Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- added_tokens.json +28 -0
- chat_template.jinja +85 -0
- config.json +38 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model-00001-of-00013.safetensors +3 -0
- model-00002-of-00013.safetensors +3 -0
- model-00003-of-00013.safetensors +3 -0
- model-00004-of-00013.safetensors +3 -0
- model-00005-of-00013.safetensors +3 -0
- model-00006-of-00013.safetensors +3 -0
- model-00007-of-00013.safetensors +3 -0
- model-00008-of-00013.safetensors +3 -0
- model-00009-of-00013.safetensors +3 -0
- model-00010-of-00013.safetensors +3 -0
- model-00011-of-00013.safetensors +3 -0
- model-00012-of-00013.safetensors +3 -0
- model-00013-of-00013.safetensors +3 -0
- model.safetensors.index.json +0 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_state.json +1798 -0
- training_args.bin +3 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,85 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{{- messages[0].content + '\n\n' }}
|
| 5 |
+
{%- endif %}
|
| 6 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 7 |
+
{%- for tool in tools %}
|
| 8 |
+
{{- "\n" }}
|
| 9 |
+
{{- tool | tojson }}
|
| 10 |
+
{%- endfor %}
|
| 11 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 12 |
+
{%- else %}
|
| 13 |
+
{%- if messages[0].role == 'system' %}
|
| 14 |
+
{{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
|
| 15 |
+
{%- endif %}
|
| 16 |
+
{%- endif %}
|
| 17 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 18 |
+
{%- for message in messages[::-1] %}
|
| 19 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 20 |
+
{%- if ns.multi_step_tool and message.role == "user" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
|
| 21 |
+
{%- set ns.multi_step_tool = false %}
|
| 22 |
+
{%- set ns.last_query_index = index %}
|
| 23 |
+
{%- endif %}
|
| 24 |
+
{%- endfor %}
|
| 25 |
+
{%- for message in messages %}
|
| 26 |
+
{%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
|
| 27 |
+
{{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
|
| 28 |
+
{%- elif message.role == "assistant" %}
|
| 29 |
+
{%- set content = message.content %}
|
| 30 |
+
{%- set reasoning_content = '' %}
|
| 31 |
+
{%- if message.reasoning_content is defined and message.reasoning_content is not none %}
|
| 32 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 33 |
+
{%- else %}
|
| 34 |
+
{%- if '</think>' in message.content %}
|
| 35 |
+
{%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
|
| 36 |
+
{%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 37 |
+
{%- endif %}
|
| 38 |
+
{%- endif %}
|
| 39 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 40 |
+
{%- if loop.last or (not loop.last and reasoning_content) %}
|
| 41 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
|
| 42 |
+
{%- else %}
|
| 43 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- else %}
|
| 46 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 47 |
+
{%- endif %}
|
| 48 |
+
{%- if message.tool_calls %}
|
| 49 |
+
{%- for tool_call in message.tool_calls %}
|
| 50 |
+
{%- if (loop.first and content) or (not loop.first) %}
|
| 51 |
+
{{- '\n' }}
|
| 52 |
+
{%- endif %}
|
| 53 |
+
{%- if tool_call.function %}
|
| 54 |
+
{%- set tool_call = tool_call.function %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 57 |
+
{{- tool_call.name }}
|
| 58 |
+
{{- '", "arguments": ' }}
|
| 59 |
+
{%- if tool_call.arguments is string %}
|
| 60 |
+
{{- tool_call.arguments }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{{- tool_call.arguments | tojson }}
|
| 63 |
+
{%- endif %}
|
| 64 |
+
{{- '}\n</tool_call>' }}
|
| 65 |
+
{%- endfor %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{{- '<|im_end|>\n' }}
|
| 68 |
+
{%- elif message.role == "tool" %}
|
| 69 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 70 |
+
{{- '<|im_start|>user' }}
|
| 71 |
+
{%- endif %}
|
| 72 |
+
{{- '\n<tool_response>\n' }}
|
| 73 |
+
{{- message.content }}
|
| 74 |
+
{{- '\n</tool_response>' }}
|
| 75 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 76 |
+
{{- '<|im_end|>\n' }}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{%- endif %}
|
| 79 |
+
{%- endfor %}
|
| 80 |
+
{%- if add_generation_prompt %}
|
| 81 |
+
{{- '<|im_start|>assistant\n' }}
|
| 82 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 83 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 84 |
+
{%- endif %}
|
| 85 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3MoeForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"decoder_sparse_step": 1,
|
| 9 |
+
"eos_token_id": 151643,
|
| 10 |
+
"head_dim": 128,
|
| 11 |
+
"hidden_act": "silu",
|
| 12 |
+
"hidden_size": 2048,
|
| 13 |
+
"initializer_range": 0.02,
|
| 14 |
+
"intermediate_size": 6144,
|
| 15 |
+
"max_position_embeddings": 32768,
|
| 16 |
+
"max_window_layers": 48,
|
| 17 |
+
"mlp_only_layers": [],
|
| 18 |
+
"model_type": "qwen3_moe",
|
| 19 |
+
"moe_intermediate_size": 768,
|
| 20 |
+
"norm_topk_prob": true,
|
| 21 |
+
"num_attention_heads": 32,
|
| 22 |
+
"num_experts": 128,
|
| 23 |
+
"num_experts_per_tok": 8,
|
| 24 |
+
"num_hidden_layers": 48,
|
| 25 |
+
"num_key_value_heads": 4,
|
| 26 |
+
"output_router_logits": false,
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_scaling": null,
|
| 29 |
+
"rope_theta": 1000000.0,
|
| 30 |
+
"router_aux_loss_coef": 0.001,
|
| 31 |
+
"sliding_window": null,
|
| 32 |
+
"tie_word_embeddings": false,
|
| 33 |
+
"torch_dtype": "bfloat16",
|
| 34 |
+
"transformers_version": "4.52.0.dev0",
|
| 35 |
+
"use_cache": false,
|
| 36 |
+
"use_sliding_window": false,
|
| 37 |
+
"vocab_size": 151936
|
| 38 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"eos_token_id": 151643,
|
| 4 |
+
"max_new_tokens": 2048,
|
| 5 |
+
"transformers_version": "4.52.0.dev0"
|
| 6 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4d33cd88aa3310cbf160894dc3fa912d33ecfa9e5ccef9da615be7c324b09a4c
|
| 3 |
+
size 4997184968
|
model-00002-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35bbc16d5d9e1f0148b92dfcb0e6ad7cd339486a83946d1246354a5ec2c00ddc
|
| 3 |
+
size 4997741608
|
model-00003-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2a0daf19c8e0fd2db7cbd8661807b6646449d42f0099d18b73b9378022792261
|
| 3 |
+
size 4997742208
|
model-00004-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54f48ad36b027658998ec22178e1f3fa2fc2a544a79535aa3531e1de71583a01
|
| 3 |
+
size 4997743184
|
model-00005-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26dfe3319a42e191128811674cf3feef36acebf892663b117f915df7cd1bbdb7
|
| 3 |
+
size 4997743184
|
model-00006-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f111a55e14c371cd2c6ee3b29f62baf7959c9db67fb19f340950af4304bbd20c
|
| 3 |
+
size 4997743184
|
model-00007-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a9ad9e5d2ceb2e9d473be36df661ba9d1cecc3ce1adc46ec25e5c87551bd804
|
| 3 |
+
size 4997743184
|
model-00008-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4100ba07b090fce3467b5059c5ce70b1a53b1594f7dc241194c0791a96c9f2dd
|
