Training in progress, step 442, checkpoint
Browse files- .gitattributes +1 -0
- last-checkpoint/added_tokens.json +28 -0
- last-checkpoint/chat_template.jinja +99 -0
- last-checkpoint/config.json +49 -0
- last-checkpoint/generation_config.json +9 -0
- last-checkpoint/merges.txt +0 -0
- last-checkpoint/model.safetensors +3 -0
- last-checkpoint/optimizer.pt +3 -0
- last-checkpoint/rng_state.pth +3 -0
- last-checkpoint/scheduler.pt +3 -0
- last-checkpoint/special_tokens_map.json +25 -0
- last-checkpoint/tokenizer.json +3 -0
- last-checkpoint/tokenizer_config.json +240 -0
- last-checkpoint/trainer_state.json +3128 -0
- last-checkpoint/training_args.bin +3 -0
- last-checkpoint/vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -34,3 +34,4 @@ saved_model/**/* 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
|
|
|
|
|
|
| 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
|
| 37 |
+
last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
last-checkpoint/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 |
+
}
|
last-checkpoint/chat_template.jinja
ADDED
|
@@ -0,0 +1,99 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 forward_message in messages %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- set message = messages[index] %}
|
| 21 |
+
{%- set current_content = message.content if message.content is defined and message.content is not none else '' %}
|
| 22 |
+
{%- set tool_start = '<tool_response>' %}
|
| 23 |
+
{%- set tool_start_length = tool_start|length %}
|
| 24 |
+
{%- set start_of_message = current_content[:tool_start_length] %}
|
| 25 |
+
{%- set tool_end = '</tool_response>' %}
|
| 26 |
+
{%- set tool_end_length = tool_end|length %}
|
| 27 |
+
{%- set start_pos = (current_content|length) - tool_end_length %}
|
| 28 |
+
{%- if start_pos < 0 %}
|
| 29 |
+
{%- set start_pos = 0 %}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- set end_of_message = current_content[start_pos:] %}
|
| 32 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
|
| 33 |
+
{%- set ns.multi_step_tool = false %}
|
| 34 |
+
{%- set ns.last_query_index = index %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- endfor %}
|
| 37 |
+
{%- for message in messages %}
|
| 38 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 39 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 40 |
+
{%- elif message.role == "assistant" %}
|
| 41 |
+
{%- set m_content = message.content if message.content is defined and message.content is not none else '' %}
|
| 42 |
+
{%- set content = m_content %}
|
| 43 |
+
{%- set reasoning_content = '' %}
|
| 44 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 45 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 46 |
+
{%- else %}
|
| 47 |
+
{%- if '</think>' in m_content %}
|
| 48 |
+
{%- set content = (m_content.split('</think>')|last).lstrip('\n') %}
|
| 49 |
+
{%- set reasoning_content = (m_content.split('</think>')|first).rstrip('\n') %}
|
| 50 |
+
{%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
|
| 51 |
+
{%- endif %}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 54 |
+
{%- if loop.last or (not loop.last and (not reasoning_content.strip() == '')) %}
|
| 55 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 56 |
+
{%- else %}
|
| 57 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- else %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{%- if message.tool_calls %}
|
| 63 |
+
{%- for tool_call in message.tool_calls %}
|
| 64 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 65 |
+
{{- '\n' }}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- if tool_call.function %}
|
| 68 |
+
{%- set tool_call = tool_call.function %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 71 |
+
{{- tool_call.name }}
|
| 72 |
+
{{- '", "arguments": ' }}
|
| 73 |
+
{%- if tool_call.arguments is string %}
|
| 74 |
+
{{- tool_call.arguments }}
|
| 75 |
+
{%- else %}
|
| 76 |
+
{{- tool_call.arguments | tojson }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '}\n</tool_call>' }}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{{- '<|im_end|>\n' }}
|
| 82 |
+
{%- elif message.role == "tool" %}
|
| 83 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 84 |
+
{{- '<|im_start|>user' }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '\n<tool_response>\n' }}
|
| 87 |
+
{{- message.content }}
|
| 88 |
+
{{- '\n</tool_response>' }}
|
| 89 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 90 |
+
{{- '<|im_end|>\n' }}
|
| 91 |
+
{%- endif %}
|
| 92 |
+
{%- endif %}
|
| 93 |
+
{%- endfor %}
|
| 94 |
+
{%- if add_generation_prompt %}
|
| 95 |
+
{{- '<|im_start|>assistant\n' }}
|
| 96 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 97 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- endif %}
|
last-checkpoint/config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 1280,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 3840,
|
| 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 |
+
],
|
| 32 |
+
"max_position_embeddings": 8192,
|
| 33 |
+
"max_window_layers": 16,
|
| 34 |
+
"model_type": "qwen3",
|
| 35 |
+
"num_attention_heads": 16,
|
| 36 |
+
"num_hidden_layers": 16,
|
| 37 |
+
"num_key_value_heads": 8,
|
| 38 |
+
"pad_token_id": 151654,
|
| 39 |
+
"rms_norm_eps": 1e-06,
|
| 40 |
+
"rope_scaling": null,
|
| 41 |
+
"rope_theta": 10000,
|
| 42 |
+
"sliding_window": null,
|
| 43 |
+
"tie_word_embeddings": true,
|
| 44 |
+
"transformers_version": "4.57.1",
|
| 45 |
+
"unsloth_version": "2025.11.1",
|
| 46 |
+
"use_cache": true,
|
| 47 |
+
"use_sliding_window": false,
|
| 48 |
+
"vocab_size": 151669
|
| 49 |
+
}
|
last-checkpoint/generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645
|
| 5 |
+
],
|
| 6 |
+
"max_length": 8192,
|
| 7 |
+
"pad_token_id": 151654,
|
| 8 |
+
"transformers_version": "4.57.1"
|
| 9 |
+
}
|
last-checkpoint/merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
last-checkpoint/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bffa2eb75d6f942ffb07cb2cec03eb820da89bb47d6f11e056bb0635696d2275
|
| 3 |
+
size 1111902928
|
last-checkpoint/optimizer.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c75cbef9cd95dfd4e0ef43e3fa61af711ed219408f0b20f2c6d8d1b55a56bdb2
|
| 3 |
+
size 2288456331
|
last-checkpoint/rng_state.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e831a926501c469a9775d4b96fe9f086ccb9933946219ebf4fe959ebd9224d3
|
| 3 |
+
size 14709
|
last-checkpoint/scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d415e1f77dfc6801ebed818c2a5ef490db2aa6f2d96fe9a23307103fc3461014
|
| 3 |
+
size 1465
|
last-checkpoint/special_tokens_map.json
ADDED
|
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": "<|vision_pad|>"
|
| 25 |
+
}
|
last-checkpoint/tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
last-checkpoint/tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 40960,
|
| 235 |
+
"pad_token": "<|vision_pad|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
last-checkpoint/trainer_state.json
ADDED
|
@@ -0,0 +1,3128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.011008888681330656,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 442,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 2.4906987966811438e-05,
|
| 14 |
+
"grad_norm": 1.4296875,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 2.5993,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 4.9813975933622875e-05,
|
| 21 |
+
"grad_norm": 1.296875,
|
| 22 |
+
"learning_rate": 2.2624434389140273e-06,
|
| 23 |
+
"loss": 2.5577,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 7.472096390043431e-05,
|
| 28 |
+
"grad_norm": 1.1640625,
|
| 29 |
+
"learning_rate": 4.5248868778280546e-06,
|
| 30 |
+
"loss": 2.5977,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 9.962795186724575e-05,
|
| 35 |
+
"grad_norm": 1.5234375,
|
| 36 |
+
"learning_rate": 6.787330316742082e-06,
|
| 37 |
+
"loss": 2.5585,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0001245349398340572,
|
| 42 |
+
"grad_norm": 1.21875,
|
| 43 |
+
"learning_rate": 9.049773755656109e-06,
|
| 44 |
+
"loss": 2.503,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.00014944192780086863,
|
| 49 |
+
"grad_norm": 1.1171875,
|
| 50 |
+
"learning_rate": 1.1312217194570136e-05,
|
| 51 |
+
"loss": 2.6021,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.00017434891576768006,
|
| 56 |
+
"grad_norm": 1.1015625,
|
| 57 |
+
"learning_rate": 1.3574660633484164e-05,
|
| 58 |
+
"loss": 2.4201,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.0001992559037344915,
|
| 63 |
+
"grad_norm": 1.109375,
|
| 64 |
+
"learning_rate": 1.583710407239819e-05,
|
| 65 |
+
"loss": 2.5722,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.00022416289170130294,
|
| 70 |
+
"grad_norm": 1.078125,
|
| 71 |
+
"learning_rate": 1.8099547511312218e-05,
|
| 72 |
+
"loss": 2.5791,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0002490698796681144,
|
| 77 |
+
"grad_norm": 1.2109375,
|
| 78 |
+
"learning_rate": 2.0361990950226245e-05,
|
| 79 |
+
"loss": 2.6173,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0002739768676349258,
|
| 84 |
+
"grad_norm": 0.796875,
|
| 85 |
+
"learning_rate": 2.262443438914027e-05,
|
| 86 |
+
"loss": 2.5212,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.00029888385560173725,
|
| 91 |
+
"grad_norm": 0.7109375,
|
| 92 |
+
"learning_rate": 2.4886877828054298e-05,
|
| 93 |
+
"loss": 2.3938,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.0003237908435685487,
|
| 98 |
+
"grad_norm": 0.54296875,
|
| 99 |
+
"learning_rate": 2.7149321266968327e-05,
|
| 100 |
+
"loss": 2.5098,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0003486978315353601,
|
| 105 |
+
"grad_norm": 0.498046875,
|
| 106 |
+
"learning_rate": 2.9411764705882354e-05,
|
| 107 |
+
"loss": 2.5943,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.00037360481950217156,
|
| 112 |
+
"grad_norm": 0.5,
|
| 113 |
+
"learning_rate": 3.167420814479638e-05,
|
| 114 |
+
"loss": 2.62,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.000398511807468983,
|
| 119 |
+
"grad_norm": 0.44140625,
|
| 120 |
+
"learning_rate": 3.39366515837104e-05,
|
| 121 |
+
"loss": 2.5929,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.00042341879543579444,
|
| 126 |
+
"grad_norm": 0.41796875,
|
| 127 |
+
"learning_rate": 3.6199095022624436e-05,
|
| 128 |
+
"loss": 2.4759,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.0004483257834026059,
|
| 133 |
+
"grad_norm": 0.357421875,
|
| 134 |
+
"learning_rate": 3.846153846153846e-05,
|
| 135 |
+
"loss": 2.4947,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.0004732327713694173,
|
| 140 |
+
"grad_norm": 0.298828125,
|
| 141 |
+
"learning_rate": 4.072398190045249e-05,
|
| 142 |
+
"loss": 2.5114,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.0004981397593362288,
|
| 147 |
+
"grad_norm": 0.353515625,
|
| 148 |
+
"learning_rate": 4.2986425339366516e-05,
|
| 149 |
+
"loss": 2.5178,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.0005230467473030402,
|
| 154 |
+
"grad_norm": 0.3046875,
|
| 155 |
+
"learning_rate": 4.524886877828054e-05,
|
| 156 |
+
"loss": 2.5433,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.0005479537352698516,
|
| 161 |
+
"grad_norm": 0.259765625,
|
| 162 |
+
"learning_rate": 4.751131221719457e-05,
|
| 163 |
+
"loss": 2.4161,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.0005728607232366631,
|
| 168 |
+
"grad_norm": 0.255859375,
|
| 169 |
+
"learning_rate": 4.9773755656108595e-05,
|
| 170 |
+
"loss": 2.4005,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0005977677112034745,
|
| 175 |
+
"grad_norm": 0.2431640625,
|
| 176 |
+
"learning_rate": 5.203619909502263e-05,
|
| 177 |
+
"loss": 2.503,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.0006226746991702859,
|
| 182 |
+
"grad_norm": 0.228515625,
|
| 183 |
+
"learning_rate": 5.4298642533936655e-05,
|
| 184 |
+
"loss": 2.4587,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.0006475816871370974,
|
| 189 |
+
"grad_norm": 0.2451171875,
|
| 190 |
+
"learning_rate": 5.656108597285068e-05,
|
| 191 |
+
"loss": 2.4831,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.0006724886751039088,
|
| 196 |
+
"grad_norm": 0.26171875,
|
