Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/config-checkpoint.json +25 -0
- .ipynb_checkpoints/tokenizer-checkpoint.json +0 -0
- .ipynb_checkpoints/tokenizer_config-checkpoint.json +79 -0
- .ipynb_checkpoints/trainer_state-checkpoint.json +1864 -0
- added_tokens.json +6 -0
- config.json +25 -0
- generation_config.json +6 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +298 -0
- runs/Dec20_15-03-06_378092d8ce00/events.out.tfevents.1703084840.378092d8ce00.11515.0 +3 -0
- runs/Dec20_15-09-57_378092d8ce00/events.out.tfevents.1703085273.378092d8ce00.14090.0 +3 -0
- runs/Dec20_15-26-28_378092d8ce00/events.out.tfevents.1703086280.378092d8ce00.20180.0 +3 -0
- runs/Dec20_17-32-07_378092d8ce00/events.out.tfevents.1703093818.378092d8ce00.28304.0 +3 -0
- special_tokens_map.json +54 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer/added_tokens.json +6 -0
- tokenizer/special_tokens_map.json +54 -0
- tokenizer/tokenizer.json +0 -0
- tokenizer/tokenizer.model +3 -0
- tokenizer/tokenizer_config.json +79 -0
- tokenizer_config.json +79 -0
- trainer_state.json +1864 -0
- training_args.bin +3 -0
.ipynb_checkpoints/config-checkpoint.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 14336,
|
| 12 |
+
"max_position_embeddings": 32768,
|
| 13 |
+
"model_type": "mistral",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"num_key_value_heads": 8,
|
| 17 |
+
"rms_norm_eps": 1e-05,
|
| 18 |
+
"rope_theta": 10000.0,
|
| 19 |
+
"sliding_window": 8192,
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "bfloat16",
|
| 22 |
+
"transformers_version": "4.35.2",
|
| 23 |
+
"use_cache": false,
|
| 24 |
+
"vocab_size": 32004
|
| 25 |
+
}
|
.ipynb_checkpoints/tokenizer-checkpoint.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
.ipynb_checkpoints/tokenizer_config-checkpoint.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"32000": {
|
| 28 |
+
"content": "<|content|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<|recipient|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<|from|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<|stop|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"additional_special_tokens": [
|
| 61 |
+
"<|content|>",
|
| 62 |
+
"<|recipient|>",
|
| 63 |
+
"<|from|>",
|
| 64 |
+
"<|stop|>"
|
| 65 |
+
],
|
| 66 |
+
"bos_token": "<s>",
|
| 67 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' or message['role'] == 'system' %}\n{{ '<|from|>' + message['role'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% elif message['role'] == 'tool' %}\n{{ '<|from|>' + message['name'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% else %}\n{% set contain_content='no'%}\n{% if message['content'] is not none %}\n{{ '<|from|>assistant\n<|recipient|>all\n<|content|>' + message['content'] }}{% set contain_content='yes'%}\n{% endif %}\n{% if 'tool_calls' in message and message['tool_calls'] is not none %}\n{% for tool_call in message['tool_calls'] %}\n{% set prompt='<|from|>assistant\n<|recipient|>' + tool_call['function']['name'] + '\n<|content|>' + tool_call['function']['arguments'] %}\n{% if loop.index == 1 and contain_content == \"no\" %}\n{{ prompt }}{% else %}\n{{ '\n' + prompt}}{% endif %}\n{% endfor %}\n{% endif %}\n{{ '<|stop|>\n' }}{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}{{ '<|from|>assistant\n<|recipient|>' }}{% endif %}",
|
| 68 |
+
"clean_up_tokenization_spaces": false,
|
| 69 |
+
"eos_token": "</s>",
|
| 70 |
+
"legacy": true,
|
| 71 |
+
"model_max_length": 8192,
|
| 72 |
+
"pad_token": "</s>",
|
| 73 |
+
"padding_side": "left",
|
| 74 |
+
"sp_model_kwargs": {},
|
| 75 |
+
"spaces_between_special_tokens": false,
|
| 76 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 77 |
+
"unk_token": "<unk>",
|
| 78 |
+
"use_default_system_prompt": false
|
| 79 |
+
}
|
.ipynb_checkpoints/trainer_state-checkpoint.json
ADDED
|
@@ -0,0 +1,1864 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 75,
|
| 6 |
+
"global_step": 297,
|
| 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": 1e-06,
|
| 14 |
+
"loss": 0.9799,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 2e-06,
|
| 20 |
+
"loss": 1.0088,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 3e-06,
|
| 26 |
+
"loss": 1.0716,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 4e-06,
|
| 32 |
+
"loss": 0.8604,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 5e-06,
|
| 38 |
+
"loss": 0.8246,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 6e-06,
|
| 44 |
+
"loss": 0.8132,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 7e-06,
|
| 50 |
+
"loss": 0.6148,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 8e-06,
|
| 56 |
+
"loss": 0.7729,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 9e-06,
|
| 62 |
+
"loss": 0.7227,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 8.999732272500674e-06,
|
| 68 |
+
"loss": 0.8967,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.04,
|
| 73 |
+
"learning_rate": 8.998929121859591e-06,
|
| 74 |
+
"loss": 1.0003,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 8.997590643643646e-06,
|
| 80 |
+
"loss": 0.8262,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 8.99571699711836e-06,
|
| 86 |
+
"loss": 0.9495,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.05,
|
| 91 |
+
"learning_rate": 8.993308405228933e-06,
|
| 92 |
+
"loss": 0.8094,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 8.990365154573717e-06,
|
| 98 |
+
"loss": 0.8528,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 8.9868875953701e-06,
|
| 104 |
+
"loss": 0.8767,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.06,
|
| 109 |
+
"learning_rate": 8.982876141412855e-06,
|
| 110 |
+
"loss": 0.8405,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.06,
|
| 115 |
+
"learning_rate": 8.978331270024886e-06,
|
| 116 |
+
"loss": 0.9105,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.06,
|
| 121 |
+
"learning_rate": 8.973253522000438e-06,
|
| 122 |
+
"loss": 0.9109,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.07,
|
| 127 |
+
"learning_rate": 8.967643501540747e-06,
|
| 128 |
+
"loss": 0.8691,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07,
|
| 133 |
+
"learning_rate": 8.961501876182148e-06,
|
| 134 |
+
"loss": 0.7543,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 8.954829376716635e-06,
|
| 140 |
+
"loss": 0.7925,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.08,
|
| 145 |
+
"learning_rate": 8.947626797104924e-06,
|
| 146 |
+
"loss": 0.8162,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.08,
|
| 151 |
+
"learning_rate": 8.939894994381956e-06,
|
| 152 |
+
"loss": 0.7787,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.08,
|
| 157 |
+
"learning_rate": 8.931634888554937e-06,
|
| 158 |
+
"loss": 0.8244,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.09,
|
| 163 |
+
"learning_rate": 8.922847462493856e-06,
|
| 164 |
+
"loss": 0.8088,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.09,
|
| 169 |
+
"learning_rate": 8.913533761814537e-06,
|
| 170 |
+
"loss": 0.8405,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09,
|
| 175 |
+
"learning_rate": 8.903694894754222e-06,
|
| 176 |
+
"loss": 0.8361,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 8.8933320320397e-06,
|
| 182 |
+
"loss": 0.6428,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.1,
|
| 187 |
+
"learning_rate": 8.882446406748002e-06,
|
| 188 |
+
"loss": 0.6581,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.1,
|
| 193 |
+
"learning_rate": 8.871039314159675e-06,
|
| 194 |
+
"loss": 0.8059,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.11,
|
| 199 |
+
"learning_rate": 8.859112111604669e-06,
|
| 200 |
+
"loss": 0.8403,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.11,
|
| 205 |
+
"learning_rate": 8.846666218300807e-06,
|
| 206 |
+
"loss": 0.712,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.11,
|
| 211 |
+
"learning_rate": 8.833703115184932e-06,
|
| 212 |
+
"loss": 0.7188,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.12,
|
| 217 |
+
"learning_rate": 8.82022434473668e-06,
|
| 218 |
+
"loss": 0.7583,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 8.80623151079494e-06,
|
| 224 |
+
"loss": 0.7899,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.12,
|
| 229 |
+
"learning_rate": 8.791726278367021e-06,
|
| 230 |
+
"loss": 0.8039,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.13,
|
| 235 |
+
"learning_rate": 8.776710373430525e-06,
|
| 236 |
+
"loss": 0.8014,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.13,
|
| 241 |
+
"learning_rate": 8.761185582727977e-06,
|
| 242 |
+
"loss": 0.8441,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.13,
|
| 247 |
+
"learning_rate": 8.745153753554214e-06,
|
| 248 |
+
"loss": 0.6469,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.14,
|
| 253 |
+
"learning_rate": 8.728616793536588e-06,
|
| 254 |
+
"loss": 0.711,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.14,
|
| 259 |
+
"learning_rate": 8.711576670407966e-06,
|
| 260 |
+
"loss": 0.6167,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 8.694035411772595e-06,
|
| 266 |
+
"loss": 0.8141,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.15,
|
| 271 |
+
"learning_rate": 8.675995104864831e-06,
|
| 272 |
+
"loss": 0.5856,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.15,
|
| 277 |
+
"learning_rate": 8.65745789630079e-06,
|
| 278 |
+
"loss": 0.6113,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.15,
|
| 283 |
+
"learning_rate": 8.638425991822915e-06,
|
| 284 |
+
"loss": 0.8029,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.16,
|
| 289 |
+
"learning_rate": 8.618901656037513e-06,
|
| 290 |
+
"loss": 0.7917,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.16,
|
| 295 |
+
"learning_rate": 8.598887212145291e-06,
|
| 296 |
+
"loss": 0.6432,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16,
|
| 301 |
+
"learning_rate": 8.578385041664925e-06,
|
| 302 |
+
"loss": 0.6574,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 8.557397584149673e-06,
|
| 308 |
+
"loss": 0.5809,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.17,
|
| 313 |
+
"learning_rate": 8.535927336897097e-06,
|
| 314 |
+
"loss": 0.6016,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.18,
|
| 319 |
+
"learning_rate": 8.513976854651913e-06,
|
| 320 |
+
"loss": 0.6247,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.18,
|
| 325 |
+
"learning_rate": 8.491548749301997e-06,
|
| 326 |
+
"loss": 0.5538,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.18,
|
| 331 |
+
"learning_rate": 8.468645689567598e-06,
|
| 332 |
+
"loss": 0.6069,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.19,
|
| 337 |
+
"learning_rate": 8.445270400683786e-06,
|
| 338 |
+
"loss": 0.6994,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.19,
|
| 343 |
+
"learning_rate": 8.421425664076177e-06,
|
| 344 |
+
"loss": 0.5385,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19,
|
| 349 |
+
"learning_rate": 8.397114317029975e-06,
|
| 350 |
+
"loss": 0.7693,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.2,
|
| 355 |
+
"learning_rate": 8.372339252352355e-06,
|
| 356 |
+
"loss": 0.6196,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.2,
|
| 361 |
+
"learning_rate": 8.347103418028259e-06,
|
| 362 |
+
"loss": 0.7083,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.2,
|
| 367 |
+
"learning_rate": 8.321409816869605e-06,
|
| 368 |
+
"loss": 0.6298,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.21,
|
| 373 |
+
"learning_rate": 8.295261506157985e-06,
|
| 374 |
+
"loss": 0.5166,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.21,
|
| 379 |
+
"learning_rate": 8.268661597280886e-06,
|
| 380 |
+
"loss": 0.7171,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.21,
|
| 385 |
+
"learning_rate": 8.241613255361455e-06,
|
| 386 |
+
"loss": 0.7374,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 8.214119698881887e-06,
|
| 392 |
+
"loss": 0.5147,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.22,
|
| 397 |
+
"learning_rate": 8.186184199300463e-06,
|
| 398 |
+
"loss": 0.7629,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.22,
|
| 403 |
+
"learning_rate": 8.157810080662269e-06,
|
| 404 |
+
"loss": 0.6447,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.23,
|
| 409 |
+
"learning_rate": 8.129000719203673e-06,
|
| 410 |
+
"loss": 0.5669,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.23,
|
| 415 |
+
"learning_rate": 8.099759542950583e-06,
|
| 416 |
+
"loss": 0.6644,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.23,
|
| 421 |
+
"learning_rate": 8.070090031310558e-06,
|
| 422 |
+
"loss": 0.637,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.24,
|
| 427 |
+
"learning_rate": 8.039995714658776e-06,
|
| 428 |
+
"loss": 0.6364,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 8.009480173917969e-06,
|
| 434 |
+
"loss": 0.6313,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.24,
|
| 439 |
+
"learning_rate": 7.978547040132316e-06,
|
| 440 |
+
"loss": 0.6522,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.25,
|
| 445 |
+
"learning_rate": 7.947199994035401e-06,
|
| 446 |
+
"loss": 0.6039,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.25,
|
| 451 |
+
"learning_rate": 7.915442765612229e-06,
|
| 452 |
+
"loss": 0.5923,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.25,
|
| 457 |
+
"learning_rate": 7.883279133655398e-06,
|
| 458 |
+
"loss": 0.5145,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.25,
|
| 463 |
+
"eval_accuracy": 0.8153410115496591,
|
| 464 |
+
"eval_accuracy_<|content|>": 0.9983489268024216,
|
| 465 |
+
"eval_accuracy_<|from|>": 0.975,
|
| 466 |
+
"eval_accuracy_<|recipient|>": 0.7946428571428571,
|
| 467 |
+
"eval_accuracy_<|stop|>": 0.8509316770186336,
|
| 468 |
+
"eval_accuracy_total_num_<|content|>": 3634,
|
| 469 |
+
"eval_accuracy_total_num_<|from|>": 560,
|
| 470 |
+
"eval_accuracy_total_num_<|recipient|>": 560,
|
| 471 |
+
"eval_accuracy_total_num_<|stop|>": 3059,
|
| 472 |
+
"eval_loss": 0.6158567070960999,
|
| 473 |
+
"eval_perplexity": 1.0609388823519776,
|
| 474 |
+
"eval_runtime": 222.2983,
|
| 475 |
+
"eval_samples_per_second": 4.705,
|
| 476 |
+
"eval_steps_per_second": 0.148,
|
| 477 |
+
"step": 75
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.26,
|
| 481 |
+
"learning_rate": 7.850712925315468e-06,
|
| 482 |
+
"loss": 0.7307,
|
| 483 |
+
"step": 76
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.26,
|
| 487 |
+
"learning_rate": 7.817748015645558e-06,
|
| 488 |
+
"loss": 0.6347,
|
| 489 |
+
"step": 77
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.26,
|
| 493 |
+
"learning_rate": 7.78438832714026e-06,
|
| 494 |
+
"loss": 0.5611,
|
| 495 |
+
"step": 78
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.27,
|
| 499 |
+
"learning_rate": 7.7506378292689e-06,
|
| 500 |
+
"loss": 0.5914,
|
| 501 |
+
"step": 79
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.27,
|
| 505 |
+
"learning_rate": 7.716500538003208e-06,
|
| 506 |
+
"loss": 0.4936,
|
| 507 |
+
"step": 80
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.27,
|
| 511 |
+
"learning_rate": 7.681980515339464e-06,
|
| 512 |
+
"loss": 0.543,
|
| 513 |
+
"step": 81
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.28,
|
| 517 |
+
"learning_rate": 7.647081868815153e-06,
|
| 518 |
+
"loss": 0.5267,
|
| 519 |
+
"step": 82
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.28,
|
| 523 |
+
"learning_rate": 7.611808751020213e-06,
|
| 524 |
+
"loss": 0.6759,
|
| 525 |
+
"step": 83
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.28,
|
| 529 |
