Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- checkpoint-420/README.md +34 -0
- checkpoint-420/adapter_config.json +21 -0
- checkpoint-420/adapter_model.bin +3 -0
- checkpoint-420/added_tokens.json +3 -0
- checkpoint-420/optimizer.pt +3 -0
- checkpoint-420/rng_state.pth +3 -0
- checkpoint-420/scheduler.pt +3 -0
- checkpoint-420/special_tokens_map.json +24 -0
- checkpoint-420/tokenizer.json +0 -0
- checkpoint-420/tokenizer.model +3 -0
- checkpoint-420/tokenizer_config.json +46 -0
- checkpoint-420/trainer_state.json +859 -0
- checkpoint-420/training_args.bin +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +46 -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 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
|
| 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 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:790e315a75e2c37a171b62b155e340e35a628264990f1bdd8be1cf3b1d05ea3f
|
| 3 |
+
size 33600906
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-420/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 0.5.0
|
| 33 |
+
|
| 34 |
+
- PEFT 0.5.0
|
checkpoint-420/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "NousResearch/Llama-2-7b-chat-hf",
|
| 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 |
+
],
|
| 20 |
+
"task_type": "CAUSAL_LM"
|
| 21 |
+
}
|
checkpoint-420/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:790e315a75e2c37a171b62b155e340e35a628264990f1bdd8be1cf3b1d05ea3f
|
| 3 |
+
size 33600906
|
checkpoint-420/added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<pad>": 32000
|
| 3 |
+
}
|
checkpoint-420/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66f070658da8644e2cd030e6336e603dd6ba94c7e44b554b2be2c3e698fc5b49
|
| 3 |
+
size 67217018
|
checkpoint-420/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4afa55a48d30b91d56690f06f5ccd7a6981030510744a72930369036d7f201fa
|
| 3 |
+
size 14244
|
checkpoint-420/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:add5417f9438f14ff3f09dec479ad7588172e871bd7f31f6bd485c8aea8626b7
|
| 3 |
+
size 1064
|
checkpoint-420/special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-420/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-420/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
checkpoint-420/tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<pad>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": false,
|
| 38 |
+
"eos_token": "</s>",
|
| 39 |
+
"legacy": false,
|
| 40 |
+
"model_max_length": 2048,
|
| 41 |
+
"pad_token": "<unk>",
|
| 42 |
+
"sp_model_kwargs": {},
|
| 43 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
+
"unk_token": "<unk>",
|
| 45 |
+
"use_default_system_prompt": true
|
| 46 |
+
}
|
checkpoint-420/trainer_state.json
ADDED
|
@@ -0,0 +1,859 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 59.388888888888886,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 420,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.17,
|
| 13 |
+
"learning_rate": 5.555555555555556e-06,
|
| 14 |
+
"loss": 1.7272,
|
| 15 |
+
"step": 3
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.33,
|
| 19 |
+
"learning_rate": 1.1111111111111112e-05,
|
| 20 |
+
"loss": 1.9664,
|
| 21 |
+
"step": 6
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.11,
|
| 25 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 26 |
+
"loss": 1.8802,
|
| 27 |
+
"step": 9
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.28,
|
| 31 |
+
"learning_rate": 2.2222222222222223e-05,
|
| 32 |
+
"loss": 1.641,
|
| 33 |
+
"step": 12
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.06,
|
| 37 |
+
"learning_rate": 2.777777777777778e-05,
|
| 38 |
+
"loss": 1.9065,
|
| 39 |
+
"step": 15
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.22,
|
| 43 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 44 |
+
"loss": 1.5674,
|
| 45 |
+
"step": 18
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 2.39,
|
| 49 |
+
"learning_rate": 3.888888888888889e-05,
|
| 50 |
+
"loss": 1.7742,
|
| 51 |
+
"step": 21
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 3.17,
|
| 55 |
+