| 197 |
+
"learning_rate": 5.882352941176471e-05,
|
| 198 |
+
"loss": 2.3818,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.0006973956630707203,
|
| 203 |
+
"grad_norm": 0.234375,
|
| 204 |
+
"learning_rate": 6.108597285067873e-05,
|
| 205 |
+
"loss": 2.4358,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.0007223026510375317,
|
| 210 |
+
"grad_norm": 0.2578125,
|
| 211 |
+
"learning_rate": 6.334841628959275e-05,
|
| 212 |
+
"loss": 2.3935,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.0007472096390043431,
|
| 217 |
+
"grad_norm": 0.240234375,
|
| 218 |
+
"learning_rate": 6.561085972850679e-05,
|
| 219 |
+
"loss": 2.4789,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.0007721166269711546,
|
| 224 |
+
"grad_norm": 0.2373046875,
|
| 225 |
+
"learning_rate": 6.78733031674208e-05,
|
| 226 |
+
"loss": 2.5053,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.000797023614937966,
|
| 231 |
+
"grad_norm": 0.21484375,
|
| 232 |
+
"learning_rate": 7.013574660633484e-05,
|
| 233 |
+
"loss": 2.3181,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.0008219306029047774,
|
| 238 |
+
"grad_norm": 0.208984375,
|
| 239 |
+
"learning_rate": 7.239819004524887e-05,
|
| 240 |
+
"loss": 2.3652,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.0008468375908715889,
|
| 245 |
+
"grad_norm": 0.2119140625,
|
| 246 |
+
"learning_rate": 7.466063348416289e-05,
|
| 247 |
+
"loss": 2.4159,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.0008717445788384003,
|
| 252 |
+
"grad_norm": 0.212890625,
|
| 253 |
+
"learning_rate": 7.692307692307693e-05,
|
| 254 |
+
"loss": 2.3582,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.0008966515668052118,
|
| 259 |
+
"grad_norm": 0.21484375,
|
| 260 |
+
"learning_rate": 7.918552036199095e-05,
|
| 261 |
+
"loss": 2.4828,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.0009215585547720232,
|
| 266 |
+
"grad_norm": 0.2041015625,
|
| 267 |
+
"learning_rate": 8.144796380090498e-05,
|
| 268 |
+
"loss": 2.4326,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.0009464655427388346,
|
| 273 |
+
"grad_norm": 0.1875,
|
| 274 |
+
"learning_rate": 8.3710407239819e-05,
|
| 275 |
+
"loss": 2.4593,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.0009713725307056461,
|
| 280 |
+
"grad_norm": 0.1875,
|
| 281 |
+
"learning_rate": 8.597285067873303e-05,
|
| 282 |
+
"loss": 2.4074,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.0009962795186724575,
|
| 287 |
+
"grad_norm": 0.1884765625,
|
| 288 |
+
"learning_rate": 8.823529411764706e-05,
|
| 289 |
+
"loss": 2.2908,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.001021186506639269,
|
| 294 |
+
"grad_norm": 0.1845703125,
|
| 295 |
+
"learning_rate": 9.049773755656108e-05,
|
| 296 |
+
"loss": 2.2791,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.0010460934946060804,
|
| 301 |
+
"grad_norm": 0.1953125,
|
| 302 |
+
"learning_rate": 9.276018099547512e-05,
|
| 303 |
+
"loss": 2.3716,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.001071000482572892,
|
| 308 |
+
"grad_norm": 0.2001953125,
|
| 309 |
+
"learning_rate": 9.502262443438914e-05,
|
| 310 |
+
"loss": 2.2369,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.0010959074705397033,
|
| 315 |
+
"grad_norm": 0.1875,
|
| 316 |
+
"learning_rate": 9.728506787330317e-05,
|
| 317 |
+
"loss": 2.5227,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.0011208144585065148,
|
| 322 |
+
"grad_norm": 0.197265625,
|
| 323 |
+
"learning_rate": 9.954751131221719e-05,
|
| 324 |
+
"loss": 2.4047,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.0011457214464733261,
|
| 329 |
+
"grad_norm": 0.1865234375,
|
| 330 |
+
"learning_rate": 0.00010180995475113122,
|
| 331 |
+
"loss": 2.4256,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.0011706284344401377,
|
| 336 |
+
"grad_norm": 0.185546875,
|
| 337 |
+
"learning_rate": 0.00010407239819004526,
|
| 338 |
+
"loss": 2.3188,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.001195535422406949,
|
| 343 |
+
"grad_norm": 0.193359375,
|
| 344 |
+
"learning_rate": 0.00010633484162895928,
|
| 345 |
+
"loss": 2.4604,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.0012204424103737605,
|
| 350 |
+
"grad_norm": 0.18359375,
|
| 351 |
+
"learning_rate": 0.00010859728506787331,
|
| 352 |
+
"loss": 2.3848,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.0012453493983405719,
|
| 357 |
+
"grad_norm": 0.173828125,
|
| 358 |
+
"learning_rate": 0.00011085972850678733,
|
| 359 |
+
"loss": 2.3164,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.0012702563863073834,
|
| 364 |
+
"grad_norm": 0.2490234375,
|
| 365 |
+
"learning_rate": 0.00011312217194570136,
|
| 366 |
+
"loss": 2.3475,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.0012951633742741948,
|
| 371 |
+
"grad_norm": 0.173828125,
|
| 372 |
+
"learning_rate": 0.0001153846153846154,
|
| 373 |
+
"loss": 2.3531,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.0013200703622410063,
|
| 378 |
+
"grad_norm": 0.171875,
|
| 379 |
+
"learning_rate": 0.00011764705882352942,
|
| 380 |
+
"loss": 2.4035,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.0013449773502078176,
|
| 385 |
+
"grad_norm": 0.1669921875,
|
| 386 |
+
"learning_rate": 0.00011990950226244345,
|
| 387 |
+
"loss": 2.3487,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0013698843381746292,
|
| 392 |
+
"grad_norm": 0.1708984375,
|
| 393 |
+
"learning_rate": 0.00012217194570135747,
|
| 394 |
+
"loss": 2.2191,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.0013947913261414405,
|
| 399 |
+
"grad_norm": 0.1845703125,
|
| 400 |
+
"learning_rate": 0.0001244343891402715,
|
| 401 |
+
"loss": 2.4777,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.001419698314108252,
|
| 406 |
+
"grad_norm": 0.1669921875,
|
| 407 |
+
"learning_rate": 0.0001266968325791855,
|
| 408 |
+
"loss": 2.3476,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.0014446053020750634,
|
| 413 |
+
"grad_norm": 0.177734375,
|
| 414 |
+
"learning_rate": 0.00012895927601809957,
|
| 415 |
+
"loss": 2.2576,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.001469512290041875,
|
| 420 |
+
"grad_norm": 0.1845703125,
|
| 421 |
+
"learning_rate": 0.00013122171945701357,
|
| 422 |
+
"loss": 2.3497,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.0014944192780086863,
|
| 427 |
+
"grad_norm": 0.1787109375,
|
| 428 |
+
"learning_rate": 0.0001334841628959276,
|
| 429 |
+
"loss": 2.327,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.0015193262659754978,
|
| 434 |
+
"grad_norm": 0.1884765625,
|
| 435 |
+
"learning_rate": 0.0001357466063348416,
|
| 436 |
+
"loss": 2.333,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.0015442332539423091,
|
| 441 |
+
"grad_norm": 0.1640625,
|
| 442 |
+
"learning_rate": 0.00013800904977375567,
|
| 443 |
+
"loss": 2.3042,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.0015691402419091207,
|
| 448 |
+
"grad_norm": 0.1611328125,
|
| 449 |
+
"learning_rate": 0.00014027149321266968,
|
| 450 |
+
"loss": 2.1978,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.001594047229875932,
|
| 455 |
+
"grad_norm": 0.1728515625,
|
| 456 |
+
"learning_rate": 0.0001425339366515837,
|
| 457 |
+
"loss": 2.4038,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.0016189542178427435,
|
| 462 |
+
"grad_norm": 0.171875,
|
| 463 |
+
"learning_rate": 0.00014479638009049775,
|
| 464 |
+
"loss": 2.2969,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.0016438612058095549,
|
| 469 |
+
"grad_norm": 0.169921875,
|
| 470 |
+
"learning_rate": 0.00014705882352941178,
|
| 471 |
+
"loss": 2.3699,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.0016687681937763664,
|
| 476 |
+
"grad_norm": 0.1689453125,
|
| 477 |
+
"learning_rate": 0.00014932126696832579,
|
| 478 |
+
"loss": 2.3437,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.0016936751817431778,
|
| 483 |
+
"grad_norm": 0.1708984375,
|
| 484 |
+
"learning_rate": 0.00015158371040723982,
|
| 485 |
+
"loss": 2.4376,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.0017185821697099893,
|
| 490 |
+
"grad_norm": 0.1689453125,
|
| 491 |
+
"learning_rate": 0.00015384615384615385,
|
| 492 |
+
"loss": 2.3433,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.0017434891576768006,
|
| 497 |
+
"grad_norm": 0.181640625,
|
| 498 |
+
"learning_rate": 0.00015610859728506788,
|
| 499 |
+
"loss": 2.3733,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.0017683961456436122,
|
| 504 |
+
"grad_norm": 0.16796875,
|
| 505 |
+
"learning_rate": 0.0001583710407239819,
|
| 506 |
+
"loss": 2.3686,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.0017933031336104235,
|
| 511 |
+
"grad_norm": 0.1796875,
|
| 512 |
+
"learning_rate": 0.00016063348416289595,
|
| 513 |
+
"loss": 2.2983,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.001818210121577235,
|
| 518 |
+
"grad_norm": 0.1611328125,
|
| 519 |
+
"learning_rate": 0.00016289592760180996,
|
| 520 |
+
"loss": 2.4371,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.0018431171095440464,
|
| 525 |
+
"grad_norm": 0.1748046875,
|
| 526 |
+
"learning_rate": 0.000165158371040724,
|
| 527 |
+
"loss": 2.187,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.001868024097510858,
|
| 532 |
+
"grad_norm": 0.19140625,
|
| 533 |
+
"learning_rate": 0.000167420814479638,
|
| 534 |
+
"loss": 2.3516,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.0018929310854776693,
|
| 539 |
+
"grad_norm": 0.1728515625,
|
| 540 |
+
"learning_rate": 0.00016968325791855206,
|
| 541 |
+
"loss": 2.3696,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.0019178380734444808,
|
| 546 |
+
"grad_norm": 0.1767578125,
|
| 547 |
+
"learning_rate": 0.00017194570135746606,
|
| 548 |
+
"loss": 2.257,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.0019427450614112921,
|
| 553 |
+
"grad_norm": 0.16796875,
|
| 554 |
+
"learning_rate": 0.0001742081447963801,
|
| 555 |
+
"loss": 2.3406,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.0019676520493781035,
|
| 560 |
+
"grad_norm": 0.16796875,
|
| 561 |
+
"learning_rate": 0.00017647058823529413,
|
| 562 |
+
"loss": 2.2555,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.001992559037344915,
|
| 567 |
+
"grad_norm": 0.1640625,
|
| 568 |
+
"learning_rate": 0.00017873303167420816,
|
| 569 |
+
"loss": 2.3142,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.0020174660253117266,
|
| 574 |
+
"grad_norm": 0.1748046875,
|
| 575 |
+
"learning_rate": 0.00018099547511312217,
|
| 576 |
+
"loss": 2.2988,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.002042373013278538,
|
| 581 |
+
"grad_norm": 0.1748046875,
|
| 582 |
+
"learning_rate": 0.0001832579185520362,
|
| 583 |
+
"loss": 2.3889,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.002067280001245349,
|
| 588 |
+
"grad_norm": 0.1767578125,
|
| 589 |
+
"learning_rate": 0.00018552036199095024,
|
| 590 |
+
"loss": 2.3014,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.0020921869892121608,
|
| 595 |
+
"grad_norm": 0.1630859375,
|
| 596 |
+
"learning_rate": 0.00018778280542986427,
|
| 597 |
+
"loss": 2.2278,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.0021170939771789723,
|
| 602 |
+
"grad_norm": 0.162109375,
|
| 603 |
+
"learning_rate": 0.00019004524886877827,
|
| 604 |
+
"loss": 2.343,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.002142000965145784,
|
| 609 |
+
"grad_norm": 0.1787109375,
|
| 610 |
+
"learning_rate": 0.00019230769230769233,
|
| 611 |
+
"loss": 2.3358,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.002166907953112595,
|
| 616 |
+
"grad_norm": 0.1767578125,
|
| 617 |
+
"learning_rate": 0.00019457013574660634,
|
| 618 |
+
"loss": 2.3003,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.0021918149410794065,
|
| 623 |
+
"grad_norm": 0.1689453125,
|
| 624 |
+
"learning_rate": 0.00019683257918552037,
|
| 625 |
+
"loss": 2.306,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.002216721929046218,
|
| 630 |
+
"grad_norm": 0.1806640625,
|
| 631 |
+
"learning_rate": 0.00019909502262443438,
|
| 632 |
+
"loss": 2.3809,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.0022416289170130296,
|
| 637 |
+
"grad_norm": 0.1689453125,
|
| 638 |
+
"learning_rate": 0.0002013574660633484,
