Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +87 -0
- config.json +68 -0
- generation_config.json +12 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +407 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +239 -0
- trainer_state.json +2266 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,87 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{%- else %}
|
| 85 |
+
{{- '<think>\n\n' }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,68 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"dtype": "bfloat16",
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"head_dim": 128,
|
| 10 |
+
"hidden_act": "silu",
|
| 11 |
+
"hidden_size": 4096,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 12288,
|
| 14 |
+
"layer_types": [
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"full_attention",
|
| 42 |
+
"full_attention",
|
| 43 |
+
"full_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"full_attention",
|
| 46 |
+
"full_attention",
|
| 47 |
+
"full_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"full_attention",
|
| 50 |
+
"full_attention"
|
| 51 |
+
],
|
| 52 |
+
"max_position_embeddings": 40960,
|
| 53 |
+
"max_window_layers": 36,
|
| 54 |
+
"model_type": "qwen3",
|
| 55 |
+
"num_attention_heads": 32,
|
| 56 |
+
"num_hidden_layers": 36,
|
| 57 |
+
"num_key_value_heads": 8,
|
| 58 |
+
"pad_token_id": 151643,
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_scaling": null,
|
| 61 |
+
"rope_theta": 1000000,
|
| 62 |
+
"sliding_window": null,
|
| 63 |
+
"tie_word_embeddings": false,
|
| 64 |
+
"transformers_version": "4.57.3",
|
| 65 |
+
"use_cache": false,
|
| 66 |
+
"use_sliding_window": false,
|
| 67 |
+
"vocab_size": 151936
|
| 68 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151643
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 151643,
|
| 8 |
+
"temperature": 0.6,
|
| 9 |
+
"top_k": 20,
|
| 10 |
+
"top_p": 0.95,
|
| 11 |
+
"transformers_version": "4.57.3"
|
| 12 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eb8718c7e3d2e6bc68b3ff4423b039121f4d493c8a4e3e9ee5d6e587a60c4ad1
|
| 3 |
+
size 4902257696
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa518de503f8fb7e418b0ed8e4fb7f33211794386e6bacaa8fb3857f26e90886
|
| 3 |
+
size 4915960368
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d818da7f7e26608610c9756de52c84d156330843349f50cd50be60ee75e257e4
|
| 3 |
+
size 4983068496
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cff78bb628dc25dec54d4a01dd2cd13534edc35c9c544a6d93ff4a19e94cdcdc
|
| 3 |
+
size 1580230264
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,407 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 8190735360,
|
| 4 |
+
"total_size": 16381470720
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 131 |
+
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 132 |
+
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 134 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 135 |
+
"model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 153 |
+
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 154 |
+
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 155 |
+
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 156 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 157 |
+
"model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 158 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 159 |
+
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 160 |
+
"model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 161 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 162 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 163 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 164 |
+
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 165 |
+
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 166 |
+
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 167 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 168 |
+
"model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 169 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 170 |
+
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 171 |
+
"model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 172 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 173 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 174 |
+
"model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 180 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 181 |
+
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 182 |
+
"model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 183 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 184 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 185 |
+
"model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 296 |
+
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 297 |
+
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 298 |
+
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 299 |
+
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 300 |
+
"model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 307 |
+
"model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 308 |
+
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 309 |
+
"model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 310 |
+
"model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 311 |
+
"model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 312 |
+
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 313 |
+
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 314 |
+
"model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 315 |
+
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 316 |
+
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 317 |
+
"model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 318 |
+
"model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 319 |
+
"model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 320 |
+
"model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 321 |
+
"model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 322 |
+
"model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 323 |
+
"model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 324 |
+
"model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 325 |
+
"model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 326 |
+
"model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 327 |
+
"model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 328 |
+
"model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 335 |
+
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 338 |
+
"model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 339 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 362 |
+
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 363 |
+
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 366 |
+
"model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 373 |
+
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 374 |
+
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 375 |
+
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 376 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 377 |
+
"model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 378 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 379 |
+
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 380 |
+
"model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 381 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 382 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 383 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 384 |
+
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 385 |
+
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 386 |
+
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 387 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 388 |
+
"model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 389 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 390 |
+
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 391 |
+
"model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 392 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 393 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 394 |
+
"model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 397 |
+
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 400 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 401 |
+
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 402 |
+
"model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 403 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 404 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 405 |
+
"model.norm.weight": "model-00004-of-00004.safetensors"
|
| 406 |
+
}
|
| 407 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,239 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"split_special_tokens": false,
|
| 237 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 238 |
+
"unk_token": null
|
| 239 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2266 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 2.956175298804781,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 186,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.01593625498007968,
|
| 14 |
+
"grad_norm": 4.5625,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.4053,
|
| 17 |
+
"memory/device_reserved (GiB)": 61.34,
|
| 18 |
+
"memory/max_active (GiB)": 49.6,
|
| 19 |
+
"memory/max_allocated (GiB)": 49.6,
|
| 20 |
+
"step": 1,
|
| 21 |
+
"tokens_per_second_per_gpu": 4706.79,
|
| 22 |
+
"total_tokens": 180518
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"epoch": 0.03187250996015936,
|
| 26 |
+
"grad_norm": 4.34375,
|
| 27 |
+
"learning_rate": 1.111111111111111e-06,
|
| 28 |
+
"loss": 1.3369,
|
| 29 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 30 |
+
"memory/max_active (GiB)": 64.91,
|
| 31 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 32 |
+
"step": 2,
|
| 33 |
+
"tokens_per_second_per_gpu": 5826.72,
|
| 34 |
+
"total_tokens": 363757
|
| 35 |
+
},
|
| 36 |
+
{
|
| 37 |
+
"epoch": 0.04780876494023904,
|
| 38 |
+
"grad_norm": 4.15625,
|
| 39 |
+
"learning_rate": 2.222222222222222e-06,
|
| 40 |
+
"loss": 1.3623,
|
| 41 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 42 |
+
"memory/max_active (GiB)": 64.91,
|
| 43 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 44 |
+
"step": 3,
|
| 45 |
+
"tokens_per_second_per_gpu": 5939.96,
|
| 46 |
+
"total_tokens": 558043
|
| 47 |
+
},
|
| 48 |
+
{
|
| 49 |
+
"epoch": 0.06374501992031872,
|
| 50 |
+
"grad_norm": 4.34375,
|
| 51 |
+
"learning_rate": 3.3333333333333333e-06,
|
| 52 |
+
"loss": 1.3643,
|
| 53 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 54 |
+
"memory/max_active (GiB)": 64.91,
|
| 55 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 56 |
+
"step": 4,
|
| 57 |
+
"tokens_per_second_per_gpu": 5941.47,
|
| 58 |
+
"total_tokens": 743276
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"epoch": 0.0796812749003984,
|
| 62 |
+
"grad_norm": 3.90625,
|
| 63 |
+
"learning_rate": 4.444444444444444e-06,
|
| 64 |
+
"loss": 1.2998,
|
| 65 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 66 |
+
"memory/max_active (GiB)": 64.91,
|
| 67 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 68 |
+
"step": 5,
|
| 69 |
+
"tokens_per_second_per_gpu": 5380.38,
|
| 70 |
+
"total_tokens": 929761
|
| 71 |
+
},
|
| 72 |
+
{
|
| 73 |
+
"epoch": 0.09561752988047809,
|
| 74 |
+
"grad_norm": 3.546875,
|
| 75 |
+
"learning_rate": 5.555555555555557e-06,
|
| 76 |
+
"loss": 1.3018,
|
| 77 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 78 |
+
"memory/max_active (GiB)": 64.91,
|
| 79 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 80 |
+
"step": 6,
|
| 81 |
+
"tokens_per_second_per_gpu": 5949.69,
|
| 82 |
+
"total_tokens": 1118316
|
| 83 |
+
},
|
| 84 |
+
{
|
| 85 |
+
"epoch": 0.11155378486055777,
|
| 86 |
+
"grad_norm": 3.171875,
|
| 87 |
+
"learning_rate": 6.666666666666667e-06,
|
| 88 |
+
"loss": 1.2793,
|
| 89 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 90 |
+
"memory/max_active (GiB)": 64.91,
|
