Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- llama3-os-121/README.md +91 -0
- llama3-os-121/all_results.json +12 -0
- llama3-os-121/chat_template.jinja +109 -0
- llama3-os-121/config.json +36 -0
- llama3-os-121/eval_results.json +7 -0
- llama3-os-121/generation_config.json +14 -0
- llama3-os-121/model-00001-of-00004.safetensors +3 -0
- llama3-os-121/model-00002-of-00004.safetensors +3 -0
- llama3-os-121/model-00003-of-00004.safetensors +3 -0
- llama3-os-121/model-00004-of-00004.safetensors +3 -0
- llama3-os-121/model.safetensors.index.json +299 -0
- llama3-os-121/runs/Jan21_17-17-52_hgx001/events.out.tfevents.1768987207.hgx001.1602084.0 +3 -0
- llama3-os-121/runs/Jan21_17-17-52_hgx001/events.out.tfevents.1768994033.hgx001.1602084.1 +3 -0
- llama3-os-121/special_tokens_map.json +26 -0
- llama3-os-121/tokenizer.json +3 -0
- llama3-os-121/tokenizer_config.json +2068 -0
- llama3-os-121/train_results.json +8 -0
- llama3-os-121/trainer_log.jsonl +160 -0
- llama3-os-121/trainer_state.json +1182 -0
- llama3-os-121/training_args.bin +3 -0
- llama3-os-121/training_eval_loss.png +0 -0
- llama3-os-121/training_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -53,3 +53,4 @@ qwen2-gob-plan-119/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
| 53 |
llama3-ob-plan-120-ckt-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 54 |
llama3-ob-plan-120-ckt-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
qwen2-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 53 |
llama3-ob-plan-120-ckt-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 54 |
llama3-ob-plan-120-ckt-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 55 |
qwen2-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
llama3-os-121/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
llama3-os-121/README.md
ADDED
|
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: meta-llama/Llama-3.1-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: llama3-os-121
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# llama3-os-121
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/ceph/home/muhan01/huggingfacemodels/Meta-Llama-3.1-8B-Instruct](https://huggingface.co//ceph/home/muhan01/huggingfacemodels/Meta-Llama-3.1-8B-Instruct) on the osgenesis_sft dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.4377
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 1
|
| 42 |
+
- eval_batch_size: 1
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 4
|
| 46 |
+
- gradient_accumulation_steps: 4
|
| 47 |
+
- total_train_batch_size: 16
|
| 48 |
+
- total_eval_batch_size: 4
|
| 49 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 3.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.5324 | 0.1124 | 50 | 0.4907 |
|
| 59 |
+
| 0.5193 | 0.2247 | 100 | 0.4939 |
|
| 60 |
+
| 0.541 | 0.3371 | 150 | 0.5116 |
|
| 61 |
+
| 0.5009 | 0.4494 | 200 | 0.4971 |
|
| 62 |
+
| 0.4856 | 0.5618 | 250 | 0.4789 |
|
| 63 |
+
| 0.4855 | 0.6742 | 300 | 0.4701 |
|
| 64 |
+
| 0.4586 | 0.7865 | 350 | 0.4575 |
|
| 65 |
+
| 0.4786 | 0.8989 | 400 | 0.4472 |
|
| 66 |
+
| 0.39 | 1.0112 | 450 | 0.4302 |
|
| 67 |
+
| 0.3046 | 1.1236 | 500 | 0.4396 |
|
| 68 |
+
| 0.2974 | 1.2360 | 550 | 0.4299 |
|
| 69 |
+
| 0.2836 | 1.3483 | 600 | 0.4244 |
|
| 70 |
+
| 0.2679 | 1.4607 | 650 | 0.4181 |
|
| 71 |
+
| 0.3064 | 1.5730 | 700 | 0.4071 |
|
| 72 |
+
| 0.2741 | 1.6854 | 750 | 0.4025 |
|
| 73 |
+
| 0.2558 | 1.7978 | 800 | 0.3933 |
|
| 74 |
+
| 0.2701 | 1.9101 | 850 | 0.3824 |
|
| 75 |
+
| 0.1197 | 2.0225 | 900 | 0.4405 |
|
| 76 |
+
| 0.104 | 2.1348 | 950 | 0.4304 |
|
| 77 |
+
| 0.1085 | 2.2472 | 1000 | 0.4354 |
|
| 78 |
+
| 0.1004 | 2.3596 | 1050 | 0.4359 |
|
| 79 |
+
| 0.0944 | 2.4719 | 1100 | 0.4427 |
|
| 80 |
+
| 0.0984 | 2.5843 | 1150 | 0.4366 |
|
| 81 |
+
| 0.1041 | 2.6966 | 1200 | 0.4398 |
|
| 82 |
+
| 0.0951 | 2.8090 | 1250 | 0.4376 |
|
| 83 |
+
| 0.0804 | 2.9213 | 1300 | 0.4377 |
|
| 84 |
+
|
| 85 |
+
|
| 86 |
+
### Framework versions
|
| 87 |
+
|
| 88 |
+
- Transformers 4.57.1
|
| 89 |
+
- Pytorch 2.7.1+cu126
|
| 90 |
+
- Datasets 4.0.0
|
| 91 |
+
- Tokenizers 0.22.2-rc0
|
llama3-os-121/all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.43772968649864197,
|
| 4 |
+
"eval_runtime": 24.9509,
|
| 5 |
+
"eval_samples_per_second": 15.03,
|
| 6 |
+
"eval_steps_per_second": 3.767,
|
| 7 |
+
"total_flos": 57488427909120.0,
|
| 8 |
+
"train_loss": 0.29718317360467233,
|
| 9 |
+
"train_runtime": 6776.8475,
|
| 10 |
+
"train_samples_per_second": 3.152,
|
| 11 |
+
"train_steps_per_second": 0.197
|
| 12 |
+
}
|
llama3-os-121/chat_template.jinja
ADDED
|
@@ -0,0 +1,109 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{{- bos_token }}
|
| 2 |
+
{%- if custom_tools is defined %}
|
| 3 |
+
{%- set tools = custom_tools %}
|
| 4 |
+
{%- endif %}
|
| 5 |
+
{%- if not tools_in_user_message is defined %}
|
| 6 |
+
{%- set tools_in_user_message = true %}
|
| 7 |
+
{%- endif %}
|
| 8 |
+
{%- if not date_string is defined %}
|
| 9 |
+
{%- set date_string = "26 Jul 2024" %}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- if not tools is defined %}
|
| 12 |
+
{%- set tools = none %}
|
| 13 |
+
{%- endif %}
|
| 14 |
+
|
| 15 |
+
{#- This block extracts the system message, so we can slot it into the right place. #}
|
| 16 |
+
{%- if messages[0]['role'] == 'system' %}
|
| 17 |
+
{%- set system_message = messages[0]['content']|trim %}
|
| 18 |
+
{%- set messages = messages[1:] %}
|
| 19 |
+
{%- else %}
|
| 20 |
+
{%- set system_message = "" %}
|
| 21 |
+
{%- endif %}
|
| 22 |
+
|
| 23 |
+
{#- System message + builtin tools #}
|
| 24 |
+
{{- "<|start_header_id|>system<|end_header_id|>\n\n" }}
|
| 25 |
+
{%- if builtin_tools is defined or tools is not none %}
|
| 26 |
+
{{- "Environment: ipython\n" }}
|
| 27 |
+
{%- endif %}
|
| 28 |
+
{%- if builtin_tools is defined %}
|
| 29 |
+
{{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{{- "Cutting Knowledge Date: December 2023\n" }}
|
| 32 |
+
{{- "Today Date: " + date_string + "\n\n" }}
|
| 33 |
+
{%- if tools is not none and not tools_in_user_message %}
|
| 34 |
+
{{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }}
|
| 35 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 36 |
+
{{- "Do not use variables.\n\n" }}
|
| 37 |
+
{%- for t in tools %}
|
| 38 |
+
{{- t | tojson(indent=4) }}
|
| 39 |
+
{{- "\n\n" }}
|
| 40 |
+
{%- endfor %}
|
| 41 |
+
{%- endif %}
|
| 42 |
+
{{- system_message }}
|
| 43 |
+
{{- "<|eot_id|>" }}
|
| 44 |
+
|
| 45 |
+
{#- Custom tools are passed in a user message with some extra guidance #}
|
| 46 |
+
{%- if tools_in_user_message and not tools is none %}
|
| 47 |
+
{#- Extract the first user message so we can plug it in here #}
|
| 48 |
+
{%- if messages | length != 0 %}
|
| 49 |
+
{%- set first_user_message = messages[0]['content']|trim %}
|
| 50 |
+
{%- set messages = messages[1:] %}
|
| 51 |
+
{%- else %}
|
| 52 |
+
{{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }}
|
| 53 |
+
{%- endif %}
|
| 54 |
+
{{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}
|
| 55 |
+
{{- "Given the following functions, please respond with a JSON for a function call " }}
|
| 56 |
+
{{- "with its proper arguments that best answers the given prompt.\n\n" }}
|
| 57 |
+
{{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }}
|
| 58 |
+
{{- "Do not use variables.\n\n" }}
|
| 59 |
+
{%- for t in tools %}
|
| 60 |
+
{{- t | tojson(indent=4) }}
|
| 61 |
+
{{- "\n\n" }}
|
| 62 |
+
{%- endfor %}
|
| 63 |
+
{{- first_user_message + "<|eot_id|>"}}
|
| 64 |
+
{%- endif %}
|
| 65 |
+
|
| 66 |
+
{%- for message in messages %}
|
| 67 |
+
{%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}
|
| 68 |
+
{{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }}
|
| 69 |
+
{%- elif 'tool_calls' in message %}
|
| 70 |
+
{%- if not message.tool_calls|length == 1 %}
|
| 71 |
+
{{- raise_exception("This model only supports single tool-calls at once!") }}
|
| 72 |
+
{%- endif %}
|
| 73 |
+
{%- set tool_call = message.tool_calls[0].function %}
|
| 74 |
+
{%- if builtin_tools is defined and tool_call.name in builtin_tools %}
|
| 75 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 76 |
+
{{- "<|python_tag|>" + tool_call.name + ".call(" }}
|
| 77 |
+
{%- for arg_name, arg_val in tool_call.arguments | items %}
|
| 78 |
+
{{- arg_name + '="' + arg_val + '"' }}
|
| 79 |
+
{%- if not loop.last %}
|
| 80 |
+
{{- ", " }}
|
| 81 |
+
{%- endif %}
|
| 82 |
+
{%- endfor %}
|
| 83 |
+
{{- ")" }}
|
| 84 |
+
{%- else %}
|
| 85 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}
|
| 86 |
+
{{- '{"name": "' + tool_call.name + '", ' }}
|
| 87 |
+
{{- '"parameters": ' }}
|
| 88 |
+
{{- tool_call.arguments | tojson }}
|
| 89 |
+
{{- "}" }}
|
| 90 |
+
{%- endif %}
|
| 91 |
+
{%- if builtin_tools is defined %}
|
| 92 |
+
{#- This means we're in ipython mode #}
|
| 93 |
+
{{- "<|eom_id|>" }}
|
| 94 |
+
{%- else %}
|
| 95 |
+
{{- "<|eot_id|>" }}
|
| 96 |
+
{%- endif %}
|
| 97 |
+
{%- elif message.role == "tool" or message.role == "ipython" %}
|
| 98 |
+
{{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }}
|
| 99 |
+
{%- if message.content is mapping or message.content is iterable %}
|
| 100 |
+
{{- message.content | tojson }}
|
| 101 |
+
{%- else %}
|
| 102 |
+
{{- message.content }}
|
| 103 |
+
{%- endif %}
|
| 104 |
+
{{- "<|eot_id|>" }}
|
| 105 |
+
{%- endif %}
|
| 106 |
+
{%- endfor %}
|
| 107 |
+
{%- if add_generation_prompt %}
|
| 108 |
+
{{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}
|
| 109 |
+
{%- endif %}
|
llama3-os-121/config.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"dtype": "bfloat16",
|
| 9 |
+
"eos_token_id": 128009,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 4096,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 14336,
|
| 15 |
+
"max_position_embeddings": 131072,
|
| 16 |
+
"mlp_bias": false,
|
| 17 |
+
"model_type": "llama",
|
| 18 |
+
"num_attention_heads": 32,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"num_key_value_heads": 8,
|
| 21 |
+
"pad_token_id": 128009,
|
| 22 |
+
"pretraining_tp": 1,
|
| 23 |
+
"rms_norm_eps": 1e-05,
|
| 24 |
+
"rope_scaling": {
|
| 25 |
+
"factor": 8.0,
|
| 26 |
+
"high_freq_factor": 4.0,
|
| 27 |
+
"low_freq_factor": 1.0,
|
| 28 |
+
"original_max_position_embeddings": 8192,
|
| 29 |
+
"rope_type": "llama3"
|
| 30 |
+
},
|
| 31 |
+
"rope_theta": 500000.0,
|
| 32 |
+
"tie_word_embeddings": false,
|
| 33 |
+
"transformers_version": "4.57.1",
|
| 34 |
+
"use_cache": false,
|
| 35 |
+
"vocab_size": 128256
|
| 36 |
+
}
|
llama3-os-121/eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"eval_loss": 0.43772968649864197,
|
| 4 |
+
"eval_runtime": 24.9509,
|
| 5 |
+
"eval_samples_per_second": 15.03,
|
| 6 |
+
"eval_steps_per_second": 3.767
|
| 7 |
+
}
|
llama3-os-121/generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128009,
|
| 6 |
+
128001,
|
| 7 |
+
128008,
|
| 8 |
+
128009
|
| 9 |
+
],
|
| 10 |
+
"pad_token_id": 128009,
|
| 11 |
+
"temperature": 0.6,
|
| 12 |
+
"top_p": 0.9,
|
| 13 |
+
"transformers_version": "4.57.1"
|
| 14 |
+
}
|
llama3-os-121/model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b1ccc84fea7c7c81d366d79a605cbb4ba09fb6ce0610bda91c9077b7aa05f15
|
| 3 |
+
size 4976698672
|
llama3-os-121/model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d4ea2c12926d3f65f8176ab61ec544ce650a116b57d8368e5a57d1b12164b3c
|
| 3 |
+
size 4999802720
|
llama3-os-121/model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3e24f1aa43893d27d8d4c20be6872c4510494727d89d161ae90828ec3b7ff4df
|
| 3 |
+
size 4915916176
|
llama3-os-121/model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4319b29d318586f6d00154191c5b4699c87825b7a3cd804215f43fdeb9c4b9b7
|
| 3 |
+
size 1168138808
|
llama3-os-121/model.safetensors.index.json
ADDED
|
@@ -0,0 +1,299 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 266240,
|
| 4 |
+
"total_size": 16060522496
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 28 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 29 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 30 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 118 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 119 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 120 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 121 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 122 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 123 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 124 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 125 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 126 |
+
"model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 127 |
+
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 128 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 130 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 136 |
+
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 137 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 138 |
+
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 139 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 140 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 141 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 142 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 143 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 144 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 145 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 146 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 147 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 148 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 149 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 150 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 151 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 152 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 217 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 218 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 219 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 220 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 221 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 222 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 223 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 224 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 225 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 235 |
+
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 236 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 239 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 244 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 245 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 246 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 247 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 248 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 249 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 250 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 251 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 252 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 253 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 254 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 255 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 256 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 257 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 258 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 259 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 260 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 261 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 262 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 274 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 275 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 276 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 277 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 278 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 279 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 280 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 281 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 282 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 283 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 284 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 285 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 286 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 287 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 288 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 289 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 290 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 291 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 292 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 293 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 294 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 295 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 296 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 297 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 298 |
+
}
|
| 299 |
+
}
|
llama3-os-121/runs/Jan21_17-17-52_hgx001/events.out.tfevents.1768987207.hgx001.1602084.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c22fd8b824319f8ad30591d8d3d8539871b20c5fbaa78f049382af39365c848f
|
| 3 |
+
size 41145
|
llama3-os-121/runs/Jan21_17-17-52_hgx001/events.out.tfevents.1768994033.hgx001.1602084.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97f8ccda823b9773752bad6d01f1db59ecbfa4eeeba0077f9f58076267ec19d3
|
| 3 |
+
size 359
|
llama3-os-121/special_tokens_map.json
ADDED
|
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
{
|
| 4 |
+
"content": "<|eom_id|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false