| 3 |
+
size 4997743184
|
model-00009-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d83902a901b4cfecfb5a097ce9aff5aa6ed732d3583a44dbee734c3ec15779a3
|
| 3 |
+
size 4997743184
|
model-00010-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c15271990b84e35b4a3c65873ebbfb8f7c2890cf312f91758733b2ac36833f6c
|
| 3 |
+
size 4997743184
|
model-00011-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2392ac1743e93b6645460863c2909fef1808972129d0893ed943d0553db9146b
|
| 3 |
+
size 4997743184
|
model-00012-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:71b008cf3dc2ed993ec6b27b539a567ff5d450a2d77b74a2c2a59169a91ff011
|
| 3 |
+
size 4997743184
|
model-00013-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5fccf736f62a74462e04f7744f5f0d53310c7a8b650d13dc98c02ec5b64cde61
|
| 3 |
+
size 1094220288
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,240 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 131072,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"split_special_tokens": false,
|
| 238 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 239 |
+
"unk_token": null
|
| 240 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1798 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 4.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 252,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.016,
|
| 14 |
+
"grad_norm": 2.3387899124656393,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.1321,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.032,
|
| 21 |
+
"grad_norm": 2.2739175729395282,
|
| 22 |
+
"learning_rate": 3.2258064516129035e-07,
|
| 23 |
+
"loss": 0.9759,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.048,
|
| 28 |
+
"grad_norm": 3.2333006230979437,
|
| 29 |
+
"learning_rate": 6.451612903225807e-07,
|
| 30 |
+
"loss": 1.0141,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.064,
|
| 35 |
+
"grad_norm": 2.350357276823565,
|
| 36 |
+
"learning_rate": 9.67741935483871e-07,
|
| 37 |
+
"loss": 0.9947,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.08,
|
| 42 |
+
"grad_norm": 2.1839271581694755,
|
| 43 |
+
"learning_rate": 1.2903225806451614e-06,
|
| 44 |
+
"loss": 1.023,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.096,
|
| 49 |
+
"grad_norm": 2.153599307977408,
|
| 50 |
+
"learning_rate": 1.6129032258064516e-06,
|
| 51 |
+
"loss": 0.9609,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.112,
|
| 56 |
+
"grad_norm": 2.1555129140427067,
|
| 57 |
+
"learning_rate": 1.935483870967742e-06,
|
| 58 |
+
"loss": 0.9622,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.128,
|
| 63 |
+
"grad_norm": 2.008278114649717,
|
| 64 |
+
"learning_rate": 2.2580645161290324e-06,
|
| 65 |
+
"loss": 0.9711,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.144,
|
| 70 |
+
"grad_norm": 1.9242182990110015,
|
| 71 |
+
"learning_rate": 2.580645161290323e-06,
|
| 72 |
+
"loss": 0.9673,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.16,
|
| 77 |
+
"grad_norm": 1.750252408219067,
|
| 78 |
+
"learning_rate": 2.903225806451613e-06,
|
| 79 |
+
"loss": 0.9438,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.176,
|
| 84 |
+
"grad_norm": 1.6939070396617073,
|
| 85 |
+
"learning_rate": 3.225806451612903e-06,
|
| 86 |
+
"loss": 0.8756,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.192,
|
| 91 |
+
"grad_norm": 1.2834939133740737,
|
| 92 |
+
"learning_rate": 3.548387096774194e-06,
|
| 93 |
+
"loss": 0.9823,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.208,
|
| 98 |
+
"grad_norm": 1.4367519479529964,
|
| 99 |
+
"learning_rate": 3.870967741935484e-06,
|
| 100 |
+
"loss": 0.9596,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.224,
|
| 105 |
+
"grad_norm": 1.3144994907230427,
|
| 106 |
+
"learning_rate": 4.193548387096774e-06,
|
| 107 |
+
"loss": 1.0521,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.24,
|
| 112 |
+
"grad_norm": 1.0689628463958285,
|
| 113 |
+
"learning_rate": 4.516129032258065e-06,
|
| 114 |
+
"loss": 0.938,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.256,
|
| 119 |
+
"grad_norm": 1.2021712620582392,
|
| 120 |
+
"learning_rate": 4.838709677419355e-06,
|
| 121 |
+
"loss": 1.0955,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.272,
|
| 126 |
+
"grad_norm": 1.2539951248917753,
|
| 127 |
+
"learning_rate": 5.161290322580646e-06,
|
| 128 |
+
"loss": 0.9417,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.288,
|
| 133 |
+
"grad_norm": 1.4053233581800462,
|
| 134 |
+
"learning_rate": 5.483870967741935e-06,
|
| 135 |
+
"loss": 0.9956,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.304,
|
| 140 |
+
"grad_norm": 1.0278616263126648,
|
| 141 |
+
"learning_rate": 5.806451612903226e-06,
|
| 142 |
+
"loss": 0.7439,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.32,
|
| 147 |
+
"grad_norm": 1.256128877382818,
|
| 148 |
+
"learning_rate": 6.129032258064517e-06,
|
| 149 |
+
"loss": 0.9542,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.336,
|
| 154 |
+
"grad_norm": 0.9487549369343321,
|
| 155 |
+
"learning_rate": 6.451612903225806e-06,
|
| 156 |
+
"loss": 0.9816,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.352,
|
| 161 |
+
"grad_norm": 1.0891896971338342,
|
| 162 |
+
"learning_rate": 6.774193548387097e-06,
|
| 163 |
+
"loss": 1.0704,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.368,
|
| 168 |
+
"grad_norm": 1.1660258370107575,
|
| 169 |
+
"learning_rate": 7.096774193548388e-06,
|
| 170 |
+
"loss": 0.8931,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.384,
|
| 175 |
+
"grad_norm": 0.9415137340919071,
|
| 176 |
+
"learning_rate": 7.4193548387096784e-06,
|
| 177 |
+
"loss": 0.8683,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.4,
|
| 182 |
+
"grad_norm": 1.0798354285638785,
|
| 183 |
+
"learning_rate": 7.741935483870968e-06,
|
| 184 |
+
"loss": 1.0478,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.416,
|
| 189 |
+
"grad_norm": 0.8096142802637235,
|
| 190 |
+
"learning_rate": 8.064516129032258e-06,
|
| 191 |
+
"loss": 0.8466,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.432,
|
| 196 |
+
"grad_norm": 0.7447999799600428,
|
| 197 |
+
"learning_rate": 8.387096774193549e-06,
|
| 198 |
+
"loss": 0.7486,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.448,
|
| 203 |
+
"grad_norm": 0.8621800122661538,
|
| 204 |
+
"learning_rate": 8.70967741935484e-06,
|
| 205 |
+
"loss": 0.9581,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.464,
|
| 210 |
+
"grad_norm": 0.7940321530754582,
|
| 211 |
+
"learning_rate": 9.03225806451613e-06,
|
| 212 |
+
"loss": 0.8867,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.48,
|
| 217 |
+
"grad_norm": 0.8496750615573763,
|
| 218 |
+
"learning_rate": 9.35483870967742e-06,
|
| 219 |
+
"loss": 0.9179,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.496,
|
| 224 |
+
"grad_norm": 0.8798601594137285,
|
| 225 |
+
"learning_rate": 9.67741935483871e-06,
|
| 226 |
+
"loss": 0.8834,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.512,
|
| 231 |
+
"grad_norm": 0.8818390794513048,
|