| 91 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 92 |
+
"step": 7,
|
| 93 |
+
"tokens_per_second_per_gpu": 5785.23,
|
| 94 |
+
"total_tokens": 1301615
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.12749003984063745,
|
| 98 |
+
"grad_norm": 2.96875,
|
| 99 |
+
"learning_rate": 7.77777777777778e-06,
|
| 100 |
+
"loss": 1.3115,
|
| 101 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 102 |
+
"memory/max_active (GiB)": 64.91,
|
| 103 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 104 |
+
"step": 8,
|
| 105 |
+
"tokens_per_second_per_gpu": 5941.21,
|
| 106 |
+
"total_tokens": 1490474
|
| 107 |
+
},
|
| 108 |
+
{
|
| 109 |
+
"epoch": 0.14342629482071714,
|
| 110 |
+
"grad_norm": 2.296875,
|
| 111 |
+
"learning_rate": 8.888888888888888e-06,
|
| 112 |
+
"loss": 1.2588,
|
| 113 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 114 |
+
"memory/max_active (GiB)": 64.91,
|
| 115 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 116 |
+
"step": 9,
|
| 117 |
+
"tokens_per_second_per_gpu": 5534.49,
|
| 118 |
+
"total_tokens": 1667576
|
| 119 |
+
},
|
| 120 |
+
{
|
| 121 |
+
"epoch": 0.1593625498007968,
|
| 122 |
+
"grad_norm": 1.5625,
|
| 123 |
+
"learning_rate": 1e-05,
|
| 124 |
+
"loss": 1.1992,
|
| 125 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 126 |
+
"memory/max_active (GiB)": 64.91,
|
| 127 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 128 |
+
"step": 10,
|
| 129 |
+
"tokens_per_second_per_gpu": 6154.87,
|
| 130 |
+
"total_tokens": 1857807
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"epoch": 0.1752988047808765,
|
| 134 |
+
"grad_norm": 1.0703125,
|
| 135 |
+
"learning_rate": 1.1111111111111113e-05,
|
| 136 |
+
"loss": 1.1436,
|
| 137 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 138 |
+
"memory/max_active (GiB)": 64.91,
|
| 139 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 140 |
+
"step": 11,
|
| 141 |
+
"tokens_per_second_per_gpu": 5715.6,
|
| 142 |
+
"total_tokens": 2041489
|
| 143 |
+
},
|
| 144 |
+
{
|
| 145 |
+
"epoch": 0.19123505976095617,
|
| 146 |
+
"grad_norm": 0.9765625,
|
| 147 |
+
"learning_rate": 1.2222222222222224e-05,
|
| 148 |
+
"loss": 1.2402,
|
| 149 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 150 |
+
"memory/max_active (GiB)": 64.91,
|
| 151 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 152 |
+
"step": 12,
|
| 153 |
+
"tokens_per_second_per_gpu": 5749.37,
|
| 154 |
+
"total_tokens": 2216014
|
| 155 |
+
},
|
| 156 |
+
{
|
| 157 |
+
"epoch": 0.20717131474103587,
|
| 158 |
+
"grad_norm": 0.9609375,
|
| 159 |
+
"learning_rate": 1.3333333333333333e-05,
|
| 160 |
+
"loss": 1.2051,
|
| 161 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 162 |
+
"memory/max_active (GiB)": 64.91,
|
| 163 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 164 |
+
"step": 13,
|
| 165 |
+
"tokens_per_second_per_gpu": 5748.94,
|
| 166 |
+
"total_tokens": 2397131
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"epoch": 0.22310756972111553,
|
| 170 |
+
"grad_norm": 0.921875,
|
| 171 |
+
"learning_rate": 1.4444444444444446e-05,
|
| 172 |
+
"loss": 1.1211,
|
| 173 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 174 |
+
"memory/max_active (GiB)": 64.91,
|
| 175 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 176 |
+
"step": 14,
|
| 177 |
+
"tokens_per_second_per_gpu": 6171.1,
|
| 178 |
+
"total_tokens": 2590472
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.23904382470119523,
|
| 182 |
+
"grad_norm": 0.8984375,
|
| 183 |
+
"learning_rate": 1.555555555555556e-05,
|
| 184 |
+
"loss": 1.1777,
|
| 185 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 186 |
+
"memory/max_active (GiB)": 64.91,
|
| 187 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 188 |
+
"step": 15,
|
| 189 |
+
"tokens_per_second_per_gpu": 6160.5,
|
| 190 |
+
"total_tokens": 2780711
|
| 191 |
+
},
|
| 192 |
+
{
|
| 193 |
+
"epoch": 0.2549800796812749,
|
| 194 |
+
"grad_norm": 0.80078125,
|
| 195 |
+
"learning_rate": 1.6666666666666667e-05,
|
| 196 |
+
"loss": 1.1025,
|
| 197 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 198 |
+
"memory/max_active (GiB)": 64.91,
|
| 199 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 200 |
+
"step": 16,
|
| 201 |
+
"tokens_per_second_per_gpu": 5706.58,
|
| 202 |
+
"total_tokens": 2968588
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"epoch": 0.27091633466135456,
|
| 206 |
+
"grad_norm": 0.65234375,
|
| 207 |
+
"learning_rate": 1.7777777777777777e-05,
|
| 208 |
+
"loss": 1.2041,
|
| 209 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 210 |
+
"memory/max_active (GiB)": 64.91,
|
| 211 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 212 |
+
"step": 17,
|
| 213 |
+
"tokens_per_second_per_gpu": 5569.19,
|
| 214 |
+
"total_tokens": 3148691
|
| 215 |
+
},
|
| 216 |
+
{
|
| 217 |
+
"epoch": 0.2868525896414343,
|
| 218 |
+
"grad_norm": 0.59765625,
|
| 219 |
+
"learning_rate": 1.888888888888889e-05,
|
| 220 |
+
"loss": 1.168,
|
| 221 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 222 |
+
"memory/max_active (GiB)": 64.91,
|
| 223 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 224 |
+
"step": 18,
|
| 225 |
+
"tokens_per_second_per_gpu": 5894.91,
|
| 226 |
+
"total_tokens": 3332398
|
| 227 |
+
},
|
| 228 |
+
{
|
| 229 |
+
"epoch": 0.30278884462151395,
|
| 230 |
+
"grad_norm": 0.5625,
|
| 231 |
+
"learning_rate": 2e-05,
|
| 232 |
+
"loss": 1.0977,
|
| 233 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 234 |
+
"memory/max_active (GiB)": 64.91,
|
| 235 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 236 |
+
"step": 19,
|
| 237 |
+
"tokens_per_second_per_gpu": 6092.09,
|
| 238 |
+
"total_tokens": 3526610
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"epoch": 0.3187250996015936,
|
| 242 |
+
"grad_norm": 0.54296875,
|
| 243 |
+
"learning_rate": 1.9998251609127465e-05,
|
| 244 |
+
"loss": 1.1372,
|
| 245 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 246 |
+
"memory/max_active (GiB)": 64.91,
|
| 247 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 248 |
+
"step": 20,
|
| 249 |
+
"tokens_per_second_per_gpu": 5971.19,
|
| 250 |
+
"total_tokens": 3711042
|
| 251 |
+
},
|
| 252 |
+
{
|
| 253 |
+
"epoch": 0.3346613545816733,
|
| 254 |
+
"grad_norm": 0.5078125,
|
| 255 |
+
"learning_rate": 1.9993007047883988e-05,
|
| 256 |
+
"loss": 1.0659,
|
| 257 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 258 |
+
"memory/max_active (GiB)": 64.91,
|
| 259 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 260 |
+
"step": 21,
|
| 261 |
+
"tokens_per_second_per_gpu": 5750.71,
|
| 262 |
+
"total_tokens": 3890841
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.350597609561753,
|
| 266 |
+
"grad_norm": 0.50390625,
|
| 267 |
+
"learning_rate": 1.998426815017817e-05,
|
| 268 |
+
"loss": 1.124,
|
| 269 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 270 |
+
"memory/max_active (GiB)": 64.91,
|
| 271 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 272 |
+
"step": 22,
|
| 273 |
+
"tokens_per_second_per_gpu": 5968.21,
|
| 274 |
+
"total_tokens": 4074024
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"epoch": 0.3665338645418327,
|
| 278 |
+
"grad_norm": 0.4609375,
|
| 279 |
+
"learning_rate": 1.9972037971811802e-05,
|
| 280 |
+
"loss": 1.064,
|
| 281 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 282 |
+
"memory/max_active (GiB)": 64.91,
|
| 283 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 284 |
+
"step": 23,
|
| 285 |
+
"tokens_per_second_per_gpu": 5672.93,
|
| 286 |
+
"total_tokens": 4261426
|
| 287 |
+
},
|
| 288 |
+
{
|
| 289 |
+
"epoch": 0.38247011952191234,
|
| 290 |
+
"grad_norm": 0.458984375,
|
| 291 |
+
"learning_rate": 1.9956320789411338e-05,
|
| 292 |
+
"loss": 1.0977,
|
| 293 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 294 |
+
"memory/max_active (GiB)": 64.91,
|
| 295 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 296 |
+
"step": 24,
|
| 297 |
+
"tokens_per_second_per_gpu": 5947.63,
|
| 298 |
+
"total_tokens": 4448221
|
| 299 |
+
},
|
| 300 |
+
{
|
| 301 |
+
"epoch": 0.398406374501992,
|
| 302 |
+
"grad_norm": 0.400390625,
|
| 303 |
+
"learning_rate": 1.9937122098932428e-05,
|
| 304 |
+
"loss": 0.9438,
|
| 305 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 306 |
+
"memory/max_active (GiB)": 64.91,
|
| 307 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 308 |
+
"step": 25,
|
| 309 |
+
"tokens_per_second_per_gpu": 5830.3,
|
| 310 |
+
"total_tokens": 4643418
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"epoch": 0.41434262948207173,
|
| 314 |
+
"grad_norm": 0.451171875,
|
| 315 |
+
"learning_rate": 1.9914448613738107e-05,
|
| 316 |
+
"loss": 1.0786,
|
| 317 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 318 |
+
"memory/max_active (GiB)": 64.91,
|
| 319 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 320 |
+
"step": 26,
|
| 321 |
+
"tokens_per_second_per_gpu": 5753.23,
|
| 322 |
+
"total_tokens": 4826564
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"epoch": 0.4302788844621514,
|
| 326 |
+
"grad_norm": 0.41796875,
|
| 327 |
+
"learning_rate": 1.9888308262251286e-05,
|
| 328 |
+
"loss": 1.1084,
|
| 329 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 330 |
+
"memory/max_active (GiB)": 64.91,
|
| 331 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 332 |
+
"step": 27,
|
| 333 |
+
"tokens_per_second_per_gpu": 5786.21,
|
| 334 |
+
"total_tokens": 5008617
|
| 335 |
+
},
|
| 336 |
+
{
|
| 337 |
+
"epoch": 0.44621513944223107,
|
| 338 |
+
"grad_norm": 0.392578125,
|
| 339 |
+
"learning_rate": 1.985871018518236e-05,
|
| 340 |
+
"loss": 1.0488,
|
| 341 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 342 |
+
"memory/max_active (GiB)": 64.91,
|
| 343 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 344 |
+
"step": 28,
|
| 345 |
+
"tokens_per_second_per_gpu": 5935.98,
|
| 346 |
+
"total_tokens": 5194550
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.46215139442231074,
|
| 350 |
+
"grad_norm": 0.37109375,
|
| 351 |
+
"learning_rate": 1.9825664732332886e-05,
|
| 352 |
+
"loss": 1.0894,
|
| 353 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 354 |
+
"memory/max_active (GiB)": 64.91,
|
| 355 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 356 |
+
"step": 29,
|
| 357 |
+
"tokens_per_second_per_gpu": 5927.93,
|
| 358 |
+
"total_tokens": 5380376
|
| 359 |
+
},
|
| 360 |
+
{
|
| 361 |
+
"epoch": 0.47808764940239046,
|
| 362 |
+
"grad_norm": 0.35546875,
|
| 363 |
+
"learning_rate": 1.9789183458976485e-05,
|
| 364 |
+
"loss": 1.0869,
|
| 365 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 366 |
+
"memory/max_active (GiB)": 64.91,
|
| 367 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 368 |
+
"step": 30,
|
| 369 |
+
"tokens_per_second_per_gpu": 6097.05,
|
| 370 |
+
"total_tokens": 5567310
|
| 371 |
+
},
|
| 372 |
+
{
|
| 373 |
+
"epoch": 0.4940239043824701,
|
| 374 |
+
"grad_norm": 0.37109375,
|
| 375 |
+
"learning_rate": 1.9749279121818235e-05,
|
| 376 |
+
"loss": 1.0181,
|
| 377 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 378 |
+
"memory/max_active (GiB)": 64.91,
|
| 379 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 380 |
+
"step": 31,
|
| 381 |
+
"tokens_per_second_per_gpu": 6055.18,
|
| 382 |
+
"total_tokens": 5750982
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.5099601593625498,
|
| 386 |
+
"grad_norm": 0.380859375,
|
| 387 |
+
"learning_rate": 1.970596567453391e-05,
|
| 388 |
+
"loss": 1.0552,
|
| 389 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 390 |
+
"memory/max_active (GiB)": 64.91,
|
| 391 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 392 |
+
"step": 32,
|
| 393 |
+
"tokens_per_second_per_gpu": 6008.39,
|
| 394 |
+
"total_tokens": 5937332
|
| 395 |
+
},
|
| 396 |
+
{
|
| 397 |
+
"epoch": 0.5258964143426295,
|
| 398 |
+
"grad_norm": 0.376953125,
|
| 399 |
+
"learning_rate": 1.9659258262890683e-05,
|
| 400 |
+
"loss": 1.0439,
|
| 401 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 402 |
+
"memory/max_active (GiB)": 64.91,
|
| 403 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 404 |
+
"step": 33,
|
| 405 |
+
"tokens_per_second_per_gpu": 6030.07,