+
"learning_rate": 7.57616535910292e-06,
|
| 530 |
+
"loss": 0.5291,
|
| 531 |
+
"step": 84
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.29,
|
| 535 |
+
"learning_rate": 7.540155934270472e-06,
|
| 536 |
+
"loss": 0.7263,
|
| 537 |
+
"step": 85
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.29,
|
| 541 |
+
"learning_rate": 7.5037847612843135e-06,
|
| 542 |
+
"loss": 0.6477,
|
| 543 |
+
"step": 86
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.29,
|
| 547 |
+
"learning_rate": 7.46705616795031e-06,
|
| 548 |
+
"loss": 0.6295,
|
| 549 |
+
"step": 87
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3,
|
| 553 |
+
"learning_rate": 7.429974524603771e-06,
|
| 554 |
+
"loss": 0.5567,
|
| 555 |
+
"step": 88
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3,
|
| 559 |
+
"learning_rate": 7.392544243589427e-06,
|
| 560 |
+
"loss": 0.5361,
|
| 561 |
+
"step": 89
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.3,
|
| 565 |
+
"learning_rate": 7.354769778736405e-06,
|
| 566 |
+
"loss": 0.752,
|
| 567 |
+
"step": 90
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.31,
|
| 571 |
+
"learning_rate": 7.316655624828267e-06,
|
| 572 |
+
"loss": 0.581,
|
| 573 |
+
"step": 91
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.31,
|
| 577 |
+
"learning_rate": 7.278206317068173e-06,
|
| 578 |
+
"loss": 0.5523,
|
| 579 |
+
"step": 92
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.31,
|
| 583 |
+
"learning_rate": 7.239426430539243e-06,
|
| 584 |
+
"loss": 0.6416,
|
| 585 |
+
"step": 93
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.32,
|
| 589 |
+
"learning_rate": 7.2003205796601645e-06,
|
| 590 |
+
"loss": 0.6665,
|
| 591 |
+
"step": 94
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.32,
|
| 595 |
+
"learning_rate": 7.160893417636121e-06,
|
| 596 |
+
"loss": 0.7361,
|
| 597 |
+
"step": 95
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.32,
|
| 601 |
+
"learning_rate": 7.121149635905111e-06,
|
| 602 |
+
"loss": 0.507,
|
| 603 |
+
"step": 96
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.33,
|
| 607 |
+
"learning_rate": 7.081093963579708e-06,
|
| 608 |
+
"loss": 0.6335,
|
| 609 |
+
"step": 97
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.33,
|
| 613 |
+
"learning_rate": 7.040731166884352e-06,
|
| 614 |
+
"loss": 0.545,
|
| 615 |
+
"step": 98
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.33,
|
| 619 |
+
"learning_rate": 7.00006604858821e-06,
|
| 620 |
+
"loss": 0.7382,
|
| 621 |
+
"step": 99
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.34,
|
| 625 |
+
"learning_rate": 6.959103447433696e-06,
|
| 626 |
+
"loss": 0.7749,
|
| 627 |
+
"step": 100
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.34,
|
| 631 |
+
"learning_rate": 6.917848237560708e-06,
|
| 632 |
+
"loss": 0.5616,
|
| 633 |
+
"step": 101
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.34,
|
| 637 |
+
"learning_rate": 6.876305327926656e-06,
|
| 638 |
+
"loss": 0.6483,
|
| 639 |
+
"step": 102
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.35,
|
| 643 |
+
"learning_rate": 6.834479661722347e-06,
|
| 644 |
+
"loss": 0.7207,
|
| 645 |
+
"step": 103
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.35,
|
| 649 |
+
"learning_rate": 6.792376215783789e-06,
|
| 650 |
+
"loss": 0.5815,
|
| 651 |
+
"step": 104
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.35,
|
| 655 |
+
"learning_rate": 6.75e-06,
|
| 656 |
+
"loss": 0.4725,
|
| 657 |
+
"step": 105
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.36,
|
| 661 |
+
"learning_rate": 6.707356056716886e-06,
|
| 662 |
+
"loss": 0.7133,
|
| 663 |
+
"step": 106
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.36,
|
| 667 |
+
"learning_rate": 6.664449460137245e-06,
|
| 668 |
+
"loss": 0.5666,
|
| 669 |
+
"step": 107
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.36,
|
| 673 |
+
"learning_rate": 6.621285315716991e-06,
|
| 674 |
+
"loss": 0.545,
|
| 675 |
+
"step": 108
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.37,
|
| 679 |
+
"learning_rate": 6.5778687595576535e-06,
|
| 680 |
+
"loss": 0.7437,
|
| 681 |
+
"step": 109
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.37,
|
| 685 |
+
"learning_rate": 6.5342049577952396e-06,
|
| 686 |
+
"loss": 0.5496,
|
| 687 |
+
"step": 110
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.37,
|
| 691 |
+
"learning_rate": 6.490299105985506e-06,
|
| 692 |
+
"loss": 0.5883,
|
| 693 |
+
"step": 111
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.38,
|
| 697 |
+
"learning_rate": 6.446156428485748e-06,
|
| 698 |
+
"loss": 0.5355,
|
| 699 |
+
"step": 112
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.38,
|
| 703 |
+
"learning_rate": 6.401782177833148e-06,
|
| 704 |
+
"loss": 0.6925,
|
| 705 |
+
"step": 113
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.38,
|
| 709 |
+
"learning_rate": 6.357181634119776e-06,
|
| 710 |
+
"loss": 0.7328,
|
| 711 |
+
"step": 114
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.39,
|
| 715 |
+
"learning_rate": 6.312360104364318e-06,
|
| 716 |
+
"loss": 0.6417,
|
| 717 |
+
"step": 115
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.39,
|
| 721 |
+
"learning_rate": 6.267322921880584e-06,
|
| 722 |
+
"loss": 0.6352,
|
| 723 |
+
"step": 116
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.39,
|
| 727 |
+
"learning_rate": 6.222075445642905e-06,
|
| 728 |
+
"loss": 0.6245,
|
| 729 |
+
"step": 117
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.4,
|
| 733 |
+
"learning_rate": 6.176623059648463e-06,
|
| 734 |
+
"loss": 0.572,
|
| 735 |
+
"step": 118
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.4,
|
| 739 |
+
"learning_rate": 6.130971172276657e-06,
|
| 740 |
+
"loss": 0.5957,
|
| 741 |
+
"step": 119
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.4,
|
| 745 |
+
"learning_rate": 6.085125215645551e-06,
|
| 746 |
+
"loss": 0.5968,
|
| 747 |
+
"step": 120
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.41,
|
| 751 |
+
"learning_rate": 6.03909064496551e-06,
|
| 752 |
+
"loss": 0.7397,
|
| 753 |
+
"step": 121
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.41,
|
| 757 |
+
"learning_rate": 5.992872937890085e-06,
|
| 758 |
+
"loss": 0.4958,
|
| 759 |
+
"step": 122
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.41,
|
| 763 |
+
"learning_rate": 5.946477593864227e-06,
|
| 764 |
+
"loss": 0.6392,
|
| 765 |
+
"step": 123
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.42,
|
| 769 |
+
"learning_rate": 5.899910133469909e-06,
|
| 770 |
+
"loss": 0.5666,
|
| 771 |
+
"step": 124
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.42,
|
| 775 |
+
"learning_rate": 5.853176097769229e-06,
|
| 776 |
+
"loss": 0.4596,
|
| 777 |
+
"step": 125
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.42,
|
| 781 |
+
"learning_rate": 5.80628104764508e-06,
|
| 782 |
+
"loss": 0.6385,
|
| 783 |
+
"step": 126
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.43,
|
| 787 |
+
"learning_rate": 5.7592305631394655e-06,
|
| 788 |
+
"loss": 0.578,
|
| 789 |
+
"step": 127
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.43,
|
| 793 |
+
"learning_rate": 5.7120302427895185e-06,
|
| 794 |
+
"loss": 0.8049,
|
| 795 |
+
"step": 128
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.43,
|
| 799 |
+
"learning_rate": 5.664685702961344e-06,
|
| 800 |
+
"loss": 0.4874,
|
| 801 |
+
"step": 129
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.44,
|
| 805 |
+
"learning_rate": 5.617202577181723e-06,
|
| 806 |
+
"loss": 0.5195,
|
| 807 |
+
"step": 130
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.44,
|
| 811 |
+
"learning_rate": 5.569586515467779e-06,
|
| 812 |
+
"loss": 0.6092,
|
| 813 |
+
"step": 131
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.44,
|
| 817 |
+
"learning_rate": 5.521843183654679e-06,
|
| 818 |
+
"loss": 0.6794,
|
| 819 |
+
"step": 132
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.45,
|
| 823 |
+
"learning_rate": 5.473978262721463e-06,
|
| 824 |
+
"loss": 0.4674,
|
| 825 |
+
"step": 133
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.45,
|
| 829 |
+
"learning_rate": 5.425997448115057e-06,
|
| 830 |
+
"loss": 0.5482,
|
| 831 |
+
"step": 134
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.45,
|
| 835 |
+
"learning_rate": 5.377906449072578e-06,
|
| 836 |
+
"loss": 0.4731,
|
| 837 |
+
"step": 135
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.46,
|
| 841 |
+
"learning_rate": 5.3297109879419855e-06,
|
| 842 |
+
"loss": 0.6931,
|
| 843 |
+
"step": 136
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.46,
|
| 847 |
+
"learning_rate": 5.281416799501187e-06,
|
| 848 |
+
"loss": 0.5254,
|
| 849 |
+
"step": 137
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.46,
|
| 853 |
+
"learning_rate": 5.23302963027565e-06,
|
| 854 |
+
"loss": 0.5313,
|
| 855 |
+
"step": 138
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.47,
|
| 859 |
+
"learning_rate": 5.184555237854625e-06,
|
| 860 |
+
"loss": 0.5622,
|
| 861 |
+
"step": 139
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.47,
|
| 865 |
+
"learning_rate": 5.1359993902060545e-06,
|
| 866 |
+
"loss": 0.5621,
|
| 867 |
+
"step": 140
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.47,
|
| 871 |
+
"learning_rate": 5.087367864990233e-06,
|
| 872 |
+
"loss": 0.5534,
|
| 873 |
+
"step": 141
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.48,
|
| 877 |
+
"learning_rate": 5.038666448872331e-06,
|
| 878 |
+
"loss": 0.5932,
|
| 879 |
+
"step": 142
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.48,
|
| 883 |
+
"learning_rate": 4.989900936833841e-06,
|
| 884 |
+
"loss": 0.5931,
|
| 885 |
+
"step": 143
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48,
|
| 889 |
+
"learning_rate": 4.941077131483024e-06,
|
| 890 |
+
"loss": 0.5631,
|
| 891 |
+
"step": 144
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.49,
|
| 895 |
+
"learning_rate": 4.892200842364463e-06,
|
| 896 |
+
"loss": 0.6102,
|
| 897 |
+
"step": 145
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.49,
|
| 901 |
+
"learning_rate": 4.843277885267786e-06,
|
| 902 |
+
"loss": 0.6519,
|
| 903 |
+
"step": 146
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.49,
|
| 907 |
+
"learning_rate": 4.794314081535644e-06,
|
| 908 |
+
"loss": 0.4957,
|
| 909 |
+
"step": 147
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.5,
|
| 913 |
+
"learning_rate": 4.745315257371029e-06,
|
| 914 |
+
"loss": 0.6076,
|
| 915 |
+
"step": 148
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.5,
|
| 919 |
+
"learning_rate": 4.696287243144012e-06,
|
| 920 |
+
"loss": 0.6205,
|
| 921 |
+
"step": 149
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.51,
|
| 925 |
+
"learning_rate": 4.647235872697993e-06,
|
| 926 |
+
"loss": 0.5454,
|
| 927 |
+
"step": 150
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.51,
|
| 931 |
+
"eval_accuracy": 0.8247416654541203,
|
| 932 |
+
"eval_accuracy_<|content|>": 1.0,
|
| 933 |
+
"eval_accuracy_<|from|>": 0.9892857142857143,
|
| 934 |
+
"eval_accuracy_<|recipient|>": 1.0,
|
| 935 |
+
"eval_accuracy_<|stop|>": 0.8996404053612291,
|
| 936 |
+
"eval_accuracy_total_num_<|content|>": 3634,
|
| 937 |
+
"eval_accuracy_total_num_<|from|>": 560,
|
| 938 |
+
"eval_accuracy_total_num_<|recipient|>": 560,
|
| 939 |
+
"eval_accuracy_total_num_<|stop|>": 3059,
|
| 940 |
+
"eval_loss": 0.5723979473114014,
|
| 941 |
+
"eval_perplexity": 1.056601002074663,
|
| 942 |
+
"eval_runtime": 170.3858,
|
| 943 |
+
"eval_samples_per_second": 6.139,
|
| 944 |
+
"eval_steps_per_second": 0.194,
|
| 945 |
+
"step": 150
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.51,
|
| 949 |
+
"learning_rate": 4.598166982655526e-06,
|
| 950 |
+
"loss": 0.6884,
|
| 951 |
+
"step": 151
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.51,
|
| 955 |
+
"learning_rate": 4.549086411723821e-06,
|
| 956 |
+
"loss": 0.5796,
|
| 957 |
+
"step": 152
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.52,
|
| 961 |
+
"learning_rate": 4.5e-06,
|
| 962 |
+
"loss": 0.5955,
|
| 963 |
+
"step": 153
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.52,
|
| 967 |
+
"learning_rate": 4.45091358827618e-06,
|
| 968 |
+
"loss": 0.5985,
|
| 969 |
+
"step": 154
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.52,
|
| 973 |
+
"learning_rate": 4.401833017344475e-06,
|
| 974 |
+
"loss": 0.451,
|
| 975 |
+
"step": 155
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.53,
|
| 979 |
+
"learning_rate": 4.352764127302008e-06,
|
| 980 |
+
"loss": 0.7329,
|
| 981 |
+
"step": 156
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.53,
|
| 985 |
+
"learning_rate": 4.303712756855989e-06,
|
| 986 |
+
"loss": 0.6437,
|
| 987 |
+
"step": 157
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.53,
|
| 991 |
+
"learning_rate": 4.254684742628971e-06,
|
| 992 |
+
"loss": 0.4884,
|
| 993 |
+
"step": 158
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.54,
|
| 997 |
+
"learning_rate": 4.205685918464356e-06,
|
| 998 |
+
"loss": 0.5665,
|
| 999 |
+
"step": 159
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.54,
|
| 1003 |
+
"learning_rate": 4.156722114732214e-06,
|
| 1004 |
+
"loss": 0.5799,
|
| 1005 |
+
"step": 160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.54,
|
| 1009 |
+
"learning_rate": 4.107799157635538e-06,
|
| 1010 |
+
"loss": 0.6255,
|
| 1011 |
+
"step": 161
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.55,
|
| 1015 |
+
"learning_rate": 4.058922868516977e-06,
|
| 1016 |
+
"loss": 0.6124,
|
| 1017 |
+
"step": 162
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.55,
|
| 1021 |
+
"learning_rate": 4.01009906316616e-06,
|
| 1022 |
+
"loss": 0.5434,
|
| 1023 |
+
"step": 163
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.55,
|
| 1027 |
+
"learning_rate": 3.96133355112767e-06,
|
| 1028 |
+
"loss": 0.565,
|
| 1029 |
+
"step": 164
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.56,
|
| 1033 |
+
"learning_rate": 3.912632135009769e-06,
|
| 1034 |
+
"loss": 0.4637,
|
| 1035 |
+
"step": 165
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.56,
|
| 1039 |
+
"learning_rate": 3.8640006097939474e-06,
|
| 1040 |
+
"loss": 0.5655,
|
| 1041 |
+
"step": 166
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.56,
|
| 1045 |
+
"learning_rate": 3.815444762145375e-06,
|
| 1046 |
+
"loss": 0.6105,
|
| 1047 |
+
"step": 167
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.57,
|
| 1051 |
+
"learning_rate": 3.7669703697243513e-06,
|
| 1052 |
+
"loss": 0.5689,
|
| 1053 |
+
"step": 168
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.57,
|
| 1057 |
+
"learning_rate": 3.718583200498814e-06,
|
| 1058 |
+
"loss": 0.6725,
|
| 1059 |
+
"step": 169
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.57,
|
| 1063 |
+
"learning_rate": 3.6702890120580148e-06,
|
| 1064 |
+
"loss": 0.4064,
|
| 1065 |
+
"step": 170
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.58,
|
| 1069 |
+
"learning_rate": 3.6220935509274233e-06,
|
| 1070 |
+
"loss": 0.4969,
|
| 1071 |
+
"step": 171
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.58,
|
| 1075 |
+
"learning_rate": 3.5740025518849432e-06,
|
| 1076 |
+
"loss": 0.5846,
|
| 1077 |
+
"step": 172
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.58,
|
| 1081 |
+
"learning_rate": 3.5260217372785372e-06,
|
| 1082 |
+
"loss": 0.5228,
|
| 1083 |
+
"step": 173
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.59,
|
| 1087 |
+
"learning_rate": 3.478156816345321e-06,
|
| 1088 |
+
"loss": 0.603,
|
| 1089 |
+
"step": 174
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.59,
|
