Upload Thera dialogue fine-tuned model
Browse files- .gitattributes +3 -0
- README.md +4 -4
- Thera-adapters/adapter_config.json +46 -0
- Thera-adapters/adapter_model.safetensors +3 -0
- Thera-adapters/loss_plots.png +3 -0
- Thera-adapters/training_args.bin +3 -0
- Thera-adapters/training_history.json +843 -0
- checkpoint-405/README.md +209 -0
- checkpoint-405/adapter_config.json +46 -0
- checkpoint-405/adapter_model.safetensors +3 -0
- checkpoint-405/added_tokens.json +28 -0
- checkpoint-405/chat_template.jinja +89 -0
- checkpoint-405/merges.txt +0 -0
- checkpoint-405/optimizer.pt +3 -0
- checkpoint-405/rng_state.pth +3 -0
- checkpoint-405/scheduler.pt +3 -0
- checkpoint-405/special_tokens_map.json +31 -0
- checkpoint-405/tokenizer.json +3 -0
- checkpoint-405/tokenizer_config.json +239 -0
- checkpoint-405/trainer_state.json +445 -0
- checkpoint-405/training_args.bin +3 -0
- checkpoint-405/vocab.json +0 -0
- checkpoint-810/README.md +209 -0
- checkpoint-810/adapter_config.json +46 -0
- checkpoint-810/adapter_model.safetensors +3 -0
- checkpoint-810/added_tokens.json +28 -0
- checkpoint-810/chat_template.jinja +89 -0
- checkpoint-810/merges.txt +0 -0
- checkpoint-810/optimizer.pt +3 -0
- checkpoint-810/rng_state.pth +3 -0
- checkpoint-810/scheduler.pt +3 -0
- checkpoint-810/special_tokens_map.json +31 -0
- checkpoint-810/tokenizer.json +3 -0
- checkpoint-810/tokenizer_config.json +239 -0
- checkpoint-810/trainer_state.json +866 -0
- checkpoint-810/training_args.bin +3 -0
- checkpoint-810/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,6 @@ saved_model/**/* 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
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
| 37 |
+
Thera-adapters/loss_plots.png filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
checkpoint-405/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
checkpoint-810/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-4B
|
| 3 |
library_name: peft
|
| 4 |
-
model_name:
|
| 5 |
tags:
|
| 6 |
- base_model:adapter:Qwen/Qwen3-4B
|
| 7 |
- lora
|
|
@@ -12,7 +12,7 @@ licence: license
|
|
| 12 |
pipeline_tag: text-generation
|
| 13 |
---
|
| 14 |
|
| 15 |
-
# Model Card for
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B).
|
| 18 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
@@ -38,8 +38,8 @@ This model was trained with SFT.
|
|
| 38 |
### Framework versions
|
| 39 |
|
| 40 |
- PEFT 0.18.0
|
| 41 |
-
- TRL: 0.
|
| 42 |
-
- Transformers: 4.57.
|
| 43 |
- Pytorch: 2.9.0+cu126
|
| 44 |
- Datasets: 4.0.0
|
| 45 |
- Tokenizers: 0.22.1
|
|
|
|
| 1 |
---
|
| 2 |
base_model: Qwen/Qwen3-4B
|
| 3 |
library_name: peft
|
| 4 |
+
model_name: Thera-qwen-finetuned
|
| 5 |
tags:
|
| 6 |
- base_model:adapter:Qwen/Qwen3-4B
|
| 7 |
- lora
|
|
|
|
| 12 |
pipeline_tag: text-generation
|
| 13 |
---
|
| 14 |
|
| 15 |
+
# Model Card for Thera-qwen-finetuned
|
| 16 |
|
| 17 |
This model is a fine-tuned version of [Qwen/Qwen3-4B](https://huggingface.co/Qwen/Qwen3-4B).
|
| 18 |
It has been trained using [TRL](https://github.com/huggingface/trl).
|
|
|
|
| 38 |
### Framework versions
|
| 39 |
|
| 40 |
- PEFT 0.18.0
|
| 41 |
+
- TRL: 0.26.0
|
| 42 |
+
- Transformers: 4.57.3
|
| 43 |
- Pytorch: 2.9.0+cu126
|
| 44 |
- Datasets: 4.0.0
|
| 45 |
- Tokenizers: 0.22.1
|
Thera-adapters/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-4B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 64,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"gate_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
Thera-adapters/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee9a1c85427ea72b1cf64eb53727331a8834b098a399a8d3b5ac16a6539e898c
|
| 3 |
+
size 528550256
|
Thera-adapters/loss_plots.png
ADDED
|
Git LFS Details
|
Thera-adapters/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:602933e14cee181956b6ba86efd1c972acb28b64c16c9da71ac0844bc4a294d9
|
| 3 |
+
size 6225
|
Thera-adapters/training_history.json
ADDED
|
@@ -0,0 +1,843 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"loss": 3.5346,
|
| 4 |
+
"grad_norm": 2.9517738819122314,
|
| 5 |
+
"learning_rate": 5.555555555555555e-05,
|
| 6 |
+
"entropy": 1.6250975668430327,
|
| 7 |
+
"num_tokens": 5217.0,
|
| 8 |
+
"mean_token_accuracy": 0.4640115313231945,
|
| 9 |
+
"epoch": 0.024737167594310452,
|
| 10 |
+
"step": 10
|
| 11 |
+
},
|
| 12 |
+
{
|
| 13 |
+
"loss": 1.151,
|
| 14 |
+
"grad_norm": 1.3123714923858643,
|
| 15 |
+
"learning_rate": 0.00011728395061728394,
|
| 16 |
+
"entropy": 1.2365971699357032,
|
| 17 |
+
"num_tokens": 10339.0,
|
| 18 |
+
"mean_token_accuracy": 0.7842043608427047,
|
| 19 |
+
"epoch": 0.049474335188620905,
|
| 20 |
+
"step": 20
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"loss": 0.7884,
|
| 24 |
+
"grad_norm": 1.1022770404815674,
|
| 25 |
+
"learning_rate": 0.00017901234567901234,
|
| 26 |
+
"entropy": 0.8006420895457268,
|
| 27 |
+
"num_tokens": 15466.0,
|
| 28 |
+
"mean_token_accuracy": 0.8256171777844429,
|
| 29 |
+
"epoch": 0.07421150278293136,
|
| 30 |
+
"step": 30
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"loss": 0.8226,
|
| 34 |
+
"grad_norm": 0.6970203518867493,
|
| 35 |
+
"learning_rate": 0.00024074074074074072,
|
| 36 |
+
"entropy": 0.7944120116531849,
|
| 37 |
+
"num_tokens": 20751.0,
|
| 38 |
+
"mean_token_accuracy": 0.8202412217855454,
|
| 39 |
+
"epoch": 0.09894867037724181,
|
| 40 |
+
"step": 40
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"loss": 0.7494,
|
| 44 |
+
"grad_norm": 0.8590984344482422,
|
| 45 |
+
"learning_rate": 0.00030246913580246913,
|
| 46 |
+
"entropy": 0.7060609392821788,
|
| 47 |
+
"num_tokens": 25959.0,
|
| 48 |
+
"mean_token_accuracy": 0.8315540343523026,
|
| 49 |
+
"epoch": 0.12368583797155226,
|
| 50 |
+
"step": 50
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"loss": 0.7744,
|
| 54 |
+
"grad_norm": 0.7957938313484192,
|
| 55 |
+
"learning_rate": 0.00036419753086419757,
|
| 56 |
+
"entropy": 0.7671719007194042,
|
| 57 |
+
"num_tokens": 31167.0,
|
| 58 |
+
"mean_token_accuracy": 0.8240246027708054,
|
| 59 |
+
"epoch": 0.14842300556586271,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"loss": 0.7366,
|
| 64 |
+
"grad_norm": 0.8324401378631592,
|
| 65 |
+
"learning_rate": 0.00042592592592592595,
|
| 66 |
+
"entropy": 0.7414519913494587,
|
| 67 |
+
"num_tokens": 36361.0,
|
| 68 |
+
"mean_token_accuracy": 0.8289650768041611,
|
| 69 |
+
"epoch": 0.17316017316017315,
|
| 70 |
+
"step": 70
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"loss": 0.7674,
|
| 74 |
+
"grad_norm": 0.7674175500869751,
|
| 75 |
+
"learning_rate": 0.00048765432098765433,
|
| 76 |
+
"entropy": 0.7403566606342793,
|
| 77 |
+
"num_tokens": 41652.0,
|
| 78 |
+
"mean_token_accuracy": 0.8263674512505531,
|
| 79 |
+
"epoch": 0.19789734075448362,
|
| 80 |
+
"step": 80
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"loss": 0.7769,
|
| 84 |
+
"grad_norm": 0.8532105088233948,
|
| 85 |
+
"learning_rate": 0.0004998514434997615,
|
| 86 |
+
"entropy": 0.7672358199954032,
|
| 87 |
+
"num_tokens": 46935.0,
|
| 88 |
+
"mean_token_accuracy": 0.8204340368509293,
|
| 89 |
+
"epoch": 0.22263450834879406,
|
| 90 |
+
"step": 90
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"loss": 0.759,
|
| 94 |
+
"grad_norm": 0.7918670773506165,
|
| 95 |
+
"learning_rate": 0.000499248235291948,
|
| 96 |
+
"entropy": 0.7317010335624218,
|
| 97 |
+
"num_tokens": 52141.0,
|
| 98 |
+
"mean_token_accuracy": 0.82643341422081,
|
| 99 |
+
"epoch": 0.24737167594310452,
|
| 100 |
+
"step": 100
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"loss": 0.7792,
|
| 104 |
+
"grad_norm": 0.9036818146705627,
|
| 105 |
+
"learning_rate": 0.0004981822098019347,
|
| 106 |
+
"entropy": 0.7418206945061684,
|
| 107 |
+
"num_tokens": 57323.0,
|
| 108 |
+
"mean_token_accuracy": 0.8211499944329261,
|
| 109 |
+
"epoch": 0.272108843537415,
|
| 110 |
+
"step": 110
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"loss": 0.8088,
|
| 114 |
+
"grad_norm": 0.9364569783210754,
|
| 115 |
+
"learning_rate": 0.0004966553464821318,
|
| 116 |
+
"entropy": 0.788830752670765,
|
| 117 |
+
"num_tokens": 62559.0,
|
| 118 |
+
"mean_token_accuracy": 0.8202816650271416,
|
| 119 |
+
"epoch": 0.29684601113172543,
|
| 120 |
+
"step": 120
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"loss": 0.8429,
|
| 124 |
+
"grad_norm": 0.849193274974823,
|
| 125 |
+
"learning_rate": 0.0004946704804929611,
|
| 126 |
+
"entropy": 0.8334563881158829,
|
| 127 |
+
"num_tokens": 67796.0,
|
| 128 |
+
"mean_token_accuracy": 0.8172205120325089,
|
| 129 |
+
"epoch": 0.32158317872603587,
|
| 130 |
+
"step": 130
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"loss": 0.8252,
|
| 134 |
+
"grad_norm": 0.8545674085617065,
|
| 135 |
+
"learning_rate": 0.0004922312974383811,
|
| 136 |
+
"entropy": 0.819231541454792,
|
| 137 |
+
"num_tokens": 73053.0,
|
| 138 |
+
"mean_token_accuracy": 0.8214908227324486,
|
| 139 |
+
"epoch": 0.3463203463203463,
|
| 140 |
+
"step": 140
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"loss": 0.833,
|
| 144 |
+
"grad_norm": 0.8818181157112122,
|
| 145 |
+
"learning_rate": 0.0004893423265222629,
|
| 146 |
+
"entropy": 0.8317434027791023,
|
| 147 |
+
"num_tokens": 78244.0,
|
| 148 |
+
"mean_token_accuracy": 0.818103215098381,
|
| 149 |
+
"epoch": 0.37105751391465674,
|
| 150 |
+
"step": 150
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"loss": 0.8259,
|
| 154 |
+
"grad_norm": 2.9915354251861572,
|
| 155 |
+
"learning_rate": 0.000486008932138325,
|
| 156 |
+
"entropy": 0.8188002541661262,
|
| 157 |
+
"num_tokens": 83400.0,
|
| 158 |
+
"mean_token_accuracy": 0.8210815489292145,
|
| 159 |
+
"epoch": 0.39579468150896724,
|
| 160 |
+
"step": 160
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"loss": 0.848,
|
| 164 |
+
"grad_norm": 1.1181414127349854,
|
| 165 |
+
"learning_rate": 0.0004822373039092439,
|
| 166 |
+
"entropy": 0.8377857849001884,
|
| 167 |
+
"num_tokens": 88646.0,
|
| 168 |
+
"mean_token_accuracy": 0.8190183833241462,
|
| 169 |
+
"epoch": 0.4205318491032777,
|
| 170 |
+
"step": 170
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"loss": 0.8064,
|
| 174 |
+
"grad_norm": 3.424036979675293,
|
| 175 |
+
"learning_rate": 0.0004780344451934363,
|
| 176 |
+
"entropy": 0.8113411583006382,
|
| 177 |
+
"num_tokens": 93860.0,
|
| 178 |
+
"mean_token_accuracy": 0.8218150183558464,
|
| 179 |
+
"epoch": 0.4452690166975881,
|
| 180 |
+
"step": 180
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"loss": 0.9719,
|
| 184 |
+
"grad_norm": 1.6186113357543945,
|
| 185 |
+
"learning_rate": 0.00047340816008085306,
|
| 186 |
+
"entropy": 0.8306475475430488,
|
| 187 |
+
"num_tokens": 99115.0,
|
| 188 |
+
"mean_token_accuracy": 0.7976664826273918,
|
| 189 |
+
"epoch": 0.47000618429189855,
|
| 190 |
+
"step": 190
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"loss": 0.8337,
|
| 194 |
+
"grad_norm": 0.9495635628700256,
|
| 195 |
+