|
| 9 |
+
}
|
| 10 |
+
],
|
| 11 |
+
"bos_token": {
|
| 12 |
+
"content": "<|begin_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false
|
| 17 |
+
},
|
| 18 |
+
"eos_token": {
|
| 19 |
+
"content": "<|eot_id|>",
|
| 20 |
+
"lstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"rstrip": false,
|
| 23 |
+
"single_word": false
|
| 24 |
+
},
|
| 25 |
+
"pad_token": "<|eot_id|>"
|
| 26 |
+
}
|
llama3-os-121/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
|
| 3 |
+
size 17209920
|
llama3-os-121/tokenizer_config.json
ADDED
|
@@ -0,0 +1,2068 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"128000": {
|
| 4 |
+
"content": "<|begin_of_text|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"128001": {
|
| 12 |
+
"content": "<|end_of_text|>",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"128002": {
|
| 20 |
+
"content": "<|reserved_special_token_0|>",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"128003": {
|
| 28 |
+
"content": "<|reserved_special_token_1|>",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128004": {
|
| 36 |
+
"content": "<|finetune_right_pad_id|>",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"128005": {
|
| 44 |
+
"content": "<|reserved_special_token_2|>",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"128006": {
|
| 52 |
+
"content": "<|start_header_id|>",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"128007": {
|
| 60 |
+
"content": "<|end_header_id|>",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"128008": {
|
| 68 |
+
"content": "<|eom_id|>",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"128009": {
|
| 76 |
+
"content": "<|eot_id|>",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"128010": {
|
| 84 |
+
"content": "<|python_tag|>",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"128011": {
|
| 92 |
+
"content": "<|reserved_special_token_3|>",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"128012": {
|
| 100 |
+
"content": "<|reserved_special_token_4|>",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"128013": {
|
| 108 |
+
"content": "<|reserved_special_token_5|>",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"128014": {
|
| 116 |
+
"content": "<|reserved_special_token_6|>",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"128015": {
|
| 124 |
+
"content": "<|reserved_special_token_7|>",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"128016": {
|
| 132 |
+
"content": "<|reserved_special_token_8|>",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"128017": {
|
| 140 |
+
"content": "<|reserved_special_token_9|>",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"128018": {
|
| 148 |
+
"content": "<|reserved_special_token_10|>",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"128019": {
|
| 156 |
+
"content": "<|reserved_special_token_11|>",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"128020": {
|
| 164 |
+
"content": "<|reserved_special_token_12|>",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"128021": {
|
| 172 |
+
"content": "<|reserved_special_token_13|>",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"128022": {
|
| 180 |
+
"content": "<|reserved_special_token_14|>",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"128023": {
|
| 188 |
+
"content": "<|reserved_special_token_15|>",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"128024": {
|
| 196 |
+
"content": "<|reserved_special_token_16|>",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"128025": {
|
| 204 |
+
"content": "<|reserved_special_token_17|>",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"128026": {
|
| 212 |
+
"content": "<|reserved_special_token_18|>",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"128027": {
|
| 220 |
+
"content": "<|reserved_special_token_19|>",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"128028": {
|
| 228 |
+
"content": "<|reserved_special_token_20|>",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"128029": {
|
| 236 |
+
"content": "<|reserved_special_token_21|>",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"128030": {
|
| 244 |
+
"content": "<|reserved_special_token_22|>",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"128031": {
|
| 252 |
+
"content": "<|reserved_special_token_23|>",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"128032": {
|
| 260 |
+
"content": "<|reserved_special_token_24|>",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"128033": {
|
| 268 |
+
"content": "<|reserved_special_token_25|>",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"128034": {
|
| 276 |
+
"content": "<|reserved_special_token_26|>",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"128035": {
|
| 284 |
+
"content": "<|reserved_special_token_27|>",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"128036": {
|
| 292 |
+
"content": "<|reserved_special_token_28|>",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"128037": {
|
| 300 |
+
"content": "<|reserved_special_token_29|>",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"128038": {
|
| 308 |
+
"content": "<|reserved_special_token_30|>",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"128039": {
|
| 316 |
+
"content": "<|reserved_special_token_31|>",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"128040": {
|
| 324 |
+
"content": "<|reserved_special_token_32|>",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"128041": {
|
| 332 |
+
"content": "<|reserved_special_token_33|>",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"128042": {
|
| 340 |
+
"content": "<|reserved_special_token_34|>",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"128043": {
|
| 348 |
+
"content": "<|reserved_special_token_35|>",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"128044": {
|
| 356 |
+
"content": "<|reserved_special_token_36|>",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"128045": {
|
| 364 |
+
"content": "<|reserved_special_token_37|>",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"128046": {
|
| 372 |
+
"content": "<|reserved_special_token_38|>",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"128047": {
|
| 380 |
+
"content": "<|reserved_special_token_39|>",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"128048": {
|
| 388 |
+
"content": "<|reserved_special_token_40|>",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"128049": {
|
| 396 |
+
"content": "<|reserved_special_token_41|>",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"128050": {
|
| 404 |
+
"content": "<|reserved_special_token_42|>",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"128051": {
|
| 412 |
+
"content": "<|reserved_special_token_43|>",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"128052": {
|
| 420 |
+
"content": "<|reserved_special_token_44|>",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"128053": {
|
| 428 |
+
"content": "<|reserved_special_token_45|>",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"128054": {
|
| 436 |
+
"content": "<|reserved_special_token_46|>",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"128055": {
|
| 444 |
+
"content": "<|reserved_special_token_47|>",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"128056": {
|
| 452 |
+
"content": "<|reserved_special_token_48|>",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"128057": {
|
| 460 |
+
"content": "<|reserved_special_token_49|>",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"128058": {
|
| 468 |
+
"content": "<|reserved_special_token_50|>",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"128059": {
|
| 476 |
+
"content": "<|reserved_special_token_51|>",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"128060": {
|
| 484 |
+
"content": "<|reserved_special_token_52|>",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"128061": {
|
| 492 |
+
"content": "<|reserved_special_token_53|>",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"128062": {
|
| 500 |
+
"content": "<|reserved_special_token_54|>",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"128063": {
|
| 508 |
+
"content": "<|reserved_special_token_55|>",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"128064": {
|
| 516 |
+
"content": "<|reserved_special_token_56|>",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"128065": {
|
| 524 |
+
"content": "<|reserved_special_token_57|>",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"128066": {
|
| 532 |
+
"content": "<|reserved_special_token_58|>",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"128067": {
|
| 540 |
+
"content": "<|reserved_special_token_59|>",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"128068": {
|
| 548 |
+
"content": "<|reserved_special_token_60|>",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"128069": {
|
| 556 |
+
"content": "<|reserved_special_token_61|>",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"128070": {
|
| 564 |
+
"content": "<|reserved_special_token_62|>",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"128071": {
|
| 572 |
+
"content": "<|reserved_special_token_63|>",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"128072": {
|
| 580 |
+
"content": "<|reserved_special_token_64|>",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"128073": {
|
| 588 |
+
"content": "<|reserved_special_token_65|>",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"128074": {
|
| 596 |
+
"content": "<|reserved_special_token_66|>",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"128075": {
|
| 604 |
+
"content": "<|reserved_special_token_67|>",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"128076": {
|
| 612 |
+
"content": "<|reserved_special_token_68|>",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"128077": {
|
| 620 |
+
"content": "<|reserved_special_token_69|>",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"128078": {
|
| 628 |
+
"content": "<|reserved_special_token_70|>",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"128079": {
|
| 636 |
+
"content": "<|reserved_special_token_71|>",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"128080": {
|
| 644 |
+
"content": "<|reserved_special_token_72|>",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"128081": {
|
| 652 |
+
"content": "<|reserved_special_token_73|>",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"128082": {
|
| 660 |
+
"content": "<|reserved_special_token_74|>",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"128083": {
|
| 668 |
+
"content": "<|reserved_special_token_75|>",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"128084": {
|
| 676 |
+
"content": "<|reserved_special_token_76|>",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"128085": {
|
| 684 |
+
"content": "<|reserved_special_token_77|>",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"128086": {
|
| 692 |
+
"content": "<|reserved_special_token_78|>",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"128087": {
|
| 700 |
+
"content": "<|reserved_special_token_79|>",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"128088": {
|
| 708 |
+
"content": "<|reserved_special_token_80|>",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"128089": {
|
| 716 |
+
"content": "<|reserved_special_token_81|>",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"128090": {
|
| 724 |
+
"content": "<|reserved_special_token_82|>",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"128091": {
|
| 732 |
+
"content": "<|reserved_special_token_83|>",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"128092": {
|
| 740 |
+
"content": "<|reserved_special_token_84|>",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"128093": {
|
| 748 |
+
"content": "<|reserved_special_token_85|>",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"128094": {
|
| 756 |
+
"content": "<|reserved_special_token_86|>",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"128095": {
|
| 764 |
+
"content": "<|reserved_special_token_87|>",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"128096": {
|
| 772 |
+
"content": "<|reserved_special_token_88|>",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"128097": {
|
| 780 |
+
"content": "<|reserved_special_token_89|>",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"128098": {
|
| 788 |
+
"content": "<|reserved_special_token_90|>",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"128099": {
|
| 796 |
+
"content": "<|reserved_special_token_91|>",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"128100": {
|
| 804 |
+
"content": "<|reserved_special_token_92|>",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"128101": {
|
| 812 |
+
"content": "<|reserved_special_token_93|>",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"128102": {
|
| 820 |
+
"content": "<|reserved_special_token_94|>",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"128103": {
|
| 828 |
+
"content": "<|reserved_special_token_95|>",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"128104": {
|
| 836 |
+
"content": "<|reserved_special_token_96|>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
"128105": {
|
| 844 |
+
"content": "<|reserved_special_token_97|>",
|
| 845 |
+
"lstrip": false,
|
| 846 |
+
"normalized": false,
|
| 847 |
+
"rstrip": false,
|
| 848 |
+
"single_word": false,
|
| 849 |
+
"special": true
|
| 850 |
+
},
|
| 851 |
+
"128106": {
|
| 852 |
+
"content": "<|reserved_special_token_98|>",
|
| 853 |
+
"lstrip": false,
|
| 854 |
+
"normalized": false,
|
| 855 |
+
"rstrip": false,
|
| 856 |
+
"single_word": false,
|
| 857 |
+
"special": true
|
| 858 |
+
},
|
| 859 |
+
"128107": {
|
| 860 |
+
"content": "<|reserved_special_token_99|>",
|
| 861 |
+
"lstrip": false,
|
| 862 |
+
"normalized": false,
|
| 863 |
+
"rstrip": false,
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"special": true
|
| 866 |
+
},
|
| 867 |
+
"128108": {
|
| 868 |
+
"content": "<|reserved_special_token_100|>",
|
| 869 |
+
"lstrip": false,
|
| 870 |
+
"normalized": false,
|
| 871 |
+
"rstrip": false,
|
| 872 |
+
"single_word": false,
|
| 873 |
+
"special": true
|
| 874 |
+
},
|
| 875 |
+
"128109": {
|
| 876 |
+
"content": "<|reserved_special_token_101|>",
|
| 877 |
+
"lstrip": false,
|
| 878 |
+
"normalized": false,
|
| 879 |
+
"rstrip": false,
|
| 880 |
+
"single_word": false,
|
| 881 |
+
"special": true
|
| 882 |
+
},
|
| 883 |
+
"128110": {
|
| 884 |
+
"content": "<|reserved_special_token_102|>",
|
| 885 |
+
"lstrip": false,
|
| 886 |
+
"normalized": false,
|
| 887 |
+
"rstrip": false,
|
| 888 |
+
"single_word": false,
|
| 889 |
+
"special": true
|
| 890 |
+
},
|
| 891 |
+
"128111": {
|
| 892 |
+
"content": "<|reserved_special_token_103|>",
|
| 893 |
+
"lstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"rstrip": false,
|
| 896 |
+
"single_word": false,
|
| 897 |
+
"special": true
|
| 898 |
+
},
|
| 899 |
+
"128112": {
|
| 900 |
+
"content": "<|reserved_special_token_104|>",
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"normalized": false,
|
| 903 |
+
"rstrip": false,
|
| 904 |
+
"single_word": false,
|
| 905 |
+
"special": true
|
| 906 |
+
},
|
| 907 |
+
"128113": {
|
| 908 |
+
"content": "<|reserved_special_token_105|>",
|
| 909 |
+
"lstrip": false,
|
| 910 |
+
"normalized": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"single_word": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
"128114": {
|
| 916 |
+
"content": "<|reserved_special_token_106|>",
|
| 917 |
+
"lstrip": false,
|
| 918 |
+
"normalized": false,
|
| 919 |
+
"rstrip": false,
|
| 920 |
+
"single_word": false,
|
| 921 |
+
"special": true
|
| 922 |
+
},
|
| 923 |
+
"128115": {
|
| 924 |
+
"content": "<|reserved_special_token_107|>",
|
| 925 |
+
"lstrip": false,
|
| 926 |
+
"normalized": false,
|
| 927 |
+
"rstrip": false,
|
| 928 |
+
"single_word": false,
|
| 929 |
+
"special": true
|
| 930 |
+
},
|
| 931 |
+
"128116": {
|
| 932 |
+
"content": "<|reserved_special_token_108|>",
|
| 933 |
+
"lstrip": false,
|
| 934 |
+
"normalized": false,
|
| 935 |
+
"rstrip": false,
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"special": true
|
| 938 |
+
},
|
| 939 |
+
"128117": {
|
| 940 |
+
"content": "<|reserved_special_token_109|>",
|
| 941 |
+
"lstrip": false,
|
| 942 |
+
"normalized": false,
|
| 943 |
+
"rstrip": false,
|
| 944 |
+
"single_word": false,
|
| 945 |
+
"special": true
|
| 946 |
+
},
|
| 947 |
+
"128118": {
|
| 948 |
+
"content": "<|reserved_special_token_110|>",
|
| 949 |
+
"lstrip": false,
|
| 950 |
+
"normalized": false,
|
| 951 |
+
"rstrip": false,
|
| 952 |
+
"single_word": false,
|
| 953 |
+
"special": true
|
| 954 |
+
},
|
| 955 |
+
"128119": {
|
| 956 |
+
"content": "<|reserved_special_token_111|>",
|
| 957 |
+
"lstrip": false,
|
| 958 |
+
"normalized": false,
|
| 959 |
+
"rstrip": false,
|
| 960 |
+
"single_word": false,
|
| 961 |
+
"special": true
|
| 962 |
+
},
|
| 963 |
+
"128120": {
|
| 964 |
+
"content": "<|reserved_special_token_112|>",
|
| 965 |
+
"lstrip": false,
|
| 966 |
+
"normalized": false,
|
| 967 |
+
"rstrip": false,
|
| 968 |
+
"single_word": false,
|
| 969 |
+
"special": true
|
| 970 |
+
},
|
| 971 |
+
"128121": {
|
| 972 |
+
"content": "<|reserved_special_token_113|>",
|
| 973 |
+
"lstrip": false,
|
| 974 |
+
"normalized": false,
|
| 975 |
+
"rstrip": false,
|
| 976 |
+
"single_word": false,
|
| 977 |
+
"special": true
|
| 978 |
+
},
|
| 979 |
+
"128122": {
|
| 980 |
+
"content": "<|reserved_special_token_114|>",
|
| 981 |
+
"lstrip": false,
|
| 982 |
+
"normalized": false,
|
| 983 |
+
"rstrip": false,
|
| 984 |
+
"single_word": false,
|
| 985 |
+
"special": true
|
| 986 |