| 1093 |
+
"learning_rate": 3.4304134845322217e-06,
|
| 1094 |
+
"loss": 0.6142,
|
| 1095 |
+
"step": 175
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.59,
|
| 1099 |
+
"learning_rate": 3.3827974228182764e-06,
|
| 1100 |
+
"loss": 0.5525,
|
| 1101 |
+
"step": 176
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.6,
|
| 1105 |
+
"learning_rate": 3.335314297038656e-06,
|
| 1106 |
+
"loss": 0.637,
|
| 1107 |
+
"step": 177
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.6,
|
| 1111 |
+
"learning_rate": 3.287969757210483e-06,
|
| 1112 |
+
"loss": 0.4829,
|
| 1113 |
+
"step": 178
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.6,
|
| 1117 |
+
"learning_rate": 3.240769436860536e-06,
|
| 1118 |
+
"loss": 0.7065,
|
| 1119 |
+
"step": 179
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.61,
|
| 1123 |
+
"learning_rate": 3.1937189523549205e-06,
|
| 1124 |
+
"loss": 0.4831,
|
| 1125 |
+
"step": 180
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.61,
|
| 1129 |
+
"learning_rate": 3.1468239022307714e-06,
|
| 1130 |
+
"loss": 0.535,
|
| 1131 |
+
"step": 181
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.61,
|
| 1135 |
+
"learning_rate": 3.1000898665300915e-06,
|
| 1136 |
+
"loss": 0.5843,
|
| 1137 |
+
"step": 182
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.62,
|
| 1141 |
+
"learning_rate": 3.053522406135774e-06,
|
| 1142 |
+
"loss": 0.5178,
|
| 1143 |
+
"step": 183
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.62,
|
| 1147 |
+
"learning_rate": 3.007127062109917e-06,
|
| 1148 |
+
"loss": 0.5917,
|
| 1149 |
+
"step": 184
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.62,
|
| 1153 |
+
"learning_rate": 2.9609093550344912e-06,
|
| 1154 |
+
"loss": 0.5379,
|
| 1155 |
+
"step": 185
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.63,
|
| 1159 |
+
"learning_rate": 2.9148747843544492e-06,
|
| 1160 |
+
"loss": 0.6937,
|
| 1161 |
+
"step": 186
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.63,
|
| 1165 |
+
"learning_rate": 2.869028827723343e-06,
|
| 1166 |
+
"loss": 0.4999,
|
| 1167 |
+
"step": 187
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.63,
|
| 1171 |
+
"learning_rate": 2.823376940351537e-06,
|
| 1172 |
+
"loss": 0.6532,
|
| 1173 |
+
"step": 188
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.64,
|
| 1177 |
+
"learning_rate": 2.7779245543570964e-06,
|
| 1178 |
+
"loss": 0.4854,
|
| 1179 |
+
"step": 189
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.64,
|
| 1183 |
+
"learning_rate": 2.7326770781194174e-06,
|
| 1184 |
+
"loss": 0.54,
|
| 1185 |
+
"step": 190
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.64,
|
| 1189 |
+
"learning_rate": 2.6876398956356833e-06,
|
| 1190 |
+
"loss": 0.4441,
|
| 1191 |
+
"step": 191
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.65,
|
| 1195 |
+
"learning_rate": 2.642818365880224e-06,
|
| 1196 |
+
"loss": 0.551,
|
| 1197 |
+
"step": 192
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.65,
|
| 1201 |
+
"learning_rate": 2.5982178221668532e-06,
|
| 1202 |
+
"loss": 0.6079,
|
| 1203 |
+
"step": 193
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.65,
|
| 1207 |
+
"learning_rate": 2.5538435715142517e-06,
|
| 1208 |
+
"loss": 0.5439,
|
| 1209 |
+
"step": 194
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.66,
|
| 1213 |
+
"learning_rate": 2.5097008940144952e-06,
|
| 1214 |
+
"loss": 0.6502,
|
| 1215 |
+
"step": 195
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.66,
|
| 1219 |
+
"learning_rate": 2.4657950422047615e-06,
|
| 1220 |
+
"loss": 0.5396,
|
| 1221 |
+
"step": 196
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.66,
|
| 1225 |
+
"learning_rate": 2.4221312404423484e-06,
|
| 1226 |
+
"loss": 0.6481,
|
| 1227 |
+
"step": 197
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.67,
|
| 1231 |
+
"learning_rate": 2.3787146842830103e-06,
|
| 1232 |
+
"loss": 0.5903,
|
| 1233 |
+
"step": 198
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.67,
|
| 1237 |
+
"learning_rate": 2.3355505398627564e-06,
|
| 1238 |
+
"loss": 0.5244,
|
| 1239 |
+
"step": 199
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.67,
|
| 1243 |
+
"learning_rate": 2.292643943283114e-06,
|
| 1244 |
+
"loss": 0.6796,
|
| 1245 |
+
"step": 200
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.68,
|
| 1249 |
+
"learning_rate": 2.250000000000001e-06,
|
| 1250 |
+
"loss": 0.6146,
|
| 1251 |
+
"step": 201
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.68,
|
| 1255 |
+
"learning_rate": 2.207623784216212e-06,
|
| 1256 |
+
"loss": 0.5408,
|
| 1257 |
+
"step": 202
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.68,
|
| 1261 |
+
"learning_rate": 2.1655203382776525e-06,
|
| 1262 |
+
"loss": 0.6249,
|
| 1263 |
+
"step": 203
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.69,
|
| 1267 |
+
"learning_rate": 2.123694672073344e-06,
|
| 1268 |
+
"loss": 0.5816,
|
| 1269 |
+
"step": 204
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.69,
|
| 1273 |
+
"learning_rate": 2.082151762439292e-06,
|
| 1274 |
+
"loss": 0.4743,
|
| 1275 |
+
"step": 205
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.69,
|
| 1279 |
+
"learning_rate": 2.040896552566305e-06,
|
| 1280 |
+
"loss": 0.6727,
|
| 1281 |
+
"step": 206
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.7,
|
| 1285 |
+
"learning_rate": 1.999933951411791e-06,
|
| 1286 |
+
"loss": 0.4752,
|
| 1287 |
+
"step": 207
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.7,
|
| 1291 |
+
"learning_rate": 1.9592688331156483e-06,
|
| 1292 |
+
"loss": 0.5629,
|
| 1293 |
+
"step": 208
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.7,
|
| 1297 |
+
"learning_rate": 1.9189060364202938e-06,
|
| 1298 |
+
"loss": 0.4636,
|
| 1299 |
+
"step": 209
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.71,
|
| 1303 |
+
"learning_rate": 1.8788503640948908e-06,
|
| 1304 |
+
"loss": 0.5113,
|
| 1305 |
+
"step": 210
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.71,
|
| 1309 |
+
"learning_rate": 1.8391065823638805e-06,
|
| 1310 |
+
"loss": 0.4424,
|
| 1311 |
+
"step": 211
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.71,
|
| 1315 |
+
"learning_rate": 1.7996794203398362e-06,
|
| 1316 |
+
"loss": 0.4023,
|
| 1317 |
+
"step": 212
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.72,
|
| 1321 |
+
"learning_rate": 1.760573569460757e-06,
|
| 1322 |
+
"loss": 0.5816,
|
| 1323 |
+
"step": 213
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.72,
|
| 1327 |
+
"learning_rate": 1.7217936829318283e-06,
|
| 1328 |
+
"loss": 0.5428,
|
| 1329 |
+
"step": 214
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.72,
|
| 1333 |
+
"learning_rate": 1.6833443751717342e-06,
|
| 1334 |
+
"loss": 0.4079,
|
| 1335 |
+
"step": 215
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.73,
|
| 1339 |
+
"learning_rate": 1.6452302212635958e-06,
|
| 1340 |
+
"loss": 0.614,
|
| 1341 |
+
"step": 216
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.73,
|
| 1345 |
+
"learning_rate": 1.6074557564105728e-06,
|
| 1346 |
+
"loss": 0.3744,
|
| 1347 |
+
"step": 217
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.73,
|
| 1351 |
+
"learning_rate": 1.5700254753962297e-06,
|
| 1352 |
+
"loss": 0.7146,
|
| 1353 |
+
"step": 218
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.74,
|
| 1357 |
+
"learning_rate": 1.5329438320496903e-06,
|
| 1358 |
+
"loss": 0.4597,
|
| 1359 |
+
"step": 219
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.74,
|
| 1363 |
+
"learning_rate": 1.4962152387156875e-06,
|
| 1364 |
+
"loss": 0.5789,
|
| 1365 |
+
"step": 220
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.74,
|
| 1369 |
+
"learning_rate": 1.459844065729529e-06,
|
| 1370 |
+
"loss": 0.5392,
|
| 1371 |
+
"step": 221
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.75,
|
| 1375 |
+
"learning_rate": 1.423834640897079e-06,
|
| 1376 |
+
"loss": 0.6789,
|
| 1377 |
+
"step": 222
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.75,
|
| 1381 |
+
"learning_rate": 1.3881912489797881e-06,
|
| 1382 |
+
"loss": 0.6218,
|
| 1383 |
+
"step": 223
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.75,
|
| 1387 |
+
"learning_rate": 1.3529181311848478e-06,
|
| 1388 |
+
"loss": 0.5378,
|
| 1389 |
+
"step": 224
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.76,
|
| 1393 |
+
"learning_rate": 1.3180194846605365e-06,
|
| 1394 |
+
"loss": 0.4189,
|
| 1395 |
+
"step": 225
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.76,
|
| 1399 |
+
"eval_accuracy": 0.8321450379495904,
|
| 1400 |
+
"eval_accuracy_<|content|>": 1.0,
|
| 1401 |
+
"eval_accuracy_<|from|>": 0.9946428571428572,
|
| 1402 |
+
"eval_accuracy_<|recipient|>": 1.0,
|
| 1403 |
+
"eval_accuracy_<|stop|>": 0.9150049035632559,
|
| 1404 |
+
"eval_accuracy_total_num_<|content|>": 3634,
|
| 1405 |
+
"eval_accuracy_total_num_<|from|>": 560,
|
| 1406 |
+
"eval_accuracy_total_num_<|recipient|>": 560,
|
| 1407 |
+
"eval_accuracy_total_num_<|stop|>": 3059,
|
| 1408 |
+
"eval_loss": 0.5402337908744812,
|
| 1409 |
+
"eval_perplexity": 1.0533657385611068,
|
| 1410 |
+
"eval_runtime": 170.1194,
|
| 1411 |
+
"eval_samples_per_second": 6.149,
|
| 1412 |
+
"eval_steps_per_second": 0.194,
|
| 1413 |
+
"step": 225
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.76,
|
| 1417 |
+
"learning_rate": 1.2834994619967923e-06,
|
| 1418 |
+
"loss": 0.4984,
|
| 1419 |
+
"step": 226
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.76,
|
| 1423 |
+
"learning_rate": 1.2493621707311002e-06,
|
| 1424 |
+
"loss": 0.4659,
|
| 1425 |
+
"step": 227
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.77,
|
| 1429 |
+
"learning_rate": 1.2156116728597408e-06,
|
| 1430 |
+
"loss": 0.5902,
|
| 1431 |
+
"step": 228
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.77,
|
| 1435 |
+
"learning_rate": 1.1822519843544422e-06,
|
| 1436 |
+
"loss": 0.6117,
|
| 1437 |
+
"step": 229
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.77,
|
| 1441 |
+
"learning_rate": 1.1492870746845319e-06,
|
| 1442 |
+
"loss": 0.6365,
|
| 1443 |
+
"step": 230
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.78,
|
| 1447 |
+
"learning_rate": 1.1167208663446024e-06,
|
| 1448 |
+
"loss": 0.5319,
|
| 1449 |
+
"step": 231
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.78,
|
| 1453 |
+
"learning_rate": 1.0845572343877717e-06,
|
| 1454 |
+
"loss": 0.5895,
|
| 1455 |
+
"step": 232
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.78,
|
| 1459 |
+
"learning_rate": 1.0528000059645994e-06,
|
| 1460 |
+
"loss": 0.5318,
|
| 1461 |
+
"step": 233
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.79,
|
| 1465 |
+
"learning_rate": 1.0214529598676836e-06,
|
| 1466 |
+
"loss": 0.6035,
|
| 1467 |
+
"step": 234
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.79,
|
| 1471 |
+
"learning_rate": 9.905198260820328e-07,
|
| 1472 |
+
"loss": 0.5598,
|
| 1473 |
+
"step": 235
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.79,
|
| 1477 |
+
"learning_rate": 9.600042853412235e-07,
|
| 1478 |
+
"loss": 0.5064,
|
| 1479 |
+
"step": 236
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.8,
|
| 1483 |
+
"learning_rate": 9.299099686894423e-07,
|
| 1484 |
+
"loss": 0.6721,
|
| 1485 |
+
"step": 237
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.8,
|
| 1489 |
+
"learning_rate": 9.002404570494167e-07,
|
| 1490 |
+
"loss": 0.5706,
|
| 1491 |
+
"step": 238
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.8,
|
| 1495 |
+
"learning_rate": 8.709992807963281e-07,
|
| 1496 |
+
"loss": 0.6527,
|
| 1497 |
+
"step": 239
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.81,
|
| 1501 |
+
"learning_rate": 8.42189919337732e-07,
|
| 1502 |
+
"loss": 0.6001,
|
| 1503 |
+
"step": 240
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.81,
|
| 1507 |
+
"learning_rate": 8.138158006995364e-07,
|
| 1508 |
+
"loss": 0.6725,
|
| 1509 |
+
"step": 241
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.81,
|
| 1513 |
+
"learning_rate": 7.85880301118113e-07,
|
| 1514 |
+
"loss": 0.4701,
|
| 1515 |
+
"step": 242
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.82,
|
| 1519 |
+
"learning_rate": 7.58386744638546e-07,
|
| 1520 |
+
"loss": 0.5473,
|
| 1521 |
+
"step": 243
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.82,
|
| 1525 |
+
"learning_rate": 7.313384027191149e-07,
|
| 1526 |
+
"loss": 0.5739,
|
| 1527 |
+
"step": 244
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.82,
|
| 1531 |
+
"learning_rate": 7.047384938420153e-07,
|
| 1532 |
+
"loss": 0.367,
|
| 1533 |
+
"step": 245
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.83,
|
| 1537 |
+
"learning_rate": 6.785901831303956e-07,
|
| 1538 |
+
"loss": 0.4433,
|
| 1539 |
+
"step": 246
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.83,
|
| 1543 |
+
"learning_rate": 6.528965819717413e-07,
|
| 1544 |
+
"loss": 0.4839,
|
| 1545 |
+
"step": 247
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.84,
|
| 1549 |
+
"learning_rate": 6.27660747647645e-07,
|
| 1550 |
+
"loss": 0.6045,
|
| 1551 |
+
"step": 248
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.84,
|
| 1555 |
+
"learning_rate": 6.028856829700259e-07,
|
| 1556 |
+
"loss": 0.565,
|
| 1557 |
+
"step": 249
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.84,
|
| 1561 |
+
"learning_rate": 5.785743359238243e-07,
|
| 1562 |
+
"loss": 0.5618,
|
| 1563 |
+
"step": 250
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.85,
|
| 1567 |
+
"learning_rate": 5.547295993162155e-07,
|
| 1568 |
+
"loss": 0.397,
|
| 1569 |
+
"step": 251
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.85,
|
| 1573 |
+
"learning_rate": 5.313543104324028e-07,
|
| 1574 |
+
"loss": 0.5715,
|
| 1575 |
+
"step": 252
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.85,
|
| 1579 |
+
"learning_rate": 5.084512506980023e-07,
|
| 1580 |
+
"loss": 0.5927,
|
| 1581 |
+
"step": 253
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.86,
|
| 1585 |
+
"learning_rate": 4.860231453480866e-07,
|
| 1586 |
+
"loss": 0.4835,
|
| 1587 |
+
"step": 254
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.86,
|
| 1591 |
+
"learning_rate": 4.640726631029029e-07,
|
| 1592 |
+
"loss": 0.5396,
|
| 1593 |
+
"step": 255
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.86,
|
| 1597 |
+
"learning_rate": 4.426024158503282e-07,
|
| 1598 |
+
"loss": 0.4446,
|
| 1599 |
+
"step": 256
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.87,
|
| 1603 |
+
"learning_rate": 4.216149583350753e-07,
|
| 1604 |
+
"loss": 0.5833,
|
| 1605 |
+
"step": 257
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.87,
|
| 1609 |
+
"learning_rate": 4.0111278785470846e-07,
|
| 1610 |
+
"loss": 0.478,
|
| 1611 |
+
"step": 258
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.87,
|
| 1615 |
+
"learning_rate": 3.8109834396248805e-07,
|
| 1616 |
+
"loss": 0.5802,
|
| 1617 |
+
"step": 259
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.88,
|
| 1621 |
+
"learning_rate": 3.6157400817708485e-07,
|
| 1622 |
+
"loss": 0.4553,
|
| 1623 |
+
"step": 260
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.88,
|
| 1627 |
+
"learning_rate": 3.425421036992097e-07,
|
| 1628 |
+
"loss": 0.5408,
|
| 1629 |
+
"step": 261
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.88,
|
| 1633 |
+
"learning_rate": 3.2400489513517e-07,
|
| 1634 |
+
"loss": 0.4659,
|
| 1635 |
+
"step": 262
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.89,
|
| 1639 |
+
"learning_rate": 3.0596458822740705e-07,
|
| 1640 |
+
"loss": 0.3709,
|
| 1641 |
+
"step": 263
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.89,
|
