Agrego archivos
Browse files- README.md +56 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- optimizer.pt +3 -0
- rng_state.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer_config.json +34 -0
- trainer_state.json +976 -0
- training_args.bin +3 -0
README.md
ADDED
|
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
---
|
| 4 |
+
## Training procedure
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 8 |
+
- load_in_8bit: False
|
| 9 |
+
- load_in_4bit: True
|
| 10 |
+
- llm_int8_threshold: 6.0
|
| 11 |
+
- llm_int8_skip_modules: None
|
| 12 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 13 |
+
- llm_int8_has_fp16_weight: False
|
| 14 |
+
- bnb_4bit_quant_type: nf4
|
| 15 |
+
- bnb_4bit_use_double_quant: False
|
| 16 |
+
- bnb_4bit_compute_dtype: float16
|
| 17 |
+
|
| 18 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 19 |
+
- load_in_8bit: False
|
| 20 |
+
- load_in_4bit: True
|
| 21 |
+
- llm_int8_threshold: 6.0
|
| 22 |
+
- llm_int8_skip_modules: None
|
| 23 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 24 |
+
- llm_int8_has_fp16_weight: False
|
| 25 |
+
- bnb_4bit_quant_type: nf4
|
| 26 |
+
- bnb_4bit_use_double_quant: False
|
| 27 |
+
- bnb_4bit_compute_dtype: float16
|
| 28 |
+
|
| 29 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 30 |
+
- load_in_8bit: False
|
| 31 |
+
- load_in_4bit: True
|
| 32 |
+
- llm_int8_threshold: 6.0
|
| 33 |
+
- llm_int8_skip_modules: None
|
| 34 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 35 |
+
- llm_int8_has_fp16_weight: False
|
| 36 |
+
- bnb_4bit_quant_type: nf4
|
| 37 |
+
- bnb_4bit_use_double_quant: False
|
| 38 |
+
- bnb_4bit_compute_dtype: float16
|
| 39 |
+
|
| 40 |
+
The following `bitsandbytes` quantization config was used during training:
|
| 41 |
+
- load_in_8bit: False
|
| 42 |
+
- load_in_4bit: True
|
| 43 |
+
- llm_int8_threshold: 6.0
|
| 44 |
+
- llm_int8_skip_modules: None
|
| 45 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
| 46 |
+
- llm_int8_has_fp16_weight: False
|
| 47 |
+
- bnb_4bit_quant_type: nf4
|
| 48 |
+
- bnb_4bit_use_double_quant: False
|
| 49 |
+
- bnb_4bit_compute_dtype: float16
|
| 50 |
+
### Framework versions
|
| 51 |
+
|
| 52 |
+
- PEFT 0.4.0
|
| 53 |
+
- PEFT 0.4.0
|
| 54 |
+
- PEFT 0.4.0
|
| 55 |
+
|
| 56 |
+
- PEFT 0.4.0
|
adapter_config.json
ADDED
|
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"auto_mapping": null,
|
| 3 |
+
"base_model_name_or_path": "meta-llama/Llama-2-13b-chat-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 16,
|
| 11 |
+
"lora_dropout": 0.1,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 64,
|
| 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 sha256:98e4e57f60f41136a0299201b8ae90b9ee7880ded35c6d15541d1c19f2c981e1
|
| 3 |
+
size 209773322
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:86a407b80fbd0c4559a4daff4437a1a997f8437a2a7766db1858d4135b85d812
|
| 3 |
+
size 419529722
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42a1450bb3a0c7b90a30917ce360678cd76950c9b75920ffe95eeb132c8f11b9
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1f057d13d6a57dceb36953f14488876c44552c296edcb5325a011835c0c7f791
|
| 3 |
+
size 1064
|
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_config.json
ADDED
|
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"__type": "AddedToken",
|
| 4 |
+
"content": "<s>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
"chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<<SYS>>\\n' + system_message + '\\n<</SYS>>\\n\\n' + message['content'] %}{% else %}{% set content = message['content'] %}{% endif %}{% if message['role'] == 'user' %}{{ bos_token + '[INST] ' + content.strip() + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ ' ' + content.strip() + ' ' + eos_token }}{% endif %}{% endfor %}",
|
| 11 |
+
"clean_up_tokenization_spaces": false,
|
| 12 |
+
"eos_token": {
|
| 13 |
+
"__type": "AddedToken",
|
| 14 |
+
"content": "</s>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false
|
| 19 |
+
},
|
| 20 |
+
"legacy": false,
|
