Add files using upload-large-folder tool
Browse files- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/adapter_config.json +48 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/chat_template.jinja +85 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/tokenizer_config.json +29 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/trainer_state.json +701 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/README.md +209 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/adapter_config.json +48 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/chat_template.jinja +85 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/tokenizer_config.json +29 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/trainer_state.json +802 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/README.md +209 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/adapter_config.json +48 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/chat_template.jinja +85 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/tokenizer_config.json +29 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/trainer_state.json +903 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/README.md +209 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/adapter_config.json +48 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/chat_template.jinja +85 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/tokenizer_config.json +29 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/trainer_state.json +125 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/README.md +209 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/adapter_config.json +48 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/chat_template.jinja +85 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/tokenizer_config.json +29 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/trainer_state.json +994 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/README.md +209 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/adapter_config.json +48 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/chat_template.jinja +85 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/tokenizer_config.json +29 -0
- DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/trainer_state.json +226 -0
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-14B-Base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.010622890133962027,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 128,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"q_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-2996/trainer_state.json
ADDED
|
@@ -0,0 +1,701 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 7.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 2996,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7805559730529785,
|
| 14 |
+
"epoch": 0.11682242990654206,
|
| 15 |
+
"grad_norm": 0.5128960013389587,
|
| 16 |
+
"learning_rate": 1.950005322230992e-06,
|
| 17 |
+
"loss": 1.770846405029297,
|
| 18 |
+
"mean_token_accuracy": 0.6305050283670426,
|
| 19 |
+
"num_tokens": 162248.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5725344836711883,
|
| 24 |
+
"epoch": 0.2336448598130841,
|
| 25 |
+
"grad_norm": 0.7059135437011719,
|
| 26 |
+
"learning_rate": 3.93980667144629e-06,
|
| 27 |
+
"loss": 1.5153414916992187,
|
| 28 |
+
"mean_token_accuracy": 0.6729821544885636,
|
| 29 |
+
"num_tokens": 327614.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.0769569373130798,
|
| 34 |
+
"epoch": 0.35046728971962615,
|
| 35 |
+
"grad_norm": 0.6092284321784973,
|
| 36 |
+
"learning_rate": 5.9296080206615885e-06,
|
| 37 |
+
"loss": 1.0251461791992187,
|
| 38 |
+
"mean_token_accuracy": 0.737835128903389,
|
| 39 |
+
"num_tokens": 494582.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.8583791655302048,
|
| 44 |
+
"epoch": 0.4672897196261682,
|
| 45 |
+
"grad_norm": 0.5586332082748413,
|
| 46 |
+
"learning_rate": 7.919409369876886e-06,
|
| 47 |
+
"loss": 0.81265869140625,
|
| 48 |
+
"mean_token_accuracy": 0.7762657129764556,
|
| 49 |
+
"num_tokens": 653981.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7744105678796768,
|
| 54 |
+
"epoch": 0.5841121495327103,
|
| 55 |
+
"grad_norm": 0.4821721613407135,
|
| 56 |
+
"learning_rate": 9.909210719092184e-06,
|
| 57 |
+
"loss": 0.7364049530029297,
|
| 58 |
+
"mean_token_accuracy": 0.7918167436122894,
|
| 59 |
+
"num_tokens": 814840.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.715560827255249,
|
| 64 |
+
"epoch": 0.7009345794392523,
|
| 65 |
+
"grad_norm": 0.6843860745429993,
|
| 66 |
+
"learning_rate": 1.1899012068307483e-05,
|
| 67 |
+
"loss": 0.6826614379882813,
|
| 68 |
+
"mean_token_accuracy": 0.8043146914243698,
|
| 69 |
+
"num_tokens": 979542.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6893886953592301,
|
| 74 |
+
"epoch": 0.8177570093457944,
|
| 75 |
+
"grad_norm": 0.6543110013008118,
|
| 76 |
+
"learning_rate": 1.3888813417522781e-05,
|
| 77 |
+
"loss": 0.6608805847167969,
|
| 78 |
+
"mean_token_accuracy": 0.8083165866136551,
|
| 79 |
+
"num_tokens": 1147400.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.652973799109459,
|
| 84 |
+
"epoch": 0.9345794392523364,
|
| 85 |
+
"grad_norm": 0.7437635660171509,
|
| 86 |
+
"learning_rate": 1.587861476673808e-05,
|
| 87 |
+
"loss": 0.6218611907958984,
|
| 88 |
+
"mean_token_accuracy": 0.8167323243618011,
|
| 89 |
+
"num_tokens": 1310490.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.0,
|
| 94 |
+
"eval_entropy": 0.8066210185552573,
|
| 95 |
+
"eval_loss": 0.7281543016433716,
|
| 96 |
+
"eval_mean_token_accuracy": 0.7858095281309896,
|
| 97 |
+
"eval_num_tokens": 1399670.0,
|
| 98 |
+
"eval_runtime": 46.0044,
|
| 99 |
+
"eval_samples_per_second": 26.758,
|
| 100 |
+
"eval_steps_per_second": 3.348,
|
| 101 |
+
"step": 428
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.6467276298999787,
|
| 105 |
+
"epoch": 1.0514018691588785,
|
| 106 |
+
"grad_norm": 0.626556396484375,
|
| 107 |
+
"learning_rate": 1.7031450502641085e-05,
|
| 108 |
+
"loss": 0.6161280441284179,
|
| 109 |
+
"mean_token_accuracy": 0.817004052400589,
|
| 110 |
+
"num_tokens": 1471726.0,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.6262363213300705,
|
| 115 |
+
"epoch": 1.1682242990654206,
|
| 116 |
+
"grad_norm": 0.70875084400177,
|
| 117 |
+
"learning_rate": 1.7018425538355792e-05,
|
| 118 |
+
"loss": 0.5963106536865235,
|
| 119 |
+
"mean_token_accuracy": 0.8221335035562515,
|
| 120 |
+
"num_tokens": 1638060.0,
|
| 121 |
+
"step": 500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"entropy": 0.6171189111471176,
|
| 125 |
+
"epoch": 1.2850467289719627,
|
| 126 |
+
"grad_norm": 0.6629440188407898,
|
| 127 |
+
"learning_rate": 1.6991264396738895e-05,
|
| 128 |
+
"loss": 0.5875393676757813,
|
| 129 |
+
"mean_token_accuracy": 0.8245152229070664,
|
| 130 |
+
"num_tokens": 1802005.0,
|
| 131 |
+
"step": 550
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"entropy": 0.6083133199810982,
|
| 135 |
+
"epoch": 1.4018691588785046,
|
| 136 |
+
"grad_norm": 0.5385038256645203,
|
| 137 |
+
"learning_rate": 1.6950012237904817e-05,
|
| 138 |
+
"loss": 0.5768455505371094,
|
| 139 |
+
"mean_token_accuracy": 0.8271224808692932,
|
| 140 |
+
"num_tokens": 1969267.0,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"entropy": 0.6011673760414123,
|
| 145 |
+
"epoch": 1.5186915887850467,
|
| 146 |
+
"grad_norm": 0.7062859535217285,
|
| 147 |
+
"learning_rate": 1.6894737650731013e-05,
|
| 148 |
+
"loss": 0.5666856384277343,
|
| 149 |
+
"mean_token_accuracy": 0.829860600233078,
|
| 150 |
+
"num_tokens": 2134793.0,
|
| 151 |
+
"step": 650
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"entropy": 0.5905318284034728,
|
| 155 |
+
"epoch": 1.6355140186915889,
|
| 156 |
+
"grad_norm": 0.646713137626648,
|
| 157 |
+
"learning_rate": 1.682553253881702e-05,
|
| 158 |
+
"loss": 0.560577392578125,
|
| 159 |
+
"mean_token_accuracy": 0.8313507026433945,
|
| 160 |
+
"num_tokens": 2300672.0,
|
| 161 |
+
"step": 700
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"entropy": 0.5964298728108406,
|
| 165 |
+
"epoch": 1.7523364485981308,
|
| 166 |
+
"grad_norm": 0.6510505080223083,
|
| 167 |
+
"learning_rate": 1.674251196767876e-05,
|
| 168 |
+
"loss": 0.5606492614746094,
|
| 169 |
+
"mean_token_accuracy": 0.8313686531782151,
|
| 170 |
+
"num_tokens": 2459315.0,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"entropy": 0.5872641482949257,
|
| 175 |
+
"epoch": 1.8691588785046729,
|
| 176 |
+
"grad_norm": 0.6211879849433899,
|
| 177 |
+
"learning_rate": 1.6645813973432182e-05,
|
| 178 |
+
"loss": 0.556594352722168,
|
| 179 |
+
"mean_token_accuracy": 0.8333250796794891,
|
| 180 |
+
"num_tokens": 2616878.0,
|
| 181 |
+
"step": 800
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"entropy": 0.5889243066310883,
|
| 185 |
+
"epoch": 1.985981308411215,
|
| 186 |
+
"grad_norm": 0.6804038882255554,
|
| 187 |
+
"learning_rate": 1.6535599333284194e-05,
|
| 188 |
+
"loss": 0.5578879928588867,
|
| 189 |
+
"mean_token_accuracy": 0.831966199874878,
|
| 190 |
+
"num_tokens": 2778909.0,
|
| 191 |
+
"step": 850
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
+
"eval_entropy": 0.7079034389613511,
|
| 196 |
+
"eval_loss": 0.6832069158554077,
|
| 197 |
+
"eval_mean_token_accuracy": 0.8022074165282311,
|
| 198 |
+
"eval_num_tokens": 2799340.0,
|
| 199 |
+
"eval_runtime": 46.0398,
|
| 200 |
+
"eval_samples_per_second": 26.738,
|
| 201 |
+
"eval_steps_per_second": 3.345,
|
| 202 |
+
"step": 856
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"entropy": 0.5462229257822037,
|
| 206 |
+
"epoch": 2.102803738317757,
|
| 207 |
+
"grad_norm": 0.5834382772445679,
|
| 208 |
+
"learning_rate": 1.6412051298212675e-05,
|
| 209 |
+
"loss": 0.5115155029296875,
|
| 210 |
+
"mean_token_accuracy": 0.8419190347194672,
|
| 211 |
+
"num_tokens": 2951115.0,
|
| 212 |
+
"step": 900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"entropy": 0.5501805812120437,
|
| 216 |
+
"epoch": 2.2196261682242993,
|
| 217 |
+
"grad_norm": 0.774409830570221,
|
| 218 |
+
"learning_rate": 1.627537528827988e-05,
|
| 219 |
+
"loss": 0.5193024826049805,
|
| 220 |
+
"mean_token_accuracy": 0.8415862208604813,
|
| 221 |
+
"num_tokens": 3115016.0,
|
| 222 |
+
"step": 950
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"entropy": 0.5417112326622009,
|
| 226 |
+
"epoch": 2.336448598130841,
|
| 227 |
+
"grad_norm": 0.8148911595344543,
|
| 228 |
+
"learning_rate": 1.612579855108594e-05,
|
| 229 |
+
"loss": 0.5099837875366211,
|
| 230 |
+
"mean_token_accuracy": 0.8432273292541503,
|
| 231 |
+
"num_tokens": 3274313.0,
|
| 232 |
+
"step": 1000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"entropy": 0.5426027116179466,
|
| 236 |
+
"epoch": 2.453271028037383,
|
| 237 |
+
"grad_norm": 0.738017737865448,
|
| 238 |
+
"learning_rate": 1.596356978393025e-05,
|
| 239 |
+
"loss": 0.5110509490966797,
|
| 240 |
+
"mean_token_accuracy": 0.8447510355710983,
|
| 241 |
+
"num_tokens": 3440379.0,
|
| 242 |
+
"step": 1050
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"entropy": 0.536553855240345,
|
| 246 |
+
"epoch": 2.5700934579439254,
|
| 247 |
+
"grad_norm": 0.6512451767921448,
|
| 248 |
+
"learning_rate": 1.5788958720309008e-05,
|
| 249 |
+
"loss": 0.5046747207641602,
|
| 250 |
+
"mean_token_accuracy": 0.8439748030900955,
|
| 251 |
+
"num_tokens": 3606755.0,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"entropy": 0.5361887359619141,
|
| 256 |
+
"epoch": 2.6869158878504673,
|
| 257 |
+
"grad_norm": 0.7650485038757324,
|
| 258 |
+
"learning_rate": 1.5602255681436483e-05,
|
| 259 |
+
"loss": 0.5043494415283203,
|
| 260 |
+
"mean_token_accuracy": 0.8450696021318436,
|
| 261 |
+
"num_tokens": 3766555.0,
|
| 262 |
+
"step": 1150
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"entropy": 0.5419432005286217,
|
| 266 |
+
"epoch": 2.803738317757009,
|
| 267 |
+
"grad_norm": 0.6945335268974304,
|
| 268 |
+
"learning_rate": 1.5403771093535538e-05,
|
| 269 |
+
"loss": 0.5108187103271484,
|
| 270 |
+
"mean_token_accuracy": 0.8431807065010071,
|
| 271 |
+
"num_tokens": 3927164.0,
|
| 272 |
+
"step": 1200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"entropy": 0.5400136861205102,
|
| 276 |
+
"epoch": 2.9205607476635516,
|
| 277 |
+
"grad_norm": 0.774668276309967,
|
| 278 |
+
"learning_rate": 1.5193834971700146e-05,
|
| 279 |
+
"loss": 0.5082107543945312,
|
| 280 |
+
"mean_token_accuracy": 0.8444043332338333,
|
| 281 |
+
"num_tokens": 4090727.0,
|
| 282 |
+
"step": 1250
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.0,
|
| 286 |
+
"eval_entropy": 0.6524020644364419,
|
| 287 |
+
"eval_loss": 0.6701120138168335,
|
| 288 |
+
"eval_mean_token_accuracy": 0.8018650695101007,
|
| 289 |
+
"eval_num_tokens": 4199010.0,
|
| 290 |
+
"eval_runtime": 46.004,
|
| 291 |
+
"eval_samples_per_second": 26.759,
|
| 292 |
+
"eval_steps_per_second": 3.348,
|
| 293 |
+
"step": 1284
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"entropy": 0.5256310805678368,
|
| 297 |
+
"epoch": 3.0373831775700935,
|
| 298 |
+
"grad_norm": 0.8875723481178284,
|
| 299 |
+
"learning_rate": 1.4972796371187997e-05,
|
| 300 |
+
"loss": 0.49435077667236327,
|
| 301 |
+
"mean_token_accuracy": 0.8473169440031052,
|
| 302 |
+
"num_tokens": 4252535.0,
|
| 303 |
+
"step": 1300
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"entropy": 0.4986111795902252,
|
| 307 |
+
"epoch": 3.1542056074766354,
|
| 308 |
+
"grad_norm": 0.8605287671089172,
|
| 309 |
+
"learning_rate": 1.4741022807055508e-05,
|
| 310 |
+
"loss": 0.4662786483764648,
|
| 311 |
+
"mean_token_accuracy": 0.8552708566188812,
|
| 312 |
+
"num_tokens": 4414122.0,
|
| 313 |
+
"step": 1350
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"entropy": 0.5061789083480835,
|
| 317 |
+
"epoch": 3.2710280373831777,
|
| 318 |
+
"grad_norm": 0.8101795315742493,
|
| 319 |
+
"learning_rate": 1.4498899643100226e-05,
|
| 320 |
+
"loss": 0.47242179870605466,
|
| 321 |
+
"mean_token_accuracy": 0.8520459419488907,
|
| 322 |
+
"num_tokens": 4571859.0,
|
| 323 |
+
"step": 1400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"entropy": 0.4939887225627899,
|
| 327 |
+
"epoch": 3.3878504672897196,
|
| 328 |
+
"grad_norm": 0.8013083338737488,
|
| 329 |
+
"learning_rate": 1.4246829451126602e-05,
|
| 330 |
+
"loss": 0.4614598846435547,
|
| 331 |
+
"mean_token_accuracy": 0.8552495676279068,
|
| 332 |
+
"num_tokens": 4735006.0,
|
| 333 |
+
"step": 1450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"entropy": 0.4918920609354973,
|
| 337 |
+
"epoch": 3.5046728971962615,
|
| 338 |
+
"grad_norm": 0.7743699550628662,
|
| 339 |
+
"learning_rate": 1.3985231341600455e-05,
|
| 340 |
+
"loss": 0.46159915924072265,
|
| 341 |
+
"mean_token_accuracy": 0.8550176537036895,
|
| 342 |
+
"num_tokens": 4898228.0,
|
| 343 |
+
"step": 1500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"entropy": 0.49779762893915175,
|
| 347 |
+
"epoch": 3.621495327102804,
|
| 348 |
+
"grad_norm": 0.8169922828674316,
|
| 349 |
+
"learning_rate": 1.3714540266805045e-05,
|
| 350 |
+
"loss": 0.46558887481689454,
|
| 351 |
+
"mean_token_accuracy": 0.8540038305521012,
|
| 352 |
+
"num_tokens": 5063413.0,
|
| 353 |
+
"step": 1550
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"entropy": 0.5015265879034996,
|
| 357 |
+
"epoch": 3.7383177570093458,
|
| 358 |
+
"grad_norm": 0.851017951965332,
|
| 359 |
+
"learning_rate": 1.343520629765737e-05,
|
| 360 |
+
"loss": 0.46733531951904295,
|
| 361 |
+
"mean_token_accuracy": 0.8522392755746842,
|
| 362 |
+
"num_tokens": 5227672.0,
|
| 363 |
+
"step": 1600
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"entropy": 0.501338247358799,
|
| 367 |
+
"epoch": 3.8551401869158877,
|
| 368 |
+
"grad_norm": 0.8121753334999084,
|
| 369 |
+
"learning_rate": 1.3147693875387126e-05,
|
| 370 |
+
"loss": 0.4710521697998047,
|
| 371 |
+
"mean_token_accuracy": 0.8534136080741882,
|
| 372 |
+
"num_tokens": 5389834.0,
|
| 373 |
+
"step": 1650
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"entropy": 0.49478380143642425,
|
| 377 |
+
"epoch": 3.97196261682243,
|
| 378 |
+
"grad_norm": 0.6918302178382874,
|
| 379 |
+
"learning_rate": 1.2852481039322492e-05,
|
| 380 |
+
"loss": 0.4646331405639648,
|
| 381 |
+
"mean_token_accuracy": 0.8551374357938767,
|
| 382 |
+
"num_tokens": 5559167.0,
|
| 383 |
+
"step": 1700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.0,
|
| 387 |
+
"eval_entropy": 0.6295453201640736,
|
| 388 |
+
"eval_loss": 0.666642427444458,
|
| 389 |
+
"eval_mean_token_accuracy": 0.8111948270302314,
|
| 390 |
+
"eval_num_tokens": 5598680.0,
|
| 391 |
+
"eval_runtime": 45.8725,
|
| 392 |
+
"eval_samples_per_second": 26.835,
|
| 393 |
+
"eval_steps_per_second": 3.357,
|
| 394 |
+
"step": 1712
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"entropy": 0.46167980462312697,
|
| 398 |
+
"epoch": 4.088785046728972,
|
| 399 |
+
"grad_norm": 0.8769540190696716,
|
| 400 |
+
"learning_rate": 1.2550058632066751e-05,
|
| 401 |
+
"loss": 0.4263522338867187,
|
| 402 |
+
"mean_token_accuracy": 0.8653014451265335,
|
| 403 |
+
"num_tokens": 5721701.0,
|
| 404 |
+
"step": 1750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"entropy": 0.4534104973077774,
|
| 408 |
+
"epoch": 4.205607476635514,
|
| 409 |
+
"grad_norm": 1.1420735120773315,
|
| 410 |
+
"learning_rate": 1.2240929483387228e-05,
|
| 411 |
+
"loss": 0.41863834381103515,
|
| 412 |
+
"mean_token_accuracy": 0.8667230373620987,
|
| 413 |
+
"num_tokens": 5884163.0,
|
| 414 |
+
"step": 1800
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"entropy": 0.4606948295235634,
|
| 418 |
+
"epoch": 4.322429906542056,
|
| 419 |
+
"grad_norm": 1.0596942901611328,
|
| 420 |
+
"learning_rate": 1.1925607574173476e-05,
|
| 421 |
+
"loss": 0.42718273162841797,
|
| 422 |
+
"mean_token_accuracy": 0.8641588741540909,
|
| 423 |
+
"num_tokens": 6053869.0,
|
| 424 |
+
"step": 1850
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"entropy": 0.45681062549352647,
|
| 428 |
+
"epoch": 4.4392523364485985,
|
| 429 |
+
"grad_norm": 0.9009803533554077,
|
| 430 |
+
"learning_rate": 1.1604617181854806e-05,
|
| 431 |
+
"loss": 0.42521621704101564,
|
| 432 |
+
"mean_token_accuracy": 0.8644315087795258,
|
| 433 |
+
"num_tokens": 6217351.0,
|
| 434 |
+
"step": 1900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"entropy": 0.45814105302095415,
|
| 438 |
+
"epoch": 4.55607476635514,
|
| 439 |
+
"grad_norm": 0.9394752383232117,
|
| 440 |
+
"learning_rate": 1.127849200869801e-05,
|
| 441 |
+
"loss": 0.42409008026123046,
|
| 442 |
+
"mean_token_accuracy": 0.864885100722313,
|
| 443 |
+
"num_tokens": 6379796.0,
|
| 444 |
+
"step": 1950
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"entropy": 0.4561432495713234,
|
| 448 |
+
"epoch": 4.672897196261682,
|
| 449 |
+
"grad_norm": 0.8258721828460693,
|
| 450 |
+
"learning_rate": 1.094777429443468e-05,
|
| 451 |
+
"loss": 0.42701839447021483,
|
| 452 |
+
"mean_token_accuracy": 0.8638879442214966,
|
| 453 |
+
"num_tokens": 6550276.0,
|
| 454 |
+
"step": 2000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"entropy": 0.4610430991649628,
|
| 458 |
+
"epoch": 4.789719626168225,
|
| 459 |
+
"grad_norm": 1.0002802610397339,
|
| 460 |
+
"learning_rate": 1.0613013914693477e-05,
|
| 461 |
+