"learning_rate": 4.4444444444444447e-05,
|
| 56 |
+
"loss": 1.6901,
|
| 57 |
+
"step": 24
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 3.33,
|
| 61 |
+
"learning_rate": 5e-05,
|
| 62 |
+
"loss": 1.4911,
|
| 63 |
+
"step": 27
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.11,
|
| 67 |
+
"learning_rate": 5.555555555555556e-05,
|
| 68 |
+
"loss": 1.6228,
|
| 69 |
+
"step": 30
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 4.28,
|
| 73 |
+
"learning_rate": 6.111111111111112e-05,
|
| 74 |
+
"loss": 1.4569,
|
| 75 |
+
"step": 33
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.06,
|
| 79 |
+
"learning_rate": 6.666666666666667e-05,
|
| 80 |
+
"loss": 1.1288,
|
| 81 |
+
"step": 36
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 5.22,
|
| 85 |
+
"learning_rate": 7.222222222222222e-05,
|
| 86 |
+
"loss": 1.3788,
|
| 87 |
+
"step": 39
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 5.39,
|
| 91 |
+
"learning_rate": 7.777777777777778e-05,
|
| 92 |
+
"loss": 1.3019,
|
| 93 |
+
"step": 42
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 6.17,
|
| 97 |
+
"learning_rate": 8.333333333333334e-05,
|
| 98 |
+
"loss": 1.1974,
|
| 99 |
+
"step": 45
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 6.33,
|
| 103 |
+
"learning_rate": 8.888888888888889e-05,
|
| 104 |
+
"loss": 1.2544,
|
| 105 |
+
"step": 48
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 7.11,
|
| 109 |
+
"learning_rate": 9.444444444444444e-05,
|
| 110 |
+
"loss": 1.0393,
|
| 111 |
+
"step": 51
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 7.28,
|
| 115 |
+
"learning_rate": 0.0001,
|
| 116 |
+
"loss": 1.0955,
|
| 117 |
+
"step": 54
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 8.06,
|
| 121 |
+
"learning_rate": 0.00010555555555555557,
|
| 122 |
+
"loss": 0.9618,
|
| 123 |
+
"step": 57
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 8.22,
|
| 127 |
+
"learning_rate": 0.00011111111111111112,
|
| 128 |
+
"loss": 0.7707,
|
| 129 |
+
"step": 60
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 8.39,
|
| 133 |
+
"learning_rate": 0.00011666666666666668,
|
| 134 |
+
"loss": 0.7415,
|
| 135 |
+
"step": 63
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 9.17,
|
| 139 |
+
"learning_rate": 0.00012222222222222224,
|
| 140 |
+
"loss": 0.5368,
|
| 141 |
+
"step": 66
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 9.33,
|
| 145 |
+
"learning_rate": 0.00012777777777777776,
|
| 146 |
+
"loss": 0.741,
|
| 147 |
+
"step": 69
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 10.11,
|
| 151 |
+
"learning_rate": 0.00013333333333333334,
|
| 152 |
+
"loss": 0.5261,
|
| 153 |
+
"step": 72
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 10.28,
|
| 157 |
+
"learning_rate": 0.0001388888888888889,
|
| 158 |
+
"loss": 0.5543,
|
| 159 |
+
"step": 75
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 11.06,
|
| 163 |
+
"learning_rate": 0.00014444444444444444,
|
| 164 |
+
"loss": 0.3309,
|
| 165 |
+
"step": 78
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 11.22,
|
| 169 |
+
"learning_rate": 0.00015000000000000001,
|
| 170 |
+
"loss": 0.3979,
|
| 171 |
+
"step": 81
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 11.39,
|
| 175 |
+
"learning_rate": 0.00015555555555555556,
|
| 176 |
+
"loss": 0.3294,
|
| 177 |
+
"step": 84
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 12.17,
|
| 181 |
+
"learning_rate": 0.0001611111111111111,
|
| 182 |
+
"loss": 0.3013,
|
| 183 |
+
"step": 87
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 12.33,
|
| 187 |
+
"learning_rate": 0.0001666666666666667,
|
| 188 |
+
"loss": 0.3047,
|
| 189 |
+
"step": 90
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 13.11,
|
| 193 |
+
"learning_rate": 0.00017222222222222224,
|
| 194 |
+
"loss": 0.2221,
|
| 195 |
+
"step": 93
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 13.28,
|
| 199 |
+
"learning_rate": 0.00017777777777777779,
|
| 200 |
+
"loss": 0.2132,
|
| 201 |
+
"step": 96
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 14.06,
|
| 205 |
+
"learning_rate": 0.00018333333333333334,