| 232 |
+
"learning_rate": 1e-05,
|
| 233 |
+
"loss": 0.8952,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.528,
|
| 238 |
+
"grad_norm": 0.8322934845468171,
|
| 239 |
+
"learning_rate": 9.999683023724021e-06,
|
| 240 |
+
"loss": 1.029,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.544,
|
| 245 |
+
"grad_norm": 0.7007834456821566,
|
| 246 |
+
"learning_rate": 9.998732135085665e-06,
|
| 247 |
+
"loss": 0.8438,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.56,
|
| 252 |
+
"grad_norm": 0.6137020406246253,
|
| 253 |
+
"learning_rate": 9.99714745464859e-06,
|
| 254 |
+
"loss": 0.8435,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.576,
|
| 259 |
+
"grad_norm": 0.7231796555332799,
|
| 260 |
+
"learning_rate": 9.994929183335237e-06,
|
| 261 |
+
"loss": 0.9646,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.592,
|
| 266 |
+
"grad_norm": 0.6180598082755802,
|
| 267 |
+
"learning_rate": 9.992077602401358e-06,
|
| 268 |
+
"loss": 0.9616,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.608,
|
| 273 |
+
"grad_norm": 0.6567886708960547,
|
| 274 |
+
"learning_rate": 9.988593073400354e-06,
|
| 275 |
+
"loss": 0.8522,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.624,
|
| 280 |
+
"grad_norm": 0.7454067800699115,
|
| 281 |
+
"learning_rate": 9.984476038137437e-06,
|
| 282 |
+
"loss": 0.9052,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.64,
|
| 287 |
+
"grad_norm": 0.6714316518124167,
|
| 288 |
+
"learning_rate": 9.979727018613607e-06,
|
| 289 |
+
"loss": 0.8103,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.656,
|
| 294 |
+
"grad_norm": 0.6229146249540587,
|
| 295 |
+
"learning_rate": 9.974346616959476e-06,
|
| 296 |
+
"loss": 0.8401,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.672,
|
| 301 |
+
"grad_norm": 0.6448840489157996,
|
| 302 |
+
"learning_rate": 9.968335515358916e-06,
|
| 303 |
+
"loss": 0.9144,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.688,
|
| 308 |
+
"grad_norm": 0.528060268374605,
|
| 309 |
+
"learning_rate": 9.961694475962562e-06,
|
| 310 |
+
"loss": 0.8348,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.704,
|
| 315 |
+
"grad_norm": 0.5902102953939741,
|
| 316 |
+
"learning_rate": 9.954424340791195e-06,
|
| 317 |
+
"loss": 0.7721,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.72,
|
| 322 |
+
"grad_norm": 0.5526442876969153,
|
| 323 |
+
"learning_rate": 9.94652603162896e-06,
|
| 324 |
+
"loss": 0.8438,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.736,
|
| 329 |
+
"grad_norm": 0.5331236922634145,
|
| 330 |
+
"learning_rate": 9.938000549906509e-06,
|
| 331 |
+
"loss": 0.8023,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.752,
|
| 336 |
+
"grad_norm": 0.6339240906385807,
|
| 337 |
+
"learning_rate": 9.92884897657402e-06,
|
| 338 |
+
"loss": 0.894,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.768,
|
| 343 |
+
"grad_norm": 0.5283804877111584,
|
| 344 |
+
"learning_rate": 9.919072471964146e-06,
|
| 345 |
+
"loss": 0.9069,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.784,
|
| 350 |
+
"grad_norm": 0.5170169653511614,
|
| 351 |
+
"learning_rate": 9.908672275644898e-06,
|
| 352 |
+
"loss": 0.8051,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.8,
|
| 357 |
+
"grad_norm": 0.4763529065504662,
|
| 358 |
+
"learning_rate": 9.897649706262474e-06,
|
| 359 |
+
"loss": 0.8301,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.816,
|
| 364 |
+
"grad_norm": 0.4890239660294139,
|
| 365 |
+
"learning_rate": 9.88600616137407e-06,
|
| 366 |
+
"loss": 0.8629,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.832,
|
| 371 |
+
"grad_norm": 0.37392633165922323,
|
| 372 |
+
"learning_rate": 9.873743117270691e-06,
|
| 373 |
+
"loss": 0.8343,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.848,
|
| 378 |
+
"grad_norm": 0.5097372006252004,
|
| 379 |
+
"learning_rate": 9.860862128789954e-06,
|
| 380 |
+
"loss": 0.9025,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.864,
|
| 385 |
+
"grad_norm": 0.5331140780823508,
|
| 386 |
+
"learning_rate": 9.847364829118963e-06,
|
| 387 |
+
"loss": 0.7832,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.88,
|
| 392 |
+
"grad_norm": 0.5371583880849503,
|
| 393 |
+
"learning_rate": 9.833252929587231e-06,
|
| 394 |
+
"loss": 0.7241,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.896,
|
| 399 |
+
"grad_norm": 0.45993890737280607,
|
| 400 |
+
"learning_rate": 9.818528219449705e-06,
|
| 401 |
+
"loss": 0.8964,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.912,
|
| 406 |
+
"grad_norm": 0.4715847632418153,
|
| 407 |
+
"learning_rate": 9.803192565659898e-06,
|
| 408 |
+
"loss": 0.8623,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.928,
|
| 413 |
+
"grad_norm": 0.4942244137822645,
|
| 414 |
+
"learning_rate": 9.78724791263318e-06,
|
| 415 |
+
"loss": 0.7657,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.944,
|
| 420 |
+
"grad_norm": 0.45536932211394177,
|
| 421 |
+
"learning_rate": 9.770696282000245e-06,
|
| 422 |
+
"loss": 0.8766,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.96,
|
| 427 |
+
"grad_norm": 0.4891485391099054,
|
| 428 |
+
"learning_rate": 9.753539772350792e-06,
|
| 429 |
+
"loss": 0.8621,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.976,
|
| 434 |
+
"grad_norm": 0.45887131278496746,
|
| 435 |
+
"learning_rate": 9.735780558967434e-06,
|
| 436 |
+
"loss": 0.7718,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.992,
|
| 441 |
+
"grad_norm": 0.5002555111850944,
|
| 442 |
+
"learning_rate": 9.717420893549902e-06,
|
| 443 |
+
"loss": 0.8746,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.0,
|
| 448 |
+
"grad_norm": 0.5002555111850944,
|
| 449 |
+
"learning_rate": 9.698463103929542e-06,
|
| 450 |
+
"loss": 0.7591,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.016,
|
| 455 |
+
"grad_norm": 0.7921009597496743,
|
| 456 |
+
"learning_rate": 9.67890959377418e-06,
|
| 457 |
+
"loss": 0.8141,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.032,
|
| 462 |
+
"grad_norm": 0.5263404719063407,
|
| 463 |
+
"learning_rate": 9.658762842283343e-06,
|
| 464 |
+
"loss": 0.8,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.048,
|
| 469 |
+
"grad_norm": 0.6027486092631968,
|
| 470 |
+
"learning_rate": 9.638025403873939e-06,
|
| 471 |
+
"loss": 0.8869,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.064,
|
| 476 |
+
"grad_norm": 0.5040803182249076,
|
| 477 |
+
"learning_rate": 9.616699907856368e-06,
|
| 478 |
+
"loss": 0.7434,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.08,
|
| 483 |
+
"grad_norm": 0.4794307353380867,
|
| 484 |
+
"learning_rate": 9.594789058101154e-06,
|
| 485 |
+
"loss": 0.7162,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.096,
|
| 490 |
+
"grad_norm": 0.519708365022811,
|
| 491 |
+
"learning_rate": 9.57229563269612e-06,
|
| 492 |
+
"loss": 0.9109,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.112,
|
| 497 |
+
"grad_norm": 0.5405956328678668,
|
| 498 |
+
"learning_rate": 9.549222483594154e-06,
|
| 499 |
+