"learning_rate": 0.00046836703890193313,
|
| 196 |
+
"entropy": 0.8320877499878406,
|
| 197 |
+
"num_tokens": 104288.0,
|
| 198 |
+
"mean_token_accuracy": 0.8249012738466263,
|
| 199 |
+
"epoch": 0.49474335188620905,
|
| 200 |
+
"step": 200
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"loss": 0.8317,
|
| 204 |
+
"grad_norm": 0.9904643297195435,
|
| 205 |
+
"learning_rate": 0.0004629204422766245,
|
| 206 |
+
"entropy": 0.8043741077184677,
|
| 207 |
+
"num_tokens": 109502.0,
|
| 208 |
+
"mean_token_accuracy": 0.8221358329057693,
|
| 209 |
+
"epoch": 0.5194805194805194,
|
| 210 |
+
"step": 210
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"loss": 0.865,
|
| 214 |
+
"grad_norm": 1.3911291360855103,
|
| 215 |
+
"learning_rate": 0.0004570784837330908,
|
| 216 |
+
"entropy": 0.8280141688883305,
|
| 217 |
+
"num_tokens": 114746.0,
|
| 218 |
+
"mean_token_accuracy": 0.8145962327718734,
|
| 219 |
+
"epoch": 0.54421768707483,
|
| 220 |
+
"step": 220
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"loss": 0.8203,
|
| 224 |
+
"grad_norm": 1.1356682777404785,
|
| 225 |
+
"learning_rate": 0.0004508520109283782,
|
| 226 |
+
"entropy": 0.7979148738086224,
|
| 227 |
+
"num_tokens": 119935.0,
|
| 228 |
+
"mean_token_accuracy": 0.8190253749489784,
|
| 229 |
+
"epoch": 0.5689548546691404,
|
| 230 |
+
"step": 230
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"loss": 0.856,
|
| 234 |
+
"grad_norm": 1.006868839263916,
|
| 235 |
+
"learning_rate": 0.0004442525855059136,
|
| 236 |
+
"entropy": 0.7733577877283097,
|
| 237 |
+
"num_tokens": 125174.0,
|
| 238 |
+
"mean_token_accuracy": 0.815259476006031,
|
| 239 |
+
"epoch": 0.5936920222634509,
|
| 240 |
+
"step": 240
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"loss": 0.7808,
|
| 244 |
+
"grad_norm": 0.9585395455360413,
|
| 245 |
+
"learning_rate": 0.00043729246162723404,
|
| 246 |
+
"entropy": 0.762465487420559,
|
| 247 |
+
"num_tokens": 130346.0,
|
| 248 |
+
"mean_token_accuracy": 0.8212951749563218,
|
| 249 |
+
"epoch": 0.6184291898577613,
|
| 250 |
+
"step": 250
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"loss": 0.9951,
|
| 254 |
+
"grad_norm": 0.8783559203147888,
|
| 255 |
+
"learning_rate": 0.00042998456321781284,
|
| 256 |
+
"entropy": 0.888411459326744,
|
| 257 |
+
"num_tokens": 135467.0,
|
| 258 |
+
"mean_token_accuracy": 0.8052207484841347,
|
| 259 |
+
"epoch": 0.6431663574520717,
|
| 260 |
+
"step": 260
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"loss": 0.8121,
|
| 264 |
+
"grad_norm": 0.9991810321807861,
|
| 265 |
+
"learning_rate": 0.0004223424599692327,
|
| 266 |
+
"entropy": 0.7948930785059929,
|
| 267 |
+
"num_tokens": 140671.0,
|
| 268 |
+
"mean_token_accuracy": 0.8190833777189255,
|
| 269 |
+
"epoch": 0.6679035250463822,
|
| 270 |
+
"step": 270
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"loss": 0.8352,
|
| 274 |
+
"grad_norm": 1.0719568729400635,
|
| 275 |
+
"learning_rate": 0.00041438034214226596,
|
| 276 |
+
"entropy": 0.8159038618206977,
|
| 277 |
+
"num_tokens": 145888.0,
|
| 278 |
+
"mean_token_accuracy": 0.8190872147679329,
|
| 279 |
+
"epoch": 0.6926406926406926,
|
| 280 |
+
"step": 280
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"loss": 0.8616,
|
| 284 |
+
"grad_norm": 0.9456169009208679,
|
| 285 |
+
"learning_rate": 0.0004061129942176487,
|
| 286 |
+
"entropy": 0.8683171272277832,
|
| 287 |
+
"num_tokens": 151125.0,
|
| 288 |
+
"mean_token_accuracy": 0.8180570781230927,
|
| 289 |
+
"epoch": 0.717377860235003,
|
| 290 |
+
"step": 290
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"loss": 0.8035,
|
| 294 |
+
"grad_norm": 0.8249353170394897,
|
| 295 |
+
"learning_rate": 0.0003975557674434772,
|
| 296 |
+
"entropy": 0.7405934803187847,
|
| 297 |
+
"num_tokens": 156230.0,
|
| 298 |
+
"mean_token_accuracy": 0.8308369800448417,
|
| 299 |
+
"epoch": 0.7421150278293135,
|
| 300 |
+
"step": 300
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"loss": 0.8651,
|
| 304 |
+
"grad_norm": 1.1419930458068848,
|
| 305 |
+
"learning_rate": 0.00038872455133019923,
|
| 306 |
+
"entropy": 0.8380466908216476,
|
| 307 |
+
"num_tokens": 161487.0,
|
| 308 |
+
"mean_token_accuracy": 0.8131552562117577,
|
| 309 |
+
"epoch": 0.766852195423624,
|
| 310 |
+
"step": 310
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"loss": 0.8528,
|
| 314 |
+
"grad_norm": 1.124142050743103,
|
| 315 |
+
"learning_rate": 0.00037963574414613265,
|
| 316 |
+
"entropy": 0.8332376055419445,
|
| 317 |
+
"num_tokens": 166771.0,
|
| 318 |
+
"mean_token_accuracy": 0.8137879073619843,
|
| 319 |
+
"epoch": 0.7915893630179345,
|
| 320 |
+
"step": 320
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"loss": 0.7916,
|
| 324 |
+
"grad_norm": 1.3924378156661987,
|
| 325 |
+
"learning_rate": 0.00037030622246829486,
|
| 326 |
+
"entropy": 0.7901938475668431,
|
| 327 |
+
"num_tokens": 171893.0,
|
| 328 |
+
"mean_token_accuracy": 0.8227489620447159,
|
| 329 |
+
"epoch": 0.8163265306122449,
|
| 330 |
+
"step": 330
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"loss": 0.8336,
|
| 334 |
+
"grad_norm": 2.675826072692871,
|
| 335 |
+
"learning_rate": 0.0003607533098450838,
|
| 336 |
+
"entropy": 0.8100152090191841,
|
| 337 |
+
"num_tokens": 177077.0,
|
| 338 |
+
"mean_token_accuracy": 0.8140658468008042,
|
| 339 |
+
"epoch": 0.8410636982065554,
|
| 340 |
+
"step": 340
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"loss": 0.7847,
|
| 344 |
+
"grad_norm": 0.9445605874061584,
|
| 345 |
+
"learning_rate": 0.0003509947446289984,
|
| 346 |
+
"entropy": 0.7574406780302525,
|
| 347 |
+
"num_tokens": 182234.0,
|
| 348 |
+
"mean_token_accuracy": 0.8235680922865868,
|
| 349 |
+
"epoch": 0.8658008658008658,
|
| 350 |
+
"step": 350
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"loss": 0.9156,
|
| 354 |
+
"grad_norm": 0.9632943868637085,
|
| 355 |
+
"learning_rate": 0.00034104864703912957,
|
| 356 |
+
"entropy": 0.8985893219709397,
|
| 357 |
+
"num_tokens": 187422.0,
|
| 358 |
+
"mean_token_accuracy": 0.8068240508437157,
|
| 359 |
+
"epoch": 0.8905380333951762,
|
| 360 |
+
"step": 360
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"loss": 0.7905,
|
| 364 |
+
"grad_norm": 0.8351237773895264,
|
| 365 |
+
"learning_rate": 0.0003309334855145803,
|
| 366 |
+
"entropy": 0.7982684150338173,
|
| 367 |
+
"num_tokens": 192626.0,
|
| 368 |
+
"mean_token_accuracy": 0.8268924236297608,
|
| 369 |
+
"epoch": 0.9152752009894867,
|
| 370 |
+
"step": 370
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"loss": 0.8186,
|
| 374 |
+
"grad_norm": 0.8712763786315918,
|
| 375 |
+
"learning_rate": 0.0003206680424212931,
|
| 376 |
+
"entropy": 0.7881800249218941,
|
| 377 |
+
"num_tokens": 197838.0,
|
| 378 |
+
"mean_token_accuracy": 0.8173615485429764,
|
| 379 |
+
"epoch": 0.9400123685837971,
|
| 380 |
+
"step": 380
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"loss": 0.7988,
|
| 384 |
+
"grad_norm": 0.7793152332305908,
|
| 385 |
+
"learning_rate": 0.0003102713791759616,
|
| 386 |
+
"entropy": 0.744848319888115,
|
| 387 |
+
"num_tokens": 203044.0,
|
| 388 |
+
"mean_token_accuracy": 0.8299087509512901,
|
| 389 |
+
"epoch": 0.9647495361781077,
|
| 390 |
+
"step": 390
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"loss": 0.7642,
|
| 394 |
+
"grad_norm": 0.949001669883728,
|
| 395 |
+
"learning_rate": 0.00029976280085178514,
|
| 396 |
+
"entropy": 0.7603424042463303,
|
| 397 |
+
"num_tokens": 208194.0,
|
| 398 |
+
"mean_token_accuracy": 0.8270730227231979,
|
| 399 |
+
"epoch": 0.9894867037724181,
|
| 400 |
+
"step": 400
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"eval_loss": 0.820298433303833,
|
| 404 |
+
"eval_runtime": 125.2713,
|
| 405 |
+
"eval_samples_per_second": 1.437,
|
| 406 |
+
"eval_steps_per_second": 1.437,
|
| 407 |
+
"eval_entropy": 0.8190755642122692,
|
| 408 |
+
"eval_num_tokens": 210386.0,
|
| 409 |
+
"eval_mean_token_accuracy": 0.8219989130894343,
|
| 410 |
+
"epoch": 1.0,
|
| 411 |
+
"step": 405
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"loss": 0.6928,
|
| 415 |
+
"grad_norm": 0.914890468120575,
|
| 416 |
+
"learning_rate": 0.00028916182033179015,
|
| 417 |
+
"entropy": 0.7364253015131563,
|
| 418 |
+
"num_tokens": 213021.0,
|
| 419 |
+
"mean_token_accuracy": 0.8474441170692444,
|
| 420 |
+
"epoch": 1.0123685837971552,
|
| 421 |
+
"step": 410
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"loss": 0.4485,
|
| 425 |
+
"grad_norm": 0.9826574921607971,
|
| 426 |
+
"learning_rate": 0.00027848812207627863,
|
| 427 |
+
"entropy": 0.4017741926014423,
|
| 428 |
+
"num_tokens": 218210.0,
|
| 429 |
+
"mean_token_accuracy": 0.8861656159162521,
|
| 430 |
+
"epoch": 1.0371057513914657,
|
| 431 |
+
"step": 420
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"loss": 0.4766,
|
| 435 |
+
"grad_norm": 0.7163196802139282,
|
| 436 |
+
"learning_rate": 0.0002677615255716825,
|
| 437 |
+
"entropy": 0.47752095237374304,
|
| 438 |
+
"num_tokens": 223365.0,
|
| 439 |
+
"mean_token_accuracy": 0.8819166600704194,
|
| 440 |
+
"epoch": 1.061842918985776,
|
| 441 |
+
"step": 430
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"loss": 0.4862,
|
| 445 |
+
"grad_norm": 1.2513821125030518,
|
| 446 |
+
"learning_rate": 0.000257001948528696,
|
| 447 |
+
"entropy": 0.4802557807415724,
|
| 448 |
+
"num_tokens": 228544.0,
|
| 449 |
+
"mean_token_accuracy": 0.8789629265666008,
|
| 450 |
+
"epoch": 1.0865800865800865,
|
| 451 |
+
"step": 440
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"loss": 0.4671,
|
| 455 |
+
"grad_norm": 1.333284854888916,
|
| 456 |
+
"learning_rate": 0.0002462293698980178,
|
| 457 |
+
"entropy": 0.4388812955468893,
|
| 458 |
+
"num_tokens": 233769.0,
|
| 459 |
+
"mean_token_accuracy": 0.8901433110237121,
|
| 460 |
+
"epoch": 1.111317254174397,
|
| 461 |
+
"step": 450
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"loss": 0.4783,
|
| 465 |
+
"grad_norm": 0.8889069557189941,
|
| 466 |
+
"learning_rate": 0.00023546379277238105,
|
| 467 |
+
"entropy": 0.4832085594534874,
|
| 468 |
+
"num_tokens": 238966.0,
|
| 469 |
+
"mean_token_accuracy": 0.8810128509998322,
|
| 470 |
+
"epoch": 1.1360544217687074,
|
| 471 |
+
"step": 460
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"loss": 0.4427,
|
| 475 |
+
"grad_norm": 1.0676424503326416,
|
| 476 |
+
"learning_rate": 0.00022472520724375485,
|
| 477 |
+
"entropy": 0.4265311576426029,
|
| 478 |
+
"num_tokens": 244110.0,
|
| 479 |
+
"mean_token_accuracy": 0.8863751858472824,
|
| 480 |
+
"epoch": 1.1607915893630179,
|
| 481 |
+
"step": 470
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"loss": 0.4366,
|
| 485 |
+
"grad_norm": 0.9971004128456116,
|
| 486 |
+
"learning_rate": 0.00021403355328468576,
|
| 487 |
+
"entropy": 0.458518086373806,
|
| 488 |
+
"num_tokens": 249342.0,
|
| 489 |
+
"mean_token_accuracy": 0.8863351345062256,
|
| 490 |
+
"epoch": 1.1855287569573283,
|
| 491 |
+
"step": 480