|
| 206 |
+
"loss": 0.175,
|
| 207 |
+
"step": 99
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 14.22,
|
| 211 |
+
"learning_rate": 0.00018888888888888888,
|
| 212 |
+
"loss": 0.1485,
|
| 213 |
+
"step": 102
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 14.39,
|
| 217 |
+
"learning_rate": 0.00019444444444444446,
|
| 218 |
+
"loss": 0.1709,
|
| 219 |
+
"step": 105
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 15.17,
|
| 223 |
+
"learning_rate": 0.0002,
|
| 224 |
+
"loss": 0.1427,
|
| 225 |
+
"step": 108
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 15.33,
|
| 229 |
+
"learning_rate": 0.00019938271604938272,
|
| 230 |
+
"loss": 0.1162,
|
| 231 |
+
"step": 111
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 16.11,
|
| 235 |
+
"learning_rate": 0.00019876543209876543,
|
| 236 |
+
"loss": 0.1075,
|
| 237 |
+
"step": 114
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 16.28,
|
| 241 |
+
"learning_rate": 0.00019814814814814814,
|
| 242 |
+
"loss": 0.0965,
|
| 243 |
+
"step": 117
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 17.06,
|
| 247 |
+
"learning_rate": 0.00019753086419753085,
|
| 248 |
+
"loss": 0.0955,
|
| 249 |
+
"step": 120
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 17.22,
|
| 253 |
+
"learning_rate": 0.0001969135802469136,
|
| 254 |
+
"loss": 0.0706,
|
| 255 |
+
"step": 123
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 17.39,
|
| 259 |
+
"learning_rate": 0.0001962962962962963,
|
| 260 |
+
"loss": 0.0645,
|
| 261 |
+
"step": 126
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 18.17,
|
| 265 |
+
"learning_rate": 0.000195679012345679,
|
| 266 |
+
"loss": 0.042,
|
| 267 |
+
"step": 129
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 18.33,
|
| 271 |
+
"learning_rate": 0.00019506172839506175,
|
| 272 |
+
"loss": 0.0479,
|
| 273 |
+
"step": 132
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 19.11,
|
| 277 |
+
"learning_rate": 0.00019444444444444446,
|
| 278 |
+
"loss": 0.0258,
|
| 279 |
+
"step": 135
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 19.28,
|
| 283 |
+
"learning_rate": 0.00019382716049382717,
|
| 284 |
+
"loss": 0.0426,
|
| 285 |
+
"step": 138
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 20.06,
|
| 289 |
+
"learning_rate": 0.00019320987654320988,
|
| 290 |
+
"loss": 0.0314,
|
| 291 |
+
"step": 141
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 20.22,
|
| 295 |
+
"learning_rate": 0.0001925925925925926,
|
| 296 |
+
"loss": 0.0235,
|
| 297 |
+
"step": 144
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 20.39,
|
| 301 |
+
"learning_rate": 0.00019197530864197533,
|
| 302 |
+
"loss": 0.0359,
|
| 303 |
+
"step": 147
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 21.17,
|
| 307 |
+
"learning_rate": 0.00019135802469135804,
|
| 308 |
+
"loss": 0.0218,
|
| 309 |
+
"step": 150
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 21.33,
|
| 313 |
+
"learning_rate": 0.00019074074074074075,
|
| 314 |
+
"loss": 0.0279,
|
| 315 |
+
"step": 153
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 22.11,
|
| 319 |
+
"learning_rate": 0.00019012345679012346,
|
| 320 |
+
"loss": 0.019,
|
| 321 |
+
"step": 156
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 22.28,
|
| 325 |
+
"learning_rate": 0.00018950617283950617,
|
| 326 |
+
"loss": 0.0212,
|
| 327 |
+
"step": 159
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 23.06,
|
| 331 |
+
"learning_rate": 0.00018888888888888888,
|
| 332 |
+
"loss": 0.0201,
|
| 333 |
+
"step": 162
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 23.22,
|
| 337 |
+
"learning_rate": 0.0001882716049382716,
|
| 338 |
+
"loss": 0.0133,
|
| 339 |
+
"step": 165
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 23.39,
|
| 343 |
+
"learning_rate": 0.00018765432098765433,
|
| 344 |
+
"loss": 0.0194,
|
| 345 |
+
"step": 168
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 24.17,
|
| 349 |
+
"learning_rate": 0.00018703703703703704,
|
| 350 |
+
"loss": 0.0143,
|
| 351 |
+
"step": 171
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 24.33,
