Commit
·
3c2b56c
1
Parent(s):
df8881d
Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +23 -0
- adapter_model.bin +3 -0
- checkpoint-4122/README.md +34 -0
- checkpoint-4122/adapter_config.json +23 -0
- checkpoint-4122/adapter_model.bin +3 -0
- checkpoint-4122/optimizer.pt +3 -0
- checkpoint-4122/rng_state.pth +3 -0
- checkpoint-4122/scheduler.pt +3 -0
- checkpoint-4122/special_tokens_map.json +29 -0
- checkpoint-4122/tokenizer.json +0 -0
- checkpoint-4122/tokenizer.model +3 -0
- checkpoint-4122/tokenizer_config.json +44 -0
- checkpoint-4122/trainer_state.json +1003 -0
- checkpoint-4122/training_args.bin +3 -0
- special_tokens_map.json +29 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +44 -0
- training_args.bin +3 -0
- training_params.json +1 -0
README.md
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- autotrain
|
| 4 |
+
- text-generation
|
| 5 |
+
widget:
|
| 6 |
+
- text: "I love AutoTrain because "
|
| 7 |
+
---
|
| 8 |
+
|
| 9 |
+
# Model Trained Using AutoTrain
|
adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "Intel/neural-chat-7b-v3-1",
|
| 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": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 16,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"k_proj",
|
| 20 |
+
"o_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef04c3727c11199ab341bb57910cbd50a61ec95a0117a88268911768f2579add
|
| 3 |
+
size 54618762
|
checkpoint-4122/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: True
|
| 10 |
+
- load_in_4bit: False
|
| 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: fp4
|
| 16 |
+
- bnb_4bit_use_double_quant: False
|
| 17 |
+
- bnb_4bit_compute_dtype: float32
|
| 18 |
+
|
| 19 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 20 |
+
- quant_method: bitsandbytes
|
| 21 |
+
- load_in_8bit: True
|
| 22 |
+
- load_in_4bit: False
|
| 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: fp4
|
| 28 |
+
- bnb_4bit_use_double_quant: False
|
| 29 |
+
- bnb_4bit_compute_dtype: float32
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.5.0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.5.0
|
checkpoint-4122/adapter_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "Intel/neural-chat-7b-v3-1",
|
| 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": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 16,
|
| 15 |
+
"revision": null,
|
| 16 |
+
"target_modules": [
|
| 17 |
+
"q_proj",
|
| 18 |
+
"v_proj",
|
| 19 |
+
"k_proj",
|
| 20 |
+
"o_proj"
|
| 21 |
+
],
|
| 22 |
+
"task_type": "CAUSAL_LM"
|
| 23 |
+
}
|
checkpoint-4122/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef04c3727c11199ab341bb57910cbd50a61ec95a0117a88268911768f2579add
|
| 3 |
+
size 54618762
|
checkpoint-4122/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ece8c0ee1b72ebebf9f2e19e27fdcd5613f438c94de317cfd6ac0c2471dd69b
|
| 3 |
+
size 4072
|
checkpoint-4122/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d91923fbd95309beca79b3cc9cb6a9510e28d9b6600d0d57b5b45838d2169f26
|
| 3 |
+
size 14180
|
checkpoint-4122/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8d7cc5a88feb508f7970570ff47fdb4c737f262022a3bae1d220c4e6160b7d2
|
| 3 |
+
size 1064
|
checkpoint-4122/special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": "</s>",
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
checkpoint-4122/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-4122/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-4122/tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [
|
| 29 |
+
"<unk>",
|
| 30 |
+
"<s>",
|
| 31 |
+
"</s>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": "<s>",
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"eos_token": "</s>",
|
| 36 |
+
"legacy": true,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": true
|
| 44 |
+
}
|
checkpoint-4122/trainer_state.json
ADDED
|
@@ -0,0 +1,1003 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 2.3435,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 4122,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.01,
|
| 13 |
+
"learning_rate": 3.833333333333334e-06,
|
| 14 |
+
"loss": 1.5323,
|
| 15 |
+
"step": 25