| 1645 |
+
"learning_rate": 2.884233295920351e-07,
|
| 1646 |
+
"loss": 0.3811,
|
| 1647 |
+
"step": 264
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.89,
|
| 1651 |
+
"learning_rate": 2.713832064634126e-07,
|
| 1652 |
+
"loss": 0.5523,
|
| 1653 |
+
"step": 265
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.9,
|
| 1657 |
+
"learning_rate": 2.548462464457865e-07,
|
| 1658 |
+
"loss": 0.5376,
|
| 1659 |
+
"step": 266
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.9,
|
| 1663 |
+
"learning_rate": 2.388144172720249e-07,
|
| 1664 |
+
"loss": 0.5279,
|
| 1665 |
+
"step": 267
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.9,
|
| 1669 |
+
"learning_rate": 2.23289626569475e-07,
|
| 1670 |
+
"loss": 0.5563,
|
| 1671 |
+
"step": 268
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.91,
|
| 1675 |
+
"learning_rate": 2.082737216329793e-07,
|
| 1676 |
+
"loss": 0.451,
|
| 1677 |
+
"step": 269
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.91,
|
| 1681 |
+
"learning_rate": 1.937684892050603e-07,
|
| 1682 |
+
"loss": 0.6432,
|
| 1683 |
+
"step": 270
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.91,
|
| 1687 |
+
"learning_rate": 1.797756552633213e-07,
|
| 1688 |
+
"loss": 0.4673,
|
| 1689 |
+
"step": 271
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.92,
|
| 1693 |
+
"learning_rate": 1.6629688481506783e-07,
|
| 1694 |
+
"loss": 0.5042,
|
| 1695 |
+
"step": 272
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.92,
|
| 1699 |
+
"learning_rate": 1.533337816991931e-07,
|
| 1700 |
+
"loss": 0.7103,
|
| 1701 |
+
"step": 273
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.92,
|
| 1705 |
+
"learning_rate": 1.408878883953311e-07,
|
| 1706 |
+
"loss": 0.4237,
|
| 1707 |
+
"step": 274
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.93,
|
| 1711 |
+
"learning_rate": 1.2896068584032355e-07,
|
| 1712 |
+
"loss": 0.4941,
|
| 1713 |
+
"step": 275
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.93,
|
| 1717 |
+
"learning_rate": 1.1755359325199866e-07,
|
| 1718 |
+
"loss": 0.6746,
|
| 1719 |
+
"step": 276
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.93,
|
| 1723 |
+
"learning_rate": 1.0666796796029987e-07,
|
| 1724 |
+
"loss": 0.5323,
|
| 1725 |
+
"step": 277
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.94,
|
| 1729 |
+
"learning_rate": 9.630510524577751e-08,
|
| 1730 |
+
"loss": 0.5387,
|
| 1731 |
+
"step": 278
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.94,
|
| 1735 |
+
"learning_rate": 8.646623818546307e-08,
|
| 1736 |
+
"loss": 0.5481,
|
| 1737 |
+
"step": 279
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.94,
|
| 1741 |
+
"learning_rate": 7.715253750614503e-08,
|
| 1742 |
+
"loss": 0.5632,
|
| 1743 |
+
"step": 280
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.95,
|
| 1747 |
+
"learning_rate": 6.836511144506392e-08,
|
| 1748 |
+
"loss": 0.6036,
|
| 1749 |
+
"step": 281
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.95,
|
| 1753 |
+
"learning_rate": 6.01050056180446e-08,
|
| 1754 |
+
"loss": 0.4902,
|
| 1755 |
+
"step": 282
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.95,
|
| 1759 |
+
"learning_rate": 5.237320289507702e-08,
|
| 1760 |
+
"loss": 0.4684,
|
| 1761 |
+
"step": 283
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.96,
|
| 1765 |
+
"learning_rate": 4.517062328336458e-08,
|
| 1766 |
+
"loss": 0.525,
|
| 1767 |
+
"step": 284
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.96,
|
| 1771 |
+
"learning_rate": 3.849812381785328e-08,
|
| 1772 |
+
"loss": 0.5128,
|
| 1773 |
+
"step": 285
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.96,
|
| 1777 |
+
"learning_rate": 3.235649845925231e-08,
|
| 1778 |
+
"loss": 0.7175,
|
| 1779 |
+
"step": 286
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.97,
|
| 1783 |
+
"learning_rate": 2.674647799956159e-08,
|
| 1784 |
+
"loss": 0.5206,
|
| 1785 |
+
"step": 287
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.97,
|
| 1789 |
+
"learning_rate": 2.166872997511432e-08,
|
| 1790 |
+
"loss": 0.6999,
|
| 1791 |
+
"step": 288
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.97,
|
| 1795 |
+
"learning_rate": 1.7123858587145047e-08,
|
| 1796 |
+
"loss": 0.4856,
|
| 1797 |
+
"step": 289
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 0.98,
|
| 1801 |
+
"learning_rate": 1.3112404629900154e-08,
|
| 1802 |
+
"loss": 0.6217,
|
| 1803 |
+
"step": 290
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.98,
|
| 1807 |
+
"learning_rate": 9.634845426284344e-09,
|
| 1808 |
+
"loss": 0.6083,
|
| 1809 |
+
"step": 291
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.98,
|
| 1813 |
+
"learning_rate": 6.691594771066067e-09,
|
| 1814 |
+
"loss": 0.6078,
|
| 1815 |
+
"step": 292
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.99,
|
| 1819 |
+
"learning_rate": 4.283002881639908e-09,
|
| 1820 |
+
"loss": 0.5348,
|
| 1821 |
+
"step": 293
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.99,
|
| 1825 |
+
"learning_rate": 2.4093563563544198e-09,
|
| 1826 |
+
"loss": 0.5764,
|
| 1827 |
+
"step": 294
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.99,
|
| 1831 |
+
"learning_rate": 1.070878140408904e-09,
|
| 1832 |
+
"loss": 0.5528,
|
| 1833 |
+
"step": 295
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 1.0,
|
| 1837 |
+
"learning_rate": 2.6772749932613136e-10,
|
| 1838 |
+
"loss": 0.6354,
|
| 1839 |
+
"step": 296
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.0,
|
| 1843 |
+
"learning_rate": 0.0,
|
| 1844 |
+
"loss": 0.3309,
|
| 1845 |
+
"step": 297
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.0,
|
| 1849 |
+
"step": 297,
|
| 1850 |
+
"total_flos": 124371515473920.0,
|
| 1851 |
+
"train_loss": 0.6121062839071357,
|
| 1852 |
+
"train_runtime": 9946.9361,
|
| 1853 |
+
"train_samples_per_second": 0.953,
|
| 1854 |
+
"train_steps_per_second": 0.03
|
| 1855 |
+
}
|
| 1856 |
+
],
|
| 1857 |
+
"logging_steps": 1.0,
|
| 1858 |
+
"max_steps": 297,
|
| 1859 |
+
"num_train_epochs": 1,
|
| 1860 |
+
"save_steps": 200.0,
|
| 1861 |
+
"total_flos": 124371515473920.0,
|
| 1862 |
+
"trial_name": null,
|
| 1863 |
+
"trial_params": null
|
| 1864 |
+
}
|
added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|content|>": 32000,
|
| 3 |
+
"<|from|>": 32002,
|
| 4 |
+
"<|recipient|>": 32001,
|
| 5 |
+
"<|stop|>": 32003
|
| 6 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "mistralai/Mistral-7B-v0.1",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MistralForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"eos_token_id": 2,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 4096,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 14336,
|
| 12 |
+
"max_position_embeddings": 32768,
|
| 13 |
+
"model_type": "mistral",
|
| 14 |
+
"num_attention_heads": 32,
|
| 15 |
+
"num_hidden_layers": 32,
|
| 16 |
+
"num_key_value_heads": 8,
|
| 17 |
+
"rms_norm_eps": 1e-05,
|
| 18 |
+
"rope_theta": 10000.0,
|
| 19 |
+
"sliding_window": 8192,
|
| 20 |
+
"tie_word_embeddings": false,
|
| 21 |
+
"torch_dtype": "bfloat16",
|
| 22 |
+
"transformers_version": "4.35.2",
|
| 23 |
+
"use_cache": false,
|
| 24 |
+
"vocab_size": 32004
|
| 25 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.35.2"
|
| 6 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5761112c7f9212a0e39c03b65ec04219bf813ee5ac14e3c6df838e823d20a980
|
| 3 |
+
size 4943195104
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:680276ce8e11f10d93ffc0a2978182692cc661d0154ba1987607827634b75840
|
| 3 |
+
size 4999819336
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45ec5a945576098a278cb3efb01514b3d9bfa5de95c6d1b45b19e4b3dd6ca130
|
| 3 |
+
size 4540549112
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14483529728
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"lm_head.weight": "model-00003-of-00003.safetensors",
|
| 7 |
+
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
|
| 8 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 9 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 10 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 12 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 17 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 18 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 19 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 21 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 26 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 27 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 28 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 30 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 31 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 35 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 36 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 37 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 38 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 39 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 40 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 44 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 45 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 46 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 47 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 48 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 49 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 53 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 54 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 55 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 56 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 57 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 58 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 62 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 63 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 64 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 65 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 66 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 67 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 71 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 72 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 73 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 74 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 75 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 76 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 80 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 81 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 82 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 83 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 84 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 85 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 89 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 90 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 91 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 92 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 93 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 94 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 98 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 99 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 100 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 101 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 102 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 103 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 107 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 108 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 109 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 110 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 111 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 112 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 116 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 117 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 118 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 120 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 125 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 126 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 127 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 128 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 129 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 130 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 134 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 135 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
|
| 136 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
|
| 137 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
|
| 138 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 143 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 144 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 145 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 146 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 147 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 148 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
|
| 152 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 153 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 154 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 155 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 156 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 157 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 161 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 162 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 163 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 164 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 165 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 166 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 170 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 171 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 172 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 173 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 174 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 175 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 179 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 180 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 181 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 182 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 183 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 184 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 188 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 189 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 190 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 191 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 192 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 193 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 197 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 198 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 199 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 200 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 201 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 202 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 206 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 207 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 208 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 209 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 210 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 211 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 215 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 216 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 217 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 219 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 224 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 225 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 226 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 227 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 228 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 229 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 233 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 234 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