|
| 639 |
+
"loss": 2.3923,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.0022665359049798407,
|
| 644 |
+
"grad_norm": 0.1640625,
|
| 645 |
+
"learning_rate": 0.00020361990950226245,
|
| 646 |
+
"loss": 2.2871,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.0022914428929466523,
|
| 651 |
+
"grad_norm": 0.1640625,
|
| 652 |
+
"learning_rate": 0.00020588235294117645,
|
| 653 |
+
"loss": 2.1614,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.002316349880913464,
|
| 658 |
+
"grad_norm": 0.171875,
|
| 659 |
+
"learning_rate": 0.0002081447963800905,
|
| 660 |
+
"loss": 2.4,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.0023412568688802753,
|
| 665 |
+
"grad_norm": 0.177734375,
|
| 666 |
+
"learning_rate": 0.00021040723981900452,
|
| 667 |
+
"loss": 2.2232,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.0023661638568470865,
|
| 672 |
+
"grad_norm": 0.17578125,
|
| 673 |
+
"learning_rate": 0.00021266968325791855,
|
| 674 |
+
"loss": 2.2975,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.002391070844813898,
|
| 679 |
+
"grad_norm": 0.1591796875,
|
| 680 |
+
"learning_rate": 0.00021493212669683259,
|
| 681 |
+
"loss": 2.3356,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.0024159778327807096,
|
| 686 |
+
"grad_norm": 0.171875,
|
| 687 |
+
"learning_rate": 0.00021719457013574662,
|
| 688 |
+
"loss": 2.1867,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.002440884820747521,
|
| 693 |
+
"grad_norm": 0.17578125,
|
| 694 |
+
"learning_rate": 0.00021945701357466062,
|
| 695 |
+
"loss": 2.3016,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.002465791808714332,
|
| 700 |
+
"grad_norm": 0.1640625,
|
| 701 |
+
"learning_rate": 0.00022171945701357466,
|
| 702 |
+
"loss": 2.1936,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.0024906987966811438,
|
| 707 |
+
"grad_norm": 0.1826171875,
|
| 708 |
+
"learning_rate": 0.0002239819004524887,
|
| 709 |
+
"loss": 2.2574,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.0025156057846479553,
|
| 714 |
+
"grad_norm": 0.162109375,
|
| 715 |
+
"learning_rate": 0.00022624434389140272,
|
| 716 |
+
"loss": 2.3231,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.002540512772614767,
|
| 721 |
+
"grad_norm": 0.1689453125,
|
| 722 |
+
"learning_rate": 0.00022850678733031673,
|
| 723 |
+
"loss": 2.2774,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.002565419760581578,
|
| 728 |
+
"grad_norm": 0.1669921875,
|
| 729 |
+
"learning_rate": 0.0002307692307692308,
|
| 730 |
+
"loss": 2.258,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.0025903267485483895,
|
| 735 |
+
"grad_norm": 0.1728515625,
|
| 736 |
+
"learning_rate": 0.0002330316742081448,
|
| 737 |
+
"loss": 2.3177,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.002615233736515201,
|
| 742 |
+
"grad_norm": 0.1787109375,
|
| 743 |
+
"learning_rate": 0.00023529411764705883,
|
| 744 |
+
"loss": 2.2388,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.0026401407244820126,
|
| 749 |
+
"grad_norm": 0.16796875,
|
| 750 |
+
"learning_rate": 0.00023755656108597284,
|
| 751 |
+
"loss": 2.2559,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.0026650477124488237,
|
| 756 |
+
"grad_norm": 0.1767578125,
|
| 757 |
+
"learning_rate": 0.0002398190045248869,
|
| 758 |
+
"loss": 2.3617,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.0026899547004156353,
|
| 763 |
+
"grad_norm": 0.18359375,
|
| 764 |
+
"learning_rate": 0.0002420814479638009,
|
| 765 |
+
"loss": 2.2776,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.002714861688382447,
|
| 770 |
+
"grad_norm": 0.193359375,
|
| 771 |
+
"learning_rate": 0.00024434389140271494,
|
| 772 |
+
"loss": 2.3642,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.0027397686763492583,
|
| 777 |
+
"grad_norm": 0.17578125,
|
| 778 |
+
"learning_rate": 0.000246606334841629,
|
| 779 |
+
"loss": 2.227,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.00276467566431607,
|
| 784 |
+
"grad_norm": 0.2060546875,
|
| 785 |
+
"learning_rate": 0.000248868778280543,
|
| 786 |
+
"loss": 2.3209,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.002789582652282881,
|
| 791 |
+
"grad_norm": 0.181640625,
|
| 792 |
+
"learning_rate": 0.000251131221719457,
|
| 793 |
+
"loss": 2.2919,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.0028144896402496926,
|
| 798 |
+
"grad_norm": 0.1806640625,
|
| 799 |
+
"learning_rate": 0.000253393665158371,
|
| 800 |
+
"loss": 2.2426,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.002839396628216504,
|
| 805 |
+
"grad_norm": 0.2099609375,
|
| 806 |
+
"learning_rate": 0.0002556561085972851,
|
| 807 |
+
"loss": 2.242,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.0028643036161833156,
|
| 812 |
+
"grad_norm": 0.189453125,
|
| 813 |
+
"learning_rate": 0.00025791855203619913,
|
| 814 |
+
"loss": 2.1628,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.0028892106041501268,
|
| 819 |
+
"grad_norm": 0.2021484375,
|
| 820 |
+
"learning_rate": 0.00026018099547511314,
|
| 821 |
+
"loss": 2.0504,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.0029141175921169383,
|
| 826 |
+
"grad_norm": 0.208984375,
|
| 827 |
+
"learning_rate": 0.00026244343891402715,
|
| 828 |
+
"loss": 2.3161,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.00293902458008375,
|
| 833 |
+
"grad_norm": 0.189453125,
|
| 834 |
+
"learning_rate": 0.0002647058823529412,
|
| 835 |
+
"loss": 2.2593,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.0029639315680505614,
|
| 840 |
+
"grad_norm": 0.1943359375,
|
| 841 |
+
"learning_rate": 0.0002669683257918552,
|
| 842 |
+
"loss": 2.302,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.0029888385560173725,
|
| 847 |
+
"grad_norm": 0.177734375,
|
| 848 |
+
"learning_rate": 0.0002692307692307692,
|
| 849 |
+
"loss": 2.2181,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.003013745543984184,
|
| 854 |
+
"grad_norm": 0.240234375,
|
| 855 |
+
"learning_rate": 0.0002714932126696832,
|
| 856 |
+
"loss": 2.2742,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.0030386525319509956,
|
| 861 |
+
"grad_norm": 0.212890625,
|
| 862 |
+
"learning_rate": 0.00027375565610859734,
|
| 863 |
+
"loss": 2.2828,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.003063559519917807,
|
| 868 |
+
"grad_norm": 0.171875,
|
| 869 |
+
"learning_rate": 0.00027601809954751135,
|
| 870 |
+
"loss": 2.1858,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.0030884665078846183,
|
| 875 |
+
"grad_norm": 0.263671875,
|
| 876 |
+
"learning_rate": 0.00027828054298642535,
|
| 877 |
+
"loss": 2.274,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.00311337349585143,
|
| 882 |
+
"grad_norm": 0.1884765625,
|
| 883 |
+
"learning_rate": 0.00028054298642533936,
|
| 884 |
+
"loss": 2.1885,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.0031382804838182413,
|
| 889 |
+
"grad_norm": 0.2470703125,
|
| 890 |
+
"learning_rate": 0.0002828054298642534,
|
| 891 |
+
"loss": 2.1893,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.003163187471785053,
|
| 896 |
+
"grad_norm": 0.19140625,
|
| 897 |
+
"learning_rate": 0.0002850678733031674,
|
| 898 |
+
"loss": 2.1894,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.003188094459751864,
|
| 903 |
+
"grad_norm": 0.1943359375,
|
| 904 |
+
"learning_rate": 0.00028733031674208143,
|
| 905 |
+
"loss": 2.1824,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.0032130014477186756,
|
| 910 |
+
"grad_norm": 0.1875,
|
| 911 |
+
"learning_rate": 0.0002895927601809955,
|
| 912 |
+
"loss": 2.2836,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.003237908435685487,
|
| 917 |
+
"grad_norm": 0.1943359375,
|
| 918 |
+
"learning_rate": 0.00029185520361990955,
|
| 919 |
+
"loss": 2.2123,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.0032628154236522986,
|
| 924 |
+
"grad_norm": 0.1796875,
|
| 925 |
+
"learning_rate": 0.00029411764705882356,
|
| 926 |
+
"loss": 2.1813,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.0032877224116191098,
|
| 931 |
+
"grad_norm": 0.189453125,
|
| 932 |
+
"learning_rate": 0.00029638009049773756,
|
| 933 |
+
"loss": 2.2491,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.0033126293995859213,
|
| 938 |
+
"grad_norm": 0.1689453125,
|
| 939 |
+
"learning_rate": 0.00029864253393665157,
|
| 940 |
+
"loss": 2.2597,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.003337536387552733,
|
| 945 |
+
"grad_norm": 0.1826171875,
|
| 946 |
+
"learning_rate": 0.0003009049773755656,
|
| 947 |
+
"loss": 2.148,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.0033624433755195444,
|
| 952 |
+
"grad_norm": 0.1748046875,
|
| 953 |
+
"learning_rate": 0.00030316742081447964,
|
| 954 |
+
"loss": 2.1086,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.0033873503634863555,
|
| 959 |
+
"grad_norm": 0.19140625,
|
| 960 |
+
"learning_rate": 0.0003054298642533937,
|
| 961 |
+
"loss": 2.3155,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.003412257351453167,
|
| 966 |
+
"grad_norm": 0.169921875,
|
| 967 |
+
"learning_rate": 0.0003076923076923077,
|
| 968 |
+
"loss": 2.2626,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.0034371643394199786,
|
| 973 |
+
"grad_norm": 0.1806640625,
|
| 974 |
+
"learning_rate": 0.0003099547511312217,
|
| 975 |
+
"loss": 2.2672,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.00346207132738679,
|
| 980 |
+
"grad_norm": 0.177734375,
|
| 981 |
+
"learning_rate": 0.00031221719457013577,
|
| 982 |
+
"loss": 2.2411,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.0034869783153536013,
|
| 987 |
+
"grad_norm": 0.1806640625,
|
| 988 |
+
"learning_rate": 0.0003144796380090498,
|
| 989 |
+
"loss": 2.2597,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.003511885303320413,
|
| 994 |
+
"grad_norm": 0.1787109375,
|
| 995 |
+
"learning_rate": 0.0003167420814479638,
|
| 996 |
+
"loss": 2.1941,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.0035367922912872243,
|
| 1001 |
+
"grad_norm": 0.177734375,
|
| 1002 |
+
"learning_rate": 0.0003190045248868778,
|
| 1003 |
+
"loss": 2.2151,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.003561699279254036,
|
| 1008 |
+
"grad_norm": 0.1796875,
|
| 1009 |
+
"learning_rate": 0.0003212669683257919,
|
| 1010 |
+
"loss": 2.2597,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.003586606267220847,
|
| 1015 |
+
"grad_norm": 0.1865234375,
|
| 1016 |
+
"learning_rate": 0.0003235294117647059,
|
| 1017 |
+
"loss": 2.357,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.0036115132551876586,
|
| 1022 |
+
"grad_norm": 0.2119140625,
|
| 1023 |
+
"learning_rate": 0.0003257918552036199,
|
| 1024 |
+
"loss": 2.2361,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.00363642024315447,
|
| 1029 |
+
"grad_norm": 0.1875,
|
| 1030 |
+
"learning_rate": 0.0003280542986425339,
|
| 1031 |
+
"loss": 2.1918,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.0036613272311212816,
|
| 1036 |
+
"grad_norm": 0.193359375,
|
| 1037 |
+
"learning_rate": 0.000330316742081448,
|
| 1038 |
+
"loss": 2.1713,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.0036862342190880928,
|
| 1043 |
+
"grad_norm": 0.18359375,
|
| 1044 |
+
"learning_rate": 0.000332579185520362,
|
| 1045 |
+
"loss": 2.2557,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.0037111412070549043,
|
| 1050 |
+
"grad_norm": 0.185546875,
|
| 1051 |
+
"learning_rate": 0.000334841628959276,
|
| 1052 |
+
"loss": 2.1626,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.003736048195021716,
|
| 1057 |
+
"grad_norm": 0.2197265625,
|
| 1058 |
+
"learning_rate": 0.00033710407239819005,
|
| 1059 |
+
"loss": 2.3502,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.0037609551829885274,
|
| 1064 |
+
"grad_norm": 0.2109375,
|
| 1065 |
+
"learning_rate": 0.0003393665158371041,
|
| 1066 |
+
"loss": 2.0759,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.0037858621709553385,
|
| 1071 |
+
"grad_norm": 0.189453125,
|
| 1072 |
+
"learning_rate": 0.0003416289592760181,
|
| 1073 |
+
"loss": 2.204,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.00381076915892215,
|
| 1078 |
+
"grad_norm": 0.208984375,
|
| 1079 |
+
"learning_rate": 0.0003438914027149321,
|
| 1080 |
+