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"loss": 0.4887,
|
| 495 |
+
"grad_norm": 0.958321213722229,
|
| 496 |
+
"learning_rate": 0.00020340868372270449,
|
| 497 |
+
"entropy": 0.46508664414286616,
|
| 498 |
+
"num_tokens": 254429.0,
|
| 499 |
+
"mean_token_accuracy": 0.8833811491727829,
|
| 500 |
+
"epoch": 1.210265924551639,
|
| 501 |
+
"step": 490
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"loss": 0.4232,
|
| 505 |
+
"grad_norm": 1.2300724983215332,
|
| 506 |
+
"learning_rate": 0.0001928703273765472,
|
| 507 |
+
"entropy": 0.46396653950214384,
|
| 508 |
+
"num_tokens": 259668.0,
|
| 509 |
+
"mean_token_accuracy": 0.8947284638881683,
|
| 510 |
+
"epoch": 1.2350030921459494,
|
| 511 |
+
"step": 500
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"loss": 0.4811,
|
| 515 |
+
"grad_norm": 1.1074163913726807,
|
| 516 |
+
"learning_rate": 0.00018243805242264366,
|
| 517 |
+
"entropy": 0.4458997011184692,
|
| 518 |
+
"num_tokens": 264767.0,
|
| 519 |
+
"mean_token_accuracy": 0.8797710970044136,
|
| 520 |
+
"epoch": 1.2597402597402598,
|
| 521 |
+
"step": 510
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"loss": 0.49,
|
| 525 |
+
"grad_norm": 0.9398917555809021,
|
| 526 |
+
"learning_rate": 0.00017213123005989383,
|
| 527 |
+
"entropy": 0.47095797434449194,
|
| 528 |
+
"num_tokens": 269891.0,
|
| 529 |
+
"mean_token_accuracy": 0.8802127614617348,
|
| 530 |
+
"epoch": 1.2844774273345703,
|
| 531 |
+
"step": 520
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"loss": 0.4029,
|
| 535 |
+
"grad_norm": 1.0138375759124756,
|
| 536 |
+
"learning_rate": 0.00016196899854020337,
|
| 537 |
+
"entropy": 0.4493381351232529,
|
| 538 |
+
"num_tokens": 275093.0,
|
| 539 |
+
"mean_token_accuracy": 0.8984167322516441,
|
| 540 |
+
"epoch": 1.3092145949288807,
|
| 541 |
+
"step": 530
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"loss": 0.4531,
|
| 545 |
+
"grad_norm": 1.2301913499832153,
|
| 546 |
+
"learning_rate": 0.000151970227631567,
|
| 547 |
+
"entropy": 0.4118185345083475,
|
| 548 |
+
"num_tokens": 280330.0,
|
| 549 |
+
"mean_token_accuracy": 0.8858078986406326,
|
| 550 |
+
"epoch": 1.3339517625231911,
|
| 551 |
+
"step": 540
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"loss": 0.3996,
|
| 555 |
+
"grad_norm": 1.1774884462356567,
|
| 556 |
+
"learning_rate": 0.0001421534835796867,
|
| 557 |
+
"entropy": 0.42357270009815695,
|
| 558 |
+
"num_tokens": 285557.0,
|
| 559 |
+
"mean_token_accuracy": 0.8919216230511665,
|
| 560 |
+
"epoch": 1.3586889301175016,
|
| 561 |
+
"step": 550
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"loss": 0.4248,
|
| 565 |
+
"grad_norm": 1.0505497455596924,
|
| 566 |
+
"learning_rate": 0.00013253699463318714,
|
| 567 |
+
"entropy": 0.4161256577819586,
|
| 568 |
+
"num_tokens": 290827.0,
|
| 569 |
+
"mean_token_accuracy": 0.8909587010741233,
|
| 570 |
+
"epoch": 1.383426097711812,
|
| 571 |
+
"step": 560
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"loss": 0.4593,
|
| 575 |
+
"grad_norm": 0.9745755195617676,
|
| 576 |
+
"learning_rate": 0.00012313861719644102,
|
| 577 |
+
"entropy": 0.41369549594819544,
|
| 578 |
+
"num_tokens": 296091.0,
|
| 579 |
+
"mean_token_accuracy": 0.884009575843811,
|
| 580 |
+
"epoch": 1.4081632653061225,
|
| 581 |
+
"step": 570
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"loss": 0.4465,
|
| 585 |
+
"grad_norm": 1.075348138809204,
|
| 586 |
+
"learning_rate": 0.00011397580267285432,
|
| 587 |
+
"entropy": 0.4684952672570944,
|
| 588 |
+
"num_tokens": 301292.0,
|
| 589 |
+
"mean_token_accuracy": 0.8864868000149727,
|
| 590 |
+
"epoch": 1.432900432900433,
|
| 591 |
+
"step": 580
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"loss": 0.4253,
|
| 595 |
+
"grad_norm": 0.8001469969749451,
|
| 596 |
+
"learning_rate": 0.00010506556506017992,
|
| 597 |
+
"entropy": 0.44990680664777755,
|
| 598 |
+
"num_tokens": 306515.0,
|
| 599 |
+
"mean_token_accuracy": 0.8897192627191544,
|
| 600 |
+
"epoch": 1.4576376004947433,
|
| 601 |
+
"step": 590
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"loss": 0.4213,
|
| 605 |
+
"grad_norm": 1.2559151649475098,
|
| 606 |
+
"learning_rate": 9.642444935802744e-05,
|
| 607 |
+
"entropy": 0.426817874237895,
|
| 608 |
+
"num_tokens": 311722.0,
|
| 609 |
+
"mean_token_accuracy": 0.8939041405916214,
|
| 610 |
+
"epoch": 1.4823747680890538,
|
| 611 |
+
"step": 600
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"loss": 0.416,
|
| 615 |
+
"grad_norm": 0.9963752627372742,
|
| 616 |
+
"learning_rate": 8.806850084623528e-05,
|
| 617 |
+
"entropy": 0.4087653812021017,
|
| 618 |
+
"num_tokens": 316986.0,
|
| 619 |
+
"mean_token_accuracy": 0.8879835367202759,
|
| 620 |
+
"epoch": 1.5071119356833642,
|
| 621 |
+
"step": 610
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"loss": 0.4558,
|
| 625 |
+
"grad_norm": 0.8167953491210938,
|
| 626 |
+
"learning_rate": 8.001323529114718e-05,
|
| 627 |
+
"entropy": 0.45350427702069285,
|
| 628 |
+
"num_tokens": 322177.0,
|
| 629 |
+
"mean_token_accuracy": 0.8845805168151856,
|
| 630 |
+
"epoch": 1.5318491032776747,
|
| 631 |
+
"step": 620
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"loss": 0.3814,
|
| 635 |
+
"grad_norm": 1.059950590133667,
|
| 636 |
+
"learning_rate": 7.227361013511899e-05,
|
| 637 |
+
"entropy": 0.4069512404501438,
|
| 638 |
+
"num_tokens": 327385.0,
|
| 639 |
+
"mean_token_accuracy": 0.8984012454748154,
|
| 640 |
+
"epoch": 1.556586270871985,
|
| 641 |
+
"step": 630
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"loss": 0.4644,
|
| 645 |
+
"grad_norm": 1.0526669025421143,
|
| 646 |
+
"learning_rate": 6.48639967227489e-05,
|
| 647 |
+
"entropy": 0.4181812532246113,
|
| 648 |
+
"num_tokens": 332519.0,
|
| 649 |
+
"mean_token_accuracy": 0.8847895339131355,
|
| 650 |
+
"epoch": 1.5813234384662955,
|
| 651 |
+
"step": 640
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"loss": 0.4456,
|
| 655 |
+
"grad_norm": 0.794501781463623,
|
| 656 |
+
"learning_rate": 5.779815361540727e-05,
|
| 657 |
+
"entropy": 0.44847704023122786,
|
| 658 |
+
"num_tokens": 337750.0,
|
| 659 |
+
"mean_token_accuracy": 0.8857055723667144,
|
| 660 |
+
"epoch": 1.606060606060606,
|
| 661 |
+
"step": 650
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"loss": 0.3813,
|
| 665 |
+
"grad_norm": 0.7989002466201782,
|
| 666 |
+
"learning_rate": 5.108920104361259e-05,
|
| 667 |
+
"entropy": 0.4123352896422148,
|
| 668 |
+
"num_tokens": 343062.0,
|
| 669 |
+
"mean_token_accuracy": 0.8978188335895538,
|
| 670 |
+
"epoch": 1.6307977736549164,
|
| 671 |
+
"step": 660
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"loss": 0.3863,
|
| 675 |
+
"grad_norm": 0.8852431774139404,
|
| 676 |
+
"learning_rate": 4.4749596544695404e-05,
|
| 677 |
+
"entropy": 0.38338451609015467,
|
| 678 |
+
"num_tokens": 348254.0,
|
| 679 |
+
"mean_token_accuracy": 0.8987199679017067,
|
| 680 |
+
"epoch": 1.6555349412492268,
|
| 681 |
+
"step": 670
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"loss": 0.4221,
|
| 685 |
+
"grad_norm": 1.5136176347732544,
|
| 686 |
+
"learning_rate": 3.879111183098477e-05,
|
| 687 |
+
"entropy": 0.37836207263171673,
|
| 688 |
+
"num_tokens": 353426.0,
|
| 689 |
+
"mean_token_accuracy": 0.8940739586949349,
|
| 690 |
+
"epoch": 1.6802721088435373,
|
| 691 |
+
"step": 680
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"loss": 0.4001,
|
| 695 |
+
"grad_norm": 1.0015009641647339,
|
| 696 |
+
"learning_rate": 3.322481093147178e-05,
|
| 697 |
+
"entropy": 0.4034986659884453,
|
| 698 |
+
"num_tokens": 358532.0,
|
| 699 |
+
"mean_token_accuracy": 0.8967258155345916,
|
| 700 |
+
"epoch": 1.7050092764378477,
|
| 701 |
+
"step": 690
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"loss": 0.4327,
|
| 705 |
+
"grad_norm": 1.02913236618042,
|
| 706 |
+
"learning_rate": 2.806102964753604e-05,
|
| 707 |
+
"entropy": 0.4307912774384022,
|
| 708 |
+
"num_tokens": 363792.0,
|
| 709 |
+
"mean_token_accuracy": 0.8911660447716713,
|
| 710 |
+
"epoch": 1.7297464440321582,
|
| 711 |
+
"step": 700
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"loss": 0.3895,
|
| 715 |
+
"grad_norm": 1.016865849494934,
|
| 716 |
+
"learning_rate": 2.3309356360884327e-05,
|
| 717 |
+
"entropy": 0.4226231526583433,
|
| 718 |
+
"num_tokens": 369023.0,
|
| 719 |
+
"mean_token_accuracy": 0.8997940927743912,
|
| 720 |
+
"epoch": 1.7544836116264688,
|
| 721 |
+
"step": 710
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"loss": 0.3562,
|
| 725 |
+
"grad_norm": 0.8232676982879639,
|
| 726 |
+
"learning_rate": 1.8978614229337026e-05,
|
| 727 |
+
"entropy": 0.3808727961033583,
|
| 728 |
+
"num_tokens": 374264.0,
|
| 729 |
+
"mean_token_accuracy": 0.9046193704009056,
|
| 730 |
+
"epoch": 1.7792207792207793,
|
| 731 |
+
"step": 720
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"loss": 0.4158,
|
| 735 |
+
"grad_norm": 1.228324294090271,
|
| 736 |
+
"learning_rate": 1.5076844803522921e-05,
|
| 737 |
+
"entropy": 0.4109586663544178,
|
| 738 |
+
"num_tokens": 379440.0,
|
| 739 |
+
"mean_token_accuracy": 0.8908816993236541,
|
| 740 |
+
"epoch": 1.8039579468150897,
|
| 741 |
+
"step": 730
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"loss": 0.4075,
|
| 745 |
+
"grad_norm": 0.9970471858978271,
|
| 746 |
+
"learning_rate": 1.1611293094903358e-05,
|
| 747 |
+
"entropy": 0.4193814411759377,
|
| 748 |
+
"num_tokens": 384657.0,
|
| 749 |
+
"mean_token_accuracy": 0.894894216954708,
|
| 750 |
+
"epoch": 1.8286951144094001,
|
| 751 |
+
"step": 740
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"loss": 0.5113,
|
| 755 |
+
"grad_norm": 0.8334302306175232,
|
| 756 |
+
"learning_rate": 8.588394122852589e-06,
|
| 757 |
+
"entropy": 0.4284255560487509,
|
| 758 |
+
"num_tokens": 389866.0,
|
| 759 |
+
"mean_token_accuracy": 0.8754843652248383,
|
| 760 |
+
"epoch": 1.8534322820037106,
|
| 761 |
+
"step": 750
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"loss": 0.4188,
|
| 765 |
+
"grad_norm": 1.1035089492797852,
|
| 766 |
+
"learning_rate": 6.0137609657741065e-06,
|
| 767 |
+
"entropy": 0.40159316882491114,
|
| 768 |
+
"num_tokens": 395047.0,
|
| 769 |
+
"mean_token_accuracy": 0.8867701947689056,
|
| 770 |
+
"epoch": 1.878169449598021,
|
| 771 |
+
"step": 760
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"loss": 0.4018,
|
| 775 |
+
"grad_norm": 0.9493175148963928,
|
| 776 |
+
"learning_rate": 3.892174338440136e-06,
|
| 777 |
+
"entropy": 0.4185076966881752,
|
| 778 |
+
"num_tokens": 400300.0,
|
| 779 |
+
"mean_token_accuracy": 0.8947509944438934,
|
| 780 |
+
"epoch": 1.9029066171923315,
|
| 781 |
+
"step": 770
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"loss": 0.4322,
|
| 785 |
+
"grad_norm": 0.8785578608512878,
|
| 786 |
+
"learning_rate": 2.2275737149082266e-06,
|
| 787 |
+
"entropy": 0.4141177587211132,
|
| 788 |
+
"num_tokens": 405492.0,
|
| 789 |
+
"mean_token_accuracy": 0.8923440754413605,
|
| 790 |
+