"loss": 0.4286579895019531,
|
| 462 |
+
"mean_token_accuracy": 0.8643757510185242,
|
| 463 |
+
"num_tokens": 6709429.0,
|
| 464 |
+
"step": 2050
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"entropy": 0.4558544892072678,
|
| 468 |
+
"epoch": 4.906542056074766,
|
| 469 |
+
"grad_norm": 0.9755097031593323,
|
| 470 |
+
"learning_rate": 1.0274767466736426e-05,
|
| 471 |
+
"loss": 0.4233176803588867,
|
| 472 |
+
"mean_token_accuracy": 0.8655301338434219,
|
| 473 |
+
"num_tokens": 6870956.0,
|
| 474 |
+
"step": 2100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.0,
|
| 478 |
+
"eval_entropy": 0.6000483314712326,
|
| 479 |
+
"eval_loss": 0.6985165476799011,
|
| 480 |
+
"eval_mean_token_accuracy": 0.8045627912143608,
|
| 481 |
+
"eval_num_tokens": 6998350.0,
|
| 482 |
+
"eval_runtime": 45.9034,
|
| 483 |
+
"eval_samples_per_second": 26.817,
|
| 484 |
+
"eval_steps_per_second": 3.355,
|
| 485 |
+
"step": 2140
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"entropy": 0.44992744773626325,
|
| 489 |
+
"epoch": 5.0233644859813085,
|
| 490 |
+
"grad_norm": 1.1082366704940796,
|
| 491 |
+
"learning_rate": 9.933597344019314e-06,
|
| 492 |
+
"loss": 0.41550483703613283,
|
| 493 |
+
"mean_token_accuracy": 0.8669036704301835,
|
| 494 |
+
"num_tokens": 7034085.0,
|
| 495 |
+
"step": 2150
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"entropy": 0.4088956421613693,
|
| 499 |
+
"epoch": 5.140186915887851,
|
| 500 |
+
"grad_norm": 1.0101401805877686,
|
| 501 |
+
"learning_rate": 9.59007080111491e-06,
|
| 502 |
+
"loss": 0.3716637420654297,
|
| 503 |
+
"mean_token_accuracy": 0.8802521765232086,
|
| 504 |
+
"num_tokens": 7198745.0,
|
| 505 |
+
"step": 2200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"entropy": 0.4127876952290535,
|
| 509 |
+
"epoch": 5.257009345794392,
|
| 510 |
+
"grad_norm": 1.1201362609863281,
|
| 511 |
+
"learning_rate": 9.244759010553727e-06,
|
| 512 |
+
"loss": 0.37826343536376955,
|
| 513 |
+
"mean_token_accuracy": 0.8786936563253402,
|
| 514 |
+
"num_tokens": 7366588.0,
|
| 515 |
+
"step": 2250
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"entropy": 0.4232992666959763,
|
| 519 |
+
"epoch": 5.373831775700935,
|
| 520 |
+
"grad_norm": 1.1778150796890259,
|
| 521 |
+
"learning_rate": 8.898236113150524e-06,
|
| 522 |
+
"loss": 0.38583309173583985,
|
| 523 |
+
"mean_token_accuracy": 0.8747973537445068,
|
| 524 |
+
"num_tokens": 7531696.0,
|
| 525 |
+
"step": 2300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"entropy": 0.4159915736317635,
|
| 529 |
+
"epoch": 5.490654205607477,
|
| 530 |
+
"grad_norm": 1.1592568159103394,
|
| 531 |
+
"learning_rate": 8.551078263395478e-06,
|
| 532 |
+
"loss": 0.3784225082397461,
|
| 533 |
+
"mean_token_accuracy": 0.8779372000694274,
|
| 534 |
+
"num_tokens": 7688960.0,
|
| 535 |
+
"step": 2350
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"entropy": 0.41662866294384004,
|
| 539 |
+
"epoch": 5.607476635514018,
|
| 540 |
+
"grad_norm": 1.254981517791748,
|
| 541 |
+
"learning_rate": 8.203862671497323e-06,
|
| 542 |
+
"loss": 0.37995223999023436,
|
| 543 |
+
"mean_token_accuracy": 0.8772805953025817,
|
| 544 |
+
"num_tokens": 7851053.0,
|
| 545 |
+
"step": 2400
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"entropy": 0.417872933447361,
|
| 549 |
+
"epoch": 5.724299065420561,
|
| 550 |
+
"grad_norm": 1.322206974029541,
|
| 551 |
+
"learning_rate": 7.857166643671128e-06,
|
| 552 |
+
"loss": 0.38079578399658204,
|
| 553 |
+
"mean_token_accuracy": 0.8774149787425994,
|
| 554 |
+
"num_tokens": 8001524.0,
|
| 555 |
+
"step": 2450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"entropy": 0.41878397345542906,
|
| 559 |
+
"epoch": 5.841121495327103,
|
| 560 |
+
"grad_norm": 1.2948966026306152,
|
| 561 |
+
"learning_rate": 7.511566622266466e-06,
|
| 562 |
+
"loss": 0.3861651611328125,
|
| 563 |
+
"mean_token_accuracy": 0.8755189329385757,
|
| 564 |
+
"num_tokens": 8166394.0,
|
| 565 |
+
"step": 2500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"entropy": 0.4128647845983505,
|
| 569 |
+
"epoch": 5.957943925233645,
|
| 570 |
+
"grad_norm": 1.190157175064087,
|
| 571 |
+
"learning_rate": 7.167637227331918e-06,
|
| 572 |
+
"loss": 0.37860721588134766,
|
| 573 |
+
"mean_token_accuracy": 0.8772583198547363,
|
| 574 |
+
"num_tokens": 8339045.0,
|
| 575 |
+
"step": 2550
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 6.0,
|
| 579 |
+
"eval_entropy": 0.5655807773401211,
|
| 580 |
+
"eval_loss": 0.7187017202377319,
|
| 581 |
+
"eval_mean_token_accuracy": 0.8067006375882533,
|
| 582 |
+
"eval_num_tokens": 8398020.0,
|
| 583 |
+
"eval_runtime": 45.9295,
|
| 584 |
+
"eval_samples_per_second": 26.802,
|
| 585 |
+
"eval_steps_per_second": 3.353,
|
| 586 |
+
"step": 2568
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.3961917132139206,
|
| 590 |
+
"epoch": 6.074766355140187,
|
| 591 |
+
"grad_norm": 1.1673611402511597,
|
| 592 |
+
"learning_rate": 6.82595030120946e-06,
|
| 593 |
+
"loss": 0.35439579010009764,
|
| 594 |
+
"mean_token_accuracy": 0.8850088411569595,
|
| 595 |
+
"num_tokens": 8502228.0,
|
| 596 |
+
"step": 2600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.368110328912735,
|
| 600 |
+
"epoch": 6.191588785046729,
|
| 601 |
+
"grad_norm": 1.3757716417312622,
|
| 602 |
+
"learning_rate": 6.487073957747255e-06,
|
| 603 |
+
"loss": 0.32657440185546877,
|
| 604 |
+
"mean_token_accuracy": 0.8935984402894974,
|
| 605 |
+
"num_tokens": 8670819.0,
|
| 606 |
+
"step": 2650
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 0.38117473274469377,
|
| 610 |
+
"epoch": 6.308411214953271,
|
| 611 |
+
"grad_norm": 1.5222810506820679,
|
| 612 |
+
"learning_rate": 6.151571637711756e-06,
|
| 613 |
+
"loss": 0.33884075164794925,
|
| 614 |
+
"mean_token_accuracy": 0.8893738853931427,
|
| 615 |
+
"num_tokens": 8833691.0,
|
| 616 |
+
"step": 2700
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 0.368239968419075,
|
| 620 |
+
"epoch": 6.425233644859813,
|
| 621 |
+
"grad_norm": 1.35374116897583,
|
| 622 |
+
"learning_rate": 5.820001171969559e-06,
|
| 623 |
+
"loss": 0.32751472473144533,
|
| 624 |
+
"mean_token_accuracy": 0.8923951196670532,
|
| 625 |
+
"num_tokens": 8991136.0,
|
| 626 |
+
"step": 2750
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 0.3820819303393364,
|
| 630 |
+
"epoch": 6.542056074766355,
|
| 631 |
+
"grad_norm": 1.4458277225494385,
|
| 632 |
+
"learning_rate": 5.492913853996745e-06,
|
| 633 |
+
"loss": 0.33998115539550783,
|
| 634 |
+
"mean_token_accuracy": 0.8889218932390213,
|
| 635 |
+
"num_tokens": 9156211.0,
|
| 636 |
+
"step": 2800
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 0.37935444712638855,
|
| 640 |
+
"epoch": 6.658878504672897,
|
| 641 |
+
"grad_norm": 1.407097339630127,
|
| 642 |
+
"learning_rate": 5.170853523257732e-06,
|
| 643 |
+
"loss": 0.33896163940429686,
|
| 644 |
+
"mean_token_accuracy": 0.8889170825481415,
|
| 645 |
+
"num_tokens": 9320538.0,
|
| 646 |
+
"step": 2850
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 0.3754119920730591,
|
| 650 |
+
"epoch": 6.775700934579439,
|
| 651 |
+
"grad_norm": 1.343308448791504,
|
| 652 |
+
"learning_rate": 4.854355660977731e-06,
|
| 653 |
+
"loss": 0.33744224548339846,
|
| 654 |
+
"mean_token_accuracy": 0.8890663629770279,
|
| 655 |
+
"num_tokens": 9480686.0,
|
| 656 |
+
"step": 2900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 0.3785912898182869,
|
| 660 |
+
"epoch": 6.892523364485982,
|
| 661 |
+
"grad_norm": 1.3478388786315918,
|
| 662 |
+
"learning_rate": 4.543946499812223e-06,
|
| 663 |
+
"loss": 0.3381637954711914,
|
| 664 |
+
"mean_token_accuracy": 0.890493910908699,
|
| 665 |
+
"num_tokens": 9644088.0,
|
| 666 |
+
"step": 2950
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 7.0,
|
| 670 |
+
"eval_entropy": 0.5324798737253461,
|
| 671 |
+
"eval_loss": 0.7690625786781311,
|
| 672 |
+
"eval_mean_token_accuracy": 0.8012763478539207,
|
| 673 |
+
"eval_num_tokens": 9797690.0,
|
| 674 |
+
"eval_runtime": 45.8503,
|
| 675 |
+
"eval_samples_per_second": 26.848,
|
| 676 |
+
"eval_steps_per_second": 3.359,
|
| 677 |
+
"step": 2996
|
| 678 |
+
}
|
| 679 |
+
],
|
| 680 |
+
"logging_steps": 50,
|
| 681 |
+
"max_steps": 4280,
|
| 682 |
+
"num_input_tokens_seen": 0,
|
| 683 |
+
"num_train_epochs": 10,
|
| 684 |
+
"save_steps": 500,
|
| 685 |
+
"stateful_callbacks": {
|
| 686 |
+
"TrainerControl": {
|
| 687 |
+
"args": {
|
| 688 |
+
"should_epoch_stop": false,
|
| 689 |
+
"should_evaluate": false,
|
| 690 |
+
"should_log": false,
|
| 691 |
+
"should_save": true,
|
| 692 |
+
"should_training_stop": false
|
| 693 |
+
},
|
| 694 |
+
"attributes": {}
|
| 695 |
+
}
|
| 696 |
+
},
|
| 697 |
+
"total_flos": 1.8470249147543962e+18,
|
| 698 |
+
"train_batch_size": 8,
|
| 699 |
+
"trial_name": null,
|
| 700 |
+
"trial_params": null
|
| 701 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-14B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-14B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-14B-Base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.010622890133962027,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 128,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"q_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3424/trainer_state.json
ADDED
|
@@ -0,0 +1,802 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 8.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3424,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7805559730529785,
|
| 14 |
+
"epoch": 0.11682242990654206,
|
| 15 |
+
"grad_norm": 0.5128960013389587,
|
| 16 |
+
"learning_rate": 1.950005322230992e-06,
|
| 17 |
+
"loss": 1.770846405029297,
|
| 18 |
+
"mean_token_accuracy": 0.6305050283670426,
|
| 19 |
+
"num_tokens": 162248.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5725344836711883,
|
| 24 |
+
"epoch": 0.2336448598130841,
|
| 25 |
+
"grad_norm": 0.7059135437011719,
|
| 26 |
+
"learning_rate": 3.93980667144629e-06,
|
| 27 |
+
"loss": 1.5153414916992187,
|
| 28 |
+
"mean_token_accuracy": 0.6729821544885636,
|
| 29 |
+
"num_tokens": 327614.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.0769569373130798,
|
| 34 |
+
"epoch": 0.35046728971962615,
|
| 35 |
+
"grad_norm": 0.6092284321784973,
|
| 36 |
+
"learning_rate": 5.9296080206615885e-06,
|
| 37 |
+
"loss": 1.0251461791992187,
|
| 38 |
+
"mean_token_accuracy": 0.737835128903389,
|
| 39 |
+
"num_tokens": 494582.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.8583791655302048,
|
| 44 |
+
"epoch": 0.4672897196261682,
|
| 45 |
+
"grad_norm": 0.5586332082748413,
|
| 46 |
+
"learning_rate": 7.919409369876886e-06,
|
| 47 |
+
"loss": 0.81265869140625,
|
| 48 |
+
"mean_token_accuracy": 0.7762657129764556,
|
| 49 |
+
"num_tokens": 653981.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7744105678796768,
|
| 54 |
+
"epoch": 0.5841121495327103,
|
| 55 |
+
"grad_norm": 0.4821721613407135,
|
| 56 |
+
"learning_rate": 9.909210719092184e-06,
|
| 57 |
+
"loss": 0.7364049530029297,
|
| 58 |
+
"mean_token_accuracy": 0.7918167436122894,
|
| 59 |
+
"num_tokens": 814840.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.715560827255249,
|
| 64 |
+
"epoch": 0.7009345794392523,
|
| 65 |
+
"grad_norm": 0.6843860745429993,
|
| 66 |
+
"learning_rate": 1.1899012068307483e-05,
|
| 67 |
+
"loss": 0.6826614379882813,
|
| 68 |
+
"mean_token_accuracy": 0.8043146914243698,
|
| 69 |
+
"num_tokens": 979542.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6893886953592301,
|
| 74 |
+
"epoch": 0.8177570093457944,
|
| 75 |
+
"grad_norm": 0.6543110013008118,
|
| 76 |
+
"learning_rate": 1.3888813417522781e-05,
|
| 77 |
+
"loss": 0.6608805847167969,
|
| 78 |
+
"mean_token_accuracy": 0.8083165866136551,
|
| 79 |
+
"num_tokens": 1147400.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.652973799109459,
|
| 84 |
+
"epoch": 0.9345794392523364,
|
| 85 |
+
"grad_norm": 0.7437635660171509,
|
| 86 |
+
"learning_rate": 1.587861476673808e-05,
|
| 87 |
+
"loss": 0.6218611907958984,
|
| 88 |
+
"mean_token_accuracy": 0.8167323243618011,
|
| 89 |
+
"num_tokens": 1310490.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.0,
|
| 94 |
+
"eval_entropy": 0.8066210185552573,
|
| 95 |
+
"eval_loss": 0.7281543016433716,
|
| 96 |
+
"eval_mean_token_accuracy": 0.7858095281309896,
|
| 97 |
+
"eval_num_tokens": 1399670.0,
|
| 98 |
+
"eval_runtime": 46.0044,
|
| 99 |
+
"eval_samples_per_second": 26.758,
|
| 100 |
+
"eval_steps_per_second": 3.348,
|
| 101 |
+
"step": 428
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.6467276298999787,
|
| 105 |
+
"epoch": 1.0514018691588785,
|
| 106 |
+
"grad_norm": 0.626556396484375,
|
| 107 |
+
"learning_rate": 1.7031450502641085e-05,
|
| 108 |
+
"loss": 0.6161280441284179,
|
| 109 |
+
"mean_token_accuracy": 0.817004052400589,
|
| 110 |
+
"num_tokens": 1471726.0,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.6262363213300705,
|
| 115 |
+
"epoch": 1.1682242990654206,
|
| 116 |
+
"grad_norm": 0.70875084400177,
|
| 117 |
+
"learning_rate": 1.7018425538355792e-05,
|
| 118 |
+
"loss": 0.5963106536865235,
|
| 119 |
+
"mean_token_accuracy": 0.8221335035562515,
|
| 120 |
+
"num_tokens": 1638060.0,
|
| 121 |
+
"step": 500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"entropy": 0.6171189111471176,
|
| 125 |
+
"epoch": 1.2850467289719627,
|
| 126 |
+
"grad_norm": 0.6629440188407898,
|
| 127 |
+
"learning_rate": 1.6991264396738895e-05,
|
| 128 |
+
"loss": 0.5875393676757813,
|
| 129 |
+
"mean_token_accuracy": 0.8245152229070664,
|
| 130 |
+
"num_tokens": 1802005.0,
|
| 131 |
+
"step": 550
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"entropy": 0.6083133199810982,
|
| 135 |
+
"epoch": 1.4018691588785046,
|
| 136 |
+
"grad_norm": 0.5385038256645203,
|
| 137 |
+
"learning_rate": 1.6950012237904817e-05,
|
| 138 |
+
"loss": 0.5768455505371094,
|
| 139 |
+
"mean_token_accuracy": 0.8271224808692932,
|
| 140 |
+
"num_tokens": 1969267.0,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"entropy": 0.6011673760414123,
|
| 145 |
+
"epoch": 1.5186915887850467,
|
| 146 |
+
"grad_norm": 0.7062859535217285,
|
| 147 |
+
"learning_rate": 1.6894737650731013e-05,
|
| 148 |
+
"loss": 0.5666856384277343,
|
| 149 |
+
"mean_token_accuracy": 0.829860600233078,
|
| 150 |
+
"num_tokens": 2134793.0,
|
| 151 |
+
"step": 650
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"entropy": 0.5905318284034728,
|
| 155 |
+
"epoch": 1.6355140186915889,
|
| 156 |
+
"grad_norm": 0.646713137626648,
|
| 157 |
+
"learning_rate": 1.682553253881702e-05,
|
| 158 |
+
"loss": 0.560577392578125,
|
| 159 |
+
"mean_token_accuracy": 0.8313507026433945,
|
| 160 |
+
"num_tokens": 2300672.0,
|
| 161 |
+
"step": 700
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"entropy": 0.5964298728108406,
|
| 165 |
+
"epoch": 1.7523364485981308,
|
| 166 |
+
"grad_norm": 0.6510505080223083,
|
| 167 |
+
"learning_rate": 1.674251196767876e-05,
|
| 168 |
+
"loss": 0.5606492614746094,
|
| 169 |
+
"mean_token_accuracy": 0.8313686531782151,
|
| 170 |
+
"num_tokens": 2459315.0,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"entropy": 0.5872641482949257,
|
| 175 |
+
"epoch": 1.8691588785046729,
|
| 176 |
+
"grad_norm": 0.6211879849433899,
|
| 177 |
+
"learning_rate": 1.6645813973432182e-05,
|
| 178 |
+
"loss": 0.556594352722168,
|
| 179 |
+
"mean_token_accuracy": 0.8333250796794891,
|
| 180 |
+
"num_tokens": 2616878.0,
|
| 181 |
+
"step": 800
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"entropy": 0.5889243066310883,
|
| 185 |
+
"epoch": 1.985981308411215,
|
| 186 |
+
"grad_norm": 0.6804038882255554,
|
| 187 |
+
"learning_rate": 1.6535599333284194e-05,
|
| 188 |
+
"loss": 0.5578879928588867,
|
| 189 |
+
"mean_token_accuracy": 0.831966199874878,
|
| 190 |
+
"num_tokens": 2778909.0,
|
| 191 |
+
"step": 850
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
+
"eval_entropy": 0.7079034389613511,
|
| 196 |
+
"eval_loss": 0.6832069158554077,
|
| 197 |
+
"eval_mean_token_accuracy": 0.8022074165282311,
|
| 198 |
+
"eval_num_tokens": 2799340.0,
|
| 199 |
+
"eval_runtime": 46.0398,
|
| 200 |
+
"eval_samples_per_second": 26.738,
|
| 201 |
+
"eval_steps_per_second": 3.345,
|
| 202 |
+
"step": 856
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"entropy": 0.5462229257822037,
|
| 206 |
+
"epoch": 2.102803738317757,
|
| 207 |
+
"grad_norm": 0.5834382772445679,
|
| 208 |
+
"learning_rate": 1.6412051298212675e-05,
|
| 209 |
+
"loss": 0.5115155029296875,
|
| 210 |
+
"mean_token_accuracy": 0.8419190347194672,
|
| 211 |
+
"num_tokens": 2951115.0,
|
| 212 |
+
"step": 900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"entropy": 0.5501805812120437,
|
| 216 |
+
"epoch": 2.2196261682242993,
|
| 217 |
+
"grad_norm": 0.774409830570221,
|
| 218 |
+
"learning_rate": 1.627537528827988e-05,
|
| 219 |
+
"loss": 0.5193024826049805,
|
| 220 |
+
"mean_token_accuracy": 0.8415862208604813,
|
| 221 |
+
"num_tokens": 3115016.0,
|
| 222 |
+
"step": 950
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"entropy": 0.5417112326622009,
|
| 226 |
+
"epoch": 2.336448598130841,
|
| 227 |
+
"grad_norm": 0.8148911595344543,
|
| 228 |
+
"learning_rate": 1.612579855108594e-05,
|
| 229 |
+
"loss": 0.5099837875366211,
|
| 230 |
+
"mean_token_accuracy": 0.8432273292541503,
|
| 231 |
+
"num_tokens": 3274313.0,
|
| 232 |
+
"step": 1000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"entropy": 0.5426027116179466,
|
| 236 |
+
"epoch": 2.453271028037383,
|
| 237 |
+
"grad_norm": 0.738017737865448,
|
| 238 |
+
"learning_rate": 1.596356978393025e-05,
|
| 239 |
+
"loss": 0.5110509490966797,
|
| 240 |
+
"mean_token_accuracy": 0.8447510355710983,
|
| 241 |
+
"num_tokens": 3440379.0,
|
| 242 |
+
"step": 1050
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"entropy": 0.536553855240345,
|
| 246 |
+
"epoch": 2.5700934579439254,
|
| 247 |
+
"grad_norm": 0.6512451767921448,
|
| 248 |
+
"learning_rate": 1.5788958720309008e-05,
|
| 249 |
+
"loss": 0.5046747207641602,
|
| 250 |
+
"mean_token_accuracy": 0.8439748030900955,
|
| 251 |
+
"num_tokens": 3606755.0,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"entropy": 0.5361887359619141,
|
| 256 |
+
"epoch": 2.6869158878504673,
|
| 257 |
+
"grad_norm": 0.7650485038757324,
|
| 258 |
+
"learning_rate": 1.5602255681436483e-05,
|
| 259 |
+
"loss": 0.5043494415283203,
|
| 260 |
+
"mean_token_accuracy": 0.8450696021318436,
|
| 261 |
+
"num_tokens": 3766555.0,
|
| 262 |
+
"step": 1150
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"entropy": 0.5419432005286217,
|
| 266 |
+
"epoch": 2.803738317757009,
|
| 267 |
+
"grad_norm": 0.6945335268974304,
|
| 268 |
+
"learning_rate": 1.5403771093535538e-05,
|
| 269 |
+
"loss": 0.5108187103271484,
|
| 270 |
+
"mean_token_accuracy": 0.8431807065010071,
|
| 271 |
+
"num_tokens": 3927164.0,
|
| 272 |
+
"step": 1200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"entropy": 0.5400136861205102,
|
| 276 |
+
"epoch": 2.9205607476635516,
|
| 277 |
+
"grad_norm": 0.774668276309967,
|
| 278 |
+
"learning_rate": 1.5193834971700146e-05,
|
| 279 |
+
"loss": 0.5082107543945312,
|
| 280 |
+
"mean_token_accuracy": 0.8444043332338333,
|
| 281 |
+
"num_tokens": 4090727.0,
|
| 282 |
+
"step": 1250
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.0,
|
| 286 |
+
"eval_entropy": 0.6524020644364419,
|
| 287 |
+
"eval_loss": 0.6701120138168335,
