Upload 13 files
Browse files- README.md +32 -1
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- pytorch_model.bin +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +40 -0
- trainer_state.json +529 -0
- training_args.bin +3 -0
README.md
CHANGED
|
@@ -1,3 +1,34 @@
|
|
| 1 |
---
|
| 2 |
-
|
| 3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 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 |
+
],
|
| 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:f98bbfcbe659cc25dfbee18f97558c617e8fa2ef5fd232dd8600415f43b13153
|
| 3 |
+
size 27308941
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66588c3855a4d071abb185a5de29d58636628b20737db45de801babef2e48b86
|
| 3 |
+
size 54633541
|
pytorch_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
|
| 3 |
+
size 443
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e4d65916d2dcd7f044bff5e79288a434f41a223a734e1f4a58f6f2ac6b137b57
|
| 3 |
+
size 14575
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5cacd2a6d3db6e47d0be401d663dd74996b2fd50a8b99969cbd48df91dd275a7
|
| 3 |
+
size 627
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.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": "</s>",
|
| 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 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 68.0,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 3094,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.79,
|
| 13 |
+
"learning_rate": 1.5555555555555555e-05,
|
| 14 |
+
"loss": 2.3054,
|
| 15 |
+
"step": 36
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 1.58,
|
| 19 |
+
"learning_rate": 3.155555555555556e-05,
|
| 20 |
+
"loss": 2.1949,
|
| 21 |
+
"step": 72
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 2.37,
|
| 25 |
+
"learning_rate": 4.755555555555556e-05,
|
| 26 |
+
"loss": 1.978,
|
| 27 |
+
"step": 108
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 3.16,
|
| 31 |
+
"learning_rate": 6.355555555555556e-05,
|
| 32 |
+
"loss": 1.9161,
|
| 33 |
+
"step": 144
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 3.96,
|
| 37 |
+
"learning_rate": 7.955555555555556e-05,
|
| 38 |
+
"loss": 1.8945,
|
| 39 |
+
"step": 180
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 4.75,
|
| 43 |
+
"learning_rate": 9.555555555555557e-05,
|
| 44 |
+
"loss": 1.8682,
|
| 45 |
+
"step": 216
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 5.54,
|
| 49 |
+
"learning_rate": 0.00011155555555555556,
|
| 50 |
+
"loss": 1.8492,
|
| 51 |
+
"step": 252
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 6.33,
|
| 55 |
+
"learning_rate": 0.00012755555555555556,
|
| 56 |
+
"loss": 1.8337,
|
| 57 |
+
"step": 288
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 7.12,
|
| 61 |
+
"learning_rate": 0.0001431111111111111,
|
| 62 |
+
"loss": 1.8144,
|
| 63 |
+
"step": 324
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 7.91,
|
| 67 |
+
"learning_rate": 0.00015911111111111112,
|
| 68 |
+
"loss": 1.7907,
|
| 69 |
+
"step": 360
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 8.7,
|
| 73 |
+
"learning_rate": 0.00017511111111111113,
|
| 74 |
+
"loss": 1.7382,
|
| 75 |
+
"step": 396
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 9.49,
|
| 79 |
+
"learning_rate": 0.00019111111111111114,
|
| 80 |
+
"loss": 1.6991,
|
| 81 |
+
"step": 432
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 10.29,
|
| 85 |
+
"learning_rate": 0.00019925925925925927,
|
| 86 |
+
"loss": 1.6405,
|
| 87 |
+
"step": 468
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 11.08,
|
| 91 |
+
"learning_rate": 0.00019748148148148148,
|
| 92 |
+
"loss": 1.5929,
|
| 93 |
+
"step": 504
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 11.87,
|
| 97 |
+
"learning_rate": 0.0001957037037037037,
|
| 98 |
+
"loss": 1.5414,
|
| 99 |
+
"step": 540
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 12.66,
|
| 103 |
+
"learning_rate": 0.00019392592592592592,
|
| 104 |
+
"loss": 1.447,
|
| 105 |
+
"step": 576
