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 sha256:0386b61a2c439cb6cce020f5563aa49a64b825d8b1e92a5fd1da8af7f8925840
|
| 3 |
+
size 4997184968
|
model-00002-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fe82b868fe945af32de38b81b94cbe820e3d313024824ed5137fd036208551c
|
| 3 |
+
size 4997741608
|
model-00003-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5c7f85161ffe7099e34a7ad08ccb0afcc8e548a7cb02a38dc843e4cc55f1c0ca
|
| 3 |
+
size 4997742208
|
model-00004-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:991cbbfd8553149d1fc9e8e0cd316d3b73de2bfb71c778bb73fe597836d2124d
|
| 3 |
+
size 4997743184
|
model-00005-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:21ce972afcfa6d43897716d8ce6d45ef3cd43ed8c88b5b66876417bf04fb23f0
|
| 3 |
+
size 4997743184
|
model-00006-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb1f51df277e8dfc00490e8f2eed68b73969582cbd85c0956b460d08f298cbd
|
| 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:a209a01b0ceaa037f919a12758ebd324e8f9b94322e5e70abb176d3c2d86bbc1
|
| 3 |
+
size 4997743184
|
model-00008-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:167cc1e37ca6c2f3c500426cd336f2edb99ac1c10b0e228e17798efda6a9b4d2
|
| 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:b9d22b8dfb97f64c0c4cdad962f6652c599948e2ddd1cf5cbbec1d4546499787
|
| 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:d35774e96dfcc2439877da869acd447b35b4a3f1a4eac44c04a5f33143dafc70
|
| 3 |
+
size 4997743184
|
model-00011-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1e73ba53154fa47adabdc86be90250f513e3a8971fe1966dbdee28ea58f765e2
|
| 3 |
+
size 4997743184
|
model-00012-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:169f30ca46af03043d5092a510fc3dcd9e7704c9bd977d006103a9360830dd67
|
| 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:b6a8cfc4034b8ca622364bb3e96f6c510236e5c23e1fff8064f558338c9a29eb
|
| 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": 0.015873015873015872,
|
| 14 |
+
"grad_norm": 2.3323949793109238,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 1.0469,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.031746031746031744,
|
| 21 |
+
"grad_norm": 2.317201200688066,
|
| 22 |
+
"learning_rate": 3.125e-07,
|
| 23 |
+
"loss": 0.9931,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.047619047619047616,
|
| 28 |
+
"grad_norm": 2.603689956679125,
|
| 29 |
+
"learning_rate": 6.25e-07,
|
| 30 |
+
"loss": 1.0188,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.06349206349206349,
|
| 35 |
+
"grad_norm": 2.2583787301898592,
|
| 36 |
+
"learning_rate": 9.375000000000001e-07,
|
| 37 |
+
"loss": 0.9097,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.07936507936507936,
|
| 42 |
+
"grad_norm": 2.197466891038096,
|
| 43 |
+
"learning_rate": 1.25e-06,
|
| 44 |
+
"loss": 1.0459,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.09523809523809523,
|
| 49 |
+
"grad_norm": 2.1259963361099747,
|
| 50 |
+
"learning_rate": 1.5625e-06,
|
| 51 |
+
"loss": 0.9986,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.1111111111111111,
|
| 56 |
+
"grad_norm": 2.0707820881041,
|
| 57 |
+
"learning_rate": 1.8750000000000003e-06,
|
| 58 |
+
"loss": 0.9555,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.12698412698412698,
|
| 63 |
+
"grad_norm": 1.870407527874291,
|
| 64 |
+
"learning_rate": 2.1875000000000002e-06,
|
| 65 |
+
"loss": 0.952,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.14285714285714285,
|
| 70 |
+
"grad_norm": 1.8578085390534953,
|
| 71 |
+
"learning_rate": 2.5e-06,
|
| 72 |
+
"loss": 0.9993,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.15873015873015872,
|
| 77 |
+
"grad_norm": 1.881148688458384,
|
| 78 |
+
"learning_rate": 2.8125e-06,
|
| 79 |
+
"loss": 0.9373,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.1746031746031746,
|
| 84 |
+
"grad_norm": 1.6917769845914787,
|
| 85 |
+
"learning_rate": 3.125e-06,
|
| 86 |
+
"loss": 0.8839,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.19047619047619047,
|
| 91 |
+
"grad_norm": 1.2541345576396532,
|
| 92 |
+
"learning_rate": 3.4375e-06,
|
| 93 |
+
"loss": 0.9909,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.20634920634920634,
|
| 98 |
+
"grad_norm": 1.4038335670152517,
|
| 99 |
+
"learning_rate": 3.7500000000000005e-06,
|
| 100 |
+
