Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- checkpoint-160/README.md +34 -0
- checkpoint-160/adapter_config.json +21 -0
- checkpoint-160/adapter_model.bin +3 -0
- checkpoint-160/optimizer.pt +3 -0
- checkpoint-160/rng_state.pth +3 -0
- checkpoint-160/scheduler.pt +3 -0
- checkpoint-160/special_tokens_map.json +24 -0
- checkpoint-160/tokenizer.json +0 -0
- checkpoint-160/tokenizer.model +3 -0
- checkpoint-160/tokenizer_config.json +36 -0
- checkpoint-160/trainer_state.json +979 -0
- checkpoint-160/training_args.bin +3 -0
- runs/Aug26_07-31-31_s-yaleh-autotrain-9780-igpa-vu5r-0-f9999-bb4957c87-bx4xv/events.out.tfevents.1693035092.s-yaleh-autotrain-9780-igpa-vu5r-0-f9999-bb4957c87-bx4xv.55.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +36 -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": "openlm-research/open_llama_3b_v2",
|
| 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": 0.1,
|
| 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 sha256:9462657721b93acdb2741fe743bab6b788fe34ac6c317aa038e2b3620b80a1d7
|
| 3 |
+
size 21336301
|
checkpoint-160/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-160/adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "openlm-research/open_llama_3b_v2",
|
| 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": 0.1,
|
| 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-160/adapter_model.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9462657721b93acdb2741fe743bab6b788fe34ac6c317aa038e2b3620b80a1d7
|
| 3 |
+
size 21336301
|
checkpoint-160/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c75c4fa8f3a0d6f48951386b484afce26cfc592603963205c161419db5ed65e
|
| 3 |
+
size 42685509
|
checkpoint-160/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0d15d3ce454e082b616a41e390bd09e3a4e7a62936f6dbeac8d92d729313e77
|
| 3 |
+
size 14575
|
checkpoint-160/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c768e28e5ca9944161cff6802bdcef84159a94c7597e9eb479793133648272b6
|
| 3 |
+
size 627
|
checkpoint-160/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": "</s>",
|
| 17 |
+
"unk_token": {
|
| 18 |
+
"content": "<unk>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": true,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
}
|
| 24 |
+
}
|
checkpoint-160/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
checkpoint-160/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
|
| 3 |
+
size 511574
|
checkpoint-160/tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": null,
|
| 22 |
+
"model_max_length": 2048,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"sp_model_kwargs": {},
|
| 25 |
+
"spaces_between_special_tokens": false,
|
| 26 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"use_default_system_prompt": true
|
| 36 |
+
}
|
checkpoint-160/trainer_state.json
ADDED
|
@@ -0,0 +1,979 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 79.66666666666667,
|
| 5 |
+
"eval_steps": 500,
|
| 6 |
+
"global_step": 160,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.33,
|
| 13 |
+
"learning_rate": 8.333333333333334e-06,
|
| 14 |
+
"loss": 1.1639,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.67,
|
| 19 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 20 |
+
"loss": 1.3083,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 1.33,
|
| 25 |
+
"learning_rate": 2.5e-05,
|
| 26 |
+
"loss": 1.2833,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 1.67,
|
| 31 |
+
"learning_rate": 3.3333333333333335e-05,
|
| 32 |
+
"loss": 1.063,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 2.33,
|
| 37 |
+
"learning_rate": 4.166666666666667e-05,
|
| 38 |
+
"loss": 1.2734,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 2.67,
|
| 43 |
+
"learning_rate": 5e-05,
|
| 44 |
+
"loss": 1.0514,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 3.33,