+
},
|
| 987 |
+
"128123": {
|
| 988 |
+
"content": "<|reserved_special_token_115|>",
|
| 989 |
+
"lstrip": false,
|
| 990 |
+
"normalized": false,
|
| 991 |
+
"rstrip": false,
|
| 992 |
+
"single_word": false,
|
| 993 |
+
"special": true
|
| 994 |
+
},
|
| 995 |
+
"128124": {
|
| 996 |
+
"content": "<|reserved_special_token_116|>",
|
| 997 |
+
"lstrip": false,
|
| 998 |
+
"normalized": false,
|
| 999 |
+
"rstrip": false,
|
| 1000 |
+
"single_word": false,
|
| 1001 |
+
"special": true
|
| 1002 |
+
},
|
| 1003 |
+
"128125": {
|
| 1004 |
+
"content": "<|reserved_special_token_117|>",
|
| 1005 |
+
"lstrip": false,
|
| 1006 |
+
"normalized": false,
|
| 1007 |
+
"rstrip": false,
|
| 1008 |
+
"single_word": false,
|
| 1009 |
+
"special": true
|
| 1010 |
+
},
|
| 1011 |
+
"128126": {
|
| 1012 |
+
"content": "<|reserved_special_token_118|>",
|
| 1013 |
+
"lstrip": false,
|
| 1014 |
+
"normalized": false,
|
| 1015 |
+
"rstrip": false,
|
| 1016 |
+
"single_word": false,
|
| 1017 |
+
"special": true
|
| 1018 |
+
},
|
| 1019 |
+
"128127": {
|
| 1020 |
+
"content": "<|reserved_special_token_119|>",
|
| 1021 |
+
"lstrip": false,
|
| 1022 |
+
"normalized": false,
|
| 1023 |
+
"rstrip": false,
|
| 1024 |
+
"single_word": false,
|
| 1025 |
+
"special": true
|
| 1026 |
+
},
|
| 1027 |
+
"128128": {
|
| 1028 |
+
"content": "<|reserved_special_token_120|>",
|
| 1029 |
+
"lstrip": false,
|
| 1030 |
+
"normalized": false,
|
| 1031 |
+
"rstrip": false,
|
| 1032 |
+
"single_word": false,
|
| 1033 |
+
"special": true
|
| 1034 |
+
},
|
| 1035 |
+
"128129": {
|
| 1036 |
+
"content": "<|reserved_special_token_121|>",
|
| 1037 |
+
"lstrip": false,
|
| 1038 |
+
"normalized": false,
|
| 1039 |
+
"rstrip": false,
|
| 1040 |
+
"single_word": false,
|
| 1041 |
+
"special": true
|
| 1042 |
+
},
|
| 1043 |
+
"128130": {
|
| 1044 |
+
"content": "<|reserved_special_token_122|>",
|
| 1045 |
+
"lstrip": false,
|
| 1046 |
+
"normalized": false,
|
| 1047 |
+
"rstrip": false,
|
| 1048 |
+
"single_word": false,
|
| 1049 |
+
"special": true
|
| 1050 |
+
},
|
| 1051 |
+
"128131": {
|
| 1052 |
+
"content": "<|reserved_special_token_123|>",
|
| 1053 |
+
"lstrip": false,
|
| 1054 |
+
"normalized": false,
|
| 1055 |
+
"rstrip": false,
|
| 1056 |
+
"single_word": false,
|
| 1057 |
+
"special": true
|
| 1058 |
+
},
|
| 1059 |
+
"128132": {
|
| 1060 |
+
"content": "<|reserved_special_token_124|>",
|
| 1061 |
+
"lstrip": false,
|
| 1062 |
+
"normalized": false,
|
| 1063 |
+
"rstrip": false,
|
| 1064 |
+
"single_word": false,
|
| 1065 |
+
"special": true
|
| 1066 |
+
},
|
| 1067 |
+
"128133": {
|
| 1068 |
+
"content": "<|reserved_special_token_125|>",
|
| 1069 |
+
"lstrip": false,
|
| 1070 |
+
"normalized": false,
|
| 1071 |
+
"rstrip": false,
|
| 1072 |
+
"single_word": false,
|
| 1073 |
+
"special": true
|
| 1074 |
+
},
|
| 1075 |
+
"128134": {
|
| 1076 |
+
"content": "<|reserved_special_token_126|>",
|
| 1077 |
+
"lstrip": false,
|
| 1078 |
+
"normalized": false,
|
| 1079 |
+
"rstrip": false,
|
| 1080 |
+
"single_word": false,
|
| 1081 |
+
"special": true
|
| 1082 |
+
},
|
| 1083 |
+
"128135": {
|
| 1084 |
+
"content": "<|reserved_special_token_127|>",
|
| 1085 |
+
"lstrip": false,
|
| 1086 |
+
"normalized": false,
|
| 1087 |
+
"rstrip": false,
|
| 1088 |
+
"single_word": false,
|
| 1089 |
+
"special": true
|
| 1090 |
+
},
|
| 1091 |
+
"128136": {
|
| 1092 |
+
"content": "<|reserved_special_token_128|>",
|
| 1093 |
+
"lstrip": false,
|
| 1094 |
+
"normalized": false,
|
| 1095 |
+
"rstrip": false,
|
| 1096 |
+
"single_word": false,
|
| 1097 |
+
"special": true
|
| 1098 |
+
},
|
| 1099 |
+
"128137": {
|
| 1100 |
+
"content": "<|reserved_special_token_129|>",
|
| 1101 |
+
"lstrip": false,
|
| 1102 |
+
"normalized": false,
|
| 1103 |
+
"rstrip": false,
|
| 1104 |
+
"single_word": false,
|
| 1105 |
+
"special": true
|
| 1106 |
+
},
|
| 1107 |
+
"128138": {
|
| 1108 |
+
"content": "<|reserved_special_token_130|>",
|
| 1109 |
+
"lstrip": false,
|
| 1110 |
+
"normalized": false,
|
| 1111 |
+
"rstrip": false,
|
| 1112 |
+
"single_word": false,
|
| 1113 |
+
"special": true
|
| 1114 |
+
},
|
| 1115 |
+
"128139": {
|
| 1116 |
+
"content": "<|reserved_special_token_131|>",
|
| 1117 |
+
"lstrip": false,
|
| 1118 |
+
"normalized": false,
|
| 1119 |
+
"rstrip": false,
|
| 1120 |
+
"single_word": false,
|
| 1121 |
+
"special": true
|
| 1122 |
+
},
|
| 1123 |
+
"128140": {
|
| 1124 |
+
"content": "<|reserved_special_token_132|>",
|
| 1125 |
+
"lstrip": false,
|
| 1126 |
+
"normalized": false,
|
| 1127 |
+
"rstrip": false,
|
| 1128 |
+
"single_word": false,
|
| 1129 |
+
"special": true
|
| 1130 |
+
},
|
| 1131 |
+
"128141": {
|
| 1132 |
+
"content": "<|reserved_special_token_133|>",
|
| 1133 |
+
"lstrip": false,
|
| 1134 |
+
"normalized": false,
|
| 1135 |
+
"rstrip": false,
|
| 1136 |
+
"single_word": false,
|
| 1137 |
+
"special": true
|
| 1138 |
+
},
|
| 1139 |
+
"128142": {
|
| 1140 |
+
"content": "<|reserved_special_token_134|>",
|
| 1141 |
+
"lstrip": false,
|
| 1142 |
+
"normalized": false,
|
| 1143 |
+
"rstrip": false,
|
| 1144 |
+
"single_word": false,
|
| 1145 |
+
"special": true
|
| 1146 |
+
},
|
| 1147 |
+
"128143": {
|
| 1148 |
+
"content": "<|reserved_special_token_135|>",
|
| 1149 |
+
"lstrip": false,
|
| 1150 |
+
"normalized": false,
|
| 1151 |
+
"rstrip": false,
|
| 1152 |
+
"single_word": false,
|
| 1153 |
+
"special": true
|
| 1154 |
+
},
|
| 1155 |
+
"128144": {
|
| 1156 |
+
"content": "<|reserved_special_token_136|>",
|
| 1157 |
+
"lstrip": false,
|
| 1158 |
+
"normalized": false,
|
| 1159 |
+
"rstrip": false,
|
| 1160 |
+
"single_word": false,
|
| 1161 |
+
"special": true
|
| 1162 |
+
},
|
| 1163 |
+
"128145": {
|
| 1164 |
+
"content": "<|reserved_special_token_137|>",
|
| 1165 |
+
"lstrip": false,
|
| 1166 |
+
"normalized": false,
|
| 1167 |
+
"rstrip": false,
|
| 1168 |
+
"single_word": false,
|
| 1169 |
+
"special": true
|
| 1170 |
+
},
|
| 1171 |
+
"128146": {
|
| 1172 |
+
"content": "<|reserved_special_token_138|>",
|
| 1173 |
+
"lstrip": false,
|
| 1174 |
+
"normalized": false,
|
| 1175 |
+
"rstrip": false,
|
| 1176 |
+
"single_word": false,
|
| 1177 |
+
"special": true
|
| 1178 |
+
},
|
| 1179 |
+
"128147": {
|
| 1180 |
+
"content": "<|reserved_special_token_139|>",
|
| 1181 |
+
"lstrip": false,
|
| 1182 |
+
"normalized": false,
|
| 1183 |
+
"rstrip": false,
|
| 1184 |
+
"single_word": false,
|
| 1185 |
+
"special": true
|
| 1186 |
+
},
|
| 1187 |
+
"128148": {
|
| 1188 |
+
"content": "<|reserved_special_token_140|>",
|
| 1189 |
+
"lstrip": false,
|
| 1190 |
+
"normalized": false,
|
| 1191 |
+
"rstrip": false,
|
| 1192 |
+
"single_word": false,
|
| 1193 |
+
"special": true
|
| 1194 |
+
},
|
| 1195 |
+
"128149": {
|
| 1196 |
+
"content": "<|reserved_special_token_141|>",
|
| 1197 |
+
"lstrip": false,
|
| 1198 |
+
"normalized": false,
|
| 1199 |
+
"rstrip": false,
|
| 1200 |
+
"single_word": false,
|
| 1201 |
+
"special": true
|
| 1202 |
+
},
|
| 1203 |
+
"128150": {
|
| 1204 |
+
"content": "<|reserved_special_token_142|>",
|
| 1205 |
+
"lstrip": false,
|
| 1206 |
+
"normalized": false,
|
| 1207 |
+
"rstrip": false,
|
| 1208 |
+
"single_word": false,
|
| 1209 |
+
"special": true
|
| 1210 |
+
},
|
| 1211 |
+
"128151": {
|
| 1212 |
+
"content": "<|reserved_special_token_143|>",
|
| 1213 |
+
"lstrip": false,
|
| 1214 |
+
"normalized": false,
|
| 1215 |
+
"rstrip": false,
|
| 1216 |
+
"single_word": false,
|
| 1217 |
+
"special": true
|
| 1218 |
+
},
|
| 1219 |
+
"128152": {
|
| 1220 |
+
"content": "<|reserved_special_token_144|>",
|
| 1221 |
+
"lstrip": false,
|
| 1222 |
+
"normalized": false,
|
| 1223 |
+
"rstrip": false,
|
| 1224 |
+
"single_word": false,
|
| 1225 |
+
"special": true
|
| 1226 |
+
},
|
| 1227 |
+
"128153": {
|
| 1228 |
+
"content": "<|reserved_special_token_145|>",
|
| 1229 |
+
"lstrip": false,
|
| 1230 |
+
"normalized": false,
|
| 1231 |
+
"rstrip": false,
|
| 1232 |
+
"single_word": false,
|
| 1233 |
+
"special": true
|
| 1234 |
+
},
|
| 1235 |
+
"128154": {
|
| 1236 |
+
"content": "<|reserved_special_token_146|>",
|
| 1237 |
+
"lstrip": false,
|
| 1238 |
+
"normalized": false,
|
| 1239 |
+
"rstrip": false,
|
| 1240 |
+
"single_word": false,
|
| 1241 |
+
"special": true
|
| 1242 |
+
},
|
| 1243 |
+
"128155": {
|
| 1244 |
+
"content": "<|reserved_special_token_147|>",
|
| 1245 |
+
"lstrip": false,
|
| 1246 |
+
"normalized": false,
|
| 1247 |
+
"rstrip": false,
|
| 1248 |
+
"single_word": false,
|
| 1249 |
+
"special": true
|
| 1250 |
+
},
|
| 1251 |
+
"128156": {
|
| 1252 |
+
"content": "<|reserved_special_token_148|>",
|
| 1253 |
+
"lstrip": false,
|
| 1254 |
+
"normalized": false,
|
| 1255 |
+
"rstrip": false,
|
| 1256 |
+
"single_word": false,
|
| 1257 |
+
"special": true
|
| 1258 |
+
},
|
| 1259 |
+
"128157": {
|
| 1260 |
+
"content": "<|reserved_special_token_149|>",
|
| 1261 |
+
"lstrip": false,
|
| 1262 |
+
"normalized": false,
|
| 1263 |
+
"rstrip": false,
|
| 1264 |
+
"single_word": false,
|
| 1265 |
+
"special": true
|
| 1266 |
+
},
|
| 1267 |
+
"128158": {
|
| 1268 |
+
"content": "<|reserved_special_token_150|>",
|
| 1269 |
+
"lstrip": false,
|
| 1270 |
+
"normalized": false,
|
| 1271 |
+
"rstrip": false,
|
| 1272 |
+
"single_word": false,
|
| 1273 |
+
"special": true
|
| 1274 |
+
},
|
| 1275 |
+
"128159": {
|
| 1276 |
+
"content": "<|reserved_special_token_151|>",
|
| 1277 |
+
"lstrip": false,
|
| 1278 |
+
"normalized": false,
|
| 1279 |
+
"rstrip": false,
|
| 1280 |
+
"single_word": false,
|
| 1281 |
+
"special": true
|
| 1282 |
+
},
|
| 1283 |
+
"128160": {
|
| 1284 |
+
"content": "<|reserved_special_token_152|>",
|
| 1285 |
+
"lstrip": false,
|
| 1286 |
+
"normalized": false,
|
| 1287 |
+
"rstrip": false,
|
| 1288 |
+
"single_word": false,
|
| 1289 |
+
"special": true
|
| 1290 |
+
},
|
| 1291 |
+
"128161": {
|
| 1292 |
+
"content": "<|reserved_special_token_153|>",
|
| 1293 |
+
"lstrip": false,
|
| 1294 |
+
"normalized": false,
|
| 1295 |
+
"rstrip": false,
|
| 1296 |
+
"single_word": false,
|
| 1297 |
+
"special": true
|
| 1298 |
+
},
|
| 1299 |
+
"128162": {
|
| 1300 |
+
"content": "<|reserved_special_token_154|>",
|
| 1301 |
+
"lstrip": false,
|
| 1302 |
+
"normalized": false,
|
| 1303 |
+
"rstrip": false,
|
| 1304 |
+
"single_word": false,
|
| 1305 |
+
"special": true
|
| 1306 |
+
},
|
| 1307 |
+
"128163": {
|
| 1308 |
+
"content": "<|reserved_special_token_155|>",
|
| 1309 |
+
"lstrip": false,
|
| 1310 |
+
"normalized": false,
|
| 1311 |
+
"rstrip": false,
|
| 1312 |
+
"single_word": false,
|
| 1313 |
+
"special": true
|
| 1314 |
+
},
|
| 1315 |
+
"128164": {
|
| 1316 |
+
"content": "<|reserved_special_token_156|>",
|
| 1317 |
+
"lstrip": false,
|
| 1318 |
+
"normalized": false,
|
| 1319 |
+
"rstrip": false,
|
| 1320 |
+
"single_word": false,
|
| 1321 |
+
"special": true
|
| 1322 |
+
},
|
| 1323 |
+
"128165": {
|
| 1324 |
+
"content": "<|reserved_special_token_157|>",
|
| 1325 |
+
"lstrip": false,
|
| 1326 |
+
"normalized": false,
|
| 1327 |
+
"rstrip": false,
|
| 1328 |
+
"single_word": false,
|
| 1329 |
+
"special": true
|
| 1330 |
+
},
|
| 1331 |
+
"128166": {
|
| 1332 |
+
"content": "<|reserved_special_token_158|>",
|
| 1333 |
+
"lstrip": false,
|
| 1334 |
+
"normalized": false,
|
| 1335 |
+
"rstrip": false,
|
| 1336 |
+
"single_word": false,
|
| 1337 |
+
"special": true
|
| 1338 |
+
},
|
| 1339 |
+
"128167": {
|
| 1340 |
+
"content": "<|reserved_special_token_159|>",
|
| 1341 |
+
"lstrip": false,
|
| 1342 |
+
"normalized": false,
|
| 1343 |
+
"rstrip": false,
|
| 1344 |
+
"single_word": false,
|
| 1345 |
+
"special": true
|
| 1346 |
+
},
|
| 1347 |
+
"128168": {
|
| 1348 |
+
"content": "<|reserved_special_token_160|>",
|
| 1349 |
+
"lstrip": false,
|
| 1350 |
+
"normalized": false,
|
| 1351 |
+
"rstrip": false,
|
| 1352 |
+
"single_word": false,
|
| 1353 |
+
"special": true
|
| 1354 |
+
},
|
| 1355 |
+
"128169": {
|
| 1356 |
+
"content": "<|reserved_special_token_161|>",
|
| 1357 |
+
"lstrip": false,
|
| 1358 |
+
"normalized": false,
|
| 1359 |
+
"rstrip": false,
|
| 1360 |
+
"single_word": false,
|
| 1361 |
+
"special": true
|
| 1362 |
+
},
|
| 1363 |
+
"128170": {
|
| 1364 |
+
"content": "<|reserved_special_token_162|>",
|
| 1365 |
+
"lstrip": false,
|
| 1366 |
+
"normalized": false,
|
| 1367 |
+
"rstrip": false,
|
| 1368 |
+
"single_word": false,
|
| 1369 |
+
"special": true
|
| 1370 |
+
},
|
| 1371 |
+
"128171": {
|
| 1372 |
+
"content": "<|reserved_special_token_163|>",
|
| 1373 |
+
"lstrip": false,
|
| 1374 |
+
"normalized": false,
|
| 1375 |
+
"rstrip": false,
|
| 1376 |
+
"single_word": false,
|
| 1377 |
+
"special": true
|
| 1378 |
+
},
|
| 1379 |
+
"128172": {
|
| 1380 |
+
"content": "<|reserved_special_token_164|>",
|
| 1381 |
+
"lstrip": false,
|
| 1382 |
+
"normalized": false,
|
| 1383 |
+
"rstrip": false,
|
| 1384 |
+
"single_word": false,
|
| 1385 |
+
"special": true
|
| 1386 |
+
},
|
| 1387 |
+
"128173": {
|
| 1388 |
+
"content": "<|reserved_special_token_165|>",
|
| 1389 |
+
"lstrip": false,
|
| 1390 |
+
"normalized": false,
|
| 1391 |
+
"rstrip": false,
|
| 1392 |
+
"single_word": false,
|
| 1393 |
+
"special": true
|
| 1394 |
+
},
|
| 1395 |
+
"128174": {
|
| 1396 |
+
"content": "<|reserved_special_token_166|>",
|
| 1397 |
+
"lstrip": false,
|
| 1398 |
+
"normalized": false,
|
| 1399 |
+
"rstrip": false,
|
| 1400 |
+
"single_word": false,
|
| 1401 |
+
"special": true
|
| 1402 |
+
},
|
| 1403 |
+
"128175": {
|
| 1404 |
+
"content": "<|reserved_special_token_167|>",
|
| 1405 |
+
"lstrip": false,
|
| 1406 |
+
"normalized": false,
|
| 1407 |
+
"rstrip": false,
|
| 1408 |
+
"single_word": false,
|
| 1409 |
+
"special": true
|
| 1410 |
+
},
|
| 1411 |
+
"128176": {
|
| 1412 |
+
"content": "<|reserved_special_token_168|>",
|
| 1413 |
+
"lstrip": false,
|
| 1414 |
+
"normalized": false,
|
| 1415 |
+
"rstrip": false,
|
| 1416 |
+
"single_word": false,
|
| 1417 |
+
"special": true
|
| 1418 |
+
},
|
| 1419 |
+
"128177": {
|
| 1420 |
+
"content": "<|reserved_special_token_169|>",
|
| 1421 |
+
"lstrip": false,
|
| 1422 |
+
"normalized": false,
|
| 1423 |
+
"rstrip": false,
|
| 1424 |
+
"single_word": false,
|
| 1425 |
+
"special": true
|
| 1426 |
+
},
|
| 1427 |
+
"128178": {
|
| 1428 |
+
"content": "<|reserved_special_token_170|>",
|
| 1429 |
+
"lstrip": false,
|
| 1430 |
+
"normalized": false,
|
| 1431 |
+
"rstrip": false,
|
| 1432 |
+
"single_word": false,
|
| 1433 |
+
"special": true
|
| 1434 |
+
},
|
| 1435 |
+
"128179": {
|
| 1436 |
+
"content": "<|reserved_special_token_171|>",
|
| 1437 |
+
"lstrip": false,
|
| 1438 |
+
"normalized": false,
|
| 1439 |
+
"rstrip": false,
|
| 1440 |
+
"single_word": false,
|
| 1441 |
+
"special": true
|
| 1442 |
+
},
|
| 1443 |
+
"128180": {
|
| 1444 |
+
"content": "<|reserved_special_token_172|>",
|
| 1445 |
+
"lstrip": false,
|
| 1446 |
+
"normalized": false,
|
| 1447 |
+
"rstrip": false,
|
| 1448 |
+
"single_word": false,
|
| 1449 |
+
"special": true
|
| 1450 |
+
},
|
| 1451 |
+
"128181": {
|
| 1452 |
+
"content": "<|reserved_special_token_173|>",
|
| 1453 |
+
"lstrip": false,
|
| 1454 |
+
"normalized": false,
|
| 1455 |
+
"rstrip": false,
|
| 1456 |
+
"single_word": false,
|
| 1457 |
+
"special": true
|
| 1458 |
+
},
|
| 1459 |
+
"128182": {
|
| 1460 |
+
"content": "<|reserved_special_token_174|>",
|
| 1461 |
+
"lstrip": false,
|
| 1462 |
+
"normalized": false,
|
| 1463 |
+
"rstrip": false,
|
| 1464 |
+
"single_word": false,
|
| 1465 |
+
"special": true
|
| 1466 |
+
},
|
| 1467 |
+
"128183": {
|
| 1468 |
+
"content": "<|reserved_special_token_175|>",
|
| 1469 |
+
"lstrip": false,
|
| 1470 |
+
"normalized": false,
|
| 1471 |
+
"rstrip": false,
|
| 1472 |
+
"single_word": false,
|
| 1473 |
+
"special": true
|
| 1474 |
+
},
|
| 1475 |
+
"128184": {
|
| 1476 |
+
"content": "<|reserved_special_token_176|>",
|
| 1477 |
+
"lstrip": false,
|
| 1478 |
+
"normalized": false,
|
| 1479 |
+
"rstrip": false,
|
| 1480 |
+
"single_word": false,
|
| 1481 |
+
"special": true
|
| 1482 |
+
},
|
| 1483 |
+
"128185": {
|
| 1484 |
+
"content": "<|reserved_special_token_177|>",
|
| 1485 |
+
"lstrip": false,
|
| 1486 |
+
"normalized": false,
|
| 1487 |
+
"rstrip": false,
|
| 1488 |
+
"single_word": false,
|
| 1489 |
+
"special": true
|
| 1490 |
+
},
|
| 1491 |
+
"128186": {
|
| 1492 |
+
"content": "<|reserved_special_token_178|>",
|
| 1493 |
+
"lstrip": false,
|
| 1494 |
+
"normalized": false,
|
| 1495 |
+
"rstrip": false,
|
| 1496 |
+
"single_word": false,
|
| 1497 |
+
"special": true
|
| 1498 |
+
},
|
| 1499 |
+
"128187": {
|
| 1500 |
+
"content": "<|reserved_special_token_179|>",
|
| 1501 |
+
"lstrip": false,
|
| 1502 |
+
"normalized": false,
|
| 1503 |
+
"rstrip": false,
|
| 1504 |
+
"single_word": false,
|
| 1505 |
+
"special": true
|
| 1506 |
+
},
|
| 1507 |
+
"128188": {
|
| 1508 |
+
"content": "<|reserved_special_token_180|>",
|
| 1509 |
+
"lstrip": false,
|
| 1510 |
+
"normalized": false,
|
| 1511 |
+
"rstrip": false,
|
| 1512 |
+
"single_word": false,
|
| 1513 |
+
"special": true
|
| 1514 |
+
},
|
| 1515 |
+
"128189": {
|
| 1516 |
+
"content": "<|reserved_special_token_181|>",
|
| 1517 |
+
"lstrip": false,
|
| 1518 |
+
"normalized": false,
|
| 1519 |
+
"rstrip": false,
|
| 1520 |
+
"single_word": false,
|
| 1521 |
+
"special": true
|
| 1522 |
+
},
|
| 1523 |
+
"128190": {
|
| 1524 |
+
"content": "<|reserved_special_token_182|>",
|
| 1525 |
+
"lstrip": false,
|
| 1526 |
+
"normalized": false,
|
| 1527 |
+
"rstrip": false,
|
| 1528 |
+
"single_word": false,
|
| 1529 |
+
"special": true
|
| 1530 |
+
},
|
| 1531 |
+
"128191": {
|
| 1532 |
+
"content": "<|reserved_special_token_183|>",
|
| 1533 |
+
"lstrip": false,
|
| 1534 |
