Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +22 -0
- adapter_model.bin +3 -0
- checkpoint-8825/README.md +34 -0
- checkpoint-8825/adapter_config.json +22 -0
- checkpoint-8825/adapter_model.bin +3 -0
- checkpoint-8825/optimizer.pt +3 -0
- checkpoint-8825/rng_state.pth +3 -0
- checkpoint-8825/scheduler.pt +3 -0
- checkpoint-8825/special_tokens_map.json +6 -0
- checkpoint-8825/tokenizer.json +0 -0
- checkpoint-8825/tokenizer.model +3 -0
- checkpoint-8825/tokenizer_config.json +40 -0
- checkpoint-8825/trainer_state.json +739 -0
- checkpoint-8825/training_args.bin +3 -0
- runs/Oct02_17-08-29_AM-3080TI-VR-PC/events.out.tfevents.1696262910.AM-3080TI-VR-PC.781.0 +3 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -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 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 32,
|
| 12 |
+
"lora_dropout": 0.05,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 16,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj"
|
| 20 |
+
],
|
| 21 |
+
"task_type": "CAUSAL_LM"
|
| 22 |
+
}
|
adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:288b7f41e8b497e0168906000bc67de18cfc867d5cb95c13eb23102eaa7caaa6
|
| 3 |
+
size 16800049
|
checkpoint-8825/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
|
checkpoint-8825/adapter_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alpha_pattern": {},
|
| 3 |
+
"auto_mapping": null,
|
| 4 |
+
"base_model_name_or_path": "bn22/Mistral-7B-Instruct-v0.1-sharded",
|
| 5 |
+
"bias": "none",
|
| 6 |
+
"fan_in_fan_out": false,
|
| 7 |
+
"inference_mode": true,
|
| 8 |
+
"init_lora_weights": true,
|
| 9 |
+
"layers_pattern": null,
|
| 10 |
+
"layers_to_transform": null,
|
| 11 |
+
"lora_alpha": 32,
|
| 12 |
+
"lora_dropout": 0.05,
|
| 13 |
+
"modules_to_save": null,
|
| 14 |
+
"peft_type": "LORA",
|
| 15 |
+
"r": 16,
|
| 16 |
+
"rank_pattern": {},
|
| 17 |
+
"revision": null,
|
| 18 |
+
"target_modules": [
|
| 19 |
+
"q_proj"
|
| 20 |
+
],
|
| 21 |
+
"task_type": "CAUSAL_LM"
|
| 22 |
+
}
|
checkpoint-8825/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:288b7f41e8b497e0168906000bc67de18cfc867d5cb95c13eb23102eaa7caaa6
|
| 3 |
+
size 16800049
|
checkpoint-8825/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f3bd4b216465776b8446b4ff8e11ce9fdd52c89b375b7044d0b4039e2d61866c
|
| 3 |
+
size 33608325
|
checkpoint-8825/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1415153a8090e01ca2e79f9b676cb59f9d69952de4f1e1908ae3ffd91dd838a6
|
| 3 |
+
size 14575
|
checkpoint-8825/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e4646b9235cf75047cb149a2e2ec3a2d928351a83378beb4a3c4edcd1f0af06
|
| 3 |
+
size 627
|
checkpoint-8825/special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "</s>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
checkpoint-8825/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-8825/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
checkpoint-8825/tokenizer_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"bos_token": "<s>",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": true,
|
| 33 |
+
"model_max_length": 1024,
|
| 34 |
+
"pad_token": null,
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"spaces_between_special_tokens": false,
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": true
|
| 40 |
+
}
|
checkpoint-8825/trainer_state.json
ADDED
|
@@ -0,0 +1,739 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 24.96185286103542,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 8825,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.2,
|
| 13 |
+
"learning_rate": 7.952069716775599e-06,
|
| 14 |
+