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 8.000000000000001e-06,
|
| 20 |
+
"loss": 1.5524,
|
| 21 |
+
"step": 50
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.02,
|
| 25 |
+
"learning_rate": 1.2166666666666668e-05,
|
| 26 |
+
"loss": 1.4547,
|
| 27 |
+
"step": 75
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.03,
|
| 31 |
+
"learning_rate": 1.6333333333333335e-05,
|
| 32 |
+
"loss": 1.4912,
|
| 33 |
+
"step": 100
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.03,
|
| 37 |
+
"learning_rate": 2.05e-05,
|
| 38 |
+
"loss": 1.4495,
|
| 39 |
+
"step": 125
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.04,
|
| 43 |
+
"learning_rate": 2.466666666666667e-05,
|
| 44 |
+
"loss": 1.5684,
|
| 45 |
+
"step": 150
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.04,
|
| 49 |
+
"learning_rate": 2.8833333333333334e-05,
|
| 50 |
+
"loss": 1.4968,
|
| 51 |
+
"step": 175
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.05,
|
| 55 |
+
"learning_rate": 3.3e-05,
|
| 56 |
+
"loss": 1.502,
|
| 57 |
+
"step": 200
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.06,
|
| 61 |
+
"learning_rate": 3.7166666666666664e-05,
|
| 62 |
+
"loss": 1.5562,
|
| 63 |
+
"step": 225
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.06,
|
| 67 |
+
"learning_rate": 4.133333333333333e-05,
|
| 68 |
+
"loss": 1.4938,
|
| 69 |
+
"step": 250
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.07,
|
| 73 |
+
"learning_rate": 4.55e-05,
|
| 74 |
+
"loss": 1.5588,
|
| 75 |
+
"step": 275
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.07,
|
| 79 |
+
"learning_rate": 4.966666666666667e-05,
|
| 80 |
+
"loss": 1.4588,
|
| 81 |
+
"step": 300
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.08,
|
| 85 |
+
"learning_rate": 5.383333333333334e-05,
|
| 86 |
+
"loss": 1.5069,
|
| 87 |
+
"step": 325
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.09,
|
| 91 |
+
"learning_rate": 5.8e-05,
|
| 92 |
+
"loss": 1.4487,
|
| 93 |
+
"step": 350
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.09,
|
| 97 |
+
"learning_rate": 6.216666666666667e-05,
|
| 98 |
+
"loss": 1.4181,
|
| 99 |
+
"step": 375
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.1,
|
| 103 |
+
"learning_rate": 6.633333333333334e-05,
|
| 104 |
+
"loss": 1.4582,
|
| 105 |
+
"step": 400
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.11,
|
| 109 |
+
"learning_rate": 7.033333333333334e-05,
|
| 110 |
+
"loss": 1.4703,
|
| 111 |
+
"step": 425
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.11,
|
| 115 |
+
"learning_rate": 7.450000000000001e-05,
|
| 116 |
+
"loss": 1.4574,
|
| 117 |
+
"step": 450
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.12,
|
| 121 |
+
"learning_rate": 7.866666666666666e-05,
|
| 122 |
+
"loss": 1.4634,
|
| 123 |
+
"step": 475
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.12,
|
| 127 |
+
"learning_rate": 8.283333333333335e-05,
|
| 128 |
+
"loss": 1.4442,
|
| 129 |
+
"step": 500
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.13,
|
| 133 |
+
"learning_rate": 8.7e-05,
|
| 134 |
+
"loss": 1.4699,
|
| 135 |
+
"step": 525
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.14,
|
| 139 |
+
"learning_rate": 9.116666666666667e-05,
|
| 140 |
+
"loss": 1.3843,
|
| 141 |
+
"step": 550
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.14,
|
| 145 |
+
"learning_rate": 9.533333333333334e-05,
|
| 146 |
+
"loss": 1.3936,
|
| 147 |
+
"step": 575
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.15,
|
| 151 |
+
"learning_rate": 9.95e-05,
|
| 152 |
+
"loss": 1.4198,
|
| 153 |
+
"step": 600
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.16,
|
| 157 |
+
"learning_rate": 0.00010366666666666666,
|
| 158 |
+
"loss": 1.408,
|
| 159 |
+
"step": 625
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.16,
|
| 163 |
+
"learning_rate": 0.00010783333333333334,
|
| 164 |
+
"loss": 1.3788,
|
| 165 |
+
"step": 650
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.17,
|
| 169 |
+
"learning_rate": 0.00011200000000000001,
|
| 170 |
+
"loss": 1.4037,
|
| 171 |
+
"step": 675
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.17,
|
| 175 |
+
"learning_rate": 0.00011616666666666667,
|
| 176 |
+
"loss": 1.374,
|