|
| 235 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
|
| 236 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
|
| 237 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
|
| 238 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
|
| 242 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 243 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 244 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 245 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 246 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 247 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 251 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 252 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 253 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 254 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 255 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 256 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 260 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 261 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 262 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 263 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 264 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 265 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 269 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 270 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 271 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 272 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 273 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 274 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 278 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 279 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 280 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 281 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 282 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 283 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 287 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 288 |
+
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
|
| 289 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
|
| 290 |
+
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
|
| 291 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
|
| 292 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
|
| 296 |
+
"model.norm.weight": "model-00003-of-00003.safetensors"
|
| 297 |
+
}
|
| 298 |
+
}
|
runs/Dec20_15-03-06_378092d8ce00/events.out.tfevents.1703084840.378092d8ce00.11515.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad0d5e77473e608d964be4d28d3ac05e7f3c474b293c2a00d9e48d0f6b25347a
|
| 3 |
+
size 4311
|
runs/Dec20_15-09-57_378092d8ce00/events.out.tfevents.1703085273.378092d8ce00.14090.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a496a903272b46aa28574260ee824b7d97209dc8104c7bd6a24999166985c991
|
| 3 |
+
size 4312
|
runs/Dec20_15-26-28_378092d8ce00/events.out.tfevents.1703086280.378092d8ce00.20180.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:499c9b39391fb3322c3fc728e40ec1c067beb3c3a6f130d55c292c21b9c85987
|
| 3 |
+
size 24240
|
runs/Dec20_17-32-07_378092d8ce00/events.out.tfevents.1703093818.378092d8ce00.28304.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bcfbfd31aa2e90e23a9bfc2bd0f69a63e7b91d18f2dc3f5dfb163dce5e064bba
|
| 3 |
+
size 53659
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|content|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|recipient|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|from|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<|stop|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"bos_token": {
|
| 33 |
+
"content": "<s>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"eos_token": {
|
| 40 |
+
"content": "</s>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"pad_token": "</s>",
|
| 47 |
+
"unk_token": {
|
| 48 |
+
"content": "<unk>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": false,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
}
|
| 54 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer/added_tokens.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|content|>": 32000,
|
| 3 |
+
"<|from|>": 32002,
|
| 4 |
+
"<|recipient|>": 32001,
|
| 5 |
+
"<|stop|>": 32003
|
| 6 |
+
}
|
tokenizer/special_tokens_map.json
ADDED
|
@@ -0,0 +1,54 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|content|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
},
|
| 10 |
+
{
|
| 11 |
+
"content": "<|recipient|>",
|
| 12 |
+
"lstrip": false,
|
| 13 |
+
"normalized": false,
|
| 14 |
+
"rstrip": false,
|
| 15 |
+
"single_word": false
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"content": "<|from|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"content": "<|stop|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
],
|
| 32 |
+
"bos_token": {
|
| 33 |
+
"content": "<s>",
|
| 34 |
+
"lstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"rstrip": false,
|
| 37 |
+
"single_word": false
|
| 38 |
+
},
|
| 39 |
+
"eos_token": {
|
| 40 |
+
"content": "</s>",
|
| 41 |
+
"lstrip": false,
|
| 42 |
+
"normalized": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"single_word": false
|
| 45 |
+
},
|
| 46 |
+
"pad_token": "</s>",
|
| 47 |
+
"unk_token": {
|
| 48 |
+
"content": "<unk>",
|
| 49 |
+
"lstrip": false,
|
| 50 |
+
"normalized": false,
|
| 51 |
+
"rstrip": false,
|
| 52 |
+
"single_word": false
|
| 53 |
+
}
|
| 54 |
+
}
|
tokenizer/tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer/tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
| 3 |
+
size 493443
|
tokenizer/tokenizer_config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"32000": {
|
| 28 |
+
"content": "<|content|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<|recipient|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<|from|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<|stop|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"additional_special_tokens": [
|
| 61 |
+
"<|content|>",
|
| 62 |
+
"<|recipient|>",
|
| 63 |
+
"<|from|>",
|
| 64 |
+
"<|stop|>"
|
| 65 |
+
],
|
| 66 |
+
"bos_token": "<s>",
|
| 67 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' or message['role'] == 'system' %}\n{{ '<|from|>' + message['role'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% elif message['role'] == 'tool' %}\n{{ '<|from|>' + message['name'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% else %}\n{% set contain_content='no'%}\n{% if message['content'] is not none %}\n{{ '<|from|>assistant\n<|recipient|>all\n<|content|>' + message['content'] }}{% set contain_content='yes'%}\n{% endif %}\n{% if 'tool_calls' in message and message['tool_calls'] is not none %}\n{% for tool_call in message['tool_calls'] %}\n{% set prompt='<|from|>assistant\n<|recipient|>' + tool_call['function']['name'] + '\n<|content|>' + tool_call['function']['arguments'] %}\n{% if loop.index == 1 and contain_content == \"no\" %}\n{{ prompt }}{% else %}\n{{ '\n' + prompt}}{% endif %}\n{% endfor %}\n{% endif %}\n{{ '<|stop|>\n' }}{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}{{ '<|from|>assistant\n<|recipient|>' }}{% endif %}",
|
| 68 |
+
"clean_up_tokenization_spaces": false,
|
| 69 |
+
"eos_token": "</s>",
|
| 70 |
+
"legacy": true,
|
| 71 |
+
"model_max_length": 8192,
|
| 72 |
+
"pad_token": "</s>",
|
| 73 |
+
"padding_side": "left",
|
| 74 |
+
"sp_model_kwargs": {},
|
| 75 |
+
"spaces_between_special_tokens": false,
|
| 76 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 77 |
+
"unk_token": "<unk>",
|
| 78 |
+
"use_default_system_prompt": false
|
| 79 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,79 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"32000": {
|
| 28 |
+
"content": "<|content|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"32001": {
|
| 36 |
+
"content": "<|recipient|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"32002": {
|
| 44 |
+
"content": "<|from|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"32003": {
|
| 52 |
+
"content": "<|stop|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
}
|
| 59 |
+
},
|
| 60 |
+
"additional_special_tokens": [
|
| 61 |
+
"<|content|>",
|
| 62 |
+
"<|recipient|>",
|
| 63 |
+
"<|from|>",
|
| 64 |
+
"<|stop|>"
|
| 65 |
+
],
|
| 66 |
+
"bos_token": "<s>",
|
| 67 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' or message['role'] == 'system' %}\n{{ '<|from|>' + message['role'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% elif message['role'] == 'tool' %}\n{{ '<|from|>' + message['name'] + '\n<|recipient|>all\n<|content|>' + message['content'] + '\n' }}{% else %}\n{% set contain_content='no'%}\n{% if message['content'] is not none %}\n{{ '<|from|>assistant\n<|recipient|>all\n<|content|>' + message['content'] }}{% set contain_content='yes'%}\n{% endif %}\n{% if 'tool_calls' in message and message['tool_calls'] is not none %}\n{% for tool_call in message['tool_calls'] %}\n{% set prompt='<|from|>assistant\n<|recipient|>' + tool_call['function']['name'] + '\n<|content|>' + tool_call['function']['arguments'] %}\n{% if loop.index == 1 and contain_content == \"no\" %}\n{{ prompt }}{% else %}\n{{ '\n' + prompt}}{% endif %}\n{% endfor %}\n{% endif %}\n{{ '<|stop|>\n' }}{% endif %}\n{% endfor %}\n{% if add_generation_prompt %}{{ '<|from|>assistant\n<|recipient|>' }}{% endif %}",
|
| 68 |
+
"clean_up_tokenization_spaces": false,
|
| 69 |
+
"eos_token": "</s>",
|
| 70 |
+
"legacy": true,
|
| 71 |
+
"model_max_length": 8192,
|
| 72 |
+
"pad_token": "</s>",
|
| 73 |
+
"padding_side": "left",
|
| 74 |
+
"sp_model_kwargs": {},
|
| 75 |
+
"spaces_between_special_tokens": false,
|
| 76 |
+
"tokenizer_class": "LlamaTokenizer",
|
| 77 |
+
"unk_token": "<unk>",
|
| 78 |
+
"use_default_system_prompt": false
|
| 79 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1864 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_metric": null,
|
| 3 |
+
"best_model_checkpoint": null,
|
| 4 |
+
"epoch": 1.0,
|
| 5 |
+
"eval_steps": 75,
|
| 6 |
+
"global_step": 297,
|
| 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": 1e-06,
|
| 14 |
+
"loss": 0.9799,
|
| 15 |
+
"step": 1
|
| 16 |
+
},
|
| 17 |
+
{
|
| 18 |
+
"epoch": 0.01,
|
| 19 |
+
"learning_rate": 2e-06,
|
| 20 |
+
"loss": 1.0088,
|
| 21 |
+
"step": 2
|
| 22 |
+
},
|
| 23 |
+
{
|
| 24 |
+
"epoch": 0.01,
|
| 25 |
+
"learning_rate": 3e-06,
|
| 26 |
+
"loss": 1.0716,
|
| 27 |
+
"step": 3
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"epoch": 0.01,
|
| 31 |
+
"learning_rate": 4e-06,
|
| 32 |
+
"loss": 0.8604,
|
| 33 |
+
"step": 4
|
| 34 |
+
},
|
| 35 |
+
{
|
| 36 |
+
"epoch": 0.02,
|
| 37 |
+
"learning_rate": 5e-06,
|
| 38 |
+
"loss": 0.8246,
|
| 39 |
+
"step": 5
|
| 40 |
+
},
|
| 41 |
+
{
|
| 42 |
+
"epoch": 0.02,
|
| 43 |
+
"learning_rate": 6e-06,
|
| 44 |
+
"loss": 0.8132,
|
| 45 |
+
"step": 6
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.02,
|
| 49 |
+
"learning_rate": 7e-06,
|
| 50 |
+
"loss": 0.6148,
|
| 51 |
+
"step": 7
|
| 52 |
+
},
|
| 53 |
+
{
|
| 54 |
+
"epoch": 0.03,
|
| 55 |
+
"learning_rate": 8e-06,
|
| 56 |
+
"loss": 0.7729,
|
| 57 |
+
"step": 8
|
| 58 |
+
},
|
| 59 |
+
{
|
| 60 |
+
"epoch": 0.03,
|
| 61 |
+
"learning_rate": 9e-06,
|
| 62 |
+
"loss": 0.7227,
|
| 63 |
+
"step": 9
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"epoch": 0.03,
|
| 67 |
+
"learning_rate": 8.999732272500674e-06,
|
| 68 |
+
"loss": 0.8967,
|
| 69 |
+
"step": 10
|
| 70 |
+
},
|
| 71 |
+
{
|
| 72 |
+
"epoch": 0.04,
|
| 73 |
+
"learning_rate": 8.998929121859591e-06,
|
| 74 |
+
"loss": 1.0003,
|
| 75 |
+
"step": 11
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"epoch": 0.04,
|
| 79 |
+
"learning_rate": 8.997590643643646e-06,
|
| 80 |
+
"loss": 0.8262,
|
| 81 |
+
"step": 12
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.04,
|
| 85 |
+
"learning_rate": 8.99571699711836e-06,
|
| 86 |
+
"loss": 0.9495,
|
| 87 |
+
"step": 13
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.05,
|
| 91 |
+
"learning_rate": 8.993308405228933e-06,
|
| 92 |
+
"loss": 0.8094,
|
| 93 |
+
"step": 14
|
| 94 |
+
},
|
| 95 |
+
{
|
| 96 |
+
"epoch": 0.05,
|
| 97 |
+
"learning_rate": 8.990365154573717e-06,
|
| 98 |
+
"loss": 0.8528,
|
| 99 |
+
"step": 15
|
| 100 |
+
},
|
| 101 |
+
{
|
| 102 |
+
"epoch": 0.05,
|
| 103 |
+
"learning_rate": 8.9868875953701e-06,
|
| 104 |
+
"loss": 0.8767,
|
| 105 |
+
"step": 16
|
| 106 |
+
},
|
| 107 |
+
{
|
| 108 |
+
"epoch": 0.06,
|
| 109 |
+
"learning_rate": 8.982876141412855e-06,
|
| 110 |
+
"loss": 0.8405,
|
| 111 |
+
"step": 17
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"epoch": 0.06,
|
| 115 |
+
"learning_rate": 8.978331270024886e-06,
|
| 116 |
+
"loss": 0.9105,
|
| 117 |
+
"step": 18
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.06,
|
| 121 |
+
"learning_rate": 8.973253522000438e-06,
|
| 122 |
+
"loss": 0.9109,
|
| 123 |
+
"step": 19
|
| 124 |
+
},
|
| 125 |
+
{
|
| 126 |
+
"epoch": 0.07,
|
| 127 |
+
"learning_rate": 8.967643501540747e-06,
|
| 128 |
+
"loss": 0.8691,
|
| 129 |
+
"step": 20
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.07,
|
| 133 |
+
"learning_rate": 8.961501876182148e-06,
|
| 134 |
+
"loss": 0.7543,
|
| 135 |
+
"step": 21
|
| 136 |
+
},
|
| 137 |
+
{
|
| 138 |
+
"epoch": 0.07,
|
| 139 |
+
"learning_rate": 8.954829376716635e-06,
|
| 140 |
+
"loss": 0.7925,
|
| 141 |
+
"step": 22
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"epoch": 0.08,
|
| 145 |
+
"learning_rate": 8.947626797104924e-06,
|
| 146 |
+
"loss": 0.8162,
|
| 147 |
+
"step": 23
|
| 148 |
+
},
|
| 149 |
+
{
|
| 150 |
+
"epoch": 0.08,
|
| 151 |
+
"learning_rate": 8.939894994381956e-06,
|
| 152 |
+
"loss": 0.7787,
|
| 153 |
+
"step": 24
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.08,
|
| 157 |
+
"learning_rate": 8.931634888554937e-06,
|
| 158 |
+
"loss": 0.8244,
|
| 159 |
+
"step": 25
|
| 160 |
+
},
|
| 161 |
+
{
|
| 162 |
+
"epoch": 0.09,
|
| 163 |
+
"learning_rate": 8.922847462493856e-06,
|
| 164 |
+
"loss": 0.8088,
|
| 165 |
+
"step": 26
|
| 166 |
+
},
|
| 167 |
+
{
|
| 168 |
+
"epoch": 0.09,
|
| 169 |
+
"learning_rate": 8.913533761814537e-06,
|
| 170 |
+
"loss": 0.8405,
|
| 171 |
+
"step": 27
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.09,
|
| 175 |
+
"learning_rate": 8.903694894754222e-06,
|
| 176 |
+
"loss": 0.8361,
|
| 177 |
+
"step": 28
|
| 178 |
+
},
|
| 179 |
+
{
|
| 180 |
+
"epoch": 0.1,
|
| 181 |
+
"learning_rate": 8.8933320320397e-06,
|
| 182 |
+
"loss": 0.6428,
|
| 183 |
+
"step": 29
|
| 184 |
+
},
|
| 185 |
+
{
|
| 186 |
+
"epoch": 0.1,
|
| 187 |
+
"learning_rate": 8.882446406748002e-06,
|
| 188 |
+
"loss": 0.6581,
|
| 189 |
+
"step": 30
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.1,
|
| 193 |
+
"learning_rate": 8.871039314159675e-06,
|
| 194 |
+
"loss": 0.8059,
|
| 195 |
+
"step": 31
|
| 196 |
+
},
|
| 197 |
+
{
|
| 198 |
+
"epoch": 0.11,
|
| 199 |
+
"learning_rate": 8.859112111604669e-06,
|
| 200 |
+
"loss": 0.8403,
|
| 201 |
+
"step": 32
|