|
| 49 |
+
"learning_rate": 5.833333333333334e-05,
|
| 50 |
+
"loss": 1.2548,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 3.67,
|
| 55 |
+
"learning_rate": 6.666666666666667e-05,
|
| 56 |
+
"loss": 1.0294,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 4.33,
|
| 61 |
+
"learning_rate": 7.500000000000001e-05,
|
| 62 |
+
"loss": 1.1073,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 4.67,
|
| 67 |
+
"learning_rate": 8.333333333333334e-05,
|
| 68 |
+
"loss": 1.2405,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 5.33,
|
| 73 |
+
"learning_rate": 9.166666666666667e-05,
|
| 74 |
+
"loss": 1.0698,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 5.67,
|
| 79 |
+
"learning_rate": 0.0001,
|
| 80 |
+
"loss": 1.1991,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 6.33,
|
| 85 |
+
"learning_rate": 0.00010833333333333333,
|
| 86 |
+
"loss": 1.1373,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 6.67,
|
| 91 |
+
"learning_rate": 0.00011666666666666668,
|
| 92 |
+
"loss": 0.9128,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 7.33,
|
| 97 |
+
"learning_rate": 0.000125,
|
| 98 |
+
"loss": 1.0715,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 7.67,
|
| 103 |
+
"learning_rate": 0.00013333333333333334,
|
| 104 |
+
"loss": 0.8506,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 8.33,
|
| 109 |
+
"learning_rate": 0.00014166666666666668,
|
| 110 |
+
"loss": 0.9949,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 8.67,
|
| 115 |
+
"learning_rate": 0.00015000000000000001,
|
| 116 |
+
"loss": 0.7717,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 9.33,
|
| 121 |
+
"learning_rate": 0.00015833333333333332,
|
| 122 |
+
"loss": 0.7952,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 9.67,
|
| 127 |
+
"learning_rate": 0.0001666666666666667,
|
| 128 |
+
"loss": 0.896,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 10.33,
|
| 133 |
+
"learning_rate": 0.000175,
|
| 134 |
+
"loss": 0.6957,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 10.67,
|
| 139 |
+
"learning_rate": 0.00018333333333333334,
|
| 140 |
+
"loss": 0.7991,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 11.33,
|
| 145 |
+
"learning_rate": 0.00019166666666666667,
|
| 146 |
+
"loss": 0.7089,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 11.67,
|
| 151 |
+
"learning_rate": 0.0002,
|
| 152 |
+
"loss": 0.4713,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 12.33,
|
| 157 |
+
"learning_rate": 0.0001990740740740741,
|
| 158 |
+
"loss": 0.4991,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 12.67,
|
| 163 |
+
"learning_rate": 0.00019814814814814814,
|
| 164 |
+
"loss": 0.5723,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 13.33,
|
| 169 |
+
"learning_rate": 0.00019722222222222225,
|
| 170 |
+
"loss": 0.5015,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 13.67,
|
| 175 |
+
"learning_rate": 0.0001962962962962963,
|
| 176 |
+
"loss": 0.2964,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 14.33,
|
| 181 |
+
"learning_rate": 0.00019537037037037038,
|
| 182 |
+
"loss": 0.3209,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 14.67,
|
| 187 |
+
"learning_rate": 0.00019444444444444446,
|
| 188 |
+
"loss": 0.4046,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 15.33,
|
| 193 |
+
"learning_rate": 0.0001935185185185185,
|
| 194 |
+
"loss": 0.2672,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 15.67,
|
| 199 |
+
"learning_rate": 0.0001925925925925926,
|
| 200 |
+
"loss": 0.3041,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 16.33,
|
| 205 |
+
"learning_rate": 0.00019166666666666667,
|
| 206 |
+
"loss": 0.2688,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 16.67,
|
| 211 |
+
"learning_rate": 0.00019074074074074075,
|
| 212 |
+