| 177 |
+
"step": 700
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.18,
|
| 181 |
+
"learning_rate": 0.00012033333333333335,
|
| 182 |
+
"loss": 1.3996,
|
| 183 |
+
"step": 725
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.19,
|
| 187 |
+
"learning_rate": 0.00012450000000000002,
|
| 188 |
+
"loss": 1.3591,
|
| 189 |
+
"step": 750
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.19,
|
| 193 |
+
"learning_rate": 0.00012866666666666666,
|
| 194 |
+
"loss": 1.3733,
|
| 195 |
+
"step": 775
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.2,
|
| 199 |
+
"learning_rate": 0.00013283333333333335,
|
| 200 |
+
"loss": 1.3037,
|
| 201 |
+
"step": 800
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.21,
|
| 205 |
+
"learning_rate": 0.00013700000000000002,
|
| 206 |
+
"loss": 1.3285,
|
| 207 |
+
"step": 825
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.21,
|
| 211 |
+
"learning_rate": 0.00014116666666666666,
|
| 212 |
+
"loss": 1.3496,
|
| 213 |
+
"step": 850
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.22,
|
| 217 |
+
"learning_rate": 0.00014533333333333333,
|
| 218 |
+
"loss": 1.3337,
|
| 219 |
+
"step": 875
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.23,
|
| 223 |
+
"learning_rate": 0.00014950000000000003,
|
| 224 |
+
"loss": 1.3605,
|
| 225 |
+
"step": 900
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.23,
|
| 229 |
+
"learning_rate": 0.00015366666666666667,
|
| 230 |
+
"loss": 1.302,
|
| 231 |
+
"step": 925
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.24,
|
| 235 |
+
"learning_rate": 0.00015783333333333334,
|
| 236 |
+
"loss": 1.3118,
|
| 237 |
+
"step": 950
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.24,
|
| 241 |
+
"learning_rate": 0.000162,
|
| 242 |
+
"loss": 1.3104,
|
| 243 |
+
"step": 975
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.25,
|
| 247 |
+
"learning_rate": 0.00016616666666666668,
|
| 248 |
+
"loss": 1.2881,
|
| 249 |
+
"step": 1000
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.26,
|
| 253 |
+
"learning_rate": 0.00017033333333333334,
|
| 254 |
+
"loss": 1.2606,
|
| 255 |
+
"step": 1025
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.26,
|
| 259 |
+
"learning_rate": 0.0001745,
|
| 260 |
+
"loss": 1.2912,
|
| 261 |
+
"step": 1050
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.27,
|
| 265 |
+
"learning_rate": 0.00017866666666666668,
|
| 266 |
+
"loss": 1.2651,
|
| 267 |
+
"step": 1075
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.28,
|
| 271 |
+
"learning_rate": 0.00018283333333333335,
|
| 272 |
+
"loss": 1.3028,
|
| 273 |
+
"step": 1100
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.28,
|
| 277 |
+
"learning_rate": 0.00018700000000000002,
|
| 278 |
+
"loss": 1.2867,
|
| 279 |
+
"step": 1125
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.29,
|
| 283 |
+
"learning_rate": 0.00019116666666666666,
|
| 284 |
+
"loss": 1.2531,
|
| 285 |
+
"step": 1150
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.29,
|
| 289 |
+
"learning_rate": 0.00019533333333333336,
|
| 290 |
+
"loss": 1.2456,
|
| 291 |
+
"step": 1175
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.3,
|
| 295 |
+
"learning_rate": 0.00019950000000000002,
|
| 296 |
+
"loss": 1.2449,
|
| 297 |
+
"step": 1200
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.31,
|
| 301 |
+
"learning_rate": 0.00019999795230099993,
|
| 302 |
+
"loss": 1.2648,
|
| 303 |
+
"step": 1225
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.31,
|
| 307 |
+
"learning_rate": 0.00019999065431390242,
|
| 308 |
+
"loss": 1.2348,
|
| 309 |
+
"step": 1250
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.32,
|
| 313 |
+
"learning_rate": 0.00019997806834748456,
|
| 314 |
+
"loss": 1.2385,
|
| 315 |
+
"step": 1275
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.33,
|
| 319 |
+
"learning_rate": 0.00019996019506735184,
|
| 320 |
+
"loss": 1.2761,
|
| 321 |
+
"step": 1300
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.33,
|
| 325 |
+
"learning_rate": 0.00019993703541872795,
|
| 326 |
+
"loss": 1.2532,
|
| 327 |
+
"step": 1325
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.34,
|
| 331 |
+
"learning_rate": 0.00019990859062640477,