|
| 288 |
+
"eval_mean_token_accuracy": 0.8018650695101007,
|
| 289 |
+
"eval_num_tokens": 4199010.0,
|
| 290 |
+
"eval_runtime": 46.004,
|
| 291 |
+
"eval_samples_per_second": 26.759,
|
| 292 |
+
"eval_steps_per_second": 3.348,
|
| 293 |
+
"step": 1284
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"entropy": 0.5256310805678368,
|
| 297 |
+
"epoch": 3.0373831775700935,
|
| 298 |
+
"grad_norm": 0.8875723481178284,
|
| 299 |
+
"learning_rate": 1.4972796371187997e-05,
|
| 300 |
+
"loss": 0.49435077667236327,
|
| 301 |
+
"mean_token_accuracy": 0.8473169440031052,
|
| 302 |
+
"num_tokens": 4252535.0,
|
| 303 |
+
"step": 1300
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"entropy": 0.4986111795902252,
|
| 307 |
+
"epoch": 3.1542056074766354,
|
| 308 |
+
"grad_norm": 0.8605287671089172,
|
| 309 |
+
"learning_rate": 1.4741022807055508e-05,
|
| 310 |
+
"loss": 0.4662786483764648,
|
| 311 |
+
"mean_token_accuracy": 0.8552708566188812,
|
| 312 |
+
"num_tokens": 4414122.0,
|
| 313 |
+
"step": 1350
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"entropy": 0.5061789083480835,
|
| 317 |
+
"epoch": 3.2710280373831777,
|
| 318 |
+
"grad_norm": 0.8101795315742493,
|
| 319 |
+
"learning_rate": 1.4498899643100226e-05,
|
| 320 |
+
"loss": 0.47242179870605466,
|
| 321 |
+
"mean_token_accuracy": 0.8520459419488907,
|
| 322 |
+
"num_tokens": 4571859.0,
|
| 323 |
+
"step": 1400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"entropy": 0.4939887225627899,
|
| 327 |
+
"epoch": 3.3878504672897196,
|
| 328 |
+
"grad_norm": 0.8013083338737488,
|
| 329 |
+
"learning_rate": 1.4246829451126602e-05,
|
| 330 |
+
"loss": 0.4614598846435547,
|
| 331 |
+
"mean_token_accuracy": 0.8552495676279068,
|
| 332 |
+
"num_tokens": 4735006.0,
|
| 333 |
+
"step": 1450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"entropy": 0.4918920609354973,
|
| 337 |
+
"epoch": 3.5046728971962615,
|
| 338 |
+
"grad_norm": 0.7743699550628662,
|
| 339 |
+
"learning_rate": 1.3985231341600455e-05,
|
| 340 |
+
"loss": 0.46159915924072265,
|
| 341 |
+
"mean_token_accuracy": 0.8550176537036895,
|
| 342 |
+
"num_tokens": 4898228.0,
|
| 343 |
+
"step": 1500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"entropy": 0.49779762893915175,
|
| 347 |
+
"epoch": 3.621495327102804,
|
| 348 |
+
"grad_norm": 0.8169922828674316,
|
| 349 |
+
"learning_rate": 1.3714540266805045e-05,
|
| 350 |
+
"loss": 0.46558887481689454,
|
| 351 |
+
"mean_token_accuracy": 0.8540038305521012,
|
| 352 |
+
"num_tokens": 5063413.0,
|
| 353 |
+
"step": 1550
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"entropy": 0.5015265879034996,
|
| 357 |
+
"epoch": 3.7383177570093458,
|
| 358 |
+
"grad_norm": 0.851017951965332,
|
| 359 |
+
"learning_rate": 1.343520629765737e-05,
|
| 360 |
+
"loss": 0.46733531951904295,
|
| 361 |
+
"mean_token_accuracy": 0.8522392755746842,
|
| 362 |
+
"num_tokens": 5227672.0,
|
| 363 |
+
"step": 1600
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"entropy": 0.501338247358799,
|
| 367 |
+
"epoch": 3.8551401869158877,
|
| 368 |
+
"grad_norm": 0.8121753334999084,
|
| 369 |
+
"learning_rate": 1.3147693875387126e-05,
|
| 370 |
+
"loss": 0.4710521697998047,
|
| 371 |
+
"mean_token_accuracy": 0.8534136080741882,
|
| 372 |
+
"num_tokens": 5389834.0,
|
| 373 |
+
"step": 1650
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"entropy": 0.49478380143642425,
|
| 377 |
+
"epoch": 3.97196261682243,
|
| 378 |
+
"grad_norm": 0.6918302178382874,
|
| 379 |
+
"learning_rate": 1.2852481039322492e-05,
|
| 380 |
+
"loss": 0.4646331405639648,
|
| 381 |
+
"mean_token_accuracy": 0.8551374357938767,
|
| 382 |
+
"num_tokens": 5559167.0,
|
| 383 |
+
"step": 1700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.0,
|
| 387 |
+
"eval_entropy": 0.6295453201640736,
|
| 388 |
+
"eval_loss": 0.666642427444458,
|
| 389 |
+
"eval_mean_token_accuracy": 0.8111948270302314,
|
| 390 |
+
"eval_num_tokens": 5598680.0,
|
| 391 |
+
"eval_runtime": 45.8725,
|
| 392 |
+
"eval_samples_per_second": 26.835,
|
| 393 |
+
"eval_steps_per_second": 3.357,
|
| 394 |
+
"step": 1712
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"entropy": 0.46167980462312697,
|
| 398 |
+
"epoch": 4.088785046728972,
|
| 399 |
+
"grad_norm": 0.8769540190696716,
|
| 400 |
+
"learning_rate": 1.2550058632066751e-05,
|
| 401 |
+
"loss": 0.4263522338867187,
|
| 402 |
+
"mean_token_accuracy": 0.8653014451265335,
|
| 403 |
+
"num_tokens": 5721701.0,
|
| 404 |
+
"step": 1750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"entropy": 0.4534104973077774,
|
| 408 |
+
"epoch": 4.205607476635514,
|
| 409 |
+
"grad_norm": 1.1420735120773315,
|
| 410 |
+
"learning_rate": 1.2240929483387228e-05,
|
| 411 |
+
"loss": 0.41863834381103515,
|
| 412 |
+
"mean_token_accuracy": 0.8667230373620987,
|
| 413 |
+
"num_tokens": 5884163.0,
|
| 414 |
+
"step": 1800
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"entropy": 0.4606948295235634,
|
| 418 |
+
"epoch": 4.322429906542056,
|
| 419 |
+
"grad_norm": 1.0596942901611328,
|
| 420 |
+
"learning_rate": 1.1925607574173476e-05,
|
| 421 |
+
"loss": 0.42718273162841797,
|
| 422 |
+
"mean_token_accuracy": 0.8641588741540909,
|
| 423 |
+
"num_tokens": 6053869.0,
|
| 424 |
+
"step": 1850
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"entropy": 0.45681062549352647,
|
| 428 |
+
"epoch": 4.4392523364485985,
|
| 429 |
+
"grad_norm": 0.9009803533554077,
|
| 430 |
+
"learning_rate": 1.1604617181854806e-05,
|
| 431 |
+
"loss": 0.42521621704101564,
|
| 432 |
+
"mean_token_accuracy": 0.8644315087795258,
|
| 433 |
+
"num_tokens": 6217351.0,
|
| 434 |
+
"step": 1900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"entropy": 0.45814105302095415,
|
| 438 |
+
"epoch": 4.55607476635514,
|
| 439 |
+
"grad_norm": 0.9394752383232117,
|
| 440 |
+
"learning_rate": 1.127849200869801e-05,
|
| 441 |
+
"loss": 0.42409008026123046,
|
| 442 |
+
"mean_token_accuracy": 0.864885100722313,
|
| 443 |
+
"num_tokens": 6379796.0,
|
| 444 |
+
"step": 1950
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"entropy": 0.4561432495713234,
|
| 448 |
+
"epoch": 4.672897196261682,
|
| 449 |
+
"grad_norm": 0.8258721828460693,
|
| 450 |
+
"learning_rate": 1.094777429443468e-05,
|
| 451 |
+
"loss": 0.42701839447021483,
|
| 452 |
+
"mean_token_accuracy": 0.8638879442214966,
|
| 453 |
+
"num_tokens": 6550276.0,
|
| 454 |
+
"step": 2000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"entropy": 0.4610430991649628,
|
| 458 |
+
"epoch": 4.789719626168225,
|
| 459 |
+
"grad_norm": 1.0002802610397339,
|
| 460 |
+
"learning_rate": 1.0613013914693477e-05,
|
| 461 |
+
"loss": 0.4286579895019531,
|
| 462 |
+
"mean_token_accuracy": 0.8643757510185242,
|
| 463 |
+
"num_tokens": 6709429.0,
|
| 464 |
+
"step": 2050
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"entropy": 0.4558544892072678,
|
| 468 |
+
"epoch": 4.906542056074766,
|
| 469 |
+
"grad_norm": 0.9755097031593323,
|
| 470 |
+
"learning_rate": 1.0274767466736426e-05,
|
| 471 |
+
"loss": 0.4233176803588867,
|
| 472 |
+
"mean_token_accuracy": 0.8655301338434219,
|
| 473 |
+
"num_tokens": 6870956.0,
|
| 474 |
+
"step": 2100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.0,
|
| 478 |
+
"eval_entropy": 0.6000483314712326,
|
| 479 |
+
"eval_loss": 0.6985165476799011,
|
| 480 |
+
"eval_mean_token_accuracy": 0.8045627912143608,
|
| 481 |
+
"eval_num_tokens": 6998350.0,
|
| 482 |
+
"eval_runtime": 45.9034,
|
| 483 |
+
"eval_samples_per_second": 26.817,
|
| 484 |
+
"eval_steps_per_second": 3.355,
|
| 485 |
+
"step": 2140
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"entropy": 0.44992744773626325,
|
| 489 |
+
"epoch": 5.0233644859813085,
|
| 490 |
+
"grad_norm": 1.1082366704940796,
|
| 491 |
+
"learning_rate": 9.933597344019314e-06,
|
| 492 |
+
"loss": 0.41550483703613283,
|
| 493 |
+
"mean_token_accuracy": 0.8669036704301835,
|
| 494 |
+
"num_tokens": 7034085.0,
|
| 495 |
+
"step": 2150
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"entropy": 0.4088956421613693,
|
| 499 |
+
"epoch": 5.140186915887851,
|
| 500 |
+
"grad_norm": 1.0101401805877686,
|
| 501 |
+
"learning_rate": 9.59007080111491e-06,
|
| 502 |
+
"loss": 0.3716637420654297,
|
| 503 |
+
"mean_token_accuracy": 0.8802521765232086,
|
| 504 |
+
"num_tokens": 7198745.0,
|
| 505 |
+
"step": 2200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"entropy": 0.4127876952290535,
|
| 509 |
+
"epoch": 5.257009345794392,
|
| 510 |
+
"grad_norm": 1.1201362609863281,
|
| 511 |
+
"learning_rate": 9.244759010553727e-06,
|
| 512 |
+
"loss": 0.37826343536376955,
|
| 513 |
+
"mean_token_accuracy": 0.8786936563253402,
|
| 514 |
+
"num_tokens": 7366588.0,
|
| 515 |
+
"step": 2250
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"entropy": 0.4232992666959763,
|
| 519 |
+
"epoch": 5.373831775700935,
|
| 520 |
+
"grad_norm": 1.1778150796890259,
|
| 521 |
+
"learning_rate": 8.898236113150524e-06,
|
| 522 |
+
"loss": 0.38583309173583985,
|
| 523 |
+
"mean_token_accuracy": 0.8747973537445068,
|
| 524 |
+
"num_tokens": 7531696.0,
|
| 525 |
+
"step": 2300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"entropy": 0.4159915736317635,
|
| 529 |
+
"epoch": 5.490654205607477,
|
| 530 |
+
"grad_norm": 1.1592568159103394,
|
| 531 |
+
"learning_rate": 8.551078263395478e-06,
|
| 532 |
+
"loss": 0.3784225082397461,
|
| 533 |
+
"mean_token_accuracy": 0.8779372000694274,
|
| 534 |
+
"num_tokens": 7688960.0,
|
| 535 |
+
"step": 2350
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"entropy": 0.41662866294384004,
|
| 539 |
+
"epoch": 5.607476635514018,
|
| 540 |
+
"grad_norm": 1.254981517791748,
|
| 541 |
+
"learning_rate": 8.203862671497323e-06,
|
| 542 |
+
"loss": 0.37995223999023436,
|
| 543 |
+
"mean_token_accuracy": 0.8772805953025817,
|
| 544 |
+
"num_tokens": 7851053.0,
|
| 545 |
+
"step": 2400
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"entropy": 0.417872933447361,
|
| 549 |
+
"epoch": 5.724299065420561,
|
| 550 |
+
"grad_norm": 1.322206974029541,
|
| 551 |
+
"learning_rate": 7.857166643671128e-06,
|
| 552 |
+
"loss": 0.38079578399658204,
|
| 553 |
+
"mean_token_accuracy": 0.8774149787425994,
|
| 554 |
+
"num_tokens": 8001524.0,
|
| 555 |
+
"step": 2450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"entropy": 0.41878397345542906,
|
| 559 |
+
"epoch": 5.841121495327103,
|
| 560 |
+
"grad_norm": 1.2948966026306152,
|
| 561 |
+
"learning_rate": 7.511566622266466e-06,
|
| 562 |
+
"loss": 0.3861651611328125,
|
| 563 |
+
"mean_token_accuracy": 0.8755189329385757,
|
| 564 |
+
"num_tokens": 8166394.0,
|
| 565 |
+
"step": 2500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"entropy": 0.4128647845983505,
|
| 569 |
+
"epoch": 5.957943925233645,
|
| 570 |
+
"grad_norm": 1.190157175064087,
|
| 571 |
+
"learning_rate": 7.167637227331918e-06,
|
| 572 |
+
"loss": 0.37860721588134766,
|
| 573 |
+
"mean_token_accuracy": 0.8772583198547363,
|
| 574 |
+
"num_tokens": 8339045.0,
|
| 575 |
+
"step": 2550
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 6.0,
|
| 579 |
+
"eval_entropy": 0.5655807773401211,
|
| 580 |
+
"eval_loss": 0.7187017202377319,
|
| 581 |
+
"eval_mean_token_accuracy": 0.8067006375882533,
|
| 582 |
+
"eval_num_tokens": 8398020.0,
|
| 583 |
+
"eval_runtime": 45.9295,
|
| 584 |
+
"eval_samples_per_second": 26.802,
|
| 585 |
+
"eval_steps_per_second": 3.353,
|
| 586 |
+
"step": 2568
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.3961917132139206,
|
| 590 |
+
"epoch": 6.074766355140187,
|
| 591 |
+
"grad_norm": 1.1673611402511597,
|
| 592 |
+
"learning_rate": 6.82595030120946e-06,
|
| 593 |
+
"loss": 0.35439579010009764,
|
| 594 |
+
"mean_token_accuracy": 0.8850088411569595,
|
| 595 |
+
"num_tokens": 8502228.0,
|
| 596 |
+
"step": 2600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.368110328912735,
|
| 600 |
+
"epoch": 6.191588785046729,
|
| 601 |
+
"grad_norm": 1.3757716417312622,
|
| 602 |
+
"learning_rate": 6.487073957747255e-06,
|
| 603 |
+
"loss": 0.32657440185546877,
|
| 604 |
+
"mean_token_accuracy": 0.8935984402894974,
|
| 605 |
+
"num_tokens": 8670819.0,
|
| 606 |
+
"step": 2650
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 0.38117473274469377,
|
| 610 |
+
"epoch": 6.308411214953271,
|
| 611 |
+
"grad_norm": 1.5222810506820679,
|
| 612 |
+
"learning_rate": 6.151571637711756e-06,
|
| 613 |
+
"loss": 0.33884075164794925,
|
| 614 |
+
"mean_token_accuracy": 0.8893738853931427,
|
| 615 |
+
"num_tokens": 8833691.0,
|
| 616 |
+
"step": 2700
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 0.368239968419075,
|
| 620 |
+
"epoch": 6.425233644859813,
|
| 621 |
+
"grad_norm": 1.35374116897583,
|
| 622 |
+
"learning_rate": 5.820001171969559e-06,
|
| 623 |
+
"loss": 0.32751472473144533,
|
| 624 |
+
"mean_token_accuracy": 0.8923951196670532,
|
| 625 |
+
"num_tokens": 8991136.0,
|
| 626 |
+
"step": 2750
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 0.3820819303393364,
|
| 630 |
+
"epoch": 6.542056074766355,
|
| 631 |
+
"grad_norm": 1.4458277225494385,
|
| 632 |
+
"learning_rate": 5.492913853996745e-06,
|
| 633 |
+
"loss": 0.33998115539550783,
|
| 634 |
+
"mean_token_accuracy": 0.8889218932390213,
|
| 635 |
+
"num_tokens": 9156211.0,
|
| 636 |
+
"step": 2800
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 0.37935444712638855,
|
| 640 |
+
"epoch": 6.658878504672897,
|
| 641 |
+
"grad_norm": 1.407097339630127,
|
| 642 |
+
"learning_rate": 5.170853523257732e-06,
|
| 643 |
+
"loss": 0.33896163940429686,
|
| 644 |
+
"mean_token_accuracy": 0.8889170825481415,
|
| 645 |
+
"num_tokens": 9320538.0,
|
| 646 |
+
"step": 2850
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 0.3754119920730591,
|
| 650 |
+
"epoch": 6.775700934579439,
|
| 651 |
+
"grad_norm": 1.343308448791504,
|
| 652 |
+
"learning_rate": 4.854355660977731e-06,
|
| 653 |
+
"loss": 0.33744224548339846,
|
| 654 |
+
"mean_token_accuracy": 0.8890663629770279,
|
| 655 |
+
"num_tokens": 9480686.0,
|
| 656 |
+
"step": 2900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 0.3785912898182869,
|
| 660 |
+
"epoch": 6.892523364485982,
|
| 661 |
+
"grad_norm": 1.3478388786315918,
|
| 662 |
+
"learning_rate": 4.543946499812223e-06,
|
| 663 |
+
"loss": 0.3381637954711914,
|
| 664 |
+
"mean_token_accuracy": 0.890493910908699,
|
| 665 |
+
"num_tokens": 9644088.0,
|
| 666 |
+
"step": 2950
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 7.0,
|
| 670 |
+
"eval_entropy": 0.5324798737253461,
|
| 671 |
+
"eval_loss": 0.7690625786781311,
|
| 672 |
+
"eval_mean_token_accuracy": 0.8012763478539207,
|
| 673 |
+
"eval_num_tokens": 9797690.0,
|
| 674 |
+
"eval_runtime": 45.8503,
|
| 675 |
+
"eval_samples_per_second": 26.848,
|
| 676 |
+
"eval_steps_per_second": 3.359,
|
| 677 |
+
"step": 2996
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"entropy": 0.3794779407978058,
|
| 681 |
+
"epoch": 7.009345794392523,
|
| 682 |
+
"grad_norm": 1.4755299091339111,
|
| 683 |
+
"learning_rate": 4.2401421488938005e-06,
|
| 684 |
+
"loss": 0.33749778747558595,
|
| 685 |
+
"mean_token_accuracy": 0.8893112099170685,
|
| 686 |
+
"num_tokens": 9809264.0,
|
| 687 |
+
"step": 3000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"entropy": 0.34282191276550295,
|
| 691 |
+
"epoch": 7.126168224299065,
|
| 692 |
+
"grad_norm": 2.2217698097229004,
|
| 693 |
+
"learning_rate": 3.943447735711094e-06,
|
| 694 |
+
"loss": 0.29293390274047854,
|
| 695 |
+
"mean_token_accuracy": 0.9042663037776947,
|
| 696 |
+
"num_tokens": 9972116.0,
|
| 697 |
+
"step": 3050
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"entropy": 0.34247083246707916,
|
| 701 |
+
"epoch": 7.242990654205608,
|
| 702 |
+
"grad_norm": 1.8383665084838867,
|
| 703 |
+
"learning_rate": 3.6543565662466186e-06,
|
| 704 |
+
"loss": 0.2937329292297363,
|
| 705 |
+
"mean_token_accuracy": 0.9028173768520356,
|
| 706 |
+
"num_tokens": 10137487.0,
|
| 707 |
+
"step": 3100
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"entropy": 0.335525888800621,
|
| 711 |
+
"epoch": 7.359813084112149,
|
| 712 |
+
"grad_norm": 1.473850131034851,
|
| 713 |
+
"learning_rate": 3.3733493047699217e-06,
|
| 714 |
+
"loss": 0.28937688827514646,
|
| 715 |
+
"mean_token_accuracy": 0.9054816484451294,
|
| 716 |
+
"num_tokens": 10302931.0,
|
| 717 |
+
"step": 3150
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"entropy": 0.3531618478894234,
|
| 721 |
+
"epoch": 7.4766355140186915,
|
| 722 |
+
"grad_norm": 1.4571647644042969,
|
| 723 |
+
"learning_rate": 3.1008931746497474e-06,
|
| 724 |
+
"loss": 0.3051707649230957,
|
| 725 |
+
"mean_token_accuracy": 0.9000385081768036,
|
| 726 |
+
"num_tokens": 10458987.0,
|
| 727 |
+
"step": 3200
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"entropy": 0.34587423503398895,
|
| 731 |
+
"epoch": 7.593457943925234,
|
| 732 |
+
"grad_norm": 1.4684133529663086,
|
| 733 |
+
"learning_rate": 2.837441181514078e-06,
|
| 734 |
+
"loss": 0.30000652313232423,
|
| 735 |
+
"mean_token_accuracy": 0.9019779992103577,
|
| 736 |
+
"num_tokens": 10626220.0,
|
| 737 |
+
"step": 3250
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"entropy": 0.34274055570364,
|
| 741 |
+
"epoch": 7.710280373831775,
|
| 742 |
+
"grad_norm": 1.7025630474090576,
|
| 743 |
+
"learning_rate": 2.583431360049599e-06,
|
| 744 |
+
"loss": 0.2970438957214355,
|
| 745 |
+
"mean_token_accuracy": 0.9021710187196732,
|
| 746 |
+
"num_tokens": 10791927.0,
|
| 747 |
+
"step": 3300
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"entropy": 0.3418415796756744,
|
| 751 |
+
"epoch": 7.827102803738318,
|
| 752 |
+
"grad_norm": 1.4021923542022705,
|
| 753 |
+
"learning_rate": 2.3392860456929694e-06,
|
| 754 |
+
"loss": 0.29404821395874026,
|
| 755 |
+
"mean_token_accuracy": 0.9038505190610886,
|
| 756 |
+
"num_tokens": 10959396.0,
|
| 757 |
+
"step": 3350
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"entropy": 0.3426601967215538,
|
| 761 |
+
"epoch": 7.94392523364486,
|
| 762 |
+
"grad_norm": 1.4425413608551025,
|
| 763 |
+
"learning_rate": 2.105411172424829e-06,
|
| 764 |
+
"loss": 0.295624828338623,
|
| 765 |
+
"mean_token_accuracy": 0.9028824782371521,
|
| 766 |
+
"num_tokens": 11119550.0,
|
| 767 |
+
"step": 3400
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 8.0,
|
| 771 |
+
"eval_entropy": 0.5096885060722177,
|
| 772 |
+
"eval_loss": 0.8266266584396362,
|
| 773 |
+
"eval_mean_token_accuracy": 0.7996714382202594,
|
| 774 |
+
"eval_num_tokens": 11197360.0,
|
| 775 |
+
"eval_runtime": 45.8391,
|
| 776 |
+
"eval_samples_per_second": 26.855,
|
| 777 |
+
"eval_steps_per_second": 3.36,
|
| 778 |
+
"step": 3424
|
| 779 |
+
}
|
| 780 |
+
],
|
| 781 |
+
"logging_steps": 50,
|
| 782 |
+
"max_steps": 4280,
|
| 783 |
+
"num_input_tokens_seen": 0,
|
| 784 |
+
"num_train_epochs": 10,
|
| 785 |
+
"save_steps": 500,
|
| 786 |
+
"stateful_callbacks": {
|
| 787 |
+
"TrainerControl": {
|
| 788 |
+
"args": {
|
| 789 |
+
"should_epoch_stop": false,
|
| 790 |
+
"should_evaluate": false,
|
| 791 |
+
"should_log": false,
|
| 792 |
+
"should_save": true,
|
| 793 |
+
"should_training_stop": false
|
| 794 |
+
},
|
| 795 |
+
"attributes": {}
|
| 796 |
+
}
|
| 797 |
+
},
|
| 798 |
+
"total_flos": 2.107065211340759e+18,
|
| 799 |
+
"train_batch_size": 8,
|
| 800 |
+
"trial_name": null,
|
| 801 |
+
"trial_params": null
|