| 202 |
+
},
|
| 203 |
+
{
|
| 204 |
+
"epoch": 0.11,
|
| 205 |
+
"learning_rate": 8.846666218300807e-06,
|
| 206 |
+
"loss": 0.712,
|
| 207 |
+
"step": 33
|
| 208 |
+
},
|
| 209 |
+
{
|
| 210 |
+
"epoch": 0.11,
|
| 211 |
+
"learning_rate": 8.833703115184932e-06,
|
| 212 |
+
"loss": 0.7188,
|
| 213 |
+
"step": 34
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.12,
|
| 217 |
+
"learning_rate": 8.82022434473668e-06,
|
| 218 |
+
"loss": 0.7583,
|
| 219 |
+
"step": 35
|
| 220 |
+
},
|
| 221 |
+
{
|
| 222 |
+
"epoch": 0.12,
|
| 223 |
+
"learning_rate": 8.80623151079494e-06,
|
| 224 |
+
"loss": 0.7899,
|
| 225 |
+
"step": 36
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.12,
|
| 229 |
+
"learning_rate": 8.791726278367021e-06,
|
| 230 |
+
"loss": 0.8039,
|
| 231 |
+
"step": 37
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"epoch": 0.13,
|
| 235 |
+
"learning_rate": 8.776710373430525e-06,
|
| 236 |
+
"loss": 0.8014,
|
| 237 |
+
"step": 38
|
| 238 |
+
},
|
| 239 |
+
{
|
| 240 |
+
"epoch": 0.13,
|
| 241 |
+
"learning_rate": 8.761185582727977e-06,
|
| 242 |
+
"loss": 0.8441,
|
| 243 |
+
"step": 39
|
| 244 |
+
},
|
| 245 |
+
{
|
| 246 |
+
"epoch": 0.13,
|
| 247 |
+
"learning_rate": 8.745153753554214e-06,
|
| 248 |
+
"loss": 0.6469,
|
| 249 |
+
"step": 40
|
| 250 |
+
},
|
| 251 |
+
{
|
| 252 |
+
"epoch": 0.14,
|
| 253 |
+
"learning_rate": 8.728616793536588e-06,
|
| 254 |
+
"loss": 0.711,
|
| 255 |
+
"step": 41
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.14,
|
| 259 |
+
"learning_rate": 8.711576670407966e-06,
|
| 260 |
+
"loss": 0.6167,
|
| 261 |
+
"step": 42
|
| 262 |
+
},
|
| 263 |
+
{
|
| 264 |
+
"epoch": 0.14,
|
| 265 |
+
"learning_rate": 8.694035411772595e-06,
|
| 266 |
+
"loss": 0.8141,
|
| 267 |
+
"step": 43
|
| 268 |
+
},
|
| 269 |
+
{
|
| 270 |
+
"epoch": 0.15,
|
| 271 |
+
"learning_rate": 8.675995104864831e-06,
|
| 272 |
+
"loss": 0.5856,
|
| 273 |
+
"step": 44
|
| 274 |
+
},
|
| 275 |
+
{
|
| 276 |
+
"epoch": 0.15,
|
| 277 |
+
"learning_rate": 8.65745789630079e-06,
|
| 278 |
+
"loss": 0.6113,
|
| 279 |
+
"step": 45
|
| 280 |
+
},
|
| 281 |
+
{
|
| 282 |
+
"epoch": 0.15,
|
| 283 |
+
"learning_rate": 8.638425991822915e-06,
|
| 284 |
+
"loss": 0.8029,
|
| 285 |
+
"step": 46
|
| 286 |
+
},
|
| 287 |
+
{
|
| 288 |
+
"epoch": 0.16,
|
| 289 |
+
"learning_rate": 8.618901656037513e-06,
|
| 290 |
+
"loss": 0.7917,
|
| 291 |
+
"step": 47
|
| 292 |
+
},
|
| 293 |
+
{
|
| 294 |
+
"epoch": 0.16,
|
| 295 |
+
"learning_rate": 8.598887212145291e-06,
|
| 296 |
+
"loss": 0.6432,
|
| 297 |
+
"step": 48
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.16,
|
| 301 |
+
"learning_rate": 8.578385041664925e-06,
|
| 302 |
+
"loss": 0.6574,
|
| 303 |
+
"step": 49
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.17,
|
| 307 |
+
"learning_rate": 8.557397584149673e-06,
|
| 308 |
+
"loss": 0.5809,
|
| 309 |
+
"step": 50
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"epoch": 0.17,
|
| 313 |
+
"learning_rate": 8.535927336897097e-06,
|
| 314 |
+
"loss": 0.6016,
|
| 315 |
+
"step": 51
|
| 316 |
+
},
|
| 317 |
+
{
|
| 318 |
+
"epoch": 0.18,
|
| 319 |
+
"learning_rate": 8.513976854651913e-06,
|
| 320 |
+
"loss": 0.6247,
|
| 321 |
+
"step": 52
|
| 322 |
+
},
|
| 323 |
+
{
|
| 324 |
+
"epoch": 0.18,
|
| 325 |
+
"learning_rate": 8.491548749301997e-06,
|
| 326 |
+
"loss": 0.5538,
|
| 327 |
+
"step": 53
|
| 328 |
+
},
|
| 329 |
+
{
|
| 330 |
+
"epoch": 0.18,
|
| 331 |
+
"learning_rate": 8.468645689567598e-06,
|
| 332 |
+
"loss": 0.6069,
|
| 333 |
+
"step": 54
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"epoch": 0.19,
|
| 337 |
+
"learning_rate": 8.445270400683786e-06,
|
| 338 |
+
"loss": 0.6994,
|
| 339 |
+
"step": 55
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.19,
|
| 343 |
+
"learning_rate": 8.421425664076177e-06,
|
| 344 |
+
"loss": 0.5385,
|
| 345 |
+
"step": 56
|
| 346 |
+
},
|
| 347 |
+
{
|
| 348 |
+
"epoch": 0.19,
|
| 349 |
+
"learning_rate": 8.397114317029975e-06,
|
| 350 |
+
"loss": 0.7693,
|
| 351 |
+
"step": 57
|
| 352 |
+
},
|
| 353 |
+
{
|
| 354 |
+
"epoch": 0.2,
|
| 355 |
+
"learning_rate": 8.372339252352355e-06,
|
| 356 |
+
"loss": 0.6196,
|
| 357 |
+
"step": 58
|
| 358 |
+
},
|
| 359 |
+
{
|
| 360 |
+
"epoch": 0.2,
|
| 361 |
+
"learning_rate": 8.347103418028259e-06,
|
| 362 |
+
"loss": 0.7083,
|
| 363 |
+
"step": 59
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"epoch": 0.2,
|
| 367 |
+
"learning_rate": 8.321409816869605e-06,
|
| 368 |
+
"loss": 0.6298,
|
| 369 |
+
"step": 60
|
| 370 |
+
},
|
| 371 |
+
{
|
| 372 |
+
"epoch": 0.21,
|
| 373 |
+
"learning_rate": 8.295261506157985e-06,
|
| 374 |
+
"loss": 0.5166,
|
| 375 |
+
"step": 61
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.21,
|
| 379 |
+
"learning_rate": 8.268661597280886e-06,
|
| 380 |
+
"loss": 0.7171,
|
| 381 |
+
"step": 62
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.21,
|
| 385 |
+
"learning_rate": 8.241613255361455e-06,
|
| 386 |
+
"loss": 0.7374,
|
| 387 |
+
"step": 63
|
| 388 |
+
},
|
| 389 |
+
{
|
| 390 |
+
"epoch": 0.22,
|
| 391 |
+
"learning_rate": 8.214119698881887e-06,
|
| 392 |
+
"loss": 0.5147,
|
| 393 |
+
"step": 64
|
| 394 |
+
},
|
| 395 |
+
{
|
| 396 |
+
"epoch": 0.22,
|
| 397 |
+
"learning_rate": 8.186184199300463e-06,
|
| 398 |
+
"loss": 0.7629,
|
| 399 |
+
"step": 65
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"epoch": 0.22,
|
| 403 |
+
"learning_rate": 8.157810080662269e-06,
|
| 404 |
+
"loss": 0.6447,
|
| 405 |
+
"step": 66
|
| 406 |
+
},
|
| 407 |
+
{
|
| 408 |
+
"epoch": 0.23,
|
| 409 |
+
"learning_rate": 8.129000719203673e-06,
|
| 410 |
+
"loss": 0.5669,
|
| 411 |
+
"step": 67
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 0.23,
|
| 415 |
+
"learning_rate": 8.099759542950583e-06,
|
| 416 |
+
"loss": 0.6644,
|
| 417 |
+
"step": 68
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.23,
|
| 421 |
+
"learning_rate": 8.070090031310558e-06,
|
| 422 |
+
"loss": 0.637,
|
| 423 |
+
"step": 69
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.24,
|
| 427 |
+
"learning_rate": 8.039995714658776e-06,
|
| 428 |
+
"loss": 0.6364,
|
| 429 |
+
"step": 70
|
| 430 |
+
},
|
| 431 |
+
{
|
| 432 |
+
"epoch": 0.24,
|
| 433 |
+
"learning_rate": 8.009480173917969e-06,
|
| 434 |
+
"loss": 0.6313,
|
| 435 |
+
"step": 71
|
| 436 |
+
},
|
| 437 |
+
{
|
| 438 |
+
"epoch": 0.24,
|
| 439 |
+
"learning_rate": 7.978547040132316e-06,
|
| 440 |
+
"loss": 0.6522,
|
| 441 |
+
"step": 72
|
| 442 |
+
},
|
| 443 |
+
{
|
| 444 |
+
"epoch": 0.25,
|
| 445 |
+
"learning_rate": 7.947199994035401e-06,
|
| 446 |
+
"loss": 0.6039,
|
| 447 |
+
"step": 73
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 0.25,
|
| 451 |
+
"learning_rate": 7.915442765612229e-06,
|
| 452 |
+
"loss": 0.5923,
|
| 453 |
+
"step": 74
|
| 454 |
+
},
|
| 455 |
+
{
|
| 456 |
+
"epoch": 0.25,
|
| 457 |
+
"learning_rate": 7.883279133655398e-06,
|
| 458 |
+
"loss": 0.5145,
|
| 459 |
+
"step": 75
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.25,
|
| 463 |
+
"eval_accuracy": 0.8153410115496591,
|
| 464 |
+
"eval_accuracy_<|content|>": 0.9983489268024216,
|
| 465 |
+
"eval_accuracy_<|from|>": 0.975,
|
| 466 |
+
"eval_accuracy_<|recipient|>": 0.7946428571428571,
|
| 467 |
+
"eval_accuracy_<|stop|>": 0.8509316770186336,
|
| 468 |
+
"eval_accuracy_total_num_<|content|>": 3634,
|
| 469 |
+
"eval_accuracy_total_num_<|from|>": 560,
|
| 470 |
+
"eval_accuracy_total_num_<|recipient|>": 560,
|
| 471 |
+
"eval_accuracy_total_num_<|stop|>": 3059,
|
| 472 |
+
"eval_loss": 0.6158567070960999,
|
| 473 |
+
"eval_perplexity": 1.0609388823519776,
|
| 474 |
+
"eval_runtime": 222.2983,
|
| 475 |
+
"eval_samples_per_second": 4.705,
|
| 476 |
+
"eval_steps_per_second": 0.148,
|
| 477 |
+
"step": 75
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"epoch": 0.26,
|
| 481 |
+
"learning_rate": 7.850712925315468e-06,
|
| 482 |
+
"loss": 0.7307,
|
| 483 |
+
"step": 76
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 0.26,
|
| 487 |
+
"learning_rate": 7.817748015645558e-06,
|
| 488 |
+
"loss": 0.6347,
|
| 489 |
+
"step": 77
|
| 490 |
+
},
|
| 491 |
+
{
|
| 492 |
+
"epoch": 0.26,
|
| 493 |
+
"learning_rate": 7.78438832714026e-06,
|
| 494 |
+
"loss": 0.5611,
|
| 495 |
+
"step": 78
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"epoch": 0.27,
|
| 499 |
+
"learning_rate": 7.7506378292689e-06,
|
| 500 |
+
"loss": 0.5914,
|
| 501 |
+
"step": 79
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.27,
|
| 505 |
+
"learning_rate": 7.716500538003208e-06,
|
| 506 |
+
"loss": 0.4936,
|
| 507 |
+
"step": 80
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.27,
|
| 511 |
+
"learning_rate": 7.681980515339464e-06,
|
| 512 |
+
"loss": 0.543,
|
| 513 |
+
"step": 81
|
| 514 |
+
},
|
| 515 |
+
{
|
| 516 |
+
"epoch": 0.28,
|
| 517 |
+
"learning_rate": 7.647081868815153e-06,
|
| 518 |
+
"loss": 0.5267,
|
| 519 |
+
"step": 82
|
| 520 |
+
},
|
| 521 |
+
{
|
| 522 |
+
"epoch": 0.28,
|
| 523 |
+
"learning_rate": 7.611808751020213e-06,
|
| 524 |
+
"loss": 0.6759,
|
| 525 |
+
"step": 83
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"epoch": 0.28,
|
| 529 |
+
"learning_rate": 7.57616535910292e-06,
|
| 530 |
+
"loss": 0.5291,
|
| 531 |
+
"step": 84
|
| 532 |
+
},
|
| 533 |
+
{
|
| 534 |
+
"epoch": 0.29,
|
| 535 |
+
"learning_rate": 7.540155934270472e-06,
|
| 536 |
+
"loss": 0.7263,
|
| 537 |
+
"step": 85
|
| 538 |
+
},
|
| 539 |
+
{
|
| 540 |
+
"epoch": 0.29,
|
| 541 |
+
"learning_rate": 7.5037847612843135e-06,
|
| 542 |
+
"loss": 0.6477,
|
| 543 |
+
"step": 86
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.29,
|
| 547 |
+
"learning_rate": 7.46705616795031e-06,
|
| 548 |
+
"loss": 0.6295,
|
| 549 |
+
"step": 87
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.3,
|
| 553 |
+
"learning_rate": 7.429974524603771e-06,
|
| 554 |
+
"loss": 0.5567,
|
| 555 |
+
"step": 88
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"epoch": 0.3,
|
| 559 |
+
"learning_rate": 7.392544243589427e-06,
|
| 560 |
+
"loss": 0.5361,
|
| 561 |
+
"step": 89
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 0.3,
|
| 565 |
+
"learning_rate": 7.354769778736405e-06,
|
| 566 |
+
"loss": 0.752,
|
| 567 |
+
"step": 90
|
| 568 |
+
},
|
| 569 |
+
{
|
| 570 |
+
"epoch": 0.31,
|
| 571 |
+
"learning_rate": 7.316655624828267e-06,
|
| 572 |
+
"loss": 0.581,
|
| 573 |
+
"step": 91
|
| 574 |
+
},
|
| 575 |
+
{
|
| 576 |
+
"epoch": 0.31,
|
| 577 |
+
"learning_rate": 7.278206317068173e-06,
|
| 578 |
+
"loss": 0.5523,
|
| 579 |
+
"step": 92
|
| 580 |
+
},
|
| 581 |
+
{
|
| 582 |
+
"epoch": 0.31,
|
| 583 |
+
"learning_rate": 7.239426430539243e-06,
|
| 584 |
+
"loss": 0.6416,
|
| 585 |
+
"step": 93
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.32,
|
| 589 |
+
"learning_rate": 7.2003205796601645e-06,
|
| 590 |
+
"loss": 0.6665,
|
| 591 |
+
"step": 94
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.32,
|
| 595 |
+
"learning_rate": 7.160893417636121e-06,
|
| 596 |
+
"loss": 0.7361,
|
| 597 |
+
"step": 95
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 0.32,
|
| 601 |
+
"learning_rate": 7.121149635905111e-06,
|
| 602 |
+
"loss": 0.507,
|
| 603 |
+
"step": 96
|
| 604 |
+
},
|
| 605 |
+
{
|
| 606 |
+
"epoch": 0.33,
|
| 607 |
+
"learning_rate": 7.081093963579708e-06,
|
| 608 |
+
"loss": 0.6335,
|
| 609 |
+
"step": 97
|
| 610 |
+
},
|
| 611 |
+
{
|
| 612 |
+
"epoch": 0.33,
|
| 613 |
+
"learning_rate": 7.040731166884352e-06,
|
| 614 |
+
"loss": 0.545,
|
| 615 |
+
"step": 98
|
| 616 |
+
},
|
| 617 |
+
{
|
| 618 |
+
"epoch": 0.33,
|
| 619 |
+
"learning_rate": 7.00006604858821e-06,
|
| 620 |
+
"loss": 0.7382,
|
| 621 |
+
"step": 99
|
| 622 |
+
},
|
| 623 |
+
{
|
| 624 |
+
"epoch": 0.34,
|
| 625 |
+
"learning_rate": 6.959103447433696e-06,
|
| 626 |
+
"loss": 0.7749,
|
| 627 |
+
"step": 100
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.34,
|
| 631 |
+
"learning_rate": 6.917848237560708e-06,
|
| 632 |
+
"loss": 0.5616,
|
| 633 |
+
"step": 101
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.34,
|
| 637 |
+
"learning_rate": 6.876305327926656e-06,
|
| 638 |
+
"loss": 0.6483,
|
| 639 |
+
"step": 102
|
| 640 |
+
},
|
| 641 |
+
{
|
| 642 |
+
"epoch": 0.35,
|
| 643 |
+
"learning_rate": 6.834479661722347e-06,
|
| 644 |
+
"loss": 0.7207,
|
| 645 |
+
"step": 103
|
| 646 |
+
},
|
| 647 |
+
{
|
| 648 |
+
"epoch": 0.35,
|
| 649 |
+
"learning_rate": 6.792376215783789e-06,
|
| 650 |
+
"loss": 0.5815,
|
| 651 |
+
"step": 104
|
| 652 |
+
},
|
| 653 |
+
{
|
| 654 |
+
"epoch": 0.35,
|
| 655 |
+
"learning_rate": 6.75e-06,
|
| 656 |
+
"loss": 0.4725,
|
| 657 |
+
"step": 105
|
| 658 |
+
},
|
| 659 |
+
{
|
| 660 |
+
"epoch": 0.36,
|
| 661 |
+
"learning_rate": 6.707356056716886e-06,
|
| 662 |
+
"loss": 0.7133,
|
| 663 |
+
"step": 106
|
| 664 |
+
},
|
| 665 |
+
{
|
| 666 |
+
"epoch": 0.36,
|
| 667 |
+
"learning_rate": 6.664449460137245e-06,
|
| 668 |
+
"loss": 0.5666,
|
| 669 |
+
"step": 107
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.36,
|
| 673 |
+
"learning_rate": 6.621285315716991e-06,
|
| 674 |
+
"loss": 0.545,
|
| 675 |
+
"step": 108
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.37,
|
| 679 |
+
"learning_rate": 6.5778687595576535e-06,
|
| 680 |
+
"loss": 0.7437,
|
| 681 |
+
"step": 109
|
| 682 |
+
},
|
| 683 |
+
{
|
| 684 |
+
"epoch": 0.37,
|
| 685 |
+
"learning_rate": 6.5342049577952396e-06,
|
| 686 |
+
"loss": 0.5496,
|
| 687 |
+
"step": 110
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"epoch": 0.37,
|
| 691 |
+
"learning_rate": 6.490299105985506e-06,
|
| 692 |
+
"loss": 0.5883,
|
| 693 |
+
"step": 111
|
| 694 |
+
},
|
| 695 |
+
{
|
| 696 |
+
"epoch": 0.38,
|
| 697 |
+
"learning_rate": 6.446156428485748e-06,
|
| 698 |
+
"loss": 0.5355,
|
| 699 |
+
"step": 112
|
| 700 |
+
},
|
| 701 |
+
{
|
| 702 |
+
"epoch": 0.38,
|
| 703 |
+
"learning_rate": 6.401782177833148e-06,
|
| 704 |
+
"loss": 0.6925,
|
| 705 |
+
"step": 113
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 0.38,
|
| 709 |
+
"learning_rate": 6.357181634119776e-06,
|
| 710 |
+
"loss": 0.7328,
|
| 711 |
+
"step": 114
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.39,
|
| 715 |
+
"learning_rate": 6.312360104364318e-06,
|
| 716 |
+
"loss": 0.6417,
|
| 717 |
+
"step": 115
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.39,
|
| 721 |
+
"learning_rate": 6.267322921880584e-06,
|
| 722 |
+
"loss": 0.6352,
|
| 723 |
+
"step": 116
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"epoch": 0.39,
|
| 727 |
+
"learning_rate": 6.222075445642905e-06,
|
| 728 |
+
"loss": 0.6245,
|
| 729 |
+
"step": 117
|
| 730 |
+
},
|
| 731 |
+
{
|
| 732 |
+
"epoch": 0.4,
|
| 733 |
+
"learning_rate": 6.176623059648463e-06,
|
| 734 |
+
"loss": 0.572,
|
| 735 |
+
"step": 118
|
| 736 |
+
},
|
| 737 |
+
{
|
| 738 |
+
"epoch": 0.4,
|
| 739 |
+
"learning_rate": 6.130971172276657e-06,
|
| 740 |
+
"loss": 0.5957,
|
| 741 |
+
"step": 119
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 0.4,
|
| 745 |
+
"learning_rate": 6.085125215645551e-06,
|
| 746 |
+
"loss": 0.5968,
|
| 747 |
+
"step": 120
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.41,
|
| 751 |
+
"learning_rate": 6.03909064496551e-06,
|
| 752 |
+
"loss": 0.7397,
|
| 753 |
+
"step": 121
|
| 754 |
+
},
|
| 755 |
+
{
|
| 756 |
+
"epoch": 0.41,
|
| 757 |
+
"learning_rate": 5.992872937890085e-06,
|
| 758 |
+
"loss": 0.4958,
|
| 759 |
+
"step": 122
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.41,
|
| 763 |
+
"learning_rate": 5.946477593864227e-06,
|
| 764 |
+
"loss": 0.6392,
|
| 765 |
+
"step": 123
|
| 766 |
+
},
|
| 767 |
+
{
|
| 768 |
+
