+
"grad_norm": 1.34375,
|
| 988 |
+
"learning_rate": 3.5392320534223705e-05,
|
| 989 |
+
"loss": 0.1238,
|
| 990 |
+
"step": 1150
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.31131564699512726,
|
| 994 |
+
"eval_loss": 0.17454275488853455,
|
| 995 |
+
"eval_runtime": 62.5874,
|
| 996 |
+
"eval_samples_per_second": 7.989,
|
| 997 |
+
"eval_steps_per_second": 0.256,
|
| 998 |
+
"step": 1150
|
| 999 |
+
},
|
| 1000 |
+
{
|
| 1001 |
+
"epoch": 0.31402273957769355,
|
| 1002 |
+
"grad_norm": 0.451171875,
|
| 1003 |
+
"learning_rate": 3.525319977740679e-05,
|
| 1004 |
+
"loss": 0.122,
|
| 1005 |
+
"step": 1160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.3167298321602599,
|
| 1009 |
+
"grad_norm": 2.59375,
|
| 1010 |
+
"learning_rate": 3.511407902058987e-05,
|
| 1011 |
+
"loss": 0.174,
|
| 1012 |
+
"step": 1170
|
| 1013 |
+
},
|
| 1014 |
+
{
|
| 1015 |
+
"epoch": 0.3194369247428262,
|
| 1016 |
+
"grad_norm": 1.8671875,
|
| 1017 |
+
"learning_rate": 3.497495826377295e-05,
|
| 1018 |
+
"loss": 0.1741,
|
| 1019 |
+
"step": 1180
|
| 1020 |
+
},
|
| 1021 |
+
{
|
| 1022 |
+
"epoch": 0.32214401732539255,
|
| 1023 |
+
"grad_norm": 1.5,
|
| 1024 |
+
"learning_rate": 3.483583750695604e-05,
|
| 1025 |
+
"loss": 0.1116,
|
| 1026 |
+
"step": 1190
|
| 1027 |
+
},
|
| 1028 |
+
{
|
| 1029 |
+
"epoch": 0.32485110990795885,
|
| 1030 |
+
"grad_norm": 3.875,
|
| 1031 |
+
"learning_rate": 3.469671675013913e-05,
|
| 1032 |
+
"loss": 0.1179,
|
| 1033 |
+
"step": 1200
|
| 1034 |
+
},
|
| 1035 |
+
{
|
| 1036 |
+
"epoch": 0.32485110990795885,
|
| 1037 |
+
"eval_loss": 0.17608264088630676,
|
| 1038 |
+
"eval_runtime": 62.6246,
|
| 1039 |
+
"eval_samples_per_second": 7.984,
|
| 1040 |
+
"eval_steps_per_second": 0.255,
|
| 1041 |
+
"step": 1200
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.3275582024905252,
|
| 1045 |
+
"grad_norm": 1.7421875,
|
| 1046 |
+
"learning_rate": 3.455759599332221e-05,
|
| 1047 |
+
"loss": 0.1332,
|
| 1048 |
+
"step": 1210
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.3302652950730915,
|
| 1052 |
+
"grad_norm": 2.578125,
|
| 1053 |
+
"learning_rate": 3.441847523650529e-05,
|
| 1054 |
+
"loss": 0.1425,
|
| 1055 |
+
"step": 1220
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.33297238765565784,
|
| 1059 |
+
"grad_norm": 2.734375,
|
| 1060 |
+
"learning_rate": 3.427935447968837e-05,
|
| 1061 |
+
"loss": 0.2023,
|
| 1062 |
+
"step": 1230
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.33567948023822414,
|
| 1066 |
+
"grad_norm": 0.84375,
|
| 1067 |
+
"learning_rate": 3.4140233722871455e-05,
|
| 1068 |
+
"loss": 0.1373,
|
| 1069 |
+
"step": 1240
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.3383865728207905,
|
| 1073 |
+
"grad_norm": 1.203125,
|
| 1074 |
+
"learning_rate": 3.4001112966054536e-05,
|
| 1075 |
+
"loss": 0.123,
|
| 1076 |
+
"step": 1250
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.3383865728207905,
|
| 1080 |
+
"eval_loss": 0.16774284839630127,
|
| 1081 |
+
"eval_runtime": 62.784,
|
| 1082 |
+
"eval_samples_per_second": 7.964,
|
| 1083 |
+
"eval_steps_per_second": 0.255,
|
| 1084 |
+
"step": 1250
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.3410936654033568,
|
| 1088 |
+
"grad_norm": 2.6875,
|
| 1089 |
+
"learning_rate": 3.386199220923762e-05,
|
| 1090 |
+
"loss": 0.1289,
|
| 1091 |
+
"step": 1260
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.34380075798592313,
|
| 1095 |
+
"grad_norm": 3.28125,
|
| 1096 |
+
"learning_rate": 3.37228714524207e-05,
|
| 1097 |
+
"loss": 0.1533,
|
| 1098 |
+
"step": 1270
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.34650785056848943,
|
| 1102 |
+
"grad_norm": 1.359375,
|
| 1103 |
+
"learning_rate": 3.358375069560379e-05,
|
| 1104 |
+
"loss": 0.1829,
|
| 1105 |
+
"step": 1280
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.3492149431510558,
|
| 1109 |
+
"grad_norm": 2.15625,
|
| 1110 |
+
"learning_rate": 3.344462993878687e-05,
|
| 1111 |
+
"loss": 0.128,
|
| 1112 |
+
"step": 1290
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.3519220357336221,
|
| 1116 |
+
"grad_norm": 2.21875,
|
| 1117 |
+
"learning_rate": 3.330550918196995e-05,
|
| 1118 |
+
"loss": 0.1807,
|
| 1119 |
+
"step": 1300
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.3519220357336221,
|
| 1123 |
+
"eval_loss": 0.15718665719032288,
|
| 1124 |
+
"eval_runtime": 62.4512,
|
| 1125 |
+
"eval_samples_per_second": 8.006,
|
| 1126 |
+
"eval_steps_per_second": 0.256,
|
| 1127 |
+
"step": 1300
|
| 1128 |
+
},
|
| 1129 |
+
{
|
| 1130 |
+
"epoch": 0.3546291283161884,
|
| 1131 |
+
"grad_norm": 0.5390625,
|
| 1132 |
+
"learning_rate": 3.316638842515303e-05,
|
| 1133 |
+
"loss": 0.1276,
|
| 1134 |
+
"step": 1310
|
| 1135 |
+
},
|
| 1136 |
+
{
|
| 1137 |
+
"epoch": 0.3573362208987547,
|
| 1138 |
+
"grad_norm": 1.7265625,
|
| 1139 |
+
"learning_rate": 3.302726766833611e-05,
|
| 1140 |
+
"loss": 0.1422,
|
| 1141 |
+
"step": 1320
|
| 1142 |
+
},
|
| 1143 |
+
{
|
| 1144 |
+
"epoch": 0.36004331348132107,
|
| 1145 |
+
"grad_norm": 3.125,
|
| 1146 |
+
"learning_rate": 3.28881469115192e-05,
|
| 1147 |
+
"loss": 0.2032,
|
| 1148 |
+
"step": 1330
|
| 1149 |
+
},
|
| 1150 |
+
{
|
| 1151 |
+
"epoch": 0.36275040606388737,
|
| 1152 |
+
"grad_norm": 1.8515625,
|
| 1153 |
+
"learning_rate": 3.2749026154702286e-05,
|
| 1154 |
+
"loss": 0.1726,
|
| 1155 |
+
"step": 1340
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.3654574986464537,
|
| 1159 |
+
"grad_norm": 1.0625,
|
| 1160 |
+
"learning_rate": 3.2609905397885366e-05,
|
| 1161 |
+
"loss": 0.1432,
|
| 1162 |
+
"step": 1350
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 0.3654574986464537,
|
| 1166 |
+
"eval_loss": 0.15765319764614105,
|
| 1167 |
+
"eval_runtime": 63.3444,
|
| 1168 |
+
"eval_samples_per_second": 7.893,
|
| 1169 |
+
"eval_steps_per_second": 0.253,
|
| 1170 |
+
"step": 1350
|
| 1171 |
+
},
|
| 1172 |
+
{
|
| 1173 |
+
"epoch": 0.36816459122902,
|
| 1174 |
+
"grad_norm": 1.125,
|
| 1175 |
+
"learning_rate": 3.247078464106845e-05,
|
| 1176 |
+
"loss": 0.1008,
|
| 1177 |
+
"step": 1360
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"epoch": 0.37087168381158636,
|
| 1181 |
+
"grad_norm": 1.734375,
|
| 1182 |
+
"learning_rate": 3.2331663884251534e-05,
|
| 1183 |
+
"loss": 0.1397,
|
| 1184 |
+
"step": 1370
|
| 1185 |
+
},
|
| 1186 |
+
{
|
| 1187 |
+
"epoch": 0.37357877639415266,
|
| 1188 |
+
"grad_norm": 1.6484375,
|
| 1189 |
+
"learning_rate": 3.2192543127434614e-05,
|
| 1190 |
+
"loss": 0.1342,
|
| 1191 |
+
"step": 1380
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.376285868976719,
|
| 1195 |
+
"grad_norm": 1.0859375,
|
| 1196 |
+
"learning_rate": 3.2053422370617695e-05,
|
| 1197 |
+
"loss": 0.1528,
|
| 1198 |
+
"step": 1390
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 0.3789929615592853,
|
| 1202 |
+
"grad_norm": 2.421875,
|
| 1203 |
+
"learning_rate": 3.191430161380078e-05,
|
| 1204 |
+
"loss": 0.1313,
|
| 1205 |
+
"step": 1400
|
| 1206 |
+
},
|
| 1207 |
+
{
|
| 1208 |
+
"epoch": 0.3789929615592853,
|
| 1209 |
+
"eval_loss": 0.16292478144168854,
|
| 1210 |
+
"eval_runtime": 64.15,
|
| 1211 |
+
"eval_samples_per_second": 7.794,
|
| 1212 |
+
"eval_steps_per_second": 0.249,
|
| 1213 |
+
"step": 1400
|
| 1214 |
+
},
|
| 1215 |
+
{
|
| 1216 |
+
"epoch": 0.38170005414185165,
|
| 1217 |
+
"grad_norm": 2.09375,
|
| 1218 |
+
"learning_rate": 3.177518085698387e-05,
|
| 1219 |
+
"loss": 0.1358,
|
| 1220 |
+
"step": 1410
|
| 1221 |
+
},
|
| 1222 |
+
{
|
| 1223 |
+
"epoch": 0.38440714672441795,
|
| 1224 |
+
"grad_norm": 3.0,
|
| 1225 |
+
"learning_rate": 3.163606010016695e-05,
|
| 1226 |
+
"loss": 0.1683,
|
| 1227 |
+
"step": 1420
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.3871142393069843,
|
| 1231 |
+
"grad_norm": 2.109375,
|
| 1232 |
+
"learning_rate": 3.149693934335003e-05,
|
| 1233 |
+
"loss": 0.136,
|
| 1234 |
+
"step": 1430
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 0.38982133188955065,
|
| 1238 |
+
"grad_norm": 2.15625,
|
| 1239 |
+
"learning_rate": 3.135781858653311e-05,
|
| 1240 |
+
"loss": 0.1435,
|
| 1241 |
+
"step": 1440
|
| 1242 |
+
},
|
| 1243 |
+
{
|
| 1244 |
+
"epoch": 0.39252842447211694,
|
| 1245 |
+
"grad_norm": 2.046875,
|
| 1246 |
+
"learning_rate": 3.121869782971619e-05,
|
| 1247 |
+
"loss": 0.1711,
|
| 1248 |
+
"step": 1450
|
| 1249 |
+
},
|
| 1250 |
+
{
|
| 1251 |
+
"epoch": 0.39252842447211694,
|
| 1252 |
+
"eval_loss": 0.15946637094020844,
|
| 1253 |
+
"eval_runtime": 65.0021,
|
| 1254 |
+
"eval_samples_per_second": 7.692,
|
| 1255 |
+
"eval_steps_per_second": 0.246,
|
| 1256 |
+
"step": 1450
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.3952355170546833,
|
| 1260 |
+
"grad_norm": 0.80078125,
|
| 1261 |
+
"learning_rate": 3.107957707289928e-05,
|
| 1262 |
+
"loss": 0.1672,
|
| 1263 |
+
"step": 1460
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.3979426096372496,
|
| 1267 |
+
"grad_norm": 0.703125,
|
| 1268 |
+
"learning_rate": 3.0940456316082365e-05,
|
| 1269 |
+
"loss": 0.1152,
|
| 1270 |
+
"step": 1470
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.40064970221981594,
|
| 1274 |
+
"grad_norm": 2.203125,
|
| 1275 |
+
"learning_rate": 3.0801335559265445e-05,
|
| 1276 |
+
"loss": 0.1628,
|
| 1277 |
+
"step": 1480
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.40335679480238223,
|
| 1281 |
+
"grad_norm": 1.7734375,
|
| 1282 |
+
"learning_rate": 3.0662214802448525e-05,
|
| 1283 |
+
"loss": 0.1474,
|
| 1284 |
+
"step": 1490
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.4060638873849486,
|
| 1288 |
+
"grad_norm": 1.015625,
|
| 1289 |
+
"learning_rate": 3.052309404563161e-05,
|
| 1290 |
+
"loss": 0.1211,
|
| 1291 |
+
"step": 1500
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.4060638873849486,
|
| 1295 |
+
"eval_loss": 0.16578222811222076,
|
| 1296 |
+
"eval_runtime": 77.637,
|
| 1297 |
+
"eval_samples_per_second": 6.44,
|
| 1298 |
+
"eval_steps_per_second": 0.206,
|
| 1299 |
+
"step": 1500
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.4087709799675149,
|
| 1303 |
+
"grad_norm": 2.0625,
|
| 1304 |
+
"learning_rate": 3.0383973288814693e-05,
|
| 1305 |
+
"loss": 0.1388,
|
| 1306 |
+
"step": 1510
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 0.41147807255008123,
|
| 1310 |
+
"grad_norm": 2.671875,
|
| 1311 |
+
"learning_rate": 3.0244852531997773e-05,
|
| 1312 |
+
"loss": 0.1518,
|
| 1313 |
+
"step": 1520
|
| 1314 |
+
},
|
| 1315 |
+
{
|
| 1316 |
+
"epoch": 0.4141851651326475,
|
| 1317 |
+
"grad_norm": 2.046875,
|
| 1318 |
+
"learning_rate": 3.0105731775180857e-05,
|
| 1319 |
+
"loss": 0.1536,
|
| 1320 |
+
"step": 1530
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"epoch": 0.4168922577152139,
|
| 1324 |
+
"grad_norm": 2.0625,
|
| 1325 |
+
"learning_rate": 2.9966611018363944e-05,
|
| 1326 |
+
"loss": 0.1464,
|
| 1327 |
+
"step": 1540
|
| 1328 |
+
},
|
| 1329 |
+
{
|
| 1330 |
+