| 802 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-14B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-14B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-14B-Base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.010622890133962027,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 128,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"q_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-3852/trainer_state.json
ADDED
|
@@ -0,0 +1,903 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 9.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3852,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7805559730529785,
|
| 14 |
+
"epoch": 0.11682242990654206,
|
| 15 |
+
"grad_norm": 0.5128960013389587,
|
| 16 |
+
"learning_rate": 1.950005322230992e-06,
|
| 17 |
+
"loss": 1.770846405029297,
|
| 18 |
+
"mean_token_accuracy": 0.6305050283670426,
|
| 19 |
+
"num_tokens": 162248.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5725344836711883,
|
| 24 |
+
"epoch": 0.2336448598130841,
|
| 25 |
+
"grad_norm": 0.7059135437011719,
|
| 26 |
+
"learning_rate": 3.93980667144629e-06,
|
| 27 |
+
"loss": 1.5153414916992187,
|
| 28 |
+
"mean_token_accuracy": 0.6729821544885636,
|
| 29 |
+
"num_tokens": 327614.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.0769569373130798,
|
| 34 |
+
"epoch": 0.35046728971962615,
|
| 35 |
+
"grad_norm": 0.6092284321784973,
|
| 36 |
+
"learning_rate": 5.9296080206615885e-06,
|
| 37 |
+
"loss": 1.0251461791992187,
|
| 38 |
+
"mean_token_accuracy": 0.737835128903389,
|
| 39 |
+
"num_tokens": 494582.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.8583791655302048,
|
| 44 |
+
"epoch": 0.4672897196261682,
|
| 45 |
+
"grad_norm": 0.5586332082748413,
|
| 46 |
+
"learning_rate": 7.919409369876886e-06,
|
| 47 |
+
"loss": 0.81265869140625,
|
| 48 |
+
"mean_token_accuracy": 0.7762657129764556,
|
| 49 |
+
"num_tokens": 653981.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7744105678796768,
|
| 54 |
+
"epoch": 0.5841121495327103,
|
| 55 |
+
"grad_norm": 0.4821721613407135,
|
| 56 |
+
"learning_rate": 9.909210719092184e-06,
|
| 57 |
+
"loss": 0.7364049530029297,
|
| 58 |
+
"mean_token_accuracy": 0.7918167436122894,
|
| 59 |
+
"num_tokens": 814840.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.715560827255249,
|
| 64 |
+
"epoch": 0.7009345794392523,
|
| 65 |
+
"grad_norm": 0.6843860745429993,
|
| 66 |
+
"learning_rate": 1.1899012068307483e-05,
|
| 67 |
+
"loss": 0.6826614379882813,
|
| 68 |
+
"mean_token_accuracy": 0.8043146914243698,
|
| 69 |
+
"num_tokens": 979542.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6893886953592301,
|
| 74 |
+
"epoch": 0.8177570093457944,
|
| 75 |
+
"grad_norm": 0.6543110013008118,
|
| 76 |
+
"learning_rate": 1.3888813417522781e-05,
|
| 77 |
+
"loss": 0.6608805847167969,
|
| 78 |
+
"mean_token_accuracy": 0.8083165866136551,
|
| 79 |
+
"num_tokens": 1147400.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.652973799109459,
|
| 84 |
+
"epoch": 0.9345794392523364,
|
| 85 |
+
"grad_norm": 0.7437635660171509,
|
| 86 |
+
"learning_rate": 1.587861476673808e-05,
|
| 87 |
+
"loss": 0.6218611907958984,
|
| 88 |
+
"mean_token_accuracy": 0.8167323243618011,
|
| 89 |
+
"num_tokens": 1310490.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.0,
|
| 94 |
+
"eval_entropy": 0.8066210185552573,
|
| 95 |
+
"eval_loss": 0.7281543016433716,
|
| 96 |
+
"eval_mean_token_accuracy": 0.7858095281309896,
|
| 97 |
+
"eval_num_tokens": 1399670.0,
|
| 98 |
+
"eval_runtime": 46.0044,
|
| 99 |
+
"eval_samples_per_second": 26.758,
|
| 100 |
+
"eval_steps_per_second": 3.348,
|
| 101 |
+
"step": 428
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.6467276298999787,
|
| 105 |
+
"epoch": 1.0514018691588785,
|
| 106 |
+
"grad_norm": 0.626556396484375,
|
| 107 |
+
"learning_rate": 1.7031450502641085e-05,
|
| 108 |
+
"loss": 0.6161280441284179,
|
| 109 |
+
"mean_token_accuracy": 0.817004052400589,
|
| 110 |
+
"num_tokens": 1471726.0,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.6262363213300705,
|
| 115 |
+
"epoch": 1.1682242990654206,
|
| 116 |
+
"grad_norm": 0.70875084400177,
|
| 117 |
+
"learning_rate": 1.7018425538355792e-05,
|
| 118 |
+
"loss": 0.5963106536865235,
|
| 119 |
+
"mean_token_accuracy": 0.8221335035562515,
|
| 120 |
+
"num_tokens": 1638060.0,
|
| 121 |
+
"step": 500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"entropy": 0.6171189111471176,
|
| 125 |
+
"epoch": 1.2850467289719627,
|
| 126 |
+
"grad_norm": 0.6629440188407898,
|
| 127 |
+
"learning_rate": 1.6991264396738895e-05,
|
| 128 |
+
"loss": 0.5875393676757813,
|
| 129 |
+
"mean_token_accuracy": 0.8245152229070664,
|
| 130 |
+
"num_tokens": 1802005.0,
|
| 131 |
+
"step": 550
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"entropy": 0.6083133199810982,
|
| 135 |
+
"epoch": 1.4018691588785046,
|
| 136 |
+
"grad_norm": 0.5385038256645203,
|
| 137 |
+
"learning_rate": 1.6950012237904817e-05,
|
| 138 |
+
"loss": 0.5768455505371094,
|
| 139 |
+
"mean_token_accuracy": 0.8271224808692932,
|
| 140 |
+
"num_tokens": 1969267.0,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"entropy": 0.6011673760414123,
|
| 145 |
+
"epoch": 1.5186915887850467,
|
| 146 |
+
"grad_norm": 0.7062859535217285,
|
| 147 |
+
"learning_rate": 1.6894737650731013e-05,
|
| 148 |
+
"loss": 0.5666856384277343,
|
| 149 |
+
"mean_token_accuracy": 0.829860600233078,
|
| 150 |
+
"num_tokens": 2134793.0,
|
| 151 |
+
"step": 650
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"entropy": 0.5905318284034728,
|
| 155 |
+
"epoch": 1.6355140186915889,
|
| 156 |
+
"grad_norm": 0.646713137626648,
|
| 157 |
+
"learning_rate": 1.682553253881702e-05,
|
| 158 |
+
"loss": 0.560577392578125,
|
| 159 |
+
"mean_token_accuracy": 0.8313507026433945,
|
| 160 |
+
"num_tokens": 2300672.0,
|
| 161 |
+
"step": 700
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"entropy": 0.5964298728108406,
|
| 165 |
+
"epoch": 1.7523364485981308,
|
| 166 |
+
"grad_norm": 0.6510505080223083,
|
| 167 |
+
"learning_rate": 1.674251196767876e-05,
|
| 168 |
+
"loss": 0.5606492614746094,
|
| 169 |
+
"mean_token_accuracy": 0.8313686531782151,
|
| 170 |
+
"num_tokens": 2459315.0,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"entropy": 0.5872641482949257,
|
| 175 |
+
"epoch": 1.8691588785046729,
|
| 176 |
+
"grad_norm": 0.6211879849433899,
|
| 177 |
+
"learning_rate": 1.6645813973432182e-05,
|
| 178 |
+
"loss": 0.556594352722168,
|
| 179 |
+
"mean_token_accuracy": 0.8333250796794891,
|
| 180 |
+
"num_tokens": 2616878.0,
|
| 181 |
+
"step": 800
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"entropy": 0.5889243066310883,
|
| 185 |
+
"epoch": 1.985981308411215,
|
| 186 |
+
"grad_norm": 0.6804038882255554,
|
| 187 |
+
"learning_rate": 1.6535599333284194e-05,
|
| 188 |
+
"loss": 0.5578879928588867,
|
| 189 |
+
"mean_token_accuracy": 0.831966199874878,
|
| 190 |
+
"num_tokens": 2778909.0,
|
| 191 |
+
"step": 850
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
+
"eval_entropy": 0.7079034389613511,
|
| 196 |
+
"eval_loss": 0.6832069158554077,
|
| 197 |
+
"eval_mean_token_accuracy": 0.8022074165282311,
|
| 198 |
+
"eval_num_tokens": 2799340.0,
|
| 199 |
+
"eval_runtime": 46.0398,
|
| 200 |
+
"eval_samples_per_second": 26.738,
|
| 201 |
+
"eval_steps_per_second": 3.345,
|
| 202 |
+
"step": 856
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"entropy": 0.5462229257822037,
|
| 206 |
+
"epoch": 2.102803738317757,
|
| 207 |
+
"grad_norm": 0.5834382772445679,
|
| 208 |
+
"learning_rate": 1.6412051298212675e-05,
|
| 209 |
+
"loss": 0.5115155029296875,
|
| 210 |
+
"mean_token_accuracy": 0.8419190347194672,
|
| 211 |
+
"num_tokens": 2951115.0,
|
| 212 |
+
"step": 900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"entropy": 0.5501805812120437,
|
| 216 |
+
"epoch": 2.2196261682242993,
|
| 217 |
+
"grad_norm": 0.774409830570221,
|
| 218 |
+
"learning_rate": 1.627537528827988e-05,
|
| 219 |
+
"loss": 0.5193024826049805,
|
| 220 |
+
"mean_token_accuracy": 0.8415862208604813,
|
| 221 |
+
"num_tokens": 3115016.0,
|
| 222 |
+
"step": 950
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"entropy": 0.5417112326622009,
|
| 226 |
+
"epoch": 2.336448598130841,
|
| 227 |
+
"grad_norm": 0.8148911595344543,
|
| 228 |
+
"learning_rate": 1.612579855108594e-05,
|
| 229 |
+
"loss": 0.5099837875366211,
|
| 230 |
+
"mean_token_accuracy": 0.8432273292541503,
|
| 231 |
+
"num_tokens": 3274313.0,
|
| 232 |
+
"step": 1000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"entropy": 0.5426027116179466,
|
| 236 |
+
"epoch": 2.453271028037383,
|
| 237 |
+
"grad_norm": 0.738017737865448,
|
| 238 |
+
"learning_rate": 1.596356978393025e-05,
|
| 239 |
+
"loss": 0.5110509490966797,
|
| 240 |
+
"mean_token_accuracy": 0.8447510355710983,
|
| 241 |
+
"num_tokens": 3440379.0,
|
| 242 |
+
"step": 1050
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"entropy": 0.536553855240345,
|
| 246 |
+
"epoch": 2.5700934579439254,
|
| 247 |
+
"grad_norm": 0.6512451767921448,
|
| 248 |
+
"learning_rate": 1.5788958720309008e-05,
|
| 249 |
+
"loss": 0.5046747207641602,
|
| 250 |
+
"mean_token_accuracy": 0.8439748030900955,
|
| 251 |
+
"num_tokens": 3606755.0,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"entropy": 0.5361887359619141,
|
| 256 |
+
"epoch": 2.6869158878504673,
|
| 257 |
+
"grad_norm": 0.7650485038757324,
|
| 258 |
+
"learning_rate": 1.5602255681436483e-05,
|
| 259 |
+
"loss": 0.5043494415283203,
|
| 260 |
+
"mean_token_accuracy": 0.8450696021318436,
|
| 261 |
+
"num_tokens": 3766555.0,
|
| 262 |
+
"step": 1150
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"entropy": 0.5419432005286217,
|
| 266 |
+
"epoch": 2.803738317757009,
|
| 267 |
+
"grad_norm": 0.6945335268974304,
|
| 268 |
+
"learning_rate": 1.5403771093535538e-05,
|
| 269 |
+
"loss": 0.5108187103271484,
|
| 270 |
+
"mean_token_accuracy": 0.8431807065010071,
|
| 271 |
+
"num_tokens": 3927164.0,
|
| 272 |
+
"step": 1200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"entropy": 0.5400136861205102,
|
| 276 |
+
"epoch": 2.9205607476635516,
|
| 277 |
+
"grad_norm": 0.774668276309967,
|
| 278 |
+
"learning_rate": 1.5193834971700146e-05,
|
| 279 |
+
"loss": 0.5082107543945312,
|
| 280 |
+
"mean_token_accuracy": 0.8444043332338333,
|
| 281 |
+
"num_tokens": 4090727.0,
|
| 282 |
+
"step": 1250
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.0,
|
| 286 |
+
"eval_entropy": 0.6524020644364419,
|
| 287 |
+
"eval_loss": 0.6701120138168335,
|
| 288 |
+
"eval_mean_token_accuracy": 0.8018650695101007,
|
| 289 |
+
"eval_num_tokens": 4199010.0,
|
| 290 |
+
"eval_runtime": 46.004,
|
| 291 |
+
"eval_samples_per_second": 26.759,
|
| 292 |
+
"eval_steps_per_second": 3.348,
|
| 293 |
+
"step": 1284
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"entropy": 0.5256310805678368,
|
| 297 |
+
"epoch": 3.0373831775700935,
|
| 298 |
+
"grad_norm": 0.8875723481178284,
|
| 299 |
+
"learning_rate": 1.4972796371187997e-05,
|
| 300 |
+
"loss": 0.49435077667236327,
|
| 301 |
+
"mean_token_accuracy": 0.8473169440031052,
|
| 302 |
+
"num_tokens": 4252535.0,
|
| 303 |
+
"step": 1300
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"entropy": 0.4986111795902252,
|
| 307 |
+
"epoch": 3.1542056074766354,
|
| 308 |
+
"grad_norm": 0.8605287671089172,
|
| 309 |
+
"learning_rate": 1.4741022807055508e-05,
|
| 310 |
+
"loss": 0.4662786483764648,
|
| 311 |
+
"mean_token_accuracy": 0.8552708566188812,
|
| 312 |
+
"num_tokens": 4414122.0,
|
| 313 |
+
"step": 1350
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"entropy": 0.5061789083480835,
|
| 317 |
+
"epoch": 3.2710280373831777,
|
| 318 |
+
"grad_norm": 0.8101795315742493,
|
| 319 |
+
"learning_rate": 1.4498899643100226e-05,
|
| 320 |
+
"loss": 0.47242179870605466,
|
| 321 |
+
"mean_token_accuracy": 0.8520459419488907,
|
| 322 |
+
"num_tokens": 4571859.0,
|
| 323 |
+
"step": 1400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"entropy": 0.4939887225627899,
|
| 327 |
+
"epoch": 3.3878504672897196,
|
| 328 |
+
"grad_norm": 0.8013083338737488,
|
| 329 |
+
"learning_rate": 1.4246829451126602e-05,
|
| 330 |
+
"loss": 0.4614598846435547,
|
| 331 |
+
"mean_token_accuracy": 0.8552495676279068,
|
| 332 |
+
"num_tokens": 4735006.0,
|
| 333 |
+
"step": 1450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"entropy": 0.4918920609354973,
|
| 337 |
+
"epoch": 3.5046728971962615,
|
| 338 |
+
"grad_norm": 0.7743699550628662,
|
| 339 |
+
"learning_rate": 1.3985231341600455e-05,
|
| 340 |
+
"loss": 0.46159915924072265,
|
| 341 |
+
"mean_token_accuracy": 0.8550176537036895,
|
| 342 |
+
"num_tokens": 4898228.0,
|
| 343 |
+
"step": 1500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"entropy": 0.49779762893915175,
|
| 347 |
+
"epoch": 3.621495327102804,
|
| 348 |
+
"grad_norm": 0.8169922828674316,
|
| 349 |
+
"learning_rate": 1.3714540266805045e-05,
|
| 350 |
+
"loss": 0.46558887481689454,
|
| 351 |
+
"mean_token_accuracy": 0.8540038305521012,
|
| 352 |
+
"num_tokens": 5063413.0,
|
| 353 |
+
"step": 1550
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"entropy": 0.5015265879034996,
|
| 357 |
+
"epoch": 3.7383177570093458,
|
| 358 |
+
"grad_norm": 0.851017951965332,
|
| 359 |
+
"learning_rate": 1.343520629765737e-05,
|
| 360 |
+
"loss": 0.46733531951904295,
|
| 361 |
+
"mean_token_accuracy": 0.8522392755746842,
|
| 362 |
+
"num_tokens": 5227672.0,
|
| 363 |
+
"step": 1600
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"entropy": 0.501338247358799,
|
| 367 |
+
"epoch": 3.8551401869158877,
|
| 368 |
+
"grad_norm": 0.8121753334999084,
|
| 369 |
+
"learning_rate": 1.3147693875387126e-05,
|
| 370 |
+
"loss": 0.4710521697998047,
|
| 371 |
+
"mean_token_accuracy": 0.8534136080741882,
|
| 372 |
+
"num_tokens": 5389834.0,
|
| 373 |
+
"step": 1650
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"entropy": 0.49478380143642425,
|
| 377 |
+
"epoch": 3.97196261682243,
|
| 378 |
+
"grad_norm": 0.6918302178382874,
|
| 379 |
+
"learning_rate": 1.2852481039322492e-05,
|
| 380 |
+
"loss": 0.4646331405639648,
|
| 381 |
+
"mean_token_accuracy": 0.8551374357938767,
|
| 382 |
+
"num_tokens": 5559167.0,
|
| 383 |
+
"step": 1700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.0,
|
| 387 |
+
"eval_entropy": 0.6295453201640736,
|
| 388 |
+
"eval_loss": 0.666642427444458,
|
| 389 |
+
"eval_mean_token_accuracy": 0.8111948270302314,
|
| 390 |
+
"eval_num_tokens": 5598680.0,
|
| 391 |
+
"eval_runtime": 45.8725,
|
| 392 |
+
"eval_samples_per_second": 26.835,
|
| 393 |
+
"eval_steps_per_second": 3.357,
|
| 394 |
+
"step": 1712
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"entropy": 0.46167980462312697,
|
| 398 |
+
"epoch": 4.088785046728972,
|
| 399 |
+
"grad_norm": 0.8769540190696716,
|
| 400 |
+
"learning_rate": 1.2550058632066751e-05,
|
| 401 |
+
"loss": 0.4263522338867187,
|
| 402 |
+
"mean_token_accuracy": 0.8653014451265335,
|
| 403 |
+
"num_tokens": 5721701.0,
|
| 404 |
+
"step": 1750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"entropy": 0.4534104973077774,
|
| 408 |
+
"epoch": 4.205607476635514,
|
| 409 |
+
"grad_norm": 1.1420735120773315,
|
| 410 |
+
"learning_rate": 1.2240929483387228e-05,
|
| 411 |
+
"loss": 0.41863834381103515,
|
| 412 |
+
"mean_token_accuracy": 0.8667230373620987,
|
| 413 |
+
"num_tokens": 5884163.0,
|
| 414 |
+
"step": 1800
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"entropy": 0.4606948295235634,
|
| 418 |
+
"epoch": 4.322429906542056,
|
| 419 |
+
"grad_norm": 1.0596942901611328,
|
| 420 |
+
"learning_rate": 1.1925607574173476e-05,
|
| 421 |
+
"loss": 0.42718273162841797,
|
| 422 |
+
"mean_token_accuracy": 0.8641588741540909,
|
| 423 |
+
"num_tokens": 6053869.0,
|
| 424 |
+
"step": 1850
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"entropy": 0.45681062549352647,
|
| 428 |
+
"epoch": 4.4392523364485985,
|
| 429 |
+
"grad_norm": 0.9009803533554077,
|
| 430 |
+
"learning_rate": 1.1604617181854806e-05,
|
| 431 |
+
"loss": 0.42521621704101564,
|
| 432 |
+
"mean_token_accuracy": 0.8644315087795258,
|
| 433 |
+
"num_tokens": 6217351.0,
|
| 434 |
+
"step": 1900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"entropy": 0.45814105302095415,
|
| 438 |
+
"epoch": 4.55607476635514,
|
| 439 |
+
"grad_norm": 0.9394752383232117,
|
| 440 |
+
"learning_rate": 1.127849200869801e-05,
|
| 441 |
+
"loss": 0.42409008026123046,
|
| 442 |
+
"mean_token_accuracy": 0.864885100722313,
|
| 443 |
+
"num_tokens": 6379796.0,
|
| 444 |
+
"step": 1950
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"entropy": 0.4561432495713234,
|
| 448 |
+
"epoch": 4.672897196261682,
|
| 449 |
+
"grad_norm": 0.8258721828460693,
|
| 450 |
+
"learning_rate": 1.094777429443468e-05,
|
| 451 |
+
"loss": 0.42701839447021483,
|
| 452 |
+
"mean_token_accuracy": 0.8638879442214966,
|
| 453 |
+
"num_tokens": 6550276.0,
|
| 454 |
+
"step": 2000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"entropy": 0.4610430991649628,
|
| 458 |
+
"epoch": 4.789719626168225,
|
| 459 |
+
"grad_norm": 1.0002802610397339,
|
| 460 |
+
"learning_rate": 1.0613013914693477e-05,
|
| 461 |
+
"loss": 0.4286579895019531,
|
| 462 |
+
"mean_token_accuracy": 0.8643757510185242,
|
| 463 |
+
"num_tokens": 6709429.0,
|
| 464 |
+
"step": 2050
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"entropy": 0.4558544892072678,
|
| 468 |
+
"epoch": 4.906542056074766,
|
| 469 |
+
"grad_norm": 0.9755097031593323,
|
| 470 |
+
"learning_rate": 1.0274767466736426e-05,
|
| 471 |
+
"loss": 0.4233176803588867,
|
| 472 |
+
"mean_token_accuracy": 0.8655301338434219,
|
| 473 |
+
"num_tokens": 6870956.0,
|
| 474 |
+
"step": 2100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.0,
|
| 478 |
+
"eval_entropy": 0.6000483314712326,
|
| 479 |
+
"eval_loss": 0.6985165476799011,
|
| 480 |
+
"eval_mean_token_accuracy": 0.8045627912143608,
|
| 481 |
+
"eval_num_tokens": 6998350.0,
|
| 482 |
+
"eval_runtime": 45.9034,
|
| 483 |
+
"eval_samples_per_second": 26.817,
|
| 484 |
+
"eval_steps_per_second": 3.355,
|
| 485 |
+
"step": 2140
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"entropy": 0.44992744773626325,
|
| 489 |
+
"epoch": 5.0233644859813085,
|
| 490 |
+
"grad_norm": 1.1082366704940796,
|
| 491 |
+
"learning_rate": 9.933597344019314e-06,
|
| 492 |
+
"loss": 0.41550483703613283,
|
| 493 |
+
"mean_token_accuracy": 0.8669036704301835,
|
| 494 |
+
"num_tokens": 7034085.0,
|
| 495 |
+
"step": 2150
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"entropy": 0.4088956421613693,
|
| 499 |
+
"epoch": 5.140186915887851,
|
| 500 |
+
"grad_norm": 1.0101401805877686,
|
| 501 |
+
"learning_rate": 9.59007080111491e-06,
|
| 502 |
+
"loss": 0.3716637420654297,
|
| 503 |
+
"mean_token_accuracy": 0.8802521765232086,
|
| 504 |
+
"num_tokens": 7198745.0,
|
| 505 |
+
"step": 2200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"entropy": 0.4127876952290535,
|
| 509 |
+
"epoch": 5.257009345794392,
|
| 510 |
+
"grad_norm": 1.1201362609863281,
|
| 511 |
+
"learning_rate": 9.244759010553727e-06,
|
| 512 |
+
"loss": 0.37826343536376955,
|
| 513 |
+
"mean_token_accuracy": 0.8786936563253402,
|
| 514 |
+
"num_tokens": 7366588.0,
|
| 515 |
+
"step": 2250
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"entropy": 0.4232992666959763,
|
| 519 |
+
"epoch": 5.373831775700935,
|
| 520 |
+