| 21 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
+
"pad_token": null,
|
| 23 |
+
"padding_side": "right",
|
| 24 |
+
"sp_model_kwargs": {},
|
| 25 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 26 |
+
"unk_token": {
|
| 27 |
+
"__type": "AddedToken",
|
| 28 |
+
"content": "<unk>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false
|
| 33 |
+
}
|
| 34 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,976 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.9618467457518436,
|
| 5 |
+
"global_step": 3000,
|
| 6 |
+
"is_hyper_param_search": false,
|
| 7 |
+
"is_local_process_zero": true,
|
| 8 |
+
"is_world_process_zero": true,
|
| 9 |
+
"log_history": [
|
| 10 |
+
{
|
| 11 |
+
"epoch": 0.01,
|
| 12 |
+
"learning_rate": 2.6595744680851064e-05,
|
| 13 |
+
"loss": 2.0914,
|
| 14 |
+
"step": 25
|
| 15 |
+
},
|
| 16 |
+
{
|
| 17 |
+
"epoch": 0.02,
|
| 18 |
+
"learning_rate": 5.319148936170213e-05,
|
| 19 |
+
"loss": 1.8503,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"epoch": 0.02,
|
| 24 |
+
"learning_rate": 7.978723404255319e-05,
|
| 25 |
+
"loss": 1.3555,
|
| 26 |
+
"step": 75
|
| 27 |
+
},
|
| 28 |
+
{
|
| 29 |
+
"epoch": 0.03,
|
| 30 |
+
"learning_rate": 0.00010638297872340425,
|
| 31 |
+
"loss": 1.0528,
|
| 32 |
+
"step": 100
|
| 33 |
+
},
|
| 34 |
+
{
|
| 35 |
+
"epoch": 0.03,
|
| 36 |
+
"eval_loss": 1.3641345500946045,
|
| 37 |
+
"eval_runtime": 76.7384,
|
| 38 |
+
"eval_samples_per_second": 7.089,
|
| 39 |
+
"eval_steps_per_second": 0.886,
|
| 40 |
+
"step": 100
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"epoch": 0.04,
|
| 44 |
+
"learning_rate": 0.00013297872340425532,
|
| 45 |
+
"loss": 0.9497,
|
| 46 |
+
"step": 125
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.05,
|
| 50 |
+
"learning_rate": 0.00015957446808510637,
|
| 51 |
+
"loss": 1.0081,
|
| 52 |
+
"step": 150
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06,
|
| 56 |
+
"learning_rate": 0.00018617021276595746,
|
| 57 |
+
"loss": 0.9365,
|
| 58 |
+
"step": 175
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.06,
|
| 62 |
+
"learning_rate": 0.00019999805857737166,
|
| 63 |
+
"loss": 0.9364,
|
| 64 |
+
"step": 200
|
| 65 |
+
},
|
| 66 |
+
{
|
| 67 |
+
"epoch": 0.06,
|
| 68 |
+
"eval_loss": 1.2751965522766113,
|
| 69 |
+
"eval_runtime": 76.7874,
|
| 70 |
+
"eval_samples_per_second": 7.084,
|
| 71 |
+
"eval_steps_per_second": 0.886,
|
| 72 |
+
"step": 200
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"epoch": 0.07,
|
| 76 |
+
"learning_rate": 0.0001999815435109719,
|
| 77 |
+
"loss": 0.9226,
|
| 78 |
+
"step": 225
|
| 79 |
+
},
|
| 80 |
+
{
|
| 81 |
+
"epoch": 0.08,
|
| 82 |
+
"learning_rate": 0.00019994817911010517,
|
| 83 |
+
"loss": 0.8396,
|
| 84 |
+
"step": 250
|
| 85 |
+
},
|
| 86 |
+
{
|
| 87 |
+
"epoch": 0.09,
|
| 88 |
+
"learning_rate": 0.0001998979709974887,
|
| 89 |
+
"loss": 0.8687,
|
| 90 |
+
"step": 275
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 0.1,
|
| 94 |
+
"learning_rate": 0.00019983092763441697,
|
| 95 |
+
"loss": 0.8593,
|
| 96 |
+
"step": 300
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.1,
|
| 100 |
+
"eval_loss": 1.2590458393096924,
|
| 101 |
+
"eval_runtime": 76.8321,
|
| 102 |
+
"eval_samples_per_second": 7.08,
|
| 103 |
+
"eval_steps_per_second": 0.885,
|
| 104 |
+
"step": 300
|
| 105 |
+
},
|
| 106 |
+
{
|
| 107 |
+
"epoch": 0.1,
|
| 108 |
+
"learning_rate": 0.0001997470603193358,
|
| 109 |
+
"loss": 0.8064,
|
| 110 |
+
"step": 325
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.11,
|
| 114 |
+
"learning_rate": 0.0001996463831859381,
|
| 115 |
+
"loss": 0.7851,
|
| 116 |
+
"step": 350
|
| 117 |
+
},
|
| 118 |
+
{
|
| 119 |
+
"epoch": 0.12,
|
| 120 |
+
"learning_rate": 0.00019952891320078236,
|
| 121 |
+
"loss": 0.8516,
|
| 122 |
+
"step": 375
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.13,
|
| 126 |
+
"learning_rate": 0.0001993946701604329,
|
| 127 |
+
"loss": 0.8161,
|
| 128 |
+
"step": 400
|
| 129 |
+
},
|
| 130 |
+
{
|
| 131 |
+
"epoch": 0.13,
|
| 132 |
+