|
| 406 |
+
"total_tokens": 6120851
|
| 407 |
+
},
|
| 408 |
+
{
|
| 409 |
+
"epoch": 0.5418326693227091,
|
| 410 |
+
"grad_norm": 0.369140625,
|
| 411 |
+
"learning_rate": 1.9609173219450998e-05,
|
| 412 |
+
"loss": 1.0835,
|
| 413 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 414 |
+
"memory/max_active (GiB)": 64.91,
|
| 415 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 416 |
+
"step": 34,
|
| 417 |
+
"tokens_per_second_per_gpu": 5726.88,
|
| 418 |
+
"total_tokens": 6297402
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"epoch": 0.5577689243027888,
|
| 422 |
+
"grad_norm": 0.396484375,
|
| 423 |
+
"learning_rate": 1.955572805786141e-05,
|
| 424 |
+
"loss": 1.1074,
|
| 425 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 426 |
+
"memory/max_active (GiB)": 64.91,
|
| 427 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 428 |
+
"step": 35,
|
| 429 |
+
"tokens_per_second_per_gpu": 5816.12,
|
| 430 |
+
"total_tokens": 6480316
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5737051792828686,
|
| 434 |
+
"grad_norm": 0.357421875,
|
| 435 |
+
"learning_rate": 1.9498941466728462e-05,
|
| 436 |
+
"loss": 1.0391,
|
| 437 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 438 |
+
"memory/max_active (GiB)": 64.91,
|
| 439 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 440 |
+
"step": 36,
|
| 441 |
+
"tokens_per_second_per_gpu": 5765.66,
|
| 442 |
+
"total_tokens": 6665052
|
| 443 |
+
},
|
| 444 |
+
{
|
| 445 |
+
"epoch": 0.5896414342629482,
|
| 446 |
+
"grad_norm": 0.345703125,
|
| 447 |
+
"learning_rate": 1.9438833303083677e-05,
|
| 448 |
+
"loss": 1.0371,
|
| 449 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 450 |
+
"memory/max_active (GiB)": 64.91,
|
| 451 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 452 |
+
"step": 37,
|
| 453 |
+
"tokens_per_second_per_gpu": 5749.09,
|
| 454 |
+
"total_tokens": 6849283
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"epoch": 0.6055776892430279,
|
| 458 |
+
"grad_norm": 0.34375,
|
| 459 |
+
"learning_rate": 1.9375424585439994e-05,
|
| 460 |
+
"loss": 1.0503,
|
| 461 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 462 |
+
"memory/max_active (GiB)": 64.91,
|
| 463 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 464 |
+
"step": 38,
|
| 465 |
+
"tokens_per_second_per_gpu": 5927.3,
|
| 466 |
+
"total_tokens": 7032513
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.6215139442231076,
|
| 470 |
+
"grad_norm": 0.330078125,
|
| 471 |
+
"learning_rate": 1.9308737486442045e-05,
|
| 472 |
+
"loss": 1.0479,
|
| 473 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 474 |
+
"memory/max_active (GiB)": 64.91,
|
| 475 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 476 |
+
"step": 39,
|
| 477 |
+
"tokens_per_second_per_gpu": 5905.92,
|
| 478 |
+
"total_tokens": 7214561
|
| 479 |
+
},
|
| 480 |
+
{
|
| 481 |
+
"epoch": 0.6374501992031872,
|
| 482 |
+
"grad_norm": 0.3359375,
|
| 483 |
+
"learning_rate": 1.9238795325112867e-05,
|
| 484 |
+
"loss": 1.0098,
|
| 485 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 486 |
+
"memory/max_active (GiB)": 64.91,
|
| 487 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 488 |
+
"step": 40,
|
| 489 |
+
"tokens_per_second_per_gpu": 5853.3,
|
| 490 |
+
"total_tokens": 7400854
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"epoch": 0.6533864541832669,
|
| 494 |
+
"grad_norm": 0.36328125,
|
| 495 |
+
"learning_rate": 1.9165622558699763e-05,
|
| 496 |
+
"loss": 1.106,
|
| 497 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 498 |
+
"memory/max_active (GiB)": 64.91,
|
| 499 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 500 |
+
"step": 41,
|
| 501 |
+
"tokens_per_second_per_gpu": 5556.45,
|
| 502 |
+
"total_tokens": 7577263
|
| 503 |
+
},
|
| 504 |
+
{
|
| 505 |
+
"epoch": 0.6693227091633466,
|
| 506 |
+
"grad_norm": 0.396484375,
|
| 507 |
+
"learning_rate": 1.908924477412211e-05,
|
| 508 |
+
"loss": 1.0498,
|
| 509 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 510 |
+
"memory/max_active (GiB)": 64.91,
|
| 511 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 512 |
+
"step": 42,
|
| 513 |
+
"tokens_per_second_per_gpu": 5928.26,
|
| 514 |
+
"total_tokens": 7763586
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6852589641434262,
|
| 518 |
+
"grad_norm": 0.32421875,
|
| 519 |
+
"learning_rate": 1.900968867902419e-05,
|
| 520 |
+
"loss": 1.0171,
|
| 521 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 522 |
+
"memory/max_active (GiB)": 64.91,
|
| 523 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 524 |
+
"step": 43,
|
| 525 |
+
"tokens_per_second_per_gpu": 6102.36,
|
| 526 |
+
"total_tokens": 7953595
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"epoch": 0.701195219123506,
|
| 530 |
+
"grad_norm": 0.36328125,
|
| 531 |
+
"learning_rate": 1.8926982092436117e-05,
|
| 532 |
+
"loss": 1.0688,
|
| 533 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 534 |
+
"memory/max_active (GiB)": 64.91,
|
| 535 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 536 |
+
"step": 44,
|
| 537 |
+
"tokens_per_second_per_gpu": 6058.46,
|
| 538 |
+
"total_tokens": 8135608
|
| 539 |
+
},
|
| 540 |
+
{
|
| 541 |
+
"epoch": 0.7171314741035857,
|
| 542 |
+
"grad_norm": 0.359375,
|
| 543 |
+
"learning_rate": 1.8841153935046098e-05,
|
| 544 |
+
"loss": 0.978,
|
| 545 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 546 |
+
"memory/max_active (GiB)": 64.91,
|
| 547 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 548 |
+
"step": 45,
|
| 549 |
+
"tokens_per_second_per_gpu": 5806.45,
|
| 550 |
+
"total_tokens": 8328038
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.7330677290836654,
|
| 554 |
+
"grad_norm": 0.333984375,
|
| 555 |
+
"learning_rate": 1.8752234219087538e-05,
|
| 556 |
+
"loss": 1.0435,
|
| 557 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 558 |
+
"memory/max_active (GiB)": 64.91,
|
| 559 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 560 |
+
"step": 46,
|
| 561 |
+
"tokens_per_second_per_gpu": 5940.85,
|
| 562 |
+
"total_tokens": 8517629
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"epoch": 0.749003984063745,
|
| 566 |
+
"grad_norm": 0.400390625,
|
| 567 |
+
"learning_rate": 1.866025403784439e-05,
|
| 568 |
+
"loss": 1.0317,
|
| 569 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 570 |
+
"memory/max_active (GiB)": 64.91,
|
| 571 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 572 |
+
"step": 47,
|
| 573 |
+
"tokens_per_second_per_gpu": 5929.8,
|
| 574 |
+
"total_tokens": 8700619
|
| 575 |
+
},
|
| 576 |
+
{
|
| 577 |
+
"epoch": 0.7649402390438247,
|
| 578 |
+
"grad_norm": 0.328125,
|
| 579 |
+
"learning_rate": 1.8565245554778516e-05,
|
| 580 |
+
"loss": 0.9819,
|
| 581 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 582 |
+
"memory/max_active (GiB)": 64.91,
|
| 583 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 584 |
+
"step": 48,
|
| 585 |
+
"tokens_per_second_per_gpu": 5991.89,
|
| 586 |
+
"total_tokens": 8886726
|
| 587 |
+
},
|
| 588 |
+
{
|
| 589 |
+
"epoch": 0.7808764940239044,
|
| 590 |
+
"grad_norm": 0.34765625,
|
| 591 |
+
"learning_rate": 1.8467241992282842e-05,
|
| 592 |
+
"loss": 1.0396,
|
| 593 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 594 |
+
"memory/max_active (GiB)": 64.91,
|
| 595 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 596 |
+
"step": 49,
|
| 597 |
+
"tokens_per_second_per_gpu": 5941.59,
|
| 598 |
+
"total_tokens": 9074210
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.796812749003984,
|
| 602 |
+
"grad_norm": 0.345703125,
|
| 603 |
+
"learning_rate": 1.83662776200642e-05,
|
| 604 |
+
"loss": 1.0703,
|
| 605 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 606 |
+
"memory/max_active (GiB)": 64.91,
|
| 607 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 608 |
+
"step": 50,
|
| 609 |
+
"tokens_per_second_per_gpu": 5856.71,
|
| 610 |
+
"total_tokens": 9253264
|
| 611 |
+
},
|
| 612 |
+
{
|
| 613 |
+
"epoch": 0.8127490039840638,
|
| 614 |
+
"grad_norm": 0.33203125,
|
| 615 |
+
"learning_rate": 1.826238774315995e-05,
|
| 616 |
+
"loss": 1.0078,
|
| 617 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 618 |
+
"memory/max_active (GiB)": 64.91,
|
| 619 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 620 |
+
"step": 51,
|
| 621 |
+
"tokens_per_second_per_gpu": 5883.97,
|
| 622 |
+
"total_tokens": 9437019
|
| 623 |
+
},
|
| 624 |
+
{
|
| 625 |
+
"epoch": 0.8286852589641435,
|
| 626 |
+
"grad_norm": 0.326171875,
|
| 627 |
+
"learning_rate": 1.8155608689592604e-05,
|
| 628 |
+
"loss": 1.0352,
|
| 629 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 630 |
+
"memory/max_active (GiB)": 64.91,
|
| 631 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 632 |
+
"step": 52,
|
| 633 |
+
"tokens_per_second_per_gpu": 6284.45,
|
| 634 |
+
"total_tokens": 9624777
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.8446215139442231,
|
| 638 |
+
"grad_norm": 0.34375,
|
| 639 |
+
"learning_rate": 1.8045977797666685e-05,
|
| 640 |
+
"loss": 1.0015,
|
| 641 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 642 |
+
"memory/max_active (GiB)": 64.91,
|
| 643 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 644 |
+
"step": 53,
|
| 645 |
+
"tokens_per_second_per_gpu": 6227.78,
|
| 646 |
+
"total_tokens": 9816093
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"epoch": 0.8605577689243028,
|
| 650 |
+
"grad_norm": 0.32421875,
|
| 651 |
+
"learning_rate": 1.7933533402912354e-05,
|
| 652 |
+
"loss": 1.0205,
|
| 653 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 654 |
+
"memory/max_active (GiB)": 64.91,
|
| 655 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 656 |
+
"step": 54,
|
| 657 |
+
"tokens_per_second_per_gpu": 5562.75,
|
| 658 |
+
"total_tokens": 10003875
|
| 659 |
+
},
|
| 660 |
+
{
|
| 661 |
+
"epoch": 0.8764940239043825,
|
| 662 |
+
"grad_norm": 0.3125,
|
| 663 |
+
"learning_rate": 1.78183148246803e-05,
|
| 664 |
+
"loss": 0.9985,
|
| 665 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 666 |
+
"memory/max_active (GiB)": 64.91,
|
| 667 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 668 |
+
"step": 55,
|
| 669 |
+
"tokens_per_second_per_gpu": 6029.45,
|
| 670 |
+
"total_tokens": 10195261
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"epoch": 0.8924302788844621,
|
| 674 |
+
"grad_norm": 0.328125,
|
| 675 |
+
"learning_rate": 1.7700362352392632e-05,
|
| 676 |
+
"loss": 1.0151,
|
| 677 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 678 |
+
"memory/max_active (GiB)": 64.91,
|
| 679 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 680 |
+
"step": 56,
|
| 681 |
+
"tokens_per_second_per_gpu": 5824.93,
|
| 682 |
+
"total_tokens": 10378607
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.9083665338645418,
|
| 686 |
+
"grad_norm": 0.345703125,
|
| 687 |
+
"learning_rate": 1.757971723145453e-05,
|
| 688 |
+
"loss": 1.0737,
|
| 689 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 690 |
+
"memory/max_active (GiB)": 64.91,
|
| 691 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 692 |
+
"step": 57,
|
| 693 |
+
"tokens_per_second_per_gpu": 5758.69,
|
| 694 |
+
"total_tokens": 10565102
|
| 695 |
+
},
|
| 696 |
+
{
|
| 697 |
+
"epoch": 0.9243027888446215,
|
| 698 |
+
"grad_norm": 0.330078125,
|
| 699 |
+
"learning_rate": 1.7456421648831658e-05,
|
| 700 |
+
"loss": 1.0444,
|
| 701 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 702 |
+
"memory/max_active (GiB)": 64.91,
|
| 703 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 704 |
+
"step": 58,
|
| 705 |
+
"tokens_per_second_per_gpu": 5699.09,
|
| 706 |
+
"total_tokens": 10743645
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"epoch": 0.9402390438247012,
|
| 710 |
+
"grad_norm": 0.337890625,
|
| 711 |
+
"learning_rate": 1.7330518718298263e-05,
|
| 712 |
+
"loss": 0.998,
|
| 713 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 714 |
+
"memory/max_active (GiB)": 64.91,
|
| 715 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 716 |
+
"step": 59,
|
| 717 |
+
"tokens_per_second_per_gpu": 5772.72,
|
| 718 |
+