"loss": 0.9322,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.2222222222222222,
|
| 105 |
+
"grad_norm": 1.363468897891553,
|
| 106 |
+
"learning_rate": 4.0625000000000005e-06,
|
| 107 |
+
"loss": 1.0934,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.23809523809523808,
|
| 112 |
+
"grad_norm": 1.1331989679866032,
|
| 113 |
+
"learning_rate": 4.3750000000000005e-06,
|
| 114 |
+
"loss": 0.977,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.25396825396825395,
|
| 119 |
+
"grad_norm": 0.9899834287202586,
|
| 120 |
+
"learning_rate": 4.6875000000000004e-06,
|
| 121 |
+
"loss": 1.0443,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.2698412698412698,
|
| 126 |
+
"grad_norm": 1.155920523517074,
|
| 127 |
+
"learning_rate": 5e-06,
|
| 128 |
+
"loss": 0.9483,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.2857142857142857,
|
| 133 |
+
"grad_norm": 1.2715867938274161,
|
| 134 |
+
"learning_rate": 5.3125e-06,
|
| 135 |
+
"loss": 1.0096,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.30158730158730157,
|
| 140 |
+
"grad_norm": 0.9922231339593638,
|
| 141 |
+
"learning_rate": 5.625e-06,
|
| 142 |
+
"loss": 0.7463,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.31746031746031744,
|
| 147 |
+
"grad_norm": 1.2551959582539625,
|
| 148 |
+
"learning_rate": 5.9375e-06,
|
| 149 |
+
"loss": 0.9226,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.3333333333333333,
|
| 154 |
+
"grad_norm": 0.892951024999124,
|
| 155 |
+
"learning_rate": 6.25e-06,
|
| 156 |
+
"loss": 0.988,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.3492063492063492,
|
| 161 |
+
"grad_norm": 1.4360539096520086,
|
| 162 |
+
"learning_rate": 6.5625e-06,
|
| 163 |
+
"loss": 1.0509,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.36507936507936506,
|
| 168 |
+
"grad_norm": 1.1100051374669628,
|
| 169 |
+
"learning_rate": 6.875e-06,
|
| 170 |
+
"loss": 0.8728,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.38095238095238093,
|
| 175 |
+
"grad_norm": 0.9630208551024003,
|
| 176 |
+
"learning_rate": 7.1875e-06,
|
| 177 |
+
"loss": 0.8352,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.3968253968253968,
|
| 182 |
+
"grad_norm": 1.109963225007402,
|
| 183 |
+
"learning_rate": 7.500000000000001e-06,
|
| 184 |
+
"loss": 1.0289,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.4126984126984127,
|
| 189 |
+
"grad_norm": 0.842175710243708,
|
| 190 |
+
"learning_rate": 7.8125e-06,
|
| 191 |
+
"loss": 0.8616,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.42857142857142855,
|
| 196 |
+
"grad_norm": 0.8255762742603932,
|
| 197 |
+
"learning_rate": 8.125000000000001e-06,
|
| 198 |
+
"loss": 0.7234,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.4444444444444444,
|
| 203 |
+
"grad_norm": 0.8274507712792363,
|
| 204 |
+
"learning_rate": 8.4375e-06,
|
| 205 |
+
"loss": 0.9758,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.4603174603174603,
|
| 210 |
+
"grad_norm": 0.7834224887700044,
|
| 211 |
+
"learning_rate": 8.750000000000001e-06,
|
| 212 |
+
"loss": 0.9056,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.47619047619047616,
|
| 217 |
+
"grad_norm": 1.187020605300137,
|
| 218 |
+
"learning_rate": 9.0625e-06,
|
| 219 |
+
"loss": 0.9481,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.49206349206349204,
|
| 224 |
+
"grad_norm": 1.0233176856791018,
|
| 225 |
+
"learning_rate": 9.375000000000001e-06,
|
| 226 |
+
"loss": 0.9194,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.5079365079365079,
|
| 231 |
+
"grad_norm": 0.848791394024066,
|
| 232 |
+
"learning_rate": 9.6875e-06,
|
| 233 |
+
"loss": 0.8852,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.5238095238095238,
|
| 238 |
+
"grad_norm": 0.8289281876622956,
|
| 239 |
+
"learning_rate": 1e-05,
|
| 240 |
+
"loss": 1.038,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.5396825396825397,
|
| 245 |
+
"grad_norm": 0.7738330911179299,
|
| 246 |
+
"learning_rate": 9.999691920767945e-06,
|
| 247 |
+
"loss": 0.8374,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.5555555555555556,
|
| 252 |
+
"grad_norm": 0.65004421093035,
|
| 253 |
+
"learning_rate": 9.998767721036901e-06,
|
| 254 |
+
"loss": 0.8242,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.5714285714285714,
|
| 259 |
+
"grad_norm": 0.718229691257778,
|
| 260 |
+