+
"normalized": false,
|
| 1535 |
+
"rstrip": false,
|
| 1536 |
+
"single_word": false,
|
| 1537 |
+
"special": true
|
| 1538 |
+
},
|
| 1539 |
+
"128192": {
|
| 1540 |
+
"content": "<|reserved_special_token_184|>",
|
| 1541 |
+
"lstrip": false,
|
| 1542 |
+
"normalized": false,
|
| 1543 |
+
"rstrip": false,
|
| 1544 |
+
"single_word": false,
|
| 1545 |
+
"special": true
|
| 1546 |
+
},
|
| 1547 |
+
"128193": {
|
| 1548 |
+
"content": "<|reserved_special_token_185|>",
|
| 1549 |
+
"lstrip": false,
|
| 1550 |
+
"normalized": false,
|
| 1551 |
+
"rstrip": false,
|
| 1552 |
+
"single_word": false,
|
| 1553 |
+
"special": true
|
| 1554 |
+
},
|
| 1555 |
+
"128194": {
|
| 1556 |
+
"content": "<|reserved_special_token_186|>",
|
| 1557 |
+
"lstrip": false,
|
| 1558 |
+
"normalized": false,
|
| 1559 |
+
"rstrip": false,
|
| 1560 |
+
"single_word": false,
|
| 1561 |
+
"special": true
|
| 1562 |
+
},
|
| 1563 |
+
"128195": {
|
| 1564 |
+
"content": "<|reserved_special_token_187|>",
|
| 1565 |
+
"lstrip": false,
|
| 1566 |
+
"normalized": false,
|
| 1567 |
+
"rstrip": false,
|
| 1568 |
+
"single_word": false,
|
| 1569 |
+
"special": true
|
| 1570 |
+
},
|
| 1571 |
+
"128196": {
|
| 1572 |
+
"content": "<|reserved_special_token_188|>",
|
| 1573 |
+
"lstrip": false,
|
| 1574 |
+
"normalized": false,
|
| 1575 |
+
"rstrip": false,
|
| 1576 |
+
"single_word": false,
|
| 1577 |
+
"special": true
|
| 1578 |
+
},
|
| 1579 |
+
"128197": {
|
| 1580 |
+
"content": "<|reserved_special_token_189|>",
|
| 1581 |
+
"lstrip": false,
|
| 1582 |
+
"normalized": false,
|
| 1583 |
+
"rstrip": false,
|
| 1584 |
+
"single_word": false,
|
| 1585 |
+
"special": true
|
| 1586 |
+
},
|
| 1587 |
+
"128198": {
|
| 1588 |
+
"content": "<|reserved_special_token_190|>",
|
| 1589 |
+
"lstrip": false,
|
| 1590 |
+
"normalized": false,
|
| 1591 |
+
"rstrip": false,
|
| 1592 |
+
"single_word": false,
|
| 1593 |
+
"special": true
|
| 1594 |
+
},
|
| 1595 |
+
"128199": {
|
| 1596 |
+
"content": "<|reserved_special_token_191|>",
|
| 1597 |
+
"lstrip": false,
|
| 1598 |
+
"normalized": false,
|
| 1599 |
+
"rstrip": false,
|
| 1600 |
+
"single_word": false,
|
| 1601 |
+
"special": true
|
| 1602 |
+
},
|
| 1603 |
+
"128200": {
|
| 1604 |
+
"content": "<|reserved_special_token_192|>",
|
| 1605 |
+
"lstrip": false,
|
| 1606 |
+
"normalized": false,
|
| 1607 |
+
"rstrip": false,
|
| 1608 |
+
"single_word": false,
|
| 1609 |
+
"special": true
|
| 1610 |
+
},
|
| 1611 |
+
"128201": {
|
| 1612 |
+
"content": "<|reserved_special_token_193|>",
|
| 1613 |
+
"lstrip": false,
|
| 1614 |
+
"normalized": false,
|
| 1615 |
+
"rstrip": false,
|
| 1616 |
+
"single_word": false,
|
| 1617 |
+
"special": true
|
| 1618 |
+
},
|
| 1619 |
+
"128202": {
|
| 1620 |
+
"content": "<|reserved_special_token_194|>",
|
| 1621 |
+
"lstrip": false,
|
| 1622 |
+
"normalized": false,
|
| 1623 |
+
"rstrip": false,
|
| 1624 |
+
"single_word": false,
|
| 1625 |
+
"special": true
|
| 1626 |
+
},
|
| 1627 |
+
"128203": {
|
| 1628 |
+
"content": "<|reserved_special_token_195|>",
|
| 1629 |
+
"lstrip": false,
|
| 1630 |
+
"normalized": false,
|
| 1631 |
+
"rstrip": false,
|
| 1632 |
+
"single_word": false,
|
| 1633 |
+
"special": true
|
| 1634 |
+
},
|
| 1635 |
+
"128204": {
|
| 1636 |
+
"content": "<|reserved_special_token_196|>",
|
| 1637 |
+
"lstrip": false,
|
| 1638 |
+
"normalized": false,
|
| 1639 |
+
"rstrip": false,
|
| 1640 |
+
"single_word": false,
|
| 1641 |
+
"special": true
|
| 1642 |
+
},
|
| 1643 |
+
"128205": {
|
| 1644 |
+
"content": "<|reserved_special_token_197|>",
|
| 1645 |
+
"lstrip": false,
|
| 1646 |
+
"normalized": false,
|
| 1647 |
+
"rstrip": false,
|
| 1648 |
+
"single_word": false,
|
| 1649 |
+
"special": true
|
| 1650 |
+
},
|
| 1651 |
+
"128206": {
|
| 1652 |
+
"content": "<|reserved_special_token_198|>",
|
| 1653 |
+
"lstrip": false,
|
| 1654 |
+
"normalized": false,
|
| 1655 |
+
"rstrip": false,
|
| 1656 |
+
"single_word": false,
|
| 1657 |
+
"special": true
|
| 1658 |
+
},
|
| 1659 |
+
"128207": {
|
| 1660 |
+
"content": "<|reserved_special_token_199|>",
|
| 1661 |
+
"lstrip": false,
|
| 1662 |
+
"normalized": false,
|
| 1663 |
+
"rstrip": false,
|
| 1664 |
+
"single_word": false,
|
| 1665 |
+
"special": true
|
| 1666 |
+
},
|
| 1667 |
+
"128208": {
|
| 1668 |
+
"content": "<|reserved_special_token_200|>",
|
| 1669 |
+
"lstrip": false,
|
| 1670 |
+
"normalized": false,
|
| 1671 |
+
"rstrip": false,
|
| 1672 |
+
"single_word": false,
|
| 1673 |
+
"special": true
|
| 1674 |
+
},
|
| 1675 |
+
"128209": {
|
| 1676 |
+
"content": "<|reserved_special_token_201|>",
|
| 1677 |
+
"lstrip": false,
|
| 1678 |
+
"normalized": false,
|
| 1679 |
+
"rstrip": false,
|
| 1680 |
+
"single_word": false,
|
| 1681 |
+
"special": true
|
| 1682 |
+
},
|
| 1683 |
+
"128210": {
|
| 1684 |
+
"content": "<|reserved_special_token_202|>",
|
| 1685 |
+
"lstrip": false,
|
| 1686 |
+
"normalized": false,
|
| 1687 |
+
"rstrip": false,
|
| 1688 |
+
"single_word": false,
|
| 1689 |
+
"special": true
|
| 1690 |
+
},
|
| 1691 |
+
"128211": {
|
| 1692 |
+
"content": "<|reserved_special_token_203|>",
|
| 1693 |
+
"lstrip": false,
|
| 1694 |
+
"normalized": false,
|
| 1695 |
+
"rstrip": false,
|
| 1696 |
+
"single_word": false,
|
| 1697 |
+
"special": true
|
| 1698 |
+
},
|
| 1699 |
+
"128212": {
|
| 1700 |
+
"content": "<|reserved_special_token_204|>",
|
| 1701 |
+
"lstrip": false,
|
| 1702 |
+
"normalized": false,
|
| 1703 |
+
"rstrip": false,
|
| 1704 |
+
"single_word": false,
|
| 1705 |
+
"special": true
|
| 1706 |
+
},
|
| 1707 |
+
"128213": {
|
| 1708 |
+
"content": "<|reserved_special_token_205|>",
|
| 1709 |
+
"lstrip": false,
|
| 1710 |
+
"normalized": false,
|
| 1711 |
+
"rstrip": false,
|
| 1712 |
+
"single_word": false,
|
| 1713 |
+
"special": true
|
| 1714 |
+
},
|
| 1715 |
+
"128214": {
|
| 1716 |
+
"content": "<|reserved_special_token_206|>",
|
| 1717 |
+
"lstrip": false,
|
| 1718 |
+
"normalized": false,
|
| 1719 |
+
"rstrip": false,
|
| 1720 |
+
"single_word": false,
|
| 1721 |
+
"special": true
|
| 1722 |
+
},
|
| 1723 |
+
"128215": {
|
| 1724 |
+
"content": "<|reserved_special_token_207|>",
|
| 1725 |
+
"lstrip": false,
|
| 1726 |
+
"normalized": false,
|
| 1727 |
+
"rstrip": false,
|
| 1728 |
+
"single_word": false,
|
| 1729 |
+
"special": true
|
| 1730 |
+
},
|
| 1731 |
+
"128216": {
|
| 1732 |
+
"content": "<|reserved_special_token_208|>",
|
| 1733 |
+
"lstrip": false,
|
| 1734 |
+
"normalized": false,
|
| 1735 |
+
"rstrip": false,
|
| 1736 |
+
"single_word": false,
|
| 1737 |
+
"special": true
|
| 1738 |
+
},
|
| 1739 |
+
"128217": {
|
| 1740 |
+
"content": "<|reserved_special_token_209|>",
|
| 1741 |
+
"lstrip": false,
|
| 1742 |
+
"normalized": false,
|
| 1743 |
+
"rstrip": false,
|
| 1744 |
+
"single_word": false,
|
| 1745 |
+
"special": true
|
| 1746 |
+
},
|
| 1747 |
+
"128218": {
|
| 1748 |
+
"content": "<|reserved_special_token_210|>",
|
| 1749 |
+
"lstrip": false,
|
| 1750 |
+
"normalized": false,
|
| 1751 |
+
"rstrip": false,
|
| 1752 |
+
"single_word": false,
|
| 1753 |
+
"special": true
|
| 1754 |
+
},
|
| 1755 |
+
"128219": {
|
| 1756 |
+
"content": "<|reserved_special_token_211|>",
|
| 1757 |
+
"lstrip": false,
|
| 1758 |
+
"normalized": false,
|
| 1759 |
+
"rstrip": false,
|
| 1760 |
+
"single_word": false,
|
| 1761 |
+
"special": true
|
| 1762 |
+
},
|
| 1763 |
+
"128220": {
|
| 1764 |
+
"content": "<|reserved_special_token_212|>",
|
| 1765 |
+
"lstrip": false,
|
| 1766 |
+
"normalized": false,
|
| 1767 |
+
"rstrip": false,
|
| 1768 |
+
"single_word": false,
|
| 1769 |
+
"special": true
|
| 1770 |
+
},
|
| 1771 |
+
"128221": {
|
| 1772 |
+
"content": "<|reserved_special_token_213|>",
|
| 1773 |
+
"lstrip": false,
|
| 1774 |
+
"normalized": false,
|
| 1775 |
+
"rstrip": false,
|
| 1776 |
+
"single_word": false,
|
| 1777 |
+
"special": true
|
| 1778 |
+
},
|
| 1779 |
+
"128222": {
|
| 1780 |
+
"content": "<|reserved_special_token_214|>",
|
| 1781 |
+
"lstrip": false,
|
| 1782 |
+
"normalized": false,
|
| 1783 |
+
"rstrip": false,
|
| 1784 |
+
"single_word": false,
|
| 1785 |
+
"special": true
|
| 1786 |
+
},
|
| 1787 |
+
"128223": {
|
| 1788 |
+
"content": "<|reserved_special_token_215|>",
|
| 1789 |
+
"lstrip": false,
|
| 1790 |
+
"normalized": false,
|
| 1791 |
+
"rstrip": false,
|
| 1792 |
+
"single_word": false,
|
| 1793 |
+
"special": true
|
| 1794 |
+
},
|
| 1795 |
+
"128224": {
|
| 1796 |
+
"content": "<|reserved_special_token_216|>",
|
| 1797 |
+
"lstrip": false,
|
| 1798 |
+
"normalized": false,
|
| 1799 |
+
"rstrip": false,
|
| 1800 |
+
"single_word": false,
|
| 1801 |
+
"special": true
|
| 1802 |
+
},
|
| 1803 |
+
"128225": {
|
| 1804 |
+
"content": "<|reserved_special_token_217|>",
|
| 1805 |
+
"lstrip": false,
|
| 1806 |
+
"normalized": false,
|
| 1807 |
+
"rstrip": false,
|
| 1808 |
+
"single_word": false,
|
| 1809 |
+
"special": true
|
| 1810 |
+
},
|
| 1811 |
+
"128226": {
|
| 1812 |
+
"content": "<|reserved_special_token_218|>",
|
| 1813 |
+
"lstrip": false,
|
| 1814 |
+
"normalized": false,
|
| 1815 |
+
"rstrip": false,
|
| 1816 |
+
"single_word": false,
|
| 1817 |
+
"special": true
|
| 1818 |
+
},
|
| 1819 |
+
"128227": {
|
| 1820 |
+
"content": "<|reserved_special_token_219|>",
|
| 1821 |
+
"lstrip": false,
|
| 1822 |
+
"normalized": false,
|
| 1823 |
+
"rstrip": false,
|
| 1824 |
+
"single_word": false,
|
| 1825 |
+
"special": true
|
| 1826 |
+
},
|
| 1827 |
+
"128228": {
|
| 1828 |
+
"content": "<|reserved_special_token_220|>",
|
| 1829 |
+
"lstrip": false,
|
| 1830 |
+
"normalized": false,
|
| 1831 |
+
"rstrip": false,
|
| 1832 |
+
"single_word": false,
|
| 1833 |
+
"special": true
|
| 1834 |
+
},
|
| 1835 |
+
"128229": {
|
| 1836 |
+
"content": "<|reserved_special_token_221|>",
|
| 1837 |
+
"lstrip": false,
|
| 1838 |
+
"normalized": false,
|
| 1839 |
+
"rstrip": false,
|
| 1840 |
+
"single_word": false,
|
| 1841 |
+
"special": true
|
| 1842 |
+
},
|
| 1843 |
+
"128230": {
|
| 1844 |
+
"content": "<|reserved_special_token_222|>",
|
| 1845 |
+
"lstrip": false,
|
| 1846 |
+
"normalized": false,
|
| 1847 |
+
"rstrip": false,
|
| 1848 |
+
"single_word": false,
|
| 1849 |
+
"special": true
|
| 1850 |
+
},
|
| 1851 |
+
"128231": {
|
| 1852 |
+
"content": "<|reserved_special_token_223|>",
|
| 1853 |
+
"lstrip": false,
|
| 1854 |
+
"normalized": false,
|
| 1855 |
+
"rstrip": false,
|
| 1856 |
+
"single_word": false,
|
| 1857 |
+
"special": true
|
| 1858 |
+
},
|
| 1859 |
+
"128232": {
|
| 1860 |
+
"content": "<|reserved_special_token_224|>",
|
| 1861 |
+
"lstrip": false,
|
| 1862 |
+
"normalized": false,
|
| 1863 |
+
"rstrip": false,
|
| 1864 |
+
"single_word": false,
|
| 1865 |
+
"special": true
|
| 1866 |
+
},
|
| 1867 |
+
"128233": {
|
| 1868 |
+
"content": "<|reserved_special_token_225|>",
|
| 1869 |
+
"lstrip": false,
|
| 1870 |
+
"normalized": false,
|
| 1871 |
+
"rstrip": false,
|
| 1872 |
+
"single_word": false,
|
| 1873 |
+
"special": true
|
| 1874 |
+
},
|
| 1875 |
+
"128234": {
|
| 1876 |
+
"content": "<|reserved_special_token_226|>",
|
| 1877 |
+
"lstrip": false,
|
| 1878 |
+
"normalized": false,
|
| 1879 |
+
"rstrip": false,
|
| 1880 |
+
"single_word": false,
|
| 1881 |
+
"special": true
|
| 1882 |
+
},
|
| 1883 |
+
"128235": {
|
| 1884 |
+
"content": "<|reserved_special_token_227|>",
|
| 1885 |
+
"lstrip": false,
|
| 1886 |
+
"normalized": false,
|
| 1887 |
+
"rstrip": false,
|
| 1888 |
+
"single_word": false,
|
| 1889 |
+
"special": true
|
| 1890 |
+
},
|
| 1891 |
+
"128236": {
|
| 1892 |
+
"content": "<|reserved_special_token_228|>",
|
| 1893 |
+
"lstrip": false,
|
| 1894 |
+
"normalized": false,
|
| 1895 |
+
"rstrip": false,
|
| 1896 |
+
"single_word": false,
|
| 1897 |
+
"special": true
|
| 1898 |
+
},
|
| 1899 |
+
"128237": {
|
| 1900 |
+
"content": "<|reserved_special_token_229|>",
|
| 1901 |
+
"lstrip": false,
|
| 1902 |
+
"normalized": false,
|
| 1903 |
+
"rstrip": false,
|
| 1904 |
+
"single_word": false,
|
| 1905 |
+
"special": true
|
| 1906 |
+
},
|
| 1907 |
+
"128238": {
|
| 1908 |
+
"content": "<|reserved_special_token_230|>",
|
| 1909 |
+
"lstrip": false,
|
| 1910 |
+
"normalized": false,
|
| 1911 |
+
"rstrip": false,
|
| 1912 |
+
"single_word": false,
|
| 1913 |
+
"special": true
|
| 1914 |
+
},
|
| 1915 |
+
"128239": {
|
| 1916 |
+
"content": "<|reserved_special_token_231|>",
|
| 1917 |
+
"lstrip": false,
|
| 1918 |
+
"normalized": false,
|
| 1919 |
+
"rstrip": false,
|
| 1920 |
+
"single_word": false,
|
| 1921 |
+
"special": true
|
| 1922 |
+
},
|
| 1923 |
+
"128240": {
|
| 1924 |
+
"content": "<|reserved_special_token_232|>",
|
| 1925 |
+
"lstrip": false,
|
| 1926 |
+
"normalized": false,
|
| 1927 |
+
"rstrip": false,
|
| 1928 |
+
"single_word": false,
|
| 1929 |
+
"special": true
|
| 1930 |
+
},
|
| 1931 |
+
"128241": {
|
| 1932 |
+
"content": "<|reserved_special_token_233|>",
|
| 1933 |
+
"lstrip": false,
|
| 1934 |
+
"normalized": false,
|
| 1935 |
+
"rstrip": false,
|
| 1936 |
+
"single_word": false,
|
| 1937 |
+
"special": true
|
| 1938 |
+
},
|
| 1939 |
+
"128242": {
|
| 1940 |
+
"content": "<|reserved_special_token_234|>",
|
| 1941 |
+
"lstrip": false,
|
| 1942 |
+
"normalized": false,
|
| 1943 |
+
"rstrip": false,
|
| 1944 |
+
"single_word": false,
|
| 1945 |
+
"special": true
|
| 1946 |
+
},
|
| 1947 |
+
"128243": {
|
| 1948 |
+
"content": "<|reserved_special_token_235|>",
|
| 1949 |
+
"lstrip": false,
|
| 1950 |
+
"normalized": false,
|
| 1951 |
+
"rstrip": false,
|
| 1952 |
+
"single_word": false,
|
| 1953 |
+
"special": true
|
| 1954 |
+
},
|
| 1955 |
+
"128244": {
|
| 1956 |
+
"content": "<|reserved_special_token_236|>",
|
| 1957 |
+
"lstrip": false,
|
| 1958 |
+
"normalized": false,
|
| 1959 |
+
"rstrip": false,
|
| 1960 |
+
"single_word": false,
|
| 1961 |
+
"special": true
|
| 1962 |
+
},
|
| 1963 |
+
"128245": {
|
| 1964 |
+
"content": "<|reserved_special_token_237|>",
|
| 1965 |
+
"lstrip": false,
|
| 1966 |
+
"normalized": false,
|
| 1967 |
+
"rstrip": false,
|
| 1968 |
+
"single_word": false,
|
| 1969 |
+
"special": true
|
| 1970 |
+
},
|
| 1971 |
+
"128246": {
|
| 1972 |
+
"content": "<|reserved_special_token_238|>",
|
| 1973 |
+
"lstrip": false,
|
| 1974 |
+
"normalized": false,
|
| 1975 |
+
"rstrip": false,
|
| 1976 |
+
"single_word": false,
|
| 1977 |
+
"special": true
|
| 1978 |
+
},
|
| 1979 |
+
"128247": {
|
| 1980 |
+
"content": "<|reserved_special_token_239|>",
|
| 1981 |
+
"lstrip": false,
|
| 1982 |
+
"normalized": false,
|
| 1983 |
+
"rstrip": false,
|
| 1984 |
+
"single_word": false,
|
| 1985 |
+
"special": true
|
| 1986 |
+
},
|
| 1987 |
+
"128248": {
|
| 1988 |
+
"content": "<|reserved_special_token_240|>",
|
| 1989 |
+
"lstrip": false,
|
| 1990 |
+
"normalized": false,
|
| 1991 |
+
"rstrip": false,
|
| 1992 |
+
"single_word": false,
|
| 1993 |
+
"special": true
|
| 1994 |
+
},
|
| 1995 |
+
"128249": {
|
| 1996 |
+
"content": "<|reserved_special_token_241|>",
|
| 1997 |
+
"lstrip": false,
|
| 1998 |
+
"normalized": false,
|
| 1999 |
+
"rstrip": false,
|
| 2000 |
+
"single_word": false,
|
| 2001 |
+
"special": true
|
| 2002 |
+
},
|
| 2003 |
+
"128250": {
|
| 2004 |
+
"content": "<|reserved_special_token_242|>",
|
| 2005 |
+
"lstrip": false,
|
| 2006 |
+
"normalized": false,
|
| 2007 |
+
"rstrip": false,
|
| 2008 |
+
"single_word": false,
|
| 2009 |
+
"special": true
|
| 2010 |
+
},
|
| 2011 |
+
"128251": {
|
| 2012 |
+
"content": "<|reserved_special_token_243|>",
|
| 2013 |
+
"lstrip": false,
|
| 2014 |
+
"normalized": false,
|
| 2015 |
+
"rstrip": false,
|
| 2016 |
+
"single_word": false,
|
| 2017 |
+
"special": true
|
| 2018 |
+
},
|
| 2019 |
+
"128252": {
|
| 2020 |
+
"content": "<|reserved_special_token_244|>",
|
| 2021 |
+
"lstrip": false,
|
| 2022 |
+
"normalized": false,
|
| 2023 |
+
"rstrip": false,
|
| 2024 |
+
"single_word": false,
|
| 2025 |
+
"special": true
|
| 2026 |
+
},
|
| 2027 |
+
"128253": {
|
| 2028 |
+
"content": "<|reserved_special_token_245|>",
|
| 2029 |
+
"lstrip": false,
|
| 2030 |
+
"normalized": false,
|
| 2031 |
+
"rstrip": false,
|
| 2032 |
+
"single_word": false,
|
| 2033 |
+
"special": true
|
| 2034 |
+
},
|
| 2035 |
+
"128254": {
|
| 2036 |
+
"content": "<|reserved_special_token_246|>",
|
| 2037 |
+
"lstrip": false,
|
| 2038 |
+
"normalized": false,
|
| 2039 |
+
"rstrip": false,
|
| 2040 |
+
"single_word": false,
|
| 2041 |
+
"special": true
|
| 2042 |
+
},
|
| 2043 |
+
"128255": {
|
| 2044 |
+
"content": "<|reserved_special_token_247|>",
|
| 2045 |
+
"lstrip": false,
|
| 2046 |
+
"normalized": false,
|
| 2047 |
+
"rstrip": false,
|
| 2048 |
+
"single_word": false,
|
| 2049 |
+
"special": true
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"additional_special_tokens": [
|
| 2053 |
+
"<|eom_id|>"
|
| 2054 |
+
],
|
| 2055 |
+
"bos_token": "<|begin_of_text|>",
|
| 2056 |
+
"clean_up_tokenization_spaces": true,
|
| 2057 |
+
"eos_token": "<|eot_id|>",
|
| 2058 |
+
"extra_special_tokens": {},
|
| 2059 |
+
"model_input_names": [
|
| 2060 |
+
"input_ids",
|
| 2061 |
+
"attention_mask"
|
| 2062 |
+
],
|
| 2063 |
+
"model_max_length": 131072,
|
| 2064 |
+
"pad_token": "<|eot_id|>",
|
| 2065 |
+
"padding_side": "right",
|
| 2066 |
+
"split_special_tokens": false,
|
| 2067 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 2068 |
+
}
|
llama3-os-121/train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 3.0,
|
| 3 |
+
"total_flos": 57488427909120.0,
|
| 4 |
+
"train_loss": 0.29718317360467233,
|
| 5 |
+
"train_runtime": 6776.8475,
|
| 6 |
+
"train_samples_per_second": 3.152,
|
| 7 |
+
"train_steps_per_second": 0.197
|
| 8 |
+
}
|
llama3-os-121/trainer_log.jsonl