"total_tokens": 10926325
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.9561752988047809,
|
| 722 |
+
"grad_norm": 0.361328125,
|
| 723 |
+
"learning_rate": 1.7202052465361268e-05,
|
| 724 |
+
"loss": 1.0659,
|
| 725 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 726 |
+
"memory/max_active (GiB)": 64.91,
|
| 727 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 728 |
+
"step": 60,
|
| 729 |
+
"tokens_per_second_per_gpu": 5781.99,
|
| 730 |
+
"total_tokens": 11105741
|
| 731 |
+
},
|
| 732 |
+
{
|
| 733 |
+
"epoch": 0.9721115537848606,
|
| 734 |
+
"grad_norm": 0.326171875,
|
| 735 |
+
"learning_rate": 1.7071067811865477e-05,
|
| 736 |
+
"loss": 1.0024,
|
| 737 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 738 |
+
"memory/max_active (GiB)": 64.91,
|
| 739 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 740 |
+
"step": 61,
|
| 741 |
+
"tokens_per_second_per_gpu": 5416.25,
|
| 742 |
+
"total_tokens": 11283752
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"epoch": 0.9880478087649402,
|
| 746 |
+
"grad_norm": 0.314453125,
|
| 747 |
+
"learning_rate": 1.693761056028542e-05,
|
| 748 |
+
"loss": 0.9429,
|
| 749 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 750 |
+
"memory/max_active (GiB)": 64.91,
|
| 751 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 752 |
+
"step": 62,
|
| 753 |
+
"tokens_per_second_per_gpu": 6080.81,
|
| 754 |
+
"total_tokens": 11476891
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 1.0,
|
| 758 |
+
"grad_norm": 1.03125,
|
| 759 |
+
"learning_rate": 1.6801727377709195e-05,
|
| 760 |
+
"loss": 0.8979,
|
| 761 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 762 |
+
"memory/max_active (GiB)": 64.91,
|
| 763 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 764 |
+
"step": 63,
|
| 765 |
+
"tokens_per_second_per_gpu": 4586.33,
|
| 766 |
+
"total_tokens": 11600559
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.0159362549800797,
|
| 770 |
+
"grad_norm": 0.33203125,
|
| 771 |
+
"learning_rate": 1.6663465779520042e-05,
|
| 772 |
+
"loss": 1.0391,
|
| 773 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 774 |
+
"memory/max_active (GiB)": 64.91,
|
| 775 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 776 |
+
"step": 64,
|
| 777 |
+
"tokens_per_second_per_gpu": 5765.65,
|
| 778 |
+
"total_tokens": 11781077
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"epoch": 1.0318725099601593,
|
| 782 |
+
"grad_norm": 0.328125,
|
| 783 |
+
"learning_rate": 1.6522874112781213e-05,
|
| 784 |
+
"loss": 0.9893,
|
| 785 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 786 |
+
"memory/max_active (GiB)": 64.91,
|
| 787 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 788 |
+
"step": 65,
|
| 789 |
+
"tokens_per_second_per_gpu": 5812.65,
|
| 790 |
+
"total_tokens": 11964316
|
| 791 |
+
},
|
| 792 |
+
{
|
| 793 |
+
"epoch": 1.047808764940239,
|
| 794 |
+
"grad_norm": 0.33203125,
|
| 795 |
+
"learning_rate": 1.6380001539330088e-05,
|
| 796 |
+
"loss": 1.019,
|
| 797 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 798 |
+
"memory/max_active (GiB)": 64.91,
|
| 799 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 800 |
+
"step": 66,
|
| 801 |
+
"tokens_per_second_per_gpu": 5958.35,
|
| 802 |
+
"total_tokens": 12158602
|
| 803 |
+
},
|
| 804 |
+
{
|
| 805 |
+
"epoch": 1.0637450199203187,
|
| 806 |
+
"grad_norm": 0.318359375,
|
| 807 |
+
"learning_rate": 1.6234898018587336e-05,
|
| 808 |
+
"loss": 1.0098,
|
| 809 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 810 |
+
"memory/max_active (GiB)": 64.91,
|
| 811 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 812 |
+
"step": 67,
|
| 813 |
+
"tokens_per_second_per_gpu": 5947.9,
|
| 814 |
+
"total_tokens": 12343835
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"epoch": 1.0796812749003983,
|
| 818 |
+
"grad_norm": 0.31640625,
|
| 819 |
+
"learning_rate": 1.608761429008721e-05,
|
| 820 |
+
"loss": 0.959,
|
| 821 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 822 |
+
"memory/max_active (GiB)": 64.91,
|
| 823 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 824 |
+
"step": 68,
|
| 825 |
+
"tokens_per_second_per_gpu": 5410.16,
|
| 826 |
+
"total_tokens": 12530320
|
| 827 |
+
},
|
| 828 |
+
{
|
| 829 |
+
"epoch": 1.095617529880478,
|
| 830 |
+
"grad_norm": 0.337890625,
|
| 831 |
+
"learning_rate": 1.5938201855735017e-05,
|
| 832 |
+
"loss": 0.998,
|
| 833 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 834 |
+
"memory/max_active (GiB)": 64.91,
|
| 835 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 836 |
+
"step": 69,
|
| 837 |
+
"tokens_per_second_per_gpu": 5950.0,
|
| 838 |
+
"total_tokens": 12718875
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 1.1115537848605577,
|
| 842 |
+
"grad_norm": 0.31640625,
|
| 843 |
+
"learning_rate": 1.578671296179806e-05,
|
| 844 |
+
"loss": 0.9834,
|
| 845 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 846 |
+
"memory/max_active (GiB)": 64.91,
|
| 847 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 848 |
+
"step": 70,
|
| 849 |
+
"tokens_per_second_per_gpu": 5806.97,
|
| 850 |
+
"total_tokens": 12902174
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.1274900398406373,
|
| 854 |
+
"grad_norm": 0.322265625,
|
| 855 |
+
"learning_rate": 1.563320058063622e-05,
|
| 856 |
+
"loss": 1.02,
|
| 857 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 858 |
+
"memory/max_active (GiB)": 64.91,
|
| 859 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 860 |
+
"step": 71,
|
| 861 |
+
"tokens_per_second_per_gpu": 5964.93,
|
| 862 |
+
"total_tokens": 13091033
|
| 863 |
+
},
|
| 864 |
+
{
|
| 865 |
+
"epoch": 1.1434262948207172,
|
| 866 |
+
"grad_norm": 0.328125,
|
| 867 |
+
"learning_rate": 1.5477718392178716e-05,
|
| 868 |
+
"loss": 1.001,
|
| 869 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 870 |
+
"memory/max_active (GiB)": 64.91,
|
| 871 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 872 |
+
"step": 72,
|
| 873 |
+
"tokens_per_second_per_gpu": 5543.95,
|
| 874 |
+
"total_tokens": 13268135
|
| 875 |
+
},
|
| 876 |
+
{
|
| 877 |
+
"epoch": 1.159362549800797,
|
| 878 |
+
"grad_norm": 0.322265625,
|
| 879 |
+
"learning_rate": 1.5320320765153367e-05,
|
| 880 |
+
"loss": 0.9868,
|
| 881 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 882 |
+
"memory/max_active (GiB)": 64.91,
|
| 883 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 884 |
+
"step": 73,
|
| 885 |
+
"tokens_per_second_per_gpu": 6161.46,
|
| 886 |
+
"total_tokens": 13458366
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"epoch": 1.1752988047808766,
|
| 890 |
+
"grad_norm": 0.33203125,
|
| 891 |
+
"learning_rate": 1.5161062738075068e-05,
|
| 892 |
+
"loss": 0.9404,
|
| 893 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 894 |
+
"memory/max_active (GiB)": 64.91,
|
| 895 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 896 |
+
"step": 74,
|
| 897 |
+
"tokens_per_second_per_gpu": 5781.1,
|
| 898 |
+
"total_tokens": 13642048
|
| 899 |
+
},
|
| 900 |
+
{
|
| 901 |
+
"epoch": 1.1912350597609562,
|
| 902 |
+
"grad_norm": 0.423828125,
|
| 903 |
+
"learning_rate": 1.5000000000000002e-05,
|
| 904 |
+
"loss": 1.0273,
|
| 905 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 906 |
+
"memory/max_active (GiB)": 64.91,
|
| 907 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 908 |
+
"step": 75,
|
| 909 |
+
"tokens_per_second_per_gpu": 5754.51,
|
| 910 |
+
"total_tokens": 13816573
|
| 911 |
+
},
|
| 912 |
+
{
|
| 913 |
+
"epoch": 1.207171314741036,
|
| 914 |
+
"grad_norm": 0.376953125,
|
| 915 |
+
"learning_rate": 1.4837188871052399e-05,
|
| 916 |
+
"loss": 0.999,
|
| 917 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 918 |
+
"memory/max_active (GiB)": 64.91,
|
| 919 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 920 |
+
"step": 76,
|
| 921 |
+
"tokens_per_second_per_gpu": 5745.16,
|
| 922 |
+
"total_tokens": 13997690
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 1.2231075697211156,
|
| 926 |
+
"grad_norm": 0.30859375,
|
| 927 |
+
"learning_rate": 1.4672686282730622e-05,
|
| 928 |
+
"loss": 0.9365,
|
| 929 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 930 |
+
"memory/max_active (GiB)": 64.91,
|
| 931 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 932 |
+
"step": 77,
|
| 933 |
+
"tokens_per_second_per_gpu": 6187.18,
|
| 934 |
+
"total_tokens": 14191031
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.2390438247011952,
|
| 938 |
+
"grad_norm": 0.310546875,
|
| 939 |
+
"learning_rate": 1.4506549757999456e-05,
|
| 940 |
+
"loss": 0.9932,
|
| 941 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 942 |
+
"memory/max_active (GiB)": 64.91,
|
| 943 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 944 |
+
"step": 78,
|
| 945 |
+
"tokens_per_second_per_gpu": 6189.26,
|
| 946 |
+
"total_tokens": 14381270
|
| 947 |
+
},
|
| 948 |
+
{
|
| 949 |
+
"epoch": 1.254980079681275,
|
| 950 |
+
"grad_norm": 0.361328125,
|
| 951 |
+
"learning_rate": 1.4338837391175582e-05,
|
| 952 |
+
"loss": 0.9253,
|
| 953 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 954 |
+
"memory/max_active (GiB)": 64.91,
|
| 955 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 956 |
+
"step": 79,
|
| 957 |
+
"tokens_per_second_per_gpu": 5694.92,
|
| 958 |
+
"total_tokens": 14569147
|
| 959 |
+
},
|
| 960 |
+
{
|
| 961 |
+
"epoch": 1.2709163346613546,
|
| 962 |
+
"grad_norm": 0.349609375,
|
| 963 |
+
"learning_rate": 1.4169607827613284e-05,
|
| 964 |
+
"loss": 1.0249,
|
| 965 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 966 |
+
"memory/max_active (GiB)": 64.91,
|
| 967 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 968 |
+
"step": 80,
|
| 969 |
+
"tokens_per_second_per_gpu": 5574.13,
|
| 970 |
+
"total_tokens": 14749250
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"epoch": 1.2868525896414342,
|
| 974 |
+
"grad_norm": 0.33984375,
|
| 975 |
+
"learning_rate": 1.3998920243197408e-05,
|
| 976 |
+
"loss": 1.0044,
|
| 977 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 978 |
+
"memory/max_active (GiB)": 64.91,
|
| 979 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 980 |
+
"step": 81,
|
| 981 |
+
"tokens_per_second_per_gpu": 5892.86,
|
| 982 |
+
"total_tokens": 14932957
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"epoch": 1.302788844621514,
|
| 986 |
+
"grad_norm": 0.31640625,
|
| 987 |
+
"learning_rate": 1.3826834323650899e-05,
|
| 988 |
+
"loss": 0.9443,
|
| 989 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 990 |
+
"memory/max_active (GiB)": 64.91,
|
| 991 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 992 |
+
"step": 82,
|
| 993 |
+
"tokens_per_second_per_gpu": 6084.92,
|
| 994 |
+
"total_tokens": 15127169
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"epoch": 1.3187250996015936,
|
| 998 |
+
"grad_norm": 0.328125,
|
| 999 |
+
"learning_rate": 1.3653410243663953e-05,
|
| 1000 |
+
"loss": 0.9878,
|
| 1001 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1002 |
+
"memory/max_active (GiB)": 64.91,
|
| 1003 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1004 |
+
"step": 83,
|
| 1005 |
+
"tokens_per_second_per_gpu": 5984.25,
|
| 1006 |
+
"total_tokens": 15311601
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 1.3346613545816732,
|
| 1010 |
+
"grad_norm": 0.32421875,
|
| 1011 |
+
"learning_rate": 1.3478708645852272e-05,
|
| 1012 |
+
"loss": 0.9248,
|
| 1013 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1014 |
+
"memory/max_active (GiB)": 64.91,
|
| 1015 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1016 |
+
"step": 84,
|
| 1017 |
+
"tokens_per_second_per_gpu": 5744.73,
|
| 1018 |
+
"total_tokens": 15491400
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.3505976095617531,
|
| 1022 |
+
"grad_norm": 0.33203125,
|
| 1023 |
+
"learning_rate": 1.3302790619551673e-05,
|
| 1024 |
+
"loss": 0.9824,
|
| 1025 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1026 |
+
"memory/max_active (GiB)": 64.91,
|
| 1027 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1028 |
+
"step": 85,
|
| 1029 |
+
"tokens_per_second_per_gpu": 6009.5,
|
| 1030 |
+