"learning_rate": 9.997227514697568e-06,
|
| 261 |
+
"loss": 0.9693,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.5873015873015873,
|
| 266 |
+
"grad_norm": 0.598178727036991,
|
| 267 |
+
"learning_rate": 9.99507149155218e-06,
|
| 268 |
+
"loss": 0.9843,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.6031746031746031,
|
| 273 |
+
"grad_norm": 0.6896420594948925,
|
| 274 |
+
"learning_rate": 9.992299917291118e-06,
|
| 275 |
+
"loss": 0.848,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.6190476190476191,
|
| 280 |
+
"grad_norm": 0.7218001479564617,
|
| 281 |
+
"learning_rate": 9.98891313346017e-06,
|
| 282 |
+
"loss": 0.9095,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.6349206349206349,
|
| 287 |
+
"grad_norm": 0.673383804041238,
|
| 288 |
+
"learning_rate": 9.984911557418444e-06,
|
| 289 |
+
"loss": 0.7682,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.6507936507936508,
|
| 294 |
+
"grad_norm": 0.9044903125501461,
|
| 295 |
+
"learning_rate": 9.980295682286924e-06,
|
| 296 |
+
"loss": 0.8388,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.6666666666666666,
|
| 301 |
+
"grad_norm": 0.6528626470394925,
|
| 302 |
+
"learning_rate": 9.97506607688772e-06,
|
| 303 |
+
"loss": 0.9107,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.6825396825396826,
|
| 308 |
+
"grad_norm": 0.5248039585149111,
|
| 309 |
+
"learning_rate": 9.969223385673958e-06,
|
| 310 |
+
"loss": 0.8307,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.6984126984126984,
|
| 315 |
+
"grad_norm": 0.568338771820042,
|
| 316 |
+
"learning_rate": 9.962768328650367e-06,
|
| 317 |
+
"loss": 0.7523,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.7142857142857143,
|
| 322 |
+
"grad_norm": 0.5429855696185105,
|
| 323 |
+
"learning_rate": 9.95570170128455e-06,
|
| 324 |
+
"loss": 0.8442,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.7301587301587301,
|
| 329 |
+
"grad_norm": 0.5098426033492849,
|
| 330 |
+
"learning_rate": 9.94802437440896e-06,
|
| 331 |
+
"loss": 0.7962,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.746031746031746,
|
| 336 |
+
"grad_norm": 0.6078990273192543,
|
| 337 |
+
"learning_rate": 9.939737294113585e-06,
|
| 338 |
+
"loss": 0.8969,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.7619047619047619,
|
| 343 |
+
"grad_norm": 0.4709547244829324,
|
| 344 |
+
"learning_rate": 9.930841481629358e-06,
|
| 345 |
+
"loss": 0.8885,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.7777777777777778,
|
| 350 |
+
"grad_norm": 0.54039591858629,
|
| 351 |
+
"learning_rate": 9.92133803320231e-06,
|
| 352 |
+
"loss": 0.7818,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.7936507936507936,
|
| 357 |
+
"grad_norm": 0.4875170254753124,
|
| 358 |
+
"learning_rate": 9.91122811995848e-06,
|
| 359 |
+
"loss": 0.8193,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.8095238095238095,
|
| 364 |
+
"grad_norm": 0.5005396928536703,
|
| 365 |
+
"learning_rate": 9.90051298775959e-06,
|
| 366 |
+
"loss": 0.8692,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.8253968253968254,
|
| 371 |
+
"grad_norm": 0.40245216027036546,
|
| 372 |
+
"learning_rate": 9.88919395704952e-06,
|
| 373 |
+
"loss": 0.826,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.8412698412698413,
|
| 378 |
+
"grad_norm": 0.5389952051377087,
|
| 379 |
+
"learning_rate": 9.877272422691583e-06,
|
| 380 |
+
"loss": 0.9318,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.8571428571428571,
|
| 385 |
+
"grad_norm": 0.5638980417584056,
|
| 386 |
+
"learning_rate": 9.864749853796642e-06,
|
| 387 |
+
"loss": 0.7985,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.873015873015873,
|
| 392 |
+
"grad_norm": 0.5506830661309166,
|
| 393 |
+
"learning_rate": 9.85162779354206e-06,
|
| 394 |
+
"loss": 0.7291,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.8888888888888888,
|
| 399 |
+
"grad_norm": 0.48566023212019677,
|
| 400 |
+
"learning_rate": 9.837907858981536e-06,
|
| 401 |
+
"loss": 0.8802,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.9047619047619048,
|
| 406 |
+
"grad_norm": 0.4725406192484581,
|
| 407 |
+
"learning_rate": 9.823591740845831e-06,
|
| 408 |
+
"loss": 0.8627,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.9206349206349206,
|
| 413 |
+
"grad_norm": 0.5270784935436914,
|
| 414 