"eval_loss": 1.1581201553344727,
|
| 133 |
+
"eval_runtime": 76.7611,
|
| 134 |
+
"eval_samples_per_second": 7.087,
|
| 135 |
+
"eval_steps_per_second": 0.886,
|
| 136 |
+
"step": 400
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.14,
|
| 140 |
+
"learning_rate": 0.00019924367668812417,
|
| 141 |
+
"loss": 0.838,
|
| 142 |
+
"step": 425
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.14,
|
| 146 |
+
"learning_rate": 0.00019907595822994773,
|
| 147 |
+
"loss": 0.8271,
|
| 148 |
+
"step": 450
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"epoch": 0.15,
|
| 152 |
+
"learning_rate": 0.00019889154305056426,
|
| 153 |
+
"loss": 0.8005,
|
| 154 |
+
"step": 475
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.16,
|
| 158 |
+
"learning_rate": 0.00019869046222844008,
|
| 159 |
+
"loss": 0.7916,
|
| 160 |
+
"step": 500
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.16,
|
| 164 |
+
"eval_loss": 1.1132324934005737,
|
| 165 |
+
"eval_runtime": 76.7669,
|
| 166 |
+
"eval_samples_per_second": 7.086,
|
| 167 |
+
"eval_steps_per_second": 0.886,
|
| 168 |
+
"step": 500
|
| 169 |
+
},
|
| 170 |
+
{
|
| 171 |
+
"epoch": 0.17,
|
| 172 |
+
"learning_rate": 0.00019847274965060984,
|
| 173 |
+
"loss": 0.7991,
|
| 174 |
+
"step": 525
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.18,
|
| 178 |
+
"learning_rate": 0.00019823844200696564,
|
| 179 |
+
"loss": 0.8387,
|
| 180 |
+
"step": 550
|
| 181 |
+
},
|
| 182 |
+
{
|
| 183 |
+
"epoch": 0.18,
|
| 184 |
+
"learning_rate": 0.00019798757878407386,
|
| 185 |
+
"loss": 0.8196,
|
| 186 |
+
"step": 575
|
| 187 |
+
},
|
| 188 |
+
{
|
| 189 |
+
"epoch": 0.19,
|
| 190 |
+
"learning_rate": 0.00019772020225852077,
|
| 191 |
+
"loss": 0.7508,
|
| 192 |
+
"step": 600
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.19,
|
| 196 |
+
"eval_loss": 1.0564008951187134,
|
| 197 |
+
"eval_runtime": 76.7274,
|
| 198 |
+
"eval_samples_per_second": 7.09,
|
| 199 |
+
"eval_steps_per_second": 0.886,
|
| 200 |
+
"step": 600
|
| 201 |
+
},
|
| 202 |
+
{
|
| 203 |
+
"epoch": 0.2,
|
| 204 |
+
"learning_rate": 0.0001974363574897878,
|
| 205 |
+
"loss": 0.8356,
|
| 206 |
+
"step": 625
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.21,
|
| 210 |
+
"learning_rate": 0.00019713609231265805,
|
| 211 |
+
"loss": 0.7036,
|
| 212 |
+
"step": 650
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"epoch": 0.22,
|
| 216 |
+
"learning_rate": 0.0001968194573291549,
|
| 217 |
+
"loss": 0.8082,
|
| 218 |
+
"step": 675
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"epoch": 0.22,
|
| 222 |
+
"learning_rate": 0.00019648650590001418,
|
| 223 |
+
"loss": 0.7974,
|
| 224 |
+
"step": 700
|
| 225 |
+
},
|
| 226 |
+
{
|
| 227 |
+
"epoch": 0.22,
|
| 228 |
+
"eval_loss": 1.1469172239303589,
|
| 229 |
+
"eval_runtime": 76.886,
|
| 230 |
+
"eval_samples_per_second": 7.075,
|
| 231 |
+
"eval_steps_per_second": 0.884,
|
| 232 |
+
"step": 700
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.23,
|
| 236 |
+
"learning_rate": 0.00019613729413569194,
|
| 237 |
+
"loss": 0.7804,
|
| 238 |
+
"step": 725
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.24,
|
| 242 |
+
"learning_rate": 0.00019577188088690803,
|
| 243 |
+
"loss": 0.7398,
|
| 244 |
+
"step": 750
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"epoch": 0.25,
|
| 248 |
+
"learning_rate": 0.00019539032773472866,
|
| 249 |
+
"loss": 0.7178,
|
| 250 |
+
"step": 775
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.26,
|
| 254 |
+
"learning_rate": 0.00019499269898018832,
|
| 255 |
+
"loss": 0.7303,
|
| 256 |
+
"step": 800
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"epoch": 0.26,
|
| 260 |
+
"eval_loss": 1.1135411262512207,
|
| 261 |
+
"eval_runtime": 76.7509,
|
| 262 |
+
"eval_samples_per_second": 7.088,
|
| 263 |
+
"eval_steps_per_second": 0.886,
|
| 264 |
+
"step": 800
|
| 265 |
+
},
|
| 266 |
+
{
|
| 267 |
+
"epoch": 0.26,
|
| 268 |
+
"learning_rate": 0.00019457906163345353,
|
| 269 |
+
"loss": 0.7133,
|
| 270 |
+
"step": 825
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"epoch": 0.27,