"loss": 0.7813,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.1280000000000001,
|
| 504 |
+
"grad_norm": 0.5713243651929747,
|
| 505 |
+
"learning_rate": 9.525572536251608e-06,
|
| 506 |
+
"loss": 0.7776,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.144,
|
| 511 |
+
"grad_norm": 0.7593604265555369,
|
| 512 |
+
"learning_rate": 9.501348789257373e-06,
|
| 513 |
+
"loss": 0.7817,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.16,
|
| 518 |
+
"grad_norm": 0.5104218019933199,
|
| 519 |
+
"learning_rate": 9.476554313952697e-06,
|
| 520 |
+
"loss": 0.7754,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.176,
|
| 525 |
+
"grad_norm": 0.4357678519578492,
|
| 526 |
+
"learning_rate": 9.451192254041759e-06,
|
| 527 |
+
"loss": 0.7828,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.192,
|
| 532 |
+
"grad_norm": 0.48992867265594076,
|
| 533 |
+
"learning_rate": 9.425265825193077e-06,
|
| 534 |
+
"loss": 0.7823,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.208,
|
| 539 |
+
"grad_norm": 0.4744625173124652,
|
| 540 |
+
"learning_rate": 9.398778314631801e-06,
|
| 541 |
+
"loss": 0.7303,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.224,
|
| 546 |
+
"grad_norm": 0.5598627796833753,
|
| 547 |
+
"learning_rate": 9.371733080722911e-06,
|
| 548 |
+
"loss": 0.7444,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.24,
|
| 553 |
+
"grad_norm": 0.4312343972662455,
|
| 554 |
+
"learning_rate": 9.34413355254542e-06,
|
| 555 |
+
"loss": 0.836,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.256,
|
| 560 |
+
"grad_norm": 0.624677329344369,
|
| 561 |
+
"learning_rate": 9.31598322945759e-06,
|
| 562 |
+
"loss": 0.8577,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.272,
|
| 567 |
+
"grad_norm": 0.49859023374542194,
|
| 568 |
+
"learning_rate": 9.287285680653254e-06,
|
| 569 |
+
"loss": 0.7683,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.288,
|
| 574 |
+
"grad_norm": 0.6015424998788388,
|
| 575 |
+
"learning_rate": 9.258044544709276e-06,
|
| 576 |
+
"loss": 0.8227,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.304,
|
| 581 |
+
"grad_norm": 0.44003554877608686,
|
| 582 |
+
"learning_rate": 9.228263529124199e-06,
|
| 583 |
+
"loss": 0.7863,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.32,
|
| 588 |
+
"grad_norm": 0.5609641970743867,
|
| 589 |
+
"learning_rate": 9.197946409848196e-06,
|
| 590 |
+
"loss": 0.8774,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.336,
|
| 595 |
+
"grad_norm": 0.43143646632622484,
|
| 596 |
+
"learning_rate": 9.167097030804289e-06,
|
| 597 |
+
"loss": 0.8157,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.3519999999999999,
|
| 602 |
+
"grad_norm": 0.43142249232413526,
|
| 603 |
+
"learning_rate": 9.135719303400995e-06,
|
| 604 |
+
"loss": 0.7508,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.3679999999999999,
|
| 609 |
+
"grad_norm": 0.4657223032122722,
|
| 610 |
+
"learning_rate": 9.103817206036383e-06,
|
| 611 |
+
"loss": 0.6509,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.384,
|
| 616 |
+
"grad_norm": 0.48523334387177774,
|
| 617 |
+
"learning_rate": 9.071394783593664e-06,
|
| 618 |
+
"loss": 0.8359,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.4,
|
| 623 |
+
"grad_norm": 0.46496551627210725,
|
| 624 |
+
"learning_rate": 9.038456146928325e-06,
|
| 625 |
+
"loss": 0.864,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.416,
|
| 630 |
+
"grad_norm": 0.4440780678769445,
|
| 631 |
+
"learning_rate": 9.005005472346923e-06,
|
| 632 |
+
"loss": 0.7902,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.432,
|
| 637 |
+
"grad_norm": 0.561826912899574,
|
| 638 |
+
"learning_rate": 8.971047001077561e-06,
|
| 639 |
+
"loss": 0.8076,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.448,
|
| 644 |
+
"grad_norm": 0.4900358752234758,
|
| 645 |
+
"learning_rate": 8.936585038732143e-06,
|
| 646 |
+
"loss": 0.6602,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.464,
|
| 651 |
+
"grad_norm": 0.4606489965356049,
|
| 652 |
+
"learning_rate": 8.90162395476046e-06,
|
| 653 |
+
"loss": 0.8151,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.48,
|
| 658 |
+
"grad_norm": 0.5359817129085576,
|
| 659 |
+
"learning_rate": 8.866168181896198e-06,
|
| 660 |
+
"loss": 0.8108,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.496,
|
| 665 |
+
"grad_norm": 0.4099923668319849,
|
| 666 |
+
"learning_rate": 8.83022221559489e-06,
|
| 667 |
+
"loss": 0.7473,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.512,
|
| 672 |
+
"grad_norm": 0.46662939848509505,
|
| 673 |
+
"learning_rate": 8.793790613463956e-06,
|
| 674 |
+
"loss": 0.8871,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.528,
|
| 679 |
+
"grad_norm": 0.6601471838069068,
|
| 680 |
+
"learning_rate": 8.756877994684818e-06,
|
| 681 |
+
"loss": 0.8559,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.544,
|
| 686 |
+
"grad_norm": 0.45387042686918283,
|
| 687 |
+
"learning_rate": 8.719489039427256e-06,
|
| 688 |
+
"loss": 0.7211,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.56,
|
| 693 |
+
"grad_norm": 0.39658772389509284,
|
| 694 |
+
"learning_rate": 8.681628488255986e-06,
|
| 695 |
+
"loss": 0.8225,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.576,
|
| 700 |
+
"grad_norm": 0.48808248239123686,
|
| 701 |
+
"learning_rate": 8.643301141529619e-06,
|
| 702 |
+
"loss": 0.7259,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.592,
|
| 707 |
+
"grad_norm": 0.5005912376865987,
|
| 708 |
+
"learning_rate": 8.604511858792006e-06,
|
| 709 |
+
"loss": 0.8113,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.608,
|
| 714 |
+
"grad_norm": 0.39380103997630306,
|
| 715 |
+
"learning_rate": 8.565265558156101e-06,
|
| 716 |
+
"loss": 0.782,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.624,
|
| 721 |
+
"grad_norm": 0.5511984663976129,
|
| 722 |
+
"learning_rate": 8.525567215680397e-06,
|
| 723 |
+
"loss": 0.8738,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.6400000000000001,
|
| 728 |
+
"grad_norm": 0.4456656598175722,
|
| 729 |
+
"learning_rate": 8.485421864737997e-06,
|
| 730 |
+
"loss": 0.7922,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.6560000000000001,
|
| 735 |
+
"grad_norm": 0.4908529752157155,
|
| 736 |
+
"learning_rate": 8.444834595378434e-06,
|
| 737 |
+
"loss": 0.8487,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6720000000000002,
|
| 742 |
+
"grad_norm": 0.4428491434503844,
|
| 743 |
+
"learning_rate": 8.403810553682307e-06,
|
| 744 |
+
"loss": 0.8335,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.688,
|
| 749 |
+
"grad_norm": 0.5044508101327926,
|
| 750 |
+
"learning_rate": 8.362354941108803e-06,
|
| 751 |
+
"loss": 0.7921,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.704,
|
| 756 |
+
"grad_norm": 0.5179814826203967,
|
| 757 |
+
"learning_rate": 8.320473013836197e-06,
|
| 758 |
+
"loss": 0.8403,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.72,
|
| 763 |
+
"grad_norm": 0.5470226099168956,
|
| 764 |
+
"learning_rate": 8.278170082095422e-06,
