Upload 13 files
Browse files- README.md +34 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- adapter_model.safetensors +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.model +3 -0
- tokenizer_config.json +40 -0
- trainer_state.json +815 -0
- training_args.bin +3 -0
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: True
|
| 17 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 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: True
|
| 29 |
+
- bnb_4bit_compute_dtype: bfloat16
|
| 30 |
+
### Framework versions
|
| 31 |
+
|
| 32 |
+
- PEFT 0.4.0
|
| 33 |
+
|
| 34 |
+
- 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-2-7b-chat-hf",
|
| 4 |
+
"bias": "none",
|
| 5 |
+
"fan_in_fan_out": false,
|
| 6 |
+
"inference_mode": true,
|
| 7 |
+
"init_lora_weights": true,
|
| 8 |
+
"layers_pattern": null,
|
| 9 |
+
"layers_to_transform": null,
|
| 10 |
+
"lora_alpha": 32,
|
| 11 |
+
"lora_dropout": 0.05,
|
| 12 |
+
"modules_to_save": null,
|
| 13 |
+
"peft_type": "LORA",
|
| 14 |
+
"r": 8,
|
| 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 sha256:7de667110bc25195b5295b002a18db9a16257329155a94d36eccf142a06adc98
|
| 3 |
+
size 16823434
|
adapter_model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4906f2772d341e44fd77d06b83c6bf82ec89ddc242ad469112ff39e24d7a8080
|
| 3 |
+
size 16794200
|
optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:de10babd43e9f8e4e386d64b523ff769001361d1a7e969501aa64ca585cb6878
|
| 3 |
+
size 8556090
|
rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c84fd65e9e48a2aaba56eb31f1c7ff721aec3e1d3a68505905e0e8048c884a3e
|
| 3 |
+
size 14244
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2398e2f77cd71aef986dd87578cc135e4c8437f8ee57ac4403039b04b09c9f95
|
| 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.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
| 3 |
+
size 499723
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,40 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"bos_token": "<s>",
|
| 29 |
+
"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 %}",
|
| 30 |
+
"clean_up_tokenization_spaces": false,
|
| 31 |
+
"eos_token": "</s>",
|
| 32 |
+
"legacy": false,
|
| 33 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 34 |
+
"pad_token": "</s>",
|
| 35 |
+
"padding_side": "right",
|
| 36 |
+
"sp_model_kwargs": {},
|
| 37 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 38 |
+
"unk_token": "<unk>",
|
| 39 |
+
"use_default_system_prompt": true
|
| 40 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,815 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 0.40216550657385924,
|
| 5 |
+
"eval_steps": 65,
|
| 6 |
+
"global_step": 130,
|
| 7 |
+
"is_hyper_param_search": false,
|
| 8 |
+
"is_local_process_zero": true,
|
| 9 |
+
"is_world_process_zero": true,
|
| 10 |
+
"log_history": [
|
| 11 |
+
{
|
| 12 |
+
"epoch": 0.0,
|
| 13 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 14 |
+
"loss": 2.7493,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 2.3529411764705884e-05,
|
| 20 |
+
"loss": 2.6209,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 3.529411764705883e-05,
|
| 26 |
+
"loss": 2.6323,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 4.705882352941177e-05,
|
| 32 |
+