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 13.45,
|
| 109 |
+
"learning_rate": 0.00019214814814814816,
|
| 110 |
+
"loss": 1.3947,
|
| 111 |
+
"step": 612
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 14.24,
|
| 115 |
+
"learning_rate": 0.00019037037037037037,
|
| 116 |
+
"loss": 1.3655,
|
| 117 |
+
"step": 648
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 15.03,
|
| 121 |
+
"learning_rate": 0.0001885925925925926,
|
| 122 |
+
"loss": 1.2873,
|
| 123 |
+
"step": 684
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 15.82,
|
| 127 |
+
"learning_rate": 0.0001868148148148148,
|
| 128 |
+
"loss": 1.2198,
|
| 129 |
+
"step": 720
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 16.62,
|
| 133 |
+
"learning_rate": 0.00018503703703703705,
|
| 134 |
+
"loss": 1.1512,
|
| 135 |
+
"step": 756
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 17.41,
|
| 139 |
+
"learning_rate": 0.00018325925925925926,
|
| 140 |
+
"loss": 1.1286,
|
| 141 |
+
"step": 792
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 18.2,
|
| 145 |
+
"learning_rate": 0.0001814814814814815,
|
| 146 |
+
"loss": 1.0709,
|
| 147 |
+
"step": 828
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 18.99,
|
| 151 |
+
"learning_rate": 0.0001797037037037037,
|
| 152 |
+
"loss": 1.0442,
|
| 153 |
+
"step": 864
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 19.78,
|
| 157 |
+
"learning_rate": 0.00017792592592592594,
|
| 158 |
+
"loss": 0.971,
|
| 159 |
+
"step": 900
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 20.57,
|
| 163 |
+
"learning_rate": 0.00017614814814814815,
|
| 164 |
+
"loss": 0.9412,
|
| 165 |
+
"step": 936
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 21.36,
|
| 169 |
+
"learning_rate": 0.00017437037037037039,
|
| 170 |
+
"loss": 0.9084,
|
| 171 |
+
"step": 972
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 22.15,
|
| 175 |
+
"learning_rate": 0.0001725925925925926,
|
| 176 |
+
"loss": 0.885,
|
| 177 |
+
"step": 1008
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 22.95,
|
| 181 |
+
"learning_rate": 0.00017081481481481483,
|
| 182 |
+
"loss": 0.844,
|
| 183 |
+
"step": 1044
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 23.74,
|
| 187 |
+
"learning_rate": 0.00016903703703703704,
|
| 188 |
+
"loss": 0.7975,
|
| 189 |
+
"step": 1080
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 24.53,
|
| 193 |
+
"learning_rate": 0.00016725925925925928,
|
| 194 |
+
"loss": 0.7786,
|
| 195 |
+
"step": 1116
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 25.32,
|
| 199 |
+
"learning_rate": 0.00016548148148148149,
|
| 200 |
+
"loss": 0.7465,
|
| 201 |
+
"step": 1152
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 26.11,
|
| 205 |
+
"learning_rate": 0.00016370370370370372,
|
| 206 |
+
"loss": 0.7311,
|
| 207 |
+
"step": 1188
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 26.9,
|
| 211 |
+
"learning_rate": 0.00016192592592592593,
|
| 212 |
+
"loss": 0.6955,
|
| 213 |
+
"step": 1224
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 27.69,
|
| 217 |
+
"learning_rate": 0.00016014814814814817,
|
| 218 |
+
"loss": 0.6656,
|
| 219 |
+
"step": 1260
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 28.48,
|
| 223 |
+
"learning_rate": 0.00015837037037037038,
|
| 224 |
+
"loss": 0.6507,
|
| 225 |
+
"step": 1296
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 29.27,
|
| 229 |
+
"learning_rate": 0.0001565925925925926,
|
| 230 |
+
"loss": 0.6336,
|
| 231 |
+
"step": 1332
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 30.07,
|
| 235 |
+
"learning_rate": 0.00015481481481481482,
|
| 236 |
+
"loss": 0.6142,
|
| 237 |
+
"step": 1368
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 30.86,
|
| 241 |
+
"learning_rate": 0.00015303703703703706,
|
| 242 |
+
"loss": 0.5865,
|
| 243 |
+
"step": 1404
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 31.65,
|
| 247 |
+
"learning_rate": 0.00015125925925925927,
|
| 248 |
+
"loss": 0.5649,
|
| 249 |