"loss": 0.9545,
|
| 15 |
+
"step": 73
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.4,
|
| 19 |
+
"learning_rate": 1.5904139433551197e-05,
|
| 20 |
+
"loss": 0.9152,
|
| 21 |
+
"step": 146
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.6,
|
| 25 |
+
"learning_rate": 2.38562091503268e-05,
|
| 26 |
+
"loss": 0.7448,
|
| 27 |
+
"step": 219
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.8,
|
| 31 |
+
"learning_rate": 3.1808278867102395e-05,
|
| 32 |
+
"loss": 0.5783,
|
| 33 |
+
"step": 292
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 1.03,
|
| 37 |
+
"learning_rate": 3.9760348583877995e-05,
|
| 38 |
+
"loss": 0.4973,
|
| 39 |
+
"step": 365
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 1.23,
|
| 43 |
+
"learning_rate": 4.77124183006536e-05,
|
| 44 |
+
"loss": 0.4414,
|
| 45 |
+
"step": 438
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 1.43,
|
| 49 |
+
"learning_rate": 5.5664488017429196e-05,
|
| 50 |
+
"loss": 0.4208,
|
| 51 |
+
"step": 511
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 1.63,
|
| 55 |
+
"learning_rate": 6.361655773420479e-05,
|
| 56 |
+
"loss": 0.3861,
|
| 57 |
+
"step": 584
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 1.83,
|
| 61 |
+
"learning_rate": 7.156862745098039e-05,
|
| 62 |
+
"loss": 0.3802,
|
| 63 |
+
"step": 657
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 2.07,
|
| 67 |
+
"learning_rate": 7.952069716775599e-05,
|
| 68 |
+
"loss": 0.335,
|
| 69 |
+
"step": 730
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 2.26,
|
| 73 |
+
"learning_rate": 8.74727668845316e-05,
|
| 74 |
+
"loss": 0.3216,
|
| 75 |
+
"step": 803
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 2.46,
|
| 79 |
+
"learning_rate": 9.54248366013072e-05,
|
| 80 |
+
"loss": 0.2991,
|
| 81 |
+
"step": 876
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 2.66,
|
| 85 |
+
"learning_rate": 9.962456097856366e-05,
|
| 86 |
+
"loss": 0.2919,
|
| 87 |
+
"step": 949
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 2.86,
|
| 91 |
+
"learning_rate": 9.87404626377619e-05,
|
| 92 |
+
"loss": 0.3062,
|
| 93 |
+
"step": 1022
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 3.1,
|
| 97 |
+
"learning_rate": 9.785636429696016e-05,
|
| 98 |
+
"loss": 0.2661,
|
| 99 |
+
"step": 1095
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 3.3,
|
| 103 |
+
"learning_rate": 9.697226595615842e-05,
|
| 104 |
+
"loss": 0.2547,
|
| 105 |
+
"step": 1168
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 3.5,
|
| 109 |
+
"learning_rate": 9.608816761535667e-05,
|
| 110 |
+
"loss": 0.2426,
|
| 111 |
+
"step": 1241
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 3.69,
|
| 115 |
+
"learning_rate": 9.520406927455493e-05,
|
| 116 |
+
"loss": 0.224,
|
| 117 |
+
"step": 1314
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 3.89,
|
| 121 |
+
"learning_rate": 9.431997093375319e-05,
|
| 122 |
+
"loss": 0.2164,
|
| 123 |
+
"step": 1387
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 4.13,
|
| 127 |
+
"learning_rate": 9.343587259295143e-05,
|
| 128 |
+
"loss": 0.1952,
|
| 129 |
+
"step": 1460
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 4.33,
|
| 133 |
+
"learning_rate": 9.255177425214969e-05,
|
| 134 |
+
"loss": 0.2025,
|
| 135 |
+
"step": 1533
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 4.53,
|
| 139 |
+
"learning_rate": 9.166767591134794e-05,
|
| 140 |
+
"loss": 0.1837,
|
| 141 |
+
"step": 1606
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 4.73,
|
| 145 |
+
"learning_rate": 9.078357757054621e-05,
|
| 146 |
+
"loss": 0.1911,
|
| 147 |
+
"step": 1679