"loss": 0.1287,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 17.33,
|
| 217 |
+
"learning_rate": 0.00018981481481481483,
|
| 218 |
+
"loss": 0.1681,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 17.67,
|
| 223 |
+
"learning_rate": 0.00018888888888888888,
|
| 224 |
+
"loss": 0.1952,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 18.33,
|
| 229 |
+
"learning_rate": 0.00018796296296296296,
|
| 230 |
+
"loss": 0.1729,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 18.67,
|
| 235 |
+
"learning_rate": 0.00018703703703703704,
|
| 236 |
+
"loss": 0.0856,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 19.33,
|
| 241 |
+
"learning_rate": 0.00018611111111111112,
|
| 242 |
+
"loss": 0.1393,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 19.67,
|
| 247 |
+
"learning_rate": 0.0001851851851851852,
|
| 248 |
+
"loss": 0.0723,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 20.33,
|
| 253 |
+
"learning_rate": 0.00018425925925925926,
|
| 254 |
+
"loss": 0.0938,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 20.67,
|
| 259 |
+
"learning_rate": 0.00018333333333333334,
|
| 260 |
+
"loss": 0.1085,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 21.33,
|
| 265 |
+
"learning_rate": 0.00018240740740740742,
|
| 266 |
+
"loss": 0.1015,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 21.67,
|
| 271 |
+
"learning_rate": 0.0001814814814814815,
|
| 272 |
+
"loss": 0.0668,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 22.33,
|
| 277 |
+
"learning_rate": 0.00018055555555555557,
|
| 278 |
+
"loss": 0.0659,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 22.67,
|
| 283 |
+
"learning_rate": 0.00017962962962962963,
|
| 284 |
+
"loss": 0.0878,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 23.33,
|
| 289 |
+
"learning_rate": 0.0001787037037037037,
|
| 290 |
+
"loss": 0.0638,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 23.67,
|
| 295 |
+
"learning_rate": 0.00017777777777777779,
|
| 296 |
+
"loss": 0.0683,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 24.33,
|
| 301 |
+
"learning_rate": 0.00017685185185185187,
|
| 302 |
+
"loss": 0.0544,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 24.67,
|
| 307 |
+
"learning_rate": 0.00017592592592592595,
|
| 308 |
+
"loss": 0.0636,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 25.33,
|
| 313 |
+
"learning_rate": 0.000175,
|
| 314 |
+
"loss": 0.0476,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 25.67,
|
| 319 |
+
"learning_rate": 0.00017407407407407408,
|
| 320 |
+
"loss": 0.054,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 26.33,
|
| 325 |
+
"learning_rate": 0.00017314814814814816,
|
| 326 |
+
"loss": 0.0415,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 26.67,
|
| 331 |
+
"learning_rate": 0.00017222222222222224,
|
| 332 |
+
"loss": 0.0456,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 27.33,
|
| 337 |
+
"learning_rate": 0.00017129629629629632,
|
| 338 |
+
"loss": 0.0387,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 27.67,
|
| 343 |
+
"learning_rate": 0.00017037037037037037,
|
| 344 |
+
"loss": 0.0415,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 28.33,
|
| 349 |
+
"learning_rate": 0.00016944444444444445,
|
| 350 |
+
"loss": 0.0405,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 28.67,
|
| 355 |
+
"learning_rate": 0.00016851851851851853,
|
| 356 |
+
"loss": 0.0305,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 29.33,
|
| 361 |
+
"learning_rate": 0.00016759259259259258,
|
| 362 |
+
"loss": 0.033,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 29.67,
|
| 367 |
+
"learning_rate": 0.0001666666666666667,
|
| 368 |
+
"loss": 0.038,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 30.33,
|
| 373 |
+
"learning_rate": 0.00016574074074074074,
|
| 374 |
+