|
| 332 |
+
"loss": 1.2478,
|
| 333 |
+
"step": 1350
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 1.0,
|
| 337 |
+
"learning_rate": 0.00019987486219467764,
|
| 338 |
+
"loss": 1.2108,
|
| 339 |
+
"step": 1375
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 1.01,
|
| 343 |
+
"learning_rate": 0.0001998358519072658,
|
| 344 |
+
"loss": 1.209,
|
| 345 |
+
"step": 1400
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 1.01,
|
| 349 |
+
"learning_rate": 0.0001997915618272179,
|
| 350 |
+
"loss": 1.237,
|
| 351 |
+
"step": 1425
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 1.02,
|
| 355 |
+
"learning_rate": 0.0001997419942968032,
|
| 356 |
+
"loss": 1.298,
|
| 357 |
+
"step": 1450
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 1.03,
|
| 361 |
+
"learning_rate": 0.00019968715193738738,
|
| 362 |
+
"loss": 1.1897,
|
| 363 |
+
"step": 1475
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 1.03,
|
| 367 |
+
"learning_rate": 0.0001996295434028785,
|
| 368 |
+
"loss": 1.1999,
|
| 369 |
+
"step": 1500
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 1.04,
|
| 373 |
+
"learning_rate": 0.00019956437105068297,
|
| 374 |
+
"loss": 1.1667,
|
| 375 |
+
"step": 1525
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 1.04,
|
| 379 |
+
"learning_rate": 0.00019949393326304478,
|
| 380 |
+
"loss": 1.2099,
|
| 381 |
+
"step": 1550
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 1.05,
|
| 385 |
+
"learning_rate": 0.0001994182337650477,
|
| 386 |
+
"loss": 1.21,
|
| 387 |
+
"step": 1575
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 1.06,
|
| 391 |
+
"learning_rate": 0.00019933727656003963,
|
| 392 |
+
"loss": 1.1651,
|
| 393 |
+
"step": 1600
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 1.06,
|
| 397 |
+
"learning_rate": 0.00019925106592942103,
|
| 398 |
+
"loss": 1.1462,
|
| 399 |
+
"step": 1625
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 1.07,
|
| 403 |
+
"learning_rate": 0.00019915960643241825,
|
| 404 |
+
"loss": 1.1849,
|
| 405 |
+
"step": 1650
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 1.08,
|
| 409 |
+
"learning_rate": 0.00019906290290584258,
|
| 410 |
+
"loss": 1.1645,
|
| 411 |
+
"step": 1675
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.08,
|
| 415 |
+
"learning_rate": 0.00019896096046383456,
|
| 416 |
+
"loss": 1.1824,
|
| 417 |
+
"step": 1700
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 1.09,
|
| 421 |
+
"learning_rate": 0.00019885378449759316,
|
| 422 |
+
"loss": 1.15,
|
| 423 |
+
"step": 1725
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 1.09,
|
| 427 |
+
"learning_rate": 0.0001987459771291654,
|
| 428 |
+
"loss": 1.2295,
|
| 429 |
+
"step": 1750
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 1.1,
|
| 433 |
+
"learning_rate": 0.00019862856015372317,
|
| 434 |
+
"loss": 1.15,
|
| 435 |
+
"step": 1775
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 1.11,
|
| 439 |
+
"learning_rate": 0.0001985059272329501,
|
| 440 |
+
"loss": 1.1641,
|
| 441 |
+
"step": 1800
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 1.11,
|
| 445 |
+
"learning_rate": 0.0001983780848522559,
|
| 446 |
+
"loss": 1.2108,
|
| 447 |
+
"step": 1825
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.12,
|
| 451 |
+
"learning_rate": 0.00019824503977255097,
|
| 452 |
+
"loss": 1.1669,
|
| 453 |
+
"step": 1850
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 1.13,
|
| 457 |
+
"learning_rate": 0.00019810679902988927,
|
| 458 |
+
"loss": 1.1874,
|
| 459 |
+
"step": 1875
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 1.13,
|
| 463 |
+
"learning_rate": 0.00019796336993509588,
|
| 464 |
+
"loss": 1.0834,
|
| 465 |
+
"step": 1900
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.14,
|
| 469 |
+
"learning_rate": 0.00019781476007338058,
|
| 470 |
+
"loss": 1.2298,
|
| 471 |
+
"step": 1925
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 1.14,
|
| 475 |
+
"learning_rate": 0.0001976609773039366,
|
| 476 |
+
"loss": 1.1745,
|
| 477 |
+
"step": 1950
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 1.15,
|
| 481 |
+
"learning_rate": 0.00019750202975952507,
|
| 482 |
+
"loss": 1.1523,
|