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 4.93,
|
| 151 |
+
"learning_rate": 8.989947922974447e-05,
|
| 152 |
+
"loss": 0.1737,
|
| 153 |
+
"step": 1752
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 5.16,
|
| 157 |
+
"learning_rate": 8.901538088894273e-05,
|
| 158 |
+
"loss": 0.1633,
|
| 159 |
+
"step": 1825
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 5.36,
|
| 163 |
+
"learning_rate": 8.813128254814099e-05,
|
| 164 |
+
"loss": 0.1485,
|
| 165 |
+
"step": 1898
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 5.56,
|
| 169 |
+
"learning_rate": 8.724718420733923e-05,
|
| 170 |
+
"loss": 0.1479,
|
| 171 |
+
"step": 1971
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 5.76,
|
| 175 |
+
"learning_rate": 8.636308586653749e-05,
|
| 176 |
+
"loss": 0.1625,
|
| 177 |
+
"step": 2044
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 5.96,
|
| 181 |
+
"learning_rate": 8.547898752573574e-05,
|
| 182 |
+
"loss": 0.1602,
|
| 183 |
+
"step": 2117
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 6.2,
|
| 187 |
+
"learning_rate": 8.4594889184934e-05,
|
| 188 |
+
"loss": 0.1307,
|
| 189 |
+
"step": 2190
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 6.4,
|
| 193 |
+
"learning_rate": 8.371079084413226e-05,
|
| 194 |
+
"loss": 0.1279,
|
| 195 |
+
"step": 2263
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 6.59,
|
| 199 |
+
"learning_rate": 8.282669250333051e-05,
|
| 200 |
+
"loss": 0.1231,
|
| 201 |
+
"step": 2336
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 6.79,
|
| 205 |
+
"learning_rate": 8.194259416252876e-05,
|
| 206 |
+
"loss": 0.1426,
|
| 207 |
+
"step": 2409
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 7.03,
|
| 211 |
+
"learning_rate": 8.105849582172701e-05,
|
| 212 |
+
"loss": 0.1245,
|
| 213 |
+
"step": 2482
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 7.23,
|
| 217 |
+
"learning_rate": 8.017439748092528e-05,
|
| 218 |
+
"loss": 0.1186,
|
| 219 |
+
"step": 2555
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 7.43,
|
| 223 |
+
"learning_rate": 7.929029914012354e-05,
|
| 224 |
+
"loss": 0.1081,
|
| 225 |
+
"step": 2628
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 7.63,
|
| 229 |
+
"learning_rate": 7.84062007993218e-05,
|
| 230 |
+
"loss": 0.1025,
|
| 231 |
+
"step": 2701
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 7.83,
|
| 235 |
+
"learning_rate": 7.752210245852006e-05,
|
| 236 |
+
"loss": 0.1173,
|
| 237 |
+
"step": 2774
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 8.06,
|
| 241 |
+
"learning_rate": 7.66380041177183e-05,
|
| 242 |
+
"loss": 0.0996,
|
| 243 |
+
"step": 2847
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 8.26,
|
| 247 |
+
"learning_rate": 7.575390577691656e-05,
|
| 248 |
+
"loss": 0.0861,
|
| 249 |
+
"step": 2920
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 8.46,
|
| 253 |
+
"learning_rate": 7.486980743611481e-05,
|
| 254 |
+
"loss": 0.1018,
|
| 255 |
+
"step": 2993
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 8.66,
|
| 259 |
+
"learning_rate": 7.398570909531307e-05,
|
| 260 |
+
"loss": 0.0977,
|
| 261 |
+
"step": 3066
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 8.86,
|
| 265 |
+
"learning_rate": 7.310161075451133e-05,
|
| 266 |
+
"loss": 0.1002,
|
| 267 |
+
"step": 3139
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 9.1,
|
| 271 |
+
"learning_rate": 7.221751241370958e-05,
|
| 272 |
+
"loss": 0.0839,
|
| 273 |
+
"step": 3212
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 9.29,
|
| 277 |
+
"learning_rate": 7.133341407290783e-05,
|
| 278 |
+
"loss": 0.0884,
|
| 279 |
+
"step": 3285