"loss": 0.0351,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 30.67,
|
| 379 |
+
"learning_rate": 0.00016481481481481482,
|
| 380 |
+
"loss": 0.0259,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 31.33,
|
| 385 |
+
"learning_rate": 0.0001638888888888889,
|
| 386 |
+
"loss": 0.0298,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 31.67,
|
| 391 |
+
"learning_rate": 0.00016296296296296295,
|
| 392 |
+
"loss": 0.0308,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 32.33,
|
| 397 |
+
"learning_rate": 0.00016203703703703706,
|
| 398 |
+
"loss": 0.0288,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 32.67,
|
| 403 |
+
"learning_rate": 0.0001611111111111111,
|
| 404 |
+
"loss": 0.0298,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 33.33,
|
| 409 |
+
"learning_rate": 0.0001601851851851852,
|
| 410 |
+
"loss": 0.0298,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 33.67,
|
| 415 |
+
"learning_rate": 0.00015925925925925927,
|
| 416 |
+
"loss": 0.0238,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 34.33,
|
| 421 |
+
"learning_rate": 0.00015833333333333332,
|
| 422 |
+
"loss": 0.0267,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 34.67,
|
| 427 |
+
"learning_rate": 0.00015740740740740743,
|
| 428 |
+
"loss": 0.0261,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 35.33,
|
| 433 |
+
"learning_rate": 0.00015648148148148148,
|
| 434 |
+
"loss": 0.0238,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 35.67,
|
| 439 |
+
"learning_rate": 0.00015555555555555556,
|
| 440 |
+
"loss": 0.028,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 36.33,
|
| 445 |
+
"learning_rate": 0.00015462962962962964,
|
| 446 |
+
"loss": 0.0223,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 36.67,
|
| 451 |
+
"learning_rate": 0.0001537037037037037,
|
| 452 |
+
"loss": 0.027,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 37.33,
|
| 457 |
+
"learning_rate": 0.00015277777777777777,
|
| 458 |
+
"loss": 0.0232,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 37.67,
|
| 463 |
+
"learning_rate": 0.00015185185185185185,
|
| 464 |
+
"loss": 0.0263,
|
| 465 |
+
"step": 76
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 38.33,
|
| 469 |
+
"learning_rate": 0.00015092592592592593,
|
| 470 |
+
"loss": 0.023,
|
| 471 |
+
"step": 77
|
| 472 |
+
},
|
| 473 |
+
{
|
| 474 |
+
"epoch": 38.67,
|
| 475 |
+
"learning_rate": 0.00015000000000000001,
|
| 476 |
+
"loss": 0.0257,
|
| 477 |
+
"step": 78
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 39.33,
|
| 481 |
+
"learning_rate": 0.00014907407407407407,
|
| 482 |
+
"loss": 0.0246,
|
| 483 |
+
"step": 79
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 39.67,
|
| 487 |
+
"learning_rate": 0.00014814814814814815,
|
| 488 |
+
"loss": 0.0202,
|
| 489 |
+
"step": 80
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 40.33,
|
| 493 |
+
"learning_rate": 0.00014722222222222223,
|
| 494 |
+
"loss": 0.022,
|
| 495 |
+
"step": 81
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 40.67,
|
| 499 |
+
"learning_rate": 0.0001462962962962963,
|
| 500 |
+
"loss": 0.0234,
|
| 501 |
+
"step": 82
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 41.33,
|
| 505 |
+
"learning_rate": 0.00014537037037037039,
|
| 506 |
+
"loss": 0.0222,
|
| 507 |
+
"step": 83
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 41.67,
|
| 511 |
+
"learning_rate": 0.00014444444444444444,
|
| 512 |
+
"loss": 0.0247,
|
| 513 |
+
"step": 84
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 42.33,
|
| 517 |
+
"learning_rate": 0.00014351851851851852,
|
| 518 |
+
"loss": 0.0227,
|
| 519 |
+
"step": 85
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 42.67,
|
| 523 |
+
"learning_rate": 0.0001425925925925926,
|
| 524 |
+
"loss": 0.0246,
|
| 525 |
+
"step": 86
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 43.33,