| 483 |
+
"step": 1975
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.16,
|
| 487 |
+
"learning_rate": 0.00019733792584604486,
|
| 488 |
+
"loss": 1.1434,
|
| 489 |
+
"step": 2000
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 1.16,
|
| 493 |
+
"learning_rate": 0.00019716867424208806,
|
| 494 |
+
"loss": 1.1493,
|
| 495 |
+
"step": 2025
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 1.17,
|
| 499 |
+
"learning_rate": 0.00019699428389848093,
|
| 500 |
+
"loss": 1.1317,
|
| 501 |
+
"step": 2050
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 1.18,
|
| 505 |
+
"learning_rate": 0.0001968147640378108,
|
| 506 |
+
"loss": 1.1427,
|
| 507 |
+
"step": 2075
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.18,
|
| 511 |
+
"learning_rate": 0.00019663760793213296,
|
| 512 |
+
"loss": 1.1638,
|
| 513 |
+
"step": 2100
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 1.19,
|
| 517 |
+
"learning_rate": 0.000196448062009159,
|
| 518 |
+
"loss": 1.1219,
|
| 519 |
+
"step": 2125
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 1.19,
|
| 523 |
+
"learning_rate": 0.00019625341545592226,
|
| 524 |
+
"loss": 1.1685,
|
| 525 |
+
"step": 2150
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 1.2,
|
| 529 |
+
"learning_rate": 0.0001960536785662542,
|
| 530 |
+
"loss": 1.1434,
|
| 531 |
+
"step": 2175
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 1.21,
|
| 535 |
+
"learning_rate": 0.00019584886190318742,
|
| 536 |
+
"loss": 1.098,
|
| 537 |
+
"step": 2200
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 1.21,
|
| 541 |
+
"learning_rate": 0.000195638976298397,
|
| 542 |
+
"loss": 1.1473,
|
| 543 |
+
"step": 2225
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 1.22,
|
| 547 |
+
"learning_rate": 0.0001954240328516277,
|
| 548 |
+
"loss": 1.1443,
|
| 549 |
+
"step": 2250
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.23,
|
| 553 |
+
"learning_rate": 0.00019520404293010683,
|
| 554 |
+
"loss": 1.137,
|
| 555 |
+
"step": 2275
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 1.23,
|
| 559 |
+
"learning_rate": 0.0001949790181679433,
|
| 560 |
+
"loss": 1.1211,
|
| 561 |
+
"step": 2300
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.24,
|
| 565 |
+
"learning_rate": 0.00019474897046551208,
|
| 566 |
+
"loss": 1.0878,
|
| 567 |
+
"step": 2325
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 1.24,
|
| 571 |
+
"learning_rate": 0.00019451391198882517,
|
| 572 |
+
"loss": 1.1113,
|
| 573 |
+
"step": 2350
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 1.25,
|
| 577 |
+
"learning_rate": 0.00019427385516888798,
|
| 578 |
+
"loss": 1.1411,
|
| 579 |
+
"step": 2375
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 1.26,
|
| 583 |
+
"learning_rate": 0.0001940288127010419,
|
| 584 |
+
"loss": 1.0948,
|
| 585 |
+
"step": 2400
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 1.26,
|
| 589 |
+
"learning_rate": 0.0001937787975442931,
|
| 590 |
+
"loss": 1.0966,
|
| 591 |
+
"step": 2425
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.27,
|
| 595 |
+
"learning_rate": 0.0001935238229206271,
|
| 596 |
+
"loss": 1.1556,
|
| 597 |
+
"step": 2450
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.28,
|
| 601 |
+
"learning_rate": 0.00019326390231430942,
|
| 602 |
+
"loss": 1.1422,
|
| 603 |
+
"step": 2475
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 1.28,
|
| 607 |
+
"learning_rate": 0.0001929990494711726,
|
| 608 |
+
"loss": 1.1278,
|
| 609 |
+
"step": 2500
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 1.29,
|
| 613 |
+
"learning_rate": 0.00019272927839788929,
|
| 614 |
+
"loss": 1.0958,
|
| 615 |
+
"step": 2525
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 1.29,
|
| 619 |
+
"learning_rate": 0.00019245460336123134,
|
| 620 |
+
"loss": 1.1172,
|
| 621 |
+
"step": 2550
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 1.3,
|
| 625 |
+
"learning_rate": 0.00019217503888731546,
|
| 626 |
+
"loss": 1.1393,
|
| 627 |
+
"step": 2575
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 1.31,
|
| 631 |
+
"learning_rate": 0.00019189059976083492,
|
| 632 |
+
"loss": 1.1054,
|
| 633 |
+
"step": 2600
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.31,