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 9.49,
|
| 283 |
+
"learning_rate": 7.044931573210608e-05,
|
| 284 |
+
"loss": 0.0825,
|
| 285 |
+
"step": 3358
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 9.69,
|
| 289 |
+
"learning_rate": 6.956521739130436e-05,
|
| 290 |
+
"loss": 0.0811,
|
| 291 |
+
"step": 3431
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 9.89,
|
| 295 |
+
"learning_rate": 6.868111905050261e-05,
|
| 296 |
+
"loss": 0.0851,
|
| 297 |
+
"step": 3504
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 10.13,
|
| 301 |
+
"learning_rate": 6.779702070970087e-05,
|
| 302 |
+
"loss": 0.0716,
|
| 303 |
+
"step": 3577
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 10.33,
|
| 307 |
+
"learning_rate": 6.691292236889913e-05,
|
| 308 |
+
"loss": 0.0689,
|
| 309 |
+
"step": 3650
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 10.53,
|
| 313 |
+
"learning_rate": 6.602882402809738e-05,
|
| 314 |
+
"loss": 0.0747,
|
| 315 |
+
"step": 3723
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 10.72,
|
| 319 |
+
"learning_rate": 6.514472568729563e-05,
|
| 320 |
+
"loss": 0.0728,
|
| 321 |
+
"step": 3796
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 10.92,
|
| 325 |
+
"learning_rate": 6.426062734649388e-05,
|
| 326 |
+
"loss": 0.0762,
|
| 327 |
+
"step": 3869
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 11.16,
|
| 331 |
+
"learning_rate": 6.337652900569214e-05,
|
| 332 |
+
"loss": 0.0693,
|
| 333 |
+
"step": 3942
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 11.36,
|
| 337 |
+
"learning_rate": 6.24924306648904e-05,
|
| 338 |
+
"loss": 0.0611,
|
| 339 |
+
"step": 4015
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 11.56,
|
| 343 |
+
"learning_rate": 6.160833232408865e-05,
|
| 344 |
+
"loss": 0.0616,
|
| 345 |
+
"step": 4088
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 11.76,
|
| 349 |
+
"learning_rate": 6.072423398328692e-05,
|
| 350 |
+
"loss": 0.064,
|
| 351 |
+
"step": 4161
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 11.96,
|
| 355 |
+
"learning_rate": 5.984013564248516e-05,
|
| 356 |
+
"loss": 0.0637,
|
| 357 |
+
"step": 4234
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 12.19,
|
| 361 |
+
"learning_rate": 5.895603730168342e-05,
|
| 362 |
+
"loss": 0.0548,
|
| 363 |
+
"step": 4307
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 12.39,
|
| 367 |
+
"learning_rate": 5.8071938960881676e-05,
|
| 368 |
+
"loss": 0.0583,
|
| 369 |
+
"step": 4380
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 12.59,
|
| 373 |
+
"learning_rate": 5.718784062007993e-05,
|
| 374 |
+
"loss": 0.0547,
|
| 375 |
+
"step": 4453
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 12.79,
|
| 379 |
+
"learning_rate": 5.630374227927819e-05,
|
| 380 |
+
"loss": 0.0543,
|
| 381 |
+
"step": 4526
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 13.03,
|
| 385 |
+
"learning_rate": 5.5419643938476454e-05,
|
| 386 |
+
"loss": 0.0543,
|
| 387 |
+
"step": 4599
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 13.23,
|
| 391 |
+
"learning_rate": 5.45355455976747e-05,
|
| 392 |
+
"loss": 0.0479,
|
| 393 |
+
"step": 4672
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 13.43,
|
| 397 |
+
"learning_rate": 5.3651447256872954e-05,
|
| 398 |
+
"loss": 0.0517,
|
| 399 |
+
"step": 4745
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 13.62,
|
| 403 |
+
"learning_rate": 5.276734891607121e-05,
|
| 404 |
+
"loss": 0.0466,
|
| 405 |
+
"step": 4818
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 13.82,
|
| 409 |
+
"learning_rate": 5.188325057526947e-05,
|
| 410 |
+
"loss": 0.0499,