"grad_norm": 1.1778150796890259,
|
| 521 |
+
"learning_rate": 8.898236113150524e-06,
|
| 522 |
+
"loss": 0.38583309173583985,
|
| 523 |
+
"mean_token_accuracy": 0.8747973537445068,
|
| 524 |
+
"num_tokens": 7531696.0,
|
| 525 |
+
"step": 2300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"entropy": 0.4159915736317635,
|
| 529 |
+
"epoch": 5.490654205607477,
|
| 530 |
+
"grad_norm": 1.1592568159103394,
|
| 531 |
+
"learning_rate": 8.551078263395478e-06,
|
| 532 |
+
"loss": 0.3784225082397461,
|
| 533 |
+
"mean_token_accuracy": 0.8779372000694274,
|
| 534 |
+
"num_tokens": 7688960.0,
|
| 535 |
+
"step": 2350
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"entropy": 0.41662866294384004,
|
| 539 |
+
"epoch": 5.607476635514018,
|
| 540 |
+
"grad_norm": 1.254981517791748,
|
| 541 |
+
"learning_rate": 8.203862671497323e-06,
|
| 542 |
+
"loss": 0.37995223999023436,
|
| 543 |
+
"mean_token_accuracy": 0.8772805953025817,
|
| 544 |
+
"num_tokens": 7851053.0,
|
| 545 |
+
"step": 2400
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"entropy": 0.417872933447361,
|
| 549 |
+
"epoch": 5.724299065420561,
|
| 550 |
+
"grad_norm": 1.322206974029541,
|
| 551 |
+
"learning_rate": 7.857166643671128e-06,
|
| 552 |
+
"loss": 0.38079578399658204,
|
| 553 |
+
"mean_token_accuracy": 0.8774149787425994,
|
| 554 |
+
"num_tokens": 8001524.0,
|
| 555 |
+
"step": 2450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"entropy": 0.41878397345542906,
|
| 559 |
+
"epoch": 5.841121495327103,
|
| 560 |
+
"grad_norm": 1.2948966026306152,
|
| 561 |
+
"learning_rate": 7.511566622266466e-06,
|
| 562 |
+
"loss": 0.3861651611328125,
|
| 563 |
+
"mean_token_accuracy": 0.8755189329385757,
|
| 564 |
+
"num_tokens": 8166394.0,
|
| 565 |
+
"step": 2500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"entropy": 0.4128647845983505,
|
| 569 |
+
"epoch": 5.957943925233645,
|
| 570 |
+
"grad_norm": 1.190157175064087,
|
| 571 |
+
"learning_rate": 7.167637227331918e-06,
|
| 572 |
+
"loss": 0.37860721588134766,
|
| 573 |
+
"mean_token_accuracy": 0.8772583198547363,
|
| 574 |
+
"num_tokens": 8339045.0,
|
| 575 |
+
"step": 2550
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 6.0,
|
| 579 |
+
"eval_entropy": 0.5655807773401211,
|
| 580 |
+
"eval_loss": 0.7187017202377319,
|
| 581 |
+
"eval_mean_token_accuracy": 0.8067006375882533,
|
| 582 |
+
"eval_num_tokens": 8398020.0,
|
| 583 |
+
"eval_runtime": 45.9295,
|
| 584 |
+
"eval_samples_per_second": 26.802,
|
| 585 |
+
"eval_steps_per_second": 3.353,
|
| 586 |
+
"step": 2568
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.3961917132139206,
|
| 590 |
+
"epoch": 6.074766355140187,
|
| 591 |
+
"grad_norm": 1.1673611402511597,
|
| 592 |
+
"learning_rate": 6.82595030120946e-06,
|
| 593 |
+
"loss": 0.35439579010009764,
|
| 594 |
+
"mean_token_accuracy": 0.8850088411569595,
|
| 595 |
+
"num_tokens": 8502228.0,
|
| 596 |
+
"step": 2600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.368110328912735,
|
| 600 |
+
"epoch": 6.191588785046729,
|
| 601 |
+
"grad_norm": 1.3757716417312622,
|
| 602 |
+
"learning_rate": 6.487073957747255e-06,
|
| 603 |
+
"loss": 0.32657440185546877,
|
| 604 |
+
"mean_token_accuracy": 0.8935984402894974,
|
| 605 |
+
"num_tokens": 8670819.0,
|
| 606 |
+
"step": 2650
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 0.38117473274469377,
|
| 610 |
+
"epoch": 6.308411214953271,
|
| 611 |
+
"grad_norm": 1.5222810506820679,
|
| 612 |
+
"learning_rate": 6.151571637711756e-06,
|
| 613 |
+
"loss": 0.33884075164794925,
|
| 614 |
+
"mean_token_accuracy": 0.8893738853931427,
|
| 615 |
+
"num_tokens": 8833691.0,
|
| 616 |
+
"step": 2700
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 0.368239968419075,
|
| 620 |
+
"epoch": 6.425233644859813,
|
| 621 |
+
"grad_norm": 1.35374116897583,
|
| 622 |
+
"learning_rate": 5.820001171969559e-06,
|
| 623 |
+
"loss": 0.32751472473144533,
|
| 624 |
+
"mean_token_accuracy": 0.8923951196670532,
|
| 625 |
+
"num_tokens": 8991136.0,
|
| 626 |
+
"step": 2750
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 0.3820819303393364,
|
| 630 |
+
"epoch": 6.542056074766355,
|
| 631 |
+
"grad_norm": 1.4458277225494385,
|
| 632 |
+
"learning_rate": 5.492913853996745e-06,
|
| 633 |
+
"loss": 0.33998115539550783,
|
| 634 |
+
"mean_token_accuracy": 0.8889218932390213,
|
| 635 |
+
"num_tokens": 9156211.0,
|
| 636 |
+
"step": 2800
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 0.37935444712638855,
|
| 640 |
+
"epoch": 6.658878504672897,
|
| 641 |
+
"grad_norm": 1.407097339630127,
|
| 642 |
+
"learning_rate": 5.170853523257732e-06,
|
| 643 |
+
"loss": 0.33896163940429686,
|
| 644 |
+
"mean_token_accuracy": 0.8889170825481415,
|
| 645 |
+
"num_tokens": 9320538.0,
|
| 646 |
+
"step": 2850
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 0.3754119920730591,
|
| 650 |
+
"epoch": 6.775700934579439,
|
| 651 |
+
"grad_norm": 1.343308448791504,
|
| 652 |
+
"learning_rate": 4.854355660977731e-06,
|
| 653 |
+
"loss": 0.33744224548339846,
|
| 654 |
+
"mean_token_accuracy": 0.8890663629770279,
|
| 655 |
+
"num_tokens": 9480686.0,
|
| 656 |
+
"step": 2900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 0.3785912898182869,
|
| 660 |
+
"epoch": 6.892523364485982,
|
| 661 |
+
"grad_norm": 1.3478388786315918,
|
| 662 |
+
"learning_rate": 4.543946499812223e-06,
|
| 663 |
+
"loss": 0.3381637954711914,
|
| 664 |
+
"mean_token_accuracy": 0.890493910908699,
|
| 665 |
+
"num_tokens": 9644088.0,
|
| 666 |
+
"step": 2950
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 7.0,
|
| 670 |
+
"eval_entropy": 0.5324798737253461,
|
| 671 |
+
"eval_loss": 0.7690625786781311,
|
| 672 |
+
"eval_mean_token_accuracy": 0.8012763478539207,
|
| 673 |
+
"eval_num_tokens": 9797690.0,
|
| 674 |
+
"eval_runtime": 45.8503,
|
| 675 |
+
"eval_samples_per_second": 26.848,
|
| 676 |
+
"eval_steps_per_second": 3.359,
|
| 677 |
+
"step": 2996
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"entropy": 0.3794779407978058,
|
| 681 |
+
"epoch": 7.009345794392523,
|
| 682 |
+
"grad_norm": 1.4755299091339111,
|
| 683 |
+
"learning_rate": 4.2401421488938005e-06,
|
| 684 |
+
"loss": 0.33749778747558595,
|
| 685 |
+
"mean_token_accuracy": 0.8893112099170685,
|
| 686 |
+
"num_tokens": 9809264.0,
|
| 687 |
+
"step": 3000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"entropy": 0.34282191276550295,
|
| 691 |
+
"epoch": 7.126168224299065,
|
| 692 |
+
"grad_norm": 2.2217698097229004,
|
| 693 |
+
"learning_rate": 3.943447735711094e-06,
|
| 694 |
+
"loss": 0.29293390274047854,
|
| 695 |
+
"mean_token_accuracy": 0.9042663037776947,
|
| 696 |
+
"num_tokens": 9972116.0,
|
| 697 |
+
"step": 3050
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"entropy": 0.34247083246707916,
|
| 701 |
+
"epoch": 7.242990654205608,
|
| 702 |
+
"grad_norm": 1.8383665084838867,
|
| 703 |
+
"learning_rate": 3.6543565662466186e-06,
|
| 704 |
+
"loss": 0.2937329292297363,
|
| 705 |
+
"mean_token_accuracy": 0.9028173768520356,
|
| 706 |
+
"num_tokens": 10137487.0,
|
| 707 |
+
"step": 3100
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"entropy": 0.335525888800621,
|
| 711 |
+
"epoch": 7.359813084112149,
|
| 712 |
+
"grad_norm": 1.473850131034851,
|
| 713 |
+
"learning_rate": 3.3733493047699217e-06,
|
| 714 |
+
"loss": 0.28937688827514646,
|
| 715 |
+
"mean_token_accuracy": 0.9054816484451294,
|
| 716 |
+
"num_tokens": 10302931.0,
|
| 717 |
+
"step": 3150
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"entropy": 0.3531618478894234,
|
| 721 |
+
"epoch": 7.4766355140186915,
|
| 722 |
+
"grad_norm": 1.4571647644042969,
|
| 723 |
+
"learning_rate": 3.1008931746497474e-06,
|
| 724 |
+
"loss": 0.3051707649230957,
|
| 725 |
+
"mean_token_accuracy": 0.9000385081768036,
|
| 726 |
+
"num_tokens": 10458987.0,
|
| 727 |
+
"step": 3200
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"entropy": 0.34587423503398895,
|
| 731 |
+
"epoch": 7.593457943925234,
|
| 732 |
+
"grad_norm": 1.4684133529663086,
|
| 733 |
+
"learning_rate": 2.837441181514078e-06,
|
| 734 |
+
"loss": 0.30000652313232423,
|
| 735 |
+
"mean_token_accuracy": 0.9019779992103577,
|
| 736 |
+
"num_tokens": 10626220.0,
|
| 737 |
+
"step": 3250
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"entropy": 0.34274055570364,
|
| 741 |
+
"epoch": 7.710280373831775,
|
| 742 |
+
"grad_norm": 1.7025630474090576,
|
| 743 |
+
"learning_rate": 2.583431360049599e-06,
|
| 744 |
+
"loss": 0.2970438957214355,
|
| 745 |
+
"mean_token_accuracy": 0.9021710187196732,
|
| 746 |
+
"num_tokens": 10791927.0,
|
| 747 |
+
"step": 3300
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"entropy": 0.3418415796756744,
|
| 751 |
+
"epoch": 7.827102803738318,
|
| 752 |
+
"grad_norm": 1.4021923542022705,
|
| 753 |
+
"learning_rate": 2.3392860456929694e-06,
|
| 754 |
+
"loss": 0.29404821395874026,
|
| 755 |
+
"mean_token_accuracy": 0.9038505190610886,
|
| 756 |
+
"num_tokens": 10959396.0,
|
| 757 |
+
"step": 3350
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"entropy": 0.3426601967215538,
|
| 761 |
+
"epoch": 7.94392523364486,
|
| 762 |
+
"grad_norm": 1.4425413608551025,
|
| 763 |
+
"learning_rate": 2.105411172424829e-06,
|
| 764 |
+
"loss": 0.295624828338623,
|
| 765 |
+
"mean_token_accuracy": 0.9028824782371521,
|
| 766 |
+
"num_tokens": 11119550.0,
|
| 767 |
+
"step": 3400
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 8.0,
|
| 771 |
+
"eval_entropy": 0.5096885060722177,
|
| 772 |
+
"eval_loss": 0.8266266584396362,
|
| 773 |
+
"eval_mean_token_accuracy": 0.7996714382202594,
|
| 774 |
+
"eval_num_tokens": 11197360.0,
|
| 775 |
+
"eval_runtime": 45.8391,
|
| 776 |
+
"eval_samples_per_second": 26.855,
|
| 777 |
+
"eval_steps_per_second": 3.36,
|
| 778 |
+
"step": 3424
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"entropy": 0.33504158034920695,
|
| 782 |
+
"epoch": 8.060747663551401,
|
| 783 |
+
"grad_norm": 1.7360987663269043,
|
| 784 |
+
"learning_rate": 1.8821955978340481e-06,
|
| 785 |
+
"loss": 0.2848625564575195,
|
| 786 |
+
"mean_token_accuracy": 0.9075938129425049,
|
| 787 |
+
"num_tokens": 11282774.0,
|
| 788 |
+
"step": 3450
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"entropy": 0.32288984924554825,
|
| 792 |
+
"epoch": 8.177570093457945,
|
| 793 |
+
"grad_norm": 1.6818318367004395,
|
| 794 |
+
"learning_rate": 1.6700104565744824e-06,
|
| 795 |
+
"loss": 0.26646427154541014,
|
| 796 |
+
"mean_token_accuracy": 0.9131433618068695,
|
| 797 |
+
"num_tokens": 11443420.0,
|
| 798 |
+
"step": 3500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"entropy": 0.32121765553951265,
|
| 802 |
+
"epoch": 8.294392523364486,
|
| 803 |
+
"grad_norm": 1.7594389915466309,
|
| 804 |
+
"learning_rate": 1.4692085432891538e-06,
|
| 805 |
+
"loss": 0.2693086814880371,
|
| 806 |
+
"mean_token_accuracy": 0.9124349278211593,
|
| 807 |
+
"num_tokens": 11603266.0,
|
| 808 |
+
"step": 3550
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"entropy": 0.3194531953334808,
|
| 812 |
+
"epoch": 8.411214953271028,
|
| 813 |
+
"grad_norm": 1.5076898336410522,
|
| 814 |
+
"learning_rate": 1.2801237260278847e-06,
|
| 815 |
+
"loss": 0.2668701362609863,
|
| 816 |
+
"mean_token_accuracy": 0.9122523158788681,
|
| 817 |
+
"num_tokens": 11766536.0,
|
| 818 |
+
"step": 3600
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"entropy": 0.3196700257062912,
|
| 822 |
+
"epoch": 8.52803738317757,
|
| 823 |
+
"grad_norm": 1.899849772453308,
|
| 824 |
+
"learning_rate": 1.103070391133706e-06,
|
| 825 |
+
"loss": 0.2672290420532227,
|
| 826 |
+
"mean_token_accuracy": 0.9123695671558381,
|
| 827 |
+
"num_tokens": 11934812.0,
|
| 828 |
+
"step": 3650
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"entropy": 0.32141068547964097,
|
| 832 |
+
"epoch": 8.644859813084112,
|
| 833 |
+
"grad_norm": 1.878564476966858,
|
| 834 |
+
"learning_rate": 9.38342920520968e-07,
|
| 835 |
+
"loss": 0.2677190399169922,
|
| 836 |
+
"mean_token_accuracy": 0.9121616327762604,
|
| 837 |
+
"num_tokens": 12095307.0,
|
| 838 |
+
"step": 3700
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"entropy": 0.3209075602889061,
|
| 842 |
+
"epoch": 8.761682242990654,
|
| 843 |
+
"grad_norm": 1.7056505680084229,
|
| 844 |
+
"learning_rate": 7.862152022142707e-07,
|
| 845 |
+
"loss": 0.2690747261047363,
|
| 846 |
+
"mean_token_accuracy": 0.9123590832948685,
|
| 847 |
+
"num_tokens": 12267401.0,
|
| 848 |
+
"step": 3750
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"entropy": 0.3217465075850487,
|
| 852 |
+
"epoch": 8.878504672897197,
|
| 853 |
+
"grad_norm": 1.966456651687622,
|
| 854 |
+
"learning_rate": 6.469401749620809e-07,
|
| 855 |
+
"loss": 0.2688888168334961,
|
| 856 |
+
"mean_token_accuracy": 0.912511082291603,
|
| 857 |
+
"num_tokens": 12432027.0,
|
| 858 |
+
"step": 3800
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"entropy": 0.3217696958780289,
|
| 862 |
+
"epoch": 8.995327102803738,
|
| 863 |
+
"grad_norm": 1.8051724433898926,
|
| 864 |
+
"learning_rate": 5.20749407682135e-07,
|
| 865 |
+
"loss": 0.26914966583251954,
|
| 866 |
+
"mean_token_accuracy": 0.9128880047798157,
|
| 867 |
+
"num_tokens": 12591339.0,
|
| 868 |
+
"step": 3850
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 9.0,
|
| 872 |
+
"eval_entropy": 0.4910243496105268,
|
| 873 |
+
"eval_loss": 0.8639353513717651,
|
| 874 |
+
"eval_mean_token_accuracy": 0.7988481390011775,
|
| 875 |
+
"eval_num_tokens": 12597030.0,
|
| 876 |
+
"eval_runtime": 45.8237,
|
| 877 |
+
"eval_samples_per_second": 26.864,
|
| 878 |
+
"eval_steps_per_second": 3.361,
|
| 879 |
+
"step": 3852
|
| 880 |
+
}
|
| 881 |
+
],
|
| 882 |
+
"logging_steps": 50,
|
| 883 |
+
"max_steps": 4280,
|
| 884 |
+
"num_input_tokens_seen": 0,
|
| 885 |
+
"num_train_epochs": 10,
|
| 886 |
+
"save_steps": 500,
|
| 887 |
+
"stateful_callbacks": {
|
| 888 |
+
"TrainerControl": {
|
| 889 |
+
"args": {
|
| 890 |
+
"should_epoch_stop": false,
|
| 891 |
+
"should_evaluate": false,
|
| 892 |
+
"should_log": false,
|
| 893 |
+
"should_save": true,
|
| 894 |
+
"should_training_stop": false
|
| 895 |
+
},
|
| 896 |
+
"attributes": {}
|
| 897 |
+
}
|
| 898 |
+
},
|
| 899 |
+
"total_flos": 2.3720467978019635e+18,
|
| 900 |
+
"train_batch_size": 8,
|
| 901 |
+
"trial_name": null,
|
| 902 |
+
"trial_params": null
|
| 903 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-14B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-14B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-14B-Base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.010622890133962027,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 128,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"q_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-428/trainer_state.json
ADDED
|
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 428,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7805559730529785,
|
| 14 |
+
"epoch": 0.11682242990654206,
|
| 15 |
+
"grad_norm": 0.5128960013389587,
|
| 16 |
+
"learning_rate": 1.950005322230992e-06,
|
| 17 |
+
"loss": 1.770846405029297,
|
| 18 |
+
"mean_token_accuracy": 0.6305050283670426,
|
| 19 |
+
"num_tokens": 162248.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5725344836711883,
|
| 24 |
+
"epoch": 0.2336448598130841,
|
| 25 |
+
"grad_norm": 0.7059135437011719,
|
| 26 |
+
"learning_rate": 3.93980667144629e-06,
|
| 27 |
+
"loss": 1.5153414916992187,
|
| 28 |
+
"mean_token_accuracy": 0.6729821544885636,
|
| 29 |
+
"num_tokens": 327614.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.0769569373130798,
|
| 34 |
+
"epoch": 0.35046728971962615,
|
| 35 |
+
"grad_norm": 0.6092284321784973,
|
| 36 |
+
"learning_rate": 5.9296080206615885e-06,
|
| 37 |
+
"loss": 1.0251461791992187,
|
| 38 |
+
"mean_token_accuracy": 0.737835128903389,
|
| 39 |
+
"num_tokens": 494582.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.8583791655302048,
|
| 44 |
+
"epoch": 0.4672897196261682,
|
| 45 |
+
"grad_norm": 0.5586332082748413,
|
| 46 |
+
"learning_rate": 7.919409369876886e-06,
|
| 47 |
+
"loss": 0.81265869140625,
|
| 48 |
+
"mean_token_accuracy": 0.7762657129764556,
|
| 49 |
+
"num_tokens": 653981.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7744105678796768,
|
| 54 |
+
"epoch": 0.5841121495327103,
|
| 55 |
+
"grad_norm": 0.4821721613407135,
|
| 56 |
+
"learning_rate": 9.909210719092184e-06,
|
| 57 |
+
"loss": 0.7364049530029297,
|
| 58 |
+
"mean_token_accuracy": 0.7918167436122894,
|
| 59 |
+
"num_tokens": 814840.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.715560827255249,
|
| 64 |
+
"epoch": 0.7009345794392523,
|
| 65 |
+
"grad_norm": 0.6843860745429993,
|
| 66 |
+
"learning_rate": 1.1899012068307483e-05,
|
| 67 |
+
"loss": 0.6826614379882813,
|
| 68 |
+
"mean_token_accuracy": 0.8043146914243698,
|
| 69 |
+
"num_tokens": 979542.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6893886953592301,
|
| 74 |
+
"epoch": 0.8177570093457944,
|
| 75 |
+
"grad_norm": 0.6543110013008118,
|
| 76 |
+
"learning_rate": 1.3888813417522781e-05,
|
| 77 |
+
"loss": 0.6608805847167969,
|
| 78 |
+
"mean_token_accuracy": 0.8083165866136551,
|
| 79 |
+
"num_tokens": 1147400.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.652973799109459,
|
| 84 |
+
"epoch": 0.9345794392523364,
|
| 85 |
+
"grad_norm": 0.7437635660171509,
|
| 86 |
+
"learning_rate": 1.587861476673808e-05,
|
| 87 |
+
"loss": 0.6218611907958984,
|
| 88 |
+
"mean_token_accuracy": 0.8167323243618011,
|
| 89 |
+
"num_tokens": 1310490.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.0,
|
| 94 |
+
"eval_entropy": 0.8066210185552573,
|
| 95 |
+
"eval_loss": 0.7281543016433716,
|
| 96 |
+
"eval_mean_token_accuracy": 0.7858095281309896,
|
| 97 |
+
"eval_num_tokens": 1399670.0,
|
| 98 |
+
"eval_runtime": 46.0044,
|
| 99 |
+
"eval_samples_per_second": 26.758,
|
| 100 |
+
"eval_steps_per_second": 3.348,
|
| 101 |
+
"step": 428
|
| 102 |
+
}
|
| 103 |
+
],
|
| 104 |
+
"logging_steps": 50,
|
| 105 |
+
"max_steps": 4280,
|
| 106 |
+
"num_input_tokens_seen": 0,
|
| 107 |
+
"num_train_epochs": 10,
|
| 108 |
+
"save_steps": 500,
|
| 109 |
+
"stateful_callbacks": {
|
| 110 |
+
"TrainerControl": {
|
| 111 |
+
"args": {
|
| 112 |
+
"should_epoch_stop": false,
|
| 113 |
+
"should_evaluate": false,
|
| 114 |
+
"should_log": false,
|
| 115 |
+
"should_save": true,
|
| 116 |
+
"should_training_stop": false
|
| 117 |
+
},
|
| 118 |
+
"attributes": {}
|
| 119 |
+
}
|
| 120 |
+
},
|
| 121 |
+
"total_flos": 2.6363791764000768e+17,
|
| 122 |
+
"train_batch_size": 8,
|
| 123 |
+
"trial_name": null,
|
| 124 |
+
"trial_params": null
|
| 125 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-14B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-14B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-14B-Base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.010622890133962027,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 128,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"q_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-4280/trainer_state.json
ADDED
|
@@ -0,0 +1,994 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 10.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 4280,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7805559730529785,
|
| 14 |
+
"epoch": 0.11682242990654206,
|
| 15 |
+
"grad_norm": 0.5128960013389587,
|