|
| 765 |
+
"loss": 0.8999,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.736,
|
| 770 |
+
"grad_norm": 0.41030649187861784,
|
| 771 |
+
"learning_rate": 8.23545150949679e-06,
|
| 772 |
+
"loss": 0.8033,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.752,
|
| 777 |
+
"grad_norm": 0.5622265643432103,
|
| 778 |
+
"learning_rate": 8.192322712349917e-06,
|
| 779 |
+
"loss": 0.7425,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.768,
|
| 784 |
+
"grad_norm": 0.5223132208572823,
|
| 785 |
+
"learning_rate": 8.148789158977012e-06,
|
| 786 |
+
"loss": 0.7316,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.784,
|
| 791 |
+
"grad_norm": 0.475126333442523,
|
| 792 |
+
"learning_rate": 8.104856369019525e-06,
|
| 793 |
+
"loss": 0.7683,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.8,
|
| 798 |
+
"grad_norm": 0.4948572562329079,
|
| 799 |
+
"learning_rate": 8.060529912738316e-06,
|
| 800 |
+
"loss": 0.7647,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.8159999999999998,
|
| 805 |
+
"grad_norm": 0.531807251361054,
|
| 806 |
+
"learning_rate": 8.0158154103074e-06,
|
| 807 |
+
"loss": 0.7611,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.8319999999999999,
|
| 812 |
+
"grad_norm": 0.47670080587998737,
|
| 813 |
+
"learning_rate": 7.970718531101365e-06,
|
| 814 |
+
"loss": 0.8092,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.8479999999999999,
|
| 819 |
+
"grad_norm": 0.4114578657588441,
|
| 820 |
+
"learning_rate": 7.925244992976538e-06,
|
| 821 |
+
"loss": 0.8859,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.8639999999999999,
|
| 826 |
+
"grad_norm": 0.5115548644684491,
|
| 827 |
+
"learning_rate": 7.879400561546033e-06,
|
| 828 |
+
"loss": 0.8891,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.88,
|
| 833 |
+
"grad_norm": 0.5853821031130237,
|
| 834 |
+
"learning_rate": 7.833191049448706e-06,
|
| 835 |
+
"loss": 0.6497,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.896,
|
| 840 |
+
"grad_norm": 0.3798635295552685,
|
| 841 |
+
"learning_rate": 7.786622315612182e-06,
|
| 842 |
+
"loss": 0.8151,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.912,
|
| 847 |
+
"grad_norm": 0.4971866098065484,
|
| 848 |
+
"learning_rate": 7.739700264509993e-06,
|
| 849 |
+
"loss": 0.7809,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.928,
|
| 854 |
+
"grad_norm": 0.4980674292423549,
|
| 855 |
+
"learning_rate": 7.692430845412946e-06,
|
| 856 |
+
"loss": 0.7679,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.944,
|
| 861 |
+
"grad_norm": 0.4324290073091459,
|
| 862 |
+
"learning_rate": 7.644820051634813e-06,
|
| 863 |
+
"loss": 0.8501,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.96,
|
| 868 |
+
"grad_norm": 0.47176687932737493,
|
| 869 |
+
"learning_rate": 7.596873919772438e-06,
|
| 870 |
+
"loss": 0.8027,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.976,
|
| 875 |
+
"grad_norm": 0.43463683245782003,
|
| 876 |
+
"learning_rate": 7.548598528940354e-06,
|
| 877 |
+
"loss": 0.7492,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.992,
|
| 882 |
+
"grad_norm": 0.49151296507554265,
|
| 883 |
+
"learning_rate": 7.500000000000001e-06,
|
| 884 |
+
"loss": 0.7126,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.0,
|
| 889 |
+
"grad_norm": 0.7056512813119306,
|
| 890 |
+
"learning_rate": 7.451084494783668e-06,
|
| 891 |
+
"loss": 0.9934,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.016,
|
| 896 |
+
"grad_norm": 0.8222112850756275,
|
| 897 |
+
"learning_rate": 7.401858215313228e-06,
|
| 898 |
+
"loss": 0.7107,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.032,
|
| 903 |
+
"grad_norm": 0.578857909730416,
|
| 904 |
+
"learning_rate": 7.352327403013779e-06,
|
| 905 |
+
"loss": 0.7626,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.048,
|
| 910 |
+
"grad_norm": 0.6947157428046444,
|
| 911 |
+
"learning_rate": 7.302498337922293e-06,
|
| 912 |
+
"loss": 0.8212,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.064,
|
| 917 |
+
"grad_norm": 1.3653434931121922,
|
| 918 |
+
"learning_rate": 7.2523773378913655e-06,
|
| 919 |
+
"loss": 0.7474,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.08,
|
| 924 |
+
"grad_norm": 0.8976124611811842,
|
| 925 |
+
"learning_rate": 7.201970757788172e-06,
|
| 926 |
+
"loss": 0.6376,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.096,
|
| 931 |
+
"grad_norm": 0.5152408942741,
|
| 932 |
+
"learning_rate": 7.151284988688731e-06,
|
| 933 |
+
"loss": 0.6641,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.112,
|
| 938 |
+
"grad_norm": 0.6830633595485539,
|
| 939 |
+
"learning_rate": 7.100326457067576e-06,
|
| 940 |
+
"loss": 0.7996,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.128,
|
| 945 |
+
"grad_norm": 0.5496861285450714,
|
| 946 |
+
"learning_rate": 7.049101623982938e-06,
|
| 947 |
+
"loss": 0.7581,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.144,
|
| 952 |
+
"grad_norm": 0.6403401425933127,
|
| 953 |
+
"learning_rate": 6.9976169842575526e-06,
|
| 954 |
+
"loss": 0.7457,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.16,
|
| 959 |
+
"grad_norm": 0.44381400078067595,
|
| 960 |
+
"learning_rate": 6.945879065655164e-06,
|
| 961 |
+
"loss": 0.6706,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.176,
|
| 966 |
+
"grad_norm": 0.607564640506437,
|
| 967 |
+
"learning_rate": 6.893894428052881e-06,
|
| 968 |
+
"loss": 0.7532,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.192,
|
| 973 |
+
"grad_norm": 0.5370083889151855,
|
| 974 |
+
"learning_rate": 6.841669662609437e-06,
|
| 975 |
+
"loss": 0.723,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.208,
|
| 980 |
+
"grad_norm": 0.503787140696792,
|
| 981 |
+
"learning_rate": 6.789211390929497e-06,
|
| 982 |
+
"loss": 0.6432,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.224,
|
| 987 |
+
"grad_norm": 0.48811253497835444,
|
| 988 |
+
"learning_rate": 6.736526264224101e-06,
|
| 989 |
+
"loss": 0.7416,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.24,
|
| 994 |
+
"grad_norm": 0.5393544740145144,
|
| 995 |
+
"learning_rate": 6.6836209624673575e-06,
|
| 996 |
+
"loss": 0.6972,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.2560000000000002,
|
| 1001 |
+
"grad_norm": 0.5146295742117404,
|
| 1002 |
+
"learning_rate": 6.6305021935494755e-06,
|
| 1003 |
+
"loss": 0.7735,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.2720000000000002,
|
| 1008 |
+
"grad_norm": 0.5354676350111098,
|
| 1009 |
+
"learning_rate": 6.5771766924262795e-06,
|
| 1010 |
+
"loss": 0.7254,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.288,
|
| 1015 |
+
"grad_norm": 0.48957997280536275,
|
| 1016 |
+
"learning_rate": 6.523651220265269e-06,
|
| 1017 |
+
"loss": 0.6449,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.304,
|
| 1022 |
+
"grad_norm": 0.6260723291086323,
|
| 1023 |
+
"learning_rate": 6.469932563588386e-06,
|
| 1024 |
+
"loss": 0.6024,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.32,
|
| 1029 |
+
"grad_norm": 0.6277559902277917,
|