|
| 411 |
+
"step": 4891
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 14.06,
|
| 415 |
+
"learning_rate": 5.0999152234467725e-05,
|
| 416 |
+
"loss": 0.0479,
|
| 417 |
+
"step": 4964
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 14.26,
|
| 421 |
+
"learning_rate": 5.011505389366599e-05,
|
| 422 |
+
"loss": 0.0408,
|
| 423 |
+
"step": 5037
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 14.46,
|
| 427 |
+
"learning_rate": 4.923095555286424e-05,
|
| 428 |
+
"loss": 0.0425,
|
| 429 |
+
"step": 5110
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 14.66,
|
| 433 |
+
"learning_rate": 4.8346857212062496e-05,
|
| 434 |
+
"loss": 0.0452,
|
| 435 |
+
"step": 5183
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 14.86,
|
| 439 |
+
"learning_rate": 4.746275887126075e-05,
|
| 440 |
+
"loss": 0.0462,
|
| 441 |
+
"step": 5256
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 15.09,
|
| 445 |
+
"learning_rate": 4.6578660530459004e-05,
|
| 446 |
+
"loss": 0.0452,
|
| 447 |
+
"step": 5329
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 15.29,
|
| 451 |
+
"learning_rate": 4.569456218965726e-05,
|
| 452 |
+
"loss": 0.0371,
|
| 453 |
+
"step": 5402
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 15.49,
|
| 457 |
+
"learning_rate": 4.481046384885552e-05,
|
| 458 |
+
"loss": 0.0404,
|
| 459 |
+
"step": 5475
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 15.69,
|
| 463 |
+
"learning_rate": 4.3926365508053775e-05,
|
| 464 |
+
"loss": 0.0418,
|
| 465 |
+
"step": 5548
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 15.89,
|
| 469 |
+
"learning_rate": 4.304226716725203e-05,
|
| 470 |
+
"loss": 0.0405,
|
| 471 |
+
"step": 5621
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 16.13,
|
| 475 |
+
"learning_rate": 4.215816882645028e-05,
|
| 476 |
+
"loss": 0.0365,
|
| 477 |
+
"step": 5694
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 16.32,
|
| 481 |
+
"learning_rate": 4.127407048564854e-05,
|
| 482 |
+
"loss": 0.0368,
|
| 483 |
+
"step": 5767
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 16.52,
|
| 487 |
+
"learning_rate": 4.03899721448468e-05,
|
| 488 |
+
"loss": 0.0348,
|
| 489 |
+
"step": 5840
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 16.72,
|
| 493 |
+
"learning_rate": 3.950587380404506e-05,
|
| 494 |
+
"loss": 0.0347,
|
| 495 |
+
"step": 5913
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 16.92,
|
| 499 |
+
"learning_rate": 3.862177546324331e-05,
|
| 500 |
+
"loss": 0.0409,
|
| 501 |
+
"step": 5986
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 17.16,
|
| 505 |
+
"learning_rate": 3.773767712244157e-05,
|
| 506 |
+
"loss": 0.035,
|
| 507 |
+
"step": 6059
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 17.36,
|
| 511 |
+
"learning_rate": 3.6853578781639824e-05,
|
| 512 |
+
"loss": 0.0317,
|
| 513 |
+
"step": 6132
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 17.56,
|
| 517 |
+
"learning_rate": 3.5969480440838074e-05,
|
| 518 |
+
"loss": 0.0339,
|
| 519 |
+
"step": 6205
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 17.75,
|
| 523 |
+
"learning_rate": 3.508538210003634e-05,
|
| 524 |
+
"loss": 0.034,
|
| 525 |
+
"step": 6278
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 17.95,
|
| 529 |
+
"learning_rate": 3.4201283759234595e-05,
|
| 530 |
+
"loss": 0.0336,
|
| 531 |
+
"step": 6351
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 18.19,
|
| 535 |
+
"learning_rate": 3.3317185418432845e-05,
|
| 536 |
+
"loss": 0.0306,
|
| 537 |
+
"step": 6424
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 18.39,
|
| 541 |
+