| 16 |
+
"learning_rate": 1.950005322230992e-06,
|
| 17 |
+
"loss": 1.770846405029297,
|
| 18 |
+
"mean_token_accuracy": 0.6305050283670426,
|
| 19 |
+
"num_tokens": 162248.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5725344836711883,
|
| 24 |
+
"epoch": 0.2336448598130841,
|
| 25 |
+
"grad_norm": 0.7059135437011719,
|
| 26 |
+
"learning_rate": 3.93980667144629e-06,
|
| 27 |
+
"loss": 1.5153414916992187,
|
| 28 |
+
"mean_token_accuracy": 0.6729821544885636,
|
| 29 |
+
"num_tokens": 327614.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.0769569373130798,
|
| 34 |
+
"epoch": 0.35046728971962615,
|
| 35 |
+
"grad_norm": 0.6092284321784973,
|
| 36 |
+
"learning_rate": 5.9296080206615885e-06,
|
| 37 |
+
"loss": 1.0251461791992187,
|
| 38 |
+
"mean_token_accuracy": 0.737835128903389,
|
| 39 |
+
"num_tokens": 494582.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.8583791655302048,
|
| 44 |
+
"epoch": 0.4672897196261682,
|
| 45 |
+
"grad_norm": 0.5586332082748413,
|
| 46 |
+
"learning_rate": 7.919409369876886e-06,
|
| 47 |
+
"loss": 0.81265869140625,
|
| 48 |
+
"mean_token_accuracy": 0.7762657129764556,
|
| 49 |
+
"num_tokens": 653981.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7744105678796768,
|
| 54 |
+
"epoch": 0.5841121495327103,
|
| 55 |
+
"grad_norm": 0.4821721613407135,
|
| 56 |
+
"learning_rate": 9.909210719092184e-06,
|
| 57 |
+
"loss": 0.7364049530029297,
|
| 58 |
+
"mean_token_accuracy": 0.7918167436122894,
|
| 59 |
+
"num_tokens": 814840.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.715560827255249,
|
| 64 |
+
"epoch": 0.7009345794392523,
|
| 65 |
+
"grad_norm": 0.6843860745429993,
|
| 66 |
+
"learning_rate": 1.1899012068307483e-05,
|
| 67 |
+
"loss": 0.6826614379882813,
|
| 68 |
+
"mean_token_accuracy": 0.8043146914243698,
|
| 69 |
+
"num_tokens": 979542.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6893886953592301,
|
| 74 |
+
"epoch": 0.8177570093457944,
|
| 75 |
+
"grad_norm": 0.6543110013008118,
|
| 76 |
+
"learning_rate": 1.3888813417522781e-05,
|
| 77 |
+
"loss": 0.6608805847167969,
|
| 78 |
+
"mean_token_accuracy": 0.8083165866136551,
|
| 79 |
+
"num_tokens": 1147400.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.652973799109459,
|
| 84 |
+
"epoch": 0.9345794392523364,
|
| 85 |
+
"grad_norm": 0.7437635660171509,
|
| 86 |
+
"learning_rate": 1.587861476673808e-05,
|
| 87 |
+
"loss": 0.6218611907958984,
|
| 88 |
+
"mean_token_accuracy": 0.8167323243618011,
|
| 89 |
+
"num_tokens": 1310490.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.0,
|
| 94 |
+
"eval_entropy": 0.8066210185552573,
|
| 95 |
+
"eval_loss": 0.7281543016433716,
|
| 96 |
+
"eval_mean_token_accuracy": 0.7858095281309896,
|
| 97 |
+
"eval_num_tokens": 1399670.0,
|
| 98 |
+
"eval_runtime": 46.0044,
|
| 99 |
+
"eval_samples_per_second": 26.758,
|
| 100 |
+
"eval_steps_per_second": 3.348,
|
| 101 |
+
"step": 428
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.6467276298999787,
|
| 105 |
+
"epoch": 1.0514018691588785,
|
| 106 |
+
"grad_norm": 0.626556396484375,
|
| 107 |
+
"learning_rate": 1.7031450502641085e-05,
|
| 108 |
+
"loss": 0.6161280441284179,
|
| 109 |
+
"mean_token_accuracy": 0.817004052400589,
|
| 110 |
+
"num_tokens": 1471726.0,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.6262363213300705,
|
| 115 |
+
"epoch": 1.1682242990654206,
|
| 116 |
+
"grad_norm": 0.70875084400177,
|
| 117 |
+
"learning_rate": 1.7018425538355792e-05,
|
| 118 |
+
"loss": 0.5963106536865235,
|
| 119 |
+
"mean_token_accuracy": 0.8221335035562515,
|
| 120 |
+
"num_tokens": 1638060.0,
|
| 121 |
+
"step": 500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"entropy": 0.6171189111471176,
|
| 125 |
+
"epoch": 1.2850467289719627,
|
| 126 |
+
"grad_norm": 0.6629440188407898,
|
| 127 |
+
"learning_rate": 1.6991264396738895e-05,
|
| 128 |
+
"loss": 0.5875393676757813,
|
| 129 |
+
"mean_token_accuracy": 0.8245152229070664,
|
| 130 |
+
"num_tokens": 1802005.0,
|
| 131 |
+
"step": 550
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"entropy": 0.6083133199810982,
|
| 135 |
+
"epoch": 1.4018691588785046,
|
| 136 |
+
"grad_norm": 0.5385038256645203,
|
| 137 |
+
"learning_rate": 1.6950012237904817e-05,
|
| 138 |
+
"loss": 0.5768455505371094,
|
| 139 |
+
"mean_token_accuracy": 0.8271224808692932,
|
| 140 |
+
"num_tokens": 1969267.0,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"entropy": 0.6011673760414123,
|
| 145 |
+
"epoch": 1.5186915887850467,
|
| 146 |
+
"grad_norm": 0.7062859535217285,
|
| 147 |
+
"learning_rate": 1.6894737650731013e-05,
|
| 148 |
+
"loss": 0.5666856384277343,
|
| 149 |
+
"mean_token_accuracy": 0.829860600233078,
|
| 150 |
+
"num_tokens": 2134793.0,
|
| 151 |
+
"step": 650
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"entropy": 0.5905318284034728,
|
| 155 |
+
"epoch": 1.6355140186915889,
|
| 156 |
+
"grad_norm": 0.646713137626648,
|
| 157 |
+
"learning_rate": 1.682553253881702e-05,
|
| 158 |
+
"loss": 0.560577392578125,
|
| 159 |
+
"mean_token_accuracy": 0.8313507026433945,
|
| 160 |
+
"num_tokens": 2300672.0,
|
| 161 |
+
"step": 700
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"entropy": 0.5964298728108406,
|
| 165 |
+
"epoch": 1.7523364485981308,
|
| 166 |
+
"grad_norm": 0.6510505080223083,
|
| 167 |
+
"learning_rate": 1.674251196767876e-05,
|
| 168 |
+
"loss": 0.5606492614746094,
|
| 169 |
+
"mean_token_accuracy": 0.8313686531782151,
|
| 170 |
+
"num_tokens": 2459315.0,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"entropy": 0.5872641482949257,
|
| 175 |
+
"epoch": 1.8691588785046729,
|
| 176 |
+
"grad_norm": 0.6211879849433899,
|
| 177 |
+
"learning_rate": 1.6645813973432182e-05,
|
| 178 |
+
"loss": 0.556594352722168,
|
| 179 |
+
"mean_token_accuracy": 0.8333250796794891,
|
| 180 |
+
"num_tokens": 2616878.0,
|
| 181 |
+
"step": 800
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"entropy": 0.5889243066310883,
|
| 185 |
+
"epoch": 1.985981308411215,
|
| 186 |
+
"grad_norm": 0.6804038882255554,
|
| 187 |
+
"learning_rate": 1.6535599333284194e-05,
|
| 188 |
+
"loss": 0.5578879928588867,
|
| 189 |
+
"mean_token_accuracy": 0.831966199874878,
|
| 190 |
+
"num_tokens": 2778909.0,
|
| 191 |
+
"step": 850
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
+
"eval_entropy": 0.7079034389613511,
|
| 196 |
+
"eval_loss": 0.6832069158554077,
|
| 197 |
+
"eval_mean_token_accuracy": 0.8022074165282311,
|
| 198 |
+
"eval_num_tokens": 2799340.0,
|
| 199 |
+
"eval_runtime": 46.0398,
|
| 200 |
+
"eval_samples_per_second": 26.738,
|
| 201 |
+
"eval_steps_per_second": 3.345,
|
| 202 |
+
"step": 856
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"entropy": 0.5462229257822037,
|
| 206 |
+
"epoch": 2.102803738317757,
|
| 207 |
+
"grad_norm": 0.5834382772445679,
|
| 208 |
+
"learning_rate": 1.6412051298212675e-05,
|
| 209 |
+
"loss": 0.5115155029296875,
|
| 210 |
+
"mean_token_accuracy": 0.8419190347194672,
|
| 211 |
+
"num_tokens": 2951115.0,
|
| 212 |
+
"step": 900
|
| 213 |
+
},
|
| 214 |
+
{
|
| 215 |
+
"entropy": 0.5501805812120437,
|
| 216 |
+
"epoch": 2.2196261682242993,
|
| 217 |
+
"grad_norm": 0.774409830570221,
|
| 218 |
+
"learning_rate": 1.627537528827988e-05,
|
| 219 |
+
"loss": 0.5193024826049805,
|
| 220 |
+
"mean_token_accuracy": 0.8415862208604813,
|
| 221 |
+
"num_tokens": 3115016.0,
|
| 222 |
+
"step": 950
|
| 223 |
+
},
|
| 224 |
+
{
|
| 225 |
+
"entropy": 0.5417112326622009,
|
| 226 |
+
"epoch": 2.336448598130841,
|
| 227 |
+
"grad_norm": 0.8148911595344543,
|
| 228 |
+
"learning_rate": 1.612579855108594e-05,
|
| 229 |
+
"loss": 0.5099837875366211,
|
| 230 |
+
"mean_token_accuracy": 0.8432273292541503,
|
| 231 |
+
"num_tokens": 3274313.0,
|
| 232 |
+
"step": 1000
|
| 233 |
+
},
|
| 234 |
+
{
|
| 235 |
+
"entropy": 0.5426027116179466,
|
| 236 |
+
"epoch": 2.453271028037383,
|
| 237 |
+
"grad_norm": 0.738017737865448,
|
| 238 |
+
"learning_rate": 1.596356978393025e-05,
|
| 239 |
+
"loss": 0.5110509490966797,
|
| 240 |
+
"mean_token_accuracy": 0.8447510355710983,
|
| 241 |
+
"num_tokens": 3440379.0,
|
| 242 |
+
"step": 1050
|
| 243 |
+
},
|
| 244 |
+
{
|
| 245 |
+
"entropy": 0.536553855240345,
|
| 246 |
+
"epoch": 2.5700934579439254,
|
| 247 |
+
"grad_norm": 0.6512451767921448,
|
| 248 |
+
"learning_rate": 1.5788958720309008e-05,
|
| 249 |
+
"loss": 0.5046747207641602,
|
| 250 |
+
"mean_token_accuracy": 0.8439748030900955,
|
| 251 |
+
"num_tokens": 3606755.0,
|
| 252 |
+
"step": 1100
|
| 253 |
+
},
|
| 254 |
+
{
|
| 255 |
+
"entropy": 0.5361887359619141,
|
| 256 |
+
"epoch": 2.6869158878504673,
|
| 257 |
+
"grad_norm": 0.7650485038757324,
|
| 258 |
+
"learning_rate": 1.5602255681436483e-05,
|
| 259 |
+
"loss": 0.5043494415283203,
|
| 260 |
+
"mean_token_accuracy": 0.8450696021318436,
|
| 261 |
+
"num_tokens": 3766555.0,
|
| 262 |
+
"step": 1150
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"entropy": 0.5419432005286217,
|
| 266 |
+
"epoch": 2.803738317757009,
|
| 267 |
+
"grad_norm": 0.6945335268974304,
|
| 268 |
+
"learning_rate": 1.5403771093535538e-05,
|
| 269 |
+
"loss": 0.5108187103271484,
|
| 270 |
+
"mean_token_accuracy": 0.8431807065010071,
|
| 271 |
+
"num_tokens": 3927164.0,
|
| 272 |
+
"step": 1200
|
| 273 |
+
},
|
| 274 |
+
{
|
| 275 |
+
"entropy": 0.5400136861205102,
|
| 276 |
+
"epoch": 2.9205607476635516,
|
| 277 |
+
"grad_norm": 0.774668276309967,
|
| 278 |
+
"learning_rate": 1.5193834971700146e-05,
|
| 279 |
+
"loss": 0.5082107543945312,
|
| 280 |
+
"mean_token_accuracy": 0.8444043332338333,
|
| 281 |
+
"num_tokens": 4090727.0,
|
| 282 |
+
"step": 1250
|
| 283 |
+
},
|
| 284 |
+
{
|
| 285 |
+
"epoch": 3.0,
|
| 286 |
+
"eval_entropy": 0.6524020644364419,
|
| 287 |
+
"eval_loss": 0.6701120138168335,
|
| 288 |
+
"eval_mean_token_accuracy": 0.8018650695101007,
|
| 289 |
+
"eval_num_tokens": 4199010.0,
|
| 290 |
+
"eval_runtime": 46.004,
|
| 291 |
+
"eval_samples_per_second": 26.759,
|
| 292 |
+
"eval_steps_per_second": 3.348,
|
| 293 |
+
"step": 1284
|
| 294 |
+
},
|
| 295 |
+
{
|
| 296 |
+
"entropy": 0.5256310805678368,
|
| 297 |
+
"epoch": 3.0373831775700935,
|
| 298 |
+
"grad_norm": 0.8875723481178284,
|
| 299 |
+
"learning_rate": 1.4972796371187997e-05,
|
| 300 |
+
"loss": 0.49435077667236327,
|
| 301 |
+
"mean_token_accuracy": 0.8473169440031052,
|
| 302 |
+
"num_tokens": 4252535.0,
|
| 303 |
+
"step": 1300
|
| 304 |
+
},
|
| 305 |
+
{
|
| 306 |
+
"entropy": 0.4986111795902252,
|
| 307 |
+
"epoch": 3.1542056074766354,
|
| 308 |
+
"grad_norm": 0.8605287671089172,
|
| 309 |
+
"learning_rate": 1.4741022807055508e-05,
|
| 310 |
+
"loss": 0.4662786483764648,
|
| 311 |
+
"mean_token_accuracy": 0.8552708566188812,
|
| 312 |
+
"num_tokens": 4414122.0,
|
| 313 |
+
"step": 1350
|
| 314 |
+
},
|
| 315 |
+
{
|
| 316 |
+
"entropy": 0.5061789083480835,
|
| 317 |
+
"epoch": 3.2710280373831777,
|
| 318 |
+
"grad_norm": 0.8101795315742493,
|
| 319 |
+
"learning_rate": 1.4498899643100226e-05,
|
| 320 |
+
"loss": 0.47242179870605466,
|
| 321 |
+
"mean_token_accuracy": 0.8520459419488907,
|
| 322 |
+
"num_tokens": 4571859.0,
|
| 323 |
+
"step": 1400
|
| 324 |
+
},
|
| 325 |
+
{
|
| 326 |
+
"entropy": 0.4939887225627899,
|
| 327 |
+
"epoch": 3.3878504672897196,
|
| 328 |
+
"grad_norm": 0.8013083338737488,
|
| 329 |
+
"learning_rate": 1.4246829451126602e-05,
|
| 330 |
+
"loss": 0.4614598846435547,
|
| 331 |
+
"mean_token_accuracy": 0.8552495676279068,
|
| 332 |
+
"num_tokens": 4735006.0,
|
| 333 |
+
"step": 1450
|
| 334 |
+
},
|
| 335 |
+
{
|
| 336 |
+
"entropy": 0.4918920609354973,
|
| 337 |
+
"epoch": 3.5046728971962615,
|
| 338 |
+
"grad_norm": 0.7743699550628662,
|
| 339 |
+
"learning_rate": 1.3985231341600455e-05,
|
| 340 |
+
"loss": 0.46159915924072265,
|
| 341 |
+
"mean_token_accuracy": 0.8550176537036895,
|
| 342 |
+
"num_tokens": 4898228.0,
|
| 343 |
+
"step": 1500
|
| 344 |
+
},
|
| 345 |
+
{
|
| 346 |
+
"entropy": 0.49779762893915175,
|
| 347 |
+
"epoch": 3.621495327102804,
|
| 348 |
+
"grad_norm": 0.8169922828674316,
|
| 349 |
+
"learning_rate": 1.3714540266805045e-05,
|
| 350 |
+
"loss": 0.46558887481689454,
|
| 351 |
+
"mean_token_accuracy": 0.8540038305521012,
|
| 352 |
+
"num_tokens": 5063413.0,
|
| 353 |
+
"step": 1550
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"entropy": 0.5015265879034996,
|
| 357 |
+
"epoch": 3.7383177570093458,
|
| 358 |
+
"grad_norm": 0.851017951965332,
|
| 359 |
+
"learning_rate": 1.343520629765737e-05,
|
| 360 |
+
"loss": 0.46733531951904295,
|
| 361 |
+
"mean_token_accuracy": 0.8522392755746842,
|
| 362 |
+
"num_tokens": 5227672.0,
|
| 363 |
+
"step": 1600
|
| 364 |
+
},
|
| 365 |
+
{
|
| 366 |
+
"entropy": 0.501338247358799,
|
| 367 |
+
"epoch": 3.8551401869158877,
|
| 368 |
+
"grad_norm": 0.8121753334999084,
|
| 369 |
+
"learning_rate": 1.3147693875387126e-05,
|
| 370 |
+
"loss": 0.4710521697998047,
|
| 371 |
+
"mean_token_accuracy": 0.8534136080741882,
|
| 372 |
+
"num_tokens": 5389834.0,
|
| 373 |
+
"step": 1650
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"entropy": 0.49478380143642425,
|
| 377 |
+
"epoch": 3.97196261682243,
|
| 378 |
+
"grad_norm": 0.6918302178382874,
|
| 379 |
+
"learning_rate": 1.2852481039322492e-05,
|
| 380 |
+
"loss": 0.4646331405639648,
|
| 381 |
+
"mean_token_accuracy": 0.8551374357938767,
|
| 382 |
+
"num_tokens": 5559167.0,
|
| 383 |
+
"step": 1700
|
| 384 |
+
},
|
| 385 |
+
{
|
| 386 |
+
"epoch": 4.0,
|
| 387 |
+
"eval_entropy": 0.6295453201640736,
|
| 388 |
+
"eval_loss": 0.666642427444458,
|
| 389 |
+
"eval_mean_token_accuracy": 0.8111948270302314,
|
| 390 |
+
"eval_num_tokens": 5598680.0,
|
| 391 |
+
"eval_runtime": 45.8725,
|
| 392 |
+
"eval_samples_per_second": 26.835,
|
| 393 |
+
"eval_steps_per_second": 3.357,
|
| 394 |
+
"step": 1712
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"entropy": 0.46167980462312697,
|
| 398 |
+
"epoch": 4.088785046728972,
|
| 399 |
+
"grad_norm": 0.8769540190696716,
|
| 400 |
+
"learning_rate": 1.2550058632066751e-05,
|
| 401 |
+
"loss": 0.4263522338867187,
|
| 402 |
+
"mean_token_accuracy": 0.8653014451265335,
|
| 403 |
+
"num_tokens": 5721701.0,
|
| 404 |
+
"step": 1750
|
| 405 |
+
},
|
| 406 |
+
{
|
| 407 |
+
"entropy": 0.4534104973077774,
|
| 408 |
+
"epoch": 4.205607476635514,
|
| 409 |
+
"grad_norm": 1.1420735120773315,
|
| 410 |
+
"learning_rate": 1.2240929483387228e-05,
|
| 411 |
+
"loss": 0.41863834381103515,
|
| 412 |
+
"mean_token_accuracy": 0.8667230373620987,
|
| 413 |
+
"num_tokens": 5884163.0,
|
| 414 |
+
"step": 1800
|
| 415 |
+
},
|
| 416 |
+
{
|
| 417 |
+
"entropy": 0.4606948295235634,
|
| 418 |
+
"epoch": 4.322429906542056,
|
| 419 |
+
"grad_norm": 1.0596942901611328,
|
| 420 |
+
"learning_rate": 1.1925607574173476e-05,
|
| 421 |
+
"loss": 0.42718273162841797,
|
| 422 |
+
"mean_token_accuracy": 0.8641588741540909,
|
| 423 |
+
"num_tokens": 6053869.0,
|
| 424 |
+
"step": 1850
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"entropy": 0.45681062549352647,
|
| 428 |
+
"epoch": 4.4392523364485985,
|
| 429 |
+
"grad_norm": 0.9009803533554077,
|
| 430 |
+
"learning_rate": 1.1604617181854806e-05,
|
| 431 |
+
"loss": 0.42521621704101564,
|
| 432 |
+
"mean_token_accuracy": 0.8644315087795258,
|
| 433 |
+
"num_tokens": 6217351.0,
|
| 434 |
+
"step": 1900
|
| 435 |
+
},
|
| 436 |
+
{
|
| 437 |
+
"entropy": 0.45814105302095415,
|
| 438 |
+
"epoch": 4.55607476635514,
|
| 439 |
+
"grad_norm": 0.9394752383232117,
|
| 440 |
+
"learning_rate": 1.127849200869801e-05,
|
| 441 |
+
"loss": 0.42409008026123046,
|
| 442 |
+
"mean_token_accuracy": 0.864885100722313,
|
| 443 |
+
"num_tokens": 6379796.0,
|
| 444 |
+
"step": 1950
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"entropy": 0.4561432495713234,
|
| 448 |
+
"epoch": 4.672897196261682,
|
| 449 |
+
"grad_norm": 0.8258721828460693,
|
| 450 |
+
"learning_rate": 1.094777429443468e-05,
|
| 451 |
+
"loss": 0.42701839447021483,
|
| 452 |
+
"mean_token_accuracy": 0.8638879442214966,
|
| 453 |
+
"num_tokens": 6550276.0,
|
| 454 |
+
"step": 2000
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"entropy": 0.4610430991649628,
|
| 458 |
+
"epoch": 4.789719626168225,
|
| 459 |
+
"grad_norm": 1.0002802610397339,
|
| 460 |
+
"learning_rate": 1.0613013914693477e-05,
|
| 461 |
+
"loss": 0.4286579895019531,
|
| 462 |
+
"mean_token_accuracy": 0.8643757510185242,
|
| 463 |
+
"num_tokens": 6709429.0,
|
| 464 |
+
"step": 2050
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"entropy": 0.4558544892072678,
|
| 468 |
+
"epoch": 4.906542056074766,
|
| 469 |
+
"grad_norm": 0.9755097031593323,
|
| 470 |
+
"learning_rate": 1.0274767466736426e-05,
|
| 471 |
+
"loss": 0.4233176803588867,
|
| 472 |
+
"mean_token_accuracy": 0.8655301338434219,
|
| 473 |
+
"num_tokens": 6870956.0,
|
| 474 |
+
"step": 2100
|
| 475 |
+
},
|
| 476 |
+
{
|
| 477 |
+
"epoch": 5.0,
|
| 478 |
+
"eval_entropy": 0.6000483314712326,
|
| 479 |
+
"eval_loss": 0.6985165476799011,
|
| 480 |
+
"eval_mean_token_accuracy": 0.8045627912143608,
|
| 481 |
+
"eval_num_tokens": 6998350.0,
|
| 482 |
+
"eval_runtime": 45.9034,
|
| 483 |
+
"eval_samples_per_second": 26.817,
|
| 484 |
+
"eval_steps_per_second": 3.355,
|
| 485 |
+
"step": 2140
|
| 486 |
+
},
|
| 487 |
+
{
|
| 488 |
+
"entropy": 0.44992744773626325,
|
| 489 |
+
"epoch": 5.0233644859813085,
|
| 490 |
+
"grad_norm": 1.1082366704940796,
|
| 491 |
+
"learning_rate": 9.933597344019314e-06,
|
| 492 |
+
"loss": 0.41550483703613283,
|
| 493 |
+
"mean_token_accuracy": 0.8669036704301835,
|
| 494 |
+
"num_tokens": 7034085.0,
|
| 495 |
+
"step": 2150
|
| 496 |
+
},
|
| 497 |
+
{
|
| 498 |
+
"entropy": 0.4088956421613693,
|
| 499 |
+
"epoch": 5.140186915887851,
|
| 500 |
+
"grad_norm": 1.0101401805877686,
|
| 501 |
+
"learning_rate": 9.59007080111491e-06,
|
| 502 |
+
"loss": 0.3716637420654297,
|
| 503 |
+
"mean_token_accuracy": 0.8802521765232086,
|
| 504 |
+
"num_tokens": 7198745.0,
|
| 505 |
+
"step": 2200
|
| 506 |
+
},
|
| 507 |
+
{
|
| 508 |
+
"entropy": 0.4127876952290535,
|
| 509 |
+
"epoch": 5.257009345794392,
|
| 510 |
+
"grad_norm": 1.1201362609863281,
|
| 511 |
+
"learning_rate": 9.244759010553727e-06,
|
| 512 |
+
"loss": 0.37826343536376955,
|
| 513 |
+
"mean_token_accuracy": 0.8786936563253402,
|
| 514 |
+
"num_tokens": 7366588.0,
|
| 515 |
+
"step": 2250
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"entropy": 0.4232992666959763,
|
| 519 |
+
"epoch": 5.373831775700935,
|
| 520 |
+
"grad_norm": 1.1778150796890259,
|
| 521 |
+
"learning_rate": 8.898236113150524e-06,
|
| 522 |
+
"loss": 0.38583309173583985,
|
| 523 |
+
"mean_token_accuracy": 0.8747973537445068,
|
| 524 |
+
"num_tokens": 7531696.0,
|
| 525 |
+
"step": 2300
|
| 526 |
+
},
|
| 527 |
+
{
|
| 528 |
+
"entropy": 0.4159915736317635,
|
| 529 |
+
"epoch": 5.490654205607477,
|
| 530 |
+
"grad_norm": 1.1592568159103394,
|
| 531 |
+
"learning_rate": 8.551078263395478e-06,
|
| 532 |
+
"loss": 0.3784225082397461,
|
| 533 |
+
"mean_token_accuracy": 0.8779372000694274,
|
| 534 |
+
"num_tokens": 7688960.0,
|
| 535 |
+
"step": 2350
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"entropy": 0.41662866294384004,
|
| 539 |
+
"epoch": 5.607476635514018,
|
| 540 |
+
"grad_norm": 1.254981517791748,
|
| 541 |
+
"learning_rate": 8.203862671497323e-06,
|
| 542 |
+
"loss": 0.37995223999023436,
|
| 543 |
+
"mean_token_accuracy": 0.8772805953025817,