|
| 274 |
+
"learning_rate": 0.00019414948540253,
|
| 275 |
+
"loss": 0.744,
|
| 276 |
+
"step": 850
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.28,
|
| 280 |
+
"learning_rate": 0.000193704042681515,
|
| 281 |
+
"loss": 0.7195,
|
| 282 |
+
"step": 875
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.29,
|
| 286 |
+
"learning_rate": 0.00019324280853839744,
|
| 287 |
+
"loss": 0.6909,
|
| 288 |
+
"step": 900
|
| 289 |
+
},
|
| 290 |
+
{
|
| 291 |
+
"epoch": 0.29,
|
| 292 |
+
"eval_loss": 1.1239628791809082,
|
| 293 |
+
"eval_runtime": 76.7964,
|
| 294 |
+
"eval_samples_per_second": 7.084,
|
| 295 |
+
"eval_steps_per_second": 0.885,
|
| 296 |
+
"step": 900
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.3,
|
| 300 |
+
"learning_rate": 0.00019276586070240682,
|
| 301 |
+
"loss": 0.7061,
|
| 302 |
+
"step": 925
|
| 303 |
+
},
|
| 304 |
+
{
|
| 305 |
+
"epoch": 0.3,
|
| 306 |
+
"learning_rate": 0.00019227327955091412,
|
| 307 |
+
"loss": 0.694,
|
| 308 |
+
"step": 950
|
| 309 |
+
},
|
| 310 |
+
{
|
| 311 |
+
"epoch": 0.31,
|
| 312 |
+
"learning_rate": 0.00019176514809588616,
|
| 313 |
+
"loss": 0.707,
|
| 314 |
+
"step": 975
|
| 315 |
+
},
|
| 316 |
+
{
|
| 317 |
+
"epoch": 0.32,
|
| 318 |
+
"learning_rate": 0.0001912415519698961,
|
| 319 |
+
"loss": 0.7267,
|
| 320 |
+
"step": 1000
|
| 321 |
+
},
|
| 322 |
+
{
|
| 323 |
+
"epoch": 0.32,
|
| 324 |
+
"eval_loss": 1.0490331649780273,
|
| 325 |
+
"eval_runtime": 76.7671,
|
| 326 |
+
"eval_samples_per_second": 7.086,
|
| 327 |
+
"eval_steps_per_second": 0.886,
|
| 328 |
+
"step": 1000
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"epoch": 0.33,
|
| 332 |
+
"learning_rate": 0.00019070257941169224,
|
| 333 |
+
"loss": 0.694,
|
| 334 |
+
"step": 1025
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.34,
|
| 338 |
+
"learning_rate": 0.00019014832125132763,
|
| 339 |
+
"loss": 0.638,
|
| 340 |
+
"step": 1050
|
| 341 |
+
},
|
| 342 |
+
{
|
| 343 |
+
"epoch": 0.34,
|
| 344 |
+
"learning_rate": 0.000189578870894853,
|
| 345 |
+
"loss": 0.6951,
|
| 346 |
+
"step": 1075
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.35,
|
| 350 |
+
"learning_rate": 0.00018899432430857552,
|
| 351 |
+
"loss": 0.6649,
|
| 352 |
+
"step": 1100
|
| 353 |
+
},
|
| 354 |
+
{
|
| 355 |
+
"epoch": 0.35,
|
| 356 |
+
"eval_loss": 1.127469539642334,
|
| 357 |
+
"eval_runtime": 76.7816,
|
| 358 |
+
"eval_samples_per_second": 7.085,
|
| 359 |
+
"eval_steps_per_second": 0.886,
|
| 360 |
+
"step": 1100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.36,
|
| 364 |
+
"learning_rate": 0.00018839478000288627,
|
| 365 |
+
"loss": 0.7284,
|
| 366 |
+
"step": 1125
|
| 367 |
+
},
|
| 368 |
+
{
|
| 369 |
+
"epoch": 0.37,
|
| 370 |
+
"learning_rate": 0.00018778033901565856,
|
| 371 |
+
"loss": 0.6459,
|
| 372 |
+
"step": 1150
|
| 373 |
+
},
|
| 374 |
+
{
|
| 375 |
+
"epoch": 0.38,
|
| 376 |
+
"learning_rate": 0.0001871511048952208,
|
| 377 |
+
"loss": 0.6616,
|
| 378 |
+
"step": 1175
|
| 379 |
+
},
|
| 380 |
+
{
|
| 381 |
+
"epoch": 0.38,
|
| 382 |
+
"learning_rate": 0.0001865071836829061,
|
| 383 |
+
"loss": 0.6306,
|
| 384 |
+
"step": 1200
|
| 385 |
+
},
|
| 386 |
+
{
|
| 387 |
+
"epoch": 0.38,
|
| 388 |
+
"eval_loss": 1.0801633596420288,
|
| 389 |
+
"eval_runtime": 76.7811,
|
| 390 |
+
"eval_samples_per_second": 7.085,
|
| 391 |
+
"eval_steps_per_second": 0.886,
|
| 392 |
+
"step": 1200
|
| 393 |
+
},
|
| 394 |
+
{
|
| 395 |
+
"epoch": 0.39,
|
| 396 |
+
"learning_rate": 0.00018584868389518152,
|
| 397 |
+
"loss": 0.7158,
|
| 398 |
+
"step": 1225
|
| 399 |
+
},
|
| 400 |
+
{
|
| 401 |
+
"epoch": 0.4,
|
| 402 |
+
"learning_rate": 0.00018517571650536056,
|
| 403 |
+
"loss": 0.601,
|
| 404 |
+
"step": 1250
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 0.41,
|
| 408 |
+
"learning_rate": 0.0001844883949249013,
|
| 409 |
+
"loss": 0.6362,
|
| 410 |
+
"step": 1275
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.42,
|
| 414 |
+
"learning_rate": 0.00018378683498429402,
|
| 415 |
+
"loss": 0.5795,
|