"epoch": 0.42,
|
| 769 |
+
"learning_rate": 5.899910133469909e-06,
|
| 770 |
+
"loss": 0.5666,
|
| 771 |
+
"step": 124
|
| 772 |
+
},
|
| 773 |
+
{
|
| 774 |
+
"epoch": 0.42,
|
| 775 |
+
"learning_rate": 5.853176097769229e-06,
|
| 776 |
+
"loss": 0.4596,
|
| 777 |
+
"step": 125
|
| 778 |
+
},
|
| 779 |
+
{
|
| 780 |
+
"epoch": 0.42,
|
| 781 |
+
"learning_rate": 5.80628104764508e-06,
|
| 782 |
+
"loss": 0.6385,
|
| 783 |
+
"step": 126
|
| 784 |
+
},
|
| 785 |
+
{
|
| 786 |
+
"epoch": 0.43,
|
| 787 |
+
"learning_rate": 5.7592305631394655e-06,
|
| 788 |
+
"loss": 0.578,
|
| 789 |
+
"step": 127
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.43,
|
| 793 |
+
"learning_rate": 5.7120302427895185e-06,
|
| 794 |
+
"loss": 0.8049,
|
| 795 |
+
"step": 128
|
| 796 |
+
},
|
| 797 |
+
{
|
| 798 |
+
"epoch": 0.43,
|
| 799 |
+
"learning_rate": 5.664685702961344e-06,
|
| 800 |
+
"loss": 0.4874,
|
| 801 |
+
"step": 129
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.44,
|
| 805 |
+
"learning_rate": 5.617202577181723e-06,
|
| 806 |
+
"loss": 0.5195,
|
| 807 |
+
"step": 130
|
| 808 |
+
},
|
| 809 |
+
{
|
| 810 |
+
"epoch": 0.44,
|
| 811 |
+
"learning_rate": 5.569586515467779e-06,
|
| 812 |
+
"loss": 0.6092,
|
| 813 |
+
"step": 131
|
| 814 |
+
},
|
| 815 |
+
{
|
| 816 |
+
"epoch": 0.44,
|
| 817 |
+
"learning_rate": 5.521843183654679e-06,
|
| 818 |
+
"loss": 0.6794,
|
| 819 |
+
"step": 132
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 0.45,
|
| 823 |
+
"learning_rate": 5.473978262721463e-06,
|
| 824 |
+
"loss": 0.4674,
|
| 825 |
+
"step": 133
|
| 826 |
+
},
|
| 827 |
+
{
|
| 828 |
+
"epoch": 0.45,
|
| 829 |
+
"learning_rate": 5.425997448115057e-06,
|
| 830 |
+
"loss": 0.5482,
|
| 831 |
+
"step": 134
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.45,
|
| 835 |
+
"learning_rate": 5.377906449072578e-06,
|
| 836 |
+
"loss": 0.4731,
|
| 837 |
+
"step": 135
|
| 838 |
+
},
|
| 839 |
+
{
|
| 840 |
+
"epoch": 0.46,
|
| 841 |
+
"learning_rate": 5.3297109879419855e-06,
|
| 842 |
+
"loss": 0.6931,
|
| 843 |
+
"step": 136
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.46,
|
| 847 |
+
"learning_rate": 5.281416799501187e-06,
|
| 848 |
+
"loss": 0.5254,
|
| 849 |
+
"step": 137
|
| 850 |
+
},
|
| 851 |
+
{
|
| 852 |
+
"epoch": 0.46,
|
| 853 |
+
"learning_rate": 5.23302963027565e-06,
|
| 854 |
+
"loss": 0.5313,
|
| 855 |
+
"step": 138
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 0.47,
|
| 859 |
+
"learning_rate": 5.184555237854625e-06,
|
| 860 |
+
"loss": 0.5622,
|
| 861 |
+
"step": 139
|
| 862 |
+
},
|
| 863 |
+
{
|
| 864 |
+
"epoch": 0.47,
|
| 865 |
+
"learning_rate": 5.1359993902060545e-06,
|
| 866 |
+
"loss": 0.5621,
|
| 867 |
+
"step": 140
|
| 868 |
+
},
|
| 869 |
+
{
|
| 870 |
+
"epoch": 0.47,
|
| 871 |
+
"learning_rate": 5.087367864990233e-06,
|
| 872 |
+
"loss": 0.5534,
|
| 873 |
+
"step": 141
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.48,
|
| 877 |
+
"learning_rate": 5.038666448872331e-06,
|
| 878 |
+
"loss": 0.5932,
|
| 879 |
+
"step": 142
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"epoch": 0.48,
|
| 883 |
+
"learning_rate": 4.989900936833841e-06,
|
| 884 |
+
"loss": 0.5931,
|
| 885 |
+
"step": 143
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.48,
|
| 889 |
+
"learning_rate": 4.941077131483024e-06,
|
| 890 |
+
"loss": 0.5631,
|
| 891 |
+
"step": 144
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 0.49,
|
| 895 |
+
"learning_rate": 4.892200842364463e-06,
|
| 896 |
+
"loss": 0.6102,
|
| 897 |
+
"step": 145
|
| 898 |
+
},
|
| 899 |
+
{
|
| 900 |
+
"epoch": 0.49,
|
| 901 |
+
"learning_rate": 4.843277885267786e-06,
|
| 902 |
+
"loss": 0.6519,
|
| 903 |
+
"step": 146
|
| 904 |
+
},
|
| 905 |
+
{
|
| 906 |
+
"epoch": 0.49,
|
| 907 |
+
"learning_rate": 4.794314081535644e-06,
|
| 908 |
+
"loss": 0.4957,
|
| 909 |
+
"step": 147
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"epoch": 0.5,
|
| 913 |
+
"learning_rate": 4.745315257371029e-06,
|
| 914 |
+
"loss": 0.6076,
|
| 915 |
+
"step": 148
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.5,
|
| 919 |
+
"learning_rate": 4.696287243144012e-06,
|
| 920 |
+
"loss": 0.6205,
|
| 921 |
+
"step": 149
|
| 922 |
+
},
|
| 923 |
+
{
|
| 924 |
+
"epoch": 0.51,
|
| 925 |
+
"learning_rate": 4.647235872697993e-06,
|
| 926 |
+
"loss": 0.5454,
|
| 927 |
+
"step": 150
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.51,
|
| 931 |
+
"eval_accuracy": 0.8247416654541203,
|
| 932 |
+
"eval_accuracy_<|content|>": 1.0,
|
| 933 |
+
"eval_accuracy_<|from|>": 0.9892857142857143,
|
| 934 |
+
"eval_accuracy_<|recipient|>": 1.0,
|
| 935 |
+
"eval_accuracy_<|stop|>": 0.8996404053612291,
|
| 936 |
+
"eval_accuracy_total_num_<|content|>": 3634,
|
| 937 |
+
"eval_accuracy_total_num_<|from|>": 560,
|
| 938 |
+
"eval_accuracy_total_num_<|recipient|>": 560,
|
| 939 |
+
"eval_accuracy_total_num_<|stop|>": 3059,
|
| 940 |
+
"eval_loss": 0.5723979473114014,
|
| 941 |
+
"eval_perplexity": 1.056601002074663,
|
| 942 |
+
"eval_runtime": 170.3858,
|
| 943 |
+
"eval_samples_per_second": 6.139,
|
| 944 |
+
"eval_steps_per_second": 0.194,
|
| 945 |
+
"step": 150
|
| 946 |
+
},
|
| 947 |
+
{
|
| 948 |
+
"epoch": 0.51,
|
| 949 |
+
"learning_rate": 4.598166982655526e-06,
|
| 950 |
+
"loss": 0.6884,
|
| 951 |
+
"step": 151
|
| 952 |
+
},
|
| 953 |
+
{
|
| 954 |
+
"epoch": 0.51,
|
| 955 |
+
"learning_rate": 4.549086411723821e-06,
|
| 956 |
+
"loss": 0.5796,
|
| 957 |
+
"step": 152
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.52,
|
| 961 |
+
"learning_rate": 4.5e-06,
|
| 962 |
+
"loss": 0.5955,
|
| 963 |
+
"step": 153
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 0.52,
|
| 967 |
+
"learning_rate": 4.45091358827618e-06,
|
| 968 |
+
"loss": 0.5985,
|
| 969 |
+
"step": 154
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.52,
|
| 973 |
+
"learning_rate": 4.401833017344475e-06,
|
| 974 |
+
"loss": 0.451,
|
| 975 |
+
"step": 155
|
| 976 |
+
},
|
| 977 |
+
{
|
| 978 |
+
"epoch": 0.53,
|
| 979 |
+
"learning_rate": 4.352764127302008e-06,
|
| 980 |
+
"loss": 0.7329,
|
| 981 |
+
"step": 156
|
| 982 |
+
},
|
| 983 |
+
{
|
| 984 |
+
"epoch": 0.53,
|
| 985 |
+
"learning_rate": 4.303712756855989e-06,
|
| 986 |
+
"loss": 0.6437,
|
| 987 |
+
"step": 157
|
| 988 |
+
},
|
| 989 |
+
{
|
| 990 |
+
"epoch": 0.53,
|
| 991 |
+
"learning_rate": 4.254684742628971e-06,
|
| 992 |
+
"loss": 0.4884,
|
| 993 |
+
"step": 158
|
| 994 |
+
},
|
| 995 |
+
{
|
| 996 |
+
"epoch": 0.54,
|
| 997 |
+
"learning_rate": 4.205685918464356e-06,
|
| 998 |
+
"loss": 0.5665,
|
| 999 |
+
"step": 159
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.54,
|
| 1003 |
+
"learning_rate": 4.156722114732214e-06,
|
| 1004 |
+
"loss": 0.5799,
|
| 1005 |
+
"step": 160
|
| 1006 |
+
},
|
| 1007 |
+
{
|
| 1008 |
+
"epoch": 0.54,
|
| 1009 |
+
"learning_rate": 4.107799157635538e-06,
|
| 1010 |
+
"loss": 0.6255,
|
| 1011 |
+
"step": 161
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.55,
|
| 1015 |
+
"learning_rate": 4.058922868516977e-06,
|
| 1016 |
+
"loss": 0.6124,
|
| 1017 |
+
"step": 162
|
| 1018 |
+
},
|
| 1019 |
+
{
|
| 1020 |
+
"epoch": 0.55,
|
| 1021 |
+
"learning_rate": 4.01009906316616e-06,
|
| 1022 |
+
"loss": 0.5434,
|
| 1023 |
+
"step": 163
|
| 1024 |
+
},
|
| 1025 |
+
{
|
| 1026 |
+
"epoch": 0.55,
|
| 1027 |
+
"learning_rate": 3.96133355112767e-06,
|
| 1028 |
+
"loss": 0.565,
|
| 1029 |
+
"step": 164
|
| 1030 |
+
},
|
| 1031 |
+
{
|
| 1032 |
+
"epoch": 0.56,
|
| 1033 |
+
"learning_rate": 3.912632135009769e-06,
|
| 1034 |
+
"loss": 0.4637,
|
| 1035 |
+
"step": 165
|
| 1036 |
+
},
|
| 1037 |
+
{
|
| 1038 |
+
"epoch": 0.56,
|
| 1039 |
+
"learning_rate": 3.8640006097939474e-06,
|
| 1040 |
+
"loss": 0.5655,
|
| 1041 |
+
"step": 166
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.56,
|
| 1045 |
+
"learning_rate": 3.815444762145375e-06,
|
| 1046 |
+
"loss": 0.6105,
|
| 1047 |
+
"step": 167
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"epoch": 0.57,
|
| 1051 |
+
"learning_rate": 3.7669703697243513e-06,
|
| 1052 |
+
"loss": 0.5689,
|
| 1053 |
+
"step": 168
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.57,
|
| 1057 |
+
"learning_rate": 3.718583200498814e-06,
|
| 1058 |
+
"loss": 0.6725,
|
| 1059 |
+
"step": 169
|
| 1060 |
+
},
|
| 1061 |
+
{
|
| 1062 |
+
"epoch": 0.57,
|
| 1063 |
+
"learning_rate": 3.6702890120580148e-06,
|
| 1064 |
+
"loss": 0.4064,
|
| 1065 |
+
"step": 170
|
| 1066 |
+
},
|
| 1067 |
+
{
|
| 1068 |
+
"epoch": 0.58,
|
| 1069 |
+
"learning_rate": 3.6220935509274233e-06,
|
| 1070 |
+
"loss": 0.4969,
|
| 1071 |
+
"step": 171
|
| 1072 |
+
},
|
| 1073 |
+
{
|
| 1074 |
+
"epoch": 0.58,
|
| 1075 |
+
"learning_rate": 3.5740025518849432e-06,
|
| 1076 |
+
"loss": 0.5846,
|
| 1077 |
+
"step": 172
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 0.58,
|
| 1081 |
+
"learning_rate": 3.5260217372785372e-06,
|
| 1082 |
+
"loss": 0.5228,
|
| 1083 |
+
"step": 173
|
| 1084 |
+
},
|
| 1085 |
+
{
|
| 1086 |
+
"epoch": 0.59,
|
| 1087 |
+
"learning_rate": 3.478156816345321e-06,
|
| 1088 |
+
"loss": 0.603,
|
| 1089 |
+
"step": 174
|
| 1090 |
+
},
|
| 1091 |
+
{
|
| 1092 |
+
"epoch": 0.59,
|
| 1093 |
+
"learning_rate": 3.4304134845322217e-06,
|
| 1094 |
+
"loss": 0.6142,
|
| 1095 |
+
"step": 175
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.59,
|
| 1099 |
+
"learning_rate": 3.3827974228182764e-06,
|
| 1100 |
+
"loss": 0.5525,
|
| 1101 |
+
"step": 176
|
| 1102 |
+
},
|
| 1103 |
+
{
|
| 1104 |
+
"epoch": 0.6,
|
| 1105 |
+
"learning_rate": 3.335314297038656e-06,
|
| 1106 |
+
"loss": 0.637,
|
| 1107 |
+
"step": 177
|
| 1108 |
+
},
|
| 1109 |
+
{
|
| 1110 |
+
"epoch": 0.6,
|
| 1111 |
+
"learning_rate": 3.287969757210483e-06,
|
| 1112 |
+
"loss": 0.4829,
|
| 1113 |
+
"step": 178
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 0.6,
|
| 1117 |
+
"learning_rate": 3.240769436860536e-06,
|
| 1118 |
+
"loss": 0.7065,
|
| 1119 |
+
"step": 179
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.61,
|
| 1123 |
+
"learning_rate": 3.1937189523549205e-06,
|
| 1124 |
+
"loss": 0.4831,
|
| 1125 |
+
"step": 180
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"epoch": 0.61,
|
| 1129 |
+
"learning_rate": 3.1468239022307714e-06,
|
| 1130 |
+
"loss": 0.535,
|
| 1131 |
+
"step": 181
|
| 1132 |
+
},
|
| 1133 |
+
{
|
| 1134 |
+
"epoch": 0.61,
|
| 1135 |
+
"learning_rate": 3.1000898665300915e-06,
|
| 1136 |
+
"loss": 0.5843,
|
| 1137 |
+
"step": 182
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.62,
|
| 1141 |
+
"learning_rate": 3.053522406135774e-06,
|
| 1142 |
+
"loss": 0.5178,
|
| 1143 |
+
"step": 183
|
| 1144 |
+
},
|
| 1145 |
+
{
|
| 1146 |
+
"epoch": 0.62,
|
| 1147 |
+
"learning_rate": 3.007127062109917e-06,
|
| 1148 |
+
"loss": 0.5917,
|
| 1149 |
+
"step": 184
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 0.62,
|
| 1153 |
+
"learning_rate": 2.9609093550344912e-06,
|
| 1154 |
+
"loss": 0.5379,
|
| 1155 |
+
"step": 185
|
| 1156 |
+
},
|
| 1157 |
+
{
|
| 1158 |
+
"epoch": 0.63,
|
| 1159 |
+
"learning_rate": 2.9148747843544492e-06,
|
| 1160 |
+
"loss": 0.6937,
|
| 1161 |
+
"step": 186
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.63,
|
| 1165 |
+
"learning_rate": 2.869028827723343e-06,
|
| 1166 |
+
"loss": 0.4999,
|
| 1167 |
+
"step": 187
|
| 1168 |
+
},
|
| 1169 |
+
{
|
| 1170 |
+
"epoch": 0.63,
|
| 1171 |
+
"learning_rate": 2.823376940351537e-06,
|
| 1172 |
+
"loss": 0.6532,
|
| 1173 |
+
"step": 188
|
| 1174 |
+
},
|
| 1175 |
+
{
|
| 1176 |
+
"epoch": 0.64,
|
| 1177 |
+
"learning_rate": 2.7779245543570964e-06,
|
| 1178 |
+
"loss": 0.4854,
|
| 1179 |
+
"step": 189
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.64,
|
| 1183 |
+
"learning_rate": 2.7326770781194174e-06,
|
| 1184 |
+
"loss": 0.54,
|
| 1185 |
+
"step": 190
|
| 1186 |
+
},
|
| 1187 |
+
{
|
| 1188 |
+
"epoch": 0.64,
|
| 1189 |
+
"learning_rate": 2.6876398956356833e-06,
|
| 1190 |
+
"loss": 0.4441,
|
| 1191 |
+
"step": 191
|
| 1192 |
+
},
|
| 1193 |
+
{
|
| 1194 |
+
"epoch": 0.65,
|
| 1195 |
+
"learning_rate": 2.642818365880224e-06,
|
| 1196 |
+
"loss": 0.551,
|
| 1197 |
+
"step": 192
|
| 1198 |
+
},
|
| 1199 |
+
{
|
| 1200 |
+
"epoch": 0.65,
|
| 1201 |
+
"learning_rate": 2.5982178221668532e-06,
|
| 1202 |
+
"loss": 0.6079,
|
| 1203 |
+
"step": 193
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.65,
|
| 1207 |
+
"learning_rate": 2.5538435715142517e-06,
|
| 1208 |
+
"loss": 0.5439,
|
| 1209 |
+
"step": 194
|
| 1210 |
+
},
|
| 1211 |
+
{
|
| 1212 |
+
"epoch": 0.66,
|
| 1213 |
+
"learning_rate": 2.5097008940144952e-06,
|
| 1214 |
+
"loss": 0.6502,
|
| 1215 |
+
"step": 195
|
| 1216 |
+
},
|
| 1217 |
+
{
|
| 1218 |
+
"epoch": 0.66,
|
| 1219 |
+
"learning_rate": 2.4657950422047615e-06,
|
| 1220 |
+
"loss": 0.5396,
|
| 1221 |
+
"step": 196
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.66,
|
| 1225 |
+
"learning_rate": 2.4221312404423484e-06,
|
| 1226 |
+
"loss": 0.6481,
|
| 1227 |
+
"step": 197
|
| 1228 |
+
},
|
| 1229 |
+
{
|
| 1230 |
+
"epoch": 0.67,
|
| 1231 |
+
"learning_rate": 2.3787146842830103e-06,
|
| 1232 |
+
"loss": 0.5903,
|
| 1233 |
+
"step": 198
|
| 1234 |
+
},
|
| 1235 |
+
{
|
| 1236 |
+
"epoch": 0.67,
|
| 1237 |
+
"learning_rate": 2.3355505398627564e-06,
|
| 1238 |
+
"loss": 0.5244,
|
| 1239 |
+
"step": 199
|
| 1240 |
+
},
|
| 1241 |
+
{
|
| 1242 |
+
"epoch": 0.67,
|
| 1243 |
+
"learning_rate": 2.292643943283114e-06,
|
| 1244 |
+
"loss": 0.6796,
|
| 1245 |
+
"step": 200
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.68,
|
| 1249 |
+
"learning_rate": 2.250000000000001e-06,
|
| 1250 |
+
"loss": 0.6146,
|
| 1251 |
+
"step": 201
|
| 1252 |
+
},
|
| 1253 |
+
{
|
| 1254 |
+
"epoch": 0.68,
|
| 1255 |
+
"learning_rate": 2.207623784216212e-06,
|
| 1256 |
+
"loss": 0.5408,
|
| 1257 |
+
"step": 202
|
| 1258 |
+
},
|
| 1259 |
+
{
|
| 1260 |
+
"epoch": 0.68,
|
| 1261 |
+
"learning_rate": 2.1655203382776525e-06,
|
| 1262 |
+
"loss": 0.6249,
|
| 1263 |
+
"step": 203
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.69,
|
| 1267 |
+
"learning_rate": 2.123694672073344e-06,
|
| 1268 |
+
"loss": 0.5816,
|
| 1269 |
+
"step": 204
|
| 1270 |
+
},
|
| 1271 |
+
{
|
| 1272 |
+
"epoch": 0.69,
|
| 1273 |
+
"learning_rate": 2.082151762439292e-06,
|
| 1274 |
+
"loss": 0.4743,
|
| 1275 |
+
"step": 205
|
| 1276 |
+
},
|
| 1277 |
+
{
|
| 1278 |
+
"epoch": 0.69,
|
| 1279 |
+
"learning_rate": 2.040896552566305e-06,
|
| 1280 |
+
"loss": 0.6727,
|
| 1281 |
+
"step": 206
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"epoch": 0.7,
|
| 1285 |
+
"learning_rate": 1.999933951411791e-06,
|
| 1286 |
+
"loss": 0.4752,
|
| 1287 |
+
"step": 207
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.7,
|
| 1291 |
+
"learning_rate": 1.9592688331156483e-06,
|
| 1292 |
+
"loss": 0.5629,
|
| 1293 |
+
"step": 208
|
| 1294 |
+
},
|
| 1295 |
+
{
|
| 1296 |
+
"epoch": 0.7,
|
| 1297 |
+
"learning_rate": 1.9189060364202938e-06,
|
| 1298 |
+
"loss": 0.4636,
|
| 1299 |
+
"step": 209
|
| 1300 |
+
},
|
| 1301 |
+
{
|
| 1302 |
+
"epoch": 0.71,
|
| 1303 |
+
"learning_rate": 1.8788503640948908e-06,
|
| 1304 |
+
"loss": 0.5113,
|
| 1305 |
+
"step": 210
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.71,
|
| 1309 |
+
"learning_rate": 1.8391065823638805e-06,
|
| 1310 |
+
"loss": 0.4424,
|
| 1311 |
+
"step": 211
|
| 1312 |
+
},
|
| 1313 |
+
{
|
| 1314 |
+
"epoch": 0.71,
|
| 1315 |
+
"learning_rate": 1.7996794203398362e-06,
|
| 1316 |
+
"loss": 0.4023,
|
| 1317 |
+
"step": 212
|
| 1318 |
+
},
|
| 1319 |
+
{
|
| 1320 |
+
"epoch": 0.72,
|
| 1321 |
+
"learning_rate": 1.760573569460757e-06,
|
| 1322 |
+
"loss": 0.5816,
|