+
"step": 1440
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 32.44,
|
| 253 |
+
"learning_rate": 0.00014948148148148148,
|
| 254 |
+
"loss": 0.5511,
|
| 255 |
+
"step": 1476
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 33.23,
|
| 259 |
+
"learning_rate": 0.0001477037037037037,
|
| 260 |
+
"loss": 0.5329,
|
| 261 |
+
"step": 1512
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 34.02,
|
| 265 |
+
"learning_rate": 0.00014592592592592592,
|
| 266 |
+
"loss": 0.5265,
|
| 267 |
+
"step": 1548
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 34.81,
|
| 271 |
+
"learning_rate": 0.00014414814814814816,
|
| 272 |
+
"loss": 0.4931,
|
| 273 |
+
"step": 1584
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 35.6,
|
| 277 |
+
"learning_rate": 0.00014237037037037037,
|
| 278 |
+
"loss": 0.4904,
|
| 279 |
+
"step": 1620
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 36.4,
|
| 283 |
+
"learning_rate": 0.0001405925925925926,
|
| 284 |
+
"loss": 0.466,
|
| 285 |
+
"step": 1656
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 37.19,
|
| 289 |
+
"learning_rate": 0.0001388148148148148,
|
| 290 |
+
"loss": 0.4585,
|
| 291 |
+
"step": 1692
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 37.98,
|
| 295 |
+
"learning_rate": 0.00013703703703703705,
|
| 296 |
+
"loss": 0.4545,
|
| 297 |
+
"step": 1728
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 38.77,
|
| 301 |
+
"learning_rate": 0.00013525925925925926,
|
| 302 |
+
"loss": 0.4244,
|
| 303 |
+
"step": 1764
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 39.56,
|
| 307 |
+
"learning_rate": 0.0001334814814814815,
|
| 308 |
+
"loss": 0.4143,
|
| 309 |
+
"step": 1800
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 40.35,
|
| 313 |
+
"learning_rate": 0.0001317037037037037,
|
| 314 |
+
"loss": 0.4118,
|
| 315 |
+
"step": 1836
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 41.14,
|
| 319 |
+
"learning_rate": 0.00012992592592592594,
|
| 320 |
+
"loss": 0.3963,
|
| 321 |
+
"step": 1872
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 41.93,
|
| 325 |
+
"learning_rate": 0.00012814814814814815,
|
| 326 |
+
"loss": 0.3901,
|
| 327 |
+
"step": 1908
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 42.73,
|
| 331 |
+
"learning_rate": 0.00012637037037037038,
|
| 332 |
+
"loss": 0.3697,
|
| 333 |
+
"step": 1944
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 43.52,
|
| 337 |
+
"learning_rate": 0.0001245925925925926,
|
| 338 |
+
"loss": 0.3595,
|
| 339 |
+
"step": 1980
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 44.31,
|
| 343 |
+
"learning_rate": 0.00012281481481481483,
|
| 344 |
+
"loss": 0.3609,
|
| 345 |
+
"step": 2016
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 45.1,
|
| 349 |
+
"learning_rate": 0.00012103703703703704,
|
| 350 |
+
"loss": 0.3457,
|
| 351 |
+
"step": 2052
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 45.89,
|
| 355 |
+
"learning_rate": 0.00011925925925925927,
|
| 356 |
+
"loss": 0.3342,
|
| 357 |
+
"step": 2088
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 46.68,
|
| 361 |
+
"learning_rate": 0.00011748148148148148,
|
| 362 |
+
"loss": 0.3213,
|
| 363 |
+
"step": 2124
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 47.47,
|
| 367 |
+
"learning_rate": 0.00011570370370370372,
|
| 368 |
+
"loss": 0.3183,
|
| 369 |
+
"step": 2160
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 48.26,
|
| 373 |
+
"learning_rate": 0.00011392592592592593,
|
| 374 |
+
"loss": 0.3067,
|
| 375 |
+
"step": 2196
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 49.05,
|
| 379 |
+
"learning_rate": 0.00011214814814814815,
|
| 380 |
+
"loss": 0.3062,
|
| 381 |
+
"step": 2232
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 49.85,
|
| 385 |
+
"learning_rate": 0.00011037037037037037,
|
| 386 |
+
"loss": 0.291,
|
| 387 |
+
"step": 2268
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 50.64,
|
| 391 |
+
"learning_rate": 0.0001085925925925926,