"total_tokens": 15674583
|
| 1031 |
+
},
|
| 1032 |
+
{
|
| 1033 |
+
"epoch": 1.3665338645418328,
|
| 1034 |
+
"grad_norm": 0.314453125,
|
| 1035 |
+
"learning_rate": 1.3125717679456447e-05,
|
| 1036 |
+
"loss": 0.9404,
|
| 1037 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1038 |
+
"memory/max_active (GiB)": 64.91,
|
| 1039 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1040 |
+
"step": 86,
|
| 1041 |
+
"tokens_per_second_per_gpu": 5690.82,
|
| 1042 |
+
"total_tokens": 15861985
|
| 1043 |
+
},
|
| 1044 |
+
{
|
| 1045 |
+
"epoch": 1.3824701195219125,
|
| 1046 |
+
"grad_norm": 0.34765625,
|
| 1047 |
+
"learning_rate": 1.2947551744109044e-05,
|
| 1048 |
+
"loss": 0.9731,
|
| 1049 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1050 |
+
"memory/max_active (GiB)": 64.91,
|
| 1051 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1052 |
+
"step": 87,
|
| 1053 |
+
"tokens_per_second_per_gpu": 5962.66,
|
| 1054 |
+
"total_tokens": 16048780
|
| 1055 |
+
},
|
| 1056 |
+
{
|
| 1057 |
+
"epoch": 1.3984063745019921,
|
| 1058 |
+
"grad_norm": 0.318359375,
|
| 1059 |
+
"learning_rate": 1.2768355114248493e-05,
|
| 1060 |
+
"loss": 0.8406,
|
| 1061 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1062 |
+
"memory/max_active (GiB)": 64.91,
|
| 1063 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1064 |
+
"step": 88,
|
| 1065 |
+
"tokens_per_second_per_gpu": 5796.13,
|
| 1066 |
+
"total_tokens": 16243977
|
| 1067 |
+
},
|
| 1068 |
+
{
|
| 1069 |
+
"epoch": 1.4143426294820718,
|
| 1070 |
+
"grad_norm": 0.337890625,
|
| 1071 |
+
"learning_rate": 1.2588190451025209e-05,
|
| 1072 |
+
"loss": 0.9692,
|
| 1073 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1074 |
+
"memory/max_active (GiB)": 64.91,
|
| 1075 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1076 |
+
"step": 89,
|
| 1077 |
+
"tokens_per_second_per_gpu": 5748.01,
|
| 1078 |
+
"total_tokens": 16427123
|
| 1079 |
+
},
|
| 1080 |
+
{
|
| 1081 |
+
"epoch": 1.4302788844621515,
|
| 1082 |
+
"grad_norm": 0.345703125,
|
| 1083 |
+
"learning_rate": 1.2407120754089733e-05,
|
| 1084 |
+
"loss": 0.998,
|
| 1085 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1086 |
+
"memory/max_active (GiB)": 64.91,
|
| 1087 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1088 |
+
"step": 90,
|
| 1089 |
+
"tokens_per_second_per_gpu": 5897.24,
|
| 1090 |
+
"total_tokens": 16609176
|
| 1091 |
+
},
|
| 1092 |
+
{
|
| 1093 |
+
"epoch": 1.4462151394422311,
|
| 1094 |
+
"grad_norm": 0.33203125,
|
| 1095 |
+
"learning_rate": 1.2225209339563144e-05,
|
| 1096 |
+
"loss": 0.9507,
|
| 1097 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1098 |
+
"memory/max_active (GiB)": 64.91,
|
| 1099 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1100 |
+
"step": 91,
|
| 1101 |
+
"tokens_per_second_per_gpu": 5936.81,
|
| 1102 |
+
"total_tokens": 16795109
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.4621513944223108,
|
| 1106 |
+
"grad_norm": 0.328125,
|
| 1107 |
+
"learning_rate": 1.2042519817896805e-05,
|
| 1108 |
+
"loss": 0.9912,
|
| 1109 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1110 |
+
"memory/max_active (GiB)": 64.91,
|
| 1111 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1112 |
+
"step": 92,
|
| 1113 |
+
"tokens_per_second_per_gpu": 5949.43,
|
| 1114 |
+
"total_tokens": 16980935
|
| 1115 |
+
},
|
| 1116 |
+
{
|
| 1117 |
+
"epoch": 1.4780876494023905,
|
| 1118 |
+
"grad_norm": 0.333984375,
|
| 1119 |
+
"learning_rate": 1.1859116071629148e-05,
|
| 1120 |
+
"loss": 0.9888,
|
| 1121 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1122 |
+
"memory/max_active (GiB)": 64.91,
|
| 1123 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1124 |
+
"step": 93,
|
| 1125 |
+
"tokens_per_second_per_gpu": 6095.07,
|
| 1126 |
+
"total_tokens": 17167869
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 1.4940239043824701,
|
| 1130 |
+
"grad_norm": 0.322265625,
|
| 1131 |
+
"learning_rate": 1.1675062233047365e-05,
|
| 1132 |
+
"loss": 0.9219,
|
| 1133 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1134 |
+
"memory/max_active (GiB)": 64.91,
|
| 1135 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1136 |
+
"step": 94,
|
| 1137 |
+
"tokens_per_second_per_gpu": 6067.77,
|
| 1138 |
+
"total_tokens": 17351541
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"epoch": 1.5099601593625498,
|
| 1142 |
+
"grad_norm": 0.3828125,
|
| 1143 |
+
"learning_rate": 1.1490422661761744e-05,
|
| 1144 |
+
"loss": 0.9648,
|
| 1145 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1146 |
+
"memory/max_active (GiB)": 64.91,
|
| 1147 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1148 |
+
"step": 95,
|
| 1149 |
+
"tokens_per_second_per_gpu": 6008.67,
|
| 1150 |
+
"total_tokens": 17537891
|
| 1151 |
+
},
|
| 1152 |
+
{
|
| 1153 |
+
"epoch": 1.5258964143426295,
|
| 1154 |
+
"grad_norm": 0.328125,
|
| 1155 |
+
"learning_rate": 1.130526192220052e-05,
|
| 1156 |
+
"loss": 0.9556,
|
| 1157 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1158 |
+
"memory/max_active (GiB)": 64.91,
|
| 1159 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1160 |
+
"step": 96,
|
| 1161 |
+
"tokens_per_second_per_gpu": 5955.34,
|
| 1162 |
+
"total_tokens": 17721410
|
| 1163 |
+
},
|
| 1164 |
+
{
|
| 1165 |
+
"epoch": 1.5418326693227091,
|
| 1166 |
+
"grad_norm": 0.3359375,
|
| 1167 |
+
"learning_rate": 1.1119644761033079e-05,
|
| 1168 |
+
"loss": 0.9951,
|
| 1169 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1170 |
+
"memory/max_active (GiB)": 64.91,
|
| 1171 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1172 |
+
"step": 97,
|
| 1173 |
+
"tokens_per_second_per_gpu": 5732.24,
|
| 1174 |
+
"total_tokens": 17897961
|
| 1175 |
+
},
|
| 1176 |
+
{
|
| 1177 |
+
"epoch": 1.5577689243027888,
|
| 1178 |
+
"grad_norm": 0.330078125,
|
| 1179 |
+
"learning_rate": 1.0933636084529507e-05,
|
| 1180 |
+
"loss": 1.02,
|
| 1181 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1182 |
+
"memory/max_active (GiB)": 64.91,
|
| 1183 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1184 |
+
"step": 98,
|
| 1185 |
+
"tokens_per_second_per_gpu": 5813.99,
|
| 1186 |
+
"total_tokens": 18080875
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.5737051792828685,
|
| 1190 |
+
"grad_norm": 0.330078125,
|
| 1191 |
+
"learning_rate": 1.0747300935864245e-05,
|
| 1192 |
+
"loss": 0.958,
|
| 1193 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1194 |
+
"memory/max_active (GiB)": 64.91,
|
| 1195 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1196 |
+
"step": 99,
|
| 1197 |
+
"tokens_per_second_per_gpu": 5769.52,
|
| 1198 |
+
"total_tokens": 18265611
|
| 1199 |
+
},
|
| 1200 |
+
{
|
| 1201 |
+
"epoch": 1.5896414342629481,
|
| 1202 |
+
"grad_norm": 0.326171875,
|
| 1203 |
+
"learning_rate": 1.0560704472371919e-05,
|
| 1204 |
+
"loss": 0.9561,
|
| 1205 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1206 |
+
"memory/max_active (GiB)": 64.91,
|
| 1207 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1208 |
+
"step": 100,
|
| 1209 |
+
"tokens_per_second_per_gpu": 5726.38,
|
| 1210 |
+
"total_tokens": 18449842
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 1.6055776892430278,
|
| 1214 |
+
"grad_norm": 0.326171875,
|
| 1215 |
+
"learning_rate": 1.037391194276326e-05,
|
| 1216 |
+
"loss": 0.9707,
|
| 1217 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1218 |
+
"memory/max_active (GiB)": 64.91,
|
| 1219 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1220 |
+
"step": 101,
|
| 1221 |
+
"tokens_per_second_per_gpu": 5944.93,
|
| 1222 |
+
"total_tokens": 18633072
|
| 1223 |
+
},
|
| 1224 |
+
{
|
| 1225 |
+
"epoch": 1.6215139442231075,
|
| 1226 |
+
"grad_norm": 0.3203125,
|
| 1227 |
+
"learning_rate": 1.0186988664309023e-05,
|
| 1228 |
+
"loss": 0.9707,
|
| 1229 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1230 |
+
"memory/max_active (GiB)": 64.91,
|
| 1231 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1232 |
+
"step": 102,
|
| 1233 |
+
"tokens_per_second_per_gpu": 5897.0,
|
| 1234 |
+
"total_tokens": 18815120
|
| 1235 |
+
},
|
| 1236 |
+
{
|
| 1237 |
+
"epoch": 1.6374501992031871,
|
| 1238 |
+
"grad_norm": 0.328125,
|
| 1239 |
+
"learning_rate": 1e-05,
|
| 1240 |
+
"loss": 0.9385,
|
| 1241 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1242 |
+
"memory/max_active (GiB)": 64.91,
|
| 1243 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1244 |
+
"step": 103,
|
| 1245 |
+
"tokens_per_second_per_gpu": 5841.82,
|
| 1246 |
+
"total_tokens": 19001413
|
| 1247 |
+
},
|
| 1248 |
+
{
|
| 1249 |
+
"epoch": 1.6533864541832668,
|
| 1250 |
+
"grad_norm": 0.341796875,
|
| 1251 |
+
"learning_rate": 9.81301133569098e-06,
|
| 1252 |
+
"loss": 1.0303,
|
| 1253 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1254 |
+
"memory/max_active (GiB)": 64.91,
|
| 1255 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1256 |
+
"step": 104,
|
| 1257 |
+
"tokens_per_second_per_gpu": 5567.16,
|
| 1258 |
+
"total_tokens": 19177822
|
| 1259 |
+
},
|
| 1260 |
+
{
|
| 1261 |
+
"epoch": 1.6693227091633465,
|
| 1262 |
+
"grad_norm": 0.330078125,
|
| 1263 |
+
"learning_rate": 9.626088057236745e-06,
|
| 1264 |
+
"loss": 0.9814,
|
| 1265 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1266 |
+
"memory/max_active (GiB)": 64.91,
|
| 1267 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1268 |
+
"step": 105,
|
| 1269 |
+
"tokens_per_second_per_gpu": 5850.82,
|
| 1270 |
+
"total_tokens": 19364145
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.6852589641434261,
|
| 1274 |
+
"grad_norm": 0.31640625,
|
| 1275 |
+
"learning_rate": 9.439295527628083e-06,
|
| 1276 |
+
"loss": 0.9531,
|
| 1277 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1278 |
+
"memory/max_active (GiB)": 64.91,
|
| 1279 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1280 |
+
"step": 106,
|
| 1281 |
+
"tokens_per_second_per_gpu": 6142.09,
|
| 1282 |
+
"total_tokens": 19554154
|
| 1283 |
+
},
|
| 1284 |
+
{
|
| 1285 |
+
"epoch": 1.701195219123506,
|
| 1286 |
+
"grad_norm": 0.333984375,
|
| 1287 |
+
"learning_rate": 9.252699064135759e-06,
|
| 1288 |
+
"loss": 0.998,
|
| 1289 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1290 |
+
"memory/max_active (GiB)": 64.91,
|
| 1291 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1292 |
+
"step": 107,
|
| 1293 |
+
"tokens_per_second_per_gpu": 6059.46,
|
| 1294 |
+
"total_tokens": 19736167
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 1.7171314741035857,
|
| 1298 |
+
"grad_norm": 0.33203125,
|
| 1299 |
+
"learning_rate": 9.066363915470494e-06,
|
| 1300 |
+
"loss": 0.9204,
|
| 1301 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1302 |
+
"memory/max_active (GiB)": 64.91,
|
| 1303 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1304 |
+
"step": 108,
|
| 1305 |
+
"tokens_per_second_per_gpu": 5807.52,
|
| 1306 |
+
"total_tokens": 19928597
|
| 1307 |
+
},
|
| 1308 |
+
{
|
| 1309 |
+
"epoch": 1.7330677290836654,
|
| 1310 |
+
"grad_norm": 0.3515625,
|
| 1311 |
+
"learning_rate": 8.880355238966923e-06,
|
| 1312 |
+
"loss": 0.978,
|
| 1313 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1314 |
+
"memory/max_active (GiB)": 64.91,
|
| 1315 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1316 |
+
"step": 109,
|
| 1317 |
+
"tokens_per_second_per_gpu": 5987.33,
|
| 1318 |
+
"total_tokens": 20118188
|
| 1319 |
+
},
|
| 1320 |
+
{
|
| 1321 |
+
"epoch": 1.749003984063745,
|
| 1322 |
+
"grad_norm": 0.3359375,
|
| 1323 |
+
"learning_rate": 8.694738077799487e-06,
|
| 1324 |
+
"loss": 0.9702,
|
| 1325 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1326 |
+
"memory/max_active (GiB)": 64.91,
|
| 1327 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1328 |
+
"step": 110,
|
| 1329 |
+
"tokens_per_second_per_gpu": 5888.18,
|
| 1330 |
+
"total_tokens": 20301178
|
| 1331 |
+
},
|
| 1332 |
+
{
|
| 1333 |
+
"epoch": 1.7649402390438247,
|
| 1334 |
+
"grad_norm": 0.357421875,
|
| 1335 |
+
"learning_rate": 8.509577338238255e-06,
|
| 1336 |
+
"loss": 0.9253,
|
| 1337 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1338 |
+
"memory/max_active (GiB)": 64.91,
|