| 1030 |
+
"learning_rate": 6.41602753341152e-06,
|
| 1031 |
+
"loss": 0.7118,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.336,
|
| 1036 |
+
"grad_norm": 0.5654085188913539,
|
| 1037 |
+
"learning_rate": 6.361942964380967e-06,
|
| 1038 |
+
"loss": 0.7289,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.352,
|
| 1043 |
+
"grad_norm": 0.5511085996838134,
|
| 1044 |
+
"learning_rate": 6.307685713906835e-06,
|
| 1045 |
+
"loss": 0.7078,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.368,
|
| 1050 |
+
"grad_norm": 0.48643046392503236,
|
| 1051 |
+
"learning_rate": 6.2532626612936035e-06,
|
| 1052 |
+
"loss": 0.6913,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.384,
|
| 1057 |
+
"grad_norm": 0.4251201514104161,
|
| 1058 |
+
"learning_rate": 6.1986807068678926e-06,
|
| 1059 |
+
"loss": 0.8129,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.4,
|
| 1064 |
+
"grad_norm": 0.4957551218147004,
|
| 1065 |
+
"learning_rate": 6.143946771103561e-06,
|
| 1066 |
+
"loss": 0.7541,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.416,
|
| 1071 |
+
"grad_norm": 0.5337634201089703,
|
| 1072 |
+
"learning_rate": 6.089067793744258e-06,
|
| 1073 |
+
"loss": 0.7421,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.432,
|
| 1078 |
+
"grad_norm": 0.45135282751579137,
|
| 1079 |
+
"learning_rate": 6.034050732923538e-06,
|
| 1080 |
+
"loss": 0.7623,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.448,
|
| 1085 |
+
"grad_norm": 0.40984798370772846,
|
| 1086 |
+
"learning_rate": 5.978902564282616e-06,
|
| 1087 |
+
"loss": 0.8119,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.464,
|
| 1092 |
+
"grad_norm": 0.42530164890628464,
|
| 1093 |
+
"learning_rate": 5.923630280085948e-06,
|
| 1094 |
+
"loss": 0.7985,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.48,
|
| 1099 |
+
"grad_norm": 0.390559143940863,
|
| 1100 |
+
"learning_rate": 5.8682408883346535e-06,
|
| 1101 |
+
"loss": 0.6778,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.496,
|
| 1106 |
+
"grad_norm": 0.45694185479460997,
|
| 1107 |
+
"learning_rate": 5.8127414118779825e-06,
|
| 1108 |
+
"loss": 0.7597,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.512,
|
| 1113 |
+
"grad_norm": 0.4952633583203359,
|
| 1114 |
+
"learning_rate": 5.757138887522884e-06,
|
| 1115 |
+
"loss": 0.7168,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.528,
|
| 1120 |
+
"grad_norm": 0.4342497218363157,
|
| 1121 |
+
"learning_rate": 5.701440365141799e-06,
|
| 1122 |
+
"loss": 0.6564,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.544,
|
| 1127 |
+
"grad_norm": 0.4718029081715289,
|
| 1128 |
+
"learning_rate": 5.645652906778808e-06,
|
| 1129 |
+
"loss": 0.66,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.56,
|
| 1134 |
+
"grad_norm": 0.5236548730626042,
|
| 1135 |
+
"learning_rate": 5.5897835857542315e-06,
|
| 1136 |
+
"loss": 0.7189,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.576,
|
| 1141 |
+
"grad_norm": 0.4217271822666547,
|
| 1142 |
+
"learning_rate": 5.533839485767795e-06,
|
| 1143 |
+
"loss": 0.6501,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.592,
|
| 1148 |
+
"grad_norm": 0.51236732912632,
|
| 1149 |
+
"learning_rate": 5.477827700000492e-06,
|
| 1150 |
+
"loss": 0.5564,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.608,
|
| 1155 |
+
"grad_norm": 0.5794935429954644,
|
| 1156 |
+
"learning_rate": 5.421755330215223e-06,
|
| 1157 |
+
"loss": 0.7193,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.624,
|
| 1162 |
+
"grad_norm": 0.43579809758377336,
|
| 1163 |
+
"learning_rate": 5.365629485856381e-06,
|
| 1164 |
+
"loss": 0.782,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.64,
|
| 1169 |
+
"grad_norm": 0.4273541248432265,
|
| 1170 |
+
"learning_rate": 5.30945728314841e-06,
|
| 1171 |
+
"loss": 0.6904,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.656,
|
| 1176 |
+
"grad_norm": 0.5127404572609707,
|
| 1177 |
+
"learning_rate": 5.253245844193564e-06,
|
| 1178 |
+
"loss": 0.7756,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.672,
|
| 1183 |
+
"grad_norm": 0.4502193208238627,
|
| 1184 |
+
"learning_rate": 5.197002296068878e-06,
|
| 1185 |
+
"loss": 0.7199,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.6879999999999997,
|
| 1190 |
+
"grad_norm": 0.6522139082928684,
|
| 1191 |
+
"learning_rate": 5.140733769922525e-06,
|
| 1192 |
+
"loss": 0.7523,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.7039999999999997,
|
| 1197 |
+
"grad_norm": 0.4604865675922319,
|
| 1198 |
+
"learning_rate": 5.084447400069656e-06,
|
| 1199 |
+
"loss": 0.658,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.7199999999999998,
|
| 1204 |
+
"grad_norm": 0.47189630919959746,
|
| 1205 |
+
"learning_rate": 5.0281503230878304e-06,
|
| 1206 |
+
"loss": 0.7168,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.7359999999999998,
|
| 1211 |
+
"grad_norm": 0.45853515734923483,
|
| 1212 |
+
"learning_rate": 4.971849676912172e-06,
|
| 1213 |
+
"loss": 0.59,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.752,
|
| 1218 |
+
"grad_norm": 0.6617371663600603,
|
| 1219 |
+
"learning_rate": 4.915552599930345e-06,
|
| 1220 |
+
"loss": 0.7154,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.768,
|
| 1225 |
+
"grad_norm": 0.4581535675670496,
|
| 1226 |
+
"learning_rate": 4.859266230077474e-06,
|
| 1227 |
+
"loss": 0.8279,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.784,
|
| 1232 |
+
"grad_norm": 0.44995006651439057,
|
| 1233 |
+
"learning_rate": 4.802997703931124e-06,
|
| 1234 |
+
"loss": 0.7029,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.8,
|
| 1239 |
+
"grad_norm": 0.6247080166668746,
|
| 1240 |
+
"learning_rate": 4.746754155806437e-06,
|
| 1241 |
+
"loss": 0.6663,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.816,
|
| 1246 |
+
"grad_norm": 0.43343619400050193,
|
| 1247 |
+
"learning_rate": 4.6905427168515914e-06,
|
| 1248 |
+
"loss": 0.7364,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.832,
|
| 1253 |
+
"grad_norm": 0.6592346345644005,
|
| 1254 |
+
"learning_rate": 4.63437051414362e-06,
|
| 1255 |
+
"loss": 0.7337,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.848,
|
| 1260 |
+
"grad_norm": 0.464552230592377,
|
| 1261 |
+
"learning_rate": 4.5782446697847775e-06,
|
| 1262 |
+
"loss": 0.7164,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.864,
|
| 1267 |
+
"grad_norm": 0.47084386707640963,
|
| 1268 |
+
"learning_rate": 4.52217229999951e-06,
|
| 1269 |
+
"loss": 0.7538,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.88,
|
| 1274 |
+
"grad_norm": 0.49465152130409273,
|
| 1275 |
+
"learning_rate": 4.466160514232206e-06,
|
| 1276 |
+
"loss": 0.6193,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.896,
|
| 1281 |
+
"grad_norm": 0.7463104607291,
|
| 1282 |
+
"learning_rate": 4.410216414245771e-06,
|
| 1283 |
+
"loss": 0.6887,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.912,
|
| 1288 |
+
"grad_norm": 0.5311673012762305,
|
| 1289 |
+
"learning_rate": 4.354347093221194e-06,
|
| 1290 |
+