"loss": 2.7371,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 5.882352941176471e-05,
|
| 38 |
+
"loss": 2.7399,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 7.058823529411765e-05,
|
| 44 |
+
"loss": 2.6775,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 8.23529411764706e-05,
|
| 50 |
+
"loss": 2.6392,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.02,
|
| 55 |
+
"learning_rate": 9.411764705882353e-05,
|
| 56 |
+
"loss": 2.6636,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 0.00010588235294117647,
|
| 62 |
+
"loss": 2.6269,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 0.00011764705882352942,
|
| 68 |
+
"loss": 2.6557,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.03,
|
| 73 |
+
"learning_rate": 0.00012941176470588237,
|
| 74 |
+
"loss": 2.5117,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 0.0001411764705882353,
|
| 80 |
+
"loss": 2.54,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 0.00015294117647058822,
|
| 86 |
+
"loss": 2.4645,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.04,
|
| 91 |
+
"learning_rate": 0.0001647058823529412,
|
| 92 |
+
"loss": 2.4728,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 0.00017647058823529413,
|
| 98 |
+
"loss": 2.5242,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 0.00018823529411764707,
|
| 104 |
+
"loss": 2.4592,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.05,
|
| 109 |
+
"learning_rate": 0.0002,
|
| 110 |
+
"loss": 2.364,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.06,
|
| 115 |
+
"learning_rate": 0.00019999472984871732,
|
| 116 |
+
"loss": 2.3955,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.06,
|
| 121 |
+
"learning_rate": 0.00019997891995035912,
|
| 122 |
+
"loss": 2.3193,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.06,
|
| 127 |
+
"learning_rate": 0.0001999525719713366,
|
| 128 |
+
"loss": 2.3536,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.06,
|
| 133 |
+
"learning_rate": 0.0001999156886888064,
|
| 134 |
+
"loss": 2.4059,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 0.00019986827399037812,
|
| 140 |
+
"loss": 2.4518,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.07,
|
| 145 |
+
"learning_rate": 0.00019981033287370443,
|
| 146 |
+
"loss": 2.3709,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.07,
|
| 151 |
+
"learning_rate": 0.00019974187144595432,
|
| 152 |
+
"loss": 2.4401,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.08,
|
| 157 |
+
"learning_rate": 0.00019966289692316944,
|
| 158 |
+
"loss": 2.3015,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.08,
|
| 163 |
+
"learning_rate": 0.00019957341762950344,
|
| 164 |
+
"loss": 2.3688,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.08,
|
| 169 |
+
"learning_rate": 0.00019947344299634464,
|
| 170 |
+
"loss": 2.2737,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09,
|
| 175 |
+
"learning_rate": 0.00019936298356132176,
|
| 176 |
+
"loss": 2.2844,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.09,
|
| 181 |
+
"learning_rate": 0.0001992420509671936,
|
| 182 |
+
"loss": 2.2693,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.09,
|
| 187 |
+
"learning_rate": 0.00019911065796062135,
|
| 188 |
+
"loss": 2.2691,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.1,