|
| 529 |
+
"learning_rate": 0.00014166666666666668,
|
| 530 |
+
"loss": 0.0245,
|
| 531 |
+
"step": 87
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 43.67,
|
| 535 |
+
"learning_rate": 0.00014074074074074076,
|
| 536 |
+
"loss": 0.0196,
|
| 537 |
+
"step": 88
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 44.33,
|
| 541 |
+
"learning_rate": 0.0001398148148148148,
|
| 542 |
+
"loss": 0.0239,
|
| 543 |
+
"step": 89
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 44.67,
|
| 547 |
+
"learning_rate": 0.0001388888888888889,
|
| 548 |
+
"loss": 0.0166,
|
| 549 |
+
"step": 90
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 45.33,
|
| 553 |
+
"learning_rate": 0.00013796296296296297,
|
| 554 |
+
"loss": 0.0202,
|
| 555 |
+
"step": 91
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 45.67,
|
| 559 |
+
"learning_rate": 0.00013703703703703705,
|
| 560 |
+
"loss": 0.0222,
|
| 561 |
+
"step": 92
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 46.33,
|
| 565 |
+
"learning_rate": 0.00013611111111111113,
|
| 566 |
+
"loss": 0.0215,
|
| 567 |
+
"step": 93
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 46.67,
|
| 571 |
+
"learning_rate": 0.00013518518518518518,
|
| 572 |
+
"loss": 0.0157,
|
| 573 |
+
"step": 94
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 47.33,
|
| 577 |
+
"learning_rate": 0.00013425925925925926,
|
| 578 |
+
"loss": 0.019,
|
| 579 |
+
"step": 95
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 47.67,
|
| 583 |
+
"learning_rate": 0.00013333333333333334,
|
| 584 |
+
"loss": 0.024,
|
| 585 |
+
"step": 96
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 48.33,
|
| 589 |
+
"learning_rate": 0.00013240740740740742,
|
| 590 |
+
"loss": 0.0236,
|
| 591 |
+
"step": 97
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 48.67,
|
| 595 |
+
"learning_rate": 0.0001314814814814815,
|
| 596 |
+
"loss": 0.0149,
|
| 597 |
+
"step": 98
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 49.33,
|
| 601 |
+
"learning_rate": 0.00013055555555555555,
|
| 602 |
+
"loss": 0.0192,
|
| 603 |
+
"step": 99
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 49.67,
|
| 607 |
+
"learning_rate": 0.00012962962962962963,
|
| 608 |
+
"loss": 0.0225,
|
| 609 |
+
"step": 100
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 50.33,
|
| 613 |
+
"learning_rate": 0.0001287037037037037,
|
| 614 |
+
"loss": 0.0228,
|
| 615 |
+
"step": 101
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 50.67,
|
| 619 |
+
"learning_rate": 0.00012777777777777776,
|
| 620 |
+
"loss": 0.0145,
|
| 621 |
+
"step": 102
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 51.33,
|
| 625 |
+
"learning_rate": 0.00012685185185185187,
|
| 626 |
+
"loss": 0.023,
|
| 627 |
+
"step": 103
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 51.67,
|
| 631 |
+
"learning_rate": 0.00012592592592592592,
|
| 632 |
+
"loss": 0.0145,
|
| 633 |
+
"step": 104
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 52.33,
|
| 637 |
+
"learning_rate": 0.000125,
|
| 638 |
+
"loss": 0.0175,
|
| 639 |
+
"step": 105
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 52.67,
|
| 643 |
+
"learning_rate": 0.00012407407407407408,
|
| 644 |
+
"loss": 0.0247,
|
| 645 |
+
"step": 106
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 53.33,
|
| 649 |
+
"learning_rate": 0.00012314814814814813,
|
| 650 |
+
"loss": 0.0162,
|
| 651 |
+
"step": 107
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 53.67,
|
| 655 |
+
"learning_rate": 0.00012222222222222224,
|
| 656 |
+
"loss": 0.0228,
|
| 657 |
+
"step": 108
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 54.33,
|
| 661 |
+
"learning_rate": 0.00012129629629629631,
|
| 662 |
+
"loss": 0.0164,
|
| 663 |
+
"step": 109
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 54.67,