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 1335, "loss": 0.8748, "lr": 6.716417910447762e-07, "epoch": 0.02247191011235955, "percentage": 0.75, "elapsed_time": "0:00:46", "remaining_time": "1:42:03"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 1335, "loss": 0.7324, "lr": 1.417910447761194e-06, "epoch": 0.0449438202247191, "percentage": 1.5, "elapsed_time": "0:01:30", "remaining_time": "1:39:18"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 1335, "loss": 0.614, "lr": 2.1641791044776118e-06, "epoch": 0.06741573033707865, "percentage": 2.25, "elapsed_time": "0:02:19", "remaining_time": "1:41:11"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 1335, "loss": 0.5453, "lr": 2.9104477611940303e-06, "epoch": 0.0898876404494382, "percentage": 3.0, "elapsed_time": "0:03:04", "remaining_time": "1:39:33"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 1335, "loss": 0.5324, "lr": 3.656716417910448e-06, "epoch": 0.11235955056179775, "percentage": 3.75, "elapsed_time": "0:03:50", "remaining_time": "1:38:32"}
|
| 6 |
+
{"current_steps": 50, "total_steps": 1335, "eval_loss": 0.49069538712501526, "epoch": 0.11235955056179775, "percentage": 3.75, "elapsed_time": "0:04:15", "remaining_time": "1:49:14"}
|
| 7 |
+
{"current_steps": 60, "total_steps": 1335, "loss": 0.5322, "lr": 4.402985074626866e-06, "epoch": 0.1348314606741573, "percentage": 4.49, "elapsed_time": "0:05:02", "remaining_time": "1:47:03"}
|
| 8 |
+
{"current_steps": 70, "total_steps": 1335, "loss": 0.4996, "lr": 5.149253731343285e-06, "epoch": 0.15730337078651685, "percentage": 5.24, "elapsed_time": "0:05:46", "remaining_time": "1:44:13"}
|
| 9 |
+
{"current_steps": 80, "total_steps": 1335, "loss": 0.5127, "lr": 5.895522388059702e-06, "epoch": 0.1797752808988764, "percentage": 5.99, "elapsed_time": "0:06:30", "remaining_time": "1:41:58"}
|
| 10 |
+
{"current_steps": 90, "total_steps": 1335, "loss": 0.4678, "lr": 6.64179104477612e-06, "epoch": 0.20224719101123595, "percentage": 6.74, "elapsed_time": "0:07:14", "remaining_time": "1:40:07"}
|
| 11 |
+
{"current_steps": 100, "total_steps": 1335, "loss": 0.5193, "lr": 7.3880597014925385e-06, "epoch": 0.2247191011235955, "percentage": 7.49, "elapsed_time": "0:08:03", "remaining_time": "1:39:37"}
|
| 12 |
+
{"current_steps": 100, "total_steps": 1335, "eval_loss": 0.493939608335495, "epoch": 0.2247191011235955, "percentage": 7.49, "elapsed_time": "0:08:28", "remaining_time": "1:44:45"}
|
| 13 |
+
{"current_steps": 110, "total_steps": 1335, "loss": 0.5423, "lr": 8.134328358208955e-06, "epoch": 0.24719101123595505, "percentage": 8.24, "elapsed_time": "0:09:16", "remaining_time": "1:43:15"}
|
| 14 |
+
{"current_steps": 120, "total_steps": 1335, "loss": 0.5233, "lr": 8.880597014925374e-06, "epoch": 0.2696629213483146, "percentage": 8.99, "elapsed_time": "0:10:02", "remaining_time": "1:41:35"}
|
| 15 |
+
{"current_steps": 130, "total_steps": 1335, "loss": 0.5423, "lr": 9.626865671641792e-06, "epoch": 0.29213483146067415, "percentage": 9.74, "elapsed_time": "0:10:47", "remaining_time": "1:40:01"}
|
| 16 |
+
{"current_steps": 140, "total_steps": 1335, "loss": 0.5527, "lr": 9.999572350905325e-06, "epoch": 0.3146067415730337, "percentage": 10.49, "elapsed_time": "0:11:35", "remaining_time": "1:38:54"}
|
| 17 |
+
{"current_steps": 150, "total_steps": 1335, "loss": 0.541, "lr": 9.996151597056391e-06, "epoch": 0.33707865168539325, "percentage": 11.24, "elapsed_time": "0:12:17", "remaining_time": "1:37:04"}
|
| 18 |
+
{"current_steps": 150, "total_steps": 1335, "eval_loss": 0.5116215348243713, "epoch": 0.33707865168539325, "percentage": 11.24, "elapsed_time": "0:12:43", "remaining_time": "1:40:28"}
|
| 19 |
+
{"current_steps": 160, "total_steps": 1335, "loss": 0.5541, "lr": 9.98931242987009e-06, "epoch": 0.3595505617977528, "percentage": 11.99, "elapsed_time": "0:13:27", "remaining_time": "1:38:49"}
|
| 20 |
+
{"current_steps": 170, "total_steps": 1335, "loss": 0.5233, "lr": 9.979059528768146e-06, "epoch": 0.38202247191011235, "percentage": 12.73, "elapsed_time": "0:14:12", "remaining_time": "1:37:23"}
|
| 21 |
+
{"current_steps": 180, "total_steps": 1335, "loss": 0.4969, "lr": 9.96539990888074e-06, "epoch": 0.4044943820224719, "percentage": 13.48, "elapsed_time": "0:14:56", "remaining_time": "1:35:54"}
|
| 22 |
+
{"current_steps": 190, "total_steps": 1335, "loss": 0.481, "lr": 9.948342916246702e-06, "epoch": 0.42696629213483145, "percentage": 14.23, "elapsed_time": "0:15:43", "remaining_time": "1:34:47"}
|
| 23 |
+
{"current_steps": 200, "total_steps": 1335, "loss": 0.5009, "lr": 9.92790022141885e-06, "epoch": 0.449438202247191, "percentage": 14.98, "elapsed_time": "0:16:38", "remaining_time": "1:34:26"}
|
| 24 |
+
{"current_steps": 200, "total_steps": 1335, "eval_loss": 0.4970722496509552, "epoch": 0.449438202247191, "percentage": 14.98, "elapsed_time": "0:17:03", "remaining_time": "1:36:48"}
|
| 25 |
+
{"current_steps": 210, "total_steps": 1335, "loss": 0.5279, "lr": 9.904085811478901e-06, "epoch": 0.47191011235955055, "percentage": 15.73, "elapsed_time": "0:18:06", "remaining_time": "1:36:58"}
|
| 26 |
+
{"current_steps": 220, "total_steps": 1335, "loss": 0.5073, "lr": 9.876915980467373e-06, "epoch": 0.4943820224719101, "percentage": 16.48, "elapsed_time": "0:18:49", "remaining_time": "1:35:24"}
|
| 27 |
+
{"current_steps": 230, "total_steps": 1335, "loss": 0.5346, "lr": 9.846409318235056e-06, "epoch": 0.5168539325842697, "percentage": 17.23, "elapsed_time": "0:19:35", "remaining_time": "1:34:06"}
|
| 28 |
+
{"current_steps": 240, "total_steps": 1335, "loss": 0.5289, "lr": 9.812586697723658e-06, "epoch": 0.5393258426966292, "percentage": 17.98, "elapsed_time": "0:20:21", "remaining_time": "1:32:54"}
|
| 29 |
+
{"current_steps": 250, "total_steps": 1335, "loss": 0.4856, "lr": 9.775471260684346e-06, "epoch": 0.5617977528089888, "percentage": 18.73, "elapsed_time": "0:21:04", "remaining_time": "1:31:29"}
|
| 30 |
+
{"current_steps": 250, "total_steps": 1335, "eval_loss": 0.4789491295814514, "epoch": 0.5617977528089888, "percentage": 18.73, "elapsed_time": "0:21:29", "remaining_time": "1:33:18"}
|
| 31 |
+
{"current_steps": 260, "total_steps": 1335, "loss": 0.4713, "lr": 9.735088401843948e-06, "epoch": 0.5842696629213483, "percentage": 19.48, "elapsed_time": "0:22:14", "remaining_time": "1:31:57"}
|
| 32 |
+
{"current_steps": 270, "total_steps": 1335, "loss": 0.5077, "lr": 9.691465751529645e-06, "epoch": 0.6067415730337079, "percentage": 20.22, "elapsed_time": "0:22:57", "remaining_time": "1:30:34"}
|
| 33 |
+
{"current_steps": 280, "total_steps": 1335, "loss": 0.5148, "lr": 9.644633156764038e-06, "epoch": 0.6292134831460674, "percentage": 20.97, "elapsed_time": "0:23:42", "remaining_time": "1:29:20"}
|
| 34 |
+
{"current_steps": 290, "total_steps": 1335, "loss": 0.4998, "lr": 9.594622660843547e-06, "epoch": 0.651685393258427, "percentage": 21.72, "elapsed_time": "0:24:26", "remaining_time": "1:28:05"}
|
| 35 |
+
{"current_steps": 300, "total_steps": 1335, "loss": 0.4855, "lr": 9.54146848141408e-06, "epoch": 0.6741573033707865, "percentage": 22.47, "elapsed_time": "0:25:11", "remaining_time": "1:26:55"}
|
| 36 |
+
{"current_steps": 300, "total_steps": 1335, "eval_loss": 0.4700905382633209, "epoch": 0.6741573033707865, "percentage": 22.47, "elapsed_time": "0:25:36", "remaining_time": "1:28:21"}
|
| 37 |
+
{"current_steps": 310, "total_steps": 1335, "loss": 0.4825, "lr": 9.48520698705901e-06, "epoch": 0.6966292134831461, "percentage": 23.22, "elapsed_time": "0:26:21", "remaining_time": "1:27:08"}
|
| 38 |
+
{"current_steps": 320, "total_steps": 1335, "loss": 0.4918, "lr": 9.425876672415448e-06, "epoch": 0.7191011235955056, "percentage": 23.97, "elapsed_time": "0:27:04", "remaining_time": "1:25:53"}
|
| 39 |
+
{"current_steps": 330, "total_steps": 1335, "loss": 0.4847, "lr": 9.363518131835857e-06, "epoch": 0.7415730337078652, "percentage": 24.72, "elapsed_time": "0:27:49", "remaining_time": "1:24:45"}
|
| 40 |
+
{"current_steps": 340, "total_steps": 1335, "loss": 0.4721, "lr": 9.298174031613019e-06, "epoch": 0.7640449438202247, "percentage": 25.47, "elapsed_time": "0:28:33", "remaining_time": "1:23:34"}
|
| 41 |
+
{"current_steps": 350, "total_steps": 1335, "loss": 0.4586, "lr": 9.229889080787357e-06, "epoch": 0.7865168539325843, "percentage": 26.22, "elapsed_time": "0:29:15", "remaining_time": "1:22:20"}
|
| 42 |
+
{"current_steps": 350, "total_steps": 1335, "eval_loss": 0.4575425386428833, "epoch": 0.7865168539325843, "percentage": 26.22, "elapsed_time": "0:29:41", "remaining_time": "1:23:34"}
|
| 43 |
+
{"current_steps": 360, "total_steps": 1335, "loss": 0.4914, "lr": 9.1587100005566e-06, "epoch": 0.8089887640449438, "percentage": 26.97, "elapsed_time": "0:30:25", "remaining_time": "1:22:23"}
|
| 44 |
+
{"current_steps": 370, "total_steps": 1335, "loss": 0.4282, "lr": 9.0846854923087e-06, "epoch": 0.8314606741573034, "percentage": 27.72, "elapsed_time": "0:31:10", "remaining_time": "1:21:18"}
|
| 45 |
+
{"current_steps": 380, "total_steps": 1335, "loss": 0.4505, "lr": 9.007866204299896e-06, "epoch": 0.8539325842696629, "percentage": 28.46, "elapsed_time": "0:31:56", "remaining_time": "1:20:17"}
|
| 46 |
+
{"current_steps": 390, "total_steps": 1335, "loss": 0.4597, "lr": 8.9283046970007e-06, "epoch": 0.8764044943820225, "percentage": 29.21, "elapsed_time": "0:32:40", "remaining_time": "1:19:10"}
|
| 47 |
+
{"current_steps": 400, "total_steps": 1335, "loss": 0.4786, "lr": 8.846055407133539e-06, "epoch": 0.898876404494382, "percentage": 29.96, "elapsed_time": "0:33:23", "remaining_time": "1:18:03"}
|
| 48 |
+
{"current_steps": 400, "total_steps": 1335, "eval_loss": 0.44720685482025146, "epoch": 0.898876404494382, "percentage": 29.96, "elapsed_time": "0:33:50", "remaining_time": "1:19:05"}
|
| 49 |
+
{"current_steps": 410, "total_steps": 1335, "loss": 0.4705, "lr": 8.761174610426642e-06, "epoch": 0.9213483146067416, "percentage": 30.71, "elapsed_time": "0:34:32", "remaining_time": "1:17:55"}
|
| 50 |
+
{"current_steps": 420, "total_steps": 1335, "loss": 0.4486, "lr": 8.673720383109666e-06, "epoch": 0.9438202247191011, "percentage": 31.46, "elapsed_time": "0:35:16", "remaining_time": "1:16:51"}
|
| 51 |
+
{"current_steps": 430, "total_steps": 1335, "loss": 0.4405, "lr": 8.583752562177401e-06, "epoch": 0.9662921348314607, "percentage": 32.21, "elapsed_time": "0:36:00", "remaining_time": "1:15:46"}
|
| 52 |
+
{"current_steps": 440, "total_steps": 1335, "loss": 0.4532, "lr": 8.491332704448734e-06, "epoch": 0.9887640449438202, "percentage": 32.96, "elapsed_time": "0:36:46", "remaining_time": "1:14:47"}
|
| 53 |
+
{"current_steps": 450, "total_steps": 1335, "loss": 0.39, "lr": 8.396524044448913e-06, "epoch": 1.0112359550561798, "percentage": 33.71, "elapsed_time": "0:37:32", "remaining_time": "1:13:49"}
|
| 54 |
+
{"current_steps": 450, "total_steps": 1335, "eval_loss": 0.43022894859313965, "epoch": 1.0112359550561798, "percentage": 33.71, "elapsed_time": "0:37:57", "remaining_time": "1:14:38"}
|
| 55 |
+
{"current_steps": 460, "total_steps": 1335, "loss": 0.2934, "lr": 8.299391451143887e-06, "epoch": 1.0337078651685394, "percentage": 34.46, "elapsed_time": "0:38:40", "remaining_time": "1:13:34"}
|
| 56 |
+
{"current_steps": 470, "total_steps": 1335, "loss": 0.29, "lr": 8.20000138355637e-06, "epoch": 1.0561797752808988, "percentage": 35.21, "elapsed_time": "0:39:25", "remaining_time": "1:12:33"}
|
| 57 |
+
{"current_steps": 480, "total_steps": 1335, "loss": 0.2778, "lr": 8.098421845293946e-06, "epoch": 1.0786516853932584, "percentage": 35.96, "elapsed_time": "0:40:11", "remaining_time": "1:11:34"}
|
| 58 |
+
{"current_steps": 490, "total_steps": 1335, "loss": 0.2847, "lr": 7.994722338020375e-06, "epoch": 1.101123595505618, "percentage": 36.7, "elapsed_time": "0:40:53", "remaining_time": "1:10:31"}
|
| 59 |
+
{"current_steps": 500, "total_steps": 1335, "loss": 0.3046, "lr": 7.888973813901909e-06, "epoch": 1.1235955056179776, "percentage": 37.45, "elapsed_time": "0:41:37", "remaining_time": "1:09:30"}
|
| 60 |
+
{"current_steps": 500, "total_steps": 1335, "eval_loss": 0.4396440088748932, "epoch": 1.1235955056179776, "percentage": 37.45, "elapsed_time": "0:42:01", "remaining_time": "1:10:11"}
|
| 61 |
+
{"current_steps": 510, "total_steps": 1335, "loss": 0.3076, "lr": 7.781248627061166e-06, "epoch": 1.146067415730337, "percentage": 38.2, "elapsed_time": "0:43:05", "remaining_time": "1:09:42"}
|
| 62 |
+
{"current_steps": 520, "total_steps": 1335, "loss": 0.294, "lr": 7.671620484071758e-06, "epoch": 1.1685393258426966, "percentage": 38.95, "elapsed_time": "0:43:51", "remaining_time": "1:08:43"}
|
| 63 |
+
{"current_steps": 530, "total_steps": 1335, "loss": 0.2903, "lr": 7.56016439352757e-06, "epoch": 1.1910112359550562, "percentage": 39.7, "elapsed_time": "0:44:33", "remaining_time": "1:07:41"}
|
| 64 |
+
{"current_steps": 540, "total_steps": 1335, "loss": 0.2932, "lr": 7.446956614721191e-06, "epoch": 1.2134831460674158, "percentage": 40.45, "elapsed_time": "0:45:17", "remaining_time": "1:06:41"}
|
| 65 |
+
{"current_steps": 550, "total_steps": 1335, "loss": 0.2974, "lr": 7.33207460546659e-06, "epoch": 1.2359550561797752, "percentage": 41.2, "elapsed_time": "0:46:12", "remaining_time": "1:05:57"}
|
| 66 |
+
{"current_steps": 550, "total_steps": 1335, "eval_loss": 0.42986103892326355, "epoch": 1.2359550561797752, "percentage": 41.2, "elapsed_time": "0:46:37", "remaining_time": "1:06:33"}
|
| 67 |
+
{"current_steps": 560, "total_steps": 1335, "loss": 0.2781, "lr": 7.215596969101762e-06, "epoch": 1.2584269662921348, "percentage": 41.95, "elapsed_time": "0:47:22", "remaining_time": "1:05:33"}
|
| 68 |
+
{"current_steps": 570, "total_steps": 1335, "loss": 0.2868, "lr": 7.097603400707595e-06, "epoch": 1.2808988764044944, "percentage": 42.7, "elapsed_time": "0:48:05", "remaining_time": "1:04:33"}
|
| 69 |
+
{"current_steps": 580, "total_steps": 1335, "loss": 0.2915, "lr": 6.978174632579754e-06, "epoch": 1.303370786516854, "percentage": 43.45, "elapsed_time": "0:48:59", "remaining_time": "1:03:46"}
|
| 70 |
+
{"current_steps": 590, "total_steps": 1335, "loss": 0.3, "lr": 6.857392378990895e-06, "epoch": 1.3258426966292136, "percentage": 44.19, "elapsed_time": "0:49:52", "remaining_time": "1:02:58"}
|
| 71 |
+
{"current_steps": 600, "total_steps": 1335, "loss": 0.2836, "lr": 6.735339280281001e-06, "epoch": 1.348314606741573, "percentage": 44.94, "elapsed_time": "0:50:34", "remaining_time": "1:01:57"}
|
| 72 |
+
{"current_steps": 600, "total_steps": 1335, "eval_loss": 0.424435555934906, "epoch": 1.348314606741573, "percentage": 44.94, "elapsed_time": "0:50:59", "remaining_time": "1:02:27"}
|
| 73 |
+
{"current_steps": 610, "total_steps": 1335, "loss": 0.2812, "lr": 6.6120988463140925e-06, "epoch": 1.3707865168539326, "percentage": 45.69, "elapsed_time": "0:51:45", "remaining_time": "1:01:31"}
|
| 74 |
+
{"current_steps": 620, "total_steps": 1335, "loss": 0.274, "lr": 6.487755399340005e-06, "epoch": 1.3932584269662922, "percentage": 46.44, "elapsed_time": "0:52:31", "remaining_time": "1:00:34"}
|
| 75 |
+
{"current_steps": 630, "total_steps": 1335, "loss": 0.3027, "lr": 6.362394016300315e-06, "epoch": 1.4157303370786516, "percentage": 47.19, "elapsed_time": "0:53:16", "remaining_time": "0:59:36"}
|
| 76 |
+
{"current_steps": 640, "total_steps": 1335, "loss": 0.2783, "lr": 6.2361004706179195e-06, "epoch": 1.4382022471910112, "percentage": 47.94, "elapsed_time": "0:53:59", "remaining_time": "0:58:38"}
|
| 77 |
+
{"current_steps": 650, "total_steps": 1335, "loss": 0.2679, "lr": 6.108961173510052e-06, "epoch": 1.4606741573033708, "percentage": 48.69, "elapsed_time": "0:54:41", "remaining_time": "0:57:38"}
|
| 78 |
+
{"current_steps": 650, "total_steps": 1335, "eval_loss": 0.41811907291412354, "epoch": 1.4606741573033708, "percentage": 48.69, "elapsed_time": "0:55:06", "remaining_time": "0:58:05"}
|
| 79 |
+
{"current_steps": 660, "total_steps": 1335, "loss": 0.2836, "lr": 5.981063114864928e-06, "epoch": 1.4831460674157304, "percentage": 49.44, "elapsed_time": "0:55:50", "remaining_time": "0:57:06"}
|
| 80 |
+
{"current_steps": 670, "total_steps": 1335, "loss": 0.2878, "lr": 5.8524938037224555e-06, "epoch": 1.50561797752809, "percentage": 50.19, "elapsed_time": "0:56:33", "remaining_time": "0:56:07"}
|
| 81 |
+
{"current_steps": 680, "total_steps": 1335, "loss": 0.2559, "lr": 5.723341208399737e-06, "epoch": 1.5280898876404494, "percentage": 50.94, "elapsed_time": "0:57:20", "remaining_time": "0:55:14"}
|
| 82 |
+
{"current_steps": 690, "total_steps": 1335, "loss": 0.2913, "lr": 5.593693696302333e-06, "epoch": 1.550561797752809, "percentage": 51.69, "elapsed_time": "0:58:03", "remaining_time": "0:54:16"}
|
| 83 |
+
{"current_steps": 700, "total_steps": 1335, "loss": 0.3064, "lr": 5.4636399734624534e-06, "epoch": 1.5730337078651684, "percentage": 52.43, "elapsed_time": "0:58:48", "remaining_time": "0:53:21"}
|
| 84 |
+
{"current_steps": 700, "total_steps": 1335, "eval_loss": 0.4070671498775482, "epoch": 1.5730337078651684, "percentage": 52.43, "elapsed_time": "0:59:13", "remaining_time": "0:53:43"}
|
| 85 |
+
{"current_steps": 710, "total_steps": 1335, "loss": 0.2558, "lr": 5.333269023845478e-06, "epoch": 1.595505617977528, "percentage": 53.18, "elapsed_time": "1:00:01", "remaining_time": "0:52:50"}
|
| 86 |
+
{"current_steps": 720, "total_steps": 1335, "loss": 0.2715, "lr": 5.20267004846629e-06, "epoch": 1.6179775280898876, "percentage": 53.93, "elapsed_time": "1:00:45", "remaining_time": "0:51:53"}
|
| 87 |
+