|
| 637 |
+
"learning_rate": 0.00019160130102427778,
|
| 638 |
+
"loss": 1.1073,
|
| 639 |
+
"step": 2625
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 1.32,
|
| 643 |
+
"learning_rate": 0.00019130715797713123,
|
| 644 |
+
"loss": 1.1802,
|
| 645 |
+
"step": 2650
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 1.33,
|
| 649 |
+
"learning_rate": 0.0001910081861750726,
|
| 650 |
+
"loss": 1.1162,
|
| 651 |
+
"step": 2675
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 1.33,
|
| 655 |
+
"learning_rate": 0.0001907044014291465,
|
| 656 |
+
"loss": 1.1289,
|
| 657 |
+
"step": 2700
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 1.34,
|
| 661 |
+
"learning_rate": 0.00019039581980492902,
|
| 662 |
+
"loss": 1.0892,
|
| 663 |
+
"step": 2725
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 2.0,
|
| 667 |
+
"learning_rate": 0.00019008245762167772,
|
| 668 |
+
"loss": 1.1055,
|
| 669 |
+
"step": 2750
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 2.01,
|
| 673 |
+
"learning_rate": 0.00018976433145146885,
|
| 674 |
+
"loss": 1.0787,
|
| 675 |
+
"step": 2775
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 2.01,
|
| 679 |
+
"learning_rate": 0.0001894414581183208,
|
| 680 |
+
"loss": 1.0862,
|
| 681 |
+
"step": 2800
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 2.02,
|
| 685 |
+
"learning_rate": 0.00018911385469730444,
|
| 686 |
+
"loss": 1.0763,
|
| 687 |
+
"step": 2825
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 2.03,
|
| 691 |
+
"learning_rate": 0.00018878153851364013,
|
| 692 |
+
"loss": 1.1034,
|
| 693 |
+
"step": 2850
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 2.03,
|
| 697 |
+
"learning_rate": 0.00018844452714178136,
|
| 698 |
+
"loss": 1.0982,
|
| 699 |
+
"step": 2875
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 2.04,
|
| 703 |
+
"learning_rate": 0.00018810283840448545,
|
| 704 |
+
"loss": 1.0915,
|
| 705 |
+
"step": 2900
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 2.04,
|
| 709 |
+
"learning_rate": 0.00018775649037187093,
|
| 710 |
+
"loss": 1.0945,
|
| 711 |
+
"step": 2925
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 2.05,
|
| 715 |
+
"learning_rate": 0.00018740550136046196,
|
| 716 |
+
"loss": 1.1061,
|
| 717 |
+
"step": 2950
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 2.06,
|
| 721 |
+
"learning_rate": 0.00018704988993221964,
|
| 722 |
+
"loss": 1.1178,
|
| 723 |
+
"step": 2975
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 2.06,
|
| 727 |
+
"learning_rate": 0.00018668967489356028,
|
| 728 |
+
"loss": 1.0524,
|
| 729 |
+
"step": 3000
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 2.07,
|
| 733 |
+
"learning_rate": 0.00018632487529436105,
|
| 734 |
+
"loss": 1.1349,
|
| 735 |
+
"step": 3025
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 2.08,
|
| 739 |
+
"learning_rate": 0.00018595551042695227,
|
| 740 |
+
"loss": 1.0893,
|
| 741 |
+
"step": 3050
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 2.08,
|
| 745 |
+
"learning_rate": 0.00018558159982509732,
|
| 746 |
+
"loss": 1.0633,
|
| 747 |
+
"step": 3075
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 2.09,
|
| 751 |
+
"learning_rate": 0.00018520316326295957,
|
| 752 |
+
"loss": 1.1066,
|
| 753 |
+
"step": 3100
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 2.09,
|
| 757 |
+
"learning_rate": 0.00018482022075405648,
|
| 758 |
+
"loss": 1.1457,
|
| 759 |
+
"step": 3125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 2.1,
|
| 763 |
+
"learning_rate": 0.00018443279255020152,
|
| 764 |
+
"loss": 1.0521,
|
| 765 |
+
"step": 3150
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 2.11,
|
| 769 |
+
"learning_rate": 0.00018404089914043272,
|
| 770 |
+
"loss": 1.0651,
|
| 771 |
+
"step": 3175
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 2.11,
|
| 775 |
+
"learning_rate": 0.00018364456124992954,
|
| 776 |
+
"loss": 1.0912,
|
| 777 |
+
"step": 3200
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 2.12,
|
| 781 |
+
"learning_rate": 0.0001832437998389165,
|
| 782 |
+
"loss": 1.1053,
|
| 783 |
+
"step": 3225
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 2.13,
|
| 787 |