"learning_rate": 3.24330870776311e-05,
|
| 542 |
+
"loss": 0.0312,
|
| 543 |
+
"step": 6497
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 18.59,
|
| 547 |
+
"learning_rate": 3.154898873682936e-05,
|
| 548 |
+
"loss": 0.0298,
|
| 549 |
+
"step": 6570
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 18.79,
|
| 553 |
+
"learning_rate": 3.066489039602761e-05,
|
| 554 |
+
"loss": 0.0322,
|
| 555 |
+
"step": 6643
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 19.02,
|
| 559 |
+
"learning_rate": 2.978079205522587e-05,
|
| 560 |
+
"loss": 0.0301,
|
| 561 |
+
"step": 6716
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 19.22,
|
| 565 |
+
"learning_rate": 2.8896693714424127e-05,
|
| 566 |
+
"loss": 0.0297,
|
| 567 |
+
"step": 6789
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 19.42,
|
| 571 |
+
"learning_rate": 2.801259537362238e-05,
|
| 572 |
+
"loss": 0.0282,
|
| 573 |
+
"step": 6862
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 19.62,
|
| 577 |
+
"learning_rate": 2.7128497032820637e-05,
|
| 578 |
+
"loss": 0.0283,
|
| 579 |
+
"step": 6935
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 19.82,
|
| 583 |
+
"learning_rate": 2.6244398692018894e-05,
|
| 584 |
+
"loss": 0.0293,
|
| 585 |
+
"step": 7008
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 20.06,
|
| 589 |
+
"learning_rate": 2.5360300351217148e-05,
|
| 590 |
+
"loss": 0.0294,
|
| 591 |
+
"step": 7081
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 20.26,
|
| 595 |
+
"learning_rate": 2.4476202010415405e-05,
|
| 596 |
+
"loss": 0.0264,
|
| 597 |
+
"step": 7154
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 20.46,
|
| 601 |
+
"learning_rate": 2.3592103669613662e-05,
|
| 602 |
+
"loss": 0.026,
|
| 603 |
+
"step": 7227
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 20.65,
|
| 607 |
+
"learning_rate": 2.270800532881192e-05,
|
| 608 |
+
"loss": 0.0294,
|
| 609 |
+
"step": 7300
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 20.85,
|
| 613 |
+
"learning_rate": 2.1823906988010173e-05,
|
| 614 |
+
"loss": 0.0285,
|
| 615 |
+
"step": 7373
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 21.09,
|
| 619 |
+
"learning_rate": 2.093980864720843e-05,
|
| 620 |
+
"loss": 0.0269,
|
| 621 |
+
"step": 7446
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 21.29,
|
| 625 |
+
"learning_rate": 2.0055710306406687e-05,
|
| 626 |
+
"loss": 0.0258,
|
| 627 |
+
"step": 7519
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 21.49,
|
| 631 |
+
"learning_rate": 1.917161196560494e-05,
|
| 632 |
+
"loss": 0.0254,
|
| 633 |
+
"step": 7592
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 21.69,
|
| 637 |
+
"learning_rate": 1.8287513624803197e-05,
|
| 638 |
+
"loss": 0.0278,
|
| 639 |
+
"step": 7665
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 21.89,
|
| 643 |
+
"learning_rate": 1.7403415284001454e-05,
|
| 644 |
+
"loss": 0.0262,
|
| 645 |
+
"step": 7738
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 22.12,
|
| 649 |
+
"learning_rate": 1.651931694319971e-05,
|
| 650 |
+
"loss": 0.0245,
|
| 651 |
+
"step": 7811
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 22.32,
|
| 655 |
+
"learning_rate": 1.5635218602397965e-05,
|
| 656 |
+
"loss": 0.0249,
|
| 657 |
+
"step": 7884
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 22.52,
|
| 661 |
+
"learning_rate": 1.4751120261596222e-05,
|
| 662 |
+
"loss": 0.0244,
|
| 663 |
+
"step": 7957
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 22.72,
|
| 667 |
+
"learning_rate": 1.3867021920794479e-05,
|
| 668 |
+
"loss": 0.0255,
|
| 669 |
+
"step": 8030
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 22.92,