|
| 355 |
+
"learning_rate": 0.00018641975308641978,
|
| 356 |
+
"loss": 0.0118,
|
| 357 |
+
"step": 174
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 25.11,
|
| 361 |
+
"learning_rate": 0.0001858024691358025,
|
| 362 |
+
"loss": 0.0135,
|
| 363 |
+
"step": 177
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 25.28,
|
| 367 |
+
"learning_rate": 0.0001851851851851852,
|
| 368 |
+
"loss": 0.0105,
|
| 369 |
+
"step": 180
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 26.06,
|
| 373 |
+
"learning_rate": 0.00018456790123456791,
|
| 374 |
+
"loss": 0.0125,
|
| 375 |
+
"step": 183
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 26.22,
|
| 379 |
+
"learning_rate": 0.00018395061728395062,
|
| 380 |
+
"loss": 0.012,
|
| 381 |
+
"step": 186
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 26.39,
|
| 385 |
+
"learning_rate": 0.00018333333333333334,
|
| 386 |
+
"loss": 0.012,
|
| 387 |
+
"step": 189
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 27.17,
|
| 391 |
+
"learning_rate": 0.00018271604938271605,
|
| 392 |
+
"loss": 0.0114,
|
| 393 |
+
"step": 192
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 27.33,
|
| 397 |
+
"learning_rate": 0.00018209876543209878,
|
| 398 |
+
"loss": 0.0105,
|
| 399 |
+
"step": 195
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 28.11,
|
| 403 |
+
"learning_rate": 0.0001814814814814815,
|
| 404 |
+
"loss": 0.0115,
|
| 405 |
+
"step": 198
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 28.28,
|
| 409 |
+
"learning_rate": 0.0001808641975308642,
|
| 410 |
+
"loss": 0.0077,
|
| 411 |
+
"step": 201
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 29.06,
|
| 415 |
+
"learning_rate": 0.00018024691358024692,
|
| 416 |
+
"loss": 0.0116,
|
| 417 |
+
"step": 204
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 29.22,
|
| 421 |
+
"learning_rate": 0.00017962962962962963,
|
| 422 |
+
"loss": 0.0092,
|
| 423 |
+
"step": 207
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 29.39,
|
| 427 |
+
"learning_rate": 0.00017901234567901234,
|
| 428 |
+
"loss": 0.0105,
|
| 429 |
+
"step": 210
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 30.17,
|
| 433 |
+
"learning_rate": 0.00017839506172839508,
|
| 434 |
+
"loss": 0.0113,
|
| 435 |
+
"step": 213
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 30.33,
|
| 439 |
+
"learning_rate": 0.00017777777777777779,
|
| 440 |
+
"loss": 0.0094,
|
| 441 |
+
"step": 216
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 31.11,
|
| 445 |
+
"learning_rate": 0.00017716049382716052,
|
| 446 |
+
"loss": 0.0092,
|
| 447 |
+
"step": 219
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 31.28,
|
| 451 |
+
"learning_rate": 0.00017654320987654323,
|
| 452 |
+
"loss": 0.0079,
|
| 453 |
+
"step": 222
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 32.06,
|
| 457 |
+
"learning_rate": 0.00017592592592592595,
|
| 458 |
+
"loss": 0.0089,
|
| 459 |
+
"step": 225
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 32.22,
|
| 463 |
+
"learning_rate": 0.00017530864197530866,
|
| 464 |
+
"loss": 0.0085,
|
| 465 |
+
"step": 228
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 32.39,
|
| 469 |
+
"learning_rate": 0.00017469135802469137,
|
| 470 |
+
"loss": 0.0081,
|
| 471 |
+
"step": 231
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 33.17,
|
| 475 |
+
"learning_rate": 0.00017407407407407408,
|
| 476 |
+
"loss": 0.0076,
|
| 477 |
+
"step": 234
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 33.33,
|
| 481 |
+
"learning_rate": 0.0001734567901234568,
|
| 482 |
+
"loss": 0.0059,
|
| 483 |
+
"step": 237
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 34.11,
|
| 487 |
+
"learning_rate": 0.0001728395061728395,
|
| 488 |
+
"loss": 0.0078,
|
| 489 |
+
"step": 240
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 34.28,
|
| 493 |
+
"learning_rate": 0.00017222222222222224,
|
| 494 |
+
"loss": 0.0039,
|
| 495 |
+
"step": 243
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 35.06,
|
| 499 |
+
"learning_rate": 0.00017160493827160495,
|
| 500 |
+
"loss": 0.0078,