"epoch": 1.927643784786642,
|
| 791 |
+
"step": 780
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"loss": 0.4572,
|
| 795 |
+
"grad_norm": 0.8836324214935303,
|
| 796 |
+
"learning_rate": 1.0230500134976728e-06,
|
| 797 |
+
"entropy": 0.43889166191220286,
|
| 798 |
+
"num_tokens": 410763.0,
|
| 799 |
+
"mean_token_accuracy": 0.8833968549966812,
|
| 800 |
+
"epoch": 1.9523809523809523,
|
| 801 |
+
"step": 790
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"loss": 0.3741,
|
| 805 |
+
"grad_norm": 0.9182628989219666,
|
| 806 |
+
"learning_rate": 2.808398574093984e-07,
|
| 807 |
+
"entropy": 0.3942453060299158,
|
| 808 |
+
"num_tokens": 415888.0,
|
| 809 |
+
"mean_token_accuracy": 0.90195052921772,
|
| 810 |
+
"epoch": 1.977118119975263,
|
| 811 |
+
"step": 800
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"loss": 0.4476,
|
| 815 |
+
"grad_norm": 2.5363073348999023,
|
| 816 |
+
"learning_rate": 2.3214216457456692e-09,
|
| 817 |
+
"entropy": 0.43775520332761714,
|
| 818 |
+
"num_tokens": 420772.0,
|
| 819 |
+
"mean_token_accuracy": 0.8913259683428584,
|
| 820 |
+
"epoch": 2.0,
|
| 821 |
+
"step": 810
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"eval_loss": 0.8108042478561401,
|
| 825 |
+
"eval_runtime": 125.46,
|
| 826 |
+
"eval_samples_per_second": 1.435,
|
| 827 |
+
"eval_steps_per_second": 1.435,
|
| 828 |
+
"eval_entropy": 0.5558884469999208,
|
| 829 |
+
"eval_num_tokens": 420772.0,
|
| 830 |
+
"eval_mean_token_accuracy": 0.8297225495179494,
|
| 831 |
+
"epoch": 2.0,
|
| 832 |
+
"step": 810
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"train_runtime": 5032.4896,
|
| 836 |
+
"train_samples_per_second": 0.643,
|
| 837 |
+
"train_steps_per_second": 0.161,
|
| 838 |
+
"total_flos": 9506836340035584.0,
|
| 839 |
+
"train_loss": 0.6661021294417204,
|
| 840 |
+
"epoch": 2.0,
|
| 841 |
+
"step": 810
|
| 842 |
+
}
|
| 843 |
+
]
|
checkpoint-405/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-4B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-4B
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.0
|
checkpoint-405/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-4B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 64,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"gate_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
checkpoint-405/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0264395d12ad5797c1837584db31ce1cf8a2c95aa366b0170380b0a333864d8f
|
| 3 |
+
size 528550256
|
checkpoint-405/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
checkpoint-405/chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
checkpoint-405/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-405/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:69cdb3fecbe86121fab26c392ea25ed22e09e5e5f833620a17ebe1120d05d4a1
|
| 3 |
+
size 1057397963
|
checkpoint-405/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:930d876832f0b6e6301414f28ad1253ca716a7b970dfdd8b58e173fe92cb6d39
|
| 3 |
+
size 14645
|
checkpoint-405/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7bccb4fda06950b9da8c1d2d55fb3add387799e5100f3ec32c3d3b762113e39e
|
| 3 |
+
size 1465
|
checkpoint-405/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-405/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
checkpoint-405/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
checkpoint-405/trainer_state.json
ADDED
|
@@ -0,0 +1,445 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 405,
|
| 3 |
+
"best_metric": 0.820298433303833,
|
| 4 |
+
"best_model_checkpoint": "Thera-qwen-finetuned/checkpoint-405",
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 405,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.6250975668430327,
|
| 14 |
+
"epoch": 0.024737167594310452,
|
| 15 |
+
"grad_norm": 2.9517738819122314,
|
| 16 |
+
"learning_rate": 5.555555555555555e-05,
|
| 17 |
+
"loss": 3.5346,
|
| 18 |
+
"mean_token_accuracy": 0.4640115313231945,
|
| 19 |
+
"num_tokens": 5217.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.2365971699357032,
|
| 24 |
+
"epoch": 0.049474335188620905,
|
| 25 |
+
"grad_norm": 1.3123714923858643,
|
| 26 |
+
"learning_rate": 0.00011728395061728394,
|
| 27 |
+
"loss": 1.151,
|
| 28 |
+
"mean_token_accuracy": 0.7842043608427047,
|
| 29 |
+
"num_tokens": 10339.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.8006420895457268,
|
| 34 |
+
"epoch": 0.07421150278293136,
|
| 35 |
+
"grad_norm": 1.1022770404815674,
|
| 36 |
+
"learning_rate": 0.00017901234567901234,
|
| 37 |
+
"loss": 0.7884,
|
| 38 |
+
"mean_token_accuracy": 0.8256171777844429,
|
| 39 |
+
"num_tokens": 15466.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.7944120116531849,
|
| 44 |
+
"epoch": 0.09894867037724181,
|
| 45 |
+
"grad_norm": 0.6970203518867493,
|
| 46 |
+
"learning_rate": 0.00024074074074074072,
|
| 47 |
+
"loss": 0.8226,
|
| 48 |
+
"mean_token_accuracy": 0.8202412217855454,
|
| 49 |
+
"num_tokens": 20751.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7060609392821788,
|
| 54 |
+
"epoch": 0.12368583797155226,
|
| 55 |
+
"grad_norm": 0.8590984344482422,
|
| 56 |
+
"learning_rate": 0.00030246913580246913,
|
| 57 |
+
"loss": 0.7494,
|
| 58 |
+
"mean_token_accuracy": 0.8315540343523026,
|
| 59 |
+
"num_tokens": 25959.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.7671719007194042,
|
| 64 |
+
"epoch": 0.14842300556586271,
|
| 65 |
+
"grad_norm": 0.7957938313484192,
|
| 66 |
+
"learning_rate": 0.00036419753086419757,
|
| 67 |
+
"loss": 0.7744,
|
| 68 |
+
"mean_token_accuracy": 0.8240246027708054,
|
| 69 |
+
"num_tokens": 31167.0,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.7414519913494587,
|
| 74 |
+
"epoch": 0.17316017316017315,
|
| 75 |
+
"grad_norm": 0.8324401378631592,
|
| 76 |
+
"learning_rate": 0.00042592592592592595,
|
| 77 |
+
"loss": 0.7366,
|
| 78 |
+
"mean_token_accuracy": 0.8289650768041611,
|
| 79 |
+
"num_tokens": 36361.0,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.7403566606342793,
|
| 84 |
+
"epoch": 0.19789734075448362,
|
| 85 |
+
"grad_norm": 0.7674175500869751,
|
| 86 |
+
"learning_rate": 0.00048765432098765433,
|
| 87 |
+
"loss": 0.7674,
|
| 88 |
+
"mean_token_accuracy": 0.8263674512505531,
|
| 89 |
+
"num_tokens": 41652.0,
|
| 90 |
+
"step": 80
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 0.7672358199954032,
|
| 94 |
+
"epoch": 0.22263450834879406,
|
| 95 |
+
"grad_norm": 0.8532105088233948,
|
| 96 |
+
"learning_rate": 0.0004998514434997615,
|
| 97 |
+
"loss": 0.7769,
|
| 98 |
+
"mean_token_accuracy": 0.8204340368509293,
|
| 99 |
+
"num_tokens": 46935.0,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 0.7317010335624218,
|
| 104 |
+
"epoch": 0.24737167594310452,
|
| 105 |
+
"grad_norm": 0.7918670773506165,
|
| 106 |
+
"learning_rate": 0.000499248235291948,
|
| 107 |
+
"loss": 0.759,
|
| 108 |
+
"mean_token_accuracy": 0.82643341422081,
|
| 109 |
+
"num_tokens": 52141.0,
|
| 110 |
+
"step": 100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.7418206945061684,
|
| 114 |
+
"epoch": 0.272108843537415,
|
| 115 |
+
"grad_norm": 0.9036818146705627,
|
| 116 |
+
"learning_rate": 0.0004981822098019347,
|
| 117 |
+
"loss": 0.7792,
|
| 118 |
+
"mean_token_accuracy": 0.8211499944329261,
|
| 119 |
+
"num_tokens": 57323.0,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.788830752670765,
|
| 124 |
+
"epoch": 0.29684601113172543,
|
| 125 |
+
"grad_norm": 0.9364569783210754,
|
| 126 |
+
"learning_rate": 0.0004966553464821318,
|
| 127 |
+
"loss": 0.8088,
|
| 128 |
+
"mean_token_accuracy": 0.8202816650271416,
|
| 129 |
+
"num_tokens": 62559.0,
|
| 130 |
+
"step": 120
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.8334563881158829,
|
| 134 |
+
"epoch": 0.32158317872603587,
|
| 135 |
+
"grad_norm": 0.849193274974823,
|
| 136 |
+
"learning_rate": 0.0004946704804929611,
|
| 137 |
+
"loss": 0.8429,
|
| 138 |
+
"mean_token_accuracy": 0.8172205120325089,
|
| 139 |
+
"num_tokens": 67796.0,
|
| 140 |
+
"step": 130
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.819231541454792,
|
| 144 |
+
"epoch": 0.3463203463203463,
|
| 145 |
+
"grad_norm": 0.8545674085617065,
|
| 146 |
+
"learning_rate": 0.0004922312974383811,
|
| 147 |
+
"loss": 0.8252,
|
| 148 |
+
"mean_token_accuracy": 0.8214908227324486,
|
| 149 |
+
"num_tokens": 73053.0,
|
| 150 |
+
"step": 140
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.8317434027791023,
|
| 154 |
+
"epoch": 0.37105751391465674,
|
| 155 |
+
"grad_norm": 0.8818181157112122,
|
| 156 |
+
"learning_rate": 0.0004893423265222629,
|
| 157 |
+
"loss": 0.833,
|
| 158 |
+
"mean_token_accuracy": 0.818103215098381,
|
| 159 |
+
"num_tokens": 78244.0,
|
| 160 |
+
"step": 150
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.8188002541661262,
|
| 164 |
+
"epoch": 0.39579468150896724,
|
| 165 |
+
"grad_norm": 2.9915354251861572,
|
| 166 |
+
"learning_rate": 0.000486008932138325,
|
| 167 |
+
"loss": 0.8259,
|
| 168 |
+
"mean_token_accuracy": 0.8210815489292145,
|
| 169 |
+
"num_tokens": 83400.0,
|
| 170 |
+
"step": 160
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.8377857849001884,
|
| 174 |
+
"epoch": 0.4205318491032777,
|
| 175 |
+
"grad_norm": 1.1181414127349854,
|
| 176 |
+
"learning_rate": 0.0004822373039092439,
|
| 177 |
+
"loss": 0.848,
|
| 178 |
+
"mean_token_accuracy": 0.8190183833241462,
|
| 179 |
+
"num_tokens": 88646.0,
|
| 180 |
+
"step": 170
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.8113411583006382,
|
| 184 |
+
"epoch": 0.4452690166975881,
|
| 185 |
+
"grad_norm": 3.424036979675293,
|
| 186 |
+
"learning_rate": 0.0004780344451934363,
|
| 187 |
+
"loss": 0.8064,
|
| 188 |
+
"mean_token_accuracy": 0.8218150183558464,
|
| 189 |
+
"num_tokens": 93860.0,
|
| 190 |
+
"step": 180
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.8306475475430488,
|
| 194 |
+
"epoch": 0.47000618429189855,
|
| 195 |
+
"grad_norm": 1.6186113357543945,
|
| 196 |
+
"learning_rate": 0.00047340816008085306,
|
| 197 |
+
"loss": 0.9719,
|
| 198 |
+
"mean_token_accuracy": 0.7976664826273918,
|
| 199 |
+
"num_tokens": 99115.0,
|
| 200 |
+
"step": 190
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.8320877499878406,
|
| 204 |
+
"epoch": 0.49474335188620905,
|
| 205 |
+
"grad_norm": 0.9495635628700256,
|
| 206 |
+
"learning_rate": 0.00046836703890193313,
|
| 207 |
+
"loss": 0.8337,
|
| 208 |
+
"mean_token_accuracy": 0.8249012738466263,
|
| 209 |
+
"num_tokens": 104288.0,
|
| 210 |
+
"step": 200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 0.8043741077184677,
|
| 214 |
+
"epoch": 0.5194805194805194,
|
| 215 |
+
"grad_norm": 0.9904643297195435,
|
| 216 |
+
"learning_rate": 0.0004629204422766245,
|
| 217 |
+
"loss": 0.8317,
|
| 218 |
+
"mean_token_accuracy": 0.8221358329057693,
|
| 219 |
+
"num_tokens": 109502.0,
|
| 220 |
+
"step": 210
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 0.8280141688883305,
|
| 224 |
+
"epoch": 0.54421768707483,
|
| 225 |
+
"grad_norm": 1.3911291360855103,