|
| 544 |
+
"num_tokens": 7851053.0,
|
| 545 |
+
"step": 2400
|
| 546 |
+
},
|
| 547 |
+
{
|
| 548 |
+
"entropy": 0.417872933447361,
|
| 549 |
+
"epoch": 5.724299065420561,
|
| 550 |
+
"grad_norm": 1.322206974029541,
|
| 551 |
+
"learning_rate": 7.857166643671128e-06,
|
| 552 |
+
"loss": 0.38079578399658204,
|
| 553 |
+
"mean_token_accuracy": 0.8774149787425994,
|
| 554 |
+
"num_tokens": 8001524.0,
|
| 555 |
+
"step": 2450
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"entropy": 0.41878397345542906,
|
| 559 |
+
"epoch": 5.841121495327103,
|
| 560 |
+
"grad_norm": 1.2948966026306152,
|
| 561 |
+
"learning_rate": 7.511566622266466e-06,
|
| 562 |
+
"loss": 0.3861651611328125,
|
| 563 |
+
"mean_token_accuracy": 0.8755189329385757,
|
| 564 |
+
"num_tokens": 8166394.0,
|
| 565 |
+
"step": 2500
|
| 566 |
+
},
|
| 567 |
+
{
|
| 568 |
+
"entropy": 0.4128647845983505,
|
| 569 |
+
"epoch": 5.957943925233645,
|
| 570 |
+
"grad_norm": 1.190157175064087,
|
| 571 |
+
"learning_rate": 7.167637227331918e-06,
|
| 572 |
+
"loss": 0.37860721588134766,
|
| 573 |
+
"mean_token_accuracy": 0.8772583198547363,
|
| 574 |
+
"num_tokens": 8339045.0,
|
| 575 |
+
"step": 2550
|
| 576 |
+
},
|
| 577 |
+
{
|
| 578 |
+
"epoch": 6.0,
|
| 579 |
+
"eval_entropy": 0.5655807773401211,
|
| 580 |
+
"eval_loss": 0.7187017202377319,
|
| 581 |
+
"eval_mean_token_accuracy": 0.8067006375882533,
|
| 582 |
+
"eval_num_tokens": 8398020.0,
|
| 583 |
+
"eval_runtime": 45.9295,
|
| 584 |
+
"eval_samples_per_second": 26.802,
|
| 585 |
+
"eval_steps_per_second": 3.353,
|
| 586 |
+
"step": 2568
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"entropy": 0.3961917132139206,
|
| 590 |
+
"epoch": 6.074766355140187,
|
| 591 |
+
"grad_norm": 1.1673611402511597,
|
| 592 |
+
"learning_rate": 6.82595030120946e-06,
|
| 593 |
+
"loss": 0.35439579010009764,
|
| 594 |
+
"mean_token_accuracy": 0.8850088411569595,
|
| 595 |
+
"num_tokens": 8502228.0,
|
| 596 |
+
"step": 2600
|
| 597 |
+
},
|
| 598 |
+
{
|
| 599 |
+
"entropy": 0.368110328912735,
|
| 600 |
+
"epoch": 6.191588785046729,
|
| 601 |
+
"grad_norm": 1.3757716417312622,
|
| 602 |
+
"learning_rate": 6.487073957747255e-06,
|
| 603 |
+
"loss": 0.32657440185546877,
|
| 604 |
+
"mean_token_accuracy": 0.8935984402894974,
|
| 605 |
+
"num_tokens": 8670819.0,
|
| 606 |
+
"step": 2650
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"entropy": 0.38117473274469377,
|
| 610 |
+
"epoch": 6.308411214953271,
|
| 611 |
+
"grad_norm": 1.5222810506820679,
|
| 612 |
+
"learning_rate": 6.151571637711756e-06,
|
| 613 |
+
"loss": 0.33884075164794925,
|
| 614 |
+
"mean_token_accuracy": 0.8893738853931427,
|
| 615 |
+
"num_tokens": 8833691.0,
|
| 616 |
+
"step": 2700
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"entropy": 0.368239968419075,
|
| 620 |
+
"epoch": 6.425233644859813,
|
| 621 |
+
"grad_norm": 1.35374116897583,
|
| 622 |
+
"learning_rate": 5.820001171969559e-06,
|
| 623 |
+
"loss": 0.32751472473144533,
|
| 624 |
+
"mean_token_accuracy": 0.8923951196670532,
|
| 625 |
+
"num_tokens": 8991136.0,
|
| 626 |
+
"step": 2750
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"entropy": 0.3820819303393364,
|
| 630 |
+
"epoch": 6.542056074766355,
|
| 631 |
+
"grad_norm": 1.4458277225494385,
|
| 632 |
+
"learning_rate": 5.492913853996745e-06,
|
| 633 |
+
"loss": 0.33998115539550783,
|
| 634 |
+
"mean_token_accuracy": 0.8889218932390213,
|
| 635 |
+
"num_tokens": 9156211.0,
|
| 636 |
+
"step": 2800
|
| 637 |
+
},
|
| 638 |
+
{
|
| 639 |
+
"entropy": 0.37935444712638855,
|
| 640 |
+
"epoch": 6.658878504672897,
|
| 641 |
+
"grad_norm": 1.407097339630127,
|
| 642 |
+
"learning_rate": 5.170853523257732e-06,
|
| 643 |
+
"loss": 0.33896163940429686,
|
| 644 |
+
"mean_token_accuracy": 0.8889170825481415,
|
| 645 |
+
"num_tokens": 9320538.0,
|
| 646 |
+
"step": 2850
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy": 0.3754119920730591,
|
| 650 |
+
"epoch": 6.775700934579439,
|
| 651 |
+
"grad_norm": 1.343308448791504,
|
| 652 |
+
"learning_rate": 4.854355660977731e-06,
|
| 653 |
+
"loss": 0.33744224548339846,
|
| 654 |
+
"mean_token_accuracy": 0.8890663629770279,
|
| 655 |
+
"num_tokens": 9480686.0,
|
| 656 |
+
"step": 2900
|
| 657 |
+
},
|
| 658 |
+
{
|
| 659 |
+
"entropy": 0.3785912898182869,
|
| 660 |
+
"epoch": 6.892523364485982,
|
| 661 |
+
"grad_norm": 1.3478388786315918,
|
| 662 |
+
"learning_rate": 4.543946499812223e-06,
|
| 663 |
+
"loss": 0.3381637954711914,
|
| 664 |
+
"mean_token_accuracy": 0.890493910908699,
|
| 665 |
+
"num_tokens": 9644088.0,
|
| 666 |
+
"step": 2950
|
| 667 |
+
},
|
| 668 |
+
{
|
| 669 |
+
"epoch": 7.0,
|
| 670 |
+
"eval_entropy": 0.5324798737253461,
|
| 671 |
+
"eval_loss": 0.7690625786781311,
|
| 672 |
+
"eval_mean_token_accuracy": 0.8012763478539207,
|
| 673 |
+
"eval_num_tokens": 9797690.0,
|
| 674 |
+
"eval_runtime": 45.8503,
|
| 675 |
+
"eval_samples_per_second": 26.848,
|
| 676 |
+
"eval_steps_per_second": 3.359,
|
| 677 |
+
"step": 2996
|
| 678 |
+
},
|
| 679 |
+
{
|
| 680 |
+
"entropy": 0.3794779407978058,
|
| 681 |
+
"epoch": 7.009345794392523,
|
| 682 |
+
"grad_norm": 1.4755299091339111,
|
| 683 |
+
"learning_rate": 4.2401421488938005e-06,
|
| 684 |
+
"loss": 0.33749778747558595,
|
| 685 |
+
"mean_token_accuracy": 0.8893112099170685,
|
| 686 |
+
"num_tokens": 9809264.0,
|
| 687 |
+
"step": 3000
|
| 688 |
+
},
|
| 689 |
+
{
|
| 690 |
+
"entropy": 0.34282191276550295,
|
| 691 |
+
"epoch": 7.126168224299065,
|
| 692 |
+
"grad_norm": 2.2217698097229004,
|
| 693 |
+
"learning_rate": 3.943447735711094e-06,
|
| 694 |
+
"loss": 0.29293390274047854,
|
| 695 |
+
"mean_token_accuracy": 0.9042663037776947,
|
| 696 |
+
"num_tokens": 9972116.0,
|
| 697 |
+
"step": 3050
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"entropy": 0.34247083246707916,
|
| 701 |
+
"epoch": 7.242990654205608,
|
| 702 |
+
"grad_norm": 1.8383665084838867,
|
| 703 |
+
"learning_rate": 3.6543565662466186e-06,
|
| 704 |
+
"loss": 0.2937329292297363,
|
| 705 |
+
"mean_token_accuracy": 0.9028173768520356,
|
| 706 |
+
"num_tokens": 10137487.0,
|
| 707 |
+
"step": 3100
|
| 708 |
+
},
|
| 709 |
+
{
|
| 710 |
+
"entropy": 0.335525888800621,
|
| 711 |
+
"epoch": 7.359813084112149,
|
| 712 |
+
"grad_norm": 1.473850131034851,
|
| 713 |
+
"learning_rate": 3.3733493047699217e-06,
|
| 714 |
+
"loss": 0.28937688827514646,
|
| 715 |
+
"mean_token_accuracy": 0.9054816484451294,
|
| 716 |
+
"num_tokens": 10302931.0,
|
| 717 |
+
"step": 3150
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"entropy": 0.3531618478894234,
|
| 721 |
+
"epoch": 7.4766355140186915,
|
| 722 |
+
"grad_norm": 1.4571647644042969,
|
| 723 |
+
"learning_rate": 3.1008931746497474e-06,
|
| 724 |
+
"loss": 0.3051707649230957,
|
| 725 |
+
"mean_token_accuracy": 0.9000385081768036,
|
| 726 |
+
"num_tokens": 10458987.0,
|
| 727 |
+
"step": 3200
|
| 728 |
+
},
|
| 729 |
+
{
|
| 730 |
+
"entropy": 0.34587423503398895,
|
| 731 |
+
"epoch": 7.593457943925234,
|
| 732 |
+
"grad_norm": 1.4684133529663086,
|
| 733 |
+
"learning_rate": 2.837441181514078e-06,
|
| 734 |
+
"loss": 0.30000652313232423,
|
| 735 |
+
"mean_token_accuracy": 0.9019779992103577,
|
| 736 |
+
"num_tokens": 10626220.0,
|
| 737 |
+
"step": 3250
|
| 738 |
+
},
|
| 739 |
+
{
|
| 740 |
+
"entropy": 0.34274055570364,
|
| 741 |
+
"epoch": 7.710280373831775,
|
| 742 |
+
"grad_norm": 1.7025630474090576,
|
| 743 |
+
"learning_rate": 2.583431360049599e-06,
|
| 744 |
+
"loss": 0.2970438957214355,
|
| 745 |
+
"mean_token_accuracy": 0.9021710187196732,
|
| 746 |
+
"num_tokens": 10791927.0,
|
| 747 |
+
"step": 3300
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"entropy": 0.3418415796756744,
|
| 751 |
+
"epoch": 7.827102803738318,
|
| 752 |
+
"grad_norm": 1.4021923542022705,
|
| 753 |
+
"learning_rate": 2.3392860456929694e-06,
|
| 754 |
+
"loss": 0.29404821395874026,
|
| 755 |
+
"mean_token_accuracy": 0.9038505190610886,
|
| 756 |
+
"num_tokens": 10959396.0,
|
| 757 |
+
"step": 3350
|
| 758 |
+
},
|
| 759 |
+
{
|
| 760 |
+
"entropy": 0.3426601967215538,
|
| 761 |
+
"epoch": 7.94392523364486,
|
| 762 |
+
"grad_norm": 1.4425413608551025,
|
| 763 |
+
"learning_rate": 2.105411172424829e-06,
|
| 764 |
+
"loss": 0.295624828338623,
|
| 765 |
+
"mean_token_accuracy": 0.9028824782371521,
|
| 766 |
+
"num_tokens": 11119550.0,
|
| 767 |
+
"step": 3400
|
| 768 |
+
},
|
| 769 |
+
{
|
| 770 |
+
"epoch": 8.0,
|
| 771 |
+
"eval_entropy": 0.5096885060722177,
|
| 772 |
+
"eval_loss": 0.8266266584396362,
|
| 773 |
+
"eval_mean_token_accuracy": 0.7996714382202594,
|
| 774 |
+
"eval_num_tokens": 11197360.0,
|
| 775 |
+
"eval_runtime": 45.8391,
|
| 776 |
+
"eval_samples_per_second": 26.855,
|
| 777 |
+
"eval_steps_per_second": 3.36,
|
| 778 |
+
"step": 3424
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"entropy": 0.33504158034920695,
|
| 782 |
+
"epoch": 8.060747663551401,
|
| 783 |
+
"grad_norm": 1.7360987663269043,
|
| 784 |
+
"learning_rate": 1.8821955978340481e-06,
|
| 785 |
+
"loss": 0.2848625564575195,
|
| 786 |
+
"mean_token_accuracy": 0.9075938129425049,
|
| 787 |
+
"num_tokens": 11282774.0,
|
| 788 |
+
"step": 3450
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"entropy": 0.32288984924554825,
|
| 792 |
+
"epoch": 8.177570093457945,
|
| 793 |
+
"grad_norm": 1.6818318367004395,
|
| 794 |
+
"learning_rate": 1.6700104565744824e-06,
|
| 795 |
+
"loss": 0.26646427154541014,
|
| 796 |
+
"mean_token_accuracy": 0.9131433618068695,
|
| 797 |
+
"num_tokens": 11443420.0,
|
| 798 |
+
"step": 3500
|
| 799 |
+
},
|
| 800 |
+
{
|
| 801 |
+
"entropy": 0.32121765553951265,
|
| 802 |
+
"epoch": 8.294392523364486,
|
| 803 |
+
"grad_norm": 1.7594389915466309,
|
| 804 |
+
"learning_rate": 1.4692085432891538e-06,
|
| 805 |
+
"loss": 0.2693086814880371,
|
| 806 |
+
"mean_token_accuracy": 0.9124349278211593,
|
| 807 |
+
"num_tokens": 11603266.0,
|
| 808 |
+
"step": 3550
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"entropy": 0.3194531953334808,
|
| 812 |
+
"epoch": 8.411214953271028,
|
| 813 |
+
"grad_norm": 1.5076898336410522,
|
| 814 |
+
"learning_rate": 1.2801237260278847e-06,
|
| 815 |
+
"loss": 0.2668701362609863,
|
| 816 |
+
"mean_token_accuracy": 0.9122523158788681,
|
| 817 |
+
"num_tokens": 11766536.0,
|
| 818 |
+
"step": 3600
|
| 819 |
+
},
|
| 820 |
+
{
|
| 821 |
+
"entropy": 0.3196700257062912,
|
| 822 |
+
"epoch": 8.52803738317757,
|
| 823 |
+
"grad_norm": 1.899849772453308,
|
| 824 |
+
"learning_rate": 1.103070391133706e-06,
|
| 825 |
+
"loss": 0.2672290420532227,
|
| 826 |
+
"mean_token_accuracy": 0.9123695671558381,
|
| 827 |
+
"num_tokens": 11934812.0,
|
| 828 |
+
"step": 3650
|
| 829 |
+
},
|
| 830 |
+
{
|
| 831 |
+
"entropy": 0.32141068547964097,
|
| 832 |
+
"epoch": 8.644859813084112,
|
| 833 |
+
"grad_norm": 1.878564476966858,
|
| 834 |
+
"learning_rate": 9.38342920520968e-07,
|
| 835 |
+
"loss": 0.2677190399169922,
|
| 836 |
+
"mean_token_accuracy": 0.9121616327762604,
|
| 837 |
+
"num_tokens": 12095307.0,
|
| 838 |
+
"step": 3700
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"entropy": 0.3209075602889061,
|
| 842 |
+
"epoch": 8.761682242990654,
|
| 843 |
+
"grad_norm": 1.7056505680084229,
|
| 844 |
+
"learning_rate": 7.862152022142707e-07,
|
| 845 |
+
"loss": 0.2690747261047363,
|
| 846 |
+
"mean_token_accuracy": 0.9123590832948685,
|
| 847 |
+
"num_tokens": 12267401.0,
|
| 848 |
+
"step": 3750
|
| 849 |
+
},
|
| 850 |
+
{
|
| 851 |
+
"entropy": 0.3217465075850487,
|
| 852 |
+
"epoch": 8.878504672897197,
|
| 853 |
+
"grad_norm": 1.966456651687622,
|
| 854 |
+
"learning_rate": 6.469401749620809e-07,
|
| 855 |
+
"loss": 0.2688888168334961,
|
| 856 |
+
"mean_token_accuracy": 0.912511082291603,
|
| 857 |
+
"num_tokens": 12432027.0,
|
| 858 |
+
"step": 3800
|
| 859 |
+
},
|
| 860 |
+
{
|
| 861 |
+
"entropy": 0.3217696958780289,
|
| 862 |
+
"epoch": 8.995327102803738,
|
| 863 |
+
"grad_norm": 1.8051724433898926,
|
| 864 |
+
"learning_rate": 5.20749407682135e-07,
|
| 865 |
+
"loss": 0.26914966583251954,
|
| 866 |
+
"mean_token_accuracy": 0.9128880047798157,
|
| 867 |
+
"num_tokens": 12591339.0,
|
| 868 |
+
"step": 3850
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"epoch": 9.0,
|
| 872 |
+
"eval_entropy": 0.4910243496105268,
|
| 873 |
+
"eval_loss": 0.8639353513717651,
|
| 874 |
+
"eval_mean_token_accuracy": 0.7988481390011775,
|
| 875 |
+
"eval_num_tokens": 12597030.0,
|
| 876 |
+
"eval_runtime": 45.8237,
|
| 877 |
+
"eval_samples_per_second": 26.864,
|
| 878 |
+
"eval_steps_per_second": 3.361,
|
| 879 |
+
"step": 3852
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"entropy": 0.3152778188884258,
|
| 883 |
+
"epoch": 9.11214953271028,
|
| 884 |
+
"grad_norm": 1.8005728721618652,
|
| 885 |
+
"learning_rate": 4.078527144378968e-07,
|
| 886 |
+
"loss": 0.25673791885375974,
|
| 887 |
+
"mean_token_accuracy": 0.9164336705207825,
|
| 888 |
+
"num_tokens": 12752829.0,
|
| 889 |
+
"step": 3900
|
| 890 |
+
},
|
| 891 |
+
{
|
| 892 |
+
"entropy": 0.31409676253795626,
|
| 893 |
+
"epoch": 9.228971962616823,
|
| 894 |
+
"grad_norm": 1.5963940620422363,
|
| 895 |
+
"learning_rate": 3.0843780558624924e-07,
|
| 896 |
+
"loss": 0.25571414947509763,
|
| 897 |
+
"mean_token_accuracy": 0.9168984878063202,
|
| 898 |
+
"num_tokens": 12912121.0,
|
| 899 |
+
"step": 3950
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"entropy": 0.30494138717651365,
|
| 903 |
+
"epoch": 9.345794392523365,
|
| 904 |
+
"grad_norm": 1.4225034713745117,
|
| 905 |
+
"learning_rate": 2.226699756764308e-07,
|
| 906 |
+
"loss": 0.24776287078857423,
|
| 907 |
+
"mean_token_accuracy": 0.9196718311309815,
|
| 908 |
+
"num_tokens": 13077510.0,
|
| 909 |
+
"step": 4000
|
| 910 |
+
},
|
| 911 |
+
{
|
| 912 |
+
"entropy": 0.3076481048762798,
|
| 913 |
+
"epoch": 9.462616822429906,
|
| 914 |
+
"grad_norm": 2.1019365787506104,
|
| 915 |
+
"learning_rate": 1.506918286191357e-07,
|
| 916 |
+
"loss": 0.2502549171447754,
|
| 917 |
+
"mean_token_accuracy": 0.9186357688903809,
|
| 918 |
+
"num_tokens": 13244654.0,
|
| 919 |
+
"step": 4050
|
| 920 |
+
},
|
| 921 |
+
{
|
| 922 |
+
"entropy": 0.3108975490927696,
|
| 923 |
+
"epoch": 9.57943925233645,
|
| 924 |
+
"grad_norm": 1.3740757703781128,
|
| 925 |
+
"learning_rate": 9.262304058276214e-08,
|
| 926 |
+
"loss": 0.2573278999328613,
|
| 927 |
+
"mean_token_accuracy": 0.9166838109493256,
|
| 928 |
+
"num_tokens": 13411362.0,
|
| 929 |
+
"step": 4100
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"entropy": 0.3064481493830681,
|
| 933 |
+
"epoch": 9.69626168224299,
|
| 934 |
+
"grad_norm": 1.5751773118972778,
|
| 935 |
+
"learning_rate": 4.856016101098735e-08,
|
| 936 |
+
"loss": 0.25151018142700193,
|
| 937 |
+
"mean_token_accuracy": 0.9180398142337799,
|
| 938 |
+
"num_tokens": 13577021.0,
|
| 939 |
+
"step": 4150
|
| 940 |
+
},
|
| 941 |
+
{
|
| 942 |
+
"entropy": 0.3111927331984043,
|
| 943 |
+
"epoch": 9.813084112149532,
|
| 944 |
+
"grad_norm": 1.6361159086227417,
|
| 945 |
+
"learning_rate": 1.8576452092562922e-08,
|
| 946 |
+
"loss": 0.25523736953735354,
|
| 947 |
+
"mean_token_accuracy": 0.9177506428956985,
|
| 948 |
+
"num_tokens": 13737792.0,
|
| 949 |
+
"step": 4200
|
| 950 |
+
},
|
| 951 |
+
{
|
| 952 |
+
"entropy": 0.30768390417099,
|
| 953 |
+
"epoch": 9.929906542056075,
|
| 954 |
+
"grad_norm": 1.8813536167144775,
|
| 955 |
+
"learning_rate": 2.7217669501977984e-09,
|
| 956 |
+
"loss": 0.2528882598876953,
|
| 957 |
+
"mean_token_accuracy": 0.9186167693138123,
|
| 958 |
+
"num_tokens": 13896034.0,
|
| 959 |
+
"step": 4250
|
| 960 |
+
},
|
| 961 |
+
{
|
| 962 |
+
"epoch": 10.0,
|
| 963 |
+
"eval_entropy": 0.48451440191114103,
|
| 964 |
+
"eval_loss": 0.8827346563339233,
|
| 965 |
+
"eval_mean_token_accuracy": 0.7974711935241501,
|
| 966 |
+
"eval_num_tokens": 13996700.0,
|
| 967 |
+
"eval_runtime": 45.8243,
|
| 968 |
+
"eval_samples_per_second": 26.863,
|
| 969 |
+
"eval_steps_per_second": 3.361,
|
| 970 |
+
"step": 4280
|
| 971 |
+
}
|
| 972 |
+
],
|
| 973 |
+
"logging_steps": 50,
|
| 974 |
+
"max_steps": 4280,
|
| 975 |
+
"num_input_tokens_seen": 0,
|
| 976 |
+
"num_train_epochs": 10,
|
| 977 |
+
"save_steps": 500,
|
| 978 |
+
"stateful_callbacks": {
|
| 979 |
+
"TrainerControl": {
|
| 980 |
+
"args": {
|
| 981 |
+
"should_epoch_stop": false,
|
| 982 |
+
"should_evaluate": false,
|
| 983 |
+
"should_log": false,
|
| 984 |
+
"should_save": true,
|
| 985 |
+
"should_training_stop": true
|
| 986 |
+
},
|
| 987 |
+
"attributes": {}
|
| 988 |
+
}
|
| 989 |
+
},
|
| 990 |
+
"total_flos": 2.634209464544502e+18,
|
| 991 |
+
"train_batch_size": 8,
|
| 992 |
+
"trial_name": null,
|
| 993 |
+
"trial_params": null
|
| 994 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/README.md
ADDED
|
@@ -0,0 +1,209 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
base_model: Qwen/Qwen3-14B-Base
|
| 3 |
+
library_name: peft
|
| 4 |
+
pipeline_tag: text-generation
|
| 5 |
+
tags:
|
| 6 |
+
- base_model:adapter:Qwen/Qwen3-14B-Base
|
| 7 |
+
- lora
|
| 8 |
+
- sft
|
| 9 |
+
- transformers
|
| 10 |
+
- trl
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Model Card for Model ID
|
| 14 |
+
|
| 15 |
+
<!-- Provide a quick summary of what the model is/does. -->
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
## Model Details
|
| 20 |
+
|
| 21 |
+
### Model Description
|
| 22 |
+
|
| 23 |
+
<!-- Provide a longer summary of what this model is. -->
|
| 24 |
+
|
| 25 |
+
|
| 26 |
+
|
| 27 |
+
- **Developed by:** [More Information Needed]
|
| 28 |
+
- **Funded by [optional]:** [More Information Needed]
|
| 29 |
+
- **Shared by [optional]:** [More Information Needed]
|
| 30 |
+
- **Model type:** [More Information Needed]
|
| 31 |
+
- **Language(s) (NLP):** [More Information Needed]
|
| 32 |
+
- **License:** [More Information Needed]
|
| 33 |
+
- **Finetuned from model [optional]:** [More Information Needed]
|
| 34 |
+
|
| 35 |
+
### Model Sources [optional]
|
| 36 |
+
|
| 37 |
+
<!-- Provide the basic links for the model. -->
|
| 38 |
+
|
| 39 |
+
- **Repository:** [More Information Needed]
|
| 40 |
+
- **Paper [optional]:** [More Information Needed]
|
| 41 |
+
- **Demo [optional]:** [More Information Needed]
|
| 42 |
+
|
| 43 |
+
## Uses
|
| 44 |
+
|
| 45 |
+
<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
|
| 46 |
+
|
| 47 |
+
### Direct Use
|
| 48 |
+
|
| 49 |
+
<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
|
| 50 |
+
|
| 51 |
+
[More Information Needed]
|
| 52 |
+
|
| 53 |
+
### Downstream Use [optional]
|
| 54 |
+
|
| 55 |
+
<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
|
| 56 |
+
|
| 57 |
+
[More Information Needed]
|
| 58 |
+
|
| 59 |
+
### Out-of-Scope Use
|
| 60 |
+
|
| 61 |
+
<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
|
| 62 |
+
|
| 63 |
+
[More Information Needed]
|
| 64 |
+
|
| 65 |
+
## Bias, Risks, and Limitations
|
| 66 |
+
|
| 67 |
+
<!-- This section is meant to convey both technical and sociotechnical limitations. -->
|
| 68 |
+
|
| 69 |
+
[More Information Needed]
|
| 70 |
+
|
| 71 |
+
### Recommendations
|
| 72 |
+
|
| 73 |
+
<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
|
| 74 |
+
|
| 75 |
+
Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
|
| 76 |
+
|
| 77 |
+
## How to Get Started with the Model
|
| 78 |
+
|
| 79 |
+
Use the code below to get started with the model.