"loss": 0.8275,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.928,
|
| 1295 |
+
"grad_norm": 0.4765968349930382,
|
| 1296 |
+
"learning_rate": 4.298559634858202e-06,
|
| 1297 |
+
"loss": 0.709,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.944,
|
| 1302 |
+
"grad_norm": 0.4041073627021218,
|
| 1303 |
+
"learning_rate": 4.2428611124771184e-06,
|
| 1304 |
+
"loss": 0.7103,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.96,
|
| 1309 |
+
"grad_norm": 0.5090780248152671,
|
| 1310 |
+
"learning_rate": 4.187258588122019e-06,
|
| 1311 |
+
"loss": 0.7976,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.976,
|
| 1316 |
+
"grad_norm": 0.6082158511853922,
|
| 1317 |
+
"learning_rate": 4.131759111665349e-06,
|
| 1318 |
+
"loss": 0.7694,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.992,
|
| 1323 |
+
"grad_norm": 0.5727874160786263,
|
| 1324 |
+
"learning_rate": 4.076369719914055e-06,
|
| 1325 |
+
"loss": 0.7123,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.0,
|
| 1330 |
+
"grad_norm": 0.5727874160786263,
|
| 1331 |
+
"learning_rate": 4.021097435717386e-06,
|
| 1332 |
+
"loss": 0.5299,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 3.016,
|
| 1337 |
+
"grad_norm": 0.786848104570295,
|
| 1338 |
+
"learning_rate": 3.965949267076465e-06,
|
| 1339 |
+
"loss": 0.6761,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.032,
|
| 1344 |
+
"grad_norm": 0.6468253157472471,
|
| 1345 |
+
"learning_rate": 3.910932206255742e-06,
|
| 1346 |
+
"loss": 0.681,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.048,
|
| 1351 |
+
"grad_norm": 0.5371976935352293,
|
| 1352 |
+
"learning_rate": 3.856053228896442e-06,
|
| 1353 |
+
"loss": 0.7382,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 3.064,
|
| 1358 |
+
"grad_norm": 0.67361754038798,
|
| 1359 |
+
"learning_rate": 3.8013192931321095e-06,
|
| 1360 |
+
"loss": 0.6811,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 3.08,
|
| 1365 |
+
"grad_norm": 0.5906235125913445,
|
| 1366 |
+
"learning_rate": 3.7467373387063973e-06,
|
| 1367 |
+
"loss": 0.6517,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 3.096,
|
| 1372 |
+
"grad_norm": 1.1573348876057628,
|
| 1373 |
+
"learning_rate": 3.692314286093167e-06,
|
| 1374 |
+
"loss": 0.5953,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 3.112,
|
| 1379 |
+
"grad_norm": 0.8839756051783417,
|
| 1380 |
+
"learning_rate": 3.6380570356190346e-06,
|
| 1381 |
+
"loss": 0.6948,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 3.128,
|
| 1386 |
+
"grad_norm": 0.478868590948113,
|
| 1387 |
+
"learning_rate": 3.58397246658848e-06,
|
| 1388 |
+
"loss": 0.7461,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.144,
|
| 1393 |
+
"grad_norm": 1.084603868797167,
|
| 1394 |
+
"learning_rate": 3.5300674364116173e-06,
|
| 1395 |
+
"loss": 0.765,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.16,
|
| 1400 |
+
"grad_norm": 0.6440739819259357,
|
| 1401 |
+
"learning_rate": 3.476348779734732e-06,
|
| 1402 |
+
"loss": 0.6823,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.176,
|
| 1407 |
+
"grad_norm": 0.6488776395666153,
|
| 1408 |
+
"learning_rate": 3.4228233075737225e-06,
|
| 1409 |
+
"loss": 0.6315,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 3.192,
|
| 1414 |
+
"grad_norm": 0.48544942050692214,
|
| 1415 |
+
"learning_rate": 3.3694978064505258e-06,
|
| 1416 |
+
"loss": 0.6785,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.208,
|
| 1421 |
+
"grad_norm": 0.5813475942014552,
|
| 1422 |
+
"learning_rate": 3.316379037532644e-06,
|
| 1423 |
+
"loss": 0.6103,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.224,
|
| 1428 |
+
"grad_norm": 0.5475003564476933,
|
| 1429 |
+
"learning_rate": 3.2634737357758994e-06,
|
| 1430 |
+
"loss": 0.6907,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.24,
|
| 1435 |
+
"grad_norm": 0.6514850828217877,
|
| 1436 |
+
"learning_rate": 3.2107886090705035e-06,
|
| 1437 |
+
"loss": 0.7155,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.2560000000000002,
|
| 1442 |
+
"grad_norm": 0.8216743112809076,
|
| 1443 |
+
"learning_rate": 3.158330337390565e-06,
|
| 1444 |
+
"loss": 0.5908,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.2720000000000002,
|
| 1449 |
+
"grad_norm": 0.6175170431371285,
|
| 1450 |
+
"learning_rate": 3.10610557194712e-06,
|
| 1451 |
+
"loss": 0.7275,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.288,
|
| 1456 |
+
"grad_norm": 0.49918856301616266,
|
| 1457 |
+
"learning_rate": 3.0541209343448373e-06,
|
| 1458 |
+
"loss": 0.6363,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.304,
|
| 1463 |
+
"grad_norm": 0.4505859996624395,
|
| 1464 |
+
"learning_rate": 3.0023830157424504e-06,
|
| 1465 |
+
"loss": 0.5068,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 3.32,
|
| 1470 |
+
"grad_norm": 0.6047043450034242,
|
| 1471 |
+
"learning_rate": 2.950898376017064e-06,
|
| 1472 |
+
"loss": 0.6684,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.336,
|
| 1477 |
+
"grad_norm": 0.7050300424064798,
|
| 1478 |
+
"learning_rate": 2.8996735429324256e-06,
|
| 1479 |
+
"loss": 0.5437,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 3.352,
|
| 1484 |
+
"grad_norm": 0.6046509312257183,
|
| 1485 |
+
"learning_rate": 2.848715011311271e-06,
|
| 1486 |
+
"loss": 0.6065,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.368,
|
| 1491 |
+
"grad_norm": 0.5489312138581334,
|
| 1492 |
+
"learning_rate": 2.7980292422118282e-06,
|
| 1493 |
+
"loss": 0.6238,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.384,
|
| 1498 |
+
"grad_norm": 0.5345507410785075,
|
| 1499 |
+
"learning_rate": 2.7476226621086354e-06,
|
| 1500 |
+
"loss": 0.6665,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 3.4,
|
| 1505 |
+
"grad_norm": 0.44663549941791464,
|
| 1506 |
+
"learning_rate": 2.697501662077707e-06,
|
| 1507 |
+
"loss": 0.6989,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 3.416,
|
| 1512 |
+
"grad_norm": 0.4997402304914766,
|
| 1513 |
+
"learning_rate": 2.6476725969862227e-06,
|
| 1514 |
+
"loss": 0.7103,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 3.432,
|
| 1519 |
+
"grad_norm": 0.5248320920728966,
|
| 1520 |
+
"learning_rate": 2.5981417846867753e-06,
|
| 1521 |
+
"loss": 0.708,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 3.448,
|
| 1526 |
+
"grad_norm": 0.47361876881842346,
|
| 1527 |
+
"learning_rate": 2.548915505216333e-06,
|
| 1528 |
+
"loss": 0.6161,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.464,
|
| 1533 |
+
"grad_norm": 0.38951773809344253,
|
| 1534 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 1535 |
+
"loss": 0.6242,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 3.48,
|
| 1540 |
+
"grad_norm": 0.4621052178631838,
|
| 1541 |
+
"learning_rate": 2.4514014710596467e-06,
|
| 1542 |
+
"loss": 0.6869,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 3.496,
|
| 1547 |
+
"grad_norm": 0.6218871062337231,
|
| 1548 |
+
"learning_rate": 2.4031260802275623e-06,
|
| 1549 |
+
"loss": 0.6285,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.512,