|
| 226 |
+
"learning_rate": 0.0004570784837330908,
|
| 227 |
+
"loss": 0.865,
|
| 228 |
+
"mean_token_accuracy": 0.8145962327718734,
|
| 229 |
+
"num_tokens": 114746.0,
|
| 230 |
+
"step": 220
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 0.7979148738086224,
|
| 234 |
+
"epoch": 0.5689548546691404,
|
| 235 |
+
"grad_norm": 1.1356682777404785,
|
| 236 |
+
"learning_rate": 0.0004508520109283782,
|
| 237 |
+
"loss": 0.8203,
|
| 238 |
+
"mean_token_accuracy": 0.8190253749489784,
|
| 239 |
+
"num_tokens": 119935.0,
|
| 240 |
+
"step": 230
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 0.7733577877283097,
|
| 244 |
+
"epoch": 0.5936920222634509,
|
| 245 |
+
"grad_norm": 1.006868839263916,
|
| 246 |
+
"learning_rate": 0.0004442525855059136,
|
| 247 |
+
"loss": 0.856,
|
| 248 |
+
"mean_token_accuracy": 0.815259476006031,
|
| 249 |
+
"num_tokens": 125174.0,
|
| 250 |
+
"step": 240
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.762465487420559,
|
| 254 |
+
"epoch": 0.6184291898577613,
|
| 255 |
+
"grad_norm": 0.9585395455360413,
|
| 256 |
+
"learning_rate": 0.00043729246162723404,
|
| 257 |
+
"loss": 0.7808,
|
| 258 |
+
"mean_token_accuracy": 0.8212951749563218,
|
| 259 |
+
"num_tokens": 130346.0,
|
| 260 |
+
"step": 250
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.888411459326744,
|
| 264 |
+
"epoch": 0.6431663574520717,
|
| 265 |
+
"grad_norm": 0.8783559203147888,
|
| 266 |
+
"learning_rate": 0.00042998456321781284,
|
| 267 |
+
"loss": 0.9951,
|
| 268 |
+
"mean_token_accuracy": 0.8052207484841347,
|
| 269 |
+
"num_tokens": 135467.0,
|
| 270 |
+
"step": 260
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.7948930785059929,
|
| 274 |
+
"epoch": 0.6679035250463822,
|
| 275 |
+
"grad_norm": 0.9991810321807861,
|
| 276 |
+
"learning_rate": 0.0004223424599692327,
|
| 277 |
+
"loss": 0.8121,
|
| 278 |
+
"mean_token_accuracy": 0.8190833777189255,
|
| 279 |
+
"num_tokens": 140671.0,
|
| 280 |
+
"step": 270
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.8159038618206977,
|
| 284 |
+
"epoch": 0.6926406926406926,
|
| 285 |
+
"grad_norm": 1.0719568729400635,
|
| 286 |
+
"learning_rate": 0.00041438034214226596,
|
| 287 |
+
"loss": 0.8352,
|
| 288 |
+
"mean_token_accuracy": 0.8190872147679329,
|
| 289 |
+
"num_tokens": 145888.0,
|
| 290 |
+
"step": 280
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 0.8683171272277832,
|
| 294 |
+
"epoch": 0.717377860235003,
|
| 295 |
+
"grad_norm": 0.9456169009208679,
|
| 296 |
+
"learning_rate": 0.0004061129942176487,
|
| 297 |
+
"loss": 0.8616,
|
| 298 |
+
"mean_token_accuracy": 0.8180570781230927,
|
| 299 |
+
"num_tokens": 151125.0,
|
| 300 |
+
"step": 290
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 0.7405934803187847,
|
| 304 |
+
"epoch": 0.7421150278293135,
|
| 305 |
+
"grad_norm": 0.8249353170394897,
|
| 306 |
+
"learning_rate": 0.0003975557674434772,
|
| 307 |
+
"loss": 0.8035,
|
| 308 |
+
"mean_token_accuracy": 0.8308369800448417,
|
| 309 |
+
"num_tokens": 156230.0,
|
| 310 |
+
"step": 300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 0.8380466908216476,
|
| 314 |
+
"epoch": 0.766852195423624,
|
| 315 |
+
"grad_norm": 1.1419930458068848,
|
| 316 |
+
"learning_rate": 0.00038872455133019923,
|
| 317 |
+
"loss": 0.8651,
|
| 318 |
+
"mean_token_accuracy": 0.8131552562117577,
|
| 319 |
+
"num_tokens": 161487.0,
|
| 320 |
+
"step": 310
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 0.8332376055419445,
|
| 324 |
+
"epoch": 0.7915893630179345,
|
| 325 |
+
"grad_norm": 1.124142050743103,
|
| 326 |
+
"learning_rate": 0.00037963574414613265,
|
| 327 |
+
"loss": 0.8528,
|
| 328 |
+
"mean_token_accuracy": 0.8137879073619843,
|
| 329 |
+
"num_tokens": 166771.0,
|
| 330 |
+
"step": 320
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 0.7901938475668431,
|
| 334 |
+
"epoch": 0.8163265306122449,
|
| 335 |
+
"grad_norm": 1.3924378156661987,
|
| 336 |
+
"learning_rate": 0.00037030622246829486,
|
| 337 |
+
"loss": 0.7916,
|
| 338 |
+
"mean_token_accuracy": 0.8227489620447159,
|
| 339 |
+
"num_tokens": 171893.0,
|
| 340 |
+
"step": 330
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 0.8100152090191841,
|
| 344 |
+
"epoch": 0.8410636982065554,
|
| 345 |
+
"grad_norm": 2.675826072692871,
|
| 346 |
+
"learning_rate": 0.0003607533098450838,
|
| 347 |
+
"loss": 0.8336,
|
| 348 |
+
"mean_token_accuracy": 0.8140658468008042,
|
| 349 |
+
"num_tokens": 177077.0,
|
| 350 |
+
"step": 340
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 0.7574406780302525,
|
| 354 |
+
"epoch": 0.8658008658008658,
|
| 355 |
+
"grad_norm": 0.9445605874061584,
|
| 356 |
+
"learning_rate": 0.0003509947446289984,
|
| 357 |
+
"loss": 0.7847,
|
| 358 |
+
"mean_token_accuracy": 0.8235680922865868,
|
| 359 |
+
"num_tokens": 182234.0,
|
| 360 |
+
"step": 350
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 0.8985893219709397,
|
| 364 |
+
"epoch": 0.8905380333951762,
|
| 365 |
+
"grad_norm": 0.9632943868637085,
|
| 366 |
+
"learning_rate": 0.00034104864703912957,
|
| 367 |
+
"loss": 0.9156,
|
| 368 |
+
"mean_token_accuracy": 0.8068240508437157,
|
| 369 |
+
"num_tokens": 187422.0,
|
| 370 |
+
"step": 360
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 0.7982684150338173,
|
| 374 |
+
"epoch": 0.9152752009894867,
|
| 375 |
+
"grad_norm": 0.8351237773895264,
|
| 376 |
+
"learning_rate": 0.0003309334855145803,
|
| 377 |
+
"loss": 0.7905,
|
| 378 |
+
"mean_token_accuracy": 0.8268924236297608,
|
| 379 |
+
"num_tokens": 192626.0,
|
| 380 |
+
"step": 370
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 0.7881800249218941,
|
| 384 |
+
"epoch": 0.9400123685837971,
|
| 385 |
+
"grad_norm": 0.8712763786315918,
|
| 386 |
+
"learning_rate": 0.0003206680424212931,
|
| 387 |
+
"loss": 0.8186,
|
| 388 |
+
"mean_token_accuracy": 0.8173615485429764,
|
| 389 |
+
"num_tokens": 197838.0,
|
| 390 |
+
"step": 380
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 0.744848319888115,
|
| 394 |
+
"epoch": 0.9647495361781077,
|
| 395 |
+
"grad_norm": 0.7793152332305908,
|
| 396 |
+
"learning_rate": 0.0003102713791759616,
|
| 397 |
+
"loss": 0.7988,
|
| 398 |
+
"mean_token_accuracy": 0.8299087509512901,
|
| 399 |
+
"num_tokens": 203044.0,
|
| 400 |
+
"step": 390
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 0.7603424042463303,
|
| 404 |
+
"epoch": 0.9894867037724181,
|
| 405 |
+
"grad_norm": 0.949001669883728,
|
| 406 |
+
"learning_rate": 0.00029976280085178514,
|
| 407 |
+
"loss": 0.7642,
|
| 408 |
+
"mean_token_accuracy": 0.8270730227231979,
|
| 409 |
+
"num_tokens": 208194.0,
|
| 410 |
+
"step": 400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.0,
|
| 414 |
+
"eval_entropy": 0.8190755642122692,
|
| 415 |
+
"eval_loss": 0.820298433303833,
|
| 416 |
+
"eval_mean_token_accuracy": 0.8219989130894343,
|
| 417 |
+
"eval_num_tokens": 210386.0,
|
| 418 |
+
"eval_runtime": 125.2713,
|
| 419 |
+
"eval_samples_per_second": 1.437,
|
| 420 |
+
"eval_steps_per_second": 1.437,
|
| 421 |
+
"step": 405
|
| 422 |
+
}
|
| 423 |
+
],
|
| 424 |
+
"logging_steps": 10,
|
| 425 |
+
"max_steps": 810,
|
| 426 |
+
"num_input_tokens_seen": 0,
|
| 427 |
+
"num_train_epochs": 2,
|
| 428 |
+
"save_steps": 500,
|
| 429 |
+
"stateful_callbacks": {
|
| 430 |
+
"TrainerControl": {
|
| 431 |
+
"args": {
|
| 432 |
+
"should_epoch_stop": false,
|
| 433 |
+
"should_evaluate": false,
|
| 434 |
+
"should_log": false,
|
| 435 |
+
"should_save": true,
|
| 436 |
+
"should_training_stop": false
|
| 437 |
+
},
|
| 438 |
+
"attributes": {}
|
| 439 |
+
}
|
| 440 |
+
},
|
| 441 |
+
"total_flos": 4753418170017792.0,
|
| 442 |
+
"train_batch_size": 1,
|
| 443 |
+
"trial_name": null,
|
| 444 |
+
"trial_params": null
|
| 445 |
+
}
|
checkpoint-405/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:602933e14cee181956b6ba86efd1c972acb28b64c16c9da71ac0844bc4a294d9
|
| 3 |
+
size 6225
|
checkpoint-405/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-810/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-4B
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-4B
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.18.0
|
checkpoint-810/adapter_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-4B",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.05,
|
| 22 |
+
"megatron_config": null,
|
| 23 |
+
"megatron_core": "megatron.core",
|
| 24 |
+
"modules_to_save": null,
|
| 25 |
+
"peft_type": "LORA",
|
| 26 |
+
"peft_version": "0.18.0",
|
| 27 |
+
"qalora_group_size": 16,
|
| 28 |
+
"r": 64,
|
| 29 |
+
"rank_pattern": {},
|
| 30 |
+
"revision": null,
|
| 31 |
+
"target_modules": [
|
| 32 |
+
"v_proj",
|
| 33 |
+
"up_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"q_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"k_proj",
|
| 38 |
+
"gate_proj"
|
| 39 |
+
],
|
| 40 |
+
"target_parameters": null,
|
| 41 |
+
"task_type": "CAUSAL_LM",
|
| 42 |
+
"trainable_token_indices": null,
|
| 43 |
+
"use_dora": false,
|
| 44 |
+
"use_qalora": false,
|
| 45 |
+
"use_rslora": false
|
| 46 |
+
}
|
checkpoint-810/adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee9a1c85427ea72b1cf64eb53727331a8834b098a399a8d3b5ac16a6539e898c
|
| 3 |
+
size 528550256
|
checkpoint-810/added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
checkpoint-810/chat_template.jinja
ADDED
|
@@ -0,0 +1,89 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if message.content is string %}
|
| 27 |
+
{%- set content = message.content %}
|
| 28 |
+
{%- else %}
|
| 29 |
+
{%- set content = '' %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 32 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 33 |
+
{%- elif message.role == "assistant" %}
|
| 34 |
+
{%- set reasoning_content = '' %}
|
| 35 |
+
{%- if message.reasoning_content is string %}
|
| 36 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 37 |
+
{%- else %}
|
| 38 |
+
{%- if '</think>' in content %}
|
| 39 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 40 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{%- endif %}
|
| 43 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 44 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 45 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 48 |
+
{%- endif %}
|
| 49 |
+
{%- else %}
|
| 50 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- if message.tool_calls %}
|
| 53 |
+
{%- for tool_call in message.tool_calls %}
|
| 54 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 55 |
+
{{- '\n' }}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tool_call.function %}
|
| 58 |
+
{%- set tool_call = tool_call.function %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 61 |
+
{{- tool_call.name }}
|
| 62 |
+
{{- '", "arguments": ' }}
|
| 63 |
+
{%- if tool_call.arguments is string %}
|
| 64 |
+
{{- tool_call.arguments }}
|
| 65 |
+
{%- else %}
|
| 66 |
+
{{- tool_call.arguments | tojson }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{{- '}\n</tool_call>' }}