"loss": 2.2932,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.0038356761468889616,
|
| 1085 |
+
"grad_norm": 0.1943359375,
|
| 1086 |
+
"learning_rate": 0.00034615384615384613,
|
| 1087 |
+
"loss": 2.3221,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.003860583134855773,
|
| 1092 |
+
"grad_norm": 0.2099609375,
|
| 1093 |
+
"learning_rate": 0.0003484162895927602,
|
| 1094 |
+
"loss": 2.3122,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.0038854901228225843,
|
| 1099 |
+
"grad_norm": 0.2158203125,
|
| 1100 |
+
"learning_rate": 0.0003506787330316742,
|
| 1101 |
+
"loss": 2.2034,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.003910397110789396,
|
| 1106 |
+
"grad_norm": 0.1904296875,
|
| 1107 |
+
"learning_rate": 0.00035294117647058826,
|
| 1108 |
+
"loss": 2.1404,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.003935304098756207,
|
| 1113 |
+
"grad_norm": 0.2021484375,
|
| 1114 |
+
"learning_rate": 0.00035520361990950226,
|
| 1115 |
+
"loss": 2.1166,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.0039602110867230185,
|
| 1120 |
+
"grad_norm": 0.19140625,
|
| 1121 |
+
"learning_rate": 0.0003574660633484163,
|
| 1122 |
+
"loss": 2.2004,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.00398511807468983,
|
| 1127 |
+
"grad_norm": 0.2314453125,
|
| 1128 |
+
"learning_rate": 0.00035972850678733033,
|
| 1129 |
+
"loss": 2.2178,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.0040100250626566416,
|
| 1134 |
+
"grad_norm": 0.201171875,
|
| 1135 |
+
"learning_rate": 0.00036199095022624434,
|
| 1136 |
+
"loss": 2.1347,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.004034932050623453,
|
| 1141 |
+
"grad_norm": 0.23046875,
|
| 1142 |
+
"learning_rate": 0.00036425339366515834,
|
| 1143 |
+
"loss": 2.2248,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.004059839038590265,
|
| 1148 |
+
"grad_norm": 0.1865234375,
|
| 1149 |
+
"learning_rate": 0.0003665158371040724,
|
| 1150 |
+
"loss": 2.2249,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.004084746026557076,
|
| 1155 |
+
"grad_norm": 0.25390625,
|
| 1156 |
+
"learning_rate": 0.00036877828054298646,
|
| 1157 |
+
"loss": 2.1328,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.004109653014523888,
|
| 1162 |
+
"grad_norm": 0.18359375,
|
| 1163 |
+
"learning_rate": 0.00037104072398190047,
|
| 1164 |
+
"loss": 2.2274,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.004134560002490698,
|
| 1169 |
+
"grad_norm": 0.2314453125,
|
| 1170 |
+
"learning_rate": 0.0003733031674208145,
|
| 1171 |
+
"loss": 2.1438,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.00415946699045751,
|
| 1176 |
+
"grad_norm": 0.193359375,
|
| 1177 |
+
"learning_rate": 0.00037556561085972854,
|
| 1178 |
+
"loss": 2.2602,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.0041843739784243215,
|
| 1183 |
+
"grad_norm": 0.2060546875,
|
| 1184 |
+
"learning_rate": 0.00037782805429864254,
|
| 1185 |
+
"loss": 2.2552,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.004209280966391133,
|
| 1190 |
+
"grad_norm": 0.2265625,
|
| 1191 |
+
"learning_rate": 0.00038009049773755655,
|
| 1192 |
+
"loss": 2.1874,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.004234187954357945,
|
| 1197 |
+
"grad_norm": 0.2001953125,
|
| 1198 |
+
"learning_rate": 0.00038235294117647055,
|
| 1199 |
+
"loss": 2.2309,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.004259094942324756,
|
| 1204 |
+
"grad_norm": 0.197265625,
|
| 1205 |
+
"learning_rate": 0.00038461538461538467,
|
| 1206 |
+
"loss": 2.388,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.004284001930291568,
|
| 1211 |
+
"grad_norm": 0.21875,
|
| 1212 |
+
"learning_rate": 0.0003868778280542987,
|
| 1213 |
+
"loss": 2.1057,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.004308908918258379,
|
| 1218 |
+
"grad_norm": 0.19921875,
|
| 1219 |
+
"learning_rate": 0.0003891402714932127,
|
| 1220 |
+
"loss": 2.1499,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.00433381590622519,
|
| 1225 |
+
"grad_norm": 0.255859375,
|
| 1226 |
+
"learning_rate": 0.0003914027149321267,
|
| 1227 |
+
"loss": 2.3507,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.0043587228941920015,
|
| 1232 |
+
"grad_norm": 0.2060546875,
|
| 1233 |
+
"learning_rate": 0.00039366515837104075,
|
| 1234 |
+
"loss": 2.2116,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.004383629882158813,
|
| 1239 |
+
"grad_norm": 0.2177734375,
|
| 1240 |
+
"learning_rate": 0.00039592760180995475,
|
| 1241 |
+
"loss": 2.0832,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.0044085368701256246,
|
| 1246 |
+
"grad_norm": 0.193359375,
|
| 1247 |
+
"learning_rate": 0.00039819004524886876,
|
| 1248 |
+
"loss": 2.2157,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.004433443858092436,
|
| 1253 |
+
"grad_norm": 0.294921875,
|
| 1254 |
+
"learning_rate": 0.0004004524886877828,
|
| 1255 |
+
"loss": 2.219,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.004458350846059248,
|
| 1260 |
+
"grad_norm": 0.185546875,
|
| 1261 |
+
"learning_rate": 0.0004027149321266968,
|
| 1262 |
+
"loss": 2.0963,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.004483257834026059,
|
| 1267 |
+
"grad_norm": 0.2109375,
|
| 1268 |
+
"learning_rate": 0.0004049773755656109,
|
| 1269 |
+
"loss": 2.2279,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.004508164821992871,
|
| 1274 |
+
"grad_norm": 0.1953125,
|
| 1275 |
+
"learning_rate": 0.0004072398190045249,
|
| 1276 |
+
"loss": 2.3016,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.004533071809959681,
|
| 1281 |
+
"grad_norm": 0.2177734375,
|
| 1282 |
+
"learning_rate": 0.0004095022624434389,
|
| 1283 |
+
"loss": 2.2357,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.004557978797926493,
|
| 1288 |
+
"grad_norm": 0.2236328125,
|
| 1289 |
+
"learning_rate": 0.0004117647058823529,
|
| 1290 |
+
"loss": 2.1582,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.0045828857858933045,
|
| 1295 |
+
"grad_norm": 0.1982421875,
|
| 1296 |
+
"learning_rate": 0.00041402714932126697,
|
| 1297 |
+
"loss": 2.1609,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.004607792773860116,
|
| 1302 |
+
"grad_norm": 0.236328125,
|
| 1303 |
+
"learning_rate": 0.000416289592760181,
|
| 1304 |
+
"loss": 2.2191,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.004632699761826928,
|
| 1309 |
+
"grad_norm": 0.220703125,
|
| 1310 |
+
"learning_rate": 0.00041855203619909503,
|
| 1311 |
+
"loss": 2.1683,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.004657606749793739,
|
| 1316 |
+
"grad_norm": 0.21484375,
|
| 1317 |
+
"learning_rate": 0.00042081447963800904,
|
| 1318 |
+
"loss": 2.2875,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.004682513737760551,
|
| 1323 |
+
"grad_norm": 0.2177734375,
|
| 1324 |
+
"learning_rate": 0.0004230769230769231,
|
| 1325 |
+
"loss": 2.2661,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.004707420725727362,
|
| 1330 |
+
"grad_norm": 0.2236328125,
|
| 1331 |
+
"learning_rate": 0.0004253393665158371,
|
| 1332 |
+
"loss": 2.2591,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.004732327713694173,
|
| 1337 |
+
"grad_norm": 0.208984375,
|
| 1338 |
+
"learning_rate": 0.0004276018099547511,
|
| 1339 |
+
"loss": 2.2424,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.0047572347016609845,
|
| 1344 |
+
"grad_norm": 0.2255859375,
|
| 1345 |
+
"learning_rate": 0.00042986425339366517,
|
| 1346 |
+
"loss": 2.2058,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.004782141689627796,
|
| 1351 |
+
"grad_norm": 0.1953125,
|
| 1352 |
+
"learning_rate": 0.00043212669683257923,
|
| 1353 |
+
"loss": 2.1927,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.0048070486775946076,
|
| 1358 |
+
"grad_norm": 0.2138671875,
|
| 1359 |
+
"learning_rate": 0.00043438914027149324,
|
| 1360 |
+
"loss": 2.3613,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.004831955665561419,
|
| 1365 |
+
"grad_norm": 0.1982421875,
|
| 1366 |
+
"learning_rate": 0.00043665158371040724,
|
| 1367 |
+
"loss": 2.1115,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.004856862653528231,
|
| 1372 |
+
"grad_norm": 0.197265625,
|
| 1373 |
+
"learning_rate": 0.00043891402714932125,
|
| 1374 |
+
"loss": 2.1275,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.004881769641495042,
|
| 1379 |
+
"grad_norm": 0.1953125,
|
| 1380 |
+
"learning_rate": 0.0004411764705882353,
|
| 1381 |
+
"loss": 2.3564,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.004906676629461854,
|
| 1386 |
+
"grad_norm": 0.201171875,
|
| 1387 |
+
"learning_rate": 0.0004434389140271493,
|
| 1388 |
+
"loss": 2.1501,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.004931583617428664,
|
| 1393 |
+
"grad_norm": 0.189453125,
|
| 1394 |
+
"learning_rate": 0.0004457013574660634,
|
| 1395 |
+
"loss": 2.2124,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.004956490605395476,
|
| 1400 |
+
"grad_norm": 0.1982421875,
|
| 1401 |
+
"learning_rate": 0.0004479638009049774,
|
| 1402 |
+
"loss": 2.1526,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.0049813975933622875,
|
| 1407 |
+
"grad_norm": 0.19140625,
|
| 1408 |
+
"learning_rate": 0.00045022624434389144,
|
| 1409 |
+
"loss": 2.3222,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.005006304581329099,
|
| 1414 |
+
"grad_norm": 0.1982421875,
|
| 1415 |
+
"learning_rate": 0.00045248868778280545,
|
| 1416 |
+
"loss": 2.2963,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.005031211569295911,
|
| 1421 |
+
"grad_norm": 0.193359375,
|
| 1422 |
+
"learning_rate": 0.00045475113122171945,
|
| 1423 |
+
"loss": 2.3005,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.005056118557262722,
|
| 1428 |
+
"grad_norm": 0.18359375,
|
| 1429 |
+
"learning_rate": 0.00045701357466063346,
|
| 1430 |
+
"loss": 2.2179,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.005081025545229534,
|
| 1435 |
+
"grad_norm": 0.201171875,
|
| 1436 |
+
"learning_rate": 0.0004592760180995475,
|
| 1437 |
+
"loss": 2.1617,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.005105932533196345,
|
| 1442 |
+
"grad_norm": 0.1875,
|
| 1443 |
+
"learning_rate": 0.0004615384615384616,
|
| 1444 |
+
"loss": 2.236,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.005130839521163156,
|
| 1449 |
+
"grad_norm": 0.1953125,
|
| 1450 |
+
"learning_rate": 0.0004638009049773756,
|
| 1451 |
+
"loss": 2.3082,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.0051557465091299675,
|
| 1456 |
+
"grad_norm": 0.1982421875,
|
| 1457 |
+
"learning_rate": 0.0004660633484162896,
|
| 1458 |
+
"loss": 2.2473,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.005180653497096779,
|
| 1463 |
+
"grad_norm": 0.220703125,
|
| 1464 |
+
"learning_rate": 0.00046832579185520365,
|
| 1465 |
+
"loss": 2.277,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.0052055604850635906,
|
| 1470 |
+
"grad_norm": 0.1943359375,
|
| 1471 |
+
"learning_rate": 0.00047058823529411766,
|
| 1472 |
+
"loss": 2.2359,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.005230467473030402,
|
| 1477 |
+
"grad_norm": 0.1787109375,
|
| 1478 |
+
"learning_rate": 0.00047285067873303167,
|
| 1479 |
+
"loss": 2.2038,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.005255374460997214,
|
| 1484 |
+
"grad_norm": 0.2021484375,
|
| 1485 |
+
"learning_rate": 0.00047511312217194567,
|
| 1486 |
+
"loss": 2.1556,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.005280281448964025,
|
| 1491 |
+
"grad_norm": 0.19140625,
|
| 1492 |
+
"learning_rate": 0.0004773755656108598,
|
| 1493 |
+
"loss": 2.2151,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.005305188436930837,
|
| 1498 |
+
"grad_norm": 0.203125,
|
| 1499 |
+
"learning_rate": 0.0004796380090497738,
|
| 1500 |
+
"loss": 2.156,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.005330095424897647,
|
| 1505 |
+
"grad_norm": 0.18359375,
|
| 1506 |
+
"learning_rate": 0.0004819004524886878,
|
| 1507 |
+
"loss": 2.2789,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.005355002412864459,
|
| 1512 |
+
"grad_norm": 0.19921875,
|
| 1513 |
+
"learning_rate": 0.0004841628959276018,
|
| 1514 |
+
"loss": 2.3296,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.0053799094008312705,
|
| 1519 |
+