| 1339 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1340 |
+
"step": 111,
|
| 1341 |
+
"tokens_per_second_per_gpu": 5972.68,
|
| 1342 |
+
"total_tokens": 20487285
|
| 1343 |
+
},
|
| 1344 |
+
{
|
| 1345 |
+
"epoch": 1.7808764940239044,
|
| 1346 |
+
"grad_norm": 0.337890625,
|
| 1347 |
+
"learning_rate": 8.324937766952638e-06,
|
| 1348 |
+
"loss": 0.9814,
|
| 1349 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1350 |
+
"memory/max_active (GiB)": 64.91,
|
| 1351 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1352 |
+
"step": 112,
|
| 1353 |
+
"tokens_per_second_per_gpu": 5932.16,
|
| 1354 |
+
"total_tokens": 20674769
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.796812749003984,
|
| 1358 |
+
"grad_norm": 0.341796875,
|
| 1359 |
+
"learning_rate": 8.140883928370855e-06,
|
| 1360 |
+
"loss": 1.0088,
|
| 1361 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1362 |
+
"memory/max_active (GiB)": 64.91,
|
| 1363 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1364 |
+
"step": 113,
|
| 1365 |
+
"tokens_per_second_per_gpu": 5830.81,
|
| 1366 |
+
"total_tokens": 20853823
|
| 1367 |
+
},
|
| 1368 |
+
{
|
| 1369 |
+
"epoch": 1.812749003984064,
|
| 1370 |
+
"grad_norm": 0.322265625,
|
| 1371 |
+
"learning_rate": 7.957480182103198e-06,
|
| 1372 |
+
"loss": 0.9487,
|
| 1373 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1374 |
+
"memory/max_active (GiB)": 64.91,
|
| 1375 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1376 |
+
"step": 114,
|
| 1377 |
+
"tokens_per_second_per_gpu": 5865.22,
|
| 1378 |
+
"total_tokens": 21037578
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 1.8286852589641436,
|
| 1382 |
+
"grad_norm": 0.328125,
|
| 1383 |
+
"learning_rate": 7.774790660436857e-06,
|
| 1384 |
+
"loss": 0.9819,
|
| 1385 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1386 |
+
"memory/max_active (GiB)": 64.91,
|
| 1387 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1388 |
+
"step": 115,
|
| 1389 |
+
"tokens_per_second_per_gpu": 6252.84,
|
| 1390 |
+
"total_tokens": 21225336
|
| 1391 |
+
},
|
| 1392 |
+
{
|
| 1393 |
+
"epoch": 1.8446215139442232,
|
| 1394 |
+
"grad_norm": 0.33203125,
|
| 1395 |
+
"learning_rate": 7.592879245910273e-06,
|
| 1396 |
+
"loss": 0.9482,
|
| 1397 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1398 |
+
"memory/max_active (GiB)": 64.91,
|
| 1399 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1400 |
+
"step": 116,
|
| 1401 |
+
"tokens_per_second_per_gpu": 6223.23,
|
| 1402 |
+
"total_tokens": 21416652
|
| 1403 |
+
},
|
| 1404 |
+
{
|
| 1405 |
+
"epoch": 1.860557768924303,
|
| 1406 |
+
"grad_norm": 0.322265625,
|
| 1407 |
+
"learning_rate": 7.411809548974792e-06,
|
| 1408 |
+
"loss": 0.9697,
|
| 1409 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1410 |
+
"memory/max_active (GiB)": 64.91,
|
| 1411 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1412 |
+
"step": 117,
|
| 1413 |
+
"tokens_per_second_per_gpu": 5561.76,
|
| 1414 |
+
"total_tokens": 21604434
|
| 1415 |
+
},
|
| 1416 |
+
{
|
| 1417 |
+
"epoch": 1.8764940239043826,
|
| 1418 |
+
"grad_norm": 0.30859375,
|
| 1419 |
+
"learning_rate": 7.2316448857515076e-06,
|
| 1420 |
+
"loss": 0.9468,
|
| 1421 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1422 |
+
"memory/max_active (GiB)": 64.91,
|
| 1423 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1424 |
+
"step": 118,
|
| 1425 |
+
"tokens_per_second_per_gpu": 6026.88,
|
| 1426 |
+
"total_tokens": 21795820
|
| 1427 |
+
},
|
| 1428 |
+
{
|
| 1429 |
+
"epoch": 1.8924302788844622,
|
| 1430 |
+
"grad_norm": 0.32421875,
|
| 1431 |
+
"learning_rate": 7.052448255890958e-06,
|
| 1432 |
+
"loss": 0.9624,
|
| 1433 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1434 |
+
"memory/max_active (GiB)": 64.91,
|
| 1435 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1436 |
+
"step": 119,
|
| 1437 |
+
"tokens_per_second_per_gpu": 5817.1,
|
| 1438 |
+
"total_tokens": 21979166
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.908366533864542,
|
| 1442 |
+
"grad_norm": 0.33984375,
|
| 1443 |
+
"learning_rate": 6.874282320543557e-06,
|
| 1444 |
+
"loss": 1.022,
|
| 1445 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1446 |
+
"memory/max_active (GiB)": 64.91,
|
| 1447 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1448 |
+
"step": 120,
|
| 1449 |
+
"tokens_per_second_per_gpu": 5653.71,
|
| 1450 |
+
"total_tokens": 22165661
|
| 1451 |
+
},
|
| 1452 |
+
{
|
| 1453 |
+
"epoch": 1.9243027888446216,
|
| 1454 |
+
"grad_norm": 0.32421875,
|
| 1455 |
+
"learning_rate": 6.697209380448333e-06,
|
| 1456 |
+
"loss": 0.9961,
|
| 1457 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1458 |
+
"memory/max_active (GiB)": 64.91,
|
| 1459 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1460 |
+
"step": 121,
|
| 1461 |
+
"tokens_per_second_per_gpu": 5699.1,
|
| 1462 |
+
"total_tokens": 22344204
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"epoch": 1.9402390438247012,
|
| 1466 |
+
"grad_norm": 0.33203125,
|
| 1467 |
+
"learning_rate": 6.521291354147727e-06,
|
| 1468 |
+
"loss": 0.9521,
|
| 1469 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1470 |
+
"memory/max_active (GiB)": 64.91,
|
| 1471 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1472 |
+
"step": 122,
|
| 1473 |
+
"tokens_per_second_per_gpu": 5765.79,
|
| 1474 |
+
"total_tokens": 22526884
|
| 1475 |
+
},
|
| 1476 |
+
{
|
| 1477 |
+
"epoch": 1.956175298804781,
|
| 1478 |
+
"grad_norm": 0.349609375,
|
| 1479 |
+
"learning_rate": 6.34658975633605e-06,
|
| 1480 |
+
"loss": 1.0171,
|
| 1481 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1482 |
+
"memory/max_active (GiB)": 64.91,
|
| 1483 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1484 |
+
"step": 123,
|
| 1485 |
+
"tokens_per_second_per_gpu": 5780.38,
|
| 1486 |
+
"total_tokens": 22706300
|
| 1487 |
+
},
|
| 1488 |
+
{
|
| 1489 |
+
"epoch": 1.9721115537848606,
|
| 1490 |
+
"grad_norm": 0.318359375,
|
| 1491 |
+
"learning_rate": 6.173165676349103e-06,
|
| 1492 |
+
"loss": 0.957,
|
| 1493 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1494 |
+
"memory/max_active (GiB)": 64.91,
|
| 1495 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1496 |
+
"step": 124,
|
| 1497 |
+
"tokens_per_second_per_gpu": 5399.07,
|
| 1498 |
+
"total_tokens": 22884311
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 1.9880478087649402,
|
| 1502 |
+
"grad_norm": 0.357421875,
|
| 1503 |
+
"learning_rate": 6.001079756802592e-06,
|
| 1504 |
+
"loss": 0.9028,
|
| 1505 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1506 |
+
"memory/max_active (GiB)": 64.91,
|
| 1507 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1508 |
+
"step": 125,
|
| 1509 |
+
"tokens_per_second_per_gpu": 5850.46,
|
| 1510 |
+
"total_tokens": 23077450
|
| 1511 |
+
},
|
| 1512 |
+
{
|
| 1513 |
+
"epoch": 2.0,
|
| 1514 |
+
"grad_norm": 0.39453125,
|
| 1515 |
+
"learning_rate": 5.830392172386723e-06,
|
| 1516 |
+
"loss": 0.8589,
|
| 1517 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1518 |
+
"memory/max_active (GiB)": 64.91,
|
| 1519 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1520 |
+
"step": 126,
|
| 1521 |
+
"tokens_per_second_per_gpu": 4564.2,
|
| 1522 |
+
"total_tokens": 23201118
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 2.0159362549800797,
|
| 1526 |
+
"grad_norm": 0.32421875,
|
| 1527 |
+
"learning_rate": 5.66116260882442e-06,
|
| 1528 |
+
"loss": 0.9985,
|
| 1529 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1530 |
+
"memory/max_active (GiB)": 64.91,
|
| 1531 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1532 |
+
"step": 127,
|
| 1533 |
+
"tokens_per_second_per_gpu": 5832.26,
|
| 1534 |
+
"total_tokens": 23381636
|
| 1535 |
+
},
|
| 1536 |
+
{
|
| 1537 |
+
"epoch": 2.0318725099601593,
|
| 1538 |
+
"grad_norm": 0.328125,
|
| 1539 |
+
"learning_rate": 5.493450242000546e-06,
|
| 1540 |
+
"loss": 0.9521,
|
| 1541 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1542 |
+
"memory/max_active (GiB)": 64.91,
|
| 1543 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1544 |
+
"step": 128,
|
| 1545 |
+
"tokens_per_second_per_gpu": 5774.6,
|
| 1546 |
+
"total_tokens": 23564875
|
| 1547 |
+
},
|
| 1548 |
+
{
|
| 1549 |
+
"epoch": 2.047808764940239,
|
| 1550 |
+
"grad_norm": 0.328125,
|
| 1551 |
+
"learning_rate": 5.32731371726938e-06,
|
| 1552 |
+
"loss": 0.98,
|
| 1553 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1554 |
+
"memory/max_active (GiB)": 64.91,
|
| 1555 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1556 |
+
"step": 129,
|
| 1557 |
+
"tokens_per_second_per_gpu": 5972.38,
|
| 1558 |
+
"total_tokens": 23759161
|
| 1559 |
+
},
|
| 1560 |
+
{
|
| 1561 |
+
"epoch": 2.0637450199203187,
|
| 1562 |
+
"grad_norm": 0.328125,
|
| 1563 |
+
"learning_rate": 5.1628111289476025e-06,
|
| 1564 |
+
"loss": 0.9746,
|
| 1565 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1566 |
+
"memory/max_active (GiB)": 64.91,
|
| 1567 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1568 |
+
"step": 130,
|
| 1569 |
+
"tokens_per_second_per_gpu": 5919.54,
|
| 1570 |
+
"total_tokens": 23944394
|
| 1571 |
+
},
|
| 1572 |
+
{
|
| 1573 |
+
"epoch": 2.0796812749003983,
|
| 1574 |
+
"grad_norm": 0.31640625,
|
| 1575 |
+
"learning_rate": 5.000000000000003e-06,
|
| 1576 |
+
"loss": 0.9229,
|
| 1577 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1578 |
+
"memory/max_active (GiB)": 64.91,
|
| 1579 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1580 |
+
"step": 131,
|
| 1581 |
+
"tokens_per_second_per_gpu": 5414.05,
|
| 1582 |
+
"total_tokens": 24130879
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 2.095617529880478,
|
| 1586 |
+
"grad_norm": 0.33203125,
|
| 1587 |
+
"learning_rate": 4.838937261924933e-06,
|
| 1588 |
+
"loss": 0.9639,
|
| 1589 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1590 |
+
"memory/max_active (GiB)": 64.91,
|
| 1591 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1592 |
+
"step": 132,
|
| 1593 |
+
"tokens_per_second_per_gpu": 5968.88,
|
| 1594 |
+
"total_tokens": 24319434
|
| 1595 |
+
},
|
| 1596 |
+
{
|
| 1597 |
+
"epoch": 2.1115537848605577,
|
| 1598 |
+
"grad_norm": 0.31640625,
|
| 1599 |
+
"learning_rate": 4.679679234846636e-06,
|
| 1600 |
+
"loss": 0.9502,
|
| 1601 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1602 |
+
"memory/max_active (GiB)": 64.91,
|
| 1603 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1604 |
+
"step": 133,
|
| 1605 |
+
"tokens_per_second_per_gpu": 5802.86,
|
| 1606 |
+
"total_tokens": 24502733
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 2.1274900398406373,
|
| 1610 |
+
"grad_norm": 0.318359375,
|
| 1611 |
+
"learning_rate": 4.522281607821288e-06,
|
| 1612 |
+
"loss": 0.9854,
|
| 1613 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1614 |
+
"memory/max_active (GiB)": 64.91,
|
| 1615 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1616 |
+
"step": 134,
|
| 1617 |
+
"tokens_per_second_per_gpu": 5970.96,
|
| 1618 |
+
"total_tokens": 24691592
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"epoch": 2.143426294820717,
|
| 1622 |
+
"grad_norm": 0.373046875,
|
| 1623 |
+
"learning_rate": 4.3667994193637794e-06,
|
| 1624 |
+
"loss": 0.9683,
|
| 1625 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1626 |
+
"memory/max_active (GiB)": 64.91,
|
| 1627 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1628 |
+
"step": 135,
|
| 1629 |
+
"tokens_per_second_per_gpu": 5528.1,
|
| 1630 |
+
"total_tokens": 24868694
|
| 1631 |
+
},
|
| 1632 |
+
{
|
| 1633 |
+
"epoch": 2.1593625498007967,
|
| 1634 |
+
"grad_norm": 0.318359375,
|
| 1635 |
+
"learning_rate": 4.213287038201943e-06,
|
| 1636 |
+
"loss": 0.9561,
|
| 1637 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1638 |
+
"memory/max_active (GiB)": 64.91,
|
| 1639 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1640 |
+
"step": 136,
|
| 1641 |
+
"tokens_per_second_per_gpu": 6105.7,
|
| 1642 |
+
"total_tokens": 25058925
|
| 1643 |
+
},
|
| 1644 |
+
{
|
| 1645 |
+
"epoch": 2.1752988047808763,
|
| 1646 |
+
"grad_norm": 0.322265625,
|
| 1647 |
+
"learning_rate": 4.061798144264986e-06,