|
| 193 |
+
"learning_rate": 0.00019896881839082556,
|
| 194 |
+
"loss": 2.2378,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.1,
|
| 199 |
+
"learning_rate": 0.00019881654720812594,
|
| 200 |
+
"loss": 2.1501,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.1,
|
| 205 |
+
"learning_rate": 0.00019865386046236596,
|
| 206 |
+
"loss": 2.0803,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.11,
|
| 211 |
+
"learning_rate": 0.00019848077530122083,
|
| 212 |
+
"loss": 2.1133,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.11,
|
| 217 |
+
"learning_rate": 0.0001982973099683902,
|
| 218 |
+
"loss": 2.0154,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.11,
|
| 223 |
+
"learning_rate": 0.00019810348380167527,
|
| 224 |
+
"loss": 1.962,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.11,
|
| 229 |
+
"learning_rate": 0.00019789931723094046,
|
| 230 |
+
"loss": 1.9794,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.12,
|
| 235 |
+
"learning_rate": 0.0001976848317759601,
|
| 236 |
+
"loss": 2.017,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.12,
|
| 241 |
+
"learning_rate": 0.00019746005004415005,
|
| 242 |
+
"loss": 1.9816,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.12,
|
| 247 |
+
"learning_rate": 0.00019722499572818496,
|
| 248 |
+
"loss": 1.9713,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.13,
|
| 253 |
+
"learning_rate": 0.00019697969360350098,
|
| 254 |
+
"loss": 1.9338,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.13,
|
| 259 |
+
"learning_rate": 0.00019672416952568416,
|
| 260 |
+
"loss": 1.983,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.13,
|
| 265 |
+
"learning_rate": 0.00019645845042774553,
|
| 266 |
+
"loss": 1.821,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.14,
|
| 271 |
+
"learning_rate": 0.00019618256431728194,
|
| 272 |
+
"loss": 1.9501,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.14,
|
| 277 |
+
"learning_rate": 0.00019589654027352414,
|
| 278 |
+
"loss": 1.9909,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.14,
|
| 283 |
+
"learning_rate": 0.0001956004084442718,
|
| 284 |
+
"loss": 1.8494,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.15,
|
| 289 |
+
"learning_rate": 0.00019529420004271567,
|
| 290 |
+
"loss": 1.8093,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.15,
|
| 295 |
+
"learning_rate": 0.0001949779473441478,
|
| 296 |
+
"loss": 1.7693,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.15,
|
| 301 |
+
"learning_rate": 0.00019465168368255946,
|
| 302 |
+
"loss": 1.7823,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.15,
|
| 307 |
+
"learning_rate": 0.00019431544344712776,
|
| 308 |
+
"loss": 1.7239,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.16,
|
| 313 |
+
"learning_rate": 0.00019396926207859084,
|
| 314 |
+
"loss": 2.2562,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.16,
|
| 319 |
+
"learning_rate": 0.00019361317606551238,
|
| 320 |
+
"loss": 2.201,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.16,
|
| 325 |
+
"learning_rate": 0.00019324722294043558,
|
| 326 |
+
"loss": 2.2162,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.17,
|
| 331 |
+
"learning_rate": 0.00019287144127592704,
|
| 332 |
+