"grad_norm": 0.2060546875,
|
| 1520 |
+
"learning_rate": 0.00048642533936651587,
|
| 1521 |
+
"loss": 2.1869,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.005404816388798082,
|
| 1526 |
+
"grad_norm": 0.1953125,
|
| 1527 |
+
"learning_rate": 0.0004886877828054299,
|
| 1528 |
+
"loss": 2.2933,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.005429723376764894,
|
| 1533 |
+
"grad_norm": 0.197265625,
|
| 1534 |
+
"learning_rate": 0.0004909502262443439,
|
| 1535 |
+
"loss": 2.1516,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.005454630364731705,
|
| 1540 |
+
"grad_norm": 0.1875,
|
| 1541 |
+
"learning_rate": 0.000493212669683258,
|
| 1542 |
+
"loss": 2.1953,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.005479537352698517,
|
| 1547 |
+
"grad_norm": 0.1904296875,
|
| 1548 |
+
"learning_rate": 0.000495475113122172,
|
| 1549 |
+
"loss": 2.1267,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.005504444340665328,
|
| 1554 |
+
"grad_norm": 0.2080078125,
|
| 1555 |
+
"learning_rate": 0.000497737556561086,
|
| 1556 |
+
"loss": 2.2023,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.00552935132863214,
|
| 1561 |
+
"grad_norm": 0.2001953125,
|
| 1562 |
+
"learning_rate": 0.0005,
|
| 1563 |
+
"loss": 2.1735,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.0055542583165989505,
|
| 1568 |
+
"grad_norm": 0.21484375,
|
| 1569 |
+
"learning_rate": 0.000502262443438914,
|
| 1570 |
+
"loss": 2.2553,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.005579165304565762,
|
| 1575 |
+
"grad_norm": 0.193359375,
|
| 1576 |
+
"learning_rate": 0.000504524886877828,
|
| 1577 |
+
"loss": 2.2067,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.0056040722925325736,
|
| 1582 |
+
"grad_norm": 0.1953125,
|
| 1583 |
+
"learning_rate": 0.000506787330316742,
|
| 1584 |
+
"loss": 2.0946,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.005628979280499385,
|
| 1589 |
+
"grad_norm": 0.1953125,
|
| 1590 |
+
"learning_rate": 0.000509049773755656,
|
| 1591 |
+
"loss": 2.2008,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.005653886268466197,
|
| 1596 |
+
"grad_norm": 0.220703125,
|
| 1597 |
+
"learning_rate": 0.0005113122171945701,
|
| 1598 |
+
"loss": 2.1563,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.005678793256433008,
|
| 1603 |
+
"grad_norm": 0.23828125,
|
| 1604 |
+
"learning_rate": 0.0005135746606334842,
|
| 1605 |
+
"loss": 2.2596,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.00570370024439982,
|
| 1610 |
+
"grad_norm": 0.205078125,
|
| 1611 |
+
"learning_rate": 0.0005158371040723983,
|
| 1612 |
+
"loss": 2.2006,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.005728607232366631,
|
| 1617 |
+
"grad_norm": 0.205078125,
|
| 1618 |
+
"learning_rate": 0.0005180995475113123,
|
| 1619 |
+
"loss": 2.2904,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.005753514220333442,
|
| 1624 |
+
"grad_norm": 0.1884765625,
|
| 1625 |
+
"learning_rate": 0.0005203619909502263,
|
| 1626 |
+
"loss": 2.0868,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.0057784212083002535,
|
| 1631 |
+
"grad_norm": 0.21875,
|
| 1632 |
+
"learning_rate": 0.0005226244343891403,
|
| 1633 |
+
"loss": 2.2382,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.005803328196267065,
|
| 1638 |
+
"grad_norm": 0.193359375,
|
| 1639 |
+
"learning_rate": 0.0005248868778280543,
|
| 1640 |
+
"loss": 2.3368,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.005828235184233877,
|
| 1645 |
+
"grad_norm": 0.216796875,
|
| 1646 |
+
"learning_rate": 0.0005271493212669683,
|
| 1647 |
+
"loss": 2.3023,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.005853142172200688,
|
| 1652 |
+
"grad_norm": 0.1923828125,
|
| 1653 |
+
"learning_rate": 0.0005294117647058824,
|
| 1654 |
+
"loss": 2.2422,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.0058780491601675,
|
| 1659 |
+
"grad_norm": 0.2177734375,
|
| 1660 |
+
"learning_rate": 0.0005316742081447964,
|
| 1661 |
+
"loss": 2.2776,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.005902956148134311,
|
| 1666 |
+
"grad_norm": 0.1875,
|
| 1667 |
+
"learning_rate": 0.0005339366515837104,
|
| 1668 |
+
"loss": 2.1679,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.005927863136101123,
|
| 1673 |
+
"grad_norm": 0.2001953125,
|
| 1674 |
+
"learning_rate": 0.0005361990950226244,
|
| 1675 |
+
"loss": 2.1487,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.0059527701240679335,
|
| 1680 |
+
"grad_norm": 0.1796875,
|
| 1681 |
+
"learning_rate": 0.0005384615384615384,
|
| 1682 |
+
"loss": 2.1256,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.005977677112034745,
|
| 1687 |
+
"grad_norm": 0.1884765625,
|
| 1688 |
+
"learning_rate": 0.0005407239819004524,
|
| 1689 |
+
"loss": 2.0687,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.0060025841000015566,
|
| 1694 |
+
"grad_norm": 0.185546875,
|
| 1695 |
+
"learning_rate": 0.0005429864253393665,
|
| 1696 |
+
"loss": 2.1896,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.006027491087968368,
|
| 1701 |
+
"grad_norm": 0.1884765625,
|
| 1702 |
+
"learning_rate": 0.0005452488687782805,
|
| 1703 |
+
"loss": 2.2213,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.00605239807593518,
|
| 1708 |
+
"grad_norm": 0.1962890625,
|
| 1709 |
+
"learning_rate": 0.0005475113122171947,
|
| 1710 |
+
"loss": 2.1317,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.006077305063901991,
|
| 1715 |
+
"grad_norm": 0.201171875,
|
| 1716 |
+
"learning_rate": 0.0005497737556561087,
|
| 1717 |
+
"loss": 2.1448,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.006102212051868803,
|
| 1722 |
+
"grad_norm": 0.19140625,
|
| 1723 |
+
"learning_rate": 0.0005520361990950227,
|
| 1724 |
+
"loss": 2.1999,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.006127119039835614,
|
| 1729 |
+
"grad_norm": 0.220703125,
|
| 1730 |
+
"learning_rate": 0.0005542986425339367,
|
| 1731 |
+
"loss": 2.092,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.006152026027802425,
|
| 1736 |
+
"grad_norm": 0.185546875,
|
| 1737 |
+
"learning_rate": 0.0005565610859728507,
|
| 1738 |
+
"loss": 2.2419,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.0061769330157692365,
|
| 1743 |
+
"grad_norm": 0.236328125,
|
| 1744 |
+
"learning_rate": 0.0005588235294117647,
|
| 1745 |
+
"loss": 2.1257,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.006201840003736048,
|
| 1750 |
+
"grad_norm": 0.1923828125,
|
| 1751 |
+
"learning_rate": 0.0005610859728506787,
|
| 1752 |
+
"loss": 2.2481,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.00622674699170286,
|
| 1757 |
+
"grad_norm": 0.2421875,
|
| 1758 |
+
"learning_rate": 0.0005633484162895927,
|
| 1759 |
+
"loss": 2.2016,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.006251653979669671,
|
| 1764 |
+
"grad_norm": 0.330078125,
|
| 1765 |
+
"learning_rate": 0.0005656108597285068,
|
| 1766 |
+
"loss": 2.2316,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.006276560967636483,
|
| 1771 |
+
"grad_norm": 0.291015625,
|
| 1772 |
+
"learning_rate": 0.0005678733031674208,
|
| 1773 |
+
"loss": 2.2633,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.006301467955603294,
|
| 1778 |
+
"grad_norm": 0.2275390625,
|
| 1779 |
+
"learning_rate": 0.0005701357466063349,
|
| 1780 |
+
"loss": 2.2316,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.006326374943570106,
|
| 1785 |
+
"grad_norm": 0.224609375,
|
| 1786 |
+
"learning_rate": 0.0005723981900452489,
|
| 1787 |
+
"loss": 2.1864,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.0063512819315369165,
|
| 1792 |
+
"grad_norm": 0.2138671875,
|
| 1793 |
+
"learning_rate": 0.0005746606334841629,
|
| 1794 |
+
"loss": 2.2168,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.006376188919503728,
|
| 1799 |
+
"grad_norm": 0.193359375,
|
| 1800 |
+
"learning_rate": 0.0005769230769230769,
|
| 1801 |
+
"loss": 2.1802,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.0064010959074705396,
|
| 1806 |
+
"grad_norm": 0.2158203125,
|
| 1807 |
+
"learning_rate": 0.000579185520361991,
|
| 1808 |
+
"loss": 2.1992,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.006426002895437351,
|
| 1813 |
+
"grad_norm": 0.2119140625,
|
| 1814 |
+
"learning_rate": 0.000581447963800905,
|
| 1815 |
+
"loss": 2.147,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.006450909883404163,
|
| 1820 |
+
"grad_norm": 0.2099609375,
|
| 1821 |
+
"learning_rate": 0.0005837104072398191,
|
| 1822 |
+
"loss": 2.3566,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.006475816871370974,
|
| 1827 |
+
"grad_norm": 0.1962890625,
|
| 1828 |
+
"learning_rate": 0.0005859728506787331,
|
| 1829 |
+
"loss": 2.1815,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.006500723859337786,
|
| 1834 |
+
"grad_norm": 0.19921875,
|
| 1835 |
+
"learning_rate": 0.0005882352941176471,
|
| 1836 |
+
"loss": 2.2313,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.006525630847304597,
|
| 1841 |
+
"grad_norm": 0.1884765625,
|
| 1842 |
+
"learning_rate": 0.0005904977375565611,
|
| 1843 |
+
"loss": 2.2132,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.006550537835271408,
|
| 1848 |
+
"grad_norm": 0.185546875,
|
| 1849 |
+
"learning_rate": 0.0005927601809954751,
|
| 1850 |
+
"loss": 2.0841,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.0065754448232382195,
|
| 1855 |
+
"grad_norm": 0.1982421875,
|
| 1856 |
+
"learning_rate": 0.0005950226244343891,
|
| 1857 |
+
"loss": 2.1979,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.006600351811205031,
|
| 1862 |
+
"grad_norm": 0.19140625,
|
| 1863 |
+
"learning_rate": 0.0005972850678733031,
|
| 1864 |
+
"loss": 2.1341,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.006625258799171843,
|
| 1869 |
+
"grad_norm": 0.1943359375,
|
| 1870 |
+
"learning_rate": 0.0005995475113122171,
|
| 1871 |
+
"loss": 2.2973,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.006650165787138654,
|
| 1876 |
+
"grad_norm": 0.20703125,
|
| 1877 |
+
"learning_rate": 0.0006018099547511312,
|
| 1878 |
+
"loss": 2.1169,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.006675072775105466,
|
| 1883 |
+
"grad_norm": 0.1943359375,
|
| 1884 |
+
"learning_rate": 0.0006040723981900453,
|
| 1885 |
+
"loss": 2.3145,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.006699979763072277,
|
| 1890 |
+
"grad_norm": 0.220703125,
|
| 1891 |
+
"learning_rate": 0.0006063348416289593,
|
| 1892 |
+
"loss": 2.1839,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.006724886751039089,
|
| 1897 |
+
"grad_norm": 0.23046875,
|
| 1898 |
+
"learning_rate": 0.0006085972850678733,
|
| 1899 |
+
"loss": 2.276,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.0067497937390058995,
|
| 1904 |
+
"grad_norm": 0.2041015625,
|
| 1905 |
+
"learning_rate": 0.0006108597285067874,
|
| 1906 |
+
"loss": 2.1205,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.006774700726972711,
|
| 1911 |
+
"grad_norm": 0.1943359375,
|
| 1912 |
+
"learning_rate": 0.0006131221719457014,
|
| 1913 |
+
"loss": 2.2337,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.0067996077149395226,
|
| 1918 |
+
"grad_norm": 0.2119140625,
|
| 1919 |
+
"learning_rate": 0.0006153846153846154,
|
| 1920 |
+
"loss": 2.2958,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.006824514702906334,
|
| 1925 |
+
"grad_norm": 0.197265625,
|
| 1926 |
+
"learning_rate": 0.0006176470588235294,
|
| 1927 |
+
"loss": 2.1904,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.006849421690873146,
|
| 1932 |
+
"grad_norm": 0.205078125,
|
| 1933 |
+
"learning_rate": 0.0006199095022624434,
|
| 1934 |
+
"loss": 2.2906,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.006874328678839957,
|
| 1939 |
+
"grad_norm": 0.2158203125,
|
| 1940 |
+
"learning_rate": 0.0006221719457013575,
|
| 1941 |
+
"loss": 2.3122,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.006899235666806769,
|
| 1946 |
+
"grad_norm": 0.21484375,
|
| 1947 |
+
"learning_rate": 0.0006244343891402715,
|
| 1948 |
+
"loss": 2.2199,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.00692414265477358,
|
| 1953 |
+
"grad_norm": 0.2119140625,
|
| 1954 |
+
"learning_rate": 0.0006266968325791855,
|
| 1955 |
+
"loss": 2.2455,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.006949049642740391,
