Upload folder using huggingface_hub
Browse files- README.md +34 -0
- adapter_config.json +26 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- trainer_state.json +595 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- quant_method: bitsandbytes
|
| 9 |
+
- load_in_8bit: False
|
| 10 |
+
- load_in_4bit: True
|
| 11 |
+
- llm_int8_threshold: 6.0
|
| 12 |
+
- llm_int8_skip_modules: None
|
| 13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 14 |
+
- llm_int8_has_fp16_weight: False
|
| 15 |
+
- bnb_4bit_quant_type: nf4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float16
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: False
|
| 22 |
+
- load_in_4bit: True
|
| 23 |
+
- llm_int8_threshold: 6.0
|
| 24 |
+
- llm_int8_skip_modules: None
|
| 25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 26 |
+
- llm_int8_has_fp16_weight: False
|
| 27 |
+
- bnb_4bit_quant_type: nf4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float16
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.6.0.dev0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.6.0.dev0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "PY007/TinyLlama-1.1B-step-50K-105b",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"up_proj",
|
| 19 |
+
"o_proj",
|
| 20 |
+
"k_proj",
|
| 21 |
+
"down_proj",
|
| 22 |
+
"gate_proj",
|
| 23 |
+
"v_proj"
|
| 24 |
+
],
|
| 25 |
+
"task_type": "CAUSAL_LM"
|
| 26 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2366632691f0caebb1875143b0ff2df47780829e6104bacda9a5bd7ed63663c4
|
| 3 |
+
size 201961693
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bfc89dd0802df061b3c0478a7472692faac92080167a7d240abe9919b2bd452
|
| 3 |
+
size 403890693
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a537a0c558a32380d7f6d1f0733c99d073f4b2d7677e661c600248e6c2409014
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7db45d30e786cecd0b5abfa18608b3b6e5dd4808002cfdb6aae9f52c90ccb40a
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"clean_up_tokenization_spaces": false,
|
| 11 |
+
"eos_token": {
|
| 12 |
+
"__type": "AddedToken",
|
| 13 |
+
"content": "</s>",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": false,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false
|
| 18 |
+
},
|
| 19 |
+
"legacy": false,
|
| 20 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 21 |
+
"pad_token": null,
|
| 22 |
+
"padding_side": "right",
|
| 23 |
+
"sp_model_kwargs": {},
|
| 24 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 25 |
+
"unk_token": {
|
| 26 |
+
"__type": "AddedToken",
|
| 27 |
+
"content": "<unk>",
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"normalized": false,
|
| 30 |
+
"rstrip": false,
|
| 31 |
+
"single_word": false
|
| 32 |
+
},
|
| 33 |
+
"use_default_system_prompt": true
|
| 34 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,595 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.9825242718446603,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 192,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.03,
|
| 13 |
+
"learning_rate": 6.666666666666667e-06,
|
| 14 |
+
"loss": 2.1983,
|
| 15 |
+
"step": 2
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.06,
|
| 19 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 20 |
+
"loss": 2.3655,
|
| 21 |
+
"step": 4
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.09,
|
| 25 |
+
"learning_rate": 2e-05,
|
| 26 |
+
"loss": 2.4304,
|
| 27 |
+
"step": 6
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.12,
|
| 31 |
+
"learning_rate": 1.999429490929718e-05,
|
| 32 |
+
"loss": 2.5673,
|
| 33 |
+
"step": 8
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.16,
|
| 37 |
+
"learning_rate": 1.9977186146800707e-05,
|
| 38 |
+
"loss": 2.6146,
|
| 39 |
+
"step": 10
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.19,