|
| 80 |
+
|
| 81 |
+
[More Information Needed]
|
| 82 |
+
|
| 83 |
+
## Training Details
|
| 84 |
+
|
| 85 |
+
### Training Data
|
| 86 |
+
|
| 87 |
+
<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
|
| 88 |
+
|
| 89 |
+
[More Information Needed]
|
| 90 |
+
|
| 91 |
+
### Training Procedure
|
| 92 |
+
|
| 93 |
+
<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
|
| 94 |
+
|
| 95 |
+
#### Preprocessing [optional]
|
| 96 |
+
|
| 97 |
+
[More Information Needed]
|
| 98 |
+
|
| 99 |
+
|
| 100 |
+
#### Training Hyperparameters
|
| 101 |
+
|
| 102 |
+
- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
|
| 103 |
+
|
| 104 |
+
#### Speeds, Sizes, Times [optional]
|
| 105 |
+
|
| 106 |
+
<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
|
| 107 |
+
|
| 108 |
+
[More Information Needed]
|
| 109 |
+
|
| 110 |
+
## Evaluation
|
| 111 |
+
|
| 112 |
+
<!-- This section describes the evaluation protocols and provides the results. -->
|
| 113 |
+
|
| 114 |
+
### Testing Data, Factors & Metrics
|
| 115 |
+
|
| 116 |
+
#### Testing Data
|
| 117 |
+
|
| 118 |
+
<!-- This should link to a Dataset Card if possible. -->
|
| 119 |
+
|
| 120 |
+
[More Information Needed]
|
| 121 |
+
|
| 122 |
+
#### Factors
|
| 123 |
+
|
| 124 |
+
<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
|
| 125 |
+
|
| 126 |
+
[More Information Needed]
|
| 127 |
+
|
| 128 |
+
#### Metrics
|
| 129 |
+
|
| 130 |
+
<!-- These are the evaluation metrics being used, ideally with a description of why. -->
|
| 131 |
+
|
| 132 |
+
[More Information Needed]
|
| 133 |
+
|
| 134 |
+
### Results
|
| 135 |
+
|
| 136 |
+
[More Information Needed]
|
| 137 |
+
|
| 138 |
+
#### Summary
|
| 139 |
+
|
| 140 |
+
|
| 141 |
+
|
| 142 |
+
## Model Examination [optional]
|
| 143 |
+
|
| 144 |
+
<!-- Relevant interpretability work for the model goes here -->
|
| 145 |
+
|
| 146 |
+
[More Information Needed]
|
| 147 |
+
|
| 148 |
+
## Environmental Impact
|
| 149 |
+
|
| 150 |
+
<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
|
| 151 |
+
|
| 152 |
+
Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
|
| 153 |
+
|
| 154 |
+
- **Hardware Type:** [More Information Needed]
|
| 155 |
+
- **Hours used:** [More Information Needed]
|
| 156 |
+
- **Cloud Provider:** [More Information Needed]
|
| 157 |
+
- **Compute Region:** [More Information Needed]
|
| 158 |
+
- **Carbon Emitted:** [More Information Needed]
|
| 159 |
+
|
| 160 |
+
## Technical Specifications [optional]
|
| 161 |
+
|
| 162 |
+
### Model Architecture and Objective
|
| 163 |
+
|
| 164 |
+
[More Information Needed]
|
| 165 |
+
|
| 166 |
+
### Compute Infrastructure
|
| 167 |
+
|
| 168 |
+
[More Information Needed]
|
| 169 |
+
|
| 170 |
+
#### Hardware
|
| 171 |
+
|
| 172 |
+
[More Information Needed]
|
| 173 |
+
|
| 174 |
+
#### Software
|
| 175 |
+
|
| 176 |
+
[More Information Needed]
|
| 177 |
+
|
| 178 |
+
## Citation [optional]
|
| 179 |
+
|
| 180 |
+
<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
|
| 181 |
+
|
| 182 |
+
**BibTeX:**
|
| 183 |
+
|
| 184 |
+
[More Information Needed]
|
| 185 |
+
|
| 186 |
+
**APA:**
|
| 187 |
+
|
| 188 |
+
[More Information Needed]
|
| 189 |
+
|
| 190 |
+
## Glossary [optional]
|
| 191 |
+
|
| 192 |
+
<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
|
| 193 |
+
|
| 194 |
+
[More Information Needed]
|
| 195 |
+
|
| 196 |
+
## More Information [optional]
|
| 197 |
+
|
| 198 |
+
[More Information Needed]
|
| 199 |
+
|
| 200 |
+
## Model Card Authors [optional]
|
| 201 |
+
|
| 202 |
+
[More Information Needed]
|
| 203 |
+
|
| 204 |
+
## Model Card Contact
|
| 205 |
+
|
| 206 |
+
[More Information Needed]
|
| 207 |
+
### Framework versions
|
| 208 |
+
|
| 209 |
+
- PEFT 0.19.1
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/adapter_config.json
ADDED
|
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"alora_invocation_tokens": null,
|
| 3 |
+
"alpha_pattern": {},
|
| 4 |
+
"arrow_config": null,
|
| 5 |
+
"auto_mapping": null,
|
| 6 |
+
"base_model_name_or_path": "Qwen/Qwen3-14B-Base",
|
| 7 |
+
"bias": "none",
|
| 8 |
+
"corda_config": null,
|
| 9 |
+
"ensure_weight_tying": false,
|
| 10 |
+
"eva_config": null,
|
| 11 |
+
"exclude_modules": null,
|
| 12 |
+
"fan_in_fan_out": false,
|
| 13 |
+
"inference_mode": true,
|
| 14 |
+
"init_lora_weights": true,
|
| 15 |
+
"layer_replication": null,
|
| 16 |
+
"layers_pattern": null,
|
| 17 |
+
"layers_to_transform": null,
|
| 18 |
+
"loftq_config": {},
|
| 19 |
+
"lora_alpha": 128,
|
| 20 |
+
"lora_bias": false,
|
| 21 |
+
"lora_dropout": 0.010622890133962027,
|
| 22 |
+
"lora_ga_config": null,
|
| 23 |
+
"megatron_config": null,
|
| 24 |
+
"megatron_core": "megatron.core",
|
| 25 |
+
"modules_to_save": null,
|
| 26 |
+
"peft_type": "LORA",
|
| 27 |
+
"peft_version": "0.19.1",
|
| 28 |
+
"qalora_group_size": 16,
|
| 29 |
+
"r": 128,
|
| 30 |
+
"rank_pattern": {},
|
| 31 |
+
"revision": null,
|
| 32 |
+
"target_modules": [
|
| 33 |
+
"gate_proj",
|
| 34 |
+
"o_proj",
|
| 35 |
+
"v_proj",
|
| 36 |
+
"down_proj",
|
| 37 |
+
"up_proj",
|
| 38 |
+
"k_proj",
|
| 39 |
+
"q_proj"
|
| 40 |
+
],
|
| 41 |
+
"target_parameters": null,
|
| 42 |
+
"task_type": "CAUSAL_LM",
|
| 43 |
+
"trainable_token_indices": null,
|
| 44 |
+
"use_bdlora": null,
|
| 45 |
+
"use_dora": false,
|
| 46 |
+
"use_qalora": false,
|
| 47 |
+
"use_rslora": false
|
| 48 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/tokenizer_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": null,
|
| 5 |
+
"clean_up_tokenization_spaces": false,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>",
|
| 11 |
+
"<|object_ref_start|>",
|
| 12 |
+
"<|object_ref_end|>",
|
| 13 |
+
"<|box_start|>",
|
| 14 |
+
"<|box_end|>",
|
| 15 |
+
"<|quad_start|>",
|
| 16 |
+
"<|quad_end|>",
|
| 17 |
+
"<|vision_start|>",
|
| 18 |
+
"<|vision_end|>",
|
| 19 |
+
"<|vision_pad|>",
|
| 20 |
+
"<|image_pad|>",
|
| 21 |
+
"<|video_pad|>"
|
| 22 |
+
],
|
| 23 |
+
"is_local": false,
|
| 24 |
+
"model_max_length": 131072,
|
| 25 |
+
"pad_token": "<|endoftext|>",
|
| 26 |
+
"split_special_tokens": false,
|
| 27 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 28 |
+
"unk_token": null
|
| 29 |
+
}
|
DBCA_original_Estonian/Qwen3-14B-Base_original_features_structural_train_original_features_structural_test1/checkpoint-856/trainer_state.json
ADDED
|
@@ -0,0 +1,226 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 856,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy": 1.7805559730529785,
|
| 14 |
+
"epoch": 0.11682242990654206,
|
| 15 |
+
"grad_norm": 0.5128960013389587,
|
| 16 |
+
"learning_rate": 1.950005322230992e-06,
|
| 17 |
+
"loss": 1.770846405029297,
|
| 18 |
+
"mean_token_accuracy": 0.6305050283670426,
|
| 19 |
+
"num_tokens": 162248.0,
|
| 20 |
+
"step": 50
|
| 21 |
+
},
|
| 22 |
+
{
|
| 23 |
+
"entropy": 1.5725344836711883,
|
| 24 |
+
"epoch": 0.2336448598130841,
|
| 25 |
+
"grad_norm": 0.7059135437011719,
|
| 26 |
+
"learning_rate": 3.93980667144629e-06,
|
| 27 |
+
"loss": 1.5153414916992187,
|
| 28 |
+
"mean_token_accuracy": 0.6729821544885636,
|
| 29 |
+
"num_tokens": 327614.0,
|
| 30 |
+
"step": 100
|
| 31 |
+
},
|
| 32 |
+
{
|
| 33 |
+
"entropy": 1.0769569373130798,
|
| 34 |
+
"epoch": 0.35046728971962615,
|
| 35 |
+
"grad_norm": 0.6092284321784973,
|
| 36 |
+
"learning_rate": 5.9296080206615885e-06,
|
| 37 |
+
"loss": 1.0251461791992187,
|
| 38 |
+
"mean_token_accuracy": 0.737835128903389,
|
| 39 |
+
"num_tokens": 494582.0,
|
| 40 |
+
"step": 150
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"entropy": 0.8583791655302048,
|
| 44 |
+
"epoch": 0.4672897196261682,
|
| 45 |
+
"grad_norm": 0.5586332082748413,
|
| 46 |
+
"learning_rate": 7.919409369876886e-06,
|
| 47 |
+
"loss": 0.81265869140625,
|
| 48 |
+
"mean_token_accuracy": 0.7762657129764556,
|
| 49 |
+
"num_tokens": 653981.0,
|
| 50 |
+
"step": 200
|
| 51 |
+
},
|
| 52 |
+
{
|
| 53 |
+
"entropy": 0.7744105678796768,
|
| 54 |
+
"epoch": 0.5841121495327103,
|
| 55 |
+
"grad_norm": 0.4821721613407135,
|
| 56 |
+
"learning_rate": 9.909210719092184e-06,
|
| 57 |
+
"loss": 0.7364049530029297,
|
| 58 |
+
"mean_token_accuracy": 0.7918167436122894,
|
| 59 |
+
"num_tokens": 814840.0,
|
| 60 |
+
"step": 250
|
| 61 |
+
},
|
| 62 |
+
{
|
| 63 |
+
"entropy": 0.715560827255249,
|
| 64 |
+
"epoch": 0.7009345794392523,
|
| 65 |
+
"grad_norm": 0.6843860745429993,
|
| 66 |
+
"learning_rate": 1.1899012068307483e-05,
|
| 67 |
+
"loss": 0.6826614379882813,
|
| 68 |
+
"mean_token_accuracy": 0.8043146914243698,
|
| 69 |
+
"num_tokens": 979542.0,
|
| 70 |
+
"step": 300
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"entropy": 0.6893886953592301,
|
| 74 |
+
"epoch": 0.8177570093457944,
|
| 75 |
+
"grad_norm": 0.6543110013008118,
|
| 76 |
+
"learning_rate": 1.3888813417522781e-05,
|
| 77 |
+
"loss": 0.6608805847167969,
|
| 78 |
+
"mean_token_accuracy": 0.8083165866136551,
|
| 79 |
+
"num_tokens": 1147400.0,
|
| 80 |
+
"step": 350
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"entropy": 0.652973799109459,
|
| 84 |
+
"epoch": 0.9345794392523364,
|
| 85 |
+
"grad_norm": 0.7437635660171509,
|
| 86 |
+
"learning_rate": 1.587861476673808e-05,
|
| 87 |
+
"loss": 0.6218611907958984,
|
| 88 |
+
"mean_token_accuracy": 0.8167323243618011,
|
| 89 |
+
"num_tokens": 1310490.0,
|
| 90 |
+
"step": 400
|
| 91 |
+
},
|
| 92 |
+
{
|
| 93 |
+
"epoch": 1.0,
|
| 94 |
+
"eval_entropy": 0.8066210185552573,
|
| 95 |
+
"eval_loss": 0.7281543016433716,
|
| 96 |
+
"eval_mean_token_accuracy": 0.7858095281309896,
|
| 97 |
+
"eval_num_tokens": 1399670.0,
|
| 98 |
+
"eval_runtime": 46.0044,
|
| 99 |
+
"eval_samples_per_second": 26.758,
|
| 100 |
+
"eval_steps_per_second": 3.348,
|
| 101 |
+
"step": 428
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy": 0.6467276298999787,
|
| 105 |
+
"epoch": 1.0514018691588785,
|
| 106 |
+
"grad_norm": 0.626556396484375,
|
| 107 |
+
"learning_rate": 1.7031450502641085e-05,
|
| 108 |
+
"loss": 0.6161280441284179,
|
| 109 |
+
"mean_token_accuracy": 0.817004052400589,
|
| 110 |
+
"num_tokens": 1471726.0,
|
| 111 |
+
"step": 450
|
| 112 |
+
},
|
| 113 |
+
{
|
| 114 |
+
"entropy": 0.6262363213300705,
|
| 115 |
+
"epoch": 1.1682242990654206,
|
| 116 |
+
"grad_norm": 0.70875084400177,
|
| 117 |
+
"learning_rate": 1.7018425538355792e-05,
|
| 118 |
+
"loss": 0.5963106536865235,
|
| 119 |
+
"mean_token_accuracy": 0.8221335035562515,
|
| 120 |
+
"num_tokens": 1638060.0,
|
| 121 |
+
"step": 500
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"entropy": 0.6171189111471176,
|
| 125 |
+
"epoch": 1.2850467289719627,
|
| 126 |
+
"grad_norm": 0.6629440188407898,
|
| 127 |
+
"learning_rate": 1.6991264396738895e-05,
|
| 128 |
+
"loss": 0.5875393676757813,
|
| 129 |
+
"mean_token_accuracy": 0.8245152229070664,
|
| 130 |
+
"num_tokens": 1802005.0,
|
| 131 |
+
"step": 550
|
| 132 |
+
},
|
| 133 |
+
{
|
| 134 |
+
"entropy": 0.6083133199810982,
|
| 135 |
+
"epoch": 1.4018691588785046,
|
| 136 |
+
"grad_norm": 0.5385038256645203,
|
| 137 |
+
"learning_rate": 1.6950012237904817e-05,
|
| 138 |
+
"loss": 0.5768455505371094,
|
| 139 |
+
"mean_token_accuracy": 0.8271224808692932,
|
| 140 |
+
"num_tokens": 1969267.0,
|
| 141 |
+
"step": 600
|
| 142 |
+
},
|
| 143 |
+
{
|
| 144 |
+
"entropy": 0.6011673760414123,
|
| 145 |
+
"epoch": 1.5186915887850467,
|
| 146 |
+
"grad_norm": 0.7062859535217285,
|
| 147 |
+
"learning_rate": 1.6894737650731013e-05,
|
| 148 |
+
"loss": 0.5666856384277343,
|
| 149 |
+
"mean_token_accuracy": 0.829860600233078,
|
| 150 |
+
"num_tokens": 2134793.0,
|
| 151 |
+
"step": 650
|
| 152 |
+
},
|
| 153 |
+
{
|
| 154 |
+
"entropy": 0.5905318284034728,
|
| 155 |
+
"epoch": 1.6355140186915889,
|
| 156 |
+
"grad_norm": 0.646713137626648,
|
| 157 |
+
"learning_rate": 1.682553253881702e-05,
|
| 158 |
+
"loss": 0.560577392578125,
|
| 159 |
+
"mean_token_accuracy": 0.8313507026433945,
|
| 160 |
+
"num_tokens": 2300672.0,
|
| 161 |
+
"step": 700
|
| 162 |
+
},
|
| 163 |
+
{
|
| 164 |
+
"entropy": 0.5964298728108406,
|
| 165 |
+
"epoch": 1.7523364485981308,
|
| 166 |
+
"grad_norm": 0.6510505080223083,
|
| 167 |
+
"learning_rate": 1.674251196767876e-05,
|
| 168 |
+
"loss": 0.5606492614746094,
|
| 169 |
+
"mean_token_accuracy": 0.8313686531782151,
|
| 170 |
+
"num_tokens": 2459315.0,
|
| 171 |
+
"step": 750
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"entropy": 0.5872641482949257,
|
| 175 |
+
"epoch": 1.8691588785046729,
|
| 176 |
+
"grad_norm": 0.6211879849433899,
|
| 177 |
+
"learning_rate": 1.6645813973432182e-05,
|
| 178 |
+
"loss": 0.556594352722168,
|
| 179 |
+
"mean_token_accuracy": 0.8333250796794891,
|
| 180 |
+
"num_tokens": 2616878.0,
|
| 181 |
+
"step": 800
|
| 182 |
+
},
|
| 183 |
+
{
|
| 184 |
+
"entropy": 0.5889243066310883,
|
| 185 |
+
"epoch": 1.985981308411215,
|
| 186 |
+
"grad_norm": 0.6804038882255554,
|
| 187 |
+
"learning_rate": 1.6535599333284194e-05,
|
| 188 |
+
"loss": 0.5578879928588867,
|
| 189 |
+
"mean_token_accuracy": 0.831966199874878,
|
| 190 |
+
"num_tokens": 2778909.0,
|
| 191 |
+
"step": 850
|
| 192 |
+
},
|
| 193 |
+
{
|
| 194 |
+
"epoch": 2.0,
|
| 195 |
+
"eval_entropy": 0.7079034389613511,
|
| 196 |
+
"eval_loss": 0.6832069158554077,
|
| 197 |
+
"eval_mean_token_accuracy": 0.8022074165282311,
|
| 198 |
+
"eval_num_tokens": 2799340.0,
|
| 199 |
+
"eval_runtime": 46.0398,
|
| 200 |
+
"eval_samples_per_second": 26.738,
|
| 201 |
+
"eval_steps_per_second": 3.345,
|
| 202 |
+
"step": 856
|
| 203 |
+
}
|
| 204 |
+
],
|
| 205 |
+
"logging_steps": 50,
|
| 206 |
+
"max_steps": 4280,
|
| 207 |
+
"num_input_tokens_seen": 0,
|
| 208 |
+
"num_train_epochs": 10,
|
| 209 |
+
"save_steps": 500,
|
| 210 |
+
"stateful_callbacks": {
|
| 211 |
+
"TrainerControl": {
|
| 212 |
+
"args": {
|
| 213 |
+
"should_epoch_stop": false,
|
| 214 |
+
"should_evaluate": false,
|
| 215 |
+
"should_log": false,
|
| 216 |
+
"should_save": true,
|
| 217 |
+
"should_training_stop": false
|
| 218 |
+
},
|
| 219 |
+
"attributes": {}
|
| 220 |
+
}
|
| 221 |
+
},
|
| 222 |
+
"total_flos": 5.278059926931456e+17,
|
| 223 |
+
"train_batch_size": 8,
|
| 224 |
+
"trial_name": null,
|
| 225 |
+
"trial_params": null
|
| 226 |
+
}
|