|
| 69 |
+
{%- endfor %}
|
| 70 |
+
{%- endif %}
|
| 71 |
+
{{- '<|im_end|>\n' }}
|
| 72 |
+
{%- elif message.role == "tool" %}
|
| 73 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 74 |
+
{{- '<|im_start|>user' }}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{{- '\n<tool_response>\n' }}
|
| 77 |
+
{{- content }}
|
| 78 |
+
{{- '\n</tool_response>' }}
|
| 79 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 80 |
+
{{- '<|im_end|>\n' }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endif %}
|
| 83 |
+
{%- endfor %}
|
| 84 |
+
{%- if add_generation_prompt %}
|
| 85 |
+
{{- '<|im_start|>assistant\n' }}
|
| 86 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 87 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{%- endif %}
|
checkpoint-810/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-810/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42155e9c809db451d191be5ecb7a1ac6bbaf127f28065aea6bdff8958e9565aa
|
| 3 |
+
size 1057397963
|
checkpoint-810/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ab19437d3c63cb0dcaa383269cc90e72770a17b4eb540176e54918052d83c11c
|
| 3 |
+
size 14645
|
checkpoint-810/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7816e145fe5d5b939f6789ab45747be3479b61e50fcfda43f9cd232617276600
|
| 3 |
+
size 1465
|
checkpoint-810/special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
checkpoint-810/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
checkpoint-810/tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
checkpoint-810/trainer_state.json
ADDED
|
@@ -0,0 +1,866 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": 810,
|
| 3 |
+
"best_metric": 0.8108042478561401,
|
| 4 |
+
"best_model_checkpoint": "Thera-qwen-finetuned/checkpoint-810",
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 810,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.6250975668430327,
|
| 14 |
+
"epoch": 0.024737167594310452,
|
| 15 |
+
"grad_norm": 2.9517738819122314,
|
| 16 |
+
"learning_rate": 5.555555555555555e-05,
|
| 17 |
+
"loss": 3.5346,
|
| 18 |
+
"mean_token_accuracy": 0.4640115313231945,
|
| 19 |
+
"num_tokens": 5217.0,
|
| 20 |
+
"step": 10
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.2365971699357032,
|
| 24 |
+
"epoch": 0.049474335188620905,
|
| 25 |
+
"grad_norm": 1.3123714923858643,
|
| 26 |
+
"learning_rate": 0.00011728395061728394,
|
| 27 |
+
"loss": 1.151,
|
| 28 |
+
"mean_token_accuracy": 0.7842043608427047,
|
| 29 |
+
"num_tokens": 10339.0,
|
| 30 |
+
"step": 20
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 0.8006420895457268,
|
| 34 |
+
"epoch": 0.07421150278293136,
|
| 35 |
+
"grad_norm": 1.1022770404815674,
|
| 36 |
+
"learning_rate": 0.00017901234567901234,
|
| 37 |
+
"loss": 0.7884,
|
| 38 |
+
"mean_token_accuracy": 0.8256171777844429,
|
| 39 |
+
"num_tokens": 15466.0,
|
| 40 |
+
"step": 30
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.7944120116531849,
|
| 44 |
+
"epoch": 0.09894867037724181,
|
| 45 |
+
"grad_norm": 0.6970203518867493,
|
| 46 |
+
"learning_rate": 0.00024074074074074072,
|
| 47 |
+
"loss": 0.8226,
|
| 48 |
+
"mean_token_accuracy": 0.8202412217855454,
|
| 49 |
+
"num_tokens": 20751.0,
|
| 50 |
+
"step": 40
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7060609392821788,
|
| 54 |
+
"epoch": 0.12368583797155226,
|
| 55 |
+
"grad_norm": 0.8590984344482422,
|
| 56 |
+
"learning_rate": 0.00030246913580246913,
|
| 57 |
+
"loss": 0.7494,
|
| 58 |
+
"mean_token_accuracy": 0.8315540343523026,
|
| 59 |
+
"num_tokens": 25959.0,
|
| 60 |
+
"step": 50
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.7671719007194042,
|
| 64 |
+
"epoch": 0.14842300556586271,
|
| 65 |
+
"grad_norm": 0.7957938313484192,
|
| 66 |
+
"learning_rate": 0.00036419753086419757,
|
| 67 |
+
"loss": 0.7744,
|
| 68 |
+
"mean_token_accuracy": 0.8240246027708054,
|
| 69 |
+
"num_tokens": 31167.0,
|
| 70 |
+
"step": 60
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.7414519913494587,
|
| 74 |
+
"epoch": 0.17316017316017315,
|
| 75 |
+
"grad_norm": 0.8324401378631592,
|
| 76 |
+
"learning_rate": 0.00042592592592592595,
|
| 77 |
+
"loss": 0.7366,
|
| 78 |
+
"mean_token_accuracy": 0.8289650768041611,
|
| 79 |
+
"num_tokens": 36361.0,
|
| 80 |
+
"step": 70
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.7403566606342793,
|
| 84 |
+
"epoch": 0.19789734075448362,
|
| 85 |
+
"grad_norm": 0.7674175500869751,
|
| 86 |
+
"learning_rate": 0.00048765432098765433,
|
| 87 |
+
"loss": 0.7674,
|
| 88 |
+
"mean_token_accuracy": 0.8263674512505531,
|
| 89 |
+
"num_tokens": 41652.0,
|
| 90 |
+
"step": 80
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"entropy": 0.7672358199954032,
|
| 94 |
+
"epoch": 0.22263450834879406,
|
| 95 |
+
"grad_norm": 0.8532105088233948,
|
| 96 |
+
"learning_rate": 0.0004998514434997615,
|
| 97 |
+
"loss": 0.7769,
|
| 98 |
+
"mean_token_accuracy": 0.8204340368509293,
|
| 99 |
+
"num_tokens": 46935.0,
|
| 100 |
+
"step": 90
|
| 101 |
+
},
|
| 102 |
+
{
|
| 103 |
+
"entropy": 0.7317010335624218,
|
| 104 |
+
"epoch": 0.24737167594310452,
|
| 105 |
+
"grad_norm": 0.7918670773506165,
|
| 106 |
+
"learning_rate": 0.000499248235291948,
|
| 107 |
+
"loss": 0.759,
|
| 108 |
+
"mean_token_accuracy": 0.82643341422081,
|
| 109 |
+
"num_tokens": 52141.0,
|
| 110 |
+
"step": 100
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"entropy": 0.7418206945061684,
|
| 114 |
+
"epoch": 0.272108843537415,
|
| 115 |
+
"grad_norm": 0.9036818146705627,
|
| 116 |
+
"learning_rate": 0.0004981822098019347,
|
| 117 |
+
"loss": 0.7792,
|
| 118 |
+
"mean_token_accuracy": 0.8211499944329261,
|
| 119 |
+
"num_tokens": 57323.0,
|
| 120 |
+
"step": 110
|
| 121 |
+
},
|
| 122 |
+
{
|
| 123 |
+
"entropy": 0.788830752670765,
|
| 124 |
+
"epoch": 0.29684601113172543,
|
| 125 |
+
"grad_norm": 0.9364569783210754,
|
| 126 |
+
"learning_rate": 0.0004966553464821318,
|
| 127 |
+
"loss": 0.8088,
|
| 128 |
+
"mean_token_accuracy": 0.8202816650271416,
|
| 129 |
+
"num_tokens": 62559.0,
|
| 130 |
+
"step": 120
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"entropy": 0.8334563881158829,
|
| 134 |
+
"epoch": 0.32158317872603587,
|
| 135 |
+
"grad_norm": 0.849193274974823,
|
| 136 |
+
"learning_rate": 0.0004946704804929611,
|
| 137 |
+
"loss": 0.8429,
|
| 138 |
+
"mean_token_accuracy": 0.8172205120325089,
|
| 139 |
+
"num_tokens": 67796.0,
|
| 140 |
+
"step": 130
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy": 0.819231541454792,
|
| 144 |
+
"epoch": 0.3463203463203463,
|
| 145 |
+
"grad_norm": 0.8545674085617065,
|
| 146 |
+
"learning_rate": 0.0004922312974383811,
|
| 147 |
+
"loss": 0.8252,
|
| 148 |
+
"mean_token_accuracy": 0.8214908227324486,
|
| 149 |
+
"num_tokens": 73053.0,
|
| 150 |
+
"step": 140
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"entropy": 0.8317434027791023,
|
| 154 |
+
"epoch": 0.37105751391465674,
|
| 155 |
+
"grad_norm": 0.8818181157112122,
|
| 156 |
+
"learning_rate": 0.0004893423265222629,
|
| 157 |
+
"loss": 0.833,
|
| 158 |
+
"mean_token_accuracy": 0.818103215098381,
|
| 159 |
+
"num_tokens": 78244.0,
|
| 160 |
+
"step": 150
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"entropy": 0.8188002541661262,
|
| 164 |
+
"epoch": 0.39579468150896724,
|
| 165 |
+
"grad_norm": 2.9915354251861572,
|
| 166 |
+
"learning_rate": 0.000486008932138325,
|
| 167 |
+
"loss": 0.8259,
|
| 168 |
+
"mean_token_accuracy": 0.8210815489292145,
|
| 169 |
+
"num_tokens": 83400.0,
|
| 170 |
+
"step": 160
|
| 171 |
+
},
|
| 172 |
+
{
|
| 173 |
+
"entropy": 0.8377857849001884,
|
| 174 |
+
"epoch": 0.4205318491032777,
|
| 175 |
+
"grad_norm": 1.1181414127349854,
|
| 176 |
+
"learning_rate": 0.0004822373039092439,
|
| 177 |
+
"loss": 0.848,
|
| 178 |
+
"mean_token_accuracy": 0.8190183833241462,
|
| 179 |
+
"num_tokens": 88646.0,
|
| 180 |
+
"step": 170
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"entropy": 0.8113411583006382,
|
| 184 |
+
"epoch": 0.4452690166975881,
|
| 185 |
+
"grad_norm": 3.424036979675293,
|
| 186 |
+
"learning_rate": 0.0004780344451934363,
|
| 187 |
+
"loss": 0.8064,
|
| 188 |
+
"mean_token_accuracy": 0.8218150183558464,
|
| 189 |
+
"num_tokens": 93860.0,
|
| 190 |
+
"step": 180
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"entropy": 0.8306475475430488,
|
| 194 |
+
"epoch": 0.47000618429189855,
|
| 195 |
+
"grad_norm": 1.6186113357543945,
|
| 196 |
+
"learning_rate": 0.00047340816008085306,
|
| 197 |
+
"loss": 0.9719,
|
| 198 |
+
"mean_token_accuracy": 0.7976664826273918,
|
| 199 |
+
"num_tokens": 99115.0,
|
| 200 |
+
"step": 190
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"entropy": 0.8320877499878406,
|
| 204 |
+
"epoch": 0.49474335188620905,
|
| 205 |
+
"grad_norm": 0.9495635628700256,
|
| 206 |
+
"learning_rate": 0.00046836703890193313,
|
| 207 |
+
"loss": 0.8337,
|
| 208 |
+
"mean_token_accuracy": 0.8249012738466263,
|
| 209 |
+
"num_tokens": 104288.0,
|
| 210 |
+
"step": 200
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"entropy": 0.8043741077184677,
|
| 214 |
+
"epoch": 0.5194805194805194,
|
| 215 |
+
"grad_norm": 0.9904643297195435,
|
| 216 |
+
"learning_rate": 0.0004629204422766245,
|
| 217 |
+
"loss": 0.8317,
|
| 218 |
+
"mean_token_accuracy": 0.8221358329057693,
|
| 219 |
+
"num_tokens": 109502.0,
|
| 220 |
+
"step": 210
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"entropy": 0.8280141688883305,
|
| 224 |
+
"epoch": 0.54421768707483,
|
| 225 |
+
"grad_norm": 1.3911291360855103,
|
| 226 |
+
"learning_rate": 0.0004570784837330908,
|
| 227 |
+
"loss": 0.865,
|
| 228 |
+
"mean_token_accuracy": 0.8145962327718734,
|
| 229 |
+
"num_tokens": 114746.0,
|
| 230 |
+
"step": 220
|
| 231 |
+
},
|
| 232 |
+
{
|
| 233 |
+
"entropy": 0.7979148738086224,
|
| 234 |
+
"epoch": 0.5689548546691404,
|
| 235 |
+
"grad_norm": 1.1356682777404785,
|
| 236 |
+
"learning_rate": 0.0004508520109283782,
|
| 237 |
+
"loss": 0.8203,
|
| 238 |
+
"mean_token_accuracy": 0.8190253749489784,
|
| 239 |
+
"num_tokens": 119935.0,
|
| 240 |
+
"step": 230
|
| 241 |
+
},
|
| 242 |
+
{
|
| 243 |
+
"entropy": 0.7733577877283097,
|
| 244 |
+
"epoch": 0.5936920222634509,
|
| 245 |
+
"grad_norm": 1.006868839263916,
|
| 246 |
+
"learning_rate": 0.0004442525855059136,
|
| 247 |
+
"loss": 0.856,
|
| 248 |
+
"mean_token_accuracy": 0.815259476006031,
|
| 249 |
+
"num_tokens": 125174.0,
|
| 250 |
+
"step": 240
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"entropy": 0.762465487420559,
|
| 254 |
+
"epoch": 0.6184291898577613,
|
| 255 |
+
"grad_norm": 0.9585395455360413,
|
| 256 |
+
"learning_rate": 0.00043729246162723404,
|
| 257 |
+
"loss": 0.7808,
|
| 258 |
+
"mean_token_accuracy": 0.8212951749563218,
|
| 259 |
+
"num_tokens": 130346.0,
|
| 260 |
+
"step": 250
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"entropy": 0.888411459326744,
|
| 264 |
+
"epoch": 0.6431663574520717,
|
| 265 |
+
"grad_norm": 0.8783559203147888,
|
| 266 |
+