"epoch": 0.41959935029778017,
|
| 1331 |
+
"grad_norm": 1.9609375,
|
| 1332 |
+
"learning_rate": 2.9827490261547024e-05,
|
| 1333 |
+
"loss": 0.1585,
|
| 1334 |
+
"step": 1550
|
| 1335 |
+
},
|
| 1336 |
+
{
|
| 1337 |
+
"epoch": 0.41959935029778017,
|
| 1338 |
+
"eval_loss": 0.16232775151729584,
|
| 1339 |
+
"eval_runtime": 64.4195,
|
| 1340 |
+
"eval_samples_per_second": 7.762,
|
| 1341 |
+
"eval_steps_per_second": 0.248,
|
| 1342 |
+
"step": 1550
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 0.4223064428803465,
|
| 1346 |
+
"grad_norm": 1.1640625,
|
| 1347 |
+
"learning_rate": 2.9688369504730108e-05,
|
| 1348 |
+
"loss": 0.1078,
|
| 1349 |
+
"step": 1560
|
| 1350 |
+
},
|
| 1351 |
+
{
|
| 1352 |
+
"epoch": 0.4250135354629128,
|
| 1353 |
+
"grad_norm": 0.9453125,
|
| 1354 |
+
"learning_rate": 2.954924874791319e-05,
|
| 1355 |
+
"loss": 0.1191,
|
| 1356 |
+
"step": 1570
|
| 1357 |
+
},
|
| 1358 |
+
{
|
| 1359 |
+
"epoch": 0.42772062804547917,
|
| 1360 |
+
"grad_norm": 2.328125,
|
| 1361 |
+
"learning_rate": 2.9410127991096276e-05,
|
| 1362 |
+
"loss": 0.1366,
|
| 1363 |
+
"step": 1580
|
| 1364 |
+
},
|
| 1365 |
+
{
|
| 1366 |
+
"epoch": 0.43042772062804546,
|
| 1367 |
+
"grad_norm": 1.0390625,
|
| 1368 |
+
"learning_rate": 2.9271007234279356e-05,
|
| 1369 |
+
"loss": 0.1382,
|
| 1370 |
+
"step": 1590
|
| 1371 |
+
},
|
| 1372 |
+
{
|
| 1373 |
+
"epoch": 0.4331348132106118,
|
| 1374 |
+
"grad_norm": 1.03125,
|
| 1375 |
+
"learning_rate": 2.913188647746244e-05,
|
| 1376 |
+
"loss": 0.1545,
|
| 1377 |
+
"step": 1600
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.4331348132106118,
|
| 1381 |
+
"eval_loss": 0.16547426581382751,
|
| 1382 |
+
"eval_runtime": 64.8149,
|
| 1383 |
+
"eval_samples_per_second": 7.714,
|
| 1384 |
+
"eval_steps_per_second": 0.247,
|
| 1385 |
+
"step": 1600
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.4358419057931781,
|
| 1389 |
+
"grad_norm": 1.0390625,
|
| 1390 |
+
"learning_rate": 2.899276572064552e-05,
|
| 1391 |
+
"loss": 0.1232,
|
| 1392 |
+
"step": 1610
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.43854899837574446,
|
| 1396 |
+
"grad_norm": 0.45703125,
|
| 1397 |
+
"learning_rate": 2.88536449638286e-05,
|
| 1398 |
+
"loss": 0.1371,
|
| 1399 |
+
"step": 1620
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.44125609095831075,
|
| 1403 |
+
"grad_norm": 3.28125,
|
| 1404 |
+
"learning_rate": 2.8714524207011688e-05,
|
| 1405 |
+
"loss": 0.1301,
|
| 1406 |
+
"step": 1630
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.4439631835408771,
|
| 1410 |
+
"grad_norm": 2.703125,
|
| 1411 |
+
"learning_rate": 2.857540345019477e-05,
|
| 1412 |
+
"loss": 0.122,
|
| 1413 |
+
"step": 1640
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.4466702761234434,
|
| 1417 |
+
"grad_norm": 1.203125,
|
| 1418 |
+
"learning_rate": 2.8436282693377852e-05,
|
| 1419 |
+
"loss": 0.1649,
|
| 1420 |
+
"step": 1650
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.4466702761234434,
|
| 1424 |
+
"eval_loss": 0.15991100668907166,
|
| 1425 |
+
"eval_runtime": 64.6415,
|
| 1426 |
+
"eval_samples_per_second": 7.735,
|
| 1427 |
+
"eval_steps_per_second": 0.248,
|
| 1428 |
+
"step": 1650
|
| 1429 |
+
},
|
| 1430 |
+
{
|
| 1431 |
+
"epoch": 0.44937736870600975,
|
| 1432 |
+
"grad_norm": 1.28125,
|
| 1433 |
+
"learning_rate": 2.8297161936560936e-05,
|
| 1434 |
+
"loss": 0.158,
|
| 1435 |
+
"step": 1660
|
| 1436 |
+
},
|
| 1437 |
+
{
|
| 1438 |
+
"epoch": 0.45208446128857604,
|
| 1439 |
+
"grad_norm": 0.9375,
|
| 1440 |
+
"learning_rate": 2.8158041179744023e-05,
|
| 1441 |
+
"loss": 0.1427,
|
| 1442 |
+
"step": 1670
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.4547915538711424,
|
| 1446 |
+
"grad_norm": 1.6796875,
|
| 1447 |
+
"learning_rate": 2.8018920422927103e-05,
|
| 1448 |
+
"loss": 0.1528,
|
| 1449 |
+
"step": 1680
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.4574986464537087,
|
| 1453 |
+
"grad_norm": 0.78125,
|
| 1454 |
+
"learning_rate": 2.7879799666110183e-05,
|
| 1455 |
+
"loss": 0.1117,
|
| 1456 |
+
"step": 1690
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.46020573903627504,
|
| 1460 |
+
"grad_norm": 1.3203125,
|
| 1461 |
+
"learning_rate": 2.7740678909293267e-05,
|
| 1462 |
+
"loss": 0.1069,
|
| 1463 |
+
"step": 1700
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.46020573903627504,
|
| 1467 |
+
"eval_loss": 0.16090016067028046,
|
| 1468 |
+
"eval_runtime": 64.8286,
|
| 1469 |
+
"eval_samples_per_second": 7.713,
|
| 1470 |
+
"eval_steps_per_second": 0.247,
|
| 1471 |
+
"step": 1700
|
| 1472 |
+
},
|
| 1473 |
+
{
|
| 1474 |
+
"epoch": 0.4629128316188414,
|
| 1475 |
+
"grad_norm": 1.703125,
|
| 1476 |
+
"learning_rate": 2.7601558152476354e-05,
|
| 1477 |
+
"loss": 0.1165,
|
| 1478 |
+
"step": 1710
|
| 1479 |
+
},
|
| 1480 |
+
{
|
| 1481 |
+
"epoch": 0.4656199242014077,
|
| 1482 |
+
"grad_norm": 2.015625,
|
| 1483 |
+
"learning_rate": 2.7462437395659435e-05,
|
| 1484 |
+
"loss": 0.1347,
|
| 1485 |
+
"step": 1720
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.46832701678397404,
|
| 1489 |
+
"grad_norm": 2.25,
|
| 1490 |
+
"learning_rate": 2.7323316638842515e-05,
|
| 1491 |
+
"loss": 0.2037,
|
| 1492 |
+
"step": 1730
|
| 1493 |
+
},
|
| 1494 |
+
{
|
| 1495 |
+
"epoch": 0.47103410936654033,
|
| 1496 |
+
"grad_norm": 0.7890625,
|
| 1497 |
+
"learning_rate": 2.71841958820256e-05,
|
| 1498 |
+
"loss": 0.1338,
|
| 1499 |
+
"step": 1740
|
| 1500 |
+
},
|
| 1501 |
+
{
|
| 1502 |
+
"epoch": 0.4737412019491067,
|
| 1503 |
+
"grad_norm": 1.21875,
|
| 1504 |
+
"learning_rate": 2.704507512520868e-05,
|
| 1505 |
+
"loss": 0.1245,
|
| 1506 |
+
"step": 1750
|
| 1507 |
+
},
|
| 1508 |
+
{
|
| 1509 |
+
"epoch": 0.4737412019491067,
|
| 1510 |
+
"eval_loss": 0.16117550432682037,
|
| 1511 |
+
"eval_runtime": 64.6119,
|
| 1512 |
+
"eval_samples_per_second": 7.739,
|
| 1513 |
+
"eval_steps_per_second": 0.248,
|
| 1514 |
+
"step": 1750
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"epoch": 0.476448294531673,
|
| 1518 |
+
"grad_norm": 1.796875,
|
| 1519 |
+
"learning_rate": 2.6905954368391766e-05,
|
| 1520 |
+
"loss": 0.1182,
|
| 1521 |
+
"step": 1760
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.47915538711423933,
|
| 1525 |
+
"grad_norm": 2.78125,
|
| 1526 |
+
"learning_rate": 2.676683361157485e-05,
|
| 1527 |
+
"loss": 0.1662,
|
| 1528 |
+
"step": 1770
|
| 1529 |
+
},
|
| 1530 |
+
{
|
| 1531 |
+
"epoch": 0.4818624796968056,
|
| 1532 |
+
"grad_norm": 1.0546875,
|
| 1533 |
+
"learning_rate": 2.662771285475793e-05,
|
| 1534 |
+
"loss": 0.1597,
|
| 1535 |
+
"step": 1780
|
| 1536 |
+
},
|
| 1537 |
+
{
|
| 1538 |
+
"epoch": 0.484569572279372,
|
| 1539 |
+
"grad_norm": 1.5703125,
|
| 1540 |
+
"learning_rate": 2.648859209794101e-05,
|
| 1541 |
+
"loss": 0.104,
|
| 1542 |
+
"step": 1790
|
| 1543 |
+
},
|
| 1544 |
+
{
|
| 1545 |
+
"epoch": 0.48727666486193827,
|
| 1546 |
+
"grad_norm": 3.109375,
|
| 1547 |
+
"learning_rate": 2.6349471341124098e-05,
|
| 1548 |
+
"loss": 0.1149,
|
| 1549 |
+
"step": 1800
|
| 1550 |
+
},
|
| 1551 |
+
{
|
| 1552 |
+
"epoch": 0.48727666486193827,
|
| 1553 |
+
"eval_loss": 0.1653529703617096,
|
| 1554 |
+
"eval_runtime": 65.0831,
|
| 1555 |
+
"eval_samples_per_second": 7.682,
|
| 1556 |
+
"eval_steps_per_second": 0.246,
|
| 1557 |
+
"step": 1800
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.4899837574445046,
|
| 1561 |
+
"grad_norm": 0.60546875,
|
| 1562 |
+
"learning_rate": 2.6210350584307182e-05,
|
| 1563 |
+
"loss": 0.121,
|
| 1564 |
+
"step": 1810
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.4926908500270709,
|
| 1568 |
+
"grad_norm": 2.625,
|
| 1569 |
+
"learning_rate": 2.6071229827490262e-05,
|
| 1570 |
+
"loss": 0.1797,
|
| 1571 |
+
"step": 1820
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.49539794260963727,
|
| 1575 |
+
"grad_norm": 1.9609375,
|
| 1576 |
+
"learning_rate": 2.5932109070673342e-05,
|
| 1577 |
+
"loss": 0.1159,
|
| 1578 |
+
"step": 1830
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.49810503519220356,
|
| 1582 |
+
"grad_norm": 1.546875,
|
| 1583 |
+
"learning_rate": 2.579298831385643e-05,
|
| 1584 |
+
"loss": 0.1119,
|
| 1585 |
+
"step": 1840
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.5008121277747699,
|
| 1589 |
+
"grad_norm": 2.90625,
|
| 1590 |
+
"learning_rate": 2.5653867557039513e-05,
|
| 1591 |
+
"loss": 0.1367,
|
| 1592 |
+
"step": 1850
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.5008121277747699,
|
| 1596 |
+
"eval_loss": 0.16627325117588043,
|
| 1597 |
+
"eval_runtime": 64.4654,
|
| 1598 |
+
"eval_samples_per_second": 7.756,
|
| 1599 |
+
"eval_steps_per_second": 0.248,
|
| 1600 |
+
"step": 1850
|
| 1601 |
+
},
|
| 1602 |
+
{
|
| 1603 |
+
"epoch": 0.5035192203573362,
|
| 1604 |
+
"grad_norm": 1.1640625,
|
| 1605 |
+
"learning_rate": 2.5514746800222594e-05,
|
| 1606 |
+
"loss": 0.1591,
|
| 1607 |
+
"step": 1860
|
| 1608 |
+
},
|
| 1609 |
+
{
|
| 1610 |
+
"epoch": 0.5062263129399025,
|
| 1611 |
+
"grad_norm": 2.4375,
|
| 1612 |
+
"learning_rate": 2.5375626043405677e-05,
|
| 1613 |
+
"loss": 0.1047,
|
| 1614 |
+
"step": 1870
|
| 1615 |
+
},
|
| 1616 |
+
{
|
| 1617 |
+
"epoch": 0.5089334055224689,
|
| 1618 |
+
"grad_norm": 1.78125,
|
| 1619 |
+
"learning_rate": 2.5236505286588765e-05,
|
| 1620 |
+
"loss": 0.1172,
|
| 1621 |
+
"step": 1880
|
| 1622 |
+
},
|
| 1623 |
+
{
|
| 1624 |
+
"epoch": 0.5116404981050352,
|
| 1625 |
+
"grad_norm": 1.234375,
|
| 1626 |
+
"learning_rate": 2.5097384529771845e-05,
|
| 1627 |
+
"loss": 0.1211,
|
| 1628 |
+
"step": 1890
|
| 1629 |
+
},
|
| 1630 |
+
{
|
| 1631 |
+
"epoch": 0.5143475906876015,
|
| 1632 |
+
"grad_norm": 3.0,
|
| 1633 |
+
"learning_rate": 2.4958263772954925e-05,
|
| 1634 |
+
"loss": 0.1294,
|
| 1635 |
+
"step": 1900
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.5143475906876015,
|
| 1639 |
+
"eval_loss": 0.1589047610759735,
|
| 1640 |
+
"eval_runtime": 63.4959,
|
| 1641 |
+
"eval_samples_per_second": 7.875,
|
| 1642 |
+
"eval_steps_per_second": 0.252,
|
| 1643 |
+
"step": 1900
|
| 1644 |
+
},
|
| 1645 |
+
{
|
| 1646 |
+
"epoch": 0.5170546832701678,
|
| 1647 |
+
"grad_norm": 1.8984375,
|
| 1648 |
+
"learning_rate": 2.481914301613801e-05,
|
| 1649 |
+
"loss": 0.1343,
|
| 1650 |
+
"step": 1910
|
| 1651 |
+
},
|
| 1652 |
+
{
|
| 1653 |
+
"epoch": 0.5197617758527342,
|
| 1654 |
+
"grad_norm": 2.0,
|
| 1655 |
+
"learning_rate": 2.4680022259321093e-05,
|
| 1656 |
+
"loss": 0.1357,
|
| 1657 |
+
"step": 1920
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"epoch": 0.5224688684353005,
|
| 1661 |
+
"grad_norm": 2.671875,
|
| 1662 |
+
"learning_rate": 2.4540901502504173e-05,
|
| 1663 |
+
"loss": 0.143,
|
| 1664 |
+
"step": 1930
|
| 1665 |
+
},
|
| 1666 |
+
{
|
| 1667 |
+
"epoch": 0.5251759610178668,
|
| 1668 |
+
"grad_norm": 1.3828125,
|
| 1669 |
+
"learning_rate": 2.4401780745687257e-05,
|
| 1670 |
+
"loss": 0.1321,
|