"loss": 2.2388,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.17,
|
| 337 |
+
"learning_rate": 0.0001924858706805112,
|
| 338 |
+
"loss": 2.2686,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.17,
|
| 343 |
+
"learning_rate": 0.0001920905517944954,
|
| 344 |
+
"loss": 2.213,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.18,
|
| 349 |
+
"learning_rate": 0.00019168552628568631,
|
| 350 |
+
"loss": 2.1732,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.18,
|
| 355 |
+
"learning_rate": 0.00019127083684499806,
|
| 356 |
+
"loss": 2.2206,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.18,
|
| 361 |
+
"learning_rate": 0.00019084652718195238,
|
| 362 |
+
"loss": 2.0658,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.19,
|
| 367 |
+
"learning_rate": 0.0001904126420200716,
|
| 368 |
+
"loss": 2.1432,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.19,
|
| 373 |
+
"learning_rate": 0.00018996922709216455,
|
| 374 |
+
"loss": 2.0427,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.19,
|
| 379 |
+
"learning_rate": 0.00018951632913550626,
|
| 380 |
+
"loss": 2.1674,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.19,
|
| 385 |
+
"learning_rate": 0.00018905399588691163,
|
| 386 |
+
"loss": 2.1218,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.2,
|
| 391 |
+
"learning_rate": 0.00018858227607770398,
|
| 392 |
+
"loss": 2.1721,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.2,
|
| 397 |
+
"learning_rate": 0.00018810121942857845,
|
| 398 |
+
"loss": 2.1525,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.2,
|
| 403 |
+
"eval_loss": 2.053250789642334,
|
| 404 |
+
"eval_runtime": 25.1667,
|
| 405 |
+
"eval_samples_per_second": 3.457,
|
| 406 |
+
"eval_steps_per_second": 0.437,
|
| 407 |
+
"step": 65
|
| 408 |
+
},
|
| 409 |
+
{
|
| 410 |
+
"epoch": 0.2,
|
| 411 |
+
"learning_rate": 0.00018761087664436138,
|
| 412 |
+
"loss": 2.1132,
|
| 413 |
+
"step": 66
|
| 414 |
+
},
|
| 415 |
+
{
|
| 416 |
+
"epoch": 0.21,
|
| 417 |
+
"learning_rate": 0.00018711129940866575,
|
| 418 |
+
"loss": 2.127,
|
| 419 |
+
"step": 67
|
| 420 |
+
},
|
| 421 |
+
{
|
| 422 |
+
"epoch": 0.21,
|
| 423 |
+
"learning_rate": 0.00018660254037844388,
|
| 424 |
+
"loss": 2.1563,
|
| 425 |
+
"step": 68
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 0.21,
|
| 429 |
+
"learning_rate": 0.00018608465317843678,
|
| 430 |
+
"loss": 2.0825,
|
| 431 |
+
"step": 69
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.22,
|
| 435 |
+
"learning_rate": 0.00018555769239552233,
|
| 436 |
+
"loss": 2.1625,
|
| 437 |
+
"step": 70
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.22,
|
| 441 |
+
"learning_rate": 0.00018502171357296144,
|
| 442 |
+
"loss": 2.1801,
|
| 443 |
+
"step": 71
|
| 444 |
+
},
|
| 445 |
+
{
|
| 446 |
+
"epoch": 0.22,
|
| 447 |
+
"learning_rate": 0.00018447677320454367,
|
| 448 |
+
"loss": 2.1931,
|
| 449 |
+
"step": 72
|
| 450 |
+
},
|
| 451 |
+
{
|
| 452 |
+
"epoch": 0.23,
|
| 453 |
+
"learning_rate": 0.00018392292872863267,
|
| 454 |
+
"loss": 2.1354,
|
| 455 |
+
"step": 73
|
| 456 |
+
},
|
| 457 |
+
{
|
| 458 |
+
"epoch": 0.23,
|
| 459 |
+
"learning_rate": 0.00018336023852211195,
|
| 460 |
+
"loss": 2.2592,
|
| 461 |
+
"step": 74
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 0.23,