|
| 501 |
+
"step": 246
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 35.22,
|
| 505 |
+
"learning_rate": 0.00017098765432098766,
|
| 506 |
+
"loss": 0.0041,
|
| 507 |
+
"step": 249
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 35.39,
|
| 511 |
+
"learning_rate": 0.00017037037037037037,
|
| 512 |
+
"loss": 0.0061,
|
| 513 |
+
"step": 252
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 36.17,
|
| 517 |
+
"learning_rate": 0.00016975308641975308,
|
| 518 |
+
"loss": 0.0039,
|
| 519 |
+
"step": 255
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 36.33,
|
| 523 |
+
"learning_rate": 0.00016913580246913582,
|
| 524 |
+
"loss": 0.007,
|
| 525 |
+
"step": 258
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 37.11,
|
| 529 |
+
"learning_rate": 0.00016851851851851853,
|
| 530 |
+
"loss": 0.0049,
|
| 531 |
+
"step": 261
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 37.28,
|
| 535 |
+
"learning_rate": 0.00016790123456790124,
|
| 536 |
+
"loss": 0.005,
|
| 537 |
+
"step": 264
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 38.06,
|
| 541 |
+
"learning_rate": 0.00016728395061728398,
|
| 542 |
+
"loss": 0.0074,
|
| 543 |
+
"step": 267
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 38.22,
|
| 547 |
+
"learning_rate": 0.0001666666666666667,
|
| 548 |
+
"loss": 0.0035,
|
| 549 |
+
"step": 270
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 38.39,
|
| 553 |
+
"learning_rate": 0.0001660493827160494,
|
| 554 |
+
"loss": 0.0067,
|
| 555 |
+
"step": 273
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 39.17,
|
| 559 |
+
"learning_rate": 0.0001654320987654321,
|
| 560 |
+
"loss": 0.0061,
|
| 561 |
+
"step": 276
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 39.33,
|
| 565 |
+
"learning_rate": 0.00016481481481481482,
|
| 566 |
+
"loss": 0.0047,
|
| 567 |
+
"step": 279
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 40.11,
|
| 571 |
+
"learning_rate": 0.00016419753086419753,
|
| 572 |
+
"loss": 0.0035,
|
| 573 |
+
"step": 282
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 40.28,
|
| 577 |
+
"learning_rate": 0.00016358024691358024,
|
| 578 |
+
"loss": 0.0072,
|
| 579 |
+
"step": 285
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 41.06,
|
| 583 |
+
"learning_rate": 0.00016296296296296295,
|
| 584 |
+
"loss": 0.0044,
|
| 585 |
+
"step": 288
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 41.22,
|
| 589 |
+
"learning_rate": 0.0001623456790123457,
|
| 590 |
+
"loss": 0.0031,
|
| 591 |
+
"step": 291
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 41.39,
|
| 595 |
+
"learning_rate": 0.0001617283950617284,
|
| 596 |
+
"loss": 0.0047,
|
| 597 |
+
"step": 294
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 42.17,
|
| 601 |
+
"learning_rate": 0.0001611111111111111,
|
| 602 |
+
"loss": 0.004,
|
| 603 |
+
"step": 297
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 42.33,
|
| 607 |
+
"learning_rate": 0.00016049382716049385,
|
| 608 |
+
"loss": 0.0048,
|
| 609 |
+
"step": 300
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 43.11,
|
| 613 |
+
"learning_rate": 0.00015987654320987656,
|
| 614 |
+
"loss": 0.0028,
|
| 615 |
+
"step": 303
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 43.28,
|
| 619 |
+
"learning_rate": 0.00015925925925925927,
|
| 620 |
+
"loss": 0.0043,
|
| 621 |
+
"step": 306
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 44.06,
|
| 625 |
+
"learning_rate": 0.00015864197530864198,
|
| 626 |
+
"loss": 0.0037,
|
| 627 |
+
"step": 309
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 44.22,
|
| 631 |
+
"learning_rate": 0.0001580246913580247,
|
| 632 |
+
"loss": 0.0032,
|
| 633 |
+
"step": 312
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 44.39,
|
| 637 |
+
"learning_rate": 0.00015740740740740743,
|
| 638 |
+
"loss": 0.0045,
|
| 639 |
+
"step": 315
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 45.17,
|
| 643 |
+
"learning_rate": 0.00015679012345679014,
|
| 644 |
+
"loss": 0.0041,
|
| 645 |
+
"step": 318
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 45.33,