| 1671 |
+
"step": 1940
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.5278830536004331,
|
| 1675 |
+
"grad_norm": 2.046875,
|
| 1676 |
+
"learning_rate": 2.426265998887034e-05,
|
| 1677 |
+
"loss": 0.1663,
|
| 1678 |
+
"step": 1950
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 0.5278830536004331,
|
| 1682 |
+
"eval_loss": 0.15560173988342285,
|
| 1683 |
+
"eval_runtime": 63.7793,
|
| 1684 |
+
"eval_samples_per_second": 7.84,
|
| 1685 |
+
"eval_steps_per_second": 0.251,
|
| 1686 |
+
"step": 1950
|
| 1687 |
+
},
|
| 1688 |
+
{
|
| 1689 |
+
"epoch": 0.5305901461829995,
|
| 1690 |
+
"grad_norm": 0.9296875,
|
| 1691 |
+
"learning_rate": 2.4123539232053424e-05,
|
| 1692 |
+
"loss": 0.0997,
|
| 1693 |
+
"step": 1960
|
| 1694 |
+
},
|
| 1695 |
+
{
|
| 1696 |
+
"epoch": 0.5332972387655658,
|
| 1697 |
+
"grad_norm": 2.015625,
|
| 1698 |
+
"learning_rate": 2.3984418475236505e-05,
|
| 1699 |
+
"loss": 0.1283,
|
| 1700 |
+
"step": 1970
|
| 1701 |
+
},
|
| 1702 |
+
{
|
| 1703 |
+
"epoch": 0.5360043313481321,
|
| 1704 |
+
"grad_norm": 0.89453125,
|
| 1705 |
+
"learning_rate": 2.3845297718419592e-05,
|
| 1706 |
+
"loss": 0.1407,
|
| 1707 |
+
"step": 1980
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.5387114239306985,
|
| 1711 |
+
"grad_norm": 0.8046875,
|
| 1712 |
+
"learning_rate": 2.3706176961602672e-05,
|
| 1713 |
+
"loss": 0.1171,
|
| 1714 |
+
"step": 1990
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 0.5414185165132648,
|
| 1718 |
+
"grad_norm": 1.296875,
|
| 1719 |
+
"learning_rate": 2.3567056204785756e-05,
|
| 1720 |
+
"loss": 0.1288,
|
| 1721 |
+
"step": 2000
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"epoch": 0.5414185165132648,
|
| 1725 |
+
"eval_loss": 0.15494494140148163,
|
| 1726 |
+
"eval_runtime": 79.2552,
|
| 1727 |
+
"eval_samples_per_second": 6.309,
|
| 1728 |
+
"eval_steps_per_second": 0.202,
|
| 1729 |
+
"step": 2000
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.5441256090958311,
|
| 1733 |
+
"grad_norm": 2.015625,
|
| 1734 |
+
"learning_rate": 2.3427935447968836e-05,
|
| 1735 |
+
"loss": 0.1055,
|
| 1736 |
+
"step": 2010
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.5468327016783974,
|
| 1740 |
+
"grad_norm": 1.140625,
|
| 1741 |
+
"learning_rate": 2.3288814691151924e-05,
|
| 1742 |
+
"loss": 0.1142,
|
| 1743 |
+
"step": 2020
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.5495397942609638,
|
| 1747 |
+
"grad_norm": 1.5703125,
|
| 1748 |
+
"learning_rate": 2.3149693934335004e-05,
|
| 1749 |
+
"loss": 0.1415,
|
| 1750 |
+
"step": 2030
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.5522468868435301,
|
| 1754 |
+
"grad_norm": 0.609375,
|
| 1755 |
+
"learning_rate": 2.3010573177518084e-05,
|
| 1756 |
+
"loss": 0.1086,
|
| 1757 |
+
"step": 2040
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.5549539794260964,
|
| 1761 |
+
"grad_norm": 2.921875,
|
| 1762 |
+
"learning_rate": 2.287145242070117e-05,
|
| 1763 |
+
"loss": 0.1028,
|
| 1764 |
+
"step": 2050
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.5549539794260964,
|
| 1768 |
+
"eval_loss": 0.1615983545780182,
|
| 1769 |
+
"eval_runtime": 64.4361,
|
| 1770 |
+
"eval_samples_per_second": 7.76,
|
| 1771 |
+
"eval_steps_per_second": 0.248,
|
| 1772 |
+
"step": 2050
|
| 1773 |
+
},
|
| 1774 |
+
{
|
| 1775 |
+
"epoch": 0.5576610720086627,
|
| 1776 |
+
"grad_norm": 1.6640625,
|
| 1777 |
+
"learning_rate": 2.2732331663884252e-05,
|
| 1778 |
+
"loss": 0.1268,
|
| 1779 |
+
"step": 2060
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.5603681645912291,
|
| 1783 |
+
"grad_norm": 0.55078125,
|
| 1784 |
+
"learning_rate": 2.2593210907067336e-05,
|
| 1785 |
+
"loss": 0.1187,
|
| 1786 |
+
"step": 2070
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 0.5630752571737954,
|
| 1790 |
+
"grad_norm": 1.703125,
|
| 1791 |
+
"learning_rate": 2.2454090150250416e-05,
|
| 1792 |
+
"loss": 0.1135,
|
| 1793 |
+
"step": 2080
|
| 1794 |
+
},
|
| 1795 |
+
{
|
| 1796 |
+
"epoch": 0.5657823497563617,
|
| 1797 |
+
"grad_norm": 2.71875,
|
| 1798 |
+
"learning_rate": 2.2314969393433503e-05,
|
| 1799 |
+
"loss": 0.1625,
|
| 1800 |
+
"step": 2090
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.568489442338928,
|
| 1804 |
+
"grad_norm": 1.3125,
|
| 1805 |
+
"learning_rate": 2.2175848636616583e-05,
|
| 1806 |
+
"loss": 0.1095,
|
| 1807 |
+
"step": 2100
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.568489442338928,
|
| 1811 |
+
"eval_loss": 0.16485995054244995,
|
| 1812 |
+
"eval_runtime": 63.0678,
|
| 1813 |
+
"eval_samples_per_second": 7.928,
|
| 1814 |
+
"eval_steps_per_second": 0.254,
|
| 1815 |
+
"step": 2100
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.5711965349214944,
|
| 1819 |
+
"grad_norm": 0.890625,
|
| 1820 |
+
"learning_rate": 2.2036727879799667e-05,
|
| 1821 |
+
"loss": 0.1131,
|
| 1822 |
+
"step": 2110
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 0.5739036275040607,
|
| 1826 |
+
"grad_norm": 2.296875,
|
| 1827 |
+
"learning_rate": 2.189760712298275e-05,
|
| 1828 |
+
"loss": 0.0784,
|
| 1829 |
+
"step": 2120
|
| 1830 |
+
},
|
| 1831 |
+
{
|
| 1832 |
+
"epoch": 0.576610720086627,
|
| 1833 |
+
"grad_norm": 3.4375,
|
| 1834 |
+
"learning_rate": 2.1758486366165835e-05,
|
| 1835 |
+
"loss": 0.1548,
|
| 1836 |
+
"step": 2130
|
| 1837 |
+
},
|
| 1838 |
+
{
|
| 1839 |
+
"epoch": 0.5793178126691932,
|
| 1840 |
+
"grad_norm": 0.671875,
|
| 1841 |
+
"learning_rate": 2.1619365609348915e-05,
|
| 1842 |
+
"loss": 0.1285,
|
| 1843 |
+
"step": 2140
|
| 1844 |
+
},
|
| 1845 |
+
{
|
| 1846 |
+
"epoch": 0.5820249052517596,
|
| 1847 |
+
"grad_norm": 2.265625,
|
| 1848 |
+
"learning_rate": 2.1480244852532e-05,
|
| 1849 |
+
"loss": 0.1333,
|
| 1850 |
+
"step": 2150
|
| 1851 |
+
},
|
| 1852 |
+
{
|
| 1853 |
+
"epoch": 0.5820249052517596,
|
| 1854 |
+
"eval_loss": 0.1646082103252411,
|
| 1855 |
+
"eval_runtime": 64.2796,
|
| 1856 |
+
"eval_samples_per_second": 7.779,
|
| 1857 |
+
"eval_steps_per_second": 0.249,
|
| 1858 |
+
"step": 2150
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.584731997834326,
|
| 1862 |
+
"grad_norm": 1.71875,
|
| 1863 |
+
"learning_rate": 2.1341124095715083e-05,
|
| 1864 |
+
"loss": 0.1197,
|
| 1865 |
+
"step": 2160
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.5874390904168922,
|
| 1869 |
+
"grad_norm": 0.5703125,
|
| 1870 |
+
"learning_rate": 2.1202003338898166e-05,
|
| 1871 |
+
"loss": 0.151,
|
| 1872 |
+
"step": 2170
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.5901461829994585,
|
| 1876 |
+
"grad_norm": 1.828125,
|
| 1877 |
+
"learning_rate": 2.1062882582081247e-05,
|
| 1878 |
+
"loss": 0.0958,
|
| 1879 |
+
"step": 2180
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.5928532755820249,
|
| 1883 |
+
"grad_norm": 3.15625,
|
| 1884 |
+
"learning_rate": 2.092376182526433e-05,
|
| 1885 |
+
"loss": 0.1853,
|
| 1886 |
+
"step": 2190
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.5955603681645912,
|
| 1890 |
+
"grad_norm": 2.34375,
|
| 1891 |
+
"learning_rate": 2.0784641068447414e-05,
|
| 1892 |
+
"loss": 0.1199,
|
| 1893 |
+
"step": 2200
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.5955603681645912,
|
| 1897 |
+
"eval_loss": 0.162201389670372,
|
| 1898 |
+
"eval_runtime": 64.0196,
|
| 1899 |
+
"eval_samples_per_second": 7.81,
|
| 1900 |
+
"eval_steps_per_second": 0.25,
|
| 1901 |
+
"step": 2200
|
| 1902 |
+
},
|
| 1903 |
+
{
|
| 1904 |
+
"epoch": 0.5982674607471575,
|
| 1905 |
+
"grad_norm": 1.34375,
|
| 1906 |
+
"learning_rate": 2.0645520311630495e-05,
|
| 1907 |
+
"loss": 0.1661,
|
| 1908 |
+
"step": 2210
|
| 1909 |
+
},
|
| 1910 |
+
{
|
| 1911 |
+
"epoch": 0.6009745533297238,
|
| 1912 |
+
"grad_norm": 1.5703125,
|
| 1913 |
+
"learning_rate": 2.0506399554813578e-05,
|
| 1914 |
+
"loss": 0.1106,
|
| 1915 |
+
"step": 2220
|
| 1916 |
+
},
|
| 1917 |
+
{
|
| 1918 |
+
"epoch": 0.6036816459122902,
|
| 1919 |
+
"grad_norm": 3.65625,
|
| 1920 |
+
"learning_rate": 2.0367278797996662e-05,
|
| 1921 |
+
"loss": 0.1747,
|
| 1922 |
+
"step": 2230
|
| 1923 |
+
},
|
| 1924 |
+
{
|
| 1925 |
+
"epoch": 0.6063887384948565,
|
| 1926 |
+
"grad_norm": 0.828125,
|
| 1927 |
+
"learning_rate": 2.0228158041179746e-05,
|
| 1928 |
+
"loss": 0.1247,
|
| 1929 |
+
"step": 2240
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"epoch": 0.6090958310774228,
|
| 1933 |
+
"grad_norm": 0.7734375,
|
| 1934 |
+
"learning_rate": 2.0089037284362826e-05,
|
| 1935 |
+
"loss": 0.0886,
|
| 1936 |
+
"step": 2250
|
| 1937 |
+
},
|
| 1938 |
+
{
|
| 1939 |
+
"epoch": 0.6090958310774228,
|
| 1940 |
+
"eval_loss": 0.15883322060108185,
|
| 1941 |
+
"eval_runtime": 63.686,
|
| 1942 |
+
"eval_samples_per_second": 7.851,
|
| 1943 |
+
"eval_steps_per_second": 0.251,
|
| 1944 |
+
"step": 2250
|
| 1945 |
+
},
|
| 1946 |
+
{
|
| 1947 |
+
"epoch": 0.6118029236599891,
|
| 1948 |
+
"grad_norm": 2.046875,
|
| 1949 |
+
"learning_rate": 1.994991652754591e-05,
|
| 1950 |
+
"loss": 0.1134,
|
| 1951 |
+
"step": 2260
|
| 1952 |
+
},
|
| 1953 |
+
{
|
| 1954 |
+
"epoch": 0.6145100162425555,
|
| 1955 |
+
"grad_norm": 2.296875,
|
| 1956 |
+
"learning_rate": 1.9810795770728994e-05,
|
| 1957 |
+
"loss": 0.1273,
|
| 1958 |
+
"step": 2270
|
| 1959 |
+
},
|
| 1960 |
+
{
|
| 1961 |
+
"epoch": 0.6172171088251218,
|
| 1962 |
+
"grad_norm": 1.3671875,
|
| 1963 |
+
"learning_rate": 1.9671675013912077e-05,
|
| 1964 |
+
"loss": 0.118,
|
| 1965 |
+
"step": 2280
|
| 1966 |
+
},
|
| 1967 |
+
{
|
| 1968 |
+
"epoch": 0.6199242014076881,
|
| 1969 |
+
"grad_norm": 1.3203125,
|
| 1970 |
+
"learning_rate": 1.9532554257095158e-05,
|
| 1971 |
+
"loss": 0.1127,
|
| 1972 |
+
"step": 2290
|
| 1973 |
+
},
|
| 1974 |
+
{
|
| 1975 |
+
"epoch": 0.6226312939902545,
|
| 1976 |
+
"grad_norm": 1.703125,
|
| 1977 |
+
"learning_rate": 1.9393433500278245e-05,
|
| 1978 |
+
"loss": 0.1319,
|
| 1979 |
+
"step": 2300
|
| 1980 |
+
},
|
| 1981 |
+
{
|
| 1982 |
+
"epoch": 0.6226312939902545,
|
| 1983 |
+
"eval_loss": 0.1598823368549347,
|
| 1984 |
+
"eval_runtime": 63.542,
|
| 1985 |
+
"eval_samples_per_second": 7.869,
|
| 1986 |
+
"eval_steps_per_second": 0.252,
|
| 1987 |
+
"step": 2300
|
| 1988 |
+
},
|
| 1989 |
+
{
|
| 1990 |
+
"epoch": 0.6253383865728208,
|
| 1991 |
+
"grad_norm": 1.75,
|
| 1992 |
+
"learning_rate": 1.9254312743461325e-05,
|
| 1993 |
+
"loss": 0.1115,
|
| 1994 |
+
"step": 2310
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"epoch": 0.6280454791553871,
|
| 1998 |
+
"grad_norm": 2.3125,
|
| 1999 |
+
"learning_rate": 1.911519198664441e-05,
|
| 2000 |
+
"loss": 0.1411,
|
| 2001 |
+
"step": 2320
|
| 2002 |
+
},
|
| 2003 |
+
{
|
| 2004 |
+
"epoch": 0.6307525717379534,
|
| 2005 |
+
"grad_norm": 1.1484375,
|
| 2006 |
+
"learning_rate": 1.8976071229827493e-05,
|
| 2007 |
+
"loss": 0.1097,
|
| 2008 |
+
"step": 2330
|
| 2009 |
+
},
|
| 2010 |
+
{
|
| 2011 |
+
"epoch": 0.6334596643205198,
|
| 2012 |
+
"grad_norm": 3.5,
|
| 2013 |
+