|
| 1554 |
+
"grad_norm": 0.5837366459679408,
|
| 1555 |
+
"learning_rate": 2.3551799483651894e-06,
|
| 1556 |
+
"loss": 0.601,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.528,
|
| 1561 |
+
"grad_norm": 0.5638704457348409,
|
| 1562 |
+
"learning_rate": 2.307569154587056e-06,
|
| 1563 |
+
"loss": 0.6197,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 3.544,
|
| 1568 |
+
"grad_norm": 0.48163508407083816,
|
| 1569 |
+
"learning_rate": 2.2602997354900075e-06,
|
| 1570 |
+
"loss": 0.5835,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 3.56,
|
| 1575 |
+
"grad_norm": 0.42941733644651287,
|
| 1576 |
+
"learning_rate": 2.2133776843878185e-06,
|
| 1577 |
+
"loss": 0.6948,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.576,
|
| 1582 |
+
"grad_norm": 0.5079953380381145,
|
| 1583 |
+
"learning_rate": 2.166808950551296e-06,
|
| 1584 |
+
"loss": 0.5979,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.592,
|
| 1589 |
+
"grad_norm": 0.44804407509524075,
|
| 1590 |
+
"learning_rate": 2.120599438453968e-06,
|
| 1591 |
+
"loss": 0.6914,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 3.608,
|
| 1596 |
+
"grad_norm": 0.43408421753223764,
|
| 1597 |
+
"learning_rate": 2.074755007023461e-06,
|
| 1598 |
+
"loss": 0.6357,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 3.624,
|
| 1603 |
+
"grad_norm": 0.5135247400323784,
|
| 1604 |
+
"learning_rate": 2.0292814688986375e-06,
|
| 1605 |
+
"loss": 0.657,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 3.64,
|
| 1610 |
+
"grad_norm": 0.414982645568696,
|
| 1611 |
+
"learning_rate": 1.9841845896926022e-06,
|
| 1612 |
+
"loss": 0.6087,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 3.656,
|
| 1617 |
+
"grad_norm": 0.6317365143952755,
|
| 1618 |
+
"learning_rate": 1.9394700872616856e-06,
|
| 1619 |
+
"loss": 0.6895,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 3.672,
|
| 1624 |
+
"grad_norm": 0.42574406798807973,
|
| 1625 |
+
"learning_rate": 1.8951436309804766e-06,
|
| 1626 |
+
"loss": 0.6307,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.6879999999999997,
|
| 1631 |
+
"grad_norm": 0.4066800096346742,
|
| 1632 |
+
"learning_rate": 1.8512108410229878e-06,
|
| 1633 |
+
"loss": 0.6796,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 3.7039999999999997,
|
| 1638 |
+
"grad_norm": 0.4312374117560947,
|
| 1639 |
+
"learning_rate": 1.8076772876500831e-06,
|
| 1640 |
+
"loss": 0.5983,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.7199999999999998,
|
| 1645 |
+
"grad_norm": 0.4963904945917347,
|
| 1646 |
+
"learning_rate": 1.7645484905032129e-06,
|
| 1647 |
+
"loss": 0.6899,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 3.7359999999999998,
|
| 1652 |
+
"grad_norm": 0.8069474385968237,
|
| 1653 |
+
"learning_rate": 1.7218299179045789e-06,
|
| 1654 |
+
"loss": 0.6829,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 3.752,
|
| 1659 |
+
"grad_norm": 0.4408325662467717,
|
| 1660 |
+
"learning_rate": 1.6795269861638041e-06,
|
| 1661 |
+
"loss": 0.6838,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 3.768,
|
| 1666 |
+
"grad_norm": 0.39257406551923874,
|
| 1667 |
+
"learning_rate": 1.6376450588911985e-06,
|
| 1668 |
+
"loss": 0.621,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 3.784,
|
| 1673 |
+
"grad_norm": 0.5021408990976908,
|
| 1674 |
+
"learning_rate": 1.5961894463176942e-06,
|
| 1675 |
+
"loss": 0.5381,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 3.8,
|
| 1680 |
+
"grad_norm": 1.0161511106208339,
|
| 1681 |
+
"learning_rate": 1.555165404621567e-06,
|
| 1682 |
+
"loss": 0.6631,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 3.816,
|
| 1687 |
+
"grad_norm": 0.5589883713476835,
|
| 1688 |
+
"learning_rate": 1.5145781352620054e-06,
|
| 1689 |
+
"loss": 0.7263,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 3.832,
|
| 1694 |
+
"grad_norm": 0.5170039801729964,
|
| 1695 |
+
"learning_rate": 1.4744327843196043e-06,
|
| 1696 |
+
"loss": 0.6526,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 3.848,
|
| 1701 |
+
"grad_norm": 0.4365703947702624,
|
| 1702 |
+
"learning_rate": 1.434734441843899e-06,
|
| 1703 |
+
"loss": 0.624,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.864,
|
| 1708 |
+
"grad_norm": 0.45343775193001395,
|
| 1709 |
+
"learning_rate": 1.3954881412079945e-06,
|
| 1710 |
+
"loss": 0.6207,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 3.88,
|
| 1715 |
+
"grad_norm": 0.5987276534862411,
|
| 1716 |
+
"learning_rate": 1.3566988584703817e-06,
|
| 1717 |
+
"loss": 0.6082,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 3.896,
|
| 1722 |
+
"grad_norm": 0.4189228526905657,
|
| 1723 |
+
"learning_rate": 1.3183715117440143e-06,
|
| 1724 |
+
"loss": 0.7211,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 3.912,
|
| 1729 |
+
"grad_norm": 0.4560749716198238,
|
| 1730 |
+
"learning_rate": 1.280510960572745e-06,
|
| 1731 |
+
"loss": 0.8071,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 3.928,
|
| 1736 |
+
"grad_norm": 0.43909838579399224,
|
| 1737 |
+
"learning_rate": 1.2431220053151832e-06,
|
| 1738 |
+
"loss": 0.5696,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 3.944,
|
| 1743 |
+
"grad_norm": 0.3884372689129327,
|
| 1744 |
+
"learning_rate": 1.2062093865360458e-06,
|
| 1745 |
+
"loss": 0.6917,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 3.96,
|
| 1750 |
+
"grad_norm": 0.4782590203306387,
|
| 1751 |
+
"learning_rate": 1.1697777844051105e-06,
|
| 1752 |
+
"loss": 0.6519,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 3.976,
|
| 1757 |
+
"grad_norm": 0.47207710861498847,
|
| 1758 |
+
"learning_rate": 1.1338318181038037e-06,
|
| 1759 |
+
"loss": 0.6184,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 3.992,
|
| 1764 |
+
"grad_norm": 0.599636336477758,
|
| 1765 |
+
"learning_rate": 1.0983760452395415e-06,
|
| 1766 |
+
"loss": 0.5992,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 4.0,
|
| 1771 |
+
"grad_norm": 0.7417980348609519,
|
| 1772 |
+
"learning_rate": 1.063414961267859e-06,
|
| 1773 |
+
"loss": 0.6355,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
}
|
| 1776 |
+
],
|
| 1777 |
+
"logging_steps": 1,
|
| 1778 |
+
"max_steps": 310,
|
| 1779 |
+
"num_input_tokens_seen": 0,
|
| 1780 |
+
"num_train_epochs": 5,
|
| 1781 |
+
"save_steps": 500,
|
| 1782 |
+
"stateful_callbacks": {
|
| 1783 |
+
"TrainerControl": {
|
| 1784 |
+
"args": {
|
| 1785 |
+
"should_epoch_stop": false,
|
| 1786 |
+
"should_evaluate": false,
|
| 1787 |
+
"should_log": false,
|
| 1788 |
+
"should_save": true,
|
| 1789 |
+
"should_training_stop": false
|
| 1790 |
+
},
|
| 1791 |
+
"attributes": {}
|
| 1792 |
+
}
|
| 1793 |
+
},
|
| 1794 |
+
"total_flos": 50648268668928.0,
|
| 1795 |
+
"train_batch_size": 1,
|
| 1796 |
+
"trial_name": null,
|
| 1797 |
+
"trial_params": null
|
| 1798 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c1028dc3622e720731c6412f8963725b6a7cc32a4ba1fa24bca1f33df7d5c1
|
| 3 |
+
size 8081
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|