{"current_steps": 730, "total_steps": 1335, "loss": 0.2779, "lr": 5.071932404357119e-06, "epoch": 1.6404494382022472, "percentage": 54.68, "elapsed_time": "1:01:31", "remaining_time": "0:50:59"}
|
| 88 |
+
{"current_steps": 740, "total_steps": 1335, "loss": 0.2867, "lr": 4.94114554342863e-06, "epoch": 1.6629213483146068, "percentage": 55.43, "elapsed_time": "1:02:15", "remaining_time": "0:50:03"}
|
| 89 |
+
{"current_steps": 750, "total_steps": 1335, "loss": 0.2741, "lr": 4.81039895126609e-06, "epoch": 1.6853932584269664, "percentage": 56.18, "elapsed_time": "1:02:59", "remaining_time": "0:49:07"}
|
| 90 |
+
{"current_steps": 750, "total_steps": 1335, "eval_loss": 0.40253934264183044, "epoch": 1.6853932584269664, "percentage": 56.18, "elapsed_time": "1:03:24", "remaining_time": "0:49:27"}
|
| 91 |
+
{"current_steps": 760, "total_steps": 1335, "loss": 0.2562, "lr": 4.679782085902503e-06, "epoch": 1.7078651685393258, "percentage": 56.93, "elapsed_time": "1:04:09", "remaining_time": "0:48:32"}
|
| 92 |
+
{"current_steps": 770, "total_steps": 1335, "loss": 0.2648, "lr": 4.549384316610593e-06, "epoch": 1.7303370786516854, "percentage": 57.68, "elapsed_time": "1:04:53", "remaining_time": "0:47:37"}
|
| 93 |
+
{"current_steps": 780, "total_steps": 1335, "loss": 0.2632, "lr": 4.419294862755515e-06, "epoch": 1.7528089887640448, "percentage": 58.43, "elapsed_time": "1:05:38", "remaining_time": "0:46:42"}
|
| 94 |
+
{"current_steps": 790, "total_steps": 1335, "loss": 0.2713, "lr": 4.289602732750138e-06, "epoch": 1.7752808988764044, "percentage": 59.18, "elapsed_time": "1:06:22", "remaining_time": "0:45:47"}
|
| 95 |
+
{"current_steps": 800, "total_steps": 1335, "loss": 0.2558, "lr": 4.1603966631546634e-06, "epoch": 1.797752808988764, "percentage": 59.93, "elapsed_time": "1:07:11", "remaining_time": "0:44:56"}
|
| 96 |
+
{"current_steps": 800, "total_steps": 1335, "eval_loss": 0.39331701397895813, "epoch": 1.797752808988764, "percentage": 59.93, "elapsed_time": "1:07:36", "remaining_time": "0:45:12"}
|
| 97 |
+
{"current_steps": 810, "total_steps": 1335, "loss": 0.2444, "lr": 4.031765057962243e-06, "epoch": 1.8202247191011236, "percentage": 60.67, "elapsed_time": "1:08:20", "remaining_time": "0:44:17"}
|
| 98 |
+
{"current_steps": 820, "total_steps": 1335, "loss": 0.2401, "lr": 3.9037959281121474e-06, "epoch": 1.8426966292134832, "percentage": 61.42, "elapsed_time": "1:09:10", "remaining_time": "0:43:26"}
|
| 99 |
+
{"current_steps": 830, "total_steps": 1335, "loss": 0.2726, "lr": 3.776576831271865e-06, "epoch": 1.8651685393258428, "percentage": 62.17, "elapsed_time": "1:10:00", "remaining_time": "0:42:35"}
|
| 100 |
+
{"current_steps": 840, "total_steps": 1335, "loss": 0.2528, "lr": 3.65019481192933e-06, "epoch": 1.8876404494382022, "percentage": 62.92, "elapsed_time": "1:10:42", "remaining_time": "0:41:40"}
|
| 101 |
+
{"current_steps": 850, "total_steps": 1335, "loss": 0.2701, "lr": 3.524736341836272e-06, "epoch": 1.9101123595505618, "percentage": 63.67, "elapsed_time": "1:11:25", "remaining_time": "0:40:45"}
|
| 102 |
+
{"current_steps": 850, "total_steps": 1335, "eval_loss": 0.3823501169681549, "epoch": 1.9101123595505618, "percentage": 63.67, "elapsed_time": "1:11:50", "remaining_time": "0:40:59"}
|
| 103 |
+
{"current_steps": 860, "total_steps": 1335, "loss": 0.2511, "lr": 3.400287260843454e-06, "epoch": 1.9325842696629212, "percentage": 64.42, "elapsed_time": "1:12:35", "remaining_time": "0:40:05"}
|
| 104 |
+
{"current_steps": 870, "total_steps": 1335, "loss": 0.255, "lr": 3.2769327181682307e-06, "epoch": 1.9550561797752808, "percentage": 65.17, "elapsed_time": "1:13:20", "remaining_time": "0:39:11"}
|
| 105 |
+
{"current_steps": 880, "total_steps": 1335, "loss": 0.253, "lr": 3.1547571141346756e-06, "epoch": 1.9775280898876404, "percentage": 65.92, "elapsed_time": "1:14:05", "remaining_time": "0:38:18"}
|
| 106 |
+
{"current_steps": 890, "total_steps": 1335, "loss": 0.2729, "lr": 3.0338440424260897e-06, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:14:51", "remaining_time": "0:37:25"}
|
| 107 |
+
{"current_steps": 900, "total_steps": 1335, "loss": 0.1197, "lr": 2.9142762328894273e-06, "epoch": 2.0224719101123596, "percentage": 67.42, "elapsed_time": "1:15:35", "remaining_time": "0:36:32"}
|
| 108 |
+
{"current_steps": 900, "total_steps": 1335, "eval_loss": 0.440464586019516, "epoch": 2.0224719101123596, "percentage": 67.42, "elapsed_time": "1:16:00", "remaining_time": "0:36:44"}
|
| 109 |
+
{"current_steps": 910, "total_steps": 1335, "loss": 0.1103, "lr": 2.7961354949307677e-06, "epoch": 2.044943820224719, "percentage": 68.16, "elapsed_time": "1:16:44", "remaining_time": "0:35:50"}
|
| 110 |
+
{"current_steps": 920, "total_steps": 1335, "loss": 0.1058, "lr": 2.6795026615405635e-06, "epoch": 2.067415730337079, "percentage": 68.91, "elapsed_time": "1:17:27", "remaining_time": "0:34:56"}
|
| 111 |
+
{"current_steps": 930, "total_steps": 1335, "loss": 0.0976, "lr": 2.564457533986944e-06, "epoch": 2.0898876404494384, "percentage": 69.66, "elapsed_time": "1:18:14", "remaining_time": "0:34:04"}
|
| 112 |
+
{"current_steps": 940, "total_steps": 1335, "loss": 0.1092, "lr": 2.451078827214964e-06, "epoch": 2.1123595505617976, "percentage": 70.41, "elapsed_time": "1:18:59", "remaining_time": "0:33:11"}
|
| 113 |
+
{"current_steps": 950, "total_steps": 1335, "loss": 0.104, "lr": 2.339444115989093e-06, "epoch": 2.134831460674157, "percentage": 71.16, "elapsed_time": "1:19:44", "remaining_time": "0:32:18"}
|
| 114 |
+
{"current_steps": 950, "total_steps": 1335, "eval_loss": 0.43039175868034363, "epoch": 2.134831460674157, "percentage": 71.16, "elapsed_time": "1:20:09", "remaining_time": "0:32:29"}
|
| 115 |
+
{"current_steps": 960, "total_steps": 1335, "loss": 0.1067, "lr": 2.2296297818158458e-06, "epoch": 2.157303370786517, "percentage": 71.91, "elapsed_time": "1:21:01", "remaining_time": "0:31:39"}
|
| 116 |
+
{"current_steps": 970, "total_steps": 1335, "loss": 0.1074, "lr": 2.121710960682851e-06, "epoch": 2.1797752808988764, "percentage": 72.66, "elapsed_time": "1:21:44", "remaining_time": "0:30:45"}
|
| 117 |
+
{"current_steps": 980, "total_steps": 1335, "loss": 0.1073, "lr": 2.0157614916501e-06, "epoch": 2.202247191011236, "percentage": 73.41, "elapsed_time": "1:22:28", "remaining_time": "0:29:52"}
|
| 118 |
+
{"current_steps": 990, "total_steps": 1335, "loss": 0.1048, "lr": 1.9118538663285874e-06, "epoch": 2.2247191011235956, "percentage": 74.16, "elapsed_time": "1:23:22", "remaining_time": "0:29:03"}
|
| 119 |
+
{"current_steps": 1000, "total_steps": 1335, "loss": 0.1085, "lr": 1.8100591792808652e-06, "epoch": 2.247191011235955, "percentage": 74.91, "elapsed_time": "1:24:05", "remaining_time": "0:28:10"}
|
| 120 |
+
{"current_steps": 1000, "total_steps": 1335, "eval_loss": 0.4354311227798462, "epoch": 2.247191011235955, "percentage": 74.91, "elapsed_time": "1:24:30", "remaining_time": "0:28:18"}
|
| 121 |
+
{"current_steps": 1010, "total_steps": 1335, "loss": 0.1066, "lr": 1.7104470793774959e-06, "epoch": 2.2696629213483144, "percentage": 75.66, "elapsed_time": "1:25:33", "remaining_time": "0:27:31"}
|
| 122 |
+
{"current_steps": 1020, "total_steps": 1335, "loss": 0.1049, "lr": 1.613085722142636e-06, "epoch": 2.292134831460674, "percentage": 76.4, "elapsed_time": "1:26:17", "remaining_time": "0:26:39"}
|
| 123 |
+
{"current_steps": 1030, "total_steps": 1335, "loss": 0.1054, "lr": 1.5180417231214001e-06, "epoch": 2.3146067415730336, "percentage": 77.15, "elapsed_time": "1:27:01", "remaining_time": "0:25:46"}
|
| 124 |
+
{"current_steps": 1040, "total_steps": 1335, "loss": 0.1097, "lr": 1.425380112300887e-06, "epoch": 2.337078651685393, "percentage": 77.9, "elapsed_time": "1:27:49", "remaining_time": "0:24:54"}
|
| 125 |
+
{"current_steps": 1050, "total_steps": 1335, "loss": 0.1004, "lr": 1.3351642896160522e-06, "epoch": 2.359550561797753, "percentage": 78.65, "elapsed_time": "1:28:43", "remaining_time": "0:24:04"}
|
| 126 |
+
{"current_steps": 1050, "total_steps": 1335, "eval_loss": 0.4359316825866699, "epoch": 2.359550561797753, "percentage": 78.65, "elapsed_time": "1:29:08", "remaining_time": "0:24:11"}
|
| 127 |
+
{"current_steps": 1060, "total_steps": 1335, "loss": 0.1015, "lr": 1.247455981570892e-06, "epoch": 2.3820224719101124, "percentage": 79.4, "elapsed_time": "1:29:54", "remaining_time": "0:23:19"}
|
| 128 |
+
{"current_steps": 1070, "total_steps": 1335, "loss": 0.0977, "lr": 1.162315199004585e-06, "epoch": 2.404494382022472, "percentage": 80.15, "elapsed_time": "1:30:38", "remaining_time": "0:22:26"}
|
| 129 |
+
{"current_steps": 1080, "total_steps": 1335, "loss": 0.1044, "lr": 1.0798001960315313e-06, "epoch": 2.4269662921348316, "percentage": 80.9, "elapsed_time": "1:31:22", "remaining_time": "0:21:34"}
|
| 130 |
+
{"current_steps": 1090, "total_steps": 1335, "loss": 0.0973, "lr": 9.999674301833328e-07, "epoch": 2.449438202247191, "percentage": 81.65, "elapsed_time": "1:32:16", "remaining_time": "0:20:44"}
|
| 131 |
+
{"current_steps": 1100, "total_steps": 1335, "loss": 0.0944, "lr": 9.228715237800395e-07, "epoch": 2.4719101123595504, "percentage": 82.4, "elapsed_time": "1:32:58", "remaining_time": "0:19:51"}
|
| 132 |
+
{"current_steps": 1100, "total_steps": 1335, "eval_loss": 0.4427347481250763, "epoch": 2.4719101123595504, "percentage": 82.4, "elapsed_time": "1:33:24", "remaining_time": "0:19:57"}
|
| 133 |
+
{"current_steps": 1110, "total_steps": 1335, "loss": 0.0907, "lr": 8.485652265570376e-07, "epoch": 2.49438202247191, "percentage": 83.15, "elapsed_time": "1:34:07", "remaining_time": "0:19:04"}
|
| 134 |
+
{"current_steps": 1120, "total_steps": 1335, "loss": 0.0888, "lr": 7.770993795731984e-07, "epoch": 2.5168539325842696, "percentage": 83.9, "elapsed_time": "1:34:52", "remaining_time": "0:18:12"}
|
| 135 |
+
{"current_steps": 1130, "total_steps": 1335, "loss": 0.1043, "lr": 7.085228804249538e-07, "epoch": 2.539325842696629, "percentage": 84.64, "elapsed_time": "1:35:37", "remaining_time": "0:17:20"}
|
| 136 |
+
{"current_steps": 1140, "total_steps": 1335, "loss": 0.0977, "lr": 6.428826497900992e-07, "epoch": 2.561797752808989, "percentage": 85.39, "elapsed_time": "1:36:22", "remaining_time": "0:16:29"}
|
| 137 |
+
{"current_steps": 1150, "total_steps": 1335, "loss": 0.0984, "lr": 5.802235993242428e-07, "epoch": 2.5842696629213484, "percentage": 86.14, "elapsed_time": "1:37:07", "remaining_time": "0:15:37"}
|
| 138 |
+
{"current_steps": 1150, "total_steps": 1335, "eval_loss": 0.43664875626564026, "epoch": 2.5842696629213484, "percentage": 86.14, "elapsed_time": "1:37:33", "remaining_time": "0:15:41"}
|
| 139 |
+
{"current_steps": 1160, "total_steps": 1335, "loss": 0.1038, "lr": 5.205886009318184e-07, "epoch": 2.606741573033708, "percentage": 86.89, "elapsed_time": "1:38:18", "remaining_time": "0:14:49"}
|
| 140 |
+
{"current_steps": 1170, "total_steps": 1335, "loss": 0.0911, "lr": 4.6401845743273945e-07, "epoch": 2.629213483146067, "percentage": 87.64, "elapsed_time": "1:39:02", "remaining_time": "0:13:58"}
|
| 141 |
+
{"current_steps": 1180, "total_steps": 1335, "loss": 0.0928, "lr": 4.1055187464473125e-07, "epoch": 2.6516853932584272, "percentage": 88.39, "elapsed_time": "1:39:45", "remaining_time": "0:13:06"}
|
| 142 |
+
{"current_steps": 1190, "total_steps": 1335, "loss": 0.0911, "lr": 3.602254349004447e-07, "epoch": 2.6741573033707864, "percentage": 89.14, "elapsed_time": "1:40:28", "remaining_time": "0:12:14"}
|
| 143 |
+
{"current_steps": 1200, "total_steps": 1335, "loss": 0.1041, "lr": 3.1307357201749157e-07, "epoch": 2.696629213483146, "percentage": 89.89, "elapsed_time": "1:41:12", "remaining_time": "0:11:23"}
|
| 144 |
+
{"current_steps": 1200, "total_steps": 1335, "eval_loss": 0.4398299753665924, "epoch": 2.696629213483146, "percentage": 89.89, "elapsed_time": "1:41:36", "remaining_time": "0:11:25"}
|
| 145 |
+
{"current_steps": 1210, "total_steps": 1335, "loss": 0.0903, "lr": 2.691285477384986e-07, "epoch": 2.7191011235955056, "percentage": 90.64, "elapsed_time": "1:42:20", "remaining_time": "0:10:34"}
|
| 146 |
+
{"current_steps": 1220, "total_steps": 1335, "loss": 0.0955, "lr": 2.284204296573328e-07, "epoch": 2.741573033707865, "percentage": 91.39, "elapsed_time": "1:43:03", "remaining_time": "0:09:42"}
|
| 147 |
+
{"current_steps": 1230, "total_steps": 1335, "loss": 0.1018, "lr": 1.9097707064656523e-07, "epoch": 2.764044943820225, "percentage": 92.13, "elapsed_time": "1:43:47", "remaining_time": "0:08:51"}
|
| 148 |
+
{"current_steps": 1240, "total_steps": 1335, "loss": 0.0834, "lr": 1.568240898002843e-07, "epoch": 2.7865168539325844, "percentage": 92.88, "elapsed_time": "1:44:34", "remaining_time": "0:08:00"}
|
| 149 |
+
{"current_steps": 1250, "total_steps": 1335, "loss": 0.0951, "lr": 1.259848549052689e-07, "epoch": 2.808988764044944, "percentage": 93.63, "elapsed_time": "1:45:19", "remaining_time": "0:07:09"}
|
| 150 |
+
{"current_steps": 1250, "total_steps": 1335, "eval_loss": 0.437627911567688, "epoch": 2.808988764044944, "percentage": 93.63, "elapsed_time": "1:45:44", "remaining_time": "0:07:11"}
|
| 151 |
+
{"current_steps": 1260, "total_steps": 1335, "loss": 0.0923, "lr": 9.848046645253184e-08, "epoch": 2.831460674157303, "percentage": 94.38, "elapsed_time": "1:46:29", "remaining_time": "0:06:20"}
|
| 152 |
+
{"current_steps": 1270, "total_steps": 1335, "loss": 0.0916, "lr": 7.432974320017216e-08, "epoch": 2.853932584269663, "percentage": 95.13, "elapsed_time": "1:47:14", "remaining_time": "0:05:29"}
|
| 153 |
+
{"current_steps": 1280, "total_steps": 1335, "loss": 0.0999, "lr": 5.354920929740048e-08, "epoch": 2.8764044943820224, "percentage": 95.88, "elapsed_time": "1:48:02", "remaining_time": "0:04:38"}
|
| 154 |
+
{"current_steps": 1290, "total_steps": 1335, "loss": 0.0943, "lr": 3.615308297856668e-08, "epoch": 2.898876404494382, "percentage": 96.63, "elapsed_time": "1:48:44", "remaining_time": "0:03:47"}
|
| 155 |
+
{"current_steps": 1300, "total_steps": 1335, "loss": 0.0804, "lr": 2.2153266834908927e-08, "epoch": 2.9213483146067416, "percentage": 97.38, "elapsed_time": "1:49:29", "remaining_time": "0:02:56"}
|
| 156 |
+
{"current_steps": 1300, "total_steps": 1335, "eval_loss": 0.43767842650413513, "epoch": 2.9213483146067416, "percentage": 97.38, "elapsed_time": "1:49:54", "remaining_time": "0:02:57"}
|
| 157 |
+
{"current_steps": 1310, "total_steps": 1335, "loss": 0.1001, "lr": 1.155933967069256e-08, "epoch": 2.943820224719101, "percentage": 98.13, "elapsed_time": "1:50:40", "remaining_time": "0:02:06"}
|
| 158 |
+
{"current_steps": 1320, "total_steps": 1335, "loss": 0.096, "lr": 4.378549949301536e-09, "epoch": 2.966292134831461, "percentage": 98.88, "elapsed_time": "1:51:27", "remaining_time": "0:01:15"}
|
| 159 |
+
{"current_steps": 1330, "total_steps": 1335, "loss": 0.0933, "lr": 6.158108337733782e-10, "epoch": 2.98876404494382, "percentage": 99.63, "elapsed_time": "1:52:11", "remaining_time": "0:00:25"}
|
| 160 |
+
{"current_steps": 1335, "total_steps": 1335, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "1:52:56", "remaining_time": "0:00:00"}
|
llama3-os-121/trainer_state.json
ADDED
|
@@ -0,0 +1,1182 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 50,
|
| 7 |
+
"global_step": 1335,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.02247191011235955,
|
| 14 |
+
"grad_norm": 17.14047476371622,
|
| 15 |
+
"learning_rate": 6.716417910447762e-07,
|
| 16 |
+
"loss": 0.8748,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0449438202247191,
|
| 21 |
+
"grad_norm": 8.472000851613938,
|
| 22 |
+
"learning_rate": 1.417910447761194e-06,
|
| 23 |
+
"loss": 0.7324,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.06741573033707865,
|
| 28 |
+
"grad_norm": 8.06528644822054,
|
| 29 |
+
"learning_rate": 2.1641791044776118e-06,
|
| 30 |
+
"loss": 0.614,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.0898876404494382,
|
| 35 |
+
"grad_norm": 7.027790298166711,
|
| 36 |
+
"learning_rate": 2.9104477611940303e-06,
|
| 37 |
+
"loss": 0.5453,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.11235955056179775,
|
| 42 |
+
"grad_norm": 7.765014276635496,
|
| 43 |
+
"learning_rate": 3.656716417910448e-06,
|
| 44 |
+
"loss": 0.5324,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.11235955056179775,
|
| 49 |
+
"eval_loss": 0.49069538712501526,
|
| 50 |
+
"eval_runtime": 24.963,
|
| 51 |
+
"eval_samples_per_second": 15.022,
|
| 52 |
+
"eval_steps_per_second": 3.766,
|
| 53 |
+
"step": 50
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"epoch": 0.1348314606741573,
|
| 57 |
+
"grad_norm": 5.476266519570965,
|
| 58 |
+
"learning_rate": 4.402985074626866e-06,
|
| 59 |
+
"loss": 0.5322,
|
| 60 |
+
"step": 60
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"epoch": 0.15730337078651685,
|
| 64 |
+
"grad_norm": 6.673062424117546,
|
| 65 |
+
"learning_rate": 5.149253731343285e-06,
|
| 66 |
+
"loss": 0.4996,
|
| 67 |
+
"step": 70
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"epoch": 0.1797752808988764,
|
| 71 |
+
"grad_norm": 5.867210391375941,
|
| 72 |
+
"learning_rate": 5.895522388059702e-06,
|
| 73 |
+
"loss": 0.5127,
|
| 74 |
+
"step": 80
|
| 75 |
+
},
|
| 76 |
+
{
|
| 77 |
+
"epoch": 0.20224719101123595,
|
| 78 |
+
"grad_norm": 4.86491013562436,
|
| 79 |
+
"learning_rate": 6.64179104477612e-06,
|
| 80 |
+
"loss": 0.4678,
|
| 81 |
+
"step": 90
|
| 82 |
+
},
|
| 83 |
+
{
|
| 84 |
+
"epoch": 0.2247191011235955,
|
| 85 |
+
"grad_norm": 4.233203189830148,
|
| 86 |
+
"learning_rate": 7.3880597014925385e-06,
|
| 87 |
+
"loss": 0.5193,
|
| 88 |
+
"step": 100
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"epoch": 0.2247191011235955,
|
| 92 |
+
"eval_loss": 0.493939608335495,