|
| 1648 |
+
"loss": 0.9116,
|
| 1649 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1650 |
+
"memory/max_active (GiB)": 64.91,
|
| 1651 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1652 |
+
"step": 137,
|
| 1653 |
+
"tokens_per_second_per_gpu": 5771.48,
|
| 1654 |
+
"total_tokens": 25242607
|
| 1655 |
+
},
|
| 1656 |
+
{
|
| 1657 |
+
"epoch": 2.191235059760956,
|
| 1658 |
+
"grad_norm": 0.3359375,
|
| 1659 |
+
"learning_rate": 3.912385709912794e-06,
|
| 1660 |
+
"loss": 0.9966,
|
| 1661 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1662 |
+
"memory/max_active (GiB)": 64.91,
|
| 1663 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1664 |
+
"step": 138,
|
| 1665 |
+
"tokens_per_second_per_gpu": 5723.02,
|
| 1666 |
+
"total_tokens": 25417132
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 2.2071713147410357,
|
| 1670 |
+
"grad_norm": 0.318359375,
|
| 1671 |
+
"learning_rate": 3.7651019814126656e-06,
|
| 1672 |
+
"loss": 0.9712,
|
| 1673 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1674 |
+
"memory/max_active (GiB)": 64.91,
|
| 1675 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1676 |
+
"step": 139,
|
| 1677 |
+
"tokens_per_second_per_gpu": 5739.14,
|
| 1678 |
+
"total_tokens": 25598249
|
| 1679 |
+
},
|
| 1680 |
+
{
|
| 1681 |
+
"epoch": 2.2231075697211153,
|
| 1682 |
+
"grad_norm": 0.306640625,
|
| 1683 |
+
"learning_rate": 3.619998460669916e-06,
|
| 1684 |
+
"loss": 0.9106,
|
| 1685 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1686 |
+
"memory/max_active (GiB)": 64.91,
|
| 1687 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1688 |
+
"step": 140,
|
| 1689 |
+
"tokens_per_second_per_gpu": 6168.5,
|
| 1690 |
+
"total_tokens": 25791590
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.239043824701195,
|
| 1694 |
+
"grad_norm": 0.31640625,
|
| 1695 |
+
"learning_rate": 3.4771258872187917e-06,
|
| 1696 |
+
"loss": 0.9673,
|
| 1697 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1698 |
+
"memory/max_active (GiB)": 64.91,
|
| 1699 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1700 |
+
"step": 141,
|
| 1701 |
+
"tokens_per_second_per_gpu": 6156.05,
|
| 1702 |
+
"total_tokens": 25981829
|
| 1703 |
+
},
|
| 1704 |
+
{
|
| 1705 |
+
"epoch": 2.2549800796812747,
|
| 1706 |
+
"grad_norm": 0.33203125,
|
| 1707 |
+
"learning_rate": 3.3365342204799613e-06,
|
| 1708 |
+
"loss": 0.9019,
|
| 1709 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1710 |
+
"memory/max_active (GiB)": 64.91,
|
| 1711 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1712 |
+
"step": 142,
|
| 1713 |
+
"tokens_per_second_per_gpu": 5766.33,
|
| 1714 |
+
"total_tokens": 26169706
|
| 1715 |
+
},
|
| 1716 |
+
{
|
| 1717 |
+
"epoch": 2.2709163346613543,
|
| 1718 |
+
"grad_norm": 0.50390625,
|
| 1719 |
+
"learning_rate": 3.1982726222908046e-06,
|
| 1720 |
+
"loss": 0.9995,
|
| 1721 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1722 |
+
"memory/max_active (GiB)": 64.91,
|
| 1723 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1724 |
+
"step": 143,
|
| 1725 |
+
"tokens_per_second_per_gpu": 5566.19,
|
| 1726 |
+
"total_tokens": 26349809
|
| 1727 |
+
},
|
| 1728 |
+
{
|
| 1729 |
+
"epoch": 2.2868525896414345,
|
| 1730 |
+
"grad_norm": 0.359375,
|
| 1731 |
+
"learning_rate": 3.0623894397145837e-06,
|
| 1732 |
+
"loss": 0.9805,
|
| 1733 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1734 |
+
"memory/max_active (GiB)": 64.91,
|
| 1735 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1736 |
+
"step": 144,
|
| 1737 |
+
"tokens_per_second_per_gpu": 5897.52,
|
| 1738 |
+
"total_tokens": 26533516
|
| 1739 |
+
},
|
| 1740 |
+
{
|
| 1741 |
+
"epoch": 2.302788844621514,
|
| 1742 |
+
"grad_norm": 0.375,
|
| 1743 |
+
"learning_rate": 2.9289321881345257e-06,
|
| 1744 |
+
"loss": 0.9219,
|
| 1745 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1746 |
+
"memory/max_active (GiB)": 64.91,
|
| 1747 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1748 |
+
"step": 145,
|
| 1749 |
+
"tokens_per_second_per_gpu": 6065.68,
|
| 1750 |
+
"total_tokens": 26727728
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 2.318725099601594,
|
| 1754 |
+
"grad_norm": 0.3359375,
|
| 1755 |
+
"learning_rate": 2.7979475346387363e-06,
|
| 1756 |
+
"loss": 0.9639,
|
| 1757 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1758 |
+
"memory/max_active (GiB)": 64.91,
|
| 1759 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1760 |
+
"step": 146,
|
| 1761 |
+
"tokens_per_second_per_gpu": 5976.74,
|
| 1762 |
+
"total_tokens": 26912160
|
| 1763 |
+
},
|
| 1764 |
+
{
|
| 1765 |
+
"epoch": 2.3346613545816735,
|
| 1766 |
+
"grad_norm": 0.34765625,
|
| 1767 |
+
"learning_rate": 2.669481281701739e-06,
|
| 1768 |
+
"loss": 0.9038,
|
| 1769 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1770 |
+
"memory/max_active (GiB)": 64.91,
|
| 1771 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1772 |
+
"step": 147,
|
| 1773 |
+
"tokens_per_second_per_gpu": 5726.82,
|
| 1774 |
+
"total_tokens": 27091959
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.350597609561753,
|
| 1778 |
+
"grad_norm": 0.341796875,
|
| 1779 |
+
"learning_rate": 2.5435783511683444e-06,
|
| 1780 |
+
"loss": 0.9614,
|
| 1781 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1782 |
+
"memory/max_active (GiB)": 64.91,
|
| 1783 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1784 |
+
"step": 148,
|
| 1785 |
+
"tokens_per_second_per_gpu": 5973.36,
|
| 1786 |
+
"total_tokens": 27275142
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"epoch": 2.366533864541833,
|
| 1790 |
+
"grad_norm": 0.33203125,
|
| 1791 |
+
"learning_rate": 2.420282768545469e-06,
|
| 1792 |
+
"loss": 0.9219,
|
| 1793 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1794 |
+
"memory/max_active (GiB)": 64.91,
|
| 1795 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1796 |
+
"step": 149,
|
| 1797 |
+
"tokens_per_second_per_gpu": 5654.39,
|
| 1798 |
+
"total_tokens": 27462544
|
| 1799 |
+
},
|
| 1800 |
+
{
|
| 1801 |
+
"epoch": 2.3824701195219125,
|
| 1802 |
+
"grad_norm": 0.322265625,
|
| 1803 |
+
"learning_rate": 2.2996376476073724e-06,
|
| 1804 |
+
"loss": 0.9526,
|
| 1805 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1806 |
+
"memory/max_active (GiB)": 64.91,
|
| 1807 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1808 |
+
"step": 150,
|
| 1809 |
+
"tokens_per_second_per_gpu": 5952.85,
|
| 1810 |
+
"total_tokens": 27649339
|
| 1811 |
+
},
|
| 1812 |
+
{
|
| 1813 |
+
"epoch": 2.398406374501992,
|
| 1814 |
+
"grad_norm": 0.3203125,
|
| 1815 |
+
"learning_rate": 2.1816851753197023e-06,
|
| 1816 |
+
"loss": 0.8235,
|
| 1817 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1818 |
+
"memory/max_active (GiB)": 64.91,
|
| 1819 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1820 |
+
"step": 151,
|
| 1821 |
+
"tokens_per_second_per_gpu": 5837.21,
|
| 1822 |
+
"total_tokens": 27844536
|
| 1823 |
+
},
|
| 1824 |
+
{
|
| 1825 |
+
"epoch": 2.414342629482072,
|
| 1826 |
+
"grad_norm": 0.333984375,
|
| 1827 |
+
"learning_rate": 2.0664665970876496e-06,
|
| 1828 |
+
"loss": 0.9521,
|
| 1829 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1830 |
+
"memory/max_active (GiB)": 64.91,
|
| 1831 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1832 |
+
"step": 152,
|
| 1833 |
+
"tokens_per_second_per_gpu": 5754.33,
|
| 1834 |
+
"total_tokens": 28027682
|
| 1835 |
+
},
|
| 1836 |
+
{
|
| 1837 |
+
"epoch": 2.4302788844621515,
|
| 1838 |
+
"grad_norm": 0.326171875,
|
| 1839 |
+
"learning_rate": 1.9540222023333165e-06,
|
| 1840 |
+
"loss": 0.9805,
|
| 1841 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1842 |
+
"memory/max_active (GiB)": 64.91,
|
| 1843 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1844 |
+
"step": 153,
|
| 1845 |
+
"tokens_per_second_per_gpu": 5902.39,
|
| 1846 |
+
"total_tokens": 28209735
|
| 1847 |
+
},
|
| 1848 |
+
{
|
| 1849 |
+
"epoch": 2.446215139442231,
|
| 1850 |
+
"grad_norm": 0.32421875,
|
| 1851 |
+
"learning_rate": 1.8443913104073984e-06,
|
| 1852 |
+
"loss": 0.9321,
|
| 1853 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1854 |
+
"memory/max_active (GiB)": 64.91,
|
| 1855 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1856 |
+
"step": 154,
|
| 1857 |
+
"tokens_per_second_per_gpu": 5930.45,
|
| 1858 |
+
"total_tokens": 28395668
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.462151394422311,
|
| 1862 |
+
"grad_norm": 0.3203125,
|
| 1863 |
+
"learning_rate": 1.7376122568400533e-06,
|
| 1864 |
+
"loss": 0.9756,
|
| 1865 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1866 |
+
"memory/max_active (GiB)": 64.91,
|
| 1867 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1868 |
+
"step": 155,
|
| 1869 |
+
"tokens_per_second_per_gpu": 5945.66,
|
| 1870 |
+
"total_tokens": 28581494
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 2.4780876494023905,
|
| 1874 |
+
"grad_norm": 0.322265625,
|
| 1875 |
+
"learning_rate": 1.6337223799358025e-06,
|
| 1876 |
+
"loss": 0.9736,
|
| 1877 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1878 |
+
"memory/max_active (GiB)": 64.91,
|
| 1879 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1880 |
+
"step": 156,
|
| 1881 |
+
"tokens_per_second_per_gpu": 6107.11,
|
| 1882 |
+
"total_tokens": 28768428
|
| 1883 |
+
},
|
| 1884 |
+
{
|
| 1885 |
+
"epoch": 2.49402390438247,
|
| 1886 |
+
"grad_norm": 0.31640625,
|
| 1887 |
+
"learning_rate": 1.5327580077171589e-06,
|
| 1888 |
+
"loss": 0.9067,
|
| 1889 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1890 |
+
"memory/max_active (GiB)": 64.91,
|
| 1891 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1892 |
+
"step": 157,
|
| 1893 |
+
"tokens_per_second_per_gpu": 6059.61,
|
| 1894 |
+
"total_tokens": 28952100
|
| 1895 |
+
},
|
| 1896 |
+
{
|
| 1897 |
+
"epoch": 2.50996015936255,
|
| 1898 |
+
"grad_norm": 0.326171875,
|
| 1899 |
+
"learning_rate": 1.4347544452214869e-06,
|
| 1900 |
+
"loss": 0.9512,
|
| 1901 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1902 |
+
"memory/max_active (GiB)": 64.91,
|
| 1903 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1904 |
+
"step": 158,
|
| 1905 |
+
"tokens_per_second_per_gpu": 6010.47,
|
| 1906 |
+
"total_tokens": 29138450
|
| 1907 |
+
},
|
| 1908 |
+
{
|
| 1909 |
+
"epoch": 2.5258964143426295,
|
| 1910 |
+
"grad_norm": 0.376953125,
|
| 1911 |
+
"learning_rate": 1.339745962155613e-06,
|
| 1912 |
+
"loss": 0.9409,
|
| 1913 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1914 |
+
"memory/max_active (GiB)": 64.91,
|
| 1915 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1916 |
+
"step": 159,
|
| 1917 |
+
"tokens_per_second_per_gpu": 6038.89,
|
| 1918 |
+
"total_tokens": 29321969
|
| 1919 |
+
},
|
| 1920 |
+
{
|
| 1921 |
+
"epoch": 2.541832669322709,
|
| 1922 |
+
"grad_norm": 0.330078125,
|
| 1923 |
+
"learning_rate": 1.2477657809124632e-06,
|
| 1924 |
+
"loss": 0.9824,
|
| 1925 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1926 |
+
"memory/max_active (GiB)": 64.91,
|
| 1927 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1928 |
+
"step": 160,
|
| 1929 |
+
"tokens_per_second_per_gpu": 5740.71,
|
| 1930 |
+
"total_tokens": 29498520
|
| 1931 |
+
},
|
| 1932 |
+
{
|
| 1933 |
+
"epoch": 2.557768924302789,
|
| 1934 |
+
"grad_norm": 0.328125,
|
| 1935 |
+
"learning_rate": 1.1588460649539036e-06,
|
| 1936 |
+
"loss": 1.0068,
|
| 1937 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1938 |
+
"memory/max_active (GiB)": 64.91,
|
| 1939 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1940 |
+
"step": 161,
|
| 1941 |
+
"tokens_per_second_per_gpu": 5804.04,
|
| 1942 |
+
"total_tokens": 29681434
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.5737051792828685,
|
| 1946 |
+
"grad_norm": 0.337890625,
|
| 1947 |
+
"learning_rate": 1.073017907563887e-06,
|
| 1948 |
+
"loss": 0.9453,
|
| 1949 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1950 |
+
"memory/max_active (GiB)": 64.91,
|
| 1951 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1952 |
+
"step": 162,
|
| 1953 |
+
"tokens_per_second_per_gpu": 5741.44,
|
| 1954 |
+