|
| 43 |
+
"learning_rate": 1.994869323391895e-05,
|
| 44 |
+
"loss": 2.6325,
|
| 45 |
+
"step": 12
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.22,
|
| 49 |
+
"learning_rate": 1.990884868158239e-05,
|
| 50 |
+
"loss": 2.678,
|
| 51 |
+
"step": 14
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.25,
|
| 55 |
+
"learning_rate": 1.985769795314804e-05,
|
| 56 |
+
"loss": 3.0644,
|
| 57 |
+
"step": 16
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.28,
|
| 61 |
+
"learning_rate": 1.9795299412524948e-05,
|
| 62 |
+
"loss": 2.1676,
|
| 63 |
+
"step": 18
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.31,
|
| 67 |
+
"learning_rate": 1.9721724257579907e-05,
|
| 68 |
+
"loss": 2.2736,
|
| 69 |
+
"step": 20
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.34,
|
| 73 |
+
"learning_rate": 1.963705643889941e-05,
|
| 74 |
+
"loss": 2.2697,
|
| 75 |
+
"step": 22
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.37,
|
| 79 |
+
"learning_rate": 1.954139256400049e-05,
|
| 80 |
+
"loss": 2.5691,
|
| 81 |
+
"step": 24
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.4,
|
| 85 |
+
"learning_rate": 1.9434841787099804e-05,
|
| 86 |
+
"loss": 2.5865,
|
| 87 |
+
"step": 26
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.43,
|
| 91 |
+
"learning_rate": 1.9317525684566686e-05,
|
| 92 |
+
"loss": 2.6867,
|
| 93 |
+
"step": 28
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.47,
|
| 97 |
+
"learning_rate": 1.918957811620231e-05,
|
| 98 |
+
"loss": 2.6541,
|
| 99 |
+
"step": 30
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.5,
|
| 103 |
+
"learning_rate": 1.9051145072503216e-05,
|
| 104 |
+
"loss": 3.1472,
|
| 105 |
+
"step": 32
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.53,
|
| 109 |
+
"learning_rate": 1.8902384508083518e-05,
|
| 110 |
+
"loss": 2.1783,
|
| 111 |
+
"step": 34
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.56,
|
| 115 |
+
"learning_rate": 1.8743466161445823e-05,
|
| 116 |
+
"loss": 2.3746,
|
| 117 |
+
"step": 36
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.59,
|
| 121 |
+
"learning_rate": 1.857457136130651e-05,
|
| 122 |
+
"loss": 2.5552,
|
| 123 |
+
"step": 38
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.62,
|
| 127 |
+
"learning_rate": 1.839589281969639e-05,
|
| 128 |
+
"loss": 2.486,
|
| 129 |
+
"step": 40
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.65,
|
| 133 |
+
"learning_rate": 1.8207634412072765e-05,
|
| 134 |
+
"loss": 2.5864,
|
| 135 |
+
"step": 42
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.68,
|
| 139 |
+
"learning_rate": 1.8010010944693846e-05,
|
| 140 |
+
"loss": 2.55,
|
| 141 |
+
"step": 44
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.71,
|
| 145 |
+
"learning_rate": 1.780324790952092e-05,
|
| 146 |
+
"loss": 2.5458,
|
| 147 |
+
"step": 46
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.75,
|
| 151 |
+
"learning_rate": 1.758758122692791e-05,
|
| 152 |
+
"loss": 2.8695,
|
| 153 |
+
"step": 48
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.78,
|
| 157 |
+
"learning_rate": 1.7363256976511972e-05,
|
| 158 |
+
"loss": 2.2066,
|
| 159 |
+
"step": 50
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.81,
|
| 163 |
+
"learning_rate": 1.7130531116312202e-05,
|
| 164 |
+
"loss": 2.3567,
|
| 165 |
+
"step": 52
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.84,
|
| 169 |
+
"learning_rate": 1.688966919075687e-05,
|
| 170 |
+
"loss": 2.3726,
|
| 171 |
+
"step": 54
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.87,
|
| 175 |
+
"learning_rate": 1.6640946027672395e-05,
|
| 176 |
+
"loss": 2.4341,
|
| 177 |
+
"step": 56
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.9,
|
| 181 |
+
"learning_rate": 1.6384645424699835e-05,
|
| 182 |
+
"loss": 2.6069,
|
| 183 |
+