"learning_rate": 0.00042998456321781284,
|
| 267 |
+
"loss": 0.9951,
|
| 268 |
+
"mean_token_accuracy": 0.8052207484841347,
|
| 269 |
+
"num_tokens": 135467.0,
|
| 270 |
+
"step": 260
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy": 0.7948930785059929,
|
| 274 |
+
"epoch": 0.6679035250463822,
|
| 275 |
+
"grad_norm": 0.9991810321807861,
|
| 276 |
+
"learning_rate": 0.0004223424599692327,
|
| 277 |
+
"loss": 0.8121,
|
| 278 |
+
"mean_token_accuracy": 0.8190833777189255,
|
| 279 |
+
"num_tokens": 140671.0,
|
| 280 |
+
"step": 270
|
| 281 |
+
},
|
| 282 |
+
{
|
| 283 |
+
"entropy": 0.8159038618206977,
|
| 284 |
+
"epoch": 0.6926406926406926,
|
| 285 |
+
"grad_norm": 1.0719568729400635,
|
| 286 |
+
"learning_rate": 0.00041438034214226596,
|
| 287 |
+
"loss": 0.8352,
|
| 288 |
+
"mean_token_accuracy": 0.8190872147679329,
|
| 289 |
+
"num_tokens": 145888.0,
|
| 290 |
+
"step": 280
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"entropy": 0.8683171272277832,
|
| 294 |
+
"epoch": 0.717377860235003,
|
| 295 |
+
"grad_norm": 0.9456169009208679,
|
| 296 |
+
"learning_rate": 0.0004061129942176487,
|
| 297 |
+
"loss": 0.8616,
|
| 298 |
+
"mean_token_accuracy": 0.8180570781230927,
|
| 299 |
+
"num_tokens": 151125.0,
|
| 300 |
+
"step": 290
|
| 301 |
+
},
|
| 302 |
+
{
|
| 303 |
+
"entropy": 0.7405934803187847,
|
| 304 |
+
"epoch": 0.7421150278293135,
|
| 305 |
+
"grad_norm": 0.8249353170394897,
|
| 306 |
+
"learning_rate": 0.0003975557674434772,
|
| 307 |
+
"loss": 0.8035,
|
| 308 |
+
"mean_token_accuracy": 0.8308369800448417,
|
| 309 |
+
"num_tokens": 156230.0,
|
| 310 |
+
"step": 300
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"entropy": 0.8380466908216476,
|
| 314 |
+
"epoch": 0.766852195423624,
|
| 315 |
+
"grad_norm": 1.1419930458068848,
|
| 316 |
+
"learning_rate": 0.00038872455133019923,
|
| 317 |
+
"loss": 0.8651,
|
| 318 |
+
"mean_token_accuracy": 0.8131552562117577,
|
| 319 |
+
"num_tokens": 161487.0,
|
| 320 |
+
"step": 310
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"entropy": 0.8332376055419445,
|
| 324 |
+
"epoch": 0.7915893630179345,
|
| 325 |
+
"grad_norm": 1.124142050743103,
|
| 326 |
+
"learning_rate": 0.00037963574414613265,
|
| 327 |
+
"loss": 0.8528,
|
| 328 |
+
"mean_token_accuracy": 0.8137879073619843,
|
| 329 |
+
"num_tokens": 166771.0,
|
| 330 |
+
"step": 320
|
| 331 |
+
},
|
| 332 |
+
{
|
| 333 |
+
"entropy": 0.7901938475668431,
|
| 334 |
+
"epoch": 0.8163265306122449,
|
| 335 |
+
"grad_norm": 1.3924378156661987,
|
| 336 |
+
"learning_rate": 0.00037030622246829486,
|
| 337 |
+
"loss": 0.7916,
|
| 338 |
+
"mean_token_accuracy": 0.8227489620447159,
|
| 339 |
+
"num_tokens": 171893.0,
|
| 340 |
+
"step": 330
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"entropy": 0.8100152090191841,
|
| 344 |
+
"epoch": 0.8410636982065554,
|
| 345 |
+
"grad_norm": 2.675826072692871,
|
| 346 |
+
"learning_rate": 0.0003607533098450838,
|
| 347 |
+
"loss": 0.8336,
|
| 348 |
+
"mean_token_accuracy": 0.8140658468008042,
|
| 349 |
+
"num_tokens": 177077.0,
|
| 350 |
+
"step": 340
|
| 351 |
+
},
|
| 352 |
+
{
|
| 353 |
+
"entropy": 0.7574406780302525,
|
| 354 |
+
"epoch": 0.8658008658008658,
|
| 355 |
+
"grad_norm": 0.9445605874061584,
|
| 356 |
+
"learning_rate": 0.0003509947446289984,
|
| 357 |
+
"loss": 0.7847,
|
| 358 |
+
"mean_token_accuracy": 0.8235680922865868,
|
| 359 |
+
"num_tokens": 182234.0,
|
| 360 |
+
"step": 350
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy": 0.8985893219709397,
|
| 364 |
+
"epoch": 0.8905380333951762,
|
| 365 |
+
"grad_norm": 0.9632943868637085,
|
| 366 |
+
"learning_rate": 0.00034104864703912957,
|
| 367 |
+
"loss": 0.9156,
|
| 368 |
+
"mean_token_accuracy": 0.8068240508437157,
|
| 369 |
+
"num_tokens": 187422.0,
|
| 370 |
+
"step": 360
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"entropy": 0.7982684150338173,
|
| 374 |
+
"epoch": 0.9152752009894867,
|
| 375 |
+
"grad_norm": 0.8351237773895264,
|
| 376 |
+
"learning_rate": 0.0003309334855145803,
|
| 377 |
+
"loss": 0.7905,
|
| 378 |
+
"mean_token_accuracy": 0.8268924236297608,
|
| 379 |
+
"num_tokens": 192626.0,
|
| 380 |
+
"step": 370
|
| 381 |
+
},
|
| 382 |
+
{
|
| 383 |
+
"entropy": 0.7881800249218941,
|
| 384 |
+
"epoch": 0.9400123685837971,
|
| 385 |
+
"grad_norm": 0.8712763786315918,
|
| 386 |
+
"learning_rate": 0.0003206680424212931,
|
| 387 |
+
"loss": 0.8186,
|
| 388 |
+
"mean_token_accuracy": 0.8173615485429764,
|
| 389 |
+
"num_tokens": 197838.0,
|
| 390 |
+
"step": 380
|
| 391 |
+
},
|
| 392 |
+
{
|
| 393 |
+
"entropy": 0.744848319888115,
|
| 394 |
+
"epoch": 0.9647495361781077,
|
| 395 |
+
"grad_norm": 0.7793152332305908,
|
| 396 |
+
"learning_rate": 0.0003102713791759616,
|
| 397 |
+
"loss": 0.7988,
|
| 398 |
+
"mean_token_accuracy": 0.8299087509512901,
|
| 399 |
+
"num_tokens": 203044.0,
|
| 400 |
+
"step": 390
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"entropy": 0.7603424042463303,
|
| 404 |
+
"epoch": 0.9894867037724181,
|
| 405 |
+
"grad_norm": 0.949001669883728,
|
| 406 |
+
"learning_rate": 0.00029976280085178514,
|
| 407 |
+
"loss": 0.7642,
|
| 408 |
+
"mean_token_accuracy": 0.8270730227231979,
|
| 409 |
+
"num_tokens": 208194.0,
|
| 410 |
+
"step": 400
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 1.0,
|
| 414 |
+
"eval_entropy": 0.8190755642122692,
|
| 415 |
+
"eval_loss": 0.820298433303833,
|
| 416 |
+
"eval_mean_token_accuracy": 0.8219989130894343,
|
| 417 |
+
"eval_num_tokens": 210386.0,
|
| 418 |
+
"eval_runtime": 125.2713,
|
| 419 |
+
"eval_samples_per_second": 1.437,
|
| 420 |
+
"eval_steps_per_second": 1.437,
|
| 421 |
+
"step": 405
|
| 422 |
+
},
|
| 423 |
+
{
|
| 424 |
+
"entropy": 0.7364253015131563,
|
| 425 |
+
"epoch": 1.0123685837971552,
|
| 426 |
+
"grad_norm": 0.914890468120575,
|
| 427 |
+
"learning_rate": 0.00028916182033179015,
|
| 428 |
+
"loss": 0.6928,
|
| 429 |
+
"mean_token_accuracy": 0.8474441170692444,
|
| 430 |
+
"num_tokens": 213021.0,
|
| 431 |
+
"step": 410
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"entropy": 0.4017741926014423,
|
| 435 |
+
"epoch": 1.0371057513914657,
|
| 436 |
+
"grad_norm": 0.9826574921607971,
|
| 437 |
+
"learning_rate": 0.00027848812207627863,
|
| 438 |
+
"loss": 0.4485,
|
| 439 |
+
"mean_token_accuracy": 0.8861656159162521,
|
| 440 |
+
"num_tokens": 218210.0,
|
| 441 |
+
"step": 420
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"entropy": 0.47752095237374304,
|
| 445 |
+
"epoch": 1.061842918985776,
|
| 446 |
+
"grad_norm": 0.7163196802139282,
|
| 447 |
+
"learning_rate": 0.0002677615255716825,
|
| 448 |
+
"loss": 0.4766,
|
| 449 |
+
"mean_token_accuracy": 0.8819166600704194,
|
| 450 |
+
"num_tokens": 223365.0,
|
| 451 |
+
"step": 430
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"entropy": 0.4802557807415724,
|
| 455 |
+
"epoch": 1.0865800865800865,
|
| 456 |
+
"grad_norm": 1.2513821125030518,
|
| 457 |
+
"learning_rate": 0.000257001948528696,
|
| 458 |
+
"loss": 0.4862,
|
| 459 |
+
"mean_token_accuracy": 0.8789629265666008,
|
| 460 |
+
"num_tokens": 228544.0,
|
| 461 |
+
"step": 440
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"entropy": 0.4388812955468893,
|
| 465 |
+
"epoch": 1.111317254174397,
|
| 466 |
+
"grad_norm": 1.333284854888916,
|
| 467 |
+
"learning_rate": 0.0002462293698980178,
|
| 468 |
+
"loss": 0.4671,
|
| 469 |
+
"mean_token_accuracy": 0.8901433110237121,
|
| 470 |
+
"num_tokens": 233769.0,
|
| 471 |
+
"step": 450
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"entropy": 0.4832085594534874,
|
| 475 |
+
"epoch": 1.1360544217687074,
|
| 476 |
+
"grad_norm": 0.8889069557189941,
|
| 477 |
+
"learning_rate": 0.00023546379277238105,
|
| 478 |
+
"loss": 0.4783,
|
| 479 |
+
"mean_token_accuracy": 0.8810128509998322,
|
| 480 |
+
"num_tokens": 238966.0,
|
| 481 |
+
"step": 460
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"entropy": 0.4265311576426029,
|
| 485 |
+
"epoch": 1.1607915893630179,
|
| 486 |
+
"grad_norm": 1.0676424503326416,
|
| 487 |
+
"learning_rate": 0.00022472520724375485,
|
| 488 |
+
"loss": 0.4427,
|
| 489 |
+
"mean_token_accuracy": 0.8863751858472824,
|
| 490 |
+
"num_tokens": 244110.0,
|
| 491 |
+
"step": 470
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"entropy": 0.458518086373806,
|
| 495 |
+
"epoch": 1.1855287569573283,
|
| 496 |
+
"grad_norm": 0.9971004128456116,
|
| 497 |
+
"learning_rate": 0.00021403355328468576,
|
| 498 |
+
"loss": 0.4366,
|
| 499 |
+
"mean_token_accuracy": 0.8863351345062256,
|
| 500 |
+
"num_tokens": 249342.0,
|
| 501 |
+
"step": 480
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"entropy": 0.46508664414286616,
|
| 505 |
+
"epoch": 1.210265924551639,
|
| 506 |
+
"grad_norm": 0.958321213722229,
|
| 507 |
+
"learning_rate": 0.00020340868372270449,
|
| 508 |
+
"loss": 0.4887,
|
| 509 |
+
"mean_token_accuracy": 0.8833811491727829,
|
| 510 |
+
"num_tokens": 254429.0,
|
| 511 |
+
"step": 490
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"entropy": 0.46396653950214384,
|
| 515 |
+
"epoch": 1.2350030921459494,
|
| 516 |
+
"grad_norm": 1.2300724983215332,
|
| 517 |
+
"learning_rate": 0.0001928703273765472,
|
| 518 |
+
"loss": 0.4232,
|
| 519 |
+
"mean_token_accuracy": 0.8947284638881683,
|
| 520 |
+
"num_tokens": 259668.0,
|
| 521 |
+
"step": 500
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"entropy": 0.4458997011184692,
|
| 525 |
+
"epoch": 1.2597402597402598,
|
| 526 |
+
"grad_norm": 1.1074163913726807,
|
| 527 |
+
"learning_rate": 0.00018243805242264366,
|
| 528 |
+
"loss": 0.4811,
|
| 529 |
+
"mean_token_accuracy": 0.8797710970044136,
|
| 530 |
+
"num_tokens": 264767.0,
|
| 531 |
+
"step": 510
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"entropy": 0.47095797434449194,
|
| 535 |
+
"epoch": 1.2844774273345703,
|
| 536 |
+
"grad_norm": 0.9398917555809021,
|
| 537 |
+
"learning_rate": 0.00017213123005989383,
|
| 538 |
+
"loss": 0.49,
|
| 539 |
+
"mean_token_accuracy": 0.8802127614617348,
|
| 540 |
+
"num_tokens": 269891.0,
|
| 541 |
+
"step": 520
|
| 542 |
+
},
|
| 543 |
+
{
|
| 544 |
+
"entropy": 0.4493381351232529,
|
| 545 |
+
"epoch": 1.3092145949288807,
|
| 546 |
+
"grad_norm": 1.0138375759124756,
|
| 547 |
+
"learning_rate": 0.00016196899854020337,
|
| 548 |
+
"loss": 0.4029,
|
| 549 |
+
"mean_token_accuracy": 0.8984167322516441,
|
| 550 |
+
"num_tokens": 275093.0,
|
| 551 |
+
"step": 530
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"entropy": 0.4118185345083475,
|
| 555 |
+
"epoch": 1.3339517625231911,
|
| 556 |
+
"grad_norm": 1.2301913499832153,
|
| 557 |
+
"learning_rate": 0.000151970227631567,
|
| 558 |
+
"loss": 0.4531,
|
| 559 |
+
"mean_token_accuracy": 0.8858078986406326,
|
| 560 |
+
"num_tokens": 280330.0,
|
| 561 |
+
"step": 540
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"entropy": 0.42357270009815695,
|
| 565 |
+
"epoch": 1.3586889301175016,
|
| 566 |
+
"grad_norm": 1.1774884462356567,
|
| 567 |
+
"learning_rate": 0.0001421534835796867,