| 416 |
+
"step": 1300
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.42,
|
| 420 |
+
"eval_loss": 1.1198811531066895,
|
| 421 |
+
"eval_runtime": 76.7858,
|
| 422 |
+
"eval_samples_per_second": 7.085,
|
| 423 |
+
"eval_steps_per_second": 0.886,
|
| 424 |
+
"step": 1300
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.42,
|
| 428 |
+
"learning_rate": 0.00018307115491354064,
|
| 429 |
+
"loss": 0.6037,
|
| 430 |
+
"step": 1325
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.43,
|
| 434 |
+
"learning_rate": 0.0001823414753222303,
|
| 435 |
+
"loss": 0.5866,
|
| 436 |
+
"step": 1350
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"epoch": 0.44,
|
| 440 |
+
"learning_rate": 0.00018159791917921362,
|
| 441 |
+
"loss": 0.6389,
|
| 442 |
+
"step": 1375
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.45,
|
| 446 |
+
"learning_rate": 0.00018084061179187946,
|
| 447 |
+
"loss": 0.6039,
|
| 448 |
+
"step": 1400
|
| 449 |
+
},
|
| 450 |
+
{
|
| 451 |
+
"epoch": 0.45,
|
| 452 |
+
"eval_loss": 1.1011444330215454,
|
| 453 |
+
"eval_runtime": 76.8374,
|
| 454 |
+
"eval_samples_per_second": 7.08,
|
| 455 |
+
"eval_steps_per_second": 0.885,
|
| 456 |
+
"step": 1400
|
| 457 |
+
},
|
| 458 |
+
{
|
| 459 |
+
"epoch": 0.46,
|
| 460 |
+
"learning_rate": 0.00018006968078503746,
|
| 461 |
+
"loss": 0.5734,
|
| 462 |
+
"step": 1425
|
| 463 |
+
},
|
| 464 |
+
{
|
| 465 |
+
"epoch": 0.46,
|
| 466 |
+
"learning_rate": 0.0001792852560794103,
|
| 467 |
+
"loss": 0.565,
|
| 468 |
+
"step": 1450
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 0.47,
|
| 472 |
+
"learning_rate": 0.00017848746986973883,
|
| 473 |
+
"loss": 0.6221,
|
| 474 |
+
"step": 1475
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 0.48,
|
| 478 |
+
"learning_rate": 0.00017767645660250384,
|
| 479 |
+
"loss": 0.6266,
|
| 480 |
+
"step": 1500
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.48,
|
| 484 |
+
"eval_loss": 1.0841057300567627,
|
| 485 |
+
"eval_runtime": 76.7968,
|
| 486 |
+
"eval_samples_per_second": 7.084,
|
| 487 |
+
"eval_steps_per_second": 0.885,
|
| 488 |
+
"step": 1500
|
| 489 |
+
},
|
| 490 |
+
{
|
| 491 |
+
"epoch": 0.49,
|
| 492 |
+
"learning_rate": 0.00017685235295326893,
|
| 493 |
+
"loss": 0.5798,
|
| 494 |
+
"step": 1525
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.5,
|
| 498 |
+
"learning_rate": 0.00017601529780364688,
|
| 499 |
+
"loss": 0.5628,
|
| 500 |
+
"step": 1550
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.5,
|
| 504 |
+
"learning_rate": 0.0001751654322178951,
|
| 505 |
+
"loss": 0.5943,
|
| 506 |
+
"step": 1575
|
| 507 |
+
},
|
| 508 |
+
{
|
| 509 |
+
"epoch": 0.51,
|
| 510 |
+
"learning_rate": 0.00017430289941914258,
|
| 511 |
+
"loss": 0.57,
|
| 512 |
+
"step": 1600
|
| 513 |
+
},
|
| 514 |
+
{
|
| 515 |
+
"epoch": 0.51,
|
| 516 |
+
"eval_loss": 1.067173957824707,
|
| 517 |
+
"eval_runtime": 76.7443,
|
| 518 |
+
"eval_samples_per_second": 7.088,
|
| 519 |
+
"eval_steps_per_second": 0.886,
|
| 520 |
+
"step": 1600
|
| 521 |
+
},
|
| 522 |
+
{
|
| 523 |
+
"epoch": 0.52,
|
| 524 |
+
"learning_rate": 0.00017342784476525347,
|
| 525 |
+
"loss": 0.6021,
|
| 526 |
+
"step": 1625
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.53,
|
| 530 |
+
"learning_rate": 0.00017254041572433058,
|
| 531 |
+
"loss": 0.5314,
|
| 532 |
+
"step": 1650
|
| 533 |
+
},
|
| 534 |
+
{
|
| 535 |
+
"epoch": 0.54,
|
| 536 |
+
"learning_rate": 0.00017164076184986345,
|
| 537 |
+
"loss": 0.5162,
|
| 538 |
+
"step": 1675
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.55,
|
| 542 |
+
"learning_rate": 0.00017072903475552503,
|
| 543 |
+
"loss": 0.5693,
|
| 544 |
+
"step": 1700
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"epoch": 0.55,
|
| 548 |
+
"eval_loss": 1.059133768081665,
|
| 549 |
+
"eval_runtime": 76.8125,
|
| 550 |
+
"eval_samples_per_second": 7.082,
|
| 551 |
+
"eval_steps_per_second": 0.885,
|
| 552 |
+
"step": 1700
|
| 553 |
+
},
|
| 554 |
+
{
|
| 555 |
+
"epoch": 0.55,
|
| 556 |
+
"learning_rate": 0.00016980538808962102,
|
| 557 |