|
| 649 |
+
"learning_rate": 0.00015617283950617285,
|
| 650 |
+
"loss": 0.0032,
|
| 651 |
+
"step": 321
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 46.11,
|
| 655 |
+
"learning_rate": 0.00015555555555555556,
|
| 656 |
+
"loss": 0.002,
|
| 657 |
+
"step": 324
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 46.28,
|
| 661 |
+
"learning_rate": 0.00015493827160493827,
|
| 662 |
+
"loss": 0.0038,
|
| 663 |
+
"step": 327
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 47.06,
|
| 667 |
+
"learning_rate": 0.00015432098765432098,
|
| 668 |
+
"loss": 0.0036,
|
| 669 |
+
"step": 330
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 47.22,
|
| 673 |
+
"learning_rate": 0.0001537037037037037,
|
| 674 |
+
"loss": 0.0035,
|
| 675 |
+
"step": 333
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 47.39,
|
| 679 |
+
"learning_rate": 0.0001530864197530864,
|
| 680 |
+
"loss": 0.0035,
|
| 681 |
+
"step": 336
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 48.17,
|
| 685 |
+
"learning_rate": 0.00015246913580246914,
|
| 686 |
+
"loss": 0.005,
|
| 687 |
+
"step": 339
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 48.33,
|
| 691 |
+
"learning_rate": 0.00015185185185185185,
|
| 692 |
+
"loss": 0.0019,
|
| 693 |
+
"step": 342
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 49.11,
|
| 697 |
+
"learning_rate": 0.0001512345679012346,
|
| 698 |
+
"loss": 0.0033,
|
| 699 |
+
"step": 345
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 49.28,
|
| 703 |
+
"learning_rate": 0.0001506172839506173,
|
| 704 |
+
"loss": 0.0016,
|
| 705 |
+
"step": 348
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 50.06,
|
| 709 |
+
"learning_rate": 0.00015000000000000001,
|
| 710 |
+
"loss": 0.0034,
|
| 711 |
+
"step": 351
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 50.22,
|
| 715 |
+
"learning_rate": 0.00014938271604938272,
|
| 716 |
+
"loss": 0.0028,
|
| 717 |
+
"step": 354
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 50.39,
|
| 721 |
+
"learning_rate": 0.00014876543209876544,
|
| 722 |
+
"loss": 0.0039,
|
| 723 |
+
"step": 357
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 51.17,
|
| 727 |
+
"learning_rate": 0.00014814814814814815,
|
| 728 |
+
"loss": 0.0019,
|
| 729 |
+
"step": 360
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 51.33,
|
| 733 |
+
"learning_rate": 0.00014753086419753086,
|
| 734 |
+
"loss": 0.0042,
|
| 735 |
+
"step": 363
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 52.11,
|
| 739 |
+
"learning_rate": 0.0001469135802469136,
|
| 740 |
+
"loss": 0.0016,
|
| 741 |
+
"step": 366
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 52.28,
|
| 745 |
+
"learning_rate": 0.0001462962962962963,
|
| 746 |
+
"loss": 0.0022,
|
| 747 |
+
"step": 369
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 53.06,
|
| 751 |
+
"learning_rate": 0.00014567901234567902,
|
| 752 |
+
"loss": 0.0048,
|
| 753 |
+
"step": 372
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 53.22,
|
| 757 |
+
"learning_rate": 0.00014506172839506173,
|
| 758 |
+
"loss": 0.0014,
|
| 759 |
+
"step": 375
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 53.39,
|
| 763 |
+
"learning_rate": 0.00014444444444444444,
|
| 764 |
+
"loss": 0.0026,
|
| 765 |
+
"step": 378
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 54.17,
|
| 769 |
+
"learning_rate": 0.00014382716049382718,
|
| 770 |
+
"loss": 0.0036,
|
| 771 |
+
"step": 381
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 54.33,
|
| 775 |
+
"learning_rate": 0.00014320987654320989,
|
| 776 |
+
"loss": 0.0019,
|
| 777 |
+
"step": 384
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 55.11,
|
| 781 |
+
"learning_rate": 0.0001425925925925926,
|
| 782 |
+
"loss": 0.0033,
|
| 783 |
+
"step": 387
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 55.28,
|
| 787 |
+
"learning_rate": 0.00014197530864197534,
|
| 788 |
+
"loss": 0.0012,
|
| 789 |
+
"step": 390
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 56.06,
|
| 793 |
+
"learning_rate": 0.00014135802469135805,
|
| 794 |
+
"loss": 0.0019,
|
| 795 |