|
| 568 |
+
"loss": 0.3996,
|
| 569 |
+
"mean_token_accuracy": 0.8919216230511665,
|
| 570 |
+
"num_tokens": 285557.0,
|
| 571 |
+
"step": 550
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"entropy": 0.4161256577819586,
|
| 575 |
+
"epoch": 1.383426097711812,
|
| 576 |
+
"grad_norm": 1.0505497455596924,
|
| 577 |
+
"learning_rate": 0.00013253699463318714,
|
| 578 |
+
"loss": 0.4248,
|
| 579 |
+
"mean_token_accuracy": 0.8909587010741233,
|
| 580 |
+
"num_tokens": 290827.0,
|
| 581 |
+
"step": 560
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"entropy": 0.41369549594819544,
|
| 585 |
+
"epoch": 1.4081632653061225,
|
| 586 |
+
"grad_norm": 0.9745755195617676,
|
| 587 |
+
"learning_rate": 0.00012313861719644102,
|
| 588 |
+
"loss": 0.4593,
|
| 589 |
+
"mean_token_accuracy": 0.884009575843811,
|
| 590 |
+
"num_tokens": 296091.0,
|
| 591 |
+
"step": 570
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"entropy": 0.4684952672570944,
|
| 595 |
+
"epoch": 1.432900432900433,
|
| 596 |
+
"grad_norm": 1.075348138809204,
|
| 597 |
+
"learning_rate": 0.00011397580267285432,
|
| 598 |
+
"loss": 0.4465,
|
| 599 |
+
"mean_token_accuracy": 0.8864868000149727,
|
| 600 |
+
"num_tokens": 301292.0,
|
| 601 |
+
"step": 580
|
| 602 |
+
},
|
| 603 |
+
{
|
| 604 |
+
"entropy": 0.44990680664777755,
|
| 605 |
+
"epoch": 1.4576376004947433,
|
| 606 |
+
"grad_norm": 0.8001469969749451,
|
| 607 |
+
"learning_rate": 0.00010506556506017992,
|
| 608 |
+
"loss": 0.4253,
|
| 609 |
+
"mean_token_accuracy": 0.8897192627191544,
|
| 610 |
+
"num_tokens": 306515.0,
|
| 611 |
+
"step": 590
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"entropy": 0.426817874237895,
|
| 615 |
+
"epoch": 1.4823747680890538,
|
| 616 |
+
"grad_norm": 1.2559151649475098,
|
| 617 |
+
"learning_rate": 9.642444935802744e-05,
|
| 618 |
+
"loss": 0.4213,
|
| 619 |
+
"mean_token_accuracy": 0.8939041405916214,
|
| 620 |
+
"num_tokens": 311722.0,
|
| 621 |
+
"step": 600
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"entropy": 0.4087653812021017,
|
| 625 |
+
"epoch": 1.5071119356833642,
|
| 626 |
+
"grad_norm": 0.9963752627372742,
|
| 627 |
+
"learning_rate": 8.806850084623528e-05,
|
| 628 |
+
"loss": 0.416,
|
| 629 |
+
"mean_token_accuracy": 0.8879835367202759,
|
| 630 |
+
"num_tokens": 316986.0,
|
| 631 |
+
"step": 610
|
| 632 |
+
},
|
| 633 |
+
{
|
| 634 |
+
"entropy": 0.45350427702069285,
|
| 635 |
+
"epoch": 1.5318491032776747,
|
| 636 |
+
"grad_norm": 0.8167953491210938,
|
| 637 |
+
"learning_rate": 8.001323529114718e-05,
|
| 638 |
+
"loss": 0.4558,
|
| 639 |
+
"mean_token_accuracy": 0.8845805168151856,
|
| 640 |
+
"num_tokens": 322177.0,
|
| 641 |
+
"step": 620
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"entropy": 0.4069512404501438,
|
| 645 |
+
"epoch": 1.556586270871985,
|
| 646 |
+
"grad_norm": 1.059950590133667,
|
| 647 |
+
"learning_rate": 7.227361013511899e-05,
|
| 648 |
+
"loss": 0.3814,
|
| 649 |
+
"mean_token_accuracy": 0.8984012454748154,
|
| 650 |
+
"num_tokens": 327385.0,
|
| 651 |
+
"step": 630
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"entropy": 0.4181812532246113,
|
| 655 |
+
"epoch": 1.5813234384662955,
|
| 656 |
+
"grad_norm": 1.0526669025421143,
|
| 657 |
+
"learning_rate": 6.48639967227489e-05,
|
| 658 |
+
"loss": 0.4644,
|
| 659 |
+
"mean_token_accuracy": 0.8847895339131355,
|
| 660 |
+
"num_tokens": 332519.0,
|
| 661 |
+
"step": 640
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"entropy": 0.44847704023122786,
|
| 665 |
+
"epoch": 1.606060606060606,
|
| 666 |
+
"grad_norm": 0.794501781463623,
|
| 667 |
+
"learning_rate": 5.779815361540727e-05,
|
| 668 |
+
"loss": 0.4456,
|
| 669 |
+
"mean_token_accuracy": 0.8857055723667144,
|
| 670 |
+
"num_tokens": 337750.0,
|
| 671 |
+
"step": 650
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"entropy": 0.4123352896422148,
|
| 675 |
+
"epoch": 1.6307977736549164,
|
| 676 |
+
"grad_norm": 0.7989002466201782,
|
| 677 |
+
"learning_rate": 5.108920104361259e-05,
|
| 678 |
+
"loss": 0.3813,
|
| 679 |
+
"mean_token_accuracy": 0.8978188335895538,
|
| 680 |
+
"num_tokens": 343062.0,
|
| 681 |
+
"step": 660
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"entropy": 0.38338451609015467,
|
| 685 |
+
"epoch": 1.6555349412492268,
|
| 686 |
+
"grad_norm": 0.8852431774139404,
|
| 687 |
+
"learning_rate": 4.4749596544695404e-05,
|
| 688 |
+
"loss": 0.3863,
|
| 689 |
+
"mean_token_accuracy": 0.8987199679017067,
|
| 690 |
+
"num_tokens": 348254.0,
|
| 691 |
+
"step": 670
|
| 692 |
+
},
|
| 693 |
+
{
|
| 694 |
+
"entropy": 0.37836207263171673,
|
| 695 |
+
"epoch": 1.6802721088435373,
|
| 696 |
+
"grad_norm": 1.5136176347732544,
|
| 697 |
+
"learning_rate": 3.879111183098477e-05,
|
| 698 |
+
"loss": 0.4221,
|
| 699 |
+
"mean_token_accuracy": 0.8940739586949349,
|
| 700 |
+
"num_tokens": 353426.0,
|
| 701 |
+
"step": 680
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"entropy": 0.4034986659884453,
|
| 705 |
+
"epoch": 1.7050092764378477,
|
| 706 |
+
"grad_norm": 1.0015009641647339,
|
| 707 |
+
"learning_rate": 3.322481093147178e-05,
|
| 708 |
+
"loss": 0.4001,
|
| 709 |
+
"mean_token_accuracy": 0.8967258155345916,
|
| 710 |
+
"num_tokens": 358532.0,
|
| 711 |
+
"step": 690
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"entropy": 0.4307912774384022,
|
| 715 |
+
"epoch": 1.7297464440321582,
|
| 716 |
+
"grad_norm": 1.02913236618042,
|
| 717 |
+
"learning_rate": 2.806102964753604e-05,
|
| 718 |
+
"loss": 0.4327,
|
| 719 |
+
"mean_token_accuracy": 0.8911660447716713,
|
| 720 |
+
"num_tokens": 363792.0,
|
| 721 |
+
"step": 700
|
| 722 |
+
},
|
| 723 |
+
{
|
| 724 |
+
"entropy": 0.4226231526583433,
|
| 725 |
+
"epoch": 1.7544836116264688,
|
| 726 |
+
"grad_norm": 1.016865849494934,
|
| 727 |
+
"learning_rate": 2.3309356360884327e-05,
|
| 728 |
+
"loss": 0.3895,
|
| 729 |
+
"mean_token_accuracy": 0.8997940927743912,
|
| 730 |
+
"num_tokens": 369023.0,
|
| 731 |
+
"step": 710
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"entropy": 0.3808727961033583,
|
| 735 |
+
"epoch": 1.7792207792207793,
|
| 736 |
+
"grad_norm": 0.8232676982879639,
|
| 737 |
+
"learning_rate": 1.8978614229337026e-05,
|
| 738 |
+
"loss": 0.3562,
|
| 739 |
+
"mean_token_accuracy": 0.9046193704009056,
|
| 740 |
+
"num_tokens": 374264.0,
|
| 741 |
+
"step": 720
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"entropy": 0.4109586663544178,
|
| 745 |
+
"epoch": 1.8039579468150897,
|
| 746 |
+
"grad_norm": 1.228324294090271,
|
| 747 |
+
"learning_rate": 1.5076844803522921e-05,
|
| 748 |
+
"loss": 0.4158,
|
| 749 |
+
"mean_token_accuracy": 0.8908816993236541,
|
| 750 |
+
"num_tokens": 379440.0,
|
| 751 |
+
"step": 730
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"entropy": 0.4193814411759377,
|
| 755 |
+
"epoch": 1.8286951144094001,
|
| 756 |
+
"grad_norm": 0.9970471858978271,
|
| 757 |
+
"learning_rate": 1.1611293094903358e-05,
|
| 758 |
+
"loss": 0.4075,
|
| 759 |
+
"mean_token_accuracy": 0.894894216954708,
|
| 760 |
+
"num_tokens": 384657.0,
|
| 761 |
+
"step": 740
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"entropy": 0.4284255560487509,
|
| 765 |
+
"epoch": 1.8534322820037106,
|
| 766 |
+
"grad_norm": 0.8334302306175232,
|
| 767 |
+
"learning_rate": 8.588394122852589e-06,
|
| 768 |
+
"loss": 0.5113,
|
| 769 |
+
"mean_token_accuracy": 0.8754843652248383,
|
| 770 |
+
"num_tokens": 389866.0,
|
| 771 |
+
"step": 750
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"entropy": 0.40159316882491114,
|
| 775 |
+
"epoch": 1.878169449598021,
|
| 776 |
+
"grad_norm": 1.1035089492797852,
|
| 777 |
+
"learning_rate": 6.0137609657741065e-06,
|
| 778 |
+
"loss": 0.4188,
|
| 779 |
+
"mean_token_accuracy": 0.8867701947689056,
|
| 780 |
+
"num_tokens": 395047.0,
|
| 781 |
+
"step": 760
|
| 782 |
+
},
|
| 783 |
+
{
|
| 784 |
+
"entropy": 0.4185076966881752,
|
| 785 |
+
"epoch": 1.9029066171923315,
|
| 786 |
+
"grad_norm": 0.9493175148963928,
|
| 787 |
+
"learning_rate": 3.892174338440136e-06,
|
| 788 |
+
"loss": 0.4018,
|
| 789 |
+
"mean_token_accuracy": 0.8947509944438934,
|
| 790 |
+
"num_tokens": 400300.0,
|
| 791 |
+
"step": 770
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"entropy": 0.4141177587211132,
|
| 795 |
+
"epoch": 1.927643784786642,
|
| 796 |
+
"grad_norm": 0.8785578608512878,
|
| 797 |
+
"learning_rate": 2.2275737149082266e-06,
|
| 798 |
+
"loss": 0.4322,
|
| 799 |
+
"mean_token_accuracy": 0.8923440754413605,
|
| 800 |
+
"num_tokens": 405492.0,
|
| 801 |
+
"step": 780
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"entropy": 0.43889166191220286,
|
| 805 |
+
"epoch": 1.9523809523809523,
|
| 806 |
+
"grad_norm": 0.8836324214935303,
|
| 807 |
+
"learning_rate": 1.0230500134976728e-06,
|
| 808 |
+
"loss": 0.4572,
|
| 809 |
+
"mean_token_accuracy": 0.8833968549966812,
|
| 810 |
+
"num_tokens": 410763.0,
|
| 811 |
+
"step": 790
|
| 812 |
+
},
|
| 813 |
+
{
|
| 814 |
+
"entropy": 0.3942453060299158,
|
| 815 |
+
"epoch": 1.977118119975263,
|
| 816 |
+
"grad_norm": 0.9182628989219666,
|
| 817 |
+
"learning_rate": 2.808398574093984e-07,
|
| 818 |
+
"loss": 0.3741,
|
| 819 |
+
"mean_token_accuracy": 0.90195052921772,
|
| 820 |
+
"num_tokens": 415888.0,
|
| 821 |
+
"step": 800
|
| 822 |
+
},
|
| 823 |
+
{
|
| 824 |
+
"entropy": 0.43775520332761714,
|
| 825 |
+
"epoch": 2.0,
|
| 826 |
+
"grad_norm": 2.5363073348999023,
|
| 827 |
+
"learning_rate": 2.3214216457456692e-09,
|
| 828 |
+
"loss": 0.4476,
|
| 829 |
+
"mean_token_accuracy": 0.8913259683428584,
|
| 830 |
+
"num_tokens": 420772.0,
|
| 831 |
+
"step": 810
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.0,
|
| 835 |
+
"eval_entropy": 0.5558884469999208,
|
| 836 |
+
"eval_loss": 0.8108042478561401,
|
| 837 |
+
"eval_mean_token_accuracy": 0.8297225495179494,
|
| 838 |
+
"eval_num_tokens": 420772.0,
|
| 839 |
+
"eval_runtime": 125.46,
|
| 840 |
+
"eval_samples_per_second": 1.435,
|
| 841 |
+
"eval_steps_per_second": 1.435,
|
| 842 |
+
"step": 810
|
| 843 |
+
}
|
| 844 |
+
],
|
| 845 |
+
"logging_steps": 10,
|
| 846 |
+
"max_steps": 810,
|
| 847 |
+
"num_input_tokens_seen": 0,
|
| 848 |
+
"num_train_epochs": 2,
|
| 849 |
+
"save_steps": 500,
|
| 850 |
+
"stateful_callbacks": {
|
| 851 |
+
"TrainerControl": {
|
| 852 |
+
"args": {
|
| 853 |
+
"should_epoch_stop": false,
|
| 854 |
+
"should_evaluate": false,
|
| 855 |
+
"should_log": false,
|
| 856 |
+
"should_save": true,
|
| 857 |
+
"should_training_stop": true
|
| 858 |
+
},
|
| 859 |
+
"attributes": {}
|
| 860 |
+
}
|
| 861 |
+
},
|
| 862 |
+
"total_flos": 9506836340035584.0,
|
| 863 |
+
"train_batch_size": 1,
|
| 864 |
+
"trial_name": null,
|
| 865 |
+
"trial_params": null
|
| 866 |
+
}
|
checkpoint-810/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:602933e14cee181956b6ba86efd1c972acb28b64c16c9da71ac0844bc4a294d9
|
| 3 |
+
size 6225
|
checkpoint-810/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|