+
"loss": 0.5466,
|
| 558 |
+
"step": 1725
|
| 559 |
+
},
|
| 560 |
+
{
|
| 561 |
+
"epoch": 0.56,
|
| 562 |
+
"learning_rate": 0.00016886997750919619,
|
| 563 |
+
"loss": 0.4934,
|
| 564 |
+
"step": 1750
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.57,
|
| 568 |
+
"learning_rate": 0.0001679229606538026,
|
| 569 |
+
"loss": 0.5666,
|
| 570 |
+
"step": 1775
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.58,
|
| 574 |
+
"learning_rate": 0.00016696449711893344,
|
| 575 |
+
"loss": 0.4821,
|
| 576 |
+
"step": 1800
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 0.58,
|
| 580 |
+
"eval_loss": 1.0875073671340942,
|
| 581 |
+
"eval_runtime": 76.8354,
|
| 582 |
+
"eval_samples_per_second": 7.08,
|
| 583 |
+
"eval_steps_per_second": 0.885,
|
| 584 |
+
"step": 1800
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.59,
|
| 588 |
+
"learning_rate": 0.00016599474842912722,
|
| 589 |
+
"loss": 0.5816,
|
| 590 |
+
"step": 1825
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 0.59,
|
| 594 |
+
"learning_rate": 0.0001650138780107469,
|
| 595 |
+
"loss": 0.5616,
|
| 596 |
+
"step": 1850
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"epoch": 0.6,
|
| 600 |
+
"learning_rate": 0.00016402205116443868,
|
| 601 |
+
"loss": 0.5239,
|
| 602 |
+
"step": 1875
|
| 603 |
+
},
|
| 604 |
+
{
|
| 605 |
+
"epoch": 0.61,
|
| 606 |
+
"learning_rate": 0.00016301943503727468,
|
| 607 |
+
"loss": 0.4953,
|
| 608 |
+
"step": 1900
|
| 609 |
+
},
|
| 610 |
+
{
|
| 611 |
+
"epoch": 0.61,
|
| 612 |
+
"eval_loss": 1.0953130722045898,
|
| 613 |
+
"eval_runtime": 76.7571,
|
| 614 |
+
"eval_samples_per_second": 7.087,
|
| 615 |
+
"eval_steps_per_second": 0.886,
|
| 616 |
+
"step": 1900
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"epoch": 0.62,
|
| 620 |
+
"learning_rate": 0.00016200619859458467,
|
| 621 |
+
"loss": 0.5118,
|
| 622 |
+
"step": 1925
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.63,
|
| 626 |
+
"learning_rate": 0.00016098251259148125,
|
| 627 |
+
"loss": 0.5194,
|
| 628 |
+
"step": 1950
|
| 629 |
+
},
|
| 630 |
+
{
|
| 631 |
+
"epoch": 0.63,
|
| 632 |
+
"learning_rate": 0.00015994854954408337,
|
| 633 |
+
"loss": 0.5503,
|
| 634 |
+
"step": 1975
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.64,
|
| 638 |
+
"learning_rate": 0.00015890448370044317,
|
| 639 |
+
"loss": 0.4673,
|
| 640 |
+
"step": 2000
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.64,
|
| 644 |
+
"eval_loss": 1.1145678758621216,
|
| 645 |
+
"eval_runtime": 76.7971,
|
| 646 |
+
"eval_samples_per_second": 7.084,
|
| 647 |
+
"eval_steps_per_second": 0.885,
|
| 648 |
+
"step": 2000
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.65,
|
| 652 |
+
"learning_rate": 0.0001578504910111811,
|
| 653 |
+
"loss": 0.5086,
|
| 654 |
+
"step": 2025
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.66,
|
| 658 |
+
"learning_rate": 0.00015678674909983364,
|
| 659 |
+
"loss": 0.4686,
|
| 660 |
+
"step": 2050
|
| 661 |
+
},
|
| 662 |
+
{
|
| 663 |
+
"epoch": 0.67,
|
| 664 |
+
"learning_rate": 0.00015571343723291963,
|
| 665 |
+
"loss": 0.5025,
|
| 666 |
+
"step": 2075
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 0.67,
|
| 670 |
+
"learning_rate": 0.00015463073628972936,
|
| 671 |
+
"loss": 0.5223,
|
| 672 |
+
"step": 2100
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.67,
|
| 676 |
+
"eval_loss": 1.075910210609436,
|
| 677 |
+
"eval_runtime": 76.8054,
|
| 678 |
+
"eval_samples_per_second": 7.083,
|
| 679 |
+
"eval_steps_per_second": 0.885,
|
| 680 |
+
"step": 2100
|
| 681 |
+
},
|
| 682 |
+
{
|
| 683 |
+
"epoch": 0.68,
|
| 684 |
+
"learning_rate": 0.000153538828731842,
|
| 685 |
+
"loss": 0.4457,
|
| 686 |
+
"step": 2125
|
| 687 |
+
},
|
| 688 |
+
{
|
| 689 |
+
"epoch": 0.69,
|
| 690 |
+
"learning_rate": 0.00015243789857237645,
|
| 691 |
+
"loss": 0.471,
|
| 692 |
+
"step": 2150
|
| 693 |
+
},
|
| 694 |
+
{
|
| 695 |
+
"epoch": 0.7,
|
| 696 |
+
"learning_rate": 0.00015132813134498054,
|
| 697 |
+
"loss": 0.4692,
|
| 698 |
+
"step": 2175