|
| 667 |
+
"learning_rate": 0.00012037037037037037,
|
| 668 |
+
"loss": 0.0226,
|
| 669 |
+
"step": 110
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 55.33,
|
| 673 |
+
"learning_rate": 0.00011944444444444445,
|
| 674 |
+
"loss": 0.0182,
|
| 675 |
+
"step": 111
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 55.67,
|
| 679 |
+
"learning_rate": 0.00011851851851851852,
|
| 680 |
+
"loss": 0.0202,
|
| 681 |
+
"step": 112
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 56.33,
|
| 685 |
+
"learning_rate": 0.00011759259259259259,
|
| 686 |
+
"loss": 0.0206,
|
| 687 |
+
"step": 113
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 56.67,
|
| 691 |
+
"learning_rate": 0.00011666666666666668,
|
| 692 |
+
"loss": 0.0141,
|
| 693 |
+
"step": 114
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 57.33,
|
| 697 |
+
"learning_rate": 0.00011574074074074075,
|
| 698 |
+
"loss": 0.0199,
|
| 699 |
+
"step": 115
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 57.67,
|
| 703 |
+
"learning_rate": 0.00011481481481481482,
|
| 704 |
+
"loss": 0.014,
|
| 705 |
+
"step": 116
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 58.33,
|
| 709 |
+
"learning_rate": 0.00011388888888888889,
|
| 710 |
+
"loss": 0.019,
|
| 711 |
+
"step": 117
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 58.67,
|
| 715 |
+
"learning_rate": 0.00011296296296296296,
|
| 716 |
+
"loss": 0.014,
|
| 717 |
+
"step": 118
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 59.33,
|
| 721 |
+
"learning_rate": 0.00011203703703703705,
|
| 722 |
+
"loss": 0.0161,
|
| 723 |
+
"step": 119
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 59.67,
|
| 727 |
+
"learning_rate": 0.00011111111111111112,
|
| 728 |
+
"loss": 0.0221,
|
| 729 |
+
"step": 120
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 60.33,
|
| 733 |
+
"learning_rate": 0.0001101851851851852,
|
| 734 |
+
"loss": 0.0174,
|
| 735 |
+
"step": 121
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 60.67,
|
| 739 |
+
"learning_rate": 0.00010925925925925926,
|
| 740 |
+
"loss": 0.0221,
|
| 741 |
+
"step": 122
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 61.33,
|
| 745 |
+
"learning_rate": 0.00010833333333333333,
|
| 746 |
+
"loss": 0.0171,
|
| 747 |
+
"step": 123
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 61.67,
|
| 751 |
+
"learning_rate": 0.00010740740740740742,
|
| 752 |
+
"loss": 0.0221,
|
| 753 |
+
"step": 124
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 62.33,
|
| 757 |
+
"learning_rate": 0.00010648148148148149,
|
| 758 |
+
"loss": 0.0175,
|
| 759 |
+
"step": 125
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 62.67,
|
| 763 |
+
"learning_rate": 0.00010555555555555557,
|
| 764 |
+
"loss": 0.0182,
|
| 765 |
+
"step": 126
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 63.33,
|
| 769 |
+
"learning_rate": 0.00010462962962962963,
|
| 770 |
+
"loss": 0.0141,
|
| 771 |
+
"step": 127
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 63.67,
|
| 775 |
+
"learning_rate": 0.0001037037037037037,
|
| 776 |
+
"loss": 0.0184,
|
| 777 |
+
"step": 128
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 64.33,
|
| 781 |
+
"learning_rate": 0.00010277777777777778,
|
| 782 |
+
"loss": 0.014,
|
| 783 |
+
"step": 129
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 64.67,
|
| 787 |
+
"learning_rate": 0.00010185185185185186,
|
| 788 |
+
"loss": 0.0175,
|
| 789 |
+
"step": 130
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 65.33,
|
| 793 |
+
"learning_rate": 0.00010092592592592594,
|
| 794 |
+
"loss": 0.0162,
|
| 795 |
+
"step": 131
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 65.67,
|
| 799 |
+
"learning_rate": 0.0001,
|
| 800 |
+
"loss": 0.0173,
|
| 801 |
+
"step": 132
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 66.33,