|
| 93 |
+
"eval_runtime": 24.9607,
|
| 94 |
+
"eval_samples_per_second": 15.024,
|
| 95 |
+
"eval_steps_per_second": 3.766,
|
| 96 |
+
"step": 100
|
| 97 |
+
},
|
| 98 |
+
{
|
| 99 |
+
"epoch": 0.24719101123595505,
|
| 100 |
+
"grad_norm": 5.573018903151105,
|
| 101 |
+
"learning_rate": 8.134328358208955e-06,
|
| 102 |
+
"loss": 0.5423,
|
| 103 |
+
"step": 110
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"epoch": 0.2696629213483146,
|
| 107 |
+
"grad_norm": 5.477625900509682,
|
| 108 |
+
"learning_rate": 8.880597014925374e-06,
|
| 109 |
+
"loss": 0.5233,
|
| 110 |
+
"step": 120
|
| 111 |
+
},
|
| 112 |
+
{
|
| 113 |
+
"epoch": 0.29213483146067415,
|
| 114 |
+
"grad_norm": 5.214351087686594,
|
| 115 |
+
"learning_rate": 9.626865671641792e-06,
|
| 116 |
+
"loss": 0.5423,
|
| 117 |
+
"step": 130
|
| 118 |
+
},
|
| 119 |
+
{
|
| 120 |
+
"epoch": 0.3146067415730337,
|
| 121 |
+
"grad_norm": 4.301310266081571,
|
| 122 |
+
"learning_rate": 9.999572350905325e-06,
|
| 123 |
+
"loss": 0.5527,
|
| 124 |
+
"step": 140
|
| 125 |
+
},
|
| 126 |
+
{
|
| 127 |
+
"epoch": 0.33707865168539325,
|
| 128 |
+
"grad_norm": 4.8629967281206055,
|
| 129 |
+
"learning_rate": 9.996151597056391e-06,
|
| 130 |
+
"loss": 0.541,
|
| 131 |
+
"step": 150
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"epoch": 0.33707865168539325,
|
| 135 |
+
"eval_loss": 0.5116215348243713,
|
| 136 |
+
"eval_runtime": 25.7788,
|
| 137 |
+
"eval_samples_per_second": 14.547,
|
| 138 |
+
"eval_steps_per_second": 3.646,
|
| 139 |
+
"step": 150
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"epoch": 0.3595505617977528,
|
| 143 |
+
"grad_norm": 5.134848176613839,
|
| 144 |
+
"learning_rate": 9.98931242987009e-06,
|
| 145 |
+
"loss": 0.5541,
|
| 146 |
+
"step": 160
|
| 147 |
+
},
|
| 148 |
+
{
|
| 149 |
+
"epoch": 0.38202247191011235,
|
| 150 |
+
"grad_norm": 3.7224808382592105,
|
| 151 |
+
"learning_rate": 9.979059528768146e-06,
|
| 152 |
+
"loss": 0.5233,
|
| 153 |
+
"step": 170
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"epoch": 0.4044943820224719,
|
| 157 |
+
"grad_norm": 4.097927668579947,
|
| 158 |
+
"learning_rate": 9.96539990888074e-06,
|
| 159 |
+
"loss": 0.4969,
|
| 160 |
+
"step": 180
|
| 161 |
+
},
|
| 162 |
+
{
|
| 163 |
+
"epoch": 0.42696629213483145,
|
| 164 |
+
"grad_norm": 4.074507974902033,
|
| 165 |
+
"learning_rate": 9.948342916246702e-06,
|
| 166 |
+
"loss": 0.481,
|
| 167 |
+
"step": 190
|
| 168 |
+
},
|
| 169 |
+
{
|
| 170 |
+
"epoch": 0.449438202247191,
|
| 171 |
+
"grad_norm": 4.118618237060066,
|
| 172 |
+
"learning_rate": 9.92790022141885e-06,
|
| 173 |
+
"loss": 0.5009,
|
| 174 |
+
"step": 200
|
| 175 |
+
},
|
| 176 |
+
{
|
| 177 |
+
"epoch": 0.449438202247191,
|
| 178 |
+
"eval_loss": 0.4970722496509552,
|
| 179 |
+
"eval_runtime": 24.9787,
|
| 180 |
+
"eval_samples_per_second": 15.013,
|
| 181 |
+
"eval_steps_per_second": 3.763,
|
| 182 |
+
"step": 200
|
| 183 |
+
},
|
| 184 |
+
{
|
| 185 |
+
"epoch": 0.47191011235955055,
|
| 186 |
+
"grad_norm": 4.037918196386557,
|
| 187 |
+
"learning_rate": 9.904085811478901e-06,
|
| 188 |
+
"loss": 0.5279,
|
| 189 |
+
"step": 210
|
| 190 |
+
},
|
| 191 |
+
{
|
| 192 |
+
"epoch": 0.4943820224719101,
|
| 193 |
+
"grad_norm": 3.87032723719675,
|
| 194 |
+
"learning_rate": 9.876915980467373e-06,
|
| 195 |
+
"loss": 0.5073,
|
| 196 |
+
"step": 220
|
| 197 |
+
},
|
| 198 |
+
{
|
| 199 |
+
"epoch": 0.5168539325842697,
|
| 200 |
+
"grad_norm": 3.8991555389148465,
|
| 201 |
+
"learning_rate": 9.846409318235056e-06,
|
| 202 |
+
"loss": 0.5346,
|
| 203 |
+
"step": 230
|
| 204 |
+
},
|
| 205 |
+
{
|
| 206 |
+
"epoch": 0.5393258426966292,
|
| 207 |
+
"grad_norm": 4.27998406282492,
|
| 208 |
+
"learning_rate": 9.812586697723658e-06,
|
| 209 |
+
"loss": 0.5289,
|
| 210 |
+
"step": 240
|
| 211 |
+
},
|
| 212 |
+
{
|
| 213 |
+
"epoch": 0.5617977528089888,
|
| 214 |
+
"grad_norm": 3.61171557296346,
|
| 215 |
+
"learning_rate": 9.775471260684346e-06,
|
| 216 |
+
"loss": 0.4856,
|
| 217 |
+
"step": 250
|
| 218 |
+
},
|
| 219 |
+
{
|
| 220 |
+
"epoch": 0.5617977528089888,
|
| 221 |
+
"eval_loss": 0.4789491295814514,
|
| 222 |
+
"eval_runtime": 25.1693,
|
| 223 |
+
"eval_samples_per_second": 14.899,
|
| 224 |
+
"eval_steps_per_second": 3.735,
|
| 225 |
+
"step": 250
|
| 226 |
+
},
|
| 227 |
+
{
|
| 228 |
+
"epoch": 0.5842696629213483,
|
| 229 |
+
"grad_norm": 4.505011449204735,
|
| 230 |
+
"learning_rate": 9.735088401843948e-06,
|
| 231 |
+
"loss": 0.4713,
|
| 232 |
+
"step": 260
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"epoch": 0.6067415730337079,
|
| 236 |
+
"grad_norm": 4.217861036723754,
|
| 237 |
+
"learning_rate": 9.691465751529645e-06,
|
| 238 |
+
"loss": 0.5077,
|
| 239 |
+
"step": 270
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"epoch": 0.6292134831460674,
|
| 243 |
+
"grad_norm": 4.142724019328917,
|
| 244 |
+
"learning_rate": 9.644633156764038e-06,
|
| 245 |
+
"loss": 0.5148,
|
| 246 |
+
"step": 280
|
| 247 |
+
},
|
| 248 |
+
{
|
| 249 |
+
"epoch": 0.651685393258427,
|
| 250 |
+
"grad_norm": 3.903553214089031,
|
| 251 |
+
"learning_rate": 9.594622660843547e-06,
|
| 252 |
+
"loss": 0.4998,
|
| 253 |
+
"step": 290
|
| 254 |
+
},
|
| 255 |
+
{
|
| 256 |
+
"epoch": 0.6741573033707865,
|
| 257 |
+
"grad_norm": 4.119559749705483,
|
| 258 |
+
"learning_rate": 9.54146848141408e-06,
|
| 259 |
+
"loss": 0.4855,
|
| 260 |
+
"step": 300
|
| 261 |
+
},
|
| 262 |
+
{
|
| 263 |
+
"epoch": 0.6741573033707865,
|
| 264 |
+
"eval_loss": 0.4700905382633209,
|
| 265 |
+
"eval_runtime": 24.9924,
|
| 266 |
+
"eval_samples_per_second": 15.005,
|
| 267 |
+
"eval_steps_per_second": 3.761,
|
| 268 |
+
"step": 300
|
| 269 |
+
},
|
| 270 |
+
{
|
| 271 |
+
"epoch": 0.6966292134831461,
|
| 272 |
+
"grad_norm": 3.748351807209981,
|
| 273 |
+
"learning_rate": 9.48520698705901e-06,
|
| 274 |
+
"loss": 0.4825,
|
| 275 |
+
"step": 310
|
| 276 |
+
},
|
| 277 |
+
{
|
| 278 |
+
"epoch": 0.7191011235955056,
|
| 279 |
+
"grad_norm": 3.660070209564583,
|
| 280 |
+
"learning_rate": 9.425876672415448e-06,
|
| 281 |
+
"loss": 0.4918,
|
| 282 |
+
"step": 320
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 0.7415730337078652,
|
| 286 |
+
"grad_norm": 3.581652056622651,
|
| 287 |
+
"learning_rate": 9.363518131835857e-06,
|
| 288 |
+
"loss": 0.4847,
|
| 289 |
+
"step": 330
|
| 290 |
+
},
|
| 291 |
+
{
|
| 292 |
+
"epoch": 0.7640449438202247,
|
| 293 |
+
"grad_norm": 3.2248887000209168,
|
| 294 |
+
"learning_rate": 9.298174031613019e-06,
|
| 295 |
+
"loss": 0.4721,
|
| 296 |
+
"step": 340
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"epoch": 0.7865168539325843,
|
| 300 |
+
"grad_norm": 3.433512261597286,
|
| 301 |
+
"learning_rate": 9.229889080787357e-06,
|
| 302 |
+
"loss": 0.4586,
|
| 303 |
+
"step": 350
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"epoch": 0.7865168539325843,
|
| 307 |
+
"eval_loss": 0.4575425386428833,
|
| 308 |
+
"eval_runtime": 26.1378,
|
| 309 |
+
"eval_samples_per_second": 14.347,
|
| 310 |
+
"eval_steps_per_second": 3.596,
|
| 311 |
+
"step": 350
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.8089887640449438,
|
| 315 |
+
"grad_norm": 3.1092905973335765,
|
| 316 |
+
"learning_rate": 9.1587100005566e-06,
|
| 317 |
+
"loss": 0.4914,
|
| 318 |
+
"step": 360
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.8314606741573034,
|
| 322 |
+
"grad_norm": 3.42569750691016,
|
| 323 |
+
"learning_rate": 9.0846854923087e-06,
|
| 324 |
+
"loss": 0.4282,
|
| 325 |
+
"step": 370
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.8539325842696629,
|
| 329 |
+
"grad_norm": 3.562046198162776,
|
| 330 |
+
"learning_rate": 9.007866204299896e-06,
|
| 331 |
+
"loss": 0.4505,
|
| 332 |
+
"step": 380
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.8764044943820225,
|
| 336 |
+
"grad_norm": 3.4354312620525285,
|
| 337 |
+
"learning_rate": 8.9283046970007e-06,
|
| 338 |
+
"loss": 0.4597,
|
| 339 |
+
"step": 390
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.898876404494382,
|
| 343 |
+
"grad_norm": 3.482588882448166,
|
| 344 |
+
"learning_rate": 8.846055407133539e-06,
|
| 345 |
+
"loss": 0.4786,
|
| 346 |
+
"step": 400
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.898876404494382,
|
| 350 |
+
"eval_loss": 0.44720685482025146,
|
| 351 |
+
"eval_runtime": 26.3032,
|
| 352 |
+
"eval_samples_per_second": 14.257,
|
| 353 |
+
"eval_steps_per_second": 3.574,
|
| 354 |
+
"step": 400
|
| 355 |
+
},
|
| 356 |
+
{
|
| 357 |
+
"epoch": 0.9213483146067416,
|
| 358 |
+
"grad_norm": 3.695385850551158,
|
| 359 |
+
"learning_rate": 8.761174610426642e-06,
|
| 360 |
+
"loss": 0.4705,
|
| 361 |
+
"step": 410
|
| 362 |
+
},
|
| 363 |
+
{
|
| 364 |
+
"epoch": 0.9438202247191011,
|
| 365 |
+
"grad_norm": 3.7488074789801393,
|
| 366 |
+
"learning_rate": 8.673720383109666e-06,
|
| 367 |
+
"loss": 0.4486,
|
| 368 |
+
"step": 420
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.9662921348314607,
|
| 372 |
+
"grad_norm": 3.0924702043653185,
|
| 373 |
+
"learning_rate": 8.583752562177401e-06,
|
| 374 |
+
"loss": 0.4405,
|
| 375 |
+
"step": 430
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.9887640449438202,
|
| 379 |
+
"grad_norm": 3.2520566139437888,
|
| 380 |
+
"learning_rate": 8.491332704448734e-06,
|
| 381 |
+
"loss": 0.4532,
|
| 382 |
+
"step": 440
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 1.0112359550561798,
|
| 386 |
+
"grad_norm": 2.6092030216004054,
|
| 387 |
+
"learning_rate": 8.396524044448913e-06,
|
| 388 |
+
"loss": 0.39,
|
| 389 |
+
"step": 450
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 1.0112359550561798,
|
| 393 |
+
"eval_loss": 0.43022894859313965,
|
| 394 |
+
"eval_runtime": 25.0121,
|
| 395 |
+
"eval_samples_per_second": 14.993,
|
| 396 |
+
"eval_steps_per_second": 3.758,
|
| 397 |
+
"step": 450
|
| 398 |
+
},
|
| 399 |
+
{
|
| 400 |
+
"epoch": 1.0337078651685394,
|
| 401 |
+
"grad_norm": 3.93658345571168,
|
| 402 |
+
"learning_rate": 8.299391451143887e-06,
|
| 403 |
+
"loss": 0.2934,
|
| 404 |
+
"step": 460
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"epoch": 1.0561797752808988,
|
| 408 |
+
"grad_norm": 2.574677142853337,
|
| 409 |
+
"learning_rate": 8.20000138355637e-06,
|
| 410 |
+
"loss": 0.29,
|
| 411 |
+
"step": 470
|
| 412 |
+
},
|
| 413 |
+
{
|
| 414 |
+
"epoch": 1.0786516853932584,
|
| 415 |
+
"grad_norm": 2.944888298351413,
|
| 416 |
+
"learning_rate": 8.098421845293946e-06,
|
| 417 |
+
"loss": 0.2778,
|
| 418 |
+
"step": 480
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 1.101123595505618,
|
| 422 |
+
"grad_norm": 3.4990411114909223,
|
| 423 |
+
"learning_rate": 7.994722338020375e-06,
|
| 424 |
+
"loss": 0.2847,
|
| 425 |
+
"step": 490
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"epoch": 1.1235955056179776,
|
| 429 |
+
"grad_norm": 2.429629733773841,
|
| 430 |
+
"learning_rate": 7.888973813901909e-06,
|
| 431 |
+
"loss": 0.3046,
|
| 432 |
+
"step": 500
|
| 433 |
+
},
|
| 434 |
+
{
|
| 435 |
+
"epoch": 1.1235955056179776,
|
| 436 |
+
"eval_loss": 0.4396440088748932,
|
| 437 |
+
"eval_runtime": 24.9157,
|
| 438 |
+
"eval_samples_per_second": 15.051,
|
| 439 |
+
"eval_steps_per_second": 3.773,
|
| 440 |
+
"step": 500
|
| 441 |
+
},
|
| 442 |
+
{
|
| 443 |
+
"epoch": 1.146067415730337,
|
| 444 |
+
"grad_norm": 3.69198289043942,
|
| 445 |
+
"learning_rate": 7.781248627061166e-06,
|
| 446 |
+
"loss": 0.3076,
|
| 447 |
+
"step": 510
|
| 448 |
+
},
|
| 449 |
+
{
|
| 450 |
+
"epoch": 1.1685393258426966,
|
| 451 |
+
"grad_norm": 3.7096227187973883,
|
| 452 |
+
"learning_rate": 7.671620484071758e-06,
|
| 453 |
+
"loss": 0.294,
|
| 454 |
+
"step": 520
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 1.1910112359550562,
|
| 458 |
+
"grad_norm": 3.260408384626437,
|
| 459 |
+
"learning_rate": 7.56016439352757e-06,
|
| 460 |
+
"loss": 0.2903,
|
| 461 |
+
"step": 530
|
| 462 |
+
},
|
| 463 |
+
{
|
| 464 |
+
"epoch": 1.2134831460674158,
|
| 465 |
+
"grad_norm": 3.6192953437013635,
|
| 466 |
+
"learning_rate": 7.446956614721191e-06,
|
| 467 |
+
"loss": 0.2932,
|
| 468 |
+
"step": 540
|
| 469 |
+
},
|
| 470 |
+
{
|
| 471 |
+
"epoch": 1.2359550561797752,
|
| 472 |
+
"grad_norm": 2.4190691953263728,
|
| 473 |
+
"learning_rate": 7.33207460546659e-06,
|
| 474 |
+
"loss": 0.2974,
|
| 475 |
+
"step": 550
|
| 476 |
+
},
|
| 477 |
+
{
|
| 478 |
+
"epoch": 1.2359550561797752,
|
| 479 |
+
"eval_loss": 0.42986103892326355,
|
| 480 |
+
"eval_runtime": 24.9395,
|
| 481 |
+
"eval_samples_per_second": 15.036,
|
| 482 |
+
"eval_steps_per_second": 3.769,
|
| 483 |
+
"step": 550
|
| 484 |
+
},
|
| 485 |
+
{
|
| 486 |
+
"epoch": 1.2584269662921348,
|
| 487 |
+
"grad_norm": 2.489908669669235,
|
| 488 |
+
"learning_rate": 7.215596969101762e-06,
|
| 489 |
+
"loss": 0.2781,
|
| 490 |
+
"step": 560
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 1.2808988764044944,
|
| 494 |
+
"grad_norm": 2.9484209879538463,
|
| 495 |
+
"learning_rate": 7.097603400707595e-06,
|
| 496 |
+
"loss": 0.2868,
|
| 497 |
+
"step": 570
|
| 498 |
+
},
|
| 499 |
+
{
|
| 500 |
+
"epoch": 1.303370786516854,
|
| 501 |
+
"grad_norm": 2.9400681335785,
|
| 502 |
+
"learning_rate": 6.978174632579754e-06,
|
| 503 |
+
"loss": 0.2915,
|
| 504 |
+
"step": 580
|
| 505 |
+
},
|
| 506 |
+
{
|
| 507 |
+
"epoch": 1.3258426966292136,
|
| 508 |
+
"grad_norm": 2.7813742105012946,
|
| 509 |
+
"learning_rate": 6.857392378990895e-06,
|
| 510 |
+
"loss": 0.3,
|
| 511 |
+
"step": 590
|
| 512 |
+
},
|
| 513 |
+
{
|
| 514 |
+
"epoch": 1.348314606741573,
|
| 515 |
+
"grad_norm": 3.1589920291574867,
|
| 516 |
+
"learning_rate": 6.735339280281001e-06,
|
| 517 |
+
"loss": 0.2836,
|
| 518 |
+
"step": 600
|
| 519 |
+
},
|
| 520 |
+
{
|
| 521 |
+
"epoch": 1.348314606741573,
|
| 522 |
+
"eval_loss": 0.424435555934906,
|
| 523 |
+
"eval_runtime": 24.9745,
|
| 524 |
+
"eval_samples_per_second": 15.015,
|
| 525 |
+
"eval_steps_per_second": 3.764,
|
| 526 |
+
"step": 600
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 1.3707865168539326,
|
| 530 |
+
"grad_norm": 3.2253219929109993,
|
| 531 |
+
"learning_rate": 6.6120988463140925e-06,
|
| 532 |
+
"loss": 0.2812,
|
| 533 |
+
"step": 610
|
| 534 |
+
},
|
| 535 |
+
{
|
| 536 |
+
"epoch": 1.3932584269662922,
|
| 537 |
+
"grad_norm": 2.998338433795413,
|
| 538 |
+
"learning_rate": 6.487755399340005e-06,
|
| 539 |
+
"loss": 0.274,
|
| 540 |
+
"step": 620
|
| 541 |
+
},
|
| 542 |
+
{
|
| 543 |
+
"epoch": 1.4157303370786516,
|
| 544 |
+
"grad_norm": 3.0174835800903277,
|
| 545 |
+
"learning_rate": 6.362394016300315e-06,
|
| 546 |
+
"loss": 0.3027,
|
| 547 |
+
"step": 630
|
| 548 |
+
},
|
| 549 |
+
{
|
| 550 |
+
"epoch": 1.4382022471910112,
|
| 551 |
+
"grad_norm": 3.0709749279754806,
|
| 552 |
+
"learning_rate": 6.2361004706179195e-06,
|
| 553 |
+
"loss": 0.2783,
|
| 554 |
+
"step": 640
|
| 555 |
+
},
|
| 556 |
+
{
|
| 557 |
+
"epoch": 1.4606741573033708,
|
| 558 |
+
"grad_norm": 2.8657846085406375,
|
| 559 |
+
"learning_rate": 6.108961173510052e-06,
|
| 560 |
+
"loss": 0.2679,
|
| 561 |
+
"step": 650
|
| 562 |
+
},
|
| 563 |
+
{
|
| 564 |
+
"epoch": 1.4606741573033708,
|
| 565 |
+
"eval_loss": 0.41811907291412354,
|
| 566 |
+
"eval_runtime": 24.9758,
|
| 567 |
+
"eval_samples_per_second": 15.015,
|
| 568 |
+
"eval_steps_per_second": 3.764,
|
| 569 |
+
"step": 650
|
| 570 |
+
},
|
| 571 |
+
{
|
| 572 |
+
"epoch": 1.4831460674157304,
|
| 573 |
+
"grad_norm": 2.9027078307484464,
|
| 574 |
+
"learning_rate": 5.981063114864928e-06,
|
| 575 |
+
"loss": 0.2836,
|
| 576 |
+
"step": 660
|
| 577 |
+
},
|
| 578 |
+
{
|
| 579 |
+
"epoch": 1.50561797752809,
|
| 580 |
+
"grad_norm": 3.0484816884142694,
|
| 581 |
+
"learning_rate": 5.8524938037224555e-06,
|
| 582 |
+
"loss": 0.2878,
|
| 583 |
+
"step": 670
|
| 584 |
+
},
|
| 585 |
+
{
|
| 586 |
+
"epoch": 1.5280898876404494,
|
| 587 |
+
"grad_norm": 3.546958139149415,
|
| 588 |
+
"learning_rate": 5.723341208399737e-06,
|
| 589 |
+
"loss": 0.2559,
|
| 590 |
+
"step": 680
|
| 591 |
+
},
|
| 592 |
+
{
|
| 593 |
+
"epoch": 1.550561797752809,
|
| 594 |
+
"grad_norm": 2.527705962796326,
|
| 595 |
+
"learning_rate": 5.593693696302333e-06,
|
| 596 |
+
"loss": 0.2913,
|
| 597 |
+
"step": 690
|
| 598 |
+
},
|
| 599 |
+
{
|
| 600 |
+
"epoch": 1.5730337078651684,
|
| 601 |
+
"grad_norm": 3.049149117749253,
|
| 602 |
+
"learning_rate": 5.4636399734624534e-06,
|
| 603 |
+
"loss": 0.3064,
|
| 604 |
+
"step": 700
|
| 605 |
+
},
|
| 606 |
+
{
|
| 607 |
+
"epoch": 1.5730337078651684,
|
| 608 |
+
"eval_loss": 0.4070671498775482,
|
| 609 |
+
"eval_runtime": 24.9868,
|
| 610 |
+
"eval_samples_per_second": 15.008,
|
| 611 |
+
"eval_steps_per_second": 3.762,
|
| 612 |
+
"step": 700
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.595505617977528,
|
| 616 |
+
"grad_norm": 3.3829674667472296,
|
| 617 |
+
"learning_rate": 5.333269023845478e-06,
|
| 618 |
+
"loss": 0.2558,
|
| 619 |
+
"step": 710
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.6179775280898876,
|
| 623 |
+
"grad_norm": 2.8816644316829776,
|
| 624 |
+
"learning_rate": 5.20267004846629e-06,
|
| 625 |
+
"loss": 0.2715,
|
| 626 |
+
"step": 720
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.6404494382022472,
|
| 630 |
+
"grad_norm": 2.65974535815253,
|
| 631 |
+
"learning_rate": 5.071932404357119e-06,
|
| 632 |
+
"loss": 0.2779,
|
| 633 |
+
"step": 730
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.6629213483146068,
|
| 637 |
+
"grad_norm": 3.360553702499387,
|
| 638 |
+
"learning_rate": 4.94114554342863e-06,
|
| 639 |
+
"loss": 0.2867,
|
| 640 |
+
"step": 740
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.6853932584269664,
|
| 644 |
+
"grad_norm": 2.6537127651545327,
|