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 0.71,
|
| 702 |
+
"learning_rate": 0.000150209714072564,
|
| 703 |
+
"loss": 0.4661,
|
| 704 |
+
"step": 2200
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.71,
|
| 708 |
+
"eval_loss": 1.0707464218139648,
|
| 709 |
+
"eval_runtime": 76.7556,
|
| 710 |
+
"eval_samples_per_second": 7.087,
|
| 711 |
+
"eval_steps_per_second": 0.886,
|
| 712 |
+
"step": 2200
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 0.71,
|
| 716 |
+
"learning_rate": 0.00014908283523578077,
|
| 717 |
+
"loss": 0.442,
|
| 718 |
+
"step": 2225
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.72,
|
| 722 |
+
"learning_rate": 0.00014794768474126518,
|
| 723 |
+
"loss": 0.5075,
|
| 724 |
+
"step": 2250
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.73,
|
| 728 |
+
"learning_rate": 0.00014680445388962814,
|
| 729 |
+
"loss": 0.4969,
|
| 730 |
+
"step": 2275
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.74,
|
| 734 |
+
"learning_rate": 0.00014565333534321826,
|
| 735 |
+
"loss": 0.4642,
|
| 736 |
+
"step": 2300
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"epoch": 0.74,
|
| 740 |
+
"eval_loss": 1.0463252067565918,
|
| 741 |
+
"eval_runtime": 76.7954,
|
| 742 |
+
"eval_samples_per_second": 7.084,
|
| 743 |
+
"eval_steps_per_second": 0.885,
|
| 744 |
+
"step": 2300
|
| 745 |
+
},
|
| 746 |
+
{
|
| 747 |
+
"epoch": 0.75,
|
| 748 |
+
"learning_rate": 0.0001444945230936536,
|
| 749 |
+
"loss": 0.4412,
|
| 750 |
+
"step": 2325
|
| 751 |
+
},
|
| 752 |
+
{
|
| 753 |
+
"epoch": 0.75,
|
| 754 |
+
"learning_rate": 0.00014332821242912927,
|
| 755 |
+
"loss": 0.4657,
|
| 756 |
+
"step": 2350
|
| 757 |
+
},
|
| 758 |
+
{
|
| 759 |
+
"epoch": 0.76,
|
| 760 |
+
"learning_rate": 0.0001421545999015066,
|
| 761 |
+
"loss": 0.4311,
|
| 762 |
+
"step": 2375
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 0.77,
|
| 766 |
+
"learning_rate": 0.00014097388329318943,
|
| 767 |
+
"loss": 0.45,
|
| 768 |
+
"step": 2400
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.77,
|
| 772 |
+
"eval_loss": 1.076710820198059,
|
| 773 |
+
"eval_runtime": 76.7708,
|
| 774 |
+
"eval_samples_per_second": 7.086,
|
| 775 |
+
"eval_steps_per_second": 0.886,
|
| 776 |
+
"step": 2400
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 0.78,
|
| 780 |
+
"learning_rate": 0.00013978626158379285,
|
| 781 |
+
"loss": 0.4336,
|
| 782 |
+
"step": 2425
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.79,
|
| 786 |
+
"learning_rate": 0.00013859193491661036,
|
| 787 |
+
"loss": 0.4002,
|
| 788 |
+
"step": 2450
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"epoch": 0.79,
|
| 792 |
+
"learning_rate": 0.0001373911045648846,
|
| 793 |
+
"loss": 0.4141,
|
| 794 |
+
"step": 2475
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.8,
|
| 798 |
+
"learning_rate": 0.00013618397289788832,
|
| 799 |
+
"loss": 0.452,
|
| 800 |
+
"step": 2500
|
| 801 |
+
},
|
| 802 |
+
{
|
| 803 |
+
"epoch": 0.8,
|
| 804 |
+
"eval_loss": 1.085994005203247,
|
| 805 |
+
"eval_runtime": 76.8556,
|
| 806 |
+
"eval_samples_per_second": 7.078,
|
| 807 |
+
"eval_steps_per_second": 0.885,
|
| 808 |
+
"step": 2500
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.81,
|
| 812 |
+
"learning_rate": 0.00013497074334681966,
|
| 813 |
+
"loss": 0.3574,
|
| 814 |
+
"step": 2525
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 0.82,
|
| 818 |
+
"learning_rate": 0.00013375162037051954,
|
| 819 |
+
"loss": 0.4107,
|
| 820 |
+
"step": 2550
|
| 821 |
+
},
|
| 822 |
+
{
|
| 823 |
+
"epoch": 0.83,
|
| 824 |
+
"learning_rate": 0.000132526809421015,
|
| 825 |
+
"loss": 0.4616,
|
| 826 |
+
"step": 2575
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 0.83,
|
| 830 |
+
"learning_rate": 0.0001312965169088957,
|
| 831 |
+
"loss": 0.4397,
|
| 832 |
+
"step": 2600
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"epoch": 0.83,
|
| 836 |
+
"eval_loss": 1.088114619255066,
|
| 837 |
+
"eval_runtime": 76.7923,
|
| 838 |
+
"eval_samples_per_second": 7.084,
|
| 839 |
+
"eval_steps_per_second": 0.886,