"step": 58
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.93,
|
| 187 |
+
"learning_rate": 1.612105982547663e-05,
|
| 188 |
+
"loss": 2.4177,
|
| 189 |
+
"step": 60
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.96,
|
| 193 |
+
"learning_rate": 1.5850489985953076e-05,
|
| 194 |
+
"loss": 2.6455,
|
| 195 |
+
"step": 62
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.99,
|
| 199 |
+
"learning_rate": 1.5573244631224364e-05,
|
| 200 |
+
"loss": 2.7209,
|
| 201 |
+
"step": 64
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 1.03,
|
| 205 |
+
"learning_rate": 1.5289640103269626e-05,
|
| 206 |
+
"loss": 2.2111,
|
| 207 |
+
"step": 66
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 1.06,
|
| 211 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 212 |
+
"loss": 2.3059,
|
| 213 |
+
"step": 68
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 1.09,
|
| 217 |
+
"learning_rate": 1.4704654806027558e-05,
|
| 218 |
+
"loss": 2.2463,
|
| 219 |
+
"step": 70
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 1.12,
|
| 223 |
+
"learning_rate": 1.4403941515576344e-05,
|
| 224 |
+
"loss": 2.4033,
|
| 225 |
+
"step": 72
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 1.15,
|
| 229 |
+
"learning_rate": 1.4098203247965876e-05,
|
| 230 |
+
"loss": 2.5915,
|
| 231 |
+
"step": 74
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 1.18,
|
| 235 |
+
"learning_rate": 1.3787788856105762e-05,
|
| 236 |
+
"loss": 2.4161,
|
| 237 |
+
"step": 76
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 1.21,
|
| 241 |
+
"learning_rate": 1.3473052528448203e-05,
|
| 242 |
+
"loss": 2.5666,
|
| 243 |
+
"step": 78
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 1.24,
|
| 247 |
+
"learning_rate": 1.3154353384852559e-05,
|
| 248 |
+
"loss": 2.4965,
|
| 249 |
+
"step": 80
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 1.27,
|
| 253 |
+
"learning_rate": 1.283205506682304e-05,
|
| 254 |
+
"loss": 2.1462,
|
| 255 |
+
"step": 82
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 1.3,
|
| 259 |
+
"learning_rate": 1.2506525322587207e-05,
|
| 260 |
+
"loss": 2.2062,
|
| 261 |
+
"step": 84
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 1.34,
|
| 265 |
+
"learning_rate": 1.2178135587488515e-05,
|
| 266 |
+
"loss": 2.3648,
|
| 267 |
+
"step": 86
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 1.37,
|
| 271 |
+
"learning_rate": 1.1847260560171895e-05,
|
| 272 |
+
"loss": 2.3471,
|
| 273 |
+
"step": 88
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 1.4,
|
| 277 |
+
"learning_rate": 1.1514277775045768e-05,
|
| 278 |
+
"loss": 2.5153,
|
| 279 |
+
"step": 90
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 1.43,
|
| 283 |
+
"learning_rate": 1.1179567171508463e-05,
|
| 284 |
+
"loss": 2.3952,
|
| 285 |
+
"step": 92
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 1.46,
|
| 289 |
+
"learning_rate": 1.0843510660430447e-05,
|
| 290 |
+
"loss": 2.3512,
|
| 291 |
+
"step": 94
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 1.49,
|
| 295 |
+
"learning_rate": 1.0506491688387128e-05,
|
| 296 |
+
"loss": 2.6351,
|
| 297 |
+
"step": 96
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 1.52,
|
| 301 |
+
"learning_rate": 1.0168894800139311e-05,
|
| 302 |
+
"loss": 2.3342,
|
| 303 |
+
"step": 98
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 1.55,
|
| 307 |
+
"learning_rate": 9.83110519986069e-06,
|
| 308 |
+
"loss": 2.1042,
|
| 309 |
+
"step": 100
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 1.58,
|
| 313 |
+
"learning_rate": 9.493508311612874e-06,
|
| 314 |
+
"loss": 2.2379,
|
| 315 |
+
"step": 102
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 1.62,
|
| 319 |
+
"learning_rate": 9.156489339569555e-06,
|
| 320 |
+
"loss": 2.417,
|
| 321 |
+
"step": 104