"learning_rate": 1.8836950473010573e-05,
|
| 2014 |
+
"loss": 0.1072,
|
| 2015 |
+
"step": 2340
|
| 2016 |
+
},
|
| 2017 |
+
{
|
| 2018 |
+
"epoch": 0.6361667569030861,
|
| 2019 |
+
"grad_norm": 1.09375,
|
| 2020 |
+
"learning_rate": 1.8697829716193657e-05,
|
| 2021 |
+
"loss": 0.1215,
|
| 2022 |
+
"step": 2350
|
| 2023 |
+
},
|
| 2024 |
+
{
|
| 2025 |
+
"epoch": 0.6361667569030861,
|
| 2026 |
+
"eval_loss": 0.15923769772052765,
|
| 2027 |
+
"eval_runtime": 62.8745,
|
| 2028 |
+
"eval_samples_per_second": 7.952,
|
| 2029 |
+
"eval_steps_per_second": 0.254,
|
| 2030 |
+
"step": 2350
|
| 2031 |
+
},
|
| 2032 |
+
{
|
| 2033 |
+
"epoch": 0.6388738494856524,
|
| 2034 |
+
"grad_norm": 2.78125,
|
| 2035 |
+
"learning_rate": 1.8558708959376737e-05,
|
| 2036 |
+
"loss": 0.0999,
|
| 2037 |
+
"step": 2360
|
| 2038 |
+
},
|
| 2039 |
+
{
|
| 2040 |
+
"epoch": 0.6415809420682187,
|
| 2041 |
+
"grad_norm": 0.5390625,
|
| 2042 |
+
"learning_rate": 1.8419588202559824e-05,
|
| 2043 |
+
"loss": 0.134,
|
| 2044 |
+
"step": 2370
|
| 2045 |
+
},
|
| 2046 |
+
{
|
| 2047 |
+
"epoch": 0.6442880346507851,
|
| 2048 |
+
"grad_norm": 3.703125,
|
| 2049 |
+
"learning_rate": 1.8280467445742905e-05,
|
| 2050 |
+
"loss": 0.1648,
|
| 2051 |
+
"step": 2380
|
| 2052 |
+
},
|
| 2053 |
+
{
|
| 2054 |
+
"epoch": 0.6469951272333514,
|
| 2055 |
+
"grad_norm": 2.046875,
|
| 2056 |
+
"learning_rate": 1.814134668892599e-05,
|
| 2057 |
+
"loss": 0.1272,
|
| 2058 |
+
"step": 2390
|
| 2059 |
+
},
|
| 2060 |
+
{
|
| 2061 |
+
"epoch": 0.6497022198159177,
|
| 2062 |
+
"grad_norm": 0.91796875,
|
| 2063 |
+
"learning_rate": 1.8002225932109072e-05,
|
| 2064 |
+
"loss": 0.1202,
|
| 2065 |
+
"step": 2400
|
| 2066 |
+
},
|
| 2067 |
+
{
|
| 2068 |
+
"epoch": 0.6497022198159177,
|
| 2069 |
+
"eval_loss": 0.156494602560997,
|
| 2070 |
+
"eval_runtime": 63.7775,
|
| 2071 |
+
"eval_samples_per_second": 7.84,
|
| 2072 |
+
"eval_steps_per_second": 0.251,
|
| 2073 |
+
"step": 2400
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.652409312398484,
|
| 2077 |
+
"grad_norm": 6.3125,
|
| 2078 |
+
"learning_rate": 1.7863105175292156e-05,
|
| 2079 |
+
"loss": 0.1491,
|
| 2080 |
+
"step": 2410
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.6551164049810504,
|
| 2084 |
+
"grad_norm": 1.65625,
|
| 2085 |
+
"learning_rate": 1.7723984418475236e-05,
|
| 2086 |
+
"loss": 0.1209,
|
| 2087 |
+
"step": 2420
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.6578234975636167,
|
| 2091 |
+
"grad_norm": 0.73828125,
|
| 2092 |
+
"learning_rate": 1.758486366165832e-05,
|
| 2093 |
+
"loss": 0.1295,
|
| 2094 |
+
"step": 2430
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.660530590146183,
|
| 2098 |
+
"grad_norm": 2.765625,
|
| 2099 |
+
"learning_rate": 1.7445742904841404e-05,
|
| 2100 |
+
"loss": 0.1013,
|
| 2101 |
+
"step": 2440
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.6632376827287493,
|
| 2105 |
+
"grad_norm": 0.53515625,
|
| 2106 |
+
"learning_rate": 1.7306622148024488e-05,
|
| 2107 |
+
"loss": 0.1537,
|
| 2108 |
+
"step": 2450
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.6632376827287493,
|
| 2112 |
+
"eval_loss": 0.15601959824562073,
|
| 2113 |
+
"eval_runtime": 64.3267,
|
| 2114 |
+
"eval_samples_per_second": 7.773,
|
| 2115 |
+
"eval_steps_per_second": 0.249,
|
| 2116 |
+
"step": 2450
|
| 2117 |
+
},
|
| 2118 |
+
{
|
| 2119 |
+
"epoch": 0.6659447753113157,
|
| 2120 |
+
"grad_norm": 2.984375,
|
| 2121 |
+
"learning_rate": 1.7167501391207568e-05,
|
| 2122 |
+
"loss": 0.1364,
|
| 2123 |
+
"step": 2460
|
| 2124 |
+
},
|
| 2125 |
+
{
|
| 2126 |
+
"epoch": 0.668651867893882,
|
| 2127 |
+
"grad_norm": 1.8828125,
|
| 2128 |
+
"learning_rate": 1.7028380634390652e-05,
|
| 2129 |
+
"loss": 0.1121,
|
| 2130 |
+
"step": 2470
|
| 2131 |
+
},
|
| 2132 |
+
{
|
| 2133 |
+
"epoch": 0.6713589604764483,
|
| 2134 |
+
"grad_norm": 1.40625,
|
| 2135 |
+
"learning_rate": 1.6889259877573735e-05,
|
| 2136 |
+
"loss": 0.135,
|
| 2137 |
+
"step": 2480
|
| 2138 |
+
},
|
| 2139 |
+
{
|
| 2140 |
+
"epoch": 0.6740660530590146,
|
| 2141 |
+
"grad_norm": 2.609375,
|
| 2142 |
+
"learning_rate": 1.6750139120756816e-05,
|
| 2143 |
+
"loss": 0.1312,
|
| 2144 |
+
"step": 2490
|
| 2145 |
+
},
|
| 2146 |
+
{
|
| 2147 |
+
"epoch": 0.676773145641581,
|
| 2148 |
+
"grad_norm": 1.1015625,
|
| 2149 |
+
"learning_rate": 1.66110183639399e-05,
|
| 2150 |
+
"loss": 0.1146,
|
| 2151 |
+
"step": 2500
|
| 2152 |
+
},
|
| 2153 |
+
{
|
| 2154 |
+
"epoch": 0.676773145641581,
|
| 2155 |
+
"eval_loss": 0.15720410645008087,
|
| 2156 |
+
"eval_runtime": 82.5469,
|
| 2157 |
+
"eval_samples_per_second": 6.057,
|
| 2158 |
+
"eval_steps_per_second": 0.194,
|
| 2159 |
+
"step": 2500
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.6794802382241473,
|
| 2163 |
+
"grad_norm": 2.921875,
|
| 2164 |
+
"learning_rate": 1.6471897607122983e-05,
|
| 2165 |
+
"loss": 0.132,
|
| 2166 |
+
"step": 2510
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.6821873308067136,
|
| 2170 |
+
"grad_norm": 1.109375,
|
| 2171 |
+
"learning_rate": 1.6332776850306067e-05,
|
| 2172 |
+
"loss": 0.1216,
|
| 2173 |
+
"step": 2520
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.6848944233892799,
|
| 2177 |
+
"grad_norm": 1.0625,
|
| 2178 |
+
"learning_rate": 1.6193656093489147e-05,
|
| 2179 |
+
"loss": 0.1181,
|
| 2180 |
+
"step": 2530
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.6876015159718463,
|
| 2184 |
+
"grad_norm": 0.236328125,
|
| 2185 |
+
"learning_rate": 1.605453533667223e-05,
|
| 2186 |
+
"loss": 0.1067,
|
| 2187 |
+
"step": 2540
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.6903086085544126,
|
| 2191 |
+
"grad_norm": 1.5,
|
| 2192 |
+
"learning_rate": 1.5915414579855315e-05,
|
| 2193 |
+
"loss": 0.1363,
|
| 2194 |
+
"step": 2550
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.6903086085544126,
|
| 2198 |
+
"eval_loss": 0.15796752274036407,
|
| 2199 |
+
"eval_runtime": 64.1468,
|
| 2200 |
+
"eval_samples_per_second": 7.795,
|
| 2201 |
+
"eval_steps_per_second": 0.249,
|
| 2202 |
+
"step": 2550
|
| 2203 |
+
},
|
| 2204 |
+
{
|
| 2205 |
+
"epoch": 0.6930157011369789,
|
| 2206 |
+
"grad_norm": 1.5703125,
|
| 2207 |
+
"learning_rate": 1.57762938230384e-05,
|
| 2208 |
+
"loss": 0.0929,
|
| 2209 |
+
"step": 2560
|
| 2210 |
+
},
|
| 2211 |
+
{
|
| 2212 |
+
"epoch": 0.6957227937195453,
|
| 2213 |
+
"grad_norm": 0.94140625,
|
| 2214 |
+
"learning_rate": 1.563717306622148e-05,
|
| 2215 |
+
"loss": 0.1125,
|
| 2216 |
+
"step": 2570
|
| 2217 |
+
},
|
| 2218 |
+
{
|
| 2219 |
+
"epoch": 0.6984298863021116,
|
| 2220 |
+
"grad_norm": 2.140625,
|
| 2221 |
+
"learning_rate": 1.5498052309404566e-05,
|
| 2222 |
+
"loss": 0.1053,
|
| 2223 |
+
"step": 2580
|
| 2224 |
+
},
|
| 2225 |
+
{
|
| 2226 |
+
"epoch": 0.7011369788846779,
|
| 2227 |
+
"grad_norm": 2.578125,
|
| 2228 |
+
"learning_rate": 1.5358931552587647e-05,
|
| 2229 |
+
"loss": 0.111,
|
| 2230 |
+
"step": 2590
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 0.7038440714672441,
|
| 2234 |
+
"grad_norm": 2.484375,
|
| 2235 |
+
"learning_rate": 1.521981079577073e-05,
|
| 2236 |
+
"loss": 0.111,
|
| 2237 |
+
"step": 2600
|
| 2238 |
+
},
|
| 2239 |
+
{
|
| 2240 |
+
"epoch": 0.7038440714672441,
|
| 2241 |
+
"eval_loss": 0.15660835802555084,
|
| 2242 |
+
"eval_runtime": 64.7015,
|
| 2243 |
+
"eval_samples_per_second": 7.728,
|
| 2244 |
+
"eval_steps_per_second": 0.247,
|
| 2245 |
+
"step": 2600
|
| 2246 |
+
},
|
| 2247 |
+
{
|
| 2248 |
+
"epoch": 0.7065511640498106,
|
| 2249 |
+
"grad_norm": 0.69921875,
|
| 2250 |
+
"learning_rate": 1.5080690038953812e-05,
|
| 2251 |
+
"loss": 0.1276,
|
| 2252 |
+
"step": 2610
|
| 2253 |
+
},
|
| 2254 |
+
{
|
| 2255 |
+
"epoch": 0.7092582566323768,
|
| 2256 |
+
"grad_norm": 1.6328125,
|
| 2257 |
+
"learning_rate": 1.4941569282136896e-05,
|
| 2258 |
+
"loss": 0.1508,
|
| 2259 |
+
"step": 2620
|
| 2260 |
+
},
|
| 2261 |
+
{
|
| 2262 |
+
"epoch": 0.7119653492149431,
|
| 2263 |
+
"grad_norm": 2.265625,
|
| 2264 |
+
"learning_rate": 1.4802448525319978e-05,
|
| 2265 |
+
"loss": 0.1717,
|
| 2266 |
+
"step": 2630
|
| 2267 |
+
},
|
| 2268 |
+
{
|
| 2269 |
+
"epoch": 0.7146724417975094,
|
| 2270 |
+
"grad_norm": 1.9765625,
|
| 2271 |
+
"learning_rate": 1.466332776850306e-05,
|
| 2272 |
+
"loss": 0.1422,
|
| 2273 |
+
"step": 2640
|
| 2274 |
+
},
|
| 2275 |
+
{
|
| 2276 |
+
"epoch": 0.7173795343800758,
|
| 2277 |
+
"grad_norm": 1.1796875,
|
| 2278 |
+
"learning_rate": 1.4524207011686144e-05,
|
| 2279 |
+
"loss": 0.1003,
|
| 2280 |
+
"step": 2650
|
| 2281 |
+
},
|
| 2282 |
+
{
|
| 2283 |
+
"epoch": 0.7173795343800758,
|
| 2284 |
+
"eval_loss": 0.15460146963596344,
|
| 2285 |
+
"eval_runtime": 65.1755,
|
| 2286 |
+
"eval_samples_per_second": 7.672,
|
| 2287 |
+
"eval_steps_per_second": 0.245,
|
| 2288 |
+
"step": 2650
|
| 2289 |
+
},
|
| 2290 |
+
{
|
| 2291 |
+
"epoch": 0.7200866269626421,
|
| 2292 |
+
"grad_norm": 1.796875,
|
| 2293 |
+
"learning_rate": 1.4385086254869226e-05,
|
| 2294 |
+
"loss": 0.1366,
|
| 2295 |
+
"step": 2660
|
| 2296 |
+
},
|
| 2297 |
+
{
|
| 2298 |
+
"epoch": 0.7227937195452084,
|
| 2299 |
+
"grad_norm": 1.59375,
|
| 2300 |
+
"learning_rate": 1.424596549805231e-05,
|
| 2301 |
+
"loss": 0.1316,
|
| 2302 |
+
"step": 2670
|
| 2303 |
+
},
|
| 2304 |
+
{
|
| 2305 |
+
"epoch": 0.7255008121277747,
|
| 2306 |
+
"grad_norm": 2.671875,
|
| 2307 |
+
"learning_rate": 1.4106844741235392e-05,
|
| 2308 |
+
"loss": 0.1367,
|
| 2309 |
+
"step": 2680
|
| 2310 |
+
},
|
| 2311 |
+
{
|
| 2312 |
+
"epoch": 0.7282079047103411,
|
| 2313 |
+
"grad_norm": 1.75,
|
| 2314 |
+
"learning_rate": 1.3967723984418477e-05,
|
| 2315 |
+
"loss": 0.13,
|
| 2316 |
+
"step": 2690
|
| 2317 |
+
},
|
| 2318 |
+
{
|
| 2319 |
+
"epoch": 0.7309149972929074,
|
| 2320 |
+
"grad_norm": 2.96875,
|
| 2321 |
+
"learning_rate": 1.3828603227601558e-05,
|
| 2322 |
+
"loss": 0.1213,
|
| 2323 |
+
"step": 2700
|
| 2324 |
+
},
|
| 2325 |
+
{
|
| 2326 |
+
"epoch": 0.7309149972929074,
|
| 2327 |
+
"eval_loss": 0.15699392557144165,
|
| 2328 |
+
"eval_runtime": 64.8654,
|
| 2329 |
+
"eval_samples_per_second": 7.708,
|
| 2330 |
+
"eval_steps_per_second": 0.247,
|
| 2331 |
+
"step": 2700
|
| 2332 |
+
},
|
| 2333 |
+
{
|
| 2334 |
+
"epoch": 0.7336220898754737,
|
| 2335 |
+
"grad_norm": 3.171875,
|
| 2336 |
+
"learning_rate": 1.3689482470784643e-05,
|
| 2337 |
+
"loss": 0.1303,
|
| 2338 |
+
"step": 2710
|
| 2339 |
+
},
|
| 2340 |
+
{
|
| 2341 |
+
"epoch": 0.73632918245804,
|
| 2342 |
+
"grad_norm": 0.78125,
|
| 2343 |
+
"learning_rate": 1.3550361713967724e-05,
|
| 2344 |
+
"loss": 0.1496,
|
| 2345 |
+
"step": 2720
|
| 2346 |
+
},
|
| 2347 |
+
{
|
| 2348 |
+
"epoch": 0.7390362750406064,
|
| 2349 |
+
"grad_norm": 1.2421875,
|
| 2350 |
+
"learning_rate": 1.3411240957150809e-05,
|
| 2351 |
+
"loss": 0.1129,
|
| 2352 |
+
"step": 2730
|
| 2353 |
+
},
|
| 2354 |
+
{
|
| 2355 |
+
"epoch": 0.7417433676231727,
|