| 1323 |
+
"step": 213
|
| 1324 |
+
},
|
| 1325 |
+
{
|
| 1326 |
+
"epoch": 0.72,
|
| 1327 |
+
"learning_rate": 1.7217936829318283e-06,
|
| 1328 |
+
"loss": 0.5428,
|
| 1329 |
+
"step": 214
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.72,
|
| 1333 |
+
"learning_rate": 1.6833443751717342e-06,
|
| 1334 |
+
"loss": 0.4079,
|
| 1335 |
+
"step": 215
|
| 1336 |
+
},
|
| 1337 |
+
{
|
| 1338 |
+
"epoch": 0.73,
|
| 1339 |
+
"learning_rate": 1.6452302212635958e-06,
|
| 1340 |
+
"loss": 0.614,
|
| 1341 |
+
"step": 216
|
| 1342 |
+
},
|
| 1343 |
+
{
|
| 1344 |
+
"epoch": 0.73,
|
| 1345 |
+
"learning_rate": 1.6074557564105728e-06,
|
| 1346 |
+
"loss": 0.3744,
|
| 1347 |
+
"step": 217
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.73,
|
| 1351 |
+
"learning_rate": 1.5700254753962297e-06,
|
| 1352 |
+
"loss": 0.7146,
|
| 1353 |
+
"step": 218
|
| 1354 |
+
},
|
| 1355 |
+
{
|
| 1356 |
+
"epoch": 0.74,
|
| 1357 |
+
"learning_rate": 1.5329438320496903e-06,
|
| 1358 |
+
"loss": 0.4597,
|
| 1359 |
+
"step": 219
|
| 1360 |
+
},
|
| 1361 |
+
{
|
| 1362 |
+
"epoch": 0.74,
|
| 1363 |
+
"learning_rate": 1.4962152387156875e-06,
|
| 1364 |
+
"loss": 0.5789,
|
| 1365 |
+
"step": 220
|
| 1366 |
+
},
|
| 1367 |
+
{
|
| 1368 |
+
"epoch": 0.74,
|
| 1369 |
+
"learning_rate": 1.459844065729529e-06,
|
| 1370 |
+
"loss": 0.5392,
|
| 1371 |
+
"step": 221
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.75,
|
| 1375 |
+
"learning_rate": 1.423834640897079e-06,
|
| 1376 |
+
"loss": 0.6789,
|
| 1377 |
+
"step": 222
|
| 1378 |
+
},
|
| 1379 |
+
{
|
| 1380 |
+
"epoch": 0.75,
|
| 1381 |
+
"learning_rate": 1.3881912489797881e-06,
|
| 1382 |
+
"loss": 0.6218,
|
| 1383 |
+
"step": 223
|
| 1384 |
+
},
|
| 1385 |
+
{
|
| 1386 |
+
"epoch": 0.75,
|
| 1387 |
+
"learning_rate": 1.3529181311848478e-06,
|
| 1388 |
+
"loss": 0.5378,
|
| 1389 |
+
"step": 224
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.76,
|
| 1393 |
+
"learning_rate": 1.3180194846605365e-06,
|
| 1394 |
+
"loss": 0.4189,
|
| 1395 |
+
"step": 225
|
| 1396 |
+
},
|
| 1397 |
+
{
|
| 1398 |
+
"epoch": 0.76,
|
| 1399 |
+
"eval_accuracy": 0.8321450379495904,
|
| 1400 |
+
"eval_accuracy_<|content|>": 1.0,
|
| 1401 |
+
"eval_accuracy_<|from|>": 0.9946428571428572,
|
| 1402 |
+
"eval_accuracy_<|recipient|>": 1.0,
|
| 1403 |
+
"eval_accuracy_<|stop|>": 0.9150049035632559,
|
| 1404 |
+
"eval_accuracy_total_num_<|content|>": 3634,
|
| 1405 |
+
"eval_accuracy_total_num_<|from|>": 560,
|
| 1406 |
+
"eval_accuracy_total_num_<|recipient|>": 560,
|
| 1407 |
+
"eval_accuracy_total_num_<|stop|>": 3059,
|
| 1408 |
+
"eval_loss": 0.5402337908744812,
|
| 1409 |
+
"eval_perplexity": 1.0533657385611068,
|
| 1410 |
+
"eval_runtime": 170.1194,
|
| 1411 |
+
"eval_samples_per_second": 6.149,
|
| 1412 |
+
"eval_steps_per_second": 0.194,
|
| 1413 |
+
"step": 225
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.76,
|
| 1417 |
+
"learning_rate": 1.2834994619967923e-06,
|
| 1418 |
+
"loss": 0.4984,
|
| 1419 |
+
"step": 226
|
| 1420 |
+
},
|
| 1421 |
+
{
|
| 1422 |
+
"epoch": 0.76,
|
| 1423 |
+
"learning_rate": 1.2493621707311002e-06,
|
| 1424 |
+
"loss": 0.4659,
|
| 1425 |
+
"step": 227
|
| 1426 |
+
},
|
| 1427 |
+
{
|
| 1428 |
+
"epoch": 0.77,
|
| 1429 |
+
"learning_rate": 1.2156116728597408e-06,
|
| 1430 |
+
"loss": 0.5902,
|
| 1431 |
+
"step": 228
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.77,
|
| 1435 |
+
"learning_rate": 1.1822519843544422e-06,
|
| 1436 |
+
"loss": 0.6117,
|
| 1437 |
+
"step": 229
|
| 1438 |
+
},
|
| 1439 |
+
{
|
| 1440 |
+
"epoch": 0.77,
|
| 1441 |
+
"learning_rate": 1.1492870746845319e-06,
|
| 1442 |
+
"loss": 0.6365,
|
| 1443 |
+
"step": 230
|
| 1444 |
+
},
|
| 1445 |
+
{
|
| 1446 |
+
"epoch": 0.78,
|
| 1447 |
+
"learning_rate": 1.1167208663446024e-06,
|
| 1448 |
+
"loss": 0.5319,
|
| 1449 |
+
"step": 231
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.78,
|
| 1453 |
+
"learning_rate": 1.0845572343877717e-06,
|
| 1454 |
+
"loss": 0.5895,
|
| 1455 |
+
"step": 232
|
| 1456 |
+
},
|
| 1457 |
+
{
|
| 1458 |
+
"epoch": 0.78,
|
| 1459 |
+
"learning_rate": 1.0528000059645994e-06,
|
| 1460 |
+
"loss": 0.5318,
|
| 1461 |
+
"step": 233
|
| 1462 |
+
},
|
| 1463 |
+
{
|
| 1464 |
+
"epoch": 0.79,
|
| 1465 |
+
"learning_rate": 1.0214529598676836e-06,
|
| 1466 |
+
"loss": 0.6035,
|
| 1467 |
+
"step": 234
|
| 1468 |
+
},
|
| 1469 |
+
{
|
| 1470 |
+
"epoch": 0.79,
|
| 1471 |
+
"learning_rate": 9.905198260820328e-07,
|
| 1472 |
+
"loss": 0.5598,
|
| 1473 |
+
"step": 235
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.79,
|
| 1477 |
+
"learning_rate": 9.600042853412235e-07,
|
| 1478 |
+
"loss": 0.5064,
|
| 1479 |
+
"step": 236
|
| 1480 |
+
},
|
| 1481 |
+
{
|
| 1482 |
+
"epoch": 0.8,
|
| 1483 |
+
"learning_rate": 9.299099686894423e-07,
|
| 1484 |
+
"loss": 0.6721,
|
| 1485 |
+
"step": 237
|
| 1486 |
+
},
|
| 1487 |
+
{
|
| 1488 |
+
"epoch": 0.8,
|
| 1489 |
+
"learning_rate": 9.002404570494167e-07,
|
| 1490 |
+
"loss": 0.5706,
|
| 1491 |
+
"step": 238
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.8,
|
| 1495 |
+
"learning_rate": 8.709992807963281e-07,
|
| 1496 |
+
"loss": 0.6527,
|
| 1497 |
+
"step": 239
|
| 1498 |
+
},
|
| 1499 |
+
{
|
| 1500 |
+
"epoch": 0.81,
|
| 1501 |
+
"learning_rate": 8.42189919337732e-07,
|
| 1502 |
+
"loss": 0.6001,
|
| 1503 |
+
"step": 240
|
| 1504 |
+
},
|
| 1505 |
+
{
|
| 1506 |
+
"epoch": 0.81,
|
| 1507 |
+
"learning_rate": 8.138158006995364e-07,
|
| 1508 |
+
"loss": 0.6725,
|
| 1509 |
+
"step": 241
|
| 1510 |
+
},
|
| 1511 |
+
{
|
| 1512 |
+
"epoch": 0.81,
|
| 1513 |
+
"learning_rate": 7.85880301118113e-07,
|
| 1514 |
+
"loss": 0.4701,
|
| 1515 |
+
"step": 242
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.82,
|
| 1519 |
+
"learning_rate": 7.58386744638546e-07,
|
| 1520 |
+
"loss": 0.5473,
|
| 1521 |
+
"step": 243
|
| 1522 |
+
},
|
| 1523 |
+
{
|
| 1524 |
+
"epoch": 0.82,
|
| 1525 |
+
"learning_rate": 7.313384027191149e-07,
|
| 1526 |
+
"loss": 0.5739,
|
| 1527 |
+
"step": 244
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"epoch": 0.82,
|
| 1531 |
+
"learning_rate": 7.047384938420153e-07,
|
| 1532 |
+
"loss": 0.367,
|
| 1533 |
+
"step": 245
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.83,
|
| 1537 |
+
"learning_rate": 6.785901831303956e-07,
|
| 1538 |
+
"loss": 0.4433,
|
| 1539 |
+
"step": 246
|
| 1540 |
+
},
|
| 1541 |
+
{
|
| 1542 |
+
"epoch": 0.83,
|
| 1543 |
+
"learning_rate": 6.528965819717413e-07,
|
| 1544 |
+
"loss": 0.4839,
|
| 1545 |
+
"step": 247
|
| 1546 |
+
},
|
| 1547 |
+
{
|
| 1548 |
+
"epoch": 0.84,
|
| 1549 |
+
"learning_rate": 6.27660747647645e-07,
|
| 1550 |
+
"loss": 0.6045,
|
| 1551 |
+
"step": 248
|
| 1552 |
+
},
|
| 1553 |
+
{
|
| 1554 |
+
"epoch": 0.84,
|
| 1555 |
+
"learning_rate": 6.028856829700259e-07,
|
| 1556 |
+
"loss": 0.565,
|
| 1557 |
+
"step": 249
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.84,
|
| 1561 |
+
"learning_rate": 5.785743359238243e-07,
|
| 1562 |
+
"loss": 0.5618,
|
| 1563 |
+
"step": 250
|
| 1564 |
+
},
|
| 1565 |
+
{
|
| 1566 |
+
"epoch": 0.85,
|
| 1567 |
+
"learning_rate": 5.547295993162155e-07,
|
| 1568 |
+
"loss": 0.397,
|
| 1569 |
+
"step": 251
|
| 1570 |
+
},
|
| 1571 |
+
{
|
| 1572 |
+
"epoch": 0.85,
|
| 1573 |
+
"learning_rate": 5.313543104324028e-07,
|
| 1574 |
+
"loss": 0.5715,
|
| 1575 |
+
"step": 252
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.85,
|
| 1579 |
+
"learning_rate": 5.084512506980023e-07,
|
| 1580 |
+
"loss": 0.5927,
|
| 1581 |
+
"step": 253
|
| 1582 |
+
},
|
| 1583 |
+
{
|
| 1584 |
+
"epoch": 0.86,
|
| 1585 |
+
"learning_rate": 4.860231453480866e-07,
|
| 1586 |
+
"loss": 0.4835,
|
| 1587 |
+
"step": 254
|
| 1588 |
+
},
|
| 1589 |
+
{
|
| 1590 |
+
"epoch": 0.86,
|
| 1591 |
+
"learning_rate": 4.640726631029029e-07,
|
| 1592 |
+
"loss": 0.5396,
|
| 1593 |
+
"step": 255
|
| 1594 |
+
},
|
| 1595 |
+
{
|
| 1596 |
+
"epoch": 0.86,
|
| 1597 |
+
"learning_rate": 4.426024158503282e-07,
|
| 1598 |
+
"loss": 0.4446,
|
| 1599 |
+
"step": 256
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.87,
|
| 1603 |
+
"learning_rate": 4.216149583350753e-07,
|
| 1604 |
+
"loss": 0.5833,
|
| 1605 |
+
"step": 257
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"epoch": 0.87,
|
| 1609 |
+
"learning_rate": 4.0111278785470846e-07,
|
| 1610 |
+
"loss": 0.478,
|
| 1611 |
+
"step": 258
|
| 1612 |
+
},
|
| 1613 |
+
{
|
| 1614 |
+
"epoch": 0.87,
|
| 1615 |
+
"learning_rate": 3.8109834396248805e-07,
|
| 1616 |
+
"loss": 0.5802,
|
| 1617 |
+
"step": 259
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.88,
|
| 1621 |
+
"learning_rate": 3.6157400817708485e-07,
|
| 1622 |
+
"loss": 0.4553,
|
| 1623 |
+
"step": 260
|
| 1624 |
+
},
|
| 1625 |
+
{
|
| 1626 |
+
"epoch": 0.88,
|
| 1627 |
+
"learning_rate": 3.425421036992097e-07,
|
| 1628 |
+
"loss": 0.5408,
|
| 1629 |
+
"step": 261
|
| 1630 |
+
},
|
| 1631 |
+
{
|
| 1632 |
+
"epoch": 0.88,
|
| 1633 |
+
"learning_rate": 3.2400489513517e-07,
|
| 1634 |
+
"loss": 0.4659,
|
| 1635 |
+
"step": 262
|
| 1636 |
+
},
|
| 1637 |
+
{
|
| 1638 |
+
"epoch": 0.89,
|
| 1639 |
+
"learning_rate": 3.0596458822740705e-07,
|
| 1640 |
+
"loss": 0.3709,
|
| 1641 |
+
"step": 263
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.89,
|
| 1645 |
+
"learning_rate": 2.884233295920351e-07,
|
| 1646 |
+
"loss": 0.3811,
|
| 1647 |
+
"step": 264
|
| 1648 |
+
},
|
| 1649 |
+
{
|
| 1650 |
+
"epoch": 0.89,
|
| 1651 |
+
"learning_rate": 2.713832064634126e-07,
|
| 1652 |
+
"loss": 0.5523,
|
| 1653 |
+
"step": 265
|
| 1654 |
+
},
|
| 1655 |
+
{
|
| 1656 |
+
"epoch": 0.9,
|
| 1657 |
+
"learning_rate": 2.548462464457865e-07,
|
| 1658 |
+
"loss": 0.5376,
|
| 1659 |
+
"step": 266
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.9,
|
| 1663 |
+
"learning_rate": 2.388144172720249e-07,
|
| 1664 |
+
"loss": 0.5279,
|
| 1665 |
+
"step": 267
|
| 1666 |
+
},
|
| 1667 |
+
{
|
| 1668 |
+
"epoch": 0.9,
|
| 1669 |
+
"learning_rate": 2.23289626569475e-07,
|
| 1670 |
+
"loss": 0.5563,
|
| 1671 |
+
"step": 268
|
| 1672 |
+
},
|
| 1673 |
+
{
|
| 1674 |
+
"epoch": 0.91,
|
| 1675 |
+
"learning_rate": 2.082737216329793e-07,
|
| 1676 |
+
"loss": 0.451,
|
| 1677 |
+
"step": 269
|
| 1678 |
+
},
|
| 1679 |
+
{
|
| 1680 |
+
"epoch": 0.91,
|
| 1681 |
+
"learning_rate": 1.937684892050603e-07,
|
| 1682 |
+
"loss": 0.6432,
|
| 1683 |
+
"step": 270
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.91,
|
| 1687 |
+
"learning_rate": 1.797756552633213e-07,
|
| 1688 |
+
"loss": 0.4673,
|
| 1689 |
+
"step": 271
|
| 1690 |
+
},
|
| 1691 |
+
{
|
| 1692 |
+
"epoch": 0.92,
|
| 1693 |
+
"learning_rate": 1.6629688481506783e-07,
|
| 1694 |
+
"loss": 0.5042,
|
| 1695 |
+
"step": 272
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"epoch": 0.92,
|
| 1699 |
+
"learning_rate": 1.533337816991931e-07,
|
| 1700 |
+
"loss": 0.7103,
|
| 1701 |
+
"step": 273
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.92,
|
| 1705 |
+
"learning_rate": 1.408878883953311e-07,
|
| 1706 |
+
"loss": 0.4237,
|
| 1707 |
+
"step": 274
|
| 1708 |
+
},
|
| 1709 |
+
{
|
| 1710 |
+
"epoch": 0.93,
|
| 1711 |
+
"learning_rate": 1.2896068584032355e-07,
|
| 1712 |
+
"loss": 0.4941,
|
| 1713 |
+
"step": 275
|
| 1714 |
+
},
|
| 1715 |
+
{
|
| 1716 |
+
"epoch": 0.93,
|
| 1717 |
+
"learning_rate": 1.1755359325199866e-07,
|
| 1718 |
+
"loss": 0.6746,
|
| 1719 |
+
"step": 276
|
| 1720 |
+
},
|
| 1721 |
+
{
|
| 1722 |
+
"epoch": 0.93,
|
| 1723 |
+
"learning_rate": 1.0666796796029987e-07,
|
| 1724 |
+
"loss": 0.5323,
|
| 1725 |
+
"step": 277
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.94,
|
| 1729 |
+
"learning_rate": 9.630510524577751e-08,
|
| 1730 |
+
"loss": 0.5387,
|
| 1731 |
+
"step": 278
|
| 1732 |
+
},
|
| 1733 |
+
{
|
| 1734 |
+
"epoch": 0.94,
|
| 1735 |
+
"learning_rate": 8.646623818546307e-08,
|
| 1736 |
+
"loss": 0.5481,
|
| 1737 |
+
"step": 279
|
| 1738 |
+
},
|
| 1739 |
+
{
|
| 1740 |
+
"epoch": 0.94,
|
| 1741 |
+
"learning_rate": 7.715253750614503e-08,
|
| 1742 |
+
"loss": 0.5632,
|
| 1743 |
+
"step": 280
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.95,
|
| 1747 |
+
"learning_rate": 6.836511144506392e-08,
|
| 1748 |
+
"loss": 0.6036,
|
| 1749 |
+
"step": 281
|
| 1750 |
+
},
|
| 1751 |
+
{
|
| 1752 |
+
"epoch": 0.95,
|
| 1753 |
+
"learning_rate": 6.01050056180446e-08,
|
| 1754 |
+
"loss": 0.4902,
|
| 1755 |
+
"step": 282
|
| 1756 |
+
},
|
| 1757 |
+
{
|
| 1758 |
+
"epoch": 0.95,
|
| 1759 |
+
"learning_rate": 5.237320289507702e-08,
|
| 1760 |
+
"loss": 0.4684,
|
| 1761 |
+
"step": 283
|
| 1762 |
+
},
|
| 1763 |
+
{
|
| 1764 |
+
"epoch": 0.96,
|
| 1765 |
+
"learning_rate": 4.517062328336458e-08,
|
| 1766 |
+
"loss": 0.525,
|
| 1767 |
+
"step": 284
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.96,
|
| 1771 |
+
"learning_rate": 3.849812381785328e-08,
|
| 1772 |
+
"loss": 0.5128,
|
| 1773 |
+
"step": 285
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"epoch": 0.96,
|
| 1777 |
+
"learning_rate": 3.235649845925231e-08,
|
| 1778 |
+
"loss": 0.7175,
|
| 1779 |
+
"step": 286
|
| 1780 |
+
},
|
| 1781 |
+
{
|
| 1782 |
+
"epoch": 0.97,
|
| 1783 |
+
"learning_rate": 2.674647799956159e-08,
|
| 1784 |
+
"loss": 0.5206,
|
| 1785 |
+
"step": 287
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.97,
|
| 1789 |
+
"learning_rate": 2.166872997511432e-08,
|
| 1790 |
+
"loss": 0.6999,
|
| 1791 |
+
"step": 288
|
| 1792 |
+
},
|
| 1793 |
+
{
|
| 1794 |
+
"epoch": 0.97,
|
| 1795 |
+
"learning_rate": 1.7123858587145047e-08,
|
| 1796 |
+
"loss": 0.4856,
|
| 1797 |
+
"step": 289
|
| 1798 |
+
},
|
| 1799 |
+
{
|
| 1800 |
+
"epoch": 0.98,
|
| 1801 |
+
"learning_rate": 1.3112404629900154e-08,
|
| 1802 |
+
"loss": 0.6217,
|
| 1803 |
+
"step": 290
|
| 1804 |
+
},
|
| 1805 |
+
{
|
| 1806 |
+
"epoch": 0.98,
|
| 1807 |
+
"learning_rate": 9.634845426284344e-09,
|
| 1808 |
+
"loss": 0.6083,
|
| 1809 |
+
"step": 291
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.98,
|
| 1813 |
+
"learning_rate": 6.691594771066067e-09,
|
| 1814 |
+
"loss": 0.6078,
|
| 1815 |
+
"step": 292
|
| 1816 |
+
},
|
| 1817 |
+
{
|
| 1818 |
+
"epoch": 0.99,
|
| 1819 |
+
"learning_rate": 4.283002881639908e-09,
|
| 1820 |
+
"loss": 0.5348,
|
| 1821 |
+
"step": 293
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.99,
|
| 1825 |
+
"learning_rate": 2.4093563563544198e-09,
|
| 1826 |
+
"loss": 0.5764,
|
| 1827 |
+
"step": 294
|
| 1828 |
+
},
|
| 1829 |
+
{
|
| 1830 |
+
"epoch": 0.99,
|
| 1831 |
+
"learning_rate": 1.070878140408904e-09,
|
| 1832 |
+
"loss": 0.5528,
|
| 1833 |
+
"step": 295
|
| 1834 |
+
},
|
| 1835 |
+
{
|
| 1836 |
+
"epoch": 1.0,
|
| 1837 |
+
"learning_rate": 2.6772749932613136e-10,
|
| 1838 |
+
"loss": 0.6354,
|
| 1839 |
+
"step": 296
|
| 1840 |
+
},
|
| 1841 |
+
{
|
| 1842 |
+
"epoch": 1.0,
|
| 1843 |
+
"learning_rate": 0.0,
|
| 1844 |
+
"loss": 0.3309,
|
| 1845 |
+
"step": 297
|
| 1846 |
+
},
|
| 1847 |
+
{
|
| 1848 |
+
"epoch": 1.0,
|
| 1849 |
+
"step": 297,
|
| 1850 |
+
"total_flos": 124371515473920.0,
|
| 1851 |
+
"train_loss": 0.6121062839071357,
|
| 1852 |
+
"train_runtime": 9946.9361,
|
| 1853 |
+
"train_samples_per_second": 0.953,
|
| 1854 |
+
"train_steps_per_second": 0.03
|
| 1855 |
+
}
|
| 1856 |
+
],
|
| 1857 |
+
"logging_steps": 1.0,
|
| 1858 |
+
"max_steps": 297,
|
| 1859 |
+
"num_train_epochs": 1,
|
| 1860 |
+
"save_steps": 200.0,
|
| 1861 |
+
"total_flos": 124371515473920.0,
|
| 1862 |
+
"trial_name": null,
|
| 1863 |
+
"trial_params": null
|
| 1864 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ed59c28d192f0ac9f68a71f810521ca307c1688abab6a7a35c1eaf72643b09a
|
| 3 |
+
size 5179
|