+
"learning_rate": 0.00018283863610155487,
|
| 788 |
+
"loss": 1.0853,
|
| 789 |
+
"step": 3250
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 2.13,
|
| 793 |
+
"learning_rate": 0.00018242909146482187,
|
| 794 |
+
"loss": 1.105,
|
| 795 |
+
"step": 3275
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 2.14,
|
| 799 |
+
"learning_rate": 0.00018201518758737724,
|
| 800 |
+
"loss": 1.0751,
|
| 801 |
+
"step": 3300
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 2.14,
|
| 805 |
+
"learning_rate": 0.00018159694635841819,
|
| 806 |
+
"loss": 1.1086,
|
| 807 |
+
"step": 3325
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 2.15,
|
| 811 |
+
"learning_rate": 0.0001811743898965215,
|
| 812 |
+
"loss": 1.0675,
|
| 813 |
+
"step": 3350
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 2.16,
|
| 817 |
+
"learning_rate": 0.000180747540548474,
|
| 818 |
+
"loss": 1.0697,
|
| 819 |
+
"step": 3375
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.16,
|
| 823 |
+
"learning_rate": 0.00018031642088809063,
|
| 824 |
+
"loss": 1.1664,
|
| 825 |
+
"step": 3400
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 2.17,
|
| 829 |
+
"learning_rate": 0.00017988105371502059,
|
| 830 |
+
"loss": 1.0677,
|
| 831 |
+
"step": 3425
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 2.18,
|
| 835 |
+
"learning_rate": 0.00017944146205354182,
|
| 836 |
+
"loss": 1.0478,
|
| 837 |
+
"step": 3450
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 2.18,
|
| 841 |
+
"learning_rate": 0.00017899766915134308,
|
| 842 |
+
"loss": 1.0764,
|
| 843 |
+
"step": 3475
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 2.19,
|
| 847 |
+
"learning_rate": 0.0001785496984782947,
|
| 848 |
+
"loss": 1.0744,
|
| 849 |
+
"step": 3500
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 2.19,
|
| 853 |
+
"learning_rate": 0.0001780975737252073,
|
| 854 |
+
"loss": 1.1379,
|
| 855 |
+
"step": 3525
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.2,
|
| 859 |
+
"learning_rate": 0.0001776413188025789,
|
| 860 |
+
"loss": 1.1323,
|
| 861 |
+
"step": 3550
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 2.21,
|
| 865 |
+
"learning_rate": 0.00017718095783933054,
|
| 866 |
+
"loss": 1.1317,
|
| 867 |
+
"step": 3575
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 2.21,
|
| 871 |
+
"learning_rate": 0.00017671651518153,
|
| 872 |
+
"loss": 1.0786,
|
| 873 |
+
"step": 3600
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 2.22,
|
| 877 |
+
"learning_rate": 0.00017624801539110443,
|
| 878 |
+
"loss": 1.0549,
|
| 879 |
+
"step": 3625
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 2.23,
|
| 883 |
+
"learning_rate": 0.00017577548324454147,
|
| 884 |
+
"loss": 1.1106,
|
| 885 |
+
"step": 3650
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.23,
|
| 889 |
+
"learning_rate": 0.00017529894373157875,
|
| 890 |
+
"loss": 1.0852,
|
| 891 |
+
"step": 3675
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.24,
|
| 895 |
+
"learning_rate": 0.00017481842205388244,
|
| 896 |
+
"loss": 1.1003,
|
| 897 |
+
"step": 3700
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 2.24,
|
| 901 |
+
"learning_rate": 0.0001743339436237144,
|
| 902 |
+
"loss": 1.0682,
|
| 903 |
+
"step": 3725
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 2.25,
|
| 907 |
+
"learning_rate": 0.00017384553406258842,
|
| 908 |
+
"loss": 1.0729,
|
| 909 |
+
"step": 3750
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 2.26,
|
| 913 |
+
"learning_rate": 0.0001733532191999149,
|
| 914 |
+
"loss": 1.0679,
|
| 915 |
+
"step": 3775
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 2.26,
|
| 919 |
+
"learning_rate": 0.00017285702507163534,
|
| 920 |
+
"loss": 1.028,
|
| 921 |
+
"step": 3800
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 2.27,
|
| 925 |
+
"learning_rate": 0.00017235697791884494,
|
| 926 |
+
"loss": 1.0769,
|
| 927 |
+
"step": 3825
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.28,
|
| 931 |
+
"learning_rate": 0.00017185310418640524,
|
| 932 |
+
"loss": 1.0521,
|
| 933 |
+
"step": 3850
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 2.28,
|
| 937 |
+
"learning_rate": 0.00017134543052154538,
|