|
| 1960 |
+
"grad_norm": 0.21484375,
|
| 1961 |
+
"learning_rate": 0.0006289592760180996,
|
| 1962 |
+
"loss": 2.2406,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.0069739566307072025,
|
| 1967 |
+
"grad_norm": 0.1953125,
|
| 1968 |
+
"learning_rate": 0.0006312217194570136,
|
| 1969 |
+
"loss": 2.3223,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.006998863618674014,
|
| 1974 |
+
"grad_norm": 0.1923828125,
|
| 1975 |
+
"learning_rate": 0.0006334841628959276,
|
| 1976 |
+
"loss": 2.2302,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.007023770606640826,
|
| 1981 |
+
"grad_norm": 0.189453125,
|
| 1982 |
+
"learning_rate": 0.0006357466063348416,
|
| 1983 |
+
"loss": 2.1874,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.007048677594607637,
|
| 1988 |
+
"grad_norm": 0.1904296875,
|
| 1989 |
+
"learning_rate": 0.0006380090497737556,
|
| 1990 |
+
"loss": 2.0713,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.007073584582574449,
|
| 1995 |
+
"grad_norm": 0.193359375,
|
| 1996 |
+
"learning_rate": 0.0006402714932126697,
|
| 1997 |
+
"loss": 2.1518,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.00709849157054126,
|
| 2002 |
+
"grad_norm": 0.1982421875,
|
| 2003 |
+
"learning_rate": 0.0006425339366515838,
|
| 2004 |
+
"loss": 2.1883,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.007123398558508072,
|
| 2009 |
+
"grad_norm": 0.1884765625,
|
| 2010 |
+
"learning_rate": 0.0006447963800904978,
|
| 2011 |
+
"loss": 2.1997,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.0071483055464748825,
|
| 2016 |
+
"grad_norm": 0.1962890625,
|
| 2017 |
+
"learning_rate": 0.0006470588235294118,
|
| 2018 |
+
"loss": 2.2251,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.007173212534441694,
|
| 2023 |
+
"grad_norm": 0.1865234375,
|
| 2024 |
+
"learning_rate": 0.0006493212669683258,
|
| 2025 |
+
"loss": 2.2281,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.0071981195224085056,
|
| 2030 |
+
"grad_norm": 0.1884765625,
|
| 2031 |
+
"learning_rate": 0.0006515837104072398,
|
| 2032 |
+
"loss": 2.2137,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.007223026510375317,
|
| 2037 |
+
"grad_norm": 0.1884765625,
|
| 2038 |
+
"learning_rate": 0.0006538461538461538,
|
| 2039 |
+
"loss": 2.191,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.007247933498342129,
|
| 2044 |
+
"grad_norm": 0.201171875,
|
| 2045 |
+
"learning_rate": 0.0006561085972850678,
|
| 2046 |
+
"loss": 2.1837,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.00727284048630894,
|
| 2051 |
+
"grad_norm": 0.1904296875,
|
| 2052 |
+
"learning_rate": 0.000658371040723982,
|
| 2053 |
+
"loss": 2.1985,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.007297747474275752,
|
| 2058 |
+
"grad_norm": 0.197265625,
|
| 2059 |
+
"learning_rate": 0.000660633484162896,
|
| 2060 |
+
"loss": 2.3808,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.007322654462242563,
|
| 2065 |
+
"grad_norm": 0.2041015625,
|
| 2066 |
+
"learning_rate": 0.00066289592760181,
|
| 2067 |
+
"loss": 2.1699,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.007347561450209374,
|
| 2072 |
+
"grad_norm": 0.201171875,
|
| 2073 |
+
"learning_rate": 0.000665158371040724,
|
| 2074 |
+
"loss": 2.0983,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.0073724684381761855,
|
| 2079 |
+
"grad_norm": 0.2216796875,
|
| 2080 |
+
"learning_rate": 0.000667420814479638,
|
| 2081 |
+
"loss": 2.0978,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.007397375426142997,
|
| 2086 |
+
"grad_norm": 0.19140625,
|
| 2087 |
+
"learning_rate": 0.000669683257918552,
|
| 2088 |
+
"loss": 2.1198,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.007422282414109809,
|
| 2093 |
+
"grad_norm": 0.2236328125,
|
| 2094 |
+
"learning_rate": 0.0006719457013574661,
|
| 2095 |
+
"loss": 2.1954,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.00744718940207662,
|
| 2100 |
+
"grad_norm": 0.216796875,
|
| 2101 |
+
"learning_rate": 0.0006742081447963801,
|
| 2102 |
+
"loss": 2.192,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.007472096390043432,
|
| 2107 |
+
"grad_norm": 0.2353515625,
|
| 2108 |
+
"learning_rate": 0.0006764705882352942,
|
| 2109 |
+
"loss": 2.2997,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.007497003378010243,
|
| 2114 |
+
"grad_norm": 0.2373046875,
|
| 2115 |
+
"learning_rate": 0.0006787330316742082,
|
| 2116 |
+
"loss": 2.214,
|
| 2117 |
+
"step": 301
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.007521910365977055,
|
| 2121 |
+
"grad_norm": 0.2275390625,
|
| 2122 |
+
"learning_rate": 0.0006809954751131222,
|
| 2123 |
+
"loss": 2.191,
|
| 2124 |
+
"step": 302
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.0075468173539438655,
|
| 2128 |
+
"grad_norm": 0.21875,
|
| 2129 |
+
"learning_rate": 0.0006832579185520362,
|
| 2130 |
+
"loss": 2.1278,
|
| 2131 |
+
"step": 303
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.007571724341910677,
|
| 2135 |
+
"grad_norm": 0.21875,
|
| 2136 |
+
"learning_rate": 0.0006855203619909502,
|
| 2137 |
+
"loss": 2.197,
|
| 2138 |
+
"step": 304
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.0075966313298774886,
|
| 2142 |
+
"grad_norm": 0.208984375,
|
| 2143 |
+
"learning_rate": 0.0006877828054298643,
|
| 2144 |
+
"loss": 2.1955,
|
| 2145 |
+
"step": 305
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.0076215383178443,
|
| 2149 |
+
"grad_norm": 0.21484375,
|
| 2150 |
+
"learning_rate": 0.0006900452488687783,
|
| 2151 |
+
"loss": 2.1031,
|
| 2152 |
+
"step": 306
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.007646445305811112,
|
| 2156 |
+
"grad_norm": 0.19921875,
|
| 2157 |
+
"learning_rate": 0.0006923076923076923,
|
| 2158 |
+
"loss": 2.1362,
|
| 2159 |
+
"step": 307
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.007671352293777923,
|
| 2163 |
+
"grad_norm": 0.22265625,
|
| 2164 |
+
"learning_rate": 0.0006945701357466064,
|
| 2165 |
+
"loss": 2.2547,
|
| 2166 |
+
"step": 308
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.007696259281744735,
|
| 2170 |
+
"grad_norm": 0.2109375,
|
| 2171 |
+
"learning_rate": 0.0006968325791855204,
|
| 2172 |
+
"loss": 2.0754,
|
| 2173 |
+
"step": 309
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.007721166269711546,
|
| 2177 |
+
"grad_norm": 0.22265625,
|
| 2178 |
+
"learning_rate": 0.0006990950226244344,
|
| 2179 |
+
"loss": 2.3101,
|
| 2180 |
+
"step": 310
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.007746073257678357,
|
| 2184 |
+
"grad_norm": 0.19921875,
|
| 2185 |
+
"learning_rate": 0.0007013574660633484,
|
| 2186 |
+
"loss": 2.3633,
|
| 2187 |
+
"step": 311
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.0077709802456451685,
|
| 2191 |
+
"grad_norm": 0.197265625,
|
| 2192 |
+
"learning_rate": 0.0007036199095022625,
|
| 2193 |
+
"loss": 2.1873,
|
| 2194 |
+
"step": 312
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.00779588723361198,
|
| 2198 |
+
"grad_norm": 0.208984375,
|
| 2199 |
+
"learning_rate": 0.0007058823529411765,
|
| 2200 |
+
"loss": 2.2227,
|
| 2201 |
+
"step": 313
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.007820794221578792,
|
| 2205 |
+
"grad_norm": 0.1982421875,
|
| 2206 |
+
"learning_rate": 0.0007081447963800905,
|
| 2207 |
+
"loss": 2.1064,
|
| 2208 |
+
"step": 314
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.007845701209545603,
|
| 2212 |
+
"grad_norm": 0.1962890625,
|
| 2213 |
+
"learning_rate": 0.0007104072398190045,
|
| 2214 |
+
"loss": 2.2989,
|
| 2215 |
+
"step": 315
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.007870608197512414,
|
| 2219 |
+
"grad_norm": 0.208984375,
|
| 2220 |
+
"learning_rate": 0.0007126696832579185,
|
| 2221 |
+
"loss": 2.2817,
|
| 2222 |
+
"step": 316
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.007895515185479226,
|
| 2226 |
+
"grad_norm": 0.2021484375,
|
| 2227 |
+
"learning_rate": 0.0007149321266968326,
|
| 2228 |
+
"loss": 2.1917,
|
| 2229 |
+
"step": 317
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.007920422173446037,
|
| 2233 |
+
"grad_norm": 0.2041015625,
|
| 2234 |
+
"learning_rate": 0.0007171945701357467,
|
| 2235 |
+
"loss": 2.1528,
|
| 2236 |
+
"step": 318
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.00794532916141285,
|
| 2240 |
+
"grad_norm": 0.1875,
|
| 2241 |
+
"learning_rate": 0.0007194570135746607,
|
| 2242 |
+
"loss": 2.1458,
|
| 2243 |
+
"step": 319
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.00797023614937966,
|
| 2247 |
+
"grad_norm": 0.22265625,
|
| 2248 |
+
"learning_rate": 0.0007217194570135747,
|
| 2249 |
+
"loss": 2.2374,
|
| 2250 |
+
"step": 320
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.007995143137346472,
|
| 2254 |
+
"grad_norm": 0.197265625,
|
| 2255 |
+
"learning_rate": 0.0007239819004524887,
|
| 2256 |
+
"loss": 2.1783,
|
| 2257 |
+
"step": 321
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.008020050125313283,
|
| 2261 |
+
"grad_norm": 0.1904296875,
|
| 2262 |
+
"learning_rate": 0.0007262443438914027,
|
| 2263 |
+
"loss": 2.2098,
|
| 2264 |
+
"step": 322
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.008044957113280094,
|
| 2268 |
+
"grad_norm": 0.208984375,
|
| 2269 |
+
"learning_rate": 0.0007285067873303167,
|
| 2270 |
+
"loss": 2.1929,
|
| 2271 |
+
"step": 323
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.008069864101246906,
|
| 2275 |
+
"grad_norm": 0.2197265625,
|
| 2276 |
+
"learning_rate": 0.0007307692307692307,
|
| 2277 |
+
"loss": 2.3069,
|
| 2278 |
+
"step": 324
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.008094771089213717,
|
| 2282 |
+
"grad_norm": 0.197265625,
|
| 2283 |
+
"learning_rate": 0.0007330316742081448,
|
| 2284 |
+
"loss": 2.224,
|
| 2285 |
+
"step": 325
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.00811967807718053,
|
| 2289 |
+
"grad_norm": 0.1962890625,
|
| 2290 |
+
"learning_rate": 0.0007352941176470589,
|
| 2291 |
+
"loss": 2.1641,
|
| 2292 |
+
"step": 326
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.00814458506514734,
|
| 2296 |
+
"grad_norm": 0.1884765625,
|
| 2297 |
+
"learning_rate": 0.0007375565610859729,
|
| 2298 |
+
"loss": 2.2418,
|
| 2299 |
+
"step": 327
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.008169492053114152,
|
| 2303 |
+
"grad_norm": 0.2138671875,
|
| 2304 |
+
"learning_rate": 0.0007398190045248869,
|
| 2305 |
+
"loss": 2.3361,
|
| 2306 |
+
"step": 328
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.008194399041080963,
|
| 2310 |
+
"grad_norm": 0.2060546875,
|
| 2311 |
+
"learning_rate": 0.0007420814479638009,
|
| 2312 |
+
"loss": 2.3272,
|
| 2313 |
+
"step": 329
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.008219306029047775,
|
| 2317 |
+
"grad_norm": 0.19921875,
|
| 2318 |
+
"learning_rate": 0.000744343891402715,
|
| 2319 |
+
"loss": 2.1585,
|
| 2320 |
+
"step": 330
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.008244213017014586,
|
| 2324 |
+
"grad_norm": 0.2060546875,
|
| 2325 |
+
"learning_rate": 0.000746606334841629,
|
| 2326 |
+
"loss": 2.3662,
|
| 2327 |
+
"step": 331
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.008269120004981397,
|
| 2331 |
+
"grad_norm": 0.2099609375,
|
| 2332 |
+
"learning_rate": 0.000748868778280543,
|
| 2333 |
+
"loss": 2.3024,
|
| 2334 |
+
"step": 332
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.00829402699294821,
|
| 2338 |
+
"grad_norm": 0.212890625,
|
| 2339 |
+
"learning_rate": 0.0007511312217194571,
|
| 2340 |
+
"loss": 2.1118,
|
| 2341 |
+
"step": 333
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.00831893398091502,
|
| 2345 |
+
"grad_norm": 0.2119140625,
|
| 2346 |
+
"learning_rate": 0.0007533936651583711,
|
| 2347 |
+
"loss": 2.2238,
|
| 2348 |
+
"step": 334
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.008343840968881832,
|
| 2352 |
+
"grad_norm": 0.203125,
|
| 2353 |
+
"learning_rate": 0.0007556561085972851,
|
| 2354 |
+
"loss": 2.1033,
|
| 2355 |
+
"step": 335
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.008368747956848643,
|
| 2359 |
+
"grad_norm": 0.2158203125,
|
| 2360 |
+
"learning_rate": 0.0007579185520361991,
|
| 2361 |
+
"loss": 2.2592,
|
| 2362 |
+
"step": 336