"total_tokens": 29866170
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 2.589641434262948,
|
| 1958 |
+
"grad_norm": 0.3203125,
|
| 1959 |
+
"learning_rate": 9.903113209758098e-07,
|
| 1960 |
+
"loss": 0.9443,
|
| 1961 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1962 |
+
"memory/max_active (GiB)": 64.91,
|
| 1963 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1964 |
+
"step": 163,
|
| 1965 |
+
"tokens_per_second_per_gpu": 5756.27,
|
| 1966 |
+
"total_tokens": 30050401
|
| 1967 |
+
},
|
| 1968 |
+
{
|
| 1969 |
+
"epoch": 2.605577689243028,
|
| 1970 |
+
"grad_norm": 0.32421875,
|
| 1971 |
+
"learning_rate": 9.107552258778907e-07,
|
| 1972 |
+
"loss": 0.9585,
|
| 1973 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1974 |
+
"memory/max_active (GiB)": 64.91,
|
| 1975 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1976 |
+
"step": 164,
|
| 1977 |
+
"tokens_per_second_per_gpu": 5959.88,
|
| 1978 |
+
"total_tokens": 30233631
|
| 1979 |
+
},
|
| 1980 |
+
{
|
| 1981 |
+
"epoch": 2.6215139442231075,
|
| 1982 |
+
"grad_norm": 0.3203125,
|
| 1983 |
+
"learning_rate": 8.343774413002382e-07,
|
| 1984 |
+
"loss": 0.9604,
|
| 1985 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1986 |
+
"memory/max_active (GiB)": 64.91,
|
| 1987 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 1988 |
+
"step": 165,
|
| 1989 |
+
"tokens_per_second_per_gpu": 5899.57,
|
| 1990 |
+
"total_tokens": 30415679
|
| 1991 |
+
},
|
| 1992 |
+
{
|
| 1993 |
+
"epoch": 2.637450199203187,
|
| 1994 |
+
"grad_norm": 0.326171875,
|
| 1995 |
+
"learning_rate": 7.612046748871327e-07,
|
| 1996 |
+
"loss": 0.9277,
|
| 1997 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 1998 |
+
"memory/max_active (GiB)": 64.91,
|
| 1999 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2000 |
+
"step": 166,
|
| 2001 |
+
"tokens_per_second_per_gpu": 5845.3,
|
| 2002 |
+
"total_tokens": 30601972
|
| 2003 |
+
},
|
| 2004 |
+
{
|
| 2005 |
+
"epoch": 2.653386454183267,
|
| 2006 |
+
"grad_norm": 0.33984375,
|
| 2007 |
+
"learning_rate": 6.912625135579587e-07,
|
| 2008 |
+
"loss": 1.022,
|
| 2009 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2010 |
+
"memory/max_active (GiB)": 64.91,
|
| 2011 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2012 |
+
"step": 167,
|
| 2013 |
+
"tokens_per_second_per_gpu": 5574.11,
|
| 2014 |
+
"total_tokens": 30778381
|
| 2015 |
+
},
|
| 2016 |
+
{
|
| 2017 |
+
"epoch": 2.6693227091633465,
|
| 2018 |
+
"grad_norm": 0.31640625,
|
| 2019 |
+
"learning_rate": 6.245754145600091e-07,
|
| 2020 |
+
"loss": 0.9707,
|
| 2021 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2022 |
+
"memory/max_active (GiB)": 64.91,
|
| 2023 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2024 |
+
"step": 168,
|
| 2025 |
+
"tokens_per_second_per_gpu": 5930.11,
|
| 2026 |
+
"total_tokens": 30964704
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.685258964143426,
|
| 2030 |
+
"grad_norm": 0.318359375,
|
| 2031 |
+
"learning_rate": 5.611666969163243e-07,
|
| 2032 |
+
"loss": 0.9448,
|
| 2033 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2034 |
+
"memory/max_active (GiB)": 64.91,
|
| 2035 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2036 |
+
"step": 169,
|
| 2037 |
+
"tokens_per_second_per_gpu": 6128.63,
|
| 2038 |
+
"total_tokens": 31154713
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 2.7011952191235062,
|
| 2042 |
+
"grad_norm": 0.333984375,
|
| 2043 |
+
"learning_rate": 5.010585332715401e-07,
|
| 2044 |
+
"loss": 0.9883,
|
| 2045 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2046 |
+
"memory/max_active (GiB)": 64.91,
|
| 2047 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2048 |
+
"step": 170,
|
| 2049 |
+
"tokens_per_second_per_gpu": 6064.77,
|
| 2050 |
+
"total_tokens": 31336726
|
| 2051 |
+
},
|
| 2052 |
+
{
|
| 2053 |
+
"epoch": 2.717131474103586,
|
| 2054 |
+
"grad_norm": 0.328125,
|
| 2055 |
+
"learning_rate": 4.4427194213859216e-07,
|
| 2056 |
+
"loss": 0.9131,
|
| 2057 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2058 |
+
"memory/max_active (GiB)": 64.91,
|
| 2059 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2060 |
+
"step": 171,
|
| 2061 |
+
"tokens_per_second_per_gpu": 5798.36,
|
| 2062 |
+
"total_tokens": 31529156
|
| 2063 |
+
},
|
| 2064 |
+
{
|
| 2065 |
+
"epoch": 2.7330677290836656,
|
| 2066 |
+
"grad_norm": 0.318359375,
|
| 2067 |
+
"learning_rate": 3.908267805490051e-07,
|
| 2068 |
+
"loss": 0.9697,
|
| 2069 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2070 |
+
"memory/max_active (GiB)": 64.91,
|
| 2071 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2072 |
+
"step": 172,
|
| 2073 |
+
"tokens_per_second_per_gpu": 5977.29,
|
| 2074 |
+
"total_tokens": 31718747
|
| 2075 |
+
},
|
| 2076 |
+
{
|
| 2077 |
+
"epoch": 2.7490039840637452,
|
| 2078 |
+
"grad_norm": 0.328125,
|
| 2079 |
+
"learning_rate": 3.4074173710931804e-07,
|
| 2080 |
+
"loss": 0.9619,
|
| 2081 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2082 |
+
"memory/max_active (GiB)": 64.91,
|
| 2083 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2084 |
+
"step": 173,
|
| 2085 |
+
"tokens_per_second_per_gpu": 5934.4,
|
| 2086 |
+
"total_tokens": 31901737
|
| 2087 |
+
},
|
| 2088 |
+
{
|
| 2089 |
+
"epoch": 2.764940239043825,
|
| 2090 |
+
"grad_norm": 0.322265625,
|
| 2091 |
+
"learning_rate": 2.940343254660905e-07,
|
| 2092 |
+
"loss": 0.9185,
|
| 2093 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2094 |
+
"memory/max_active (GiB)": 64.91,
|
| 2095 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2096 |
+
"step": 174,
|
| 2097 |
+
"tokens_per_second_per_gpu": 5978.89,
|
| 2098 |
+
"total_tokens": 32087844
|
| 2099 |
+
},
|
| 2100 |
+
{
|
| 2101 |
+
"epoch": 2.7808764940239046,
|
| 2102 |
+
"grad_norm": 0.328125,
|
| 2103 |
+
"learning_rate": 2.507208781817638e-07,
|
| 2104 |
+
"loss": 0.9751,
|
| 2105 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2106 |
+
"memory/max_active (GiB)": 64.91,
|
| 2107 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2108 |
+
"step": 175,
|
| 2109 |
+
"tokens_per_second_per_gpu": 5946.29,
|
| 2110 |
+
"total_tokens": 32275328
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.7968127490039842,
|
| 2114 |
+
"grad_norm": 0.337890625,
|
| 2115 |
+
"learning_rate": 2.1081654102351634e-07,
|
| 2116 |
+
"loss": 1.0015,
|
| 2117 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2118 |
+
"memory/max_active (GiB)": 64.91,
|
| 2119 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2120 |
+
"step": 176,
|
| 2121 |
+
"tokens_per_second_per_gpu": 5871.96,
|
| 2122 |
+
"total_tokens": 32454382
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 2.812749003984064,
|
| 2126 |
+
"grad_norm": 0.318359375,
|
| 2127 |
+
"learning_rate": 1.7433526766711727e-07,
|
| 2128 |
+
"loss": 0.9429,
|
| 2129 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2130 |
+
"memory/max_active (GiB)": 64.91,
|
| 2131 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2132 |
+
"step": 177,
|
| 2133 |
+
"tokens_per_second_per_gpu": 5872.24,
|
| 2134 |
+
"total_tokens": 32638137
|
| 2135 |
+
},
|
| 2136 |
+
{
|
| 2137 |
+
"epoch": 2.8286852589641436,
|
| 2138 |
+
"grad_norm": 0.3203125,
|
| 2139 |
+
"learning_rate": 1.4128981481764115e-07,
|
| 2140 |
+
"loss": 0.9746,
|
| 2141 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2142 |
+
"memory/max_active (GiB)": 64.91,
|
| 2143 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2144 |
+
"step": 178,
|
| 2145 |
+
"tokens_per_second_per_gpu": 6173.8,
|
| 2146 |
+
"total_tokens": 32825895
|
| 2147 |
+
},
|
| 2148 |
+
{
|
| 2149 |
+
"epoch": 2.8446215139442232,
|
| 2150 |
+
"grad_norm": 0.322265625,
|
| 2151 |
+
"learning_rate": 1.1169173774871478e-07,
|
| 2152 |
+
"loss": 0.9434,
|
| 2153 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2154 |
+
"memory/max_active (GiB)": 64.91,
|
| 2155 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2156 |
+
"step": 179,
|
| 2157 |
+
"tokens_per_second_per_gpu": 6232.85,
|
| 2158 |
+
"total_tokens": 33017211
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 2.860557768924303,
|
| 2162 |
+
"grad_norm": 0.3203125,
|
| 2163 |
+
"learning_rate": 8.555138626189619e-08,
|
| 2164 |
+
"loss": 0.9644,
|
| 2165 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2166 |
+
"memory/max_active (GiB)": 64.91,
|
| 2167 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2168 |
+
"step": 180,
|
| 2169 |
+
"tokens_per_second_per_gpu": 5578.64,
|
| 2170 |
+
"total_tokens": 33204993
|
| 2171 |
+
},
|
| 2172 |
+
{
|
| 2173 |
+
"epoch": 2.8764940239043826,
|
| 2174 |
+
"grad_norm": 0.310546875,
|
| 2175 |
+
"learning_rate": 6.287790106757396e-08,
|
| 2176 |
+
"loss": 0.9429,
|
| 2177 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2178 |
+
"memory/max_active (GiB)": 64.91,
|
| 2179 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2180 |
+
"step": 181,
|
| 2181 |
+
"tokens_per_second_per_gpu": 6034.66,
|
| 2182 |
+
"total_tokens": 33396379
|
| 2183 |
+
},
|
| 2184 |
+
{
|
| 2185 |
+
"epoch": 2.8924302788844622,
|
| 2186 |
+
"grad_norm": 0.318359375,
|
| 2187 |
+
"learning_rate": 4.367921058866187e-08,
|
| 2188 |
+
"loss": 0.959,
|
| 2189 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2190 |
+
"memory/max_active (GiB)": 64.91,
|
| 2191 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2192 |
+
"step": 182,
|
| 2193 |
+
"tokens_per_second_per_gpu": 5841.56,
|
| 2194 |
+
"total_tokens": 33579725
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.908366533864542,
|
| 2198 |
+
"grad_norm": 0.33984375,
|
| 2199 |
+
"learning_rate": 2.796202818819871e-08,
|
| 2200 |
+
"loss": 1.0166,
|
| 2201 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2202 |
+
"memory/max_active (GiB)": 64.91,
|
| 2203 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2204 |
+
"step": 183,
|
| 2205 |
+
"tokens_per_second_per_gpu": 5736.29,
|
| 2206 |
+
"total_tokens": 33766220
|
| 2207 |
+
},
|
| 2208 |
+
{
|
| 2209 |
+
"epoch": 2.9243027888446216,
|
| 2210 |
+
"grad_norm": 0.322265625,
|
| 2211 |
+
"learning_rate": 1.5731849821833955e-08,
|
| 2212 |
+
"loss": 0.9907,
|
| 2213 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2214 |
+
"memory/max_active (GiB)": 64.91,
|
| 2215 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2216 |
+
"step": 184,
|
| 2217 |
+
"tokens_per_second_per_gpu": 5704.78,
|
| 2218 |
+
"total_tokens": 33944763
|
| 2219 |
+
},
|
| 2220 |
+
{
|
| 2221 |
+
"epoch": 2.9402390438247012,
|
| 2222 |
+
"grad_norm": 0.326171875,
|
| 2223 |
+
"learning_rate": 6.992952116013918e-09,
|
| 2224 |
+
"loss": 0.9478,
|
| 2225 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2226 |
+
"memory/max_active (GiB)": 64.91,
|
| 2227 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2228 |
+
"step": 185,
|
| 2229 |
+
"tokens_per_second_per_gpu": 5773.31,
|
| 2230 |
+
"total_tokens": 34127443
|
| 2231 |
+
},
|
| 2232 |
+
{
|
| 2233 |
+
"epoch": 2.956175298804781,
|
| 2234 |
+
"grad_norm": 0.349609375,
|
| 2235 |
+
"learning_rate": 1.7483908725357546e-09,
|
| 2236 |
+
"loss": 1.0122,
|
| 2237 |
+
"memory/device_reserved (GiB)": 76.38,
|
| 2238 |
+
"memory/max_active (GiB)": 64.91,
|
| 2239 |
+
"memory/max_allocated (GiB)": 64.91,
|
| 2240 |
+
"step": 186,
|
| 2241 |
+
"tokens_per_second_per_gpu": 5785.44,
|
| 2242 |
+
"total_tokens": 34306859
|
| 2243 |
+
}
|
| 2244 |
+
],
|
| 2245 |
+
"logging_steps": 1,
|
| 2246 |
+
"max_steps": 186,
|
| 2247 |
+
"num_input_tokens_seen": 0,
|
| 2248 |
+
"num_train_epochs": 3,
|
| 2249 |
+
"save_steps": 62,
|
| 2250 |
+
"stateful_callbacks": {
|
| 2251 |
+
"TrainerControl": {
|
| 2252 |
+
"args": {
|
| 2253 |
+
"should_epoch_stop": false,
|
| 2254 |
+
"should_evaluate": false,
|
| 2255 |
+
"should_log": false,
|
| 2256 |
+
"should_save": true,
|
| 2257 |
+
"should_training_stop": true
|
| 2258 |
+
},
|
| 2259 |
+
"attributes": {}
|
| 2260 |
+
}
|
| 2261 |
+
},
|
| 2262 |
+
"total_flos": 2.2082055574021734e+18,
|
| 2263 |
+
"train_batch_size": 1,
|
| 2264 |
+
"trial_name": null,
|
| 2265 |
+
"trial_params": null
|
| 2266 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|