|
| 840 |
+
"step": 2600
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"epoch": 0.84,
|
| 844 |
+
"learning_rate": 0.00013006095016852848,
|
| 845 |
+
"loss": 0.3993,
|
| 846 |
+
"step": 2625
|
| 847 |
+
},
|
| 848 |
+
{
|
| 849 |
+
"epoch": 0.85,
|
| 850 |
+
"learning_rate": 0.0001288203174231168,
|
| 851 |
+
"loss": 0.3973,
|
| 852 |
+
"step": 2650
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.86,
|
| 856 |
+
"learning_rate": 0.00012757482774960964,
|
| 857 |
+
"loss": 0.3843,
|
| 858 |
+
"step": 2675
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"epoch": 0.87,
|
| 862 |
+
"learning_rate": 0.00012632469104346722,
|
| 863 |
+
"loss": 0.3932,
|
| 864 |
+
"step": 2700
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.87,
|
| 868 |
+
"eval_loss": 1.0900908708572388,
|
| 869 |
+
"eval_runtime": 76.8201,
|
| 870 |
+
"eval_samples_per_second": 7.081,
|
| 871 |
+
"eval_steps_per_second": 0.885,
|
| 872 |
+
"step": 2700
|
| 873 |
+
},
|
| 874 |
+
{
|
| 875 |
+
"epoch": 0.87,
|
| 876 |
+
"learning_rate": 0.00012507011798328823,
|
| 877 |
+
"loss": 0.367,
|
| 878 |
+
"step": 2725
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.88,
|
| 882 |
+
"learning_rate": 0.00012381131999530563,
|
| 883 |
+
"loss": 0.4149,
|
| 884 |
+
"step": 2750
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 0.89,
|
| 888 |
+
"learning_rate": 0.000122548509217756,
|
| 889 |
+
"loss": 0.3864,
|
| 890 |
+
"step": 2775
|
| 891 |
+
},
|
| 892 |
+
{
|
| 893 |
+
"epoch": 0.9,
|
| 894 |
+
"learning_rate": 0.00012128189846512894,
|
| 895 |
+
"loss": 0.3654,
|
| 896 |
+
"step": 2800
|
| 897 |
+
},
|
| 898 |
+
{
|
| 899 |
+
"epoch": 0.9,
|
| 900 |
+
"eval_loss": 1.0753364562988281,
|
| 901 |
+
"eval_runtime": 76.8365,
|
| 902 |
+
"eval_samples_per_second": 7.08,
|
| 903 |
+
"eval_steps_per_second": 0.885,
|
| 904 |
+
"step": 2800
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"epoch": 0.91,
|
| 908 |
+
"learning_rate": 0.00012001170119230286,
|
| 909 |
+
"loss": 0.387,
|
| 910 |
+
"step": 2825
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 0.91,
|
| 914 |
+
"learning_rate": 0.00011873813145857249,
|
| 915 |
+
"loss": 0.3551,
|
| 916 |
+
"step": 2850
|
| 917 |
+
},
|
| 918 |
+
{
|
| 919 |
+
"epoch": 0.92,
|
| 920 |
+
"learning_rate": 0.00011746140389157462,
|
| 921 |
+
"loss": 0.385,
|
| 922 |
+
"step": 2875
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.93,
|
| 926 |
+
"learning_rate": 0.00011618173365111824,
|
| 927 |
+
"loss": 0.3227,
|
| 928 |
+
"step": 2900
|
| 929 |
+
},
|
| 930 |
+
{
|
| 931 |
+
"epoch": 0.93,
|
| 932 |
+
"eval_loss": 1.0998799800872803,
|
| 933 |
+
"eval_runtime": 76.6275,
|
| 934 |
+
"eval_samples_per_second": 7.099,
|
| 935 |
+
"eval_steps_per_second": 0.887,
|
| 936 |
+
"step": 2900
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.94,
|
| 940 |
+
"learning_rate": 0.00011489933639292469,
|
| 941 |
+
"loss": 0.3459,
|
| 942 |
+
"step": 2925
|
| 943 |
+
},
|
| 944 |
+
{
|
| 945 |
+
"epoch": 0.95,
|
| 946 |
+
"learning_rate": 0.00011361442823228453,
|
| 947 |
+
"loss": 0.3505,
|
| 948 |
+
"step": 2950
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.95,
|
| 952 |
+
"learning_rate": 0.00011232722570763667,
|
| 953 |
+
"loss": 0.3644,
|
| 954 |
+
"step": 2975
|
| 955 |
+
},
|
| 956 |
+
{
|
| 957 |
+
"epoch": 0.96,
|
| 958 |
+
"learning_rate": 0.00011103794574407657,
|
| 959 |
+
"loss": 0.3238,
|
| 960 |
+
"step": 3000
|
| 961 |
+
},
|
| 962 |
+
{
|
| 963 |
+
"epoch": 0.96,
|
| 964 |
+
"eval_loss": 1.1243908405303955,
|
| 965 |
+
"eval_runtime": 76.7936,
|
| 966 |
+
"eval_samples_per_second": 7.084,
|
| 967 |
+
"eval_steps_per_second": 0.885,
|
| 968 |
+
"step": 3000
|
| 969 |
+
}
|
| 970 |
+
],
|
| 971 |
+
"max_steps": 6238,
|
| 972 |
+
"num_train_epochs": 2,
|
| 973 |
+
"total_flos": 6.802205860248576e+16,
|
| 974 |
+
"trial_name": null,
|
| 975 |
+
"trial_params": null
|
| 976 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ef38dd7aec7fe510347279e9dc83ccc69e2f6ac59fe3379b37872b5612d8aa4
|
| 3 |
+
size 4408
|