| 2356 |
+
"grad_norm": 2.703125,
|
| 2357 |
+
"learning_rate": 1.327212020033389e-05,
|
| 2358 |
+
"loss": 0.128,
|
| 2359 |
+
"step": 2740
|
| 2360 |
+
},
|
| 2361 |
+
{
|
| 2362 |
+
"epoch": 0.744450460205739,
|
| 2363 |
+
"grad_norm": 2.328125,
|
| 2364 |
+
"learning_rate": 1.3132999443516975e-05,
|
| 2365 |
+
"loss": 0.1081,
|
| 2366 |
+
"step": 2750
|
| 2367 |
+
},
|
| 2368 |
+
{
|
| 2369 |
+
"epoch": 0.744450460205739,
|
| 2370 |
+
"eval_loss": 0.1565748006105423,
|
| 2371 |
+
"eval_runtime": 64.732,
|
| 2372 |
+
"eval_samples_per_second": 7.724,
|
| 2373 |
+
"eval_steps_per_second": 0.247,
|
| 2374 |
+
"step": 2750
|
| 2375 |
+
},
|
| 2376 |
+
{
|
| 2377 |
+
"epoch": 0.7471575527883053,
|
| 2378 |
+
"grad_norm": 1.6015625,
|
| 2379 |
+
"learning_rate": 1.2993878686700057e-05,
|
| 2380 |
+
"loss": 0.1355,
|
| 2381 |
+
"step": 2760
|
| 2382 |
+
},
|
| 2383 |
+
{
|
| 2384 |
+
"epoch": 0.7498646453708717,
|
| 2385 |
+
"grad_norm": 1.1015625,
|
| 2386 |
+
"learning_rate": 1.285475792988314e-05,
|
| 2387 |
+
"loss": 0.1341,
|
| 2388 |
+
"step": 2770
|
| 2389 |
+
},
|
| 2390 |
+
{
|
| 2391 |
+
"epoch": 0.752571737953438,
|
| 2392 |
+
"grad_norm": 0.98828125,
|
| 2393 |
+
"learning_rate": 1.2715637173066223e-05,
|
| 2394 |
+
"loss": 0.1169,
|
| 2395 |
+
"step": 2780
|
| 2396 |
+
},
|
| 2397 |
+
{
|
| 2398 |
+
"epoch": 0.7552788305360043,
|
| 2399 |
+
"grad_norm": 0.60546875,
|
| 2400 |
+
"learning_rate": 1.2576516416249303e-05,
|
| 2401 |
+
"loss": 0.0924,
|
| 2402 |
+
"step": 2790
|
| 2403 |
+
},
|
| 2404 |
+
{
|
| 2405 |
+
"epoch": 0.7579859231185706,
|
| 2406 |
+
"grad_norm": 1.4921875,
|
| 2407 |
+
"learning_rate": 1.2437395659432388e-05,
|
| 2408 |
+
"loss": 0.1634,
|
| 2409 |
+
"step": 2800
|
| 2410 |
+
},
|
| 2411 |
+
{
|
| 2412 |
+
"epoch": 0.7579859231185706,
|
| 2413 |
+
"eval_loss": 0.1555679589509964,
|
| 2414 |
+
"eval_runtime": 65.0072,
|
| 2415 |
+
"eval_samples_per_second": 7.691,
|
| 2416 |
+
"eval_steps_per_second": 0.246,
|
| 2417 |
+
"step": 2800
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.760693015701137,
|
| 2421 |
+
"grad_norm": 1.6796875,
|
| 2422 |
+
"learning_rate": 1.229827490261547e-05,
|
| 2423 |
+
"loss": 0.1255,
|
| 2424 |
+
"step": 2810
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.7634001082837033,
|
| 2428 |
+
"grad_norm": 0.83984375,
|
| 2429 |
+
"learning_rate": 1.2159154145798554e-05,
|
| 2430 |
+
"loss": 0.0838,
|
| 2431 |
+
"step": 2820
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.7661072008662696,
|
| 2435 |
+
"grad_norm": 3.375,
|
| 2436 |
+
"learning_rate": 1.2020033388981636e-05,
|
| 2437 |
+
"loss": 0.1031,
|
| 2438 |
+
"step": 2830
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.7688142934488359,
|
| 2442 |
+
"grad_norm": 1.5,
|
| 2443 |
+
"learning_rate": 1.188091263216472e-05,
|
| 2444 |
+
"loss": 0.1125,
|
| 2445 |
+
"step": 2840
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.7715213860314023,
|
| 2449 |
+
"grad_norm": 1.7421875,
|
| 2450 |
+
"learning_rate": 1.1741791875347802e-05,
|
| 2451 |
+
"loss": 0.1427,
|
| 2452 |
+
"step": 2850
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.7715213860314023,
|
| 2456 |
+
"eval_loss": 0.15634971857070923,
|
| 2457 |
+
"eval_runtime": 64.5468,
|
| 2458 |
+
"eval_samples_per_second": 7.746,
|
| 2459 |
+
"eval_steps_per_second": 0.248,
|
| 2460 |
+
"step": 2850
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.7742284786139686,
|
| 2464 |
+
"grad_norm": 2.484375,
|
| 2465 |
+
"learning_rate": 1.1602671118530884e-05,
|
| 2466 |
+
"loss": 0.1233,
|
| 2467 |
+
"step": 2860
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.7769355711965349,
|
| 2471 |
+
"grad_norm": 0.95703125,
|
| 2472 |
+
"learning_rate": 1.1463550361713968e-05,
|
| 2473 |
+
"loss": 0.1146,
|
| 2474 |
+
"step": 2870
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.7796426637791013,
|
| 2478 |
+
"grad_norm": 1.5703125,
|
| 2479 |
+
"learning_rate": 1.132442960489705e-05,
|
| 2480 |
+
"loss": 0.1301,
|
| 2481 |
+
"step": 2880
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.7823497563616676,
|
| 2485 |
+
"grad_norm": 1.515625,
|
| 2486 |
+
"learning_rate": 1.1185308848080134e-05,
|
| 2487 |
+
"loss": 0.1238,
|
| 2488 |
+
"step": 2890
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.7850568489442339,
|
| 2492 |
+
"grad_norm": 1.828125,
|
| 2493 |
+
"learning_rate": 1.1046188091263218e-05,
|
| 2494 |
+
"loss": 0.1161,
|
| 2495 |
+
"step": 2900
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.7850568489442339,
|
| 2499 |
+
"eval_loss": 0.1560017168521881,
|
| 2500 |
+
"eval_runtime": 64.4442,
|
| 2501 |
+
"eval_samples_per_second": 7.759,
|
| 2502 |
+
"eval_steps_per_second": 0.248,
|
| 2503 |
+
"step": 2900
|
| 2504 |
+
},
|
| 2505 |
+
{
|
| 2506 |
+
"epoch": 0.7877639415268002,
|
| 2507 |
+
"grad_norm": 1.03125,
|
| 2508 |
+
"learning_rate": 1.09070673344463e-05,
|
| 2509 |
+
"loss": 0.0932,
|
| 2510 |
+
"step": 2910
|
| 2511 |
+
},
|
| 2512 |
+
{
|
| 2513 |
+
"epoch": 0.7904710341093666,
|
| 2514 |
+
"grad_norm": 1.1171875,
|
| 2515 |
+
"learning_rate": 1.0767946577629383e-05,
|
| 2516 |
+
"loss": 0.1132,
|
| 2517 |
+
"step": 2920
|
| 2518 |
+
},
|
| 2519 |
+
{
|
| 2520 |
+
"epoch": 0.7931781266919329,
|
| 2521 |
+
"grad_norm": 1.3125,
|
| 2522 |
+
"learning_rate": 1.0628825820812465e-05,
|
| 2523 |
+
"loss": 0.1272,
|
| 2524 |
+
"step": 2930
|
| 2525 |
+
},
|
| 2526 |
+
{
|
| 2527 |
+
"epoch": 0.7958852192744992,
|
| 2528 |
+
"grad_norm": 2.109375,
|
| 2529 |
+
"learning_rate": 1.0489705063995549e-05,
|
| 2530 |
+
"loss": 0.1251,
|
| 2531 |
+
"step": 2940
|
| 2532 |
+
},
|
| 2533 |
+
{
|
| 2534 |
+
"epoch": 0.7985923118570655,
|
| 2535 |
+
"grad_norm": 1.7734375,
|
| 2536 |
+
"learning_rate": 1.0350584307178631e-05,
|
| 2537 |
+
"loss": 0.1188,
|
| 2538 |
+
"step": 2950
|
| 2539 |
+
},
|
| 2540 |
+
{
|
| 2541 |
+
"epoch": 0.7985923118570655,
|
| 2542 |
+
"eval_loss": 0.1543656885623932,
|
| 2543 |
+
"eval_runtime": 63.1528,
|
| 2544 |
+
"eval_samples_per_second": 7.917,
|
| 2545 |
+
"eval_steps_per_second": 0.253,
|
| 2546 |
+
"step": 2950
|
| 2547 |
+
},
|
| 2548 |
+
{
|
| 2549 |
+
"epoch": 0.8012994044396319,
|
| 2550 |
+
"grad_norm": 1.796875,
|
| 2551 |
+
"learning_rate": 1.0211463550361715e-05,
|
| 2552 |
+
"loss": 0.1261,
|
| 2553 |
+
"step": 2960
|
| 2554 |
+
},
|
| 2555 |
+
{
|
| 2556 |
+
"epoch": 0.8040064970221982,
|
| 2557 |
+
"grad_norm": 0.67578125,
|
| 2558 |
+
"learning_rate": 1.0072342793544797e-05,
|
| 2559 |
+
"loss": 0.1121,
|
| 2560 |
+
"step": 2970
|
| 2561 |
+
},
|
| 2562 |
+
{
|
| 2563 |
+
"epoch": 0.8067135896047645,
|
| 2564 |
+
"grad_norm": 1.0390625,
|
| 2565 |
+
"learning_rate": 9.93322203672788e-06,
|
| 2566 |
+
"loss": 0.1267,
|
| 2567 |
+
"step": 2980
|
| 2568 |
+
},
|
| 2569 |
+
{
|
| 2570 |
+
"epoch": 0.8094206821873308,
|
| 2571 |
+
"grad_norm": 1.8125,
|
| 2572 |
+
"learning_rate": 9.794101279910965e-06,
|
| 2573 |
+
"loss": 0.0998,
|
| 2574 |
+
"step": 2990
|
| 2575 |
+
},
|
| 2576 |
+
{
|
| 2577 |
+
"epoch": 0.8121277747698972,
|
| 2578 |
+
"grad_norm": 1.8984375,
|
| 2579 |
+
"learning_rate": 9.654980523094045e-06,
|
| 2580 |
+
"loss": 0.1153,
|
| 2581 |
+
"step": 3000
|
| 2582 |
+
},
|
| 2583 |
+
{
|
| 2584 |
+
"epoch": 0.8121277747698972,
|
| 2585 |
+
"eval_loss": 0.15634942054748535,
|
| 2586 |
+
"eval_runtime": 78.3242,
|
| 2587 |
+
"eval_samples_per_second": 6.384,
|
| 2588 |
+
"eval_steps_per_second": 0.204,
|
| 2589 |
+
"step": 3000
|
| 2590 |
+
},
|
| 2591 |
+
{
|
| 2592 |
+
"epoch": 0.8148348673524635,
|
| 2593 |
+
"grad_norm": 0.8515625,
|
| 2594 |
+
"learning_rate": 9.515859766277129e-06,
|
| 2595 |
+
"loss": 0.1116,
|
| 2596 |
+
"step": 3010
|
| 2597 |
+
},
|
| 2598 |
+
{
|
| 2599 |
+
"epoch": 0.8175419599350298,
|
| 2600 |
+
"grad_norm": 1.5859375,
|
| 2601 |
+
"learning_rate": 9.37673900946021e-06,
|
| 2602 |
+
"loss": 0.1083,
|
| 2603 |
+
"step": 3020
|
| 2604 |
+
},
|
| 2605 |
+
{
|
| 2606 |
+
"epoch": 0.8202490525175961,
|
| 2607 |
+
"grad_norm": 1.15625,
|
| 2608 |
+
"learning_rate": 9.237618252643294e-06,
|
| 2609 |
+
"loss": 0.1535,
|
| 2610 |
+
"step": 3030
|
| 2611 |
+
},
|
| 2612 |
+
{
|
| 2613 |
+
"epoch": 0.8229561451001625,
|
| 2614 |
+
"grad_norm": 1.1796875,
|
| 2615 |
+
"learning_rate": 9.098497495826378e-06,
|
| 2616 |
+
"loss": 0.1179,
|
| 2617 |
+
"step": 3040
|
| 2618 |
+
},
|
| 2619 |
+
{
|
| 2620 |
+
"epoch": 0.8256632376827288,
|
| 2621 |
+
"grad_norm": 1.1875,
|
| 2622 |
+
"learning_rate": 8.95937673900946e-06,
|
| 2623 |
+
"loss": 0.1154,
|
| 2624 |
+
"step": 3050
|
| 2625 |
+
},
|
| 2626 |
+
{
|
| 2627 |
+
"epoch": 0.8256632376827288,
|
| 2628 |
+
"eval_loss": 0.15425148606300354,
|
| 2629 |
+
"eval_runtime": 62.8908,
|
| 2630 |
+
"eval_samples_per_second": 7.95,
|
| 2631 |
+
"eval_steps_per_second": 0.254,
|
| 2632 |
+
"step": 3050
|
| 2633 |
+
},
|
| 2634 |
+
{
|
| 2635 |
+
"epoch": 0.828370330265295,
|
| 2636 |
+
"grad_norm": 4.1875,
|
| 2637 |
+
"learning_rate": 8.820255982192544e-06,
|
| 2638 |
+
"loss": 0.1071,
|
| 2639 |
+
"step": 3060
|
| 2640 |
+
},
|
| 2641 |
+
{
|
| 2642 |
+
"epoch": 0.8310774228478613,
|
| 2643 |
+
"grad_norm": 6.0625,
|
| 2644 |
+
"learning_rate": 8.681135225375626e-06,
|
| 2645 |
+
"loss": 0.1563,
|
| 2646 |
+
"step": 3070
|
| 2647 |
+
},
|
| 2648 |
+
{
|
| 2649 |
+
"epoch": 0.8337845154304278,
|
| 2650 |
+
"grad_norm": 2.234375,
|
| 2651 |
+
"learning_rate": 8.54201446855871e-06,
|
| 2652 |
+
"loss": 0.1412,
|
| 2653 |
+
"step": 3080
|
| 2654 |
+
},
|
| 2655 |
+
{
|
| 2656 |
+
"epoch": 0.836491608012994,
|
| 2657 |
+
"grad_norm": 1.2421875,
|
| 2658 |
+
"learning_rate": 8.402893711741792e-06,
|
| 2659 |
+
"loss": 0.0991,
|
| 2660 |
+
"step": 3090
|
| 2661 |
+
},
|
| 2662 |
+
{
|
| 2663 |
+
"epoch": 0.8391987005955603,
|
| 2664 |
+
"grad_norm": 1.234375,
|
| 2665 |
+
"learning_rate": 8.263772954924876e-06,
|
| 2666 |
+
"loss": 0.1098,
|
| 2667 |
+
"step": 3100
|
| 2668 |
+
},
|
| 2669 |
+
{
|
| 2670 |
+
"epoch": 0.8391987005955603,
|
| 2671 |
+
"eval_loss": 0.15568658709526062,
|
| 2672 |
+
"eval_runtime": 63.402,
|
| 2673 |
+
"eval_samples_per_second": 7.886,
|
| 2674 |
+
"eval_steps_per_second": 0.252,
|
| 2675 |
+
"step": 3100
|
| 2676 |
+
},
|
| 2677 |
+
{
|
| 2678 |
+
"epoch": 0.8419057931781266,
|
| 2679 |
+
"grad_norm": 2.015625,
|
| 2680 |
+
"learning_rate": 8.124652198107958e-06,
|
| 2681 |
+
"loss": 0.1556,
|
| 2682 |
+
"step": 3110
|
| 2683 |
+
},
|
| 2684 |
+
{
|
| 2685 |
+
"epoch": 0.844612885760693,
|
| 2686 |
+
"grad_norm": 4.3125,
|
| 2687 |
+
"learning_rate": 7.985531441291041e-06,
|
| 2688 |
+
"loss": 0.1596,
|
| 2689 |
+
"step": 3120
|
| 2690 |
+
},
|
| 2691 |
+
{
|
| 2692 |
+
"epoch": 0.8473199783432593,
|
| 2693 |
+
"grad_norm": 2.046875,
|
| 2694 |
+
"learning_rate": 7.846410684474125e-06,
|
| 2695 |
+
"loss": 0.1437,
|
| 2696 |
+
"step": 3130
|
| 2697 |
+
},
|
| 2698 |
+
{
|
| 2699 |