|
| 465 |
+
"learning_rate": 0.00018278876189423179,
|
| 466 |
+
"loss": 2.1984,
|
| 467 |
+
"step": 75
|
| 468 |
+
},
|
| 469 |
+
{
|
| 470 |
+
"epoch": 0.24,
|
| 471 |
+
"learning_rate": 0.00018220855908035783,
|
| 472 |
+
"loss": 2.1576,
|
| 473 |
+
"step": 76
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.24,
|
| 477 |
+
"learning_rate": 0.0001816196912356222,
|
| 478 |
+
"loss": 2.158,
|
| 479 |
+
"step": 77
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.24,
|
| 483 |
+
"learning_rate": 0.00018102222042847737,
|
| 484 |
+
"loss": 2.1722,
|
| 485 |
+
"step": 78
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"epoch": 0.24,
|
| 489 |
+
"learning_rate": 0.00018041620963415417,
|
| 490 |
+
"loss": 2.144,
|
| 491 |
+
"step": 79
|
| 492 |
+
},
|
| 493 |
+
{
|
| 494 |
+
"epoch": 0.25,
|
| 495 |
+
"learning_rate": 0.000179801722728024,
|
| 496 |
+
"loss": 2.1204,
|
| 497 |
+
"step": 80
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 0.25,
|
| 501 |
+
"learning_rate": 0.00017917882447886582,
|
| 502 |
+
"loss": 2.1186,
|
| 503 |
+
"step": 81
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"epoch": 0.25,
|
| 507 |
+
"learning_rate": 0.00017854758054203988,
|
| 508 |
+
"loss": 2.1699,
|
| 509 |
+
"step": 82
|
| 510 |
+
},
|
| 511 |
+
{
|
| 512 |
+
"epoch": 0.26,
|
| 513 |
+
"learning_rate": 0.00017790805745256704,
|
| 514 |
+
"loss": 2.0864,
|
| 515 |
+
"step": 83
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.26,
|
| 519 |
+
"learning_rate": 0.0001772603226181159,
|
| 520 |
+
"loss": 2.1616,
|
| 521 |
+
"step": 84
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.26,
|
| 525 |
+
"learning_rate": 0.0001766044443118978,
|
| 526 |
+
"loss": 2.0011,
|
| 527 |
+
"step": 85
|
| 528 |
+
},
|
| 529 |
+
{
|
| 530 |
+
"epoch": 0.27,
|
| 531 |
+
"learning_rate": 0.00017594049166547073,
|
| 532 |
+
"loss": 1.9033,
|
| 533 |
+
"step": 86
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 0.27,
|
| 537 |
+
"learning_rate": 0.00017526853466145244,
|
| 538 |
+
"loss": 1.8434,
|
| 539 |
+
"step": 87
|
| 540 |
+
},
|
| 541 |
+
{
|
| 542 |
+
"epoch": 0.27,
|
| 543 |
+
"learning_rate": 0.00017458864412614434,
|
| 544 |
+
"loss": 1.9592,
|
| 545 |
+
"step": 88
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"epoch": 0.28,
|
| 549 |
+
"learning_rate": 0.00017390089172206592,
|
| 550 |
+
"loss": 1.892,
|
| 551 |
+
"step": 89
|
| 552 |
+
},
|
| 553 |
+
{
|
| 554 |
+
"epoch": 0.28,
|
| 555 |
+
"learning_rate": 0.00017320534994040148,
|
| 556 |
+
"loss": 1.8285,
|
| 557 |
+
"step": 90
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.28,
|
| 561 |
+
"learning_rate": 0.00017250209209335927,
|
| 562 |
+
"loss": 1.8733,
|
| 563 |
+
"step": 91
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.28,
|
| 567 |
+
"learning_rate": 0.0001717911923064442,
|
| 568 |
+
"loss": 1.8142,
|
| 569 |
+
"step": 92
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 0.29,
|
| 573 |
+
"learning_rate": 0.00017107272551064473,
|
| 574 |
+
"loss": 1.7412,
|
| 575 |
+
"step": 93
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 0.29,
|
| 579 |
+
"learning_rate": 0.00017034676743453499,
|
| 580 |
+
"loss": 1.721,
|
| 581 |
+
"step": 94