|
| 392 |
+
"loss": 0.2837,
|
| 393 |
+
"step": 2304
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 51.43,
|
| 397 |
+
"learning_rate": 0.0001068148148148148,
|
| 398 |
+
"loss": 0.2768,
|
| 399 |
+
"step": 2340
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 52.22,
|
| 403 |
+
"learning_rate": 0.00010503703703703704,
|
| 404 |
+
"loss": 0.2733,
|
| 405 |
+
"step": 2376
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 53.01,
|
| 409 |
+
"learning_rate": 0.00010325925925925925,
|
| 410 |
+
"loss": 0.2622,
|
| 411 |
+
"step": 2412
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 53.8,
|
| 415 |
+
"learning_rate": 0.00010148148148148149,
|
| 416 |
+
"loss": 0.254,
|
| 417 |
+
"step": 2448
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 54.59,
|
| 421 |
+
"learning_rate": 9.970370370370371e-05,
|
| 422 |
+
"loss": 0.247,
|
| 423 |
+
"step": 2484
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 55.38,
|
| 427 |
+
"learning_rate": 9.792592592592593e-05,
|
| 428 |
+
"loss": 0.2415,
|
| 429 |
+
"step": 2520
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 56.18,
|
| 433 |
+
"learning_rate": 9.614814814814816e-05,
|
| 434 |
+
"loss": 0.2391,
|
| 435 |
+
"step": 2556
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 56.97,
|
| 439 |
+
"learning_rate": 9.437037037037038e-05,
|
| 440 |
+
"loss": 0.2318,
|
| 441 |
+
"step": 2592
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 57.76,
|
| 445 |
+
"learning_rate": 9.25925925925926e-05,
|
| 446 |
+
"loss": 0.221,
|
| 447 |
+
"step": 2628
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 58.55,
|
| 451 |
+
"learning_rate": 9.081481481481482e-05,
|
| 452 |
+
"loss": 0.2179,
|
| 453 |
+
"step": 2664
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 59.34,
|
| 457 |
+
"learning_rate": 8.903703703703705e-05,
|
| 458 |
+
"loss": 0.2145,
|
| 459 |
+
"step": 2700
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 60.13,
|
| 463 |
+
"learning_rate": 8.725925925925927e-05,
|
| 464 |
+
"loss": 0.209,
|
| 465 |
+
"step": 2736
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 60.92,
|
| 469 |
+
"learning_rate": 8.548148148148148e-05,
|
| 470 |
+
"loss": 0.205,
|
| 471 |
+
"step": 2772
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 61.71,
|
| 475 |
+
"learning_rate": 8.37037037037037e-05,
|
| 476 |
+
"loss": 0.197,
|
| 477 |
+
"step": 2808
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 62.51,
|
| 481 |
+
"learning_rate": 8.192592592592592e-05,
|
| 482 |
+
"loss": 0.1948,
|
| 483 |
+
"step": 2844
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 63.3,
|
| 487 |
+
"learning_rate": 8.014814814814815e-05,
|
| 488 |
+
"loss": 0.188,
|
| 489 |
+
"step": 2880
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 64.09,
|
| 493 |
+
"learning_rate": 7.837037037037037e-05,
|
| 494 |
+
"loss": 0.188,
|
| 495 |
+
"step": 2916
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 64.88,
|
| 499 |
+
"learning_rate": 7.659259259259259e-05,
|
| 500 |
+
"loss": 0.1785,
|
| 501 |
+
"step": 2952
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 65.67,
|
| 505 |
+
"learning_rate": 7.481481481481481e-05,
|
| 506 |
+
"loss": 0.1758,
|
| 507 |
+
"step": 2988
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 66.46,
|
| 511 |
+
"learning_rate": 7.303703703703704e-05,
|
| 512 |
+
"loss": 0.1703,
|
| 513 |
+
"step": 3024
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 67.25,
|
| 517 |
+
"learning_rate": 7.125925925925926e-05,
|
| 518 |
+
"loss": 0.1702,
|
| 519 |
+
"step": 3060
|
| 520 |
+
}
|
| 521 |
+
],
|
| 522 |
+
"logging_steps": 36,
|
| 523 |
+
"max_steps": 4500,
|
| 524 |
+
"num_train_epochs": 100,
|
| 525 |
+
"save_steps": 500,
|
| 526 |
+
"total_flos": 2.6941037663276237e+18,
|
| 527 |
+
"trial_name": null,
|
| 528 |
+
"trial_params": null
|
| 529 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83ffe018190aca9df723f8c9b9ebe7cee2a8e4f04061c455fb99d0ca746c646c
|
| 3 |
+
size 4027
|