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.008393654944815455,
|
| 2366 |
+
"grad_norm": 0.1982421875,
|
| 2367 |
+
"learning_rate": 0.0007601809954751131,
|
| 2368 |
+
"loss": 2.0823,
|
| 2369 |
+
"step": 337
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.008418561932782266,
|
| 2373 |
+
"grad_norm": 0.2060546875,
|
| 2374 |
+
"learning_rate": 0.0007624434389140271,
|
| 2375 |
+
"loss": 2.1653,
|
| 2376 |
+
"step": 338
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.008443468920749079,
|
| 2380 |
+
"grad_norm": 0.2109375,
|
| 2381 |
+
"learning_rate": 0.0007647058823529411,
|
| 2382 |
+
"loss": 2.1703,
|
| 2383 |
+
"step": 339
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.00846837590871589,
|
| 2387 |
+
"grad_norm": 0.216796875,
|
| 2388 |
+
"learning_rate": 0.0007669683257918552,
|
| 2389 |
+
"loss": 2.2872,
|
| 2390 |
+
"step": 340
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.0084932828966827,
|
| 2394 |
+
"grad_norm": 0.224609375,
|
| 2395 |
+
"learning_rate": 0.0007692307692307693,
|
| 2396 |
+
"loss": 2.1202,
|
| 2397 |
+
"step": 341
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.008518189884649512,
|
| 2401 |
+
"grad_norm": 0.2119140625,
|
| 2402 |
+
"learning_rate": 0.0007714932126696833,
|
| 2403 |
+
"loss": 2.1635,
|
| 2404 |
+
"step": 342
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.008543096872616323,
|
| 2408 |
+
"grad_norm": 0.19140625,
|
| 2409 |
+
"learning_rate": 0.0007737556561085974,
|
| 2410 |
+
"loss": 2.1848,
|
| 2411 |
+
"step": 343
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.008568003860583135,
|
| 2415 |
+
"grad_norm": 0.2001953125,
|
| 2416 |
+
"learning_rate": 0.0007760180995475114,
|
| 2417 |
+
"loss": 2.2661,
|
| 2418 |
+
"step": 344
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.008592910848549946,
|
| 2422 |
+
"grad_norm": 0.2001953125,
|
| 2423 |
+
"learning_rate": 0.0007782805429864254,
|
| 2424 |
+
"loss": 2.2761,
|
| 2425 |
+
"step": 345
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.008617817836516758,
|
| 2429 |
+
"grad_norm": 0.193359375,
|
| 2430 |
+
"learning_rate": 0.0007805429864253394,
|
| 2431 |
+
"loss": 2.2526,
|
| 2432 |
+
"step": 346
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.00864272482448357,
|
| 2436 |
+
"grad_norm": 0.216796875,
|
| 2437 |
+
"learning_rate": 0.0007828054298642534,
|
| 2438 |
+
"loss": 2.1355,
|
| 2439 |
+
"step": 347
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.00866763181245038,
|
| 2443 |
+
"grad_norm": 0.22265625,
|
| 2444 |
+
"learning_rate": 0.0007850678733031674,
|
| 2445 |
+
"loss": 2.2897,
|
| 2446 |
+
"step": 348
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.008692538800417192,
|
| 2450 |
+
"grad_norm": 0.20703125,
|
| 2451 |
+
"learning_rate": 0.0007873303167420815,
|
| 2452 |
+
"loss": 2.0998,
|
| 2453 |
+
"step": 349
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.008717445788384003,
|
| 2457 |
+
"grad_norm": 0.259765625,
|
| 2458 |
+
"learning_rate": 0.0007895927601809955,
|
| 2459 |
+
"loss": 2.2198,
|
| 2460 |
+
"step": 350
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.008742352776350815,
|
| 2464 |
+
"grad_norm": 0.2314453125,
|
| 2465 |
+
"learning_rate": 0.0007918552036199095,
|
| 2466 |
+
"loss": 2.308,
|
| 2467 |
+
"step": 351
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.008767259764317626,
|
| 2471 |
+
"grad_norm": 0.2138671875,
|
| 2472 |
+
"learning_rate": 0.0007941176470588235,
|
| 2473 |
+
"loss": 2.2826,
|
| 2474 |
+
"step": 352
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.008792166752284438,
|
| 2478 |
+
"grad_norm": 0.2236328125,
|
| 2479 |
+
"learning_rate": 0.0007963800904977375,
|
| 2480 |
+
"loss": 2.1853,
|
| 2481 |
+
"step": 353
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.008817073740251249,
|
| 2485 |
+
"grad_norm": 0.2041015625,
|
| 2486 |
+
"learning_rate": 0.0007986425339366516,
|
| 2487 |
+
"loss": 2.1132,
|
| 2488 |
+
"step": 354
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.008841980728218062,
|
| 2492 |
+
"grad_norm": 0.216796875,
|
| 2493 |
+
"learning_rate": 0.0008009049773755656,
|
| 2494 |
+
"loss": 2.19,
|
| 2495 |
+
"step": 355
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.008866887716184872,
|
| 2499 |
+
"grad_norm": 0.2099609375,
|
| 2500 |
+
"learning_rate": 0.0008031674208144796,
|
| 2501 |
+
"loss": 2.2332,
|
| 2502 |
+
"step": 356
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.008891794704151683,
|
| 2506 |
+
"grad_norm": 0.2177734375,
|
| 2507 |
+
"learning_rate": 0.0008054298642533937,
|
| 2508 |
+
"loss": 2.2092,
|
| 2509 |
+
"step": 357
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.008916701692118495,
|
| 2513 |
+
"grad_norm": 0.2158203125,
|
| 2514 |
+
"learning_rate": 0.0008076923076923078,
|
| 2515 |
+
"loss": 2.3238,
|
| 2516 |
+
"step": 358
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.008941608680085306,
|
| 2520 |
+
"grad_norm": 0.20703125,
|
| 2521 |
+
"learning_rate": 0.0008099547511312218,
|
| 2522 |
+
"loss": 2.1333,
|
| 2523 |
+
"step": 359
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.008966515668052118,
|
| 2527 |
+
"grad_norm": 0.21484375,
|
| 2528 |
+
"learning_rate": 0.0008122171945701358,
|
| 2529 |
+
"loss": 2.1559,
|
| 2530 |
+
"step": 360
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.008991422656018929,
|
| 2534 |
+
"grad_norm": 0.2197265625,
|
| 2535 |
+
"learning_rate": 0.0008144796380090498,
|
| 2536 |
+
"loss": 2.352,
|
| 2537 |
+
"step": 361
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.009016329643985741,
|
| 2541 |
+
"grad_norm": 0.20703125,
|
| 2542 |
+
"learning_rate": 0.0008167420814479638,
|
| 2543 |
+
"loss": 2.229,
|
| 2544 |
+
"step": 362
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.009041236631952552,
|
| 2548 |
+
"grad_norm": 0.2060546875,
|
| 2549 |
+
"learning_rate": 0.0008190045248868778,
|
| 2550 |
+
"loss": 2.2754,
|
| 2551 |
+
"step": 363
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.009066143619919363,
|
| 2555 |
+
"grad_norm": 0.1943359375,
|
| 2556 |
+
"learning_rate": 0.0008212669683257918,
|
| 2557 |
+
"loss": 2.2063,
|
| 2558 |
+
"step": 364
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.009091050607886175,
|
| 2562 |
+
"grad_norm": 0.189453125,
|
| 2563 |
+
"learning_rate": 0.0008235294117647058,
|
| 2564 |
+
"loss": 2.3216,
|
| 2565 |
+
"step": 365
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.009115957595852986,
|
| 2569 |
+
"grad_norm": 0.1953125,
|
| 2570 |
+
"learning_rate": 0.0008257918552036199,
|
| 2571 |
+
"loss": 2.1581,
|
| 2572 |
+
"step": 366
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.009140864583819798,
|
| 2576 |
+
"grad_norm": 0.2109375,
|
| 2577 |
+
"learning_rate": 0.0008280542986425339,
|
| 2578 |
+
"loss": 2.359,
|
| 2579 |
+
"step": 367
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.009165771571786609,
|
| 2583 |
+
"grad_norm": 0.197265625,
|
| 2584 |
+
"learning_rate": 0.000830316742081448,
|
| 2585 |
+
"loss": 2.2217,
|
| 2586 |
+
"step": 368
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.009190678559753421,
|
| 2590 |
+
"grad_norm": 0.19921875,
|
| 2591 |
+
"learning_rate": 0.000832579185520362,
|
| 2592 |
+
"loss": 2.3675,
|
| 2593 |
+
"step": 369
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.009215585547720232,
|
| 2597 |
+
"grad_norm": 0.1982421875,
|
| 2598 |
+
"learning_rate": 0.0008348416289592761,
|
| 2599 |
+
"loss": 2.2559,
|
| 2600 |
+
"step": 370
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.009240492535687045,
|
| 2604 |
+
"grad_norm": 0.19921875,
|
| 2605 |
+
"learning_rate": 0.0008371040723981901,
|
| 2606 |
+
"loss": 2.2544,
|
| 2607 |
+
"step": 371
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.009265399523653855,
|
| 2611 |
+
"grad_norm": 0.1796875,
|
| 2612 |
+
"learning_rate": 0.0008393665158371041,
|
| 2613 |
+
"loss": 2.2388,
|
| 2614 |
+
"step": 372
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.009290306511620666,
|
| 2618 |
+
"grad_norm": 0.197265625,
|
| 2619 |
+
"learning_rate": 0.0008416289592760181,
|
| 2620 |
+
"loss": 2.2237,
|
| 2621 |
+
"step": 373
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.009315213499587478,
|
| 2625 |
+
"grad_norm": 0.1923828125,
|
| 2626 |
+
"learning_rate": 0.0008438914027149322,
|
| 2627 |
+
"loss": 2.3151,
|
| 2628 |
+
"step": 374
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.009340120487554289,
|
| 2632 |
+
"grad_norm": 0.2001953125,
|
| 2633 |
+
"learning_rate": 0.0008461538461538462,
|
| 2634 |
+
"loss": 2.2841,
|
| 2635 |
+
"step": 375
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.009365027475521101,
|
| 2639 |
+
"grad_norm": 0.1943359375,
|
| 2640 |
+
"learning_rate": 0.0008484162895927602,
|
| 2641 |
+
"loss": 2.1745,
|
| 2642 |
+
"step": 376
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.009389934463487912,
|
| 2646 |
+
"grad_norm": 0.1982421875,
|
| 2647 |
+
"learning_rate": 0.0008506787330316742,
|
| 2648 |
+
"loss": 2.2222,
|
| 2649 |
+
"step": 377
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.009414841451454724,
|
| 2653 |
+
"grad_norm": 0.19140625,
|
| 2654 |
+
"learning_rate": 0.0008529411764705882,
|
| 2655 |
+
"loss": 2.2672,
|
| 2656 |
+
"step": 378
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.009439748439421535,
|
| 2660 |
+
"grad_norm": 0.1923828125,
|
| 2661 |
+
"learning_rate": 0.0008552036199095022,
|
| 2662 |
+
"loss": 2.1989,
|
| 2663 |
+
"step": 379
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.009464655427388346,
|
| 2667 |
+
"grad_norm": 0.1875,
|
| 2668 |
+
"learning_rate": 0.0008574660633484162,
|
| 2669 |
+
"loss": 2.2423,
|
| 2670 |
+
"step": 380
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.009489562415355158,
|
| 2674 |
+
"grad_norm": 0.197265625,
|
| 2675 |
+
"learning_rate": 0.0008597285067873303,
|
| 2676 |
+
"loss": 2.2168,
|
| 2677 |
+
"step": 381
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.009514469403321969,
|
| 2681 |
+
"grad_norm": 0.1826171875,
|
| 2682 |
+
"learning_rate": 0.0008619909502262445,
|
| 2683 |
+
"loss": 2.2289,
|
| 2684 |
+
"step": 382
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.009539376391288781,
|
| 2688 |
+
"grad_norm": 0.1865234375,
|
| 2689 |
+
"learning_rate": 0.0008642533936651585,
|
| 2690 |
+
"loss": 2.277,
|
| 2691 |
+
"step": 383
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.009564283379255592,
|
| 2695 |
+
"grad_norm": 0.1845703125,
|
| 2696 |
+
"learning_rate": 0.0008665158371040725,
|
| 2697 |
+
"loss": 2.2716,
|
| 2698 |
+
"step": 384
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.009589190367222404,
|
| 2702 |
+
"grad_norm": 0.1875,
|
| 2703 |
+
"learning_rate": 0.0008687782805429865,
|
| 2704 |
+
"loss": 2.1815,
|
| 2705 |
+
"step": 385
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.009614097355189215,
|
| 2709 |
+
"grad_norm": 0.177734375,
|
| 2710 |
+
"learning_rate": 0.0008710407239819005,
|
| 2711 |
+
"loss": 2.2318,
|
| 2712 |
+
"step": 386
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.009639004343156028,
|
| 2716 |
+
"grad_norm": 0.1953125,
|
| 2717 |
+
"learning_rate": 0.0008733031674208145,
|
| 2718 |
+
"loss": 2.1257,
|
| 2719 |
+
"step": 387
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.009663911331122838,
|
| 2723 |
+
"grad_norm": 0.181640625,
|
| 2724 |
+
"learning_rate": 0.0008755656108597285,
|
| 2725 |
+
"loss": 2.058,
|
| 2726 |
+
"step": 388
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.009688818319089649,
|
| 2730 |
+
"grad_norm": 0.1845703125,
|
| 2731 |
+
"learning_rate": 0.0008778280542986425,
|
| 2732 |
+
"loss": 2.1454,
|
| 2733 |
+
"step": 389
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.009713725307056461,
|
| 2737 |
+
"grad_norm": 0.1953125,
|
| 2738 |
+
"learning_rate": 0.0008800904977375566,
|
| 2739 |
+
"loss": 2.2178,
|
| 2740 |
+
"step": 390
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.009738632295023272,
|
| 2744 |
+
"grad_norm": 0.1796875,
|
| 2745 |
+
"learning_rate": 0.0008823529411764706,
|
| 2746 |
+
"loss": 2.1579,
|
| 2747 |
+
"step": 391
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.009763539282990084,