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"epoch": 0.29,
|
| 585 |
+
"learning_rate": 0.0001696133945962927,
|
| 586 |
+
"loss": 1.6415,
|
| 587 |
+
"step": 95
|
| 588 |
+
},
|
| 589 |
+
{
|
| 590 |
+
"epoch": 0.3,
|
| 591 |
+
"learning_rate": 0.0001688726842956339,
|
| 592 |
+
"loss": 1.7964,
|
| 593 |
+
"step": 96
|
| 594 |
+
},
|
| 595 |
+
{
|
| 596 |
+
"epoch": 0.3,
|
| 597 |
+
"learning_rate": 0.0001681247146056654,
|
| 598 |
+
"loss": 1.5657,
|
| 599 |
+
"step": 97
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.3,
|
| 603 |
+
"learning_rate": 0.00016736956436465573,
|
| 604 |
+
"loss": 1.6301,
|
| 605 |
+
"step": 98
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.31,
|
| 609 |
+
"learning_rate": 0.00016660731316772505,
|
| 610 |
+
"loss": 1.738,
|
| 611 |
+
"step": 99
|
| 612 |
+
},
|
| 613 |
+
{
|
| 614 |
+
"epoch": 0.31,
|
| 615 |
+
"learning_rate": 0.0001658380413584558,
|
| 616 |
+
"loss": 1.5882,
|
| 617 |
+
"step": 100
|
| 618 |
+
},
|
| 619 |
+
{
|
| 620 |
+
"epoch": 0.31,
|
| 621 |
+
"learning_rate": 0.0001650618300204242,
|
| 622 |
+
"loss": 2.1436,
|
| 623 |
+
"step": 101
|
| 624 |
+
},
|
| 625 |
+
{
|
| 626 |
+
"epoch": 0.32,
|
| 627 |
+
"learning_rate": 0.00016427876096865394,
|
| 628 |
+
"loss": 2.1338,
|
| 629 |
+
"step": 102
|
| 630 |
+
},
|
| 631 |
+
{
|
| 632 |
+
"epoch": 0.32,
|
| 633 |
+
"learning_rate": 0.0001634889167409923,
|
| 634 |
+
"loss": 2.1798,
|
| 635 |
+
"step": 103
|
| 636 |
+
},
|
| 637 |
+
{
|
| 638 |
+
"epoch": 0.32,
|
| 639 |
+
"learning_rate": 0.0001626923805894107,
|
| 640 |
+
"loss": 2.1958,
|
| 641 |
+
"step": 104
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.32,
|
| 645 |
+
"learning_rate": 0.00016188923647122947,
|
| 646 |
+
"loss": 2.0973,
|
| 647 |
+
"step": 105
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.33,
|
| 651 |
+
"learning_rate": 0.0001610795690402688,
|
| 652 |
+
"loss": 2.2179,
|
| 653 |
+
"step": 106
|
| 654 |
+
},
|
| 655 |
+
{
|
| 656 |
+
"epoch": 0.33,
|
| 657 |
+
"learning_rate": 0.00016026346363792567,
|
| 658 |
+
"loss": 2.1803,
|
| 659 |
+
"step": 107
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"epoch": 0.33,
|
| 663 |
+
"learning_rate": 0.00015944100628417868,
|
| 664 |
+
"loss": 2.1251,
|
| 665 |
+
"step": 108
|
| 666 |
+
},
|
| 667 |
+
{
|
| 668 |
+
"epoch": 0.34,
|
| 669 |
+
"learning_rate": 0.00015861228366852148,
|
| 670 |
+
"loss": 2.0697,
|
| 671 |
+
"step": 109
|
| 672 |
+
},
|
| 673 |
+
{
|
| 674 |
+
"epoch": 0.34,
|
| 675 |
+
"learning_rate": 0.00015777738314082514,
|
| 676 |
+
"loss": 2.1803,
|
| 677 |
+
"step": 110
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"epoch": 0.34,
|
| 681 |
+
"learning_rate": 0.00015693639270213136,
|
| 682 |
+
"loss": 2.112,
|
| 683 |
+
"step": 111
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.35,
|
| 687 |
+
"learning_rate": 0.000156089400995377,
|
| 688 |
+
"loss": 2.1563,
|
| 689 |
+
"step": 112
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.35,
|
| 693 |
+
"learning_rate": 0.0001552364972960506,
|
| 694 |
+
"loss": 2.1587,
|
| 695 |
+
"step": 113
|
| 696 |
+
},
|
| 697 |
+
{
|
| 698 |
+
"epoch": 0.35,
|
| 699 |
+
"learning_rate": 0.00015437777150278267,
|
| 700 |
+
"loss": 2.1726,
|
| 701 |
+
"step": 114
|
| 702 |
+
},
|
| 703 |
+
{
|
| 704 |