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 1.65,
|
| 325 |
+
"learning_rate": 8.820432828491542e-06,
|
| 326 |
+
"loss": 2.3971,
|
| 327 |
+
"step": 106
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 1.68,
|
| 331 |
+
"learning_rate": 8.485722224954237e-06,
|
| 332 |
+
"loss": 2.535,
|
| 333 |
+
"step": 108
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.71,
|
| 337 |
+
"learning_rate": 8.15273943982811e-06,
|
| 338 |
+
"loss": 2.4891,
|
| 339 |
+
"step": 110
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.74,
|
| 343 |
+
"learning_rate": 7.821864412511485e-06,
|
| 344 |
+
"loss": 2.4034,
|
| 345 |
+
"step": 112
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.77,
|
| 349 |
+
"learning_rate": 7.493474677412795e-06,
|
| 350 |
+
"loss": 2.2419,
|
| 351 |
+
"step": 114
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.8,
|
| 355 |
+
"learning_rate": 7.16794493317696e-06,
|
| 356 |
+
"loss": 2.2467,
|
| 357 |
+
"step": 116
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.83,
|
| 361 |
+
"learning_rate": 6.845646615147445e-06,
|
| 362 |
+
"loss": 2.4427,
|
| 363 |
+
"step": 118
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.86,
|
| 367 |
+
"learning_rate": 6.526947471551799e-06,
|
| 368 |
+
"loss": 2.3395,
|
| 369 |
+
"step": 120
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.9,
|
| 373 |
+
"learning_rate": 6.21221114389424e-06,
|
| 374 |
+
"loss": 2.3874,
|
| 375 |
+
"step": 122
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.93,
|
| 379 |
+
"learning_rate": 5.901796752034128e-06,
|
| 380 |
+
"loss": 2.2733,
|
| 381 |
+
"step": 124
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.96,
|
| 385 |
+
"learning_rate": 5.5960584844236565e-06,
|
| 386 |
+
"loss": 2.5074,
|
| 387 |
+
"step": 126
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.99,
|
| 391 |
+
"learning_rate": 5.295345193972445e-06,
|
| 392 |
+
"loss": 2.3718,
|
| 393 |
+
"step": 128
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 2.02,
|
| 397 |
+
"learning_rate": 5.000000000000003e-06,
|
| 398 |
+
"loss": 2.0442,
|
| 399 |
+
"step": 130
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 2.05,
|
| 403 |
+
"learning_rate": 4.710359896730379e-06,
|
| 404 |
+
"loss": 2.276,
|
| 405 |
+
"step": 132
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 2.08,
|
| 409 |
+
"learning_rate": 4.426755368775637e-06,
|
| 410 |
+
"loss": 2.3767,
|
| 411 |
+
"step": 134
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 2.11,
|
| 415 |
+
"learning_rate": 4.149510014046922e-06,
|
| 416 |
+
"loss": 2.3219,
|
| 417 |
+
"step": 136
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 2.14,
|
| 421 |
+
"learning_rate": 3.878940174523371e-06,
|
| 422 |
+
"loss": 2.4413,
|
| 423 |
+
"step": 138
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 2.17,
|
| 427 |
+
"learning_rate": 3.6153545753001663e-06,
|
| 428 |
+
"loss": 2.3952,
|
| 429 |
+
"step": 140
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 2.21,
|
| 433 |
+
"learning_rate": 3.3590539723276083e-06,
|
| 434 |
+
"loss": 2.4534,
|
| 435 |
+
"step": 142
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 2.24,
|
| 439 |
+
"learning_rate": 3.110330809243134e-06,
|
| 440 |
+
"loss": 2.4202,
|
| 441 |
+
"step": 144
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 2.27,
|
| 445 |
+
"learning_rate": 2.869468883687798e-06,
|
| 446 |
+
"loss": 2.0796,
|
| 447 |
+
"step": 146
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 2.3,
|
| 451 |
+
"learning_rate": 2.6367430234880286e-06,
|
| 452 |
+
"loss": 2.1677,
|
| 453 |
+
"step": 148
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 2.33,
|
| 457 |
+
"learning_rate": 2.4124187730720916e-06,
|
| 458 |
+
"loss": 2.3557,
|
| 459 |
+
"step": 150
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 2.36,