+
"step": 393
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 56.22,
|
| 799 |
+
"learning_rate": 0.00014074074074074076,
|
| 800 |
+
"loss": 0.002,
|
| 801 |
+
"step": 396
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 56.39,
|
| 805 |
+
"learning_rate": 0.00014012345679012347,
|
| 806 |
+
"loss": 0.0031,
|
| 807 |
+
"step": 399
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 57.17,
|
| 811 |
+
"learning_rate": 0.00013950617283950618,
|
| 812 |
+
"loss": 0.0042,
|
| 813 |
+
"step": 402
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 57.33,
|
| 817 |
+
"learning_rate": 0.0001388888888888889,
|
| 818 |
+
"loss": 0.0008,
|
| 819 |
+
"step": 405
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 58.11,
|
| 823 |
+
"learning_rate": 0.0001382716049382716,
|
| 824 |
+
"loss": 0.0012,
|
| 825 |
+
"step": 408
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 58.28,
|
| 829 |
+
"learning_rate": 0.0001376543209876543,
|
| 830 |
+
"loss": 0.0026,
|
| 831 |
+
"step": 411
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 59.06,
|
| 835 |
+
"learning_rate": 0.00013703703703703705,
|
| 836 |
+
"loss": 0.0025,
|
| 837 |
+
"step": 414
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 59.22,
|
| 841 |
+
"learning_rate": 0.00013641975308641976,
|
| 842 |
+
"loss": 0.0026,
|
| 843 |
+
"step": 417
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 59.39,
|
| 847 |
+
"learning_rate": 0.00013580246913580247,
|
| 848 |
+
"loss": 0.0014,
|
| 849 |
+
"step": 420
|
| 850 |
+
}
|
| 851 |
+
],
|
| 852 |
+
"logging_steps": 3,
|
| 853 |
+
"max_steps": 1080,
|
| 854 |
+
"num_train_epochs": 60,
|
| 855 |
+
"save_steps": 500,
|
| 856 |
+
"total_flos": 3.41435505180672e+16,
|
| 857 |
+
"trial_name": null,
|
| 858 |
+
"trial_params": null
|
| 859 |
+
}
|
checkpoint-420/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2471a3a5eb507f2bc6a58a20fee11c04212f8988dbb56470331dd87ea6fba931
|
| 3 |
+
size 4472
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "<unk>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 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.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "<unk>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": true,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "<s>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": true,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "</s>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": true,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"32000": {
|
| 28 |
+
"content": "<pad>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": false
|
| 34 |
+
}
|
| 35 |
+
},
|
| 36 |
+
"bos_token": "<s>",
|
| 37 |
+
"clean_up_tokenization_spaces": false,
|
| 38 |
+
"eos_token": "</s>",
|
| 39 |
+
"legacy": false,
|
| 40 |
+
"model_max_length": 2048,
|
| 41 |
+
"pad_token": "<unk>",
|
| 42 |
+
"sp_model_kwargs": {},
|
| 43 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 44 |
+
"unk_token": "<unk>",
|
| 45 |
+
"use_default_system_prompt": true
|
| 46 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2471a3a5eb507f2bc6a58a20fee11c04212f8988dbb56470331dd87ea6fba931
|
| 3 |
+
size 4472
|
training_params.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model": "NousResearch/Llama-2-7b-chat-hf", "data_path": "Flyfer/CBDataSetBeta1", "project_name": "TestProject", "train_split": "train", "valid_split": null, "text_column": "text", "rejected_text_column": "rejected", "lr": 0.0002, "epochs": 60, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.0, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": false, "block_size": -1, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.05, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": false, "push_to_hub": true, "use_int8": false, "model_max_length": 2048, "repo_id": "Flyfer/llama2-test60ep", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": null, "use_flash_attention_2": false, "log": "none", "disable_gradient_checkpointing": false, "model_ref": null, "dpo_beta": 0.1, "prompt_text_column": "prompt"}
|