+
"epoch": 0.36,
|
| 705 |
+
"learning_rate": 0.00015351331412787004,
|
| 706 |
+
"loss": 2.0995,
|
| 707 |
+
"step": 115
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"epoch": 0.36,
|
| 711 |
+
"learning_rate": 0.0001526432162877356,
|
| 712 |
+
"loss": 2.0481,
|
| 713 |
+
"step": 116
|
| 714 |
+
},
|
| 715 |
+
{
|
| 716 |
+
"epoch": 0.36,
|
| 717 |
+
"learning_rate": 0.00015176756969332425,
|
| 718 |
+
"loss": 2.0404,
|
| 719 |
+
"step": 117
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 0.37,
|
| 723 |
+
"learning_rate": 0.0001508864666404365,
|
| 724 |
+
"loss": 2.1471,
|
| 725 |
+
"step": 118
|
| 726 |
+
},
|
| 727 |
+
{
|
| 728 |
+
"epoch": 0.37,
|
| 729 |
+
"learning_rate": 0.00015000000000000001,
|
| 730 |
+
"loss": 2.1167,
|
| 731 |
+
"step": 119
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.37,
|
| 735 |
+
"learning_rate": 0.00014910826320828084,
|
| 736 |
+
"loss": 2.1705,
|
| 737 |
+
"step": 120
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"epoch": 0.37,
|
| 741 |
+
"learning_rate": 0.0001482113502570349,
|
| 742 |
+
"loss": 2.0837,
|
| 743 |
+
"step": 121
|
| 744 |
+
},
|
| 745 |
+
{
|
| 746 |
+
"epoch": 0.38,
|
| 747 |
+
"learning_rate": 0.00014730935568360102,
|
| 748 |
+
"loss": 2.1088,
|
| 749 |
+
"step": 122
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"epoch": 0.38,
|
| 753 |
+
"learning_rate": 0.00014640237456093634,
|
| 754 |
+
"loss": 2.046,
|
| 755 |
+
"step": 123
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 0.38,
|
| 759 |
+
"learning_rate": 0.00014549050248759547,
|
| 760 |
+
"loss": 2.1104,
|
| 761 |
+
"step": 124
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.39,
|
| 765 |
+
"learning_rate": 0.00014457383557765386,
|
| 766 |
+
"loss": 2.0926,
|
| 767 |
+
"step": 125
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 0.39,
|
| 771 |
+
"learning_rate": 0.00014365247045057734,
|
| 772 |
+
"loss": 2.094,
|
| 773 |
+
"step": 126
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.39,
|
| 777 |
+
"learning_rate": 0.0001427265042210381,
|
| 778 |
+
"loss": 2.0852,
|
| 779 |
+
"step": 127
|
| 780 |
+
},
|
| 781 |
+
{
|
| 782 |
+
"epoch": 0.4,
|
| 783 |
+
"learning_rate": 0.00014179603448867835,
|
| 784 |
+
"loss": 2.0501,
|
| 785 |
+
"step": 128
|
| 786 |
+
},
|
| 787 |
+
{
|
| 788 |
+
"epoch": 0.4,
|
| 789 |
+
"learning_rate": 0.00014086115932782314,
|
| 790 |
+
"loss": 2.1239,
|
| 791 |
+
"step": 129
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 0.4,
|
| 795 |
+
"learning_rate": 0.0001399219772771431,
|
| 796 |
+
"loss": 2.0143,
|
| 797 |
+
"step": 130
|
| 798 |
+
},
|
| 799 |
+
{
|
| 800 |
+
"epoch": 0.4,
|
| 801 |
+
"eval_loss": 1.9829031229019165,
|
| 802 |
+
"eval_runtime": 25.1483,
|
| 803 |
+
"eval_samples_per_second": 3.459,
|
| 804 |
+
"eval_steps_per_second": 0.437,
|
| 805 |
+
"step": 130
|
| 806 |
+
}
|
| 807 |
+
],
|
| 808 |
+
"logging_steps": 1,
|
| 809 |
+
"max_steps": 323,
|
| 810 |
+
"num_train_epochs": 1,
|
| 811 |
+
"save_steps": 65,
|
| 812 |
+
"total_flos": 7.631867476426752e+16,
|
| 813 |
+
"trial_name": null,
|
| 814 |
+
"trial_params": null
|
| 815 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2494663c7f0e92a4fb2f2e93a0f9ede601832248f8173403d06dc46cd2aa0dad
|
| 3 |
+
size 4536
|