| 938 |
+
"loss": 1.0768,
|
| 939 |
+
"step": 3875
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 2.29,
|
| 943 |
+
"learning_rate": 0.0001708339837724529,
|
| 944 |
+
"loss": 1.0611,
|
| 945 |
+
"step": 3900
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 2.29,
|
| 949 |
+
"learning_rate": 0.00017031879098685393,
|
| 950 |
+
"loss": 1.0694,
|
| 951 |
+
"step": 3925
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 2.3,
|
| 955 |
+
"learning_rate": 0.00016979987941058273,
|
| 956 |
+
"loss": 1.067,
|
| 957 |
+
"step": 3950
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 2.31,
|
| 961 |
+
"learning_rate": 0.00016927727648614085,
|
| 962 |
+
"loss": 1.0586,
|
| 963 |
+
"step": 3975
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.31,
|
| 967 |
+
"learning_rate": 0.0001687510098512458,
|
| 968 |
+
"loss": 1.0337,
|
| 969 |
+
"step": 4000
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.32,
|
| 973 |
+
"learning_rate": 0.0001682211073373694,
|
| 974 |
+
"loss": 1.0501,
|
| 975 |
+
"step": 4025
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 2.33,
|
| 979 |
+
"learning_rate": 0.00016768759696826608,
|
| 980 |
+
"loss": 1.0818,
|
| 981 |
+
"step": 4050
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 2.33,
|
| 985 |
+
"learning_rate": 0.00016715050695849067,
|
| 986 |
+
"loss": 1.0548,
|
| 987 |
+
"step": 4075
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 2.34,
|
| 991 |
+
"learning_rate": 0.00016660986571190626,
|
| 992 |
+
"loss": 1.0919,
|
| 993 |
+
"step": 4100
|
| 994 |
+
}
|
| 995 |
+
],
|
| 996 |
+
"logging_steps": 25,
|
| 997 |
+
"max_steps": 12000,
|
| 998 |
+
"num_train_epochs": 3,
|
| 999 |
+
"save_steps": 500,
|
| 1000 |
+
"total_flos": 3.608534619248394e+17,
|
| 1001 |
+
"trial_name": null,
|
| 1002 |
+
"trial_params": null
|
| 1003 |
+
}
|
checkpoint-4122/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41e972bf5b6ffc690e7c0a26398cdcf74137de64b9f31441a70c7befc7cc1e61
|
| 3 |
+
size 4472
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<unk>",
|
| 4 |
+
"<s>",
|
| 5 |
+
"</s>"
|
| 6 |
+
],
|
| 7 |
+
"bos_token": {
|
| 8 |
+
"content": "<s>",
|
| 9 |
+
"lstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"single_word": false
|
| 13 |
+
},
|
| 14 |
+
"eos_token": {
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": false,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"pad_token": "</s>",
|
| 22 |
+
"unk_token": {
|
| 23 |
+
"content": "<unk>",
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"normalized": false,
|
| 26 |
+
"rstrip": false,
|
| 27 |
+
"single_word": false
|
| 28 |
+
}
|
| 29 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
}
|
| 27 |
+
},
|
| 28 |
+
"additional_special_tokens": [
|
| 29 |
+
"<unk>",
|
| 30 |
+
"<s>",
|
| 31 |
+
"</s>"
|
| 32 |
+
],
|
| 33 |
+
"bos_token": "<s>",
|
| 34 |
+
"clean_up_tokenization_spaces": false,
|
| 35 |
+
"eos_token": "</s>",
|
| 36 |
+
"legacy": true,
|
| 37 |
+
"model_max_length": 2048,
|
| 38 |
+
"pad_token": "</s>",
|
| 39 |
+
"sp_model_kwargs": {},
|
| 40 |
+
"spaces_between_special_tokens": false,
|
| 41 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 42 |
+
"unk_token": "<unk>",
|
| 43 |
+
"use_default_system_prompt": true
|
| 44 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41e972bf5b6ffc690e7c0a26398cdcf74137de64b9f31441a70c7befc7cc1e61
|
| 3 |
+
size 4472
|
training_params.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model": "Intel/neural-chat-7b-v3-1", "data_path": ".", "project_name": "neu-sai-fine-msz4", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 3, "batch_size": 1, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "sgd", "scheduler": "cosine", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": 2048, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": 25, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": true, "model_max_length": 2048, "repo_id": "CoruNethron/neu-sai-fine-it1-msz4", "use_int4": false, "trainer": "sft", "target_modules": "q_proj,v_proj,k_proj,o_proj", "merge_adapter": false, "username": null, "use_flash_attention_2": true, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": "prompt"}
|