| 645 |
+
"learning_rate": 4.81039895126609e-06,
|
| 646 |
+
"loss": 0.2741,
|
| 647 |
+
"step": 750
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.6853932584269664,
|
| 651 |
+
"eval_loss": 0.40253934264183044,
|
| 652 |
+
"eval_runtime": 24.8871,
|
| 653 |
+
"eval_samples_per_second": 15.068,
|
| 654 |
+
"eval_steps_per_second": 3.777,
|
| 655 |
+
"step": 750
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 1.7078651685393258,
|
| 659 |
+
"grad_norm": 3.0384594725904006,
|
| 660 |
+
"learning_rate": 4.679782085902503e-06,
|
| 661 |
+
"loss": 0.2562,
|
| 662 |
+
"step": 760
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 1.7303370786516854,
|
| 666 |
+
"grad_norm": 2.227194057742769,
|
| 667 |
+
"learning_rate": 4.549384316610593e-06,
|
| 668 |
+
"loss": 0.2648,
|
| 669 |
+
"step": 770
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 1.7528089887640448,
|
| 673 |
+
"grad_norm": 3.2027111465720863,
|
| 674 |
+
"learning_rate": 4.419294862755515e-06,
|
| 675 |
+
"loss": 0.2632,
|
| 676 |
+
"step": 780
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 1.7752808988764044,
|
| 680 |
+
"grad_norm": 2.654459629197947,
|
| 681 |
+
"learning_rate": 4.289602732750138e-06,
|
| 682 |
+
"loss": 0.2713,
|
| 683 |
+
"step": 790
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 1.797752808988764,
|
| 687 |
+
"grad_norm": 2.521648333087021,
|
| 688 |
+
"learning_rate": 4.1603966631546634e-06,
|
| 689 |
+
"loss": 0.2558,
|
| 690 |
+
"step": 800
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 1.797752808988764,
|
| 694 |
+
"eval_loss": 0.39331701397895813,
|
| 695 |
+
"eval_runtime": 24.9971,
|
| 696 |
+
"eval_samples_per_second": 15.002,
|
| 697 |
+
"eval_steps_per_second": 3.76,
|
| 698 |
+
"step": 800
|
| 699 |
+
},
|
| 700 |
+
{
|
| 701 |
+
"epoch": 1.8202247191011236,
|
| 702 |
+
"grad_norm": 2.705343161428659,
|
| 703 |
+
"learning_rate": 4.031765057962243e-06,
|
| 704 |
+
"loss": 0.2444,
|
| 705 |
+
"step": 810
|
| 706 |
+
},
|
| 707 |
+
{
|
| 708 |
+
"epoch": 1.8426966292134832,
|
| 709 |
+
"grad_norm": 2.644036695699088,
|
| 710 |
+
"learning_rate": 3.9037959281121474e-06,
|
| 711 |
+
"loss": 0.2401,
|
| 712 |
+
"step": 820
|
| 713 |
+
},
|
| 714 |
+
{
|
| 715 |
+
"epoch": 1.8651685393258428,
|
| 716 |
+
"grad_norm": 3.014535462717269,
|
| 717 |
+
"learning_rate": 3.776576831271865e-06,
|
| 718 |
+
"loss": 0.2726,
|
| 719 |
+
"step": 830
|
| 720 |
+
},
|
| 721 |
+
{
|
| 722 |
+
"epoch": 1.8876404494382022,
|
| 723 |
+
"grad_norm": 2.948495628548272,
|
| 724 |
+
"learning_rate": 3.65019481192933e-06,
|
| 725 |
+
"loss": 0.2528,
|
| 726 |
+
"step": 840
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 1.9101123595505618,
|
| 730 |
+
"grad_norm": 3.240517676713746,
|
| 731 |
+
"learning_rate": 3.524736341836272e-06,
|
| 732 |
+
"loss": 0.2701,
|
| 733 |
+
"step": 850
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 1.9101123595505618,
|
| 737 |
+
"eval_loss": 0.3823501169681549,
|
| 738 |
+
"eval_runtime": 24.9338,
|
| 739 |
+
"eval_samples_per_second": 15.04,
|
| 740 |
+
"eval_steps_per_second": 3.77,
|
| 741 |
+
"step": 850
|
| 742 |
+
},
|
| 743 |
+
{
|
| 744 |
+
"epoch": 1.9325842696629212,
|
| 745 |
+
"grad_norm": 2.464260583969927,
|
| 746 |
+
"learning_rate": 3.400287260843454e-06,
|
| 747 |
+
"loss": 0.2511,
|
| 748 |
+
"step": 860
|
| 749 |
+
},
|
| 750 |
+
{
|
| 751 |
+
"epoch": 1.9550561797752808,
|
| 752 |
+
"grad_norm": 2.516891491810393,
|
| 753 |
+
"learning_rate": 3.2769327181682307e-06,
|
| 754 |
+
"loss": 0.255,
|
| 755 |
+
"step": 870
|
| 756 |
+
},
|
| 757 |
+
{
|
| 758 |
+
"epoch": 1.9775280898876404,
|
| 759 |
+
"grad_norm": 2.796062790379466,
|
| 760 |
+
"learning_rate": 3.1547571141346756e-06,
|
| 761 |
+
"loss": 0.253,
|
| 762 |
+
"step": 880
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"epoch": 2.0,
|
| 766 |
+
"grad_norm": 2.236946411525721,
|
| 767 |
+
"learning_rate": 3.0338440424260897e-06,
|
| 768 |
+
"loss": 0.2729,
|
| 769 |
+
"step": 890
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"epoch": 2.0224719101123596,
|
| 773 |
+
"grad_norm": 2.629609243029033,
|
| 774 |
+
"learning_rate": 2.9142762328894273e-06,
|
| 775 |
+
"loss": 0.1197,
|
| 776 |
+
"step": 900
|
| 777 |
+
},
|
| 778 |
+
{
|
| 779 |
+
"epoch": 2.0224719101123596,
|
| 780 |
+
"eval_loss": 0.440464586019516,
|
| 781 |
+
"eval_runtime": 24.8972,
|
| 782 |
+
"eval_samples_per_second": 15.062,
|
| 783 |
+
"eval_steps_per_second": 3.776,
|
| 784 |
+
"step": 900
|
| 785 |
+
},
|
| 786 |
+
{
|
| 787 |
+
"epoch": 2.044943820224719,
|
| 788 |
+
"grad_norm": 3.42937110528431,
|
| 789 |
+
"learning_rate": 2.7961354949307677e-06,
|
| 790 |
+
"loss": 0.1103,
|
| 791 |
+
"step": 910
|
| 792 |
+
},
|
| 793 |
+
{
|
| 794 |
+
"epoch": 2.067415730337079,
|
| 795 |
+
"grad_norm": 2.4072280916292876,
|
| 796 |
+
"learning_rate": 2.6795026615405635e-06,
|
| 797 |
+
"loss": 0.1058,
|
| 798 |
+
"step": 920
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"epoch": 2.0898876404494384,
|
| 802 |
+
"grad_norm": 2.3294311496027964,
|
| 803 |
+
"learning_rate": 2.564457533986944e-06,
|
| 804 |
+
"loss": 0.0976,
|
| 805 |
+
"step": 930
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"epoch": 2.1123595505617976,
|
| 809 |
+
"grad_norm": 2.1539444580019533,
|
| 810 |
+
"learning_rate": 2.451078827214964e-06,
|
| 811 |
+
"loss": 0.1092,
|
| 812 |
+
"step": 940
|
| 813 |
+
},
|
| 814 |
+
{
|
| 815 |
+
"epoch": 2.134831460674157,
|
| 816 |
+
"grad_norm": 2.1960206107594415,
|
| 817 |
+
"learning_rate": 2.339444115989093e-06,
|
| 818 |
+
"loss": 0.104,
|
| 819 |
+
"step": 950
|
| 820 |
+
},
|
| 821 |
+
{
|
| 822 |
+
"epoch": 2.134831460674157,
|
| 823 |
+
"eval_loss": 0.43039175868034363,
|
| 824 |
+
"eval_runtime": 24.8719,
|
| 825 |
+
"eval_samples_per_second": 15.077,
|
| 826 |
+
"eval_steps_per_second": 3.779,
|
| 827 |
+
"step": 950
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"epoch": 2.157303370786517,
|
| 831 |
+
"grad_norm": 3.0830821666121815,
|
| 832 |
+
"learning_rate": 2.2296297818158458e-06,
|
| 833 |
+
"loss": 0.1067,
|
| 834 |
+
"step": 960
|
| 835 |
+
},
|
| 836 |
+
{
|
| 837 |
+
"epoch": 2.1797752808988764,
|
| 838 |
+
"grad_norm": 2.312666674833764,
|
| 839 |
+
"learning_rate": 2.121710960682851e-06,
|
| 840 |
+
"loss": 0.1074,
|
| 841 |
+
"step": 970
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"epoch": 2.202247191011236,
|
| 845 |
+
"grad_norm": 2.8154754878660526,
|
| 846 |
+
"learning_rate": 2.0157614916501e-06,
|
| 847 |
+
"loss": 0.1073,
|
| 848 |
+
"step": 980
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"epoch": 2.2247191011235956,
|
| 852 |
+
"grad_norm": 2.3117808629097767,
|
| 853 |
+
"learning_rate": 1.9118538663285874e-06,
|
| 854 |
+
"loss": 0.1048,
|
| 855 |
+
"step": 990
|
| 856 |
+
},
|
| 857 |
+
{
|
| 858 |
+
"epoch": 2.247191011235955,
|
| 859 |
+
"grad_norm": 2.5674069626572913,
|
| 860 |
+
"learning_rate": 1.8100591792808652e-06,
|
| 861 |
+
"loss": 0.1085,
|
| 862 |
+
"step": 1000
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 2.247191011235955,
|
| 866 |
+
"eval_loss": 0.4354311227798462,
|
| 867 |
+
"eval_runtime": 24.9225,
|
| 868 |
+
"eval_samples_per_second": 15.047,
|
| 869 |
+
"eval_steps_per_second": 3.772,
|
| 870 |
+
"step": 1000
|
| 871 |
+
},
|
| 872 |
+
{
|
| 873 |
+
"epoch": 2.2696629213483144,
|
| 874 |
+
"grad_norm": 2.4809771234626736,
|
| 875 |
+
"learning_rate": 1.7104470793774959e-06,
|
| 876 |
+
"loss": 0.1066,
|
| 877 |
+
"step": 1010
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"epoch": 2.292134831460674,
|
| 881 |
+
"grad_norm": 2.6166634424521624,
|
| 882 |
+
"learning_rate": 1.613085722142636e-06,
|
| 883 |
+
"loss": 0.1049,
|
| 884 |
+
"step": 1020
|
| 885 |
+
},
|
| 886 |
+
{
|
| 887 |
+
"epoch": 2.3146067415730336,
|
| 888 |
+
"grad_norm": 2.697070993725173,
|
| 889 |
+
"learning_rate": 1.5180417231214001e-06,
|
| 890 |
+
"loss": 0.1054,
|
| 891 |
+
"step": 1030
|
| 892 |
+
},
|
| 893 |
+
{
|
| 894 |
+
"epoch": 2.337078651685393,
|
| 895 |
+
"grad_norm": 3.150451918918423,
|
| 896 |
+
"learning_rate": 1.425380112300887e-06,
|
| 897 |
+
"loss": 0.1097,
|
| 898 |
+
"step": 1040
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 2.359550561797753,
|
| 902 |
+
"grad_norm": 2.4302921480275375,
|
| 903 |
+
"learning_rate": 1.3351642896160522e-06,
|
| 904 |
+
"loss": 0.1004,
|
| 905 |
+
"step": 1050
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"epoch": 2.359550561797753,
|
| 909 |
+
"eval_loss": 0.4359316825866699,
|
| 910 |
+
"eval_runtime": 25.0002,
|
| 911 |
+
"eval_samples_per_second": 15.0,
|
| 912 |
+
"eval_steps_per_second": 3.76,
|
| 913 |
+
"step": 1050
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.3820224719101124,
|
| 917 |
+
"grad_norm": 2.3287569510084976,
|
| 918 |
+
"learning_rate": 1.247455981570892e-06,
|
| 919 |
+
"loss": 0.1015,
|
| 920 |
+
"step": 1060
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.404494382022472,
|
| 924 |
+
"grad_norm": 2.8548222518400923,
|
| 925 |
+
"learning_rate": 1.162315199004585e-06,
|
| 926 |
+
"loss": 0.0977,
|
| 927 |
+
"step": 1070
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.4269662921348316,
|
| 931 |
+
"grad_norm": 2.0796200858413725,
|
| 932 |
+
"learning_rate": 1.0798001960315313e-06,
|
| 933 |
+
"loss": 0.1044,
|
| 934 |
+
"step": 1080
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.449438202247191,
|
| 938 |
+
"grad_norm": 2.593586601052882,
|
| 939 |
+
"learning_rate": 9.999674301833328e-07,
|
| 940 |
+
"loss": 0.0973,
|
| 941 |
+
"step": 1090
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.4719101123595504,
|
| 945 |
+
"grad_norm": 2.3446083217931526,
|
| 946 |
+
"learning_rate": 9.228715237800395e-07,
|
| 947 |
+
"loss": 0.0944,
|
| 948 |
+
"step": 1100
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.4719101123595504,
|
| 952 |
+
"eval_loss": 0.4427347481250763,
|
| 953 |
+
"eval_runtime": 25.3776,
|
| 954 |
+
"eval_samples_per_second": 14.777,
|
| 955 |
+
"eval_steps_per_second": 3.704,
|
| 956 |
+
"step": 1100
|
| 957 |
+
},
|
| 958 |
+
{
|
| 959 |
+
"epoch": 2.49438202247191,
|
| 960 |
+
"grad_norm": 2.802667763737667,
|
| 961 |
+
"learning_rate": 8.485652265570376e-07,
|
| 962 |
+
"loss": 0.0907,
|
| 963 |
+
"step": 1110
|
| 964 |
+
},
|
| 965 |
+
{
|
| 966 |
+
"epoch": 2.5168539325842696,
|
| 967 |
+
"grad_norm": 2.7830643650884515,
|
| 968 |
+
"learning_rate": 7.770993795731984e-07,
|
| 969 |
+
"loss": 0.0888,
|
| 970 |
+
"step": 1120
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 2.539325842696629,
|
| 974 |
+
"grad_norm": 2.989358499768808,
|
| 975 |
+
"learning_rate": 7.085228804249538e-07,
|
| 976 |
+
"loss": 0.1043,
|
| 977 |
+
"step": 1130
|
| 978 |
+
},
|
| 979 |
+
{
|
| 980 |
+
"epoch": 2.561797752808989,
|
| 981 |
+
"grad_norm": 2.430654309211372,
|
| 982 |
+
"learning_rate": 6.428826497900992e-07,
|
| 983 |
+
"loss": 0.0977,
|
| 984 |
+
"step": 1140
|
| 985 |
+
},
|
| 986 |
+
{
|
| 987 |
+
"epoch": 2.5842696629213484,
|
| 988 |
+
"grad_norm": 2.2803552937301506,
|
| 989 |
+
"learning_rate": 5.802235993242428e-07,
|
| 990 |
+
"loss": 0.0984,
|
| 991 |
+
"step": 1150
|
| 992 |
+
},
|
| 993 |
+
{
|
| 994 |
+
"epoch": 2.5842696629213484,
|
| 995 |
+
"eval_loss": 0.43664875626564026,
|
| 996 |
+
"eval_runtime": 25.2854,
|
| 997 |
+
"eval_samples_per_second": 14.831,
|
| 998 |
+
"eval_steps_per_second": 3.718,
|
| 999 |
+
"step": 1150
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 2.606741573033708,
|
| 1003 |
+
"grad_norm": 2.6345825648533783,
|
| 1004 |
+
"learning_rate": 5.205886009318184e-07,
|
| 1005 |
+
"loss": 0.1038,
|
| 1006 |
+
"step": 1160
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 2.629213483146067,
|
| 1010 |
+
"grad_norm": 2.6218576725676406,
|
| 1011 |
+
"learning_rate": 4.6401845743273945e-07,
|
| 1012 |
+
"loss": 0.0911,
|
| 1013 |
+
"step": 1170
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 2.6516853932584272,
|
| 1017 |
+
"grad_norm": 2.377080283615398,
|
| 1018 |
+
"learning_rate": 4.1055187464473125e-07,
|
| 1019 |
+
"loss": 0.0928,
|
| 1020 |
+
"step": 1180
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 2.6741573033707864,
|
| 1024 |
+
"grad_norm": 2.1605614535683335,
|
| 1025 |
+
"learning_rate": 3.602254349004447e-07,
|
| 1026 |
+
"loss": 0.0911,
|
| 1027 |
+
"step": 1190
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 2.696629213483146,
|
| 1031 |
+
"grad_norm": 2.9948424263111315,
|
| 1032 |
+
"learning_rate": 3.1307357201749157e-07,
|
| 1033 |
+
"loss": 0.1041,
|
| 1034 |
+
"step": 1200
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 2.696629213483146,
|
| 1038 |
+
"eval_loss": 0.4398299753665924,
|
| 1039 |
+
"eval_runtime": 24.9371,
|
| 1040 |
+
"eval_samples_per_second": 15.038,
|
| 1041 |
+
"eval_steps_per_second": 3.769,
|
| 1042 |
+
"step": 1200
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 2.7191011235955056,
|
| 1046 |
+
"grad_norm": 2.6717353934405836,
|
| 1047 |
+
"learning_rate": 2.691285477384986e-07,
|
| 1048 |
+
"loss": 0.0903,
|
| 1049 |
+
"step": 1210
|
| 1050 |
+
},
|
| 1051 |
+
{
|
| 1052 |
+
"epoch": 2.741573033707865,
|
| 1053 |
+
"grad_norm": 3.0365017973278583,
|
| 1054 |
+
"learning_rate": 2.284204296573328e-07,
|
| 1055 |
+
"loss": 0.0955,
|
| 1056 |
+
"step": 1220
|
| 1057 |
+
},
|
| 1058 |
+
{
|
| 1059 |
+
"epoch": 2.764044943820225,
|
| 1060 |
+
"grad_norm": 2.6472551463915366,
|
| 1061 |
+
"learning_rate": 1.9097707064656523e-07,
|
| 1062 |
+
"loss": 0.1018,
|
| 1063 |
+
"step": 1230
|
| 1064 |
+
},
|
| 1065 |
+
{
|
| 1066 |
+
"epoch": 2.7865168539325844,
|
| 1067 |
+
"grad_norm": 2.6329302602494953,
|
| 1068 |
+
"learning_rate": 1.568240898002843e-07,
|
| 1069 |
+
"loss": 0.0834,
|
| 1070 |
+
"step": 1240
|
| 1071 |
+
},
|
| 1072 |
+
{
|
| 1073 |
+
"epoch": 2.808988764044944,
|
| 1074 |
+
"grad_norm": 2.352624237375597,
|
| 1075 |
+
"learning_rate": 1.259848549052689e-07,
|
| 1076 |
+
"loss": 0.0951,
|
| 1077 |
+
"step": 1250
|
| 1078 |
+
},
|
| 1079 |
+
{
|
| 1080 |
+
"epoch": 2.808988764044944,
|
| 1081 |
+
"eval_loss": 0.437627911567688,
|
| 1082 |
+
"eval_runtime": 24.9621,
|
| 1083 |
+
"eval_samples_per_second": 15.023,
|
| 1084 |
+
"eval_steps_per_second": 3.766,
|
| 1085 |
+
"step": 1250
|
| 1086 |
+
},
|
| 1087 |
+
{
|
| 1088 |
+
"epoch": 2.831460674157303,
|
| 1089 |
+
"grad_norm": 2.727168898569768,
|
| 1090 |
+
"learning_rate": 9.848046645253184e-08,
|
| 1091 |
+
"loss": 0.0923,
|
| 1092 |
+
"step": 1260
|
| 1093 |
+
},
|
| 1094 |
+
{
|
| 1095 |
+
"epoch": 2.853932584269663,
|
| 1096 |
+
"grad_norm": 2.0463797034085407,
|
| 1097 |
+
"learning_rate": 7.432974320017216e-08,
|
| 1098 |
+
"loss": 0.0916,
|
| 1099 |
+
"step": 1270
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"epoch": 2.8764044943820224,
|
| 1103 |
+
"grad_norm": 2.429522905546668,
|
| 1104 |
+
"learning_rate": 5.354920929740048e-08,
|
| 1105 |
+
"loss": 0.0999,
|
| 1106 |
+
"step": 1280
|
| 1107 |
+
},
|
| 1108 |
+
{
|
| 1109 |
+
"epoch": 2.898876404494382,
|
| 1110 |
+
"grad_norm": 2.546507429916417,
|
| 1111 |
+
"learning_rate": 3.615308297856668e-08,
|
| 1112 |
+
"loss": 0.0943,
|
| 1113 |
+
"step": 1290
|
| 1114 |
+
},
|
| 1115 |
+
{
|
| 1116 |
+
"epoch": 2.9213483146067416,
|
| 1117 |
+
"grad_norm": 2.47287943920709,
|
| 1118 |
+
"learning_rate": 2.2153266834908927e-08,
|
| 1119 |
+
"loss": 0.0804,
|
| 1120 |
+
"step": 1300
|
| 1121 |
+
},
|
| 1122 |
+
{
|
| 1123 |
+
"epoch": 2.9213483146067416,
|
| 1124 |
+
"eval_loss": 0.43767842650413513,
|
| 1125 |
+
"eval_runtime": 24.9332,
|
| 1126 |
+
"eval_samples_per_second": 15.04,
|
| 1127 |
+
"eval_steps_per_second": 3.77,
|
| 1128 |
+
"step": 1300
|
| 1129 |
+
},
|
| 1130 |
+
{
|
| 1131 |
+
"epoch": 2.943820224719101,
|
| 1132 |
+
"grad_norm": 2.2759314566301017,
|
| 1133 |
+
"learning_rate": 1.155933967069256e-08,
|
| 1134 |
+
"loss": 0.1001,
|
| 1135 |
+
"step": 1310
|
| 1136 |
+
},
|
| 1137 |
+
{
|
| 1138 |
+
"epoch": 2.966292134831461,
|
| 1139 |
+
"grad_norm": 2.238456754170538,
|
| 1140 |
+
"learning_rate": 4.378549949301536e-09,
|
| 1141 |
+
"loss": 0.096,
|
| 1142 |
+
"step": 1320
|
| 1143 |
+
},
|
| 1144 |
+
{
|
| 1145 |
+
"epoch": 2.98876404494382,
|
| 1146 |
+
"grad_norm": 2.5271538666035367,
|
| 1147 |
+
"learning_rate": 6.158108337733782e-10,
|
| 1148 |
+
"loss": 0.0933,
|
| 1149 |
+
"step": 1330
|
| 1150 |
+
},
|
| 1151 |
+
{
|
| 1152 |
+
"epoch": 3.0,
|
| 1153 |
+
"step": 1335,
|
| 1154 |
+
"total_flos": 57488427909120.0,
|
| 1155 |
+
"train_loss": 0.29718317360467233,
|
| 1156 |
+
"train_runtime": 6776.8475,
|
| 1157 |
+
"train_samples_per_second": 3.152,
|
| 1158 |
+
"train_steps_per_second": 0.197
|
| 1159 |
+
}
|
| 1160 |
+
],
|
| 1161 |
+
"logging_steps": 10,
|
| 1162 |
+
"max_steps": 1335,
|
| 1163 |
+
"num_input_tokens_seen": 0,
|
| 1164 |
+
"num_train_epochs": 3,
|
| 1165 |
+
"save_steps": 500,
|
| 1166 |
+
"stateful_callbacks": {
|
| 1167 |
+
"TrainerControl": {
|
| 1168 |
+
"args": {
|
| 1169 |
+
"should_epoch_stop": false,
|
| 1170 |
+
"should_evaluate": false,
|
| 1171 |
+
"should_log": false,
|
| 1172 |
+
"should_save": true,
|
| 1173 |
+
"should_training_stop": true
|
| 1174 |
+
},
|
| 1175 |
+
"attributes": {}
|
| 1176 |
+
}
|
| 1177 |
+
},
|
| 1178 |
+
"total_flos": 57488427909120.0,
|
| 1179 |
+
"train_batch_size": 1,
|
| 1180 |
+
"trial_name": null,
|
| 1181 |
+
"trial_params": null
|
| 1182 |
+
}
|
llama3-os-121/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:49b17f59a9a6d59d17f0750427ca71358e87826b26ca66390390a53d112d1d6f
|
| 3 |
+
size 8145
|
llama3-os-121/training_eval_loss.png
ADDED
|
llama3-os-121/training_loss.png
ADDED
|