+
"epoch": 0.8500270709258256,
|
| 2700 |
+
"grad_norm": 1.15625,
|
| 2701 |
+
"learning_rate": 7.707289927657207e-06,
|
| 2702 |
+
"loss": 0.1511,
|
| 2703 |
+
"step": 3140
|
| 2704 |
+
},
|
| 2705 |
+
{
|
| 2706 |
+
"epoch": 0.852734163508392,
|
| 2707 |
+
"grad_norm": 1.9765625,
|
| 2708 |
+
"learning_rate": 7.568169170840289e-06,
|
| 2709 |
+
"loss": 0.1559,
|
| 2710 |
+
"step": 3150
|
| 2711 |
+
},
|
| 2712 |
+
{
|
| 2713 |
+
"epoch": 0.852734163508392,
|
| 2714 |
+
"eval_loss": 0.15518584847450256,
|
| 2715 |
+
"eval_runtime": 63.1606,
|
| 2716 |
+
"eval_samples_per_second": 7.916,
|
| 2717 |
+
"eval_steps_per_second": 0.253,
|
| 2718 |
+
"step": 3150
|
| 2719 |
+
},
|
| 2720 |
+
{
|
| 2721 |
+
"epoch": 0.8554412560909583,
|
| 2722 |
+
"grad_norm": 1.9921875,
|
| 2723 |
+
"learning_rate": 7.429048414023372e-06,
|
| 2724 |
+
"loss": 0.1392,
|
| 2725 |
+
"step": 3160
|
| 2726 |
+
},
|
| 2727 |
+
{
|
| 2728 |
+
"epoch": 0.8581483486735246,
|
| 2729 |
+
"grad_norm": 2.6875,
|
| 2730 |
+
"learning_rate": 7.289927657206455e-06,
|
| 2731 |
+
"loss": 0.1623,
|
| 2732 |
+
"step": 3170
|
| 2733 |
+
},
|
| 2734 |
+
{
|
| 2735 |
+
"epoch": 0.8608554412560909,
|
| 2736 |
+
"grad_norm": 3.0625,
|
| 2737 |
+
"learning_rate": 7.150806900389538e-06,
|
| 2738 |
+
"loss": 0.1358,
|
| 2739 |
+
"step": 3180
|
| 2740 |
+
},
|
| 2741 |
+
{
|
| 2742 |
+
"epoch": 0.8635625338386573,
|
| 2743 |
+
"grad_norm": 2.375,
|
| 2744 |
+
"learning_rate": 7.011686143572621e-06,
|
| 2745 |
+
"loss": 0.1483,
|
| 2746 |
+
"step": 3190
|
| 2747 |
+
},
|
| 2748 |
+
{
|
| 2749 |
+
"epoch": 0.8662696264212236,
|
| 2750 |
+
"grad_norm": 2.578125,
|
| 2751 |
+
"learning_rate": 6.872565386755704e-06,
|
| 2752 |
+
"loss": 0.1207,
|
| 2753 |
+
"step": 3200
|
| 2754 |
+
},
|
| 2755 |
+
{
|
| 2756 |
+
"epoch": 0.8662696264212236,
|
| 2757 |
+
"eval_loss": 0.15542198717594147,
|
| 2758 |
+
"eval_runtime": 63.3581,
|
| 2759 |
+
"eval_samples_per_second": 7.892,
|
| 2760 |
+
"eval_steps_per_second": 0.253,
|
| 2761 |
+
"step": 3200
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.8689767190037899,
|
| 2765 |
+
"grad_norm": 1.078125,
|
| 2766 |
+
"learning_rate": 6.733444629938787e-06,
|
| 2767 |
+
"loss": 0.1102,
|
| 2768 |
+
"step": 3210
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.8716838115863562,
|
| 2772 |
+
"grad_norm": 1.2421875,
|
| 2773 |
+
"learning_rate": 6.5943238731218705e-06,
|
| 2774 |
+
"loss": 0.1394,
|
| 2775 |
+
"step": 3220
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.8743909041689226,
|
| 2779 |
+
"grad_norm": 2.0625,
|
| 2780 |
+
"learning_rate": 6.455203116304953e-06,
|
| 2781 |
+
"loss": 0.1495,
|
| 2782 |
+
"step": 3230
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.8770979967514889,
|
| 2786 |
+
"grad_norm": 0.7890625,
|
| 2787 |
+
"learning_rate": 6.316082359488036e-06,
|
| 2788 |
+
"loss": 0.1472,
|
| 2789 |
+
"step": 3240
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.8798050893340552,
|
| 2793 |
+
"grad_norm": 6.09375,
|
| 2794 |
+
"learning_rate": 6.176961602671119e-06,
|
| 2795 |
+
"loss": 0.1169,
|
| 2796 |
+
"step": 3250
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.8798050893340552,
|
| 2800 |
+
"eval_loss": 0.15612711012363434,
|
| 2801 |
+
"eval_runtime": 62.8499,
|
| 2802 |
+
"eval_samples_per_second": 7.955,
|
| 2803 |
+
"eval_steps_per_second": 0.255,
|
| 2804 |
+
"step": 3250
|
| 2805 |
+
},
|
| 2806 |
+
{
|
| 2807 |
+
"epoch": 0.8825121819166215,
|
| 2808 |
+
"grad_norm": 1.1328125,
|
| 2809 |
+
"learning_rate": 6.037840845854201e-06,
|
| 2810 |
+
"loss": 0.1208,
|
| 2811 |
+
"step": 3260
|
| 2812 |
+
},
|
| 2813 |
+
{
|
| 2814 |
+
"epoch": 0.8852192744991879,
|
| 2815 |
+
"grad_norm": 1.78125,
|
| 2816 |
+
"learning_rate": 5.898720089037284e-06,
|
| 2817 |
+
"loss": 0.1145,
|
| 2818 |
+
"step": 3270
|
| 2819 |
+
},
|
| 2820 |
+
{
|
| 2821 |
+
"epoch": 0.8879263670817542,
|
| 2822 |
+
"grad_norm": 3.21875,
|
| 2823 |
+
"learning_rate": 5.759599332220367e-06,
|
| 2824 |
+
"loss": 0.1341,
|
| 2825 |
+
"step": 3280
|
| 2826 |
+
},
|
| 2827 |
+
{
|
| 2828 |
+
"epoch": 0.8906334596643205,
|
| 2829 |
+
"grad_norm": 2.265625,
|
| 2830 |
+
"learning_rate": 5.620478575403451e-06,
|
| 2831 |
+
"loss": 0.1278,
|
| 2832 |
+
"step": 3290
|
| 2833 |
+
},
|
| 2834 |
+
{
|
| 2835 |
+
"epoch": 0.8933405522468868,
|
| 2836 |
+
"grad_norm": 2.65625,
|
| 2837 |
+
"learning_rate": 5.481357818586534e-06,
|
| 2838 |
+
"loss": 0.1932,
|
| 2839 |
+
"step": 3300
|
| 2840 |
+
},
|
| 2841 |
+
{
|
| 2842 |
+
"epoch": 0.8933405522468868,
|
| 2843 |
+
"eval_loss": 0.15443623065948486,
|
| 2844 |
+
"eval_runtime": 63.1624,
|
| 2845 |
+
"eval_samples_per_second": 7.916,
|
| 2846 |
+
"eval_steps_per_second": 0.253,
|
| 2847 |
+
"step": 3300
|
| 2848 |
+
},
|
| 2849 |
+
{
|
| 2850 |
+
"epoch": 0.8960476448294532,
|
| 2851 |
+
"grad_norm": 2.3125,
|
| 2852 |
+
"learning_rate": 5.342237061769617e-06,
|
| 2853 |
+
"loss": 0.113,
|
| 2854 |
+
"step": 3310
|
| 2855 |
+
},
|
| 2856 |
+
{
|
| 2857 |
+
"epoch": 0.8987547374120195,
|
| 2858 |
+
"grad_norm": 1.921875,
|
| 2859 |
+
"learning_rate": 5.2031163049526995e-06,
|
| 2860 |
+
"loss": 0.0939,
|
| 2861 |
+
"step": 3320
|
| 2862 |
+
},
|
| 2863 |
+
{
|
| 2864 |
+
"epoch": 0.9014618299945858,
|
| 2865 |
+
"grad_norm": 3.125,
|
| 2866 |
+
"learning_rate": 5.0639955481357824e-06,
|
| 2867 |
+
"loss": 0.122,
|
| 2868 |
+
"step": 3330
|
| 2869 |
+
},
|
| 2870 |
+
{
|
| 2871 |
+
"epoch": 0.9041689225771521,
|
| 2872 |
+
"grad_norm": 0.84765625,
|
| 2873 |
+
"learning_rate": 4.9248747913188645e-06,
|
| 2874 |
+
"loss": 0.0583,
|
| 2875 |
+
"step": 3340
|
| 2876 |
+
},
|
| 2877 |
+
{
|
| 2878 |
+
"epoch": 0.9068760151597185,
|
| 2879 |
+
"grad_norm": 1.3125,
|
| 2880 |
+
"learning_rate": 4.785754034501947e-06,
|
| 2881 |
+
"loss": 0.0985,
|
| 2882 |
+
"step": 3350
|
| 2883 |
+
},
|
| 2884 |
+
{
|
| 2885 |
+
"epoch": 0.9068760151597185,
|
| 2886 |
+
"eval_loss": 0.1550075113773346,
|
| 2887 |
+
"eval_runtime": 63.4539,
|
| 2888 |
+
"eval_samples_per_second": 7.88,
|
| 2889 |
+
"eval_steps_per_second": 0.252,
|
| 2890 |
+
"step": 3350
|
| 2891 |
+
},
|
| 2892 |
+
{
|
| 2893 |
+
"epoch": 0.9095831077422848,
|
| 2894 |
+
"grad_norm": 1.765625,
|
| 2895 |
+
"learning_rate": 4.646633277685031e-06,
|
| 2896 |
+
"loss": 0.1216,
|
| 2897 |
+
"step": 3360
|
| 2898 |
+
},
|
| 2899 |
+
{
|
| 2900 |
+
"epoch": 0.9122902003248511,
|
| 2901 |
+
"grad_norm": 1.25,
|
| 2902 |
+
"learning_rate": 4.507512520868114e-06,
|
| 2903 |
+
"loss": 0.1355,
|
| 2904 |
+
"step": 3370
|
| 2905 |
+
},
|
| 2906 |
+
{
|
| 2907 |
+
"epoch": 0.9149972929074174,
|
| 2908 |
+
"grad_norm": 0.2236328125,
|
| 2909 |
+
"learning_rate": 4.368391764051197e-06,
|
| 2910 |
+
"loss": 0.1101,
|
| 2911 |
+
"step": 3380
|
| 2912 |
+
},
|
| 2913 |
+
{
|
| 2914 |
+
"epoch": 0.9177043854899838,
|
| 2915 |
+
"grad_norm": 1.7421875,
|
| 2916 |
+
"learning_rate": 4.22927100723428e-06,
|
| 2917 |
+
"loss": 0.0976,
|
| 2918 |
+
"step": 3390
|
| 2919 |
+
},
|
| 2920 |
+
{
|
| 2921 |
+
"epoch": 0.9204114780725501,
|
| 2922 |
+
"grad_norm": 0.83984375,
|
| 2923 |
+
"learning_rate": 4.090150250417363e-06,
|
| 2924 |
+
"loss": 0.1194,
|
| 2925 |
+
"step": 3400
|
| 2926 |
+
},
|
| 2927 |
+
{
|
| 2928 |
+
"epoch": 0.9204114780725501,
|
| 2929 |
+
"eval_loss": 0.15643475949764252,
|
| 2930 |
+
"eval_runtime": 63.0287,
|
| 2931 |
+
"eval_samples_per_second": 7.933,
|
| 2932 |
+
"eval_steps_per_second": 0.254,
|
| 2933 |
+
"step": 3400
|
| 2934 |
+
},
|
| 2935 |
+
{
|
| 2936 |
+
"epoch": 0.9231185706551164,
|
| 2937 |
+
"grad_norm": 3.0625,
|
| 2938 |
+
"learning_rate": 3.951029493600445e-06,
|
| 2939 |
+
"loss": 0.1401,
|
| 2940 |
+
"step": 3410
|
| 2941 |
+
},
|
| 2942 |
+
{
|
| 2943 |
+
"epoch": 0.9258256632376828,
|
| 2944 |
+
"grad_norm": 1.2421875,
|
| 2945 |
+
"learning_rate": 3.811908736783528e-06,
|
| 2946 |
+
"loss": 0.1137,
|
| 2947 |
+
"step": 3420
|
| 2948 |
+
},
|
| 2949 |
+
{
|
| 2950 |
+
"epoch": 0.9285327558202491,
|
| 2951 |
+
"grad_norm": 3.109375,
|
| 2952 |
+
"learning_rate": 3.672787979966611e-06,
|
| 2953 |
+
"loss": 0.1236,
|
| 2954 |
+
"step": 3430
|
| 2955 |
+
},
|
| 2956 |
+
{
|
| 2957 |
+
"epoch": 0.9312398484028154,
|
| 2958 |
+
"grad_norm": 3.109375,
|
| 2959 |
+
"learning_rate": 3.533667223149694e-06,
|
| 2960 |
+
"loss": 0.1108,
|
| 2961 |
+
"step": 3440
|
| 2962 |
+
},
|
| 2963 |
+
{
|
| 2964 |
+
"epoch": 0.9339469409853817,
|
| 2965 |
+
"grad_norm": 2.796875,
|
| 2966 |
+
"learning_rate": 3.3945464663327773e-06,
|
| 2967 |
+
"loss": 0.1309,
|
| 2968 |
+
"step": 3450
|
| 2969 |
+
},
|
| 2970 |
+
{
|
| 2971 |
+
"epoch": 0.9339469409853817,
|
| 2972 |
+
"eval_loss": 0.1561814844608307,
|
| 2973 |
+
"eval_runtime": 63.1871,
|
| 2974 |
+
"eval_samples_per_second": 7.913,
|
| 2975 |
+
"eval_steps_per_second": 0.253,
|
| 2976 |
+
"step": 3450
|
| 2977 |
+
},
|
| 2978 |
+
{
|
| 2979 |
+
"epoch": 0.9366540335679481,
|
| 2980 |
+
"grad_norm": 2.265625,
|
| 2981 |
+
"learning_rate": 3.25542570951586e-06,
|
| 2982 |
+
"loss": 0.197,
|
| 2983 |
+
"step": 3460
|
| 2984 |
+
},
|
| 2985 |
+
{
|
| 2986 |
+
"epoch": 0.9393611261505144,
|
| 2987 |
+
"grad_norm": 2.796875,
|
| 2988 |
+
"learning_rate": 3.1163049526989427e-06,
|
| 2989 |
+
"loss": 0.1253,
|
| 2990 |
+
"step": 3470
|
| 2991 |
+
},
|
| 2992 |
+
{
|
| 2993 |
+
"epoch": 0.9420682187330807,
|
| 2994 |
+
"grad_norm": 2.125,
|
| 2995 |
+
"learning_rate": 2.9771841958820256e-06,
|
| 2996 |
+
"loss": 0.1318,
|
| 2997 |
+
"step": 3480
|
| 2998 |
+
},
|
| 2999 |
+
{
|
| 3000 |
+
"epoch": 0.944775311315647,
|
| 3001 |
+
"grad_norm": 5.21875,
|
| 3002 |
+
"learning_rate": 2.838063439065109e-06,
|
| 3003 |
+
"loss": 0.1233,
|
| 3004 |
+
"step": 3490
|
| 3005 |
+
},
|
| 3006 |
+
{
|
| 3007 |
+
"epoch": 0.9474824038982134,
|
| 3008 |
+
"grad_norm": 0.703125,
|
| 3009 |
+
"learning_rate": 2.6989426822481914e-06,
|
| 3010 |
+
"loss": 0.1058,
|
| 3011 |
+
"step": 3500
|
| 3012 |
+
},
|
| 3013 |
+
{
|
| 3014 |
+
"epoch": 0.9474824038982134,
|
| 3015 |
+
"eval_loss": 0.1561388522386551,
|
| 3016 |
+
"eval_runtime": 73.2191,
|
| 3017 |
+
"eval_samples_per_second": 6.829,
|
| 3018 |
+
"eval_steps_per_second": 0.219,
|
| 3019 |
+
"step": 3500
|
| 3020 |
+
}
|
| 3021 |
+
],
|
| 3022 |
+
"logging_steps": 10,
|
| 3023 |
+
"max_steps": 3694,
|
| 3024 |
+
"num_input_tokens_seen": 0,
|
| 3025 |
+
"num_train_epochs": 1,
|
| 3026 |
+
"save_steps": 500,
|
| 3027 |
+
"stateful_callbacks": {
|
| 3028 |
+
"TrainerControl": {
|
| 3029 |
+
"args": {
|
| 3030 |
+
"should_epoch_stop": false,
|
| 3031 |
+
"should_evaluate": false,
|
| 3032 |
+
"should_log": false,
|
| 3033 |
+
"should_save": true,
|
| 3034 |
+
"should_training_stop": false
|
| 3035 |
+
},
|
| 3036 |
+
"attributes": {}
|
| 3037 |
+
}
|
| 3038 |
+
},
|
| 3039 |
+
"total_flos": 2.05068095973888e+18,
|
| 3040 |
+
"train_batch_size": 32,
|
| 3041 |
+