|
| 2751 |
+
"grad_norm": 0.1884765625,
|
| 2752 |
+
"learning_rate": 0.0008846153846153846,
|
| 2753 |
+
"loss": 2.2203,
|
| 2754 |
+
"step": 392
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.009788446270956895,
|
| 2758 |
+
"grad_norm": 0.19921875,
|
| 2759 |
+
"learning_rate": 0.0008868778280542986,
|
| 2760 |
+
"loss": 2.2514,
|
| 2761 |
+
"step": 393
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.009813353258923707,
|
| 2765 |
+
"grad_norm": 0.2060546875,
|
| 2766 |
+
"learning_rate": 0.0008891402714932126,
|
| 2767 |
+
"loss": 2.2323,
|
| 2768 |
+
"step": 394
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.009838260246890518,
|
| 2772 |
+
"grad_norm": 0.2109375,
|
| 2773 |
+
"learning_rate": 0.0008914027149321268,
|
| 2774 |
+
"loss": 2.1643,
|
| 2775 |
+
"step": 395
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.009863167234857329,
|
| 2779 |
+
"grad_norm": 0.2109375,
|
| 2780 |
+
"learning_rate": 0.0008936651583710408,
|
| 2781 |
+
"loss": 2.1877,
|
| 2782 |
+
"step": 396
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.009888074222824141,
|
| 2786 |
+
"grad_norm": 0.2021484375,
|
| 2787 |
+
"learning_rate": 0.0008959276018099548,
|
| 2788 |
+
"loss": 2.2354,
|
| 2789 |
+
"step": 397
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.009912981210790952,
|
| 2793 |
+
"grad_norm": 0.205078125,
|
| 2794 |
+
"learning_rate": 0.0008981900452488689,
|
| 2795 |
+
"loss": 2.1699,
|
| 2796 |
+
"step": 398
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.009937888198757764,
|
| 2800 |
+
"grad_norm": 0.2138671875,
|
| 2801 |
+
"learning_rate": 0.0009004524886877829,
|
| 2802 |
+
"loss": 2.21,
|
| 2803 |
+
"step": 399
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.009962795186724575,
|
| 2807 |
+
"grad_norm": 0.189453125,
|
| 2808 |
+
"learning_rate": 0.0009027149321266969,
|
| 2809 |
+
"loss": 2.1494,
|
| 2810 |
+
"step": 400
|
| 2811 |
+
},
|
| 2812 |
+
{
|
| 2813 |
+
"epoch": 0.009987702174691387,
|
| 2814 |
+
"grad_norm": 0.185546875,
|
| 2815 |
+
"learning_rate": 0.0009049773755656109,
|
| 2816 |
+
"loss": 2.16,
|
| 2817 |
+
"step": 401
|
| 2818 |
+
},
|
| 2819 |
+
{
|
| 2820 |
+
"epoch": 0.010012609162658198,
|
| 2821 |
+
"grad_norm": 0.1953125,
|
| 2822 |
+
"learning_rate": 0.0009072398190045249,
|
| 2823 |
+
"loss": 2.165,
|
| 2824 |
+
"step": 402
|
| 2825 |
+
},
|
| 2826 |
+
{
|
| 2827 |
+
"epoch": 0.01003751615062501,
|
| 2828 |
+
"grad_norm": 0.1943359375,
|
| 2829 |
+
"learning_rate": 0.0009095022624434389,
|
| 2830 |
+
"loss": 2.2792,
|
| 2831 |
+
"step": 403
|
| 2832 |
+
},
|
| 2833 |
+
{
|
| 2834 |
+
"epoch": 0.010062423138591821,
|
| 2835 |
+
"grad_norm": 0.181640625,
|
| 2836 |
+
"learning_rate": 0.0009117647058823529,
|
| 2837 |
+
"loss": 2.2543,
|
| 2838 |
+
"step": 404
|
| 2839 |
+
},
|
| 2840 |
+
{
|
| 2841 |
+
"epoch": 0.010087330126558632,
|
| 2842 |
+
"grad_norm": 0.1943359375,
|
| 2843 |
+
"learning_rate": 0.0009140271493212669,
|
| 2844 |
+
"loss": 2.2416,
|
| 2845 |
+
"step": 405
|
| 2846 |
+
},
|
| 2847 |
+
{
|
| 2848 |
+
"epoch": 0.010112237114525444,
|
| 2849 |
+
"grad_norm": 0.19921875,
|
| 2850 |
+
"learning_rate": 0.0009162895927601809,
|
| 2851 |
+
"loss": 2.2084,
|
| 2852 |
+
"step": 406
|
| 2853 |
+
},
|
| 2854 |
+
{
|
| 2855 |
+
"epoch": 0.010137144102492255,
|
| 2856 |
+
"grad_norm": 0.20703125,
|
| 2857 |
+
"learning_rate": 0.000918552036199095,
|
| 2858 |
+
"loss": 2.2821,
|
| 2859 |
+
"step": 407
|
| 2860 |
+
},
|
| 2861 |
+
{
|
| 2862 |
+
"epoch": 0.010162051090459067,
|
| 2863 |
+
"grad_norm": 0.22265625,
|
| 2864 |
+
"learning_rate": 0.000920814479638009,
|
| 2865 |
+
"loss": 2.2607,
|
| 2866 |
+
"step": 408
|
| 2867 |
+
},
|
| 2868 |
+
{
|
| 2869 |
+
"epoch": 0.010186958078425878,
|
| 2870 |
+
"grad_norm": 0.2138671875,
|
| 2871 |
+
"learning_rate": 0.0009230769230769232,
|
| 2872 |
+
"loss": 2.2744,
|
| 2873 |
+
"step": 409
|
| 2874 |
+
},
|
| 2875 |
+
{
|
| 2876 |
+
"epoch": 0.01021186506639269,
|
| 2877 |
+
"grad_norm": 0.2255859375,
|
| 2878 |
+
"learning_rate": 0.0009253393665158372,
|
| 2879 |
+
"loss": 2.2393,
|
| 2880 |
+
"step": 410
|
| 2881 |
+
},
|
| 2882 |
+
{
|
| 2883 |
+
"epoch": 0.010236772054359501,
|
| 2884 |
+
"grad_norm": 0.193359375,
|
| 2885 |
+
"learning_rate": 0.0009276018099547512,
|
| 2886 |
+
"loss": 2.2587,
|
| 2887 |
+
"step": 411
|
| 2888 |
+
},
|
| 2889 |
+
{
|
| 2890 |
+
"epoch": 0.010261679042326312,
|
| 2891 |
+
"grad_norm": 0.2021484375,
|
| 2892 |
+
"learning_rate": 0.0009298642533936652,
|
| 2893 |
+
"loss": 2.2049,
|
| 2894 |
+
"step": 412
|
| 2895 |
+
},
|
| 2896 |
+
{
|
| 2897 |
+
"epoch": 0.010286586030293124,
|
| 2898 |
+
"grad_norm": 0.18359375,
|
| 2899 |
+
"learning_rate": 0.0009321266968325792,
|
| 2900 |
+
"loss": 2.176,
|
| 2901 |
+
"step": 413
|
| 2902 |
+
},
|
| 2903 |
+
{
|
| 2904 |
+
"epoch": 0.010311493018259935,
|
| 2905 |
+
"grad_norm": 0.2119140625,
|
| 2906 |
+
"learning_rate": 0.0009343891402714932,
|
| 2907 |
+
"loss": 2.2717,
|
| 2908 |
+
"step": 414
|
| 2909 |
+
},
|
| 2910 |
+
{
|
| 2911 |
+
"epoch": 0.010336400006226747,
|
| 2912 |
+
"grad_norm": 0.216796875,
|
| 2913 |
+
"learning_rate": 0.0009366515837104073,
|
| 2914 |
+
"loss": 2.2449,
|
| 2915 |
+
"step": 415
|
| 2916 |
+
},
|
| 2917 |
+
{
|
| 2918 |
+
"epoch": 0.010361306994193558,
|
| 2919 |
+
"grad_norm": 0.1962890625,
|
| 2920 |
+
"learning_rate": 0.0009389140271493213,
|
| 2921 |
+
"loss": 2.4054,
|
| 2922 |
+
"step": 416
|
| 2923 |
+
},
|
| 2924 |
+
{
|
| 2925 |
+
"epoch": 0.01038621398216037,
|
| 2926 |
+
"grad_norm": 0.19140625,
|
| 2927 |
+
"learning_rate": 0.0009411764705882353,
|
| 2928 |
+
"loss": 2.1851,
|
| 2929 |
+
"step": 417
|
| 2930 |
+
},
|
| 2931 |
+
{
|
| 2932 |
+
"epoch": 0.010411120970127181,
|
| 2933 |
+
"grad_norm": 0.193359375,
|
| 2934 |
+
"learning_rate": 0.0009434389140271493,
|
| 2935 |
+
"loss": 2.2059,
|
| 2936 |
+
"step": 418
|
| 2937 |
+
},
|
| 2938 |
+
{
|
| 2939 |
+
"epoch": 0.010436027958093994,
|
| 2940 |
+
"grad_norm": 0.1982421875,
|
| 2941 |
+
"learning_rate": 0.0009457013574660633,
|
| 2942 |
+
"loss": 2.2598,
|
| 2943 |
+
"step": 419
|
| 2944 |
+
},
|
| 2945 |
+
{
|
| 2946 |
+
"epoch": 0.010460934946060804,
|
| 2947 |
+
"grad_norm": 0.201171875,
|
| 2948 |
+
"learning_rate": 0.0009479638009049773,
|
| 2949 |
+
"loss": 2.2428,
|
| 2950 |
+
"step": 420
|
| 2951 |
+
},
|
| 2952 |
+
{
|
| 2953 |
+
"epoch": 0.010485841934027615,
|
| 2954 |
+
"grad_norm": 0.1953125,
|
| 2955 |
+
"learning_rate": 0.0009502262443438913,
|
| 2956 |
+
"loss": 2.2067,
|
| 2957 |
+
"step": 421
|
| 2958 |
+
},
|
| 2959 |
+
{
|
| 2960 |
+
"epoch": 0.010510748921994427,
|
| 2961 |
+
"grad_norm": 0.17578125,
|
| 2962 |
+
"learning_rate": 0.0009524886877828054,
|
| 2963 |
+
"loss": 2.2184,
|
| 2964 |
+
"step": 422
|
| 2965 |
+
},
|
| 2966 |
+
{
|
| 2967 |
+
"epoch": 0.010535655909961238,
|
| 2968 |
+
"grad_norm": 0.1884765625,
|
| 2969 |
+
"learning_rate": 0.0009547511312217196,
|
| 2970 |
+
"loss": 2.1152,
|
| 2971 |
+
"step": 423
|
| 2972 |
+
},
|
| 2973 |
+
{
|
| 2974 |
+
"epoch": 0.01056056289792805,
|
| 2975 |
+
"grad_norm": 0.1806640625,
|
| 2976 |
+
"learning_rate": 0.0009570135746606336,
|
| 2977 |
+
"loss": 2.2465,
|
| 2978 |
+
"step": 424
|
| 2979 |
+
},
|
| 2980 |
+
{
|
| 2981 |
+
"epoch": 0.010585469885894861,
|
| 2982 |
+
"grad_norm": 0.1796875,
|
| 2983 |
+
"learning_rate": 0.0009592760180995476,
|
| 2984 |
+
"loss": 2.1629,
|
| 2985 |
+
"step": 425
|
| 2986 |
+
},
|
| 2987 |
+
{
|
| 2988 |
+
"epoch": 0.010610376873861673,
|
| 2989 |
+
"grad_norm": 0.1962890625,
|
| 2990 |
+
"learning_rate": 0.0009615384615384616,
|
| 2991 |
+
"loss": 2.2428,
|
| 2992 |
+
"step": 426
|
| 2993 |
+
},
|
| 2994 |
+
{
|
| 2995 |
+
"epoch": 0.010635283861828484,
|
| 2996 |
+
"grad_norm": 0.18359375,
|
| 2997 |
+
"learning_rate": 0.0009638009049773756,
|
| 2998 |
+
"loss": 2.219,
|
| 2999 |
+
"step": 427
|
| 3000 |
+
},
|
| 3001 |
+
{
|
| 3002 |
+
"epoch": 0.010660190849795295,
|
| 3003 |
+
"grad_norm": 0.201171875,
|
| 3004 |
+
"learning_rate": 0.0009660633484162896,
|
| 3005 |
+
"loss": 2.279,
|
| 3006 |
+
"step": 428
|
| 3007 |
+
},
|
| 3008 |
+
{
|
| 3009 |
+
"epoch": 0.010685097837762107,
|
| 3010 |
+
"grad_norm": 0.302734375,
|
| 3011 |
+
"learning_rate": 0.0009683257918552036,
|
| 3012 |
+
"loss": 2.2701,
|
| 3013 |
+
"step": 429
|
| 3014 |
+
},
|
| 3015 |
+
{
|
| 3016 |
+
"epoch": 0.010710004825728918,
|
| 3017 |
+
"grad_norm": 0.2236328125,
|
| 3018 |
+
"learning_rate": 0.0009705882352941176,
|
| 3019 |
+
"loss": 2.22,
|
| 3020 |
+
"step": 430
|
| 3021 |
+
},
|
| 3022 |
+
{
|
| 3023 |
+
"epoch": 0.01073491181369573,
|
| 3024 |
+
"grad_norm": 0.216796875,
|
| 3025 |
+
"learning_rate": 0.0009728506787330317,
|
| 3026 |
+
"loss": 2.2375,
|
| 3027 |
+
"step": 431
|
| 3028 |
+
},
|
| 3029 |
+
{
|
| 3030 |
+
"epoch": 0.010759818801662541,
|
| 3031 |
+
"grad_norm": 0.251953125,
|
| 3032 |
+
"learning_rate": 0.0009751131221719457,
|
| 3033 |
+
"loss": 2.2786,
|
| 3034 |
+
"step": 432
|
| 3035 |
+
},
|
| 3036 |
+
{
|
| 3037 |
+
"epoch": 0.010784725789629353,
|
| 3038 |
+
"grad_norm": 0.1884765625,
|
| 3039 |
+
"learning_rate": 0.0009773755656108597,
|
| 3040 |
+
"loss": 2.2298,
|
| 3041 |
+
"step": 433
|
| 3042 |
+
},
|
| 3043 |
+
{
|
| 3044 |
+
"epoch": 0.010809632777596164,
|
| 3045 |
+
"grad_norm": 0.208984375,
|
| 3046 |
+
"learning_rate": 0.0009796380090497736,
|
| 3047 |
+
"loss": 2.2243,
|
| 3048 |
+
"step": 434
|
| 3049 |
+
},
|
| 3050 |
+
{
|
| 3051 |
+
"epoch": 0.010834539765562977,
|
| 3052 |
+
"grad_norm": 0.2333984375,
|
| 3053 |
+
"learning_rate": 0.0009819004524886878,
|
| 3054 |
+
"loss": 2.1594,
|
| 3055 |
+
"step": 435
|
| 3056 |
+
},
|
| 3057 |
+
{
|
| 3058 |
+
"epoch": 0.010859446753529787,
|
| 3059 |
+
"grad_norm": 0.2275390625,
|
| 3060 |
+
"learning_rate": 0.0009841628959276019,
|
| 3061 |
+
"loss": 2.3005,
|
| 3062 |
+
"step": 436
|
| 3063 |
+
},
|
| 3064 |
+
{
|
| 3065 |
+
"epoch": 0.010884353741496598,
|
| 3066 |
+
"grad_norm": 0.2333984375,
|
| 3067 |
+
"learning_rate": 0.000986425339366516,
|
| 3068 |
+
"loss": 2.3622,
|
| 3069 |
+
"step": 437
|
| 3070 |
+
},
|
| 3071 |
+
{
|
| 3072 |
+
"epoch": 0.01090926072946341,
|
| 3073 |
+
"grad_norm": 0.26171875,
|
| 3074 |
+
"learning_rate": 0.0009886877828054299,
|
| 3075 |
+
"loss": 2.3587,
|
| 3076 |
+
"step": 438
|
| 3077 |
+
},
|
| 3078 |
+
{
|
| 3079 |
+
"epoch": 0.010934167717430221,
|
| 3080 |
+
"grad_norm": 0.23828125,
|
| 3081 |
+
"learning_rate": 0.000990950226244344,
|
| 3082 |
+
"loss": 2.2522,
|
| 3083 |
+
"step": 439
|
| 3084 |
+
},
|
| 3085 |
+
{
|
| 3086 |
+
"epoch": 0.010959074705397033,
|
| 3087 |
+
"grad_norm": 0.2177734375,
|
| 3088 |
+
"learning_rate": 0.000993212669683258,
|
| 3089 |
+
"loss": 2.2863,
|
| 3090 |
+
"step": 440
|
| 3091 |
+
},
|
| 3092 |
+
{
|
| 3093 |
+
"epoch": 0.010983981693363844,
|
| 3094 |
+
"grad_norm": 0.2099609375,
|
| 3095 |
+
"learning_rate": 0.000995475113122172,
|
| 3096 |
+
"loss": 2.2219,
|
| 3097 |
+
"step": 441
|
| 3098 |
+
},
|
| 3099 |
+
{
|
| 3100 |
+
"epoch": 0.011008888681330656,
|
| 3101 |
+
"grad_norm": 0.2265625,
|
| 3102 |
+
"learning_rate": 0.000997737556561086,
|
| 3103 |
+
"loss": 2.2421,
|
| 3104 |
+
"step": 442
|
| 3105 |
+
}
|
| 3106 |
+
],
|
| 3107 |
+
"logging_steps": 1,
|
| 3108 |
+
"max_steps": 44165,
|
| 3109 |
+
"num_input_tokens_seen": 0,
|
| 3110 |
+
"num_train_epochs": 2,
|
| 3111 |
+
"save_steps": 442,
|
| 3112 |
+
"stateful_callbacks": {
|
| 3113 |
+
"TrainerControl": {
|
| 3114 |
+
"args": {
|
| 3115 |
+
"should_epoch_stop": false,
|
| 3116 |
+
"should_evaluate": false,
|
| 3117 |
+
"should_log": false,
|
| 3118 |
+
"should_save": true,
|
| 3119 |
+
"should_training_stop": false
|
| 3120 |
+
},
|
| 3121 |
+
"attributes": {}
|
| 3122 |
+
}
|
| 3123 |
+
},
|
| 3124 |
+
"total_flos": 3.8286929426039194e+17,
|
| 3125 |
+
"train_batch_size": 4,
|
| 3126 |
+
"trial_name": null,
|
| 3127 |
+
"trial_params": null
|
| 3128 |
+
}
|
last-checkpoint/training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1d94381a6d273bb0f34c5ac3061a6bfdd6260785ddb9242bcb2b203b9514562
|
| 3 |
+
size 6289
|
last-checkpoint/vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|