|
| 673 |
+
"learning_rate": 1.2982923579992734e-05,
|
| 674 |
+
"loss": 0.0256,
|
| 675 |
+
"step": 8103
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 23.16,
|
| 679 |
+
"learning_rate": 1.209882523919099e-05,
|
| 680 |
+
"loss": 0.0244,
|
| 681 |
+
"step": 8176
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 23.35,
|
| 685 |
+
"learning_rate": 1.1214726898389245e-05,
|
| 686 |
+
"loss": 0.0235,
|
| 687 |
+
"step": 8249
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 23.55,
|
| 691 |
+
"learning_rate": 1.0330628557587502e-05,
|
| 692 |
+
"loss": 0.0252,
|
| 693 |
+
"step": 8322
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 23.75,
|
| 697 |
+
"learning_rate": 9.446530216785757e-06,
|
| 698 |
+
"loss": 0.0248,
|
| 699 |
+
"step": 8395
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 23.95,
|
| 703 |
+
"learning_rate": 8.562431875984014e-06,
|
| 704 |
+
"loss": 0.024,
|
| 705 |
+
"step": 8468
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 24.19,
|
| 709 |
+
"learning_rate": 7.67833353518227e-06,
|
| 710 |
+
"loss": 0.0244,
|
| 711 |
+
"step": 8541
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 24.39,
|
| 715 |
+
"learning_rate": 6.794235194380526e-06,
|
| 716 |
+
"loss": 0.023,
|
| 717 |
+
"step": 8614
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 24.59,
|
| 721 |
+
"learning_rate": 5.910136853578782e-06,
|
| 722 |
+
"loss": 0.024,
|
| 723 |
+
"step": 8687
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 24.78,
|
| 727 |
+
"learning_rate": 5.026038512777038e-06,
|
| 728 |
+
"loss": 0.0238,
|
| 729 |
+
"step": 8760
|
| 730 |
+
}
|
| 731 |
+
],
|
| 732 |
+
"logging_steps": 73,
|
| 733 |
+
"max_steps": 9175,
|
| 734 |
+
"num_train_epochs": 25,
|
| 735 |
+
"save_steps": 500,
|
| 736 |
+
"total_flos": 7.7154619490304e+17,
|
| 737 |
+
"trial_name": null,
|
| 738 |
+
"trial_params": null
|
| 739 |
+
}
|
checkpoint-8825/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70536fcd5a2e2254cc30124d6e3220ceb50c7e16d4c016d7dd0599ac6a6c61fc
|
| 3 |
+
size 4091
|
runs/Oct02_17-08-29_AM-3080TI-VR-PC/events.out.tfevents.1696262910.AM-3080TI-VR-PC.781.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c891ac60415669a10253db96686e25ea5a6930436b503068e212a82d408870cb
|
| 3 |
+
size 23729
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": "<s>",
|
| 3 |
+
"eos_token": "</s>",
|
| 4 |
+
"pad_token": "</s>",
|
| 5 |
+
"unk_token": "<unk>"
|
| 6 |
+
}
|
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 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"bos_token": "<s>",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": true,
|
| 33 |
+
"model_max_length": 1024,
|
| 34 |
+
"pad_token": null,
|
| 35 |
+
"sp_model_kwargs": {},
|
| 36 |
+
"spaces_between_special_tokens": false,
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": true
|
| 40 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70536fcd5a2e2254cc30124d6e3220ceb50c7e16d4c016d7dd0599ac6a6c61fc
|
| 3 |
+
size 4091
|
training_params.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model": "bn22/Mistral-7B-Instruct-v0.1-sharded", "data_path": "YL95/naive_chunk0", "project_name": "mistral_naive_chunk_q_proj", "train_split": "train", "valid_split": null, "text_column": "text", "lr": 0.0001, "epochs": 25, "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": 95, "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": 1024, "repo_id": "YL95/mistral_naive_chunk_q_proj0", "use_int4": true, "trainer": "sft", "target_modules": "q_proj", "merge_adapter": false, "username": "YL95", "use_flash_attention_2": false}
|