|
| 805 |
+
"learning_rate": 9.907407407407407e-05,
|
| 806 |
+
"loss": 0.0165,
|
| 807 |
+
"step": 133
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 66.67,
|
| 811 |
+
"learning_rate": 9.814814814814815e-05,
|
| 812 |
+
"loss": 0.0215,
|
| 813 |
+
"step": 134
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 67.33,
|
| 817 |
+
"learning_rate": 9.722222222222223e-05,
|
| 818 |
+
"loss": 0.0172,
|
| 819 |
+
"step": 135
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 67.67,
|
| 823 |
+
"learning_rate": 9.62962962962963e-05,
|
| 824 |
+
"loss": 0.0216,
|
| 825 |
+
"step": 136
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 68.33,
|
| 829 |
+
"learning_rate": 9.537037037037038e-05,
|
| 830 |
+
"loss": 0.0169,
|
| 831 |
+
"step": 137
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 68.67,
|
| 835 |
+
"learning_rate": 9.444444444444444e-05,
|
| 836 |
+
"loss": 0.0199,
|
| 837 |
+
"step": 138
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 69.33,
|
| 841 |
+
"learning_rate": 9.351851851851852e-05,
|
| 842 |
+
"loss": 0.0178,
|
| 843 |
+
"step": 139
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 69.67,
|
| 847 |
+
"learning_rate": 9.25925925925926e-05,
|
| 848 |
+
"loss": 0.0135,
|
| 849 |
+
"step": 140
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 70.33,
|
| 853 |
+
"learning_rate": 9.166666666666667e-05,
|
| 854 |
+
"loss": 0.0171,
|
| 855 |
+
"step": 141
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 70.67,
|
| 859 |
+
"learning_rate": 9.074074074074075e-05,
|
| 860 |
+
"loss": 0.0145,
|
| 861 |
+
"step": 142
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 71.33,
|
| 865 |
+
"learning_rate": 8.981481481481481e-05,
|
| 866 |
+
"loss": 0.0175,
|
| 867 |
+
"step": 143
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 71.67,
|
| 871 |
+
"learning_rate": 8.888888888888889e-05,
|
| 872 |
+
"loss": 0.0145,
|
| 873 |
+
"step": 144
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 72.33,
|
| 877 |
+
"learning_rate": 8.796296296296297e-05,
|
| 878 |
+
"loss": 0.014,
|
| 879 |
+
"step": 145
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 72.67,
|
| 883 |
+
"learning_rate": 8.703703703703704e-05,
|
| 884 |
+
"loss": 0.0217,
|
| 885 |
+
"step": 146
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 73.33,
|
| 889 |
+
"learning_rate": 8.611111111111112e-05,
|
| 890 |
+
"loss": 0.0139,
|
| 891 |
+
"step": 147
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 73.67,
|
| 895 |
+
"learning_rate": 8.518518518518518e-05,
|
| 896 |
+
"loss": 0.0218,
|
| 897 |
+
"step": 148
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 74.33,
|
| 901 |
+
"learning_rate": 8.425925925925926e-05,
|
| 902 |
+
"loss": 0.0139,
|
| 903 |
+
"step": 149
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 74.67,
|
| 907 |
+
"learning_rate": 8.333333333333334e-05,
|
| 908 |
+
"loss": 0.0217,
|
| 909 |
+
"step": 150
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 75.33,
|
| 913 |
+
"learning_rate": 8.240740740740741e-05,
|
| 914 |
+
"loss": 0.016,
|
| 915 |
+
"step": 151
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 75.67,
|
| 919 |
+
"learning_rate": 8.148148148148148e-05,
|
| 920 |
+
"loss": 0.0217,
|
| 921 |
+
"step": 152
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 76.33,
|
| 925 |
+
"learning_rate": 8.055555555555556e-05,
|
| 926 |
+
"loss": 0.0163,
|
| 927 |
+
"step": 153
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 76.67,
|
| 931 |
+
"learning_rate": 7.962962962962964e-05,
|
| 932 |
+
"loss": 0.0216,
|
| 933 |
+
"step": 154
|
| 934 |
+
},
|
| 935 |
+
{
|
| 936 |
+
"epoch": 77.33,
|
| 937 |
+
"learning_rate": 7.870370370370372e-05,
|
| 938 |
+
"loss": 0.021,
|
| 939 |
+
"step": 155
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"epoch": 77.67,
|
| 943 |