|
| 463 |
+
"learning_rate": 2.196752090479083e-06,
|
| 464 |
+
"loss": 2.298,
|
| 465 |
+
"step": 152
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 2.39,
|
| 469 |
+
"learning_rate": 1.9899890553061565e-06,
|
| 470 |
+
"loss": 2.3278,
|
| 471 |
+
"step": 154
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 2.42,
|
| 475 |
+
"learning_rate": 1.7923655879272395e-06,
|
| 476 |
+
"loss": 2.2523,
|
| 477 |
+
"step": 156
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 2.45,
|
| 481 |
+
"learning_rate": 1.60410718030361e-06,
|
| 482 |
+
"loss": 2.403,
|
| 483 |
+
"step": 158
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 2.49,
|
| 487 |
+
"learning_rate": 1.425428638693489e-06,
|
| 488 |
+
"loss": 2.3144,
|
| 489 |
+
"step": 160
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 2.52,
|
| 493 |
+
"learning_rate": 1.2565338385541792e-06,
|
| 494 |
+
"loss": 2.1642,
|
| 495 |
+
"step": 162
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 2.55,
|
| 499 |
+
"learning_rate": 1.097615491916485e-06,
|
| 500 |
+
"loss": 2.2077,
|
| 501 |
+
"step": 164
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 2.58,
|
| 505 |
+
"learning_rate": 9.488549274967873e-07,
|
| 506 |
+
"loss": 2.3047,
|
| 507 |
+
"step": 166
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 2.61,
|
| 511 |
+
"learning_rate": 8.10421883797694e-07,
|
| 512 |
+
"loss": 2.2174,
|
| 513 |
+
"step": 168
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 2.64,
|
| 517 |
+
"learning_rate": 6.824743154333157e-07,
|
| 518 |
+
"loss": 2.4378,
|
| 519 |
+
"step": 170
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 2.67,
|
| 523 |
+
"learning_rate": 5.651582129001987e-07,
|
| 524 |
+
"loss": 2.3691,
|
| 525 |
+
"step": 172
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 2.7,
|
| 529 |
+
"learning_rate": 4.5860743599951186e-07,
|
| 530 |
+
"loss": 2.3489,
|
| 531 |
+
"step": 174
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 2.73,
|
| 535 |
+
"learning_rate": 3.629435611005916e-07,
|
| 536 |
+
"loss": 2.4012,
|
| 537 |
+
"step": 176
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 2.77,
|
| 541 |
+
"learning_rate": 2.7827574242009434e-07,
|
| 542 |
+
"loss": 2.1272,
|
| 543 |
+
"step": 178
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 2.8,
|
| 547 |
+
"learning_rate": 2.0470058747505516e-07,
|
| 548 |
+
"loss": 2.1446,
|
| 549 |
+
"step": 180
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 2.83,
|
| 553 |
+
"learning_rate": 1.4230204685196202e-07,
|
| 554 |
+
"loss": 2.1542,
|
| 555 |
+
"step": 182
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 2.86,
|
| 559 |
+
"learning_rate": 9.11513184176116e-08,
|
| 560 |
+
"loss": 2.2928,
|
| 561 |
+
"step": 184
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 2.89,
|
| 565 |
+
"learning_rate": 5.1306766081048456e-08,
|
| 566 |
+
"loss": 2.4749,
|
| 567 |
+
"step": 186
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 2.92,
|
| 571 |
+
"learning_rate": 2.2813853199292745e-08,
|
| 572 |
+
"loss": 2.3253,
|
| 573 |
+
"step": 188
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 2.95,
|
| 577 |
+
"learning_rate": 5.705090702819993e-09,
|
| 578 |
+
"loss": 2.2604,
|
| 579 |
+
"step": 190
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 2.98,
|
| 583 |
+
"learning_rate": 0.0,
|
| 584 |
+
"loss": 2.2712,
|
| 585 |
+
"step": 192
|
| 586 |
+
}
|
| 587 |
+
],
|
| 588 |
+
"logging_steps": 2,
|
| 589 |
+
"max_steps": 192,
|
| 590 |
+
"num_train_epochs": 3,
|
| 591 |
+
"save_steps": 64,
|
| 592 |
+
"total_flos": 6344939734437888.0,
|
| 593 |
+
"trial_name": null,
|
| 594 |
+
"trial_params": null
|
| 595 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dfd52750c9c510b5182d4fe6169babb15afed71cd571c6d3e58ec1daa374704
|
| 3 |
+
size 4027
|