"trial_name": null,
|
| 3042 |
+
"trial_params": null
|
| 3043 |
+
}
|
checkpoint-3500/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a581b995cbd1ceefb231054f009a9d0777044fc25ab0e59050e256a55069eded
|
| 3 |
+
size 5048
|
git_hash.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
e8348666a5a7fff4dd7d53d81411a46f7e011eba
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_valid_processor_keys": [
|
| 3 |
+
"images",
|
| 4 |
+
"do_resize",
|
| 5 |
+
"size",
|
| 6 |
+
"resample",
|
| 7 |
+
"do_rescale",
|
| 8 |
+
"rescale_factor",
|
| 9 |
+
"do_normalize",
|
| 10 |
+
"image_mean",
|
| 11 |
+
"image_std",
|
| 12 |
+
"return_tensors",
|
| 13 |
+
"data_format",
|
| 14 |
+
"input_data_format",
|
| 15 |
+
"do_convert_rgb"
|
| 16 |
+
],
|
| 17 |
+
"do_convert_rgb": null,
|
| 18 |
+
"do_normalize": true,
|
| 19 |
+
"do_rescale": true,
|
| 20 |
+
"do_resize": true,
|
| 21 |
+
"image_mean": [
|
| 22 |
+
0.5,
|
| 23 |
+
0.5,
|
| 24 |
+
0.5
|
| 25 |
+
],
|
| 26 |
+
"image_processor_type": "SiglipImageProcessor",
|
| 27 |
+
"image_seq_length": 1024,
|
| 28 |
+
"image_std": [
|
| 29 |
+
0.5,
|
| 30 |
+
0.5,
|
| 31 |
+
0.5
|
| 32 |
+
],
|
| 33 |
+
"processor_class": "PaliGemmaProcessor",
|
| 34 |
+
"resample": 3,
|
| 35 |
+
"rescale_factor": 0.00392156862745098,
|
| 36 |
+
"size": {
|
| 37 |
+
"height": 448,
|
| 38 |
+
"width": 448
|
| 39 |
+
}
|
| 40 |
+
}
|
results.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"validation_set": {"ndcg_at_1": 0.782, "ndcg_at_3": 0.83869, "ndcg_at_5": 0.84945, "ndcg_at_10": 0.86122, "ndcg_at_20": 0.86639, "ndcg_at_100": 0.87296, "ndcg_at_1000": 0.87382, "map_at_1": 0.782, "map_at_3": 0.82567, "map_at_5": 0.83167, "map_at_10": 0.83659, "map_at_20": 0.83807, "map_at_100": 0.83894, "map_at_1000": 0.83899, "recall_at_1": 0.782, "recall_at_3": 0.876, "recall_at_5": 0.902, "recall_at_10": 0.938, "recall_at_20": 0.958, "recall_at_100": 0.994, "recall_at_1000": 1.0, "precision_at_1": 0.782, "precision_at_3": 0.292, "precision_at_5": 0.1804, "precision_at_10": 0.0938, "precision_at_20": 0.0479, "precision_at_100": 0.00994, "precision_at_1000": 0.001, "mrr_at_1": 0.786, "mrr_at_3": 0.8293333333333331, "mrr_at_5": 0.8353333333333332, "mrr_at_10": 0.8401857142857142, "mrr_at_20": 0.8413927173703489, "mrr_at_100": 0.842343017479603, "mrr_at_1000": 0.84237119907226, "naucs_at_1_max": 0.1287204083634169, "naucs_at_1_std": 0.04394670353021356, "naucs_at_1_diff1": 0.9147079015332307, "naucs_at_3_max": 0.15408207410154462, "naucs_at_3_std": 0.24171070115262258, "naucs_at_3_diff1": 0.8671703593832085, "naucs_at_5_max": 0.14837363516835303, "naucs_at_5_std": 0.31976600163875035, "naucs_at_5_diff1": 0.8631452581032408, "naucs_at_10_max": 0.1179633143579976, "naucs_at_10_std": 0.597316345893196, "naucs_at_10_diff1": 0.8860124695039325, "naucs_at_20_max": 0.12424969987995331, "naucs_at_20_std": 0.7891823396025082, "naucs_at_20_diff1": 0.9336401227157501, "naucs_at_100_max": -0.17133520074699127, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "syntheticDocQA_energy": {"ndcg_at_1": 0.87, "ndcg_at_3": 0.91917, "ndcg_at_5": 0.92347, "ndcg_at_10": 0.92937, "ndcg_at_20": 0.92937, "ndcg_at_100": 0.93128, "ndcg_at_1000": 0.93277, "map_at_1": 0.87, "map_at_3": 0.90833, "map_at_5": 0.91083, "map_at_10": 0.91294, "map_at_20": 0.91294, "map_at_100": 0.91321, "map_at_1000": 0.91331, "recall_at_1": 0.87, "recall_at_3": 0.95, "recall_at_5": 0.96, "recall_at_10": 0.98, "recall_at_20": 0.98, "recall_at_100": 0.99, "recall_at_1000": 1.0, "precision_at_1": 0.87, "precision_at_3": 0.31667, "precision_at_5": 0.192, "precision_at_10": 0.098, "precision_at_20": 0.049, "precision_at_100": 0.0099, "precision_at_1000": 0.001, "mrr_at_1": 0.88, "mrr_at_3": 0.9133333333333333, "mrr_at_5": 0.9158333333333333, "mrr_at_10": 0.9183730158730158, "mrr_at_20": 0.9183730158730158, "mrr_at_100": 0.9187453269596126, "mrr_at_1000": 0.9187453269596126, "naucs_at_1_max": 0.24364955935718074, "naucs_at_1_std": -0.12800859068355205, "naucs_at_1_diff1": 0.9218692142486855, "naucs_at_3_max": 0.21577964519141157, "naucs_at_3_std": -0.2550887021475216, "naucs_at_3_diff1": 0.9477124183006521, "naucs_at_5_max": 0.05240429505135564, "naucs_at_5_std": -0.5361811391223089, "naucs_at_5_diff1": 0.9346405228758139, "naucs_at_10_max": 0.7957516339869297, "naucs_at_10_std": 0.07936507936508234, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 0.7957516339869297, "naucs_at_20_std": 0.07936507936508234, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_100_max": 0.8692810457516374, "naucs_at_100_std": 0.7222222222222041, "naucs_at_100_diff1": 0.8692810457516374, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_healthcare_industry": {"ndcg_at_1": 0.92, "ndcg_at_3": 0.94893, "ndcg_at_5": 0.94893, "ndcg_at_10": 0.94893, "ndcg_at_20": 0.95163, "ndcg_at_100": 0.95554, "ndcg_at_1000": 0.95554, "map_at_1": 0.92, "map_at_3": 0.94167, "map_at_5": 0.94167, "map_at_10": 0.94167, "map_at_20": 0.9425, "map_at_100": 0.94313, "map_at_1000": 0.94313, "recall_at_1": 0.92, "recall_at_3": 0.97, "recall_at_5": 0.97, "recall_at_10": 0.97, "recall_at_20": 0.98, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.92, "precision_at_3": 0.32333, "precision_at_5": 0.194, "precision_at_10": 0.097, "precision_at_20": 0.049, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.92, "mrr_at_3": 0.9416666666666665, "mrr_at_5": 0.9416666666666665, "mrr_at_10": 0.9426666666666665, "mrr_at_20": 0.9426666666666665, "mrr_at_100": 0.9433152709359603, "mrr_at_1000": 0.9433152709359603, "naucs_at_1_max": 0.129493464052287, "naucs_at_1_std": -0.1989379084967342, "naucs_at_1_diff1": 0.8468137254901948, "naucs_at_3_max": -0.00964830376594965, "naucs_at_3_std": -0.7268907563025196, "naucs_at_3_diff1": 0.8638344226579548, "naucs_at_5_max": -0.009648303765951795, "naucs_at_5_std": -0.7268907563025226, "naucs_at_5_diff1": 0.8638344226579531, "naucs_at_10_max": -0.009648303765951795, "naucs_at_10_std": -0.7268907563025226, "naucs_at_10_diff1": 0.8638344226579531, "naucs_at_20_max": -0.5144724556489195, "naucs_at_20_std": -1.1517273576097127, "naucs_at_20_diff1": 0.9346405228758136, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_artificial_intelligence_test": {"ndcg_at_1": 0.95, "ndcg_at_3": 0.97393, "ndcg_at_5": 0.97393, "ndcg_at_10": 0.97393, "ndcg_at_20": 0.97393, "ndcg_at_100": 0.97581, "ndcg_at_1000": 0.97581, "map_at_1": 0.95, "map_at_3": 0.96833, "map_at_5": 0.96833, "map_at_10": 0.96833, "map_at_20": 0.96833, "map_at_100": 0.96859, "map_at_1000": 0.96859, "recall_at_1": 0.95, "recall_at_3": 0.99, "recall_at_5": 0.99, "recall_at_10": 0.99, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.95, "precision_at_3": 0.33, "precision_at_5": 0.198, "precision_at_10": 0.099, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.95, "mrr_at_3": 0.9683333333333334, "mrr_at_5": 0.9683333333333334, "mrr_at_10": 0.9683333333333334, "mrr_at_20": 0.9683333333333334, "mrr_at_100": 0.9686111111111111, "mrr_at_1000": 0.9686111111111111, "naucs_at_1_max": -0.2407096171802055, "naucs_at_1_std": -0.8749766573295958, "naucs_at_1_diff1": 0.8846872082166202, "naucs_at_3_max": -1.7399626517274398, "naucs_at_3_std": -1.7399626517274398, "naucs_at_3_diff1": 0.5541549953314585, "naucs_at_5_max": -1.7399626517273863, "naucs_at_5_std": -1.7399626517273863, "naucs_at_5_diff1": 0.5541549953314738, "naucs_at_10_max": -1.7399626517273863, "naucs_at_10_std": -1.7399626517273863, "naucs_at_10_diff1": 0.5541549953314738, "naucs_at_20_max": -1.7399626517273863, "naucs_at_20_std": -1.7399626517273863, "naucs_at_20_diff1": 0.5541549953314738, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "syntheticDocQA_government_reports": {"ndcg_at_1": 0.86, "ndcg_at_3": 0.91286, "ndcg_at_5": 0.92147, "ndcg_at_10": 0.92448, "ndcg_at_20": 0.92727, "ndcg_at_100": 0.92929, "ndcg_at_1000": 0.92929, "map_at_1": 0.86, "map_at_3": 0.9, "map_at_5": 0.905, "map_at_10": 0.90611, "map_at_20": 0.90702, "map_at_100": 0.90735, "map_at_1000": 0.90735, "recall_at_1": 0.86, "recall_at_3": 0.95, "recall_at_5": 0.97, "recall_at_10": 0.98, "recall_at_20": 0.99, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.86, "precision_at_3": 0.31667, "precision_at_5": 0.194, "precision_at_10": 0.098, "precision_at_20": 0.0495, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.86, "mrr_at_3": 0.9, "mrr_at_5": 0.905, "mrr_at_10": 0.90625, "mrr_at_20": 0.907159090909091, "mrr_at_100": 0.9075039184952978, "mrr_at_1000": 0.9075039184952978, "naucs_at_1_max": 0.43501454898157155, "naucs_at_1_std": 0.2136275460717749, "naucs_at_1_diff1": 0.9035263960094214, "naucs_at_3_max": 0.6491129785247453, "naucs_at_3_std": 0.4804855275443501, "naucs_at_3_diff1": 0.9477124183006521, "naucs_at_5_max": 1.0, "naucs_at_5_std": 1.0, "naucs_at_5_diff1": 0.9128540305010848, "naucs_at_10_max": 1.0, "naucs_at_10_std": 1.0, "naucs_at_10_diff1": 0.9346405228758136, "naucs_at_20_max": 1.0, "naucs_at_20_std": 1.0, "naucs_at_20_diff1": 0.8692810457516413, "naucs_at_100_max": NaN, "naucs_at_100_std": NaN, "naucs_at_100_diff1": NaN, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "infovqa_subsampled": {"ndcg_at_1": 0.732, "ndcg_at_3": 0.79395, "ndcg_at_5": 0.81366, "ndcg_at_10": 0.82475, "ndcg_at_20": 0.82906, "ndcg_at_100": 0.83691, "ndcg_at_1000": 0.83975, "map_at_1": 0.732, "map_at_3": 0.77933, "map_at_5": 0.79023, "map_at_10": 0.79487, "map_at_20": 0.79593, "map_at_100": 0.79706, "map_at_1000": 0.79717, "recall_at_1": 0.732, "recall_at_3": 0.836, "recall_at_5": 0.884, "recall_at_10": 0.918, "recall_at_20": 0.936, "recall_at_100": 0.978, "recall_at_1000": 1.0, "precision_at_1": 0.732, "precision_at_3": 0.27867, "precision_at_5": 0.1768, "precision_at_10": 0.0918, "precision_at_20": 0.0468, "precision_at_100": 0.00978, "precision_at_1000": 0.001, "mrr_at_1": 0.732, "mrr_at_3": 0.7786666666666665, "mrr_at_5": 0.7900666666666664, "mrr_at_10": 0.794449206349206, "mrr_at_20": 0.7953232247284874, "mrr_at_100": 0.7966255910510839, "mrr_at_1000": 0.7967190443508116, "naucs_at_1_max": 0.4347700535605503, "naucs_at_1_std": 0.0052057373871626685, "naucs_at_1_diff1": 0.865643715535724, "naucs_at_3_max": 0.6048031004775511, "naucs_at_3_std": 0.15614576084087275, "naucs_at_3_diff1": 0.8398166590674573, "naucs_at_5_max": 0.5930604282107613, "naucs_at_5_std": 0.1861700383619125, "naucs_at_5_diff1": 0.7956080527230405, "naucs_at_10_max": 0.6479242103345397, "naucs_at_10_std": 0.25604062763316404, "naucs_at_10_diff1": 0.7970326341918881, "naucs_at_20_max": 0.6982668067226916, "naucs_at_20_std": 0.40970763305321833, "naucs_at_20_diff1": 0.7613941409897302, "naucs_at_100_max": 0.9762329174093898, "naucs_at_100_std": 0.8936847466259251, "naucs_at_100_diff1": 0.80561921738392, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "docvqa_subsampled": {"ndcg_at_1": 0.458, "ndcg_at_3": 0.5249, "ndcg_at_5": 0.54987, "ndcg_at_10": 