+
"learning_rate": 7.777777777777778e-05,
|
| 944 |
+
"loss": 0.0135,
|
| 945 |
+
"step": 156
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 78.33,
|
| 949 |
+
"learning_rate": 7.685185185185185e-05,
|
| 950 |
+
"loss": 0.0203,
|
| 951 |
+
"step": 157
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 78.67,
|
| 955 |
+
"learning_rate": 7.592592592592593e-05,
|
| 956 |
+
"loss": 0.0131,
|
| 957 |
+
"step": 158
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 79.33,
|
| 961 |
+
"learning_rate": 7.500000000000001e-05,
|
| 962 |
+
"loss": 0.014,
|
| 963 |
+
"step": 159
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 79.67,
|
| 967 |
+
"learning_rate": 7.407407407407407e-05,
|
| 968 |
+
"loss": 0.0214,
|
| 969 |
+
"step": 160
|
| 970 |
+
}
|
| 971 |
+
],
|
| 972 |
+
"logging_steps": 1,
|
| 973 |
+
"max_steps": 240,
|
| 974 |
+
"num_train_epochs": 80,
|
| 975 |
+
"save_steps": 500,
|
| 976 |
+
"total_flos": 2534247235584000.0,
|
| 977 |
+
"trial_name": null,
|
| 978 |
+
"trial_params": null
|
| 979 |
+
}
|
checkpoint-160/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba50a6e415649e88d1a86d0f2414bd26d6f5dd6dfee3ddd9ab2fd780d976eae
|
| 3 |
+
size 4091
|
runs/Aug26_07-31-31_s-yaleh-autotrain-9780-igpa-vu5r-0-f9999-bb4957c87-bx4xv/events.out.tfevents.1693035092.s-yaleh-autotrain-9780-igpa-vu5r-0-f9999-bb4957c87-bx4xv.55.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5442778e763572f0b2fdffd309efd09070973db6b841a9f8b2a0689c6407c2c5
|
| 3 |
+
size 29586
|
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": "</s>",
|
| 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 sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
|
| 3 |
+
size 511574
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": true,
|
| 3 |
+
"add_eos_token": false,
|
| 4 |
+
"bos_token": {
|
| 5 |
+
"__type": "AddedToken",
|
| 6 |
+
"content": "<s>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": true,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
+
"clean_up_tokenization_spaces": false,
|
| 13 |
+
"eos_token": {
|
| 14 |
+
"__type": "AddedToken",
|
| 15 |
+
"content": "</s>",
|
| 16 |
+
"lstrip": false,
|
| 17 |
+
"normalized": true,
|
| 18 |
+
"rstrip": false,
|
| 19 |
+
"single_word": false
|
| 20 |
+
},
|
| 21 |
+
"legacy": null,
|
| 22 |
+
"model_max_length": 2048,
|
| 23 |
+
"pad_token": null,
|
| 24 |
+
"sp_model_kwargs": {},
|
| 25 |
+
"spaces_between_special_tokens": false,
|
| 26 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 27 |
+
"unk_token": {
|
| 28 |
+
"__type": "AddedToken",
|
| 29 |
+
"content": "<unk>",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false
|
| 34 |
+
},
|
| 35 |
+
"use_default_system_prompt": true
|
| 36 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cba50a6e415649e88d1a86d0f2414bd26d6f5dd6dfee3ddd9ab2fd780d976eae
|
| 3 |
+
size 4091
|
training_params.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"model": "openlm-research/open_llama_3b_v2", "data_path": "yaleh/autotrain-data-9780-igpa-vu5r", "project_name": "/tmp/model", "train_split": "train", "valid_split": null, "text_column": "autotrain_text", "lr": 0.0002, "epochs": 80, "batch_size": 2, "warmup_ratio": 0.1, "gradient_accumulation": 1, "optimizer": "adamw_torch", "scheduler": "linear", "weight_decay": 0.01, "max_grad_norm": 1.0, "seed": 42, "add_eos_token": true, "block_size": 1024, "use_peft": true, "lora_r": 16, "lora_alpha": 32, "lora_dropout": 0.1, "logging_steps": -1, "evaluation_strategy": "epoch", "save_total_limit": 1, "save_strategy": "epoch", "auto_find_batch_size": false, "fp16": true, "push_to_hub": true, "use_int8": false, "model_max_length": 2048, "repo_id": "yaleh/9780-igpa-vu5r-0", "use_int4": true, "trainer": "sft", "target_modules": null, "merge_adapter": false, "username": "yaleh"}
|