0.5691, "ndcg_at_20": 0.58534, "ndcg_at_100": 0.60898, "ndcg_at_1000": 0.62315, "map_at_1": 0.458, "map_at_3": 0.508, "map_at_5": 0.522, "map_at_10": 0.52983, "map_at_20": 0.53432, "map_at_100": 0.53744, "map_at_1000": 0.53795, "recall_at_1": 0.458, "recall_at_3": 0.574, "recall_at_5": 0.634, "recall_at_10": 0.694, "recall_at_20": 0.758, "recall_at_100": 0.888, "recall_at_1000": 1.0, "precision_at_1": 0.458, "precision_at_3": 0.19133, "precision_at_5": 0.1268, "precision_at_10": 0.0694, "precision_at_20": 0.0379, "precision_at_100": 0.00888, "precision_at_1000": 0.001, "mrr_at_1": 0.462, "mrr_at_3": 0.5103333333333334, "mrr_at_5": 0.5240333333333334, "mrr_at_10": 0.5330150793650792, "mrr_at_20": 0.5363530102594342, "mrr_at_100": 0.5398099695126392, "mrr_at_1000": 0.540360971784682, "naucs_at_1_max": 0.14478705160292352, "naucs_at_1_std": 0.3721140942241178, "naucs_at_1_diff1": 0.8556357724943732, "naucs_at_3_max": 0.0955052454658937, "naucs_at_3_std": 0.4342882512519065, "naucs_at_3_diff1": 0.7991501163256658, "naucs_at_5_max": 0.01343769437454414, "naucs_at_5_std": 0.48670912254002735, "naucs_at_5_diff1": 0.7732231206645599, "naucs_at_10_max": -0.024673527538943748, "naucs_at_10_std": 0.5356353895792051, "naucs_at_10_diff1": 0.7689667071014644, "naucs_at_20_max": -0.12562798953100113, "naucs_at_20_std": 0.5620597626854955, "naucs_at_20_diff1": 0.7722820785003025, "naucs_at_100_max": -0.23859408820346314, "naucs_at_100_std": 0.864870806277056, "naucs_at_100_diff1": 0.7339945211038957, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "arxivqa_subsampled": {"ndcg_at_1": 0.712, "ndcg_at_3": 0.76712, "ndcg_at_5": 0.78364, "ndcg_at_10": 0.80123, "ndcg_at_20": 0.812, "ndcg_at_100": 0.81995, "ndcg_at_1000": 0.82209, "map_at_1": 0.712, "map_at_3": 0.75367, "map_at_5": 0.76287, "map_at_10": 0.77019, "map_at_20": 0.77323, "map_at_100": 0.7744, "map_at_1000": 0.77449, "recall_at_1": 0.712, "recall_at_3": 0.806, "recall_at_5": 0.846, "recall_at_10": 0.9, "recall_at_20": 0.942, "recall_at_100": 0.984, "recall_at_1000": 1.0, "precision_at_1": 0.712, "precision_at_3": 0.26867, "precision_at_5": 0.1692, "precision_at_10": 0.09, "precision_at_20": 0.0471, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.724, "mrr_at_3": 0.7626666666666667, "mrr_at_5": 0.7716666666666666, "mrr_at_10": 0.7785738095238096, "mrr_at_20": 0.7814459001782531, "mrr_at_100": 0.7824821791237915, "mrr_at_1000": 0.7825927236311448, "naucs_at_1_max": 0.5179261037469994, "naucs_at_1_std": 0.0715515827456125, "naucs_at_1_diff1": 0.8994028359700004, "naucs_at_3_max": 0.5866330274286543, "naucs_at_3_std": 0.15098605444623744, "naucs_at_3_diff1": 0.8370723586175715, "naucs_at_5_max": 0.6037655521242381, "naucs_at_5_std": 0.16178021782505292, "naucs_at_5_diff1": 0.8241259674406191, "naucs_at_10_max": 0.5842483660130722, "naucs_at_10_std": 0.20487394957983113, "naucs_at_10_diff1": 0.7742016806722692, "naucs_at_20_max": 0.735455101580865, "naucs_at_20_std": 0.3710035738433312, "naucs_at_20_diff1": 0.7694871051869058, "naucs_at_100_max": 0.8503151260504297, "naucs_at_100_std": 0.5717787114846009, "naucs_at_100_diff1": 0.8129668534080331, "naucs_at_1000_max": 1.0, "naucs_at_1000_std": 1.0, "naucs_at_1000_diff1": 1.0}, "tabfquad_subsampled": {"ndcg_at_1": 0.76429, "ndcg_at_3": 0.83078, "ndcg_at_5": 0.84353, "ndcg_at_10": 0.85388, "ndcg_at_20": 0.86455, "ndcg_at_100": 0.86741, "ndcg_at_1000": 0.86741, "map_at_1": 0.76429, "map_at_3": 0.81429, "map_at_5": 0.82107, "map_at_10": 0.82532, "map_at_20": 0.82817, "map_at_100": 0.82864, "map_at_1000": 0.82864, "recall_at_1": 0.76429, "recall_at_3": 0.87857, "recall_at_5": 0.91071, "recall_at_10": 0.94286, "recall_at_20": 0.98571, "recall_at_100": 1.0, "recall_at_1000": 1.0, "precision_at_1": 0.76429, "precision_at_3": 0.29286, "precision_at_5": 0.18214, "precision_at_10": 0.09429, "precision_at_20": 0.04929, "precision_at_100": 0.01, "precision_at_1000": 0.001, "mrr_at_1": 0.7571428571428571, "mrr_at_3": 0.8095238095238096, "mrr_at_5": 0.8179166666666666, "mrr_at_10": 0.8214625850340135, "mrr_at_20": 0.8241040305215449, "mrr_at_100": 0.8247231380884232, "mrr_at_1000": 0.8247231380884232, "naucs_at_1_max": 0.4032387013842082, "naucs_at_1_std": 0.20721575143829152, "naucs_at_1_diff1": 0.8371243592356286, "naucs_at_3_max": 0.37018609096531074, "naucs_at_3_std": 0.19961207623545132, "naucs_at_3_diff1": 0.7850677461067068, "naucs_at_5_max": 0.49086834733893503, "naucs_at_5_std": 0.26750700280112155, "naucs_at_5_diff1": 0.7712791783380023, "naucs_at_10_max": 0.5342845471521948, "naucs_at_10_std": 0.382148692810459, "naucs_at_10_diff1": 0.7389122315592906, "naucs_at_20_max": 0.42938842203549277, "naucs_at_20_std": 0.5764472455649069, "naucs_at_20_diff1": 0.8978758169934754, "naucs_at_100_max": 1.0, "naucs_at_100_std": 1.0, "naucs_at_100_diff1": 1.0, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "tatdqa": {"ndcg_at_1": 0.51714, "ndcg_at_3": 0.63347, "ndcg_at_5": 0.65997, "ndcg_at_10": 0.68432, "ndcg_at_20": 0.69776, "ndcg_at_100": 0.71265, "ndcg_at_1000": 0.7148, "map_at_1": 0.51714, "map_at_3": 0.60543, "map_at_5": 0.62013, "map_at_10": 0.63032, "map_at_20": 0.63413, "map_at_100": 0.63629, "map_at_1000": 0.63639, "recall_at_1": 0.51714, "recall_at_3": 0.71437, "recall_at_5": 0.77871, "recall_at_10": 0.85328, "recall_at_20": 0.90559, "recall_at_100": 0.98437, "recall_at_1000": 1.0, "precision_at_1": 0.51714, "precision_at_3": 0.23812, "precision_at_5": 0.15574, "precision_at_10": 0.08533, "precision_at_20": 0.04528, "precision_at_100": 0.00984, "precision_at_1000": 0.001, "mrr_at_1": 0.5189416716776909, "mrr_at_3": 0.6063339346562444, "mrr_at_5": 0.6203447584686321, "mrr_at_10": 0.6304701295230465, "mrr_at_20": 0.6343502614596628, "mrr_at_100": 0.6366034259317307, "mrr_at_1000": 0.6366958159270893, "naucs_at_1_max": 0.16652309459558007, "naucs_at_1_std": -0.06670433006927416, "naucs_at_1_diff1": 0.6953792910740597, "naucs_at_3_max": 0.16902492509679246, "naucs_at_3_std": -0.03701362337519723, "naucs_at_3_diff1": 0.5494053126321319, "naucs_at_5_max": 0.21105315084874532, "naucs_at_5_std": 0.04611791703673267, "naucs_at_5_diff1": 0.5162174552139975, "naucs_at_10_max": 0.23091913809374726, "naucs_at_10_std": 0.10830125135311366, "naucs_at_10_diff1": 0.4866871626269709, "naucs_at_20_max": 0.2725948129883982, "naucs_at_20_std": 0.24954038307560938, "naucs_at_20_diff1": 0.4588931923467883, "naucs_at_100_max": 0.6502319824989845, "naucs_at_100_std": 0.6011619544721175, "naucs_at_100_diff1": 0.7480994634253559, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}, "shift_project": {"ndcg_at_1": 0.56, "ndcg_at_3": 0.70095, "ndcg_at_5": 0.72934, "ndcg_at_10": 0.74318, "ndcg_at_20": 0.7537, "ndcg_at_100": 0.75912, "ndcg_at_1000": 0.76194, "map_at_1": 0.56, "map_at_3": 0.66667, "map_at_5": 0.68217, "map_at_10": 0.68842, "map_at_20": 0.69152, "map_at_100": 0.69222, "map_at_1000": 0.69237, "recall_at_1": 0.56, "recall_at_3": 0.8, "recall_at_5": 0.87, "recall_at_10": 0.91, "recall_at_20": 0.95, "recall_at_100": 0.98, "recall_at_1000": 1.0, "precision_at_1": 0.56, "precision_at_3": 0.26667, "precision_at_5": 0.174, "precision_at_10": 0.091, "precision_at_20": 0.0475, "precision_at_100": 0.0098, "precision_at_1000": 0.001, "mrr_at_1": 0.59, "mrr_at_3": 0.69, "mrr_at_5": 0.7055, "mrr_at_10": 0.7100833333333334, "mrr_at_20": 0.7131832236391059, "mrr_at_100": 0.7139141492175927, "mrr_at_1000": 0.7140687525760177, "naucs_at_1_max": -0.06823472632296203, "naucs_at_1_std": -0.21851578469225566, "naucs_at_1_diff1": 0.6402168975698381, "naucs_at_3_max": -0.5083416583416578, "naucs_at_3_std": -0.719330669330669, "naucs_at_3_diff1": 0.49285714285714205, "naucs_at_5_max": -0.40505813522920514, "naucs_at_5_std": -0.5592460934607096, "naucs_at_5_diff1": 0.3987632377990074, "naucs_at_10_max": -0.4162776221599734, "naucs_at_10_std": -0.47852474323062383, "naucs_at_10_diff1": 0.4046062869592272, "naucs_at_20_max": -0.5808590102707625, "naucs_at_20_std": -0.5164332399626398, "naucs_at_20_diff1": 0.4697478991596656, "naucs_at_100_max": -1.4458450046685247, "naucs_at_100_std": -1.4458450046685247, "naucs_at_100_diff1": 0.6790382819794637, "naucs_at_1000_max": NaN, "naucs_at_1000_std": NaN, "naucs_at_1000_diff1": NaN}}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<image>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<bos>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<eos>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": {
|
| 26 |
+
"content": "<pad>",
|
| 27 |
+
"lstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"single_word": false
|
| 31 |
+
},
|
| 32 |
+
"unk_token": {
|
| 33 |
+
"content": "<unk>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
}
|
| 39 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ffd310e50986db7a039948ab83441d612689e7f989198e31b5c8984ca458adf6
|
| 3 |
+
size 17763459
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
training_config.yml
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
config:
|
| 2 |
+
(): colpali_engine.utils.train_colpali_engine_models.ColModelTrainingConfig
|
| 3 |
+
output_dir: !path ../../../models/right_pad/train_colpali-3b-mix-448
|
| 4 |
+
processor:
|
| 5 |
+
() : colpali_engine.utils.wrapper.AutoProcessorWrapper
|
| 6 |
+
pretrained_model_name_or_path: "./models/colpaligemma-3b-mix-448-base" # "./models/paligemma-3b-mix-448"
|
| 7 |
+
max_length: 50
|
| 8 |
+
model:
|
| 9 |
+
(): colpali_engine.utils.wrapper.AllPurposeWrapper
|
| 10 |
+
class_to_instanciate: !ext colpali_engine.models.paligemma_colbert_architecture.ColPali
|
| 11 |
+
pretrained_model_name_or_path: "./models/colpaligemma-3b-mix-448-base"
|
| 12 |
+
torch_dtype: !ext torch.bfloat16
|
| 13 |
+
# device_map: "auto"
|
| 14 |
+
# quantization_config:
|
| 15 |
+
# (): transformers.BitsAndBytesConfig
|
| 16 |
+
# load_in_4bit: true
|
| 17 |
+
# bnb_4bit_quant_type: "nf4"
|
| 18 |
+
# bnb_4bit_compute_dtype: "bfloat16"
|
| 19 |
+
# bnb_4bit_use_double_quant: true
|
| 20 |
+
|
| 21 |
+
dataset_loading_func: !ext colpali_engine.utils.dataset_transformation.load_train_set
|
| 22 |
+
eval_dataset_loader: !import ../data/test_data.yaml
|
| 23 |
+
|
| 24 |
+
max_length: 50
|
| 25 |
+
run_eval: true
|
| 26 |
+
add_suffix: true
|
| 27 |
+
loss_func:
|
| 28 |
+
(): colpali_engine.loss.colbert_loss.ColbertPairwiseCELoss
|
| 29 |
+
tr_args: !import ../tr_args/default_tr_args.yaml
|
| 30 |
+
peft_config:
|
| 31 |
+
(): peft.LoraConfig
|
| 32 |
+
r: 32
|
| 33 |
+
lora_alpha: 32
|
| 34 |
+
lora_dropout: 0.1
|
| 35 |
+
init_lora_weights: "gaussian"
|
| 36 |
+
bias: "none"
|
| 37 |
+
task_type: "FEATURE_EXTRACTION"
|
| 38 |
+
target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
| 39 |
+
# target_modules: '(.*(language_model).*(down_proj|gate_proj|up_proj|k_proj|q_proj|v_proj|o_proj).*$|.*(custom_text_proj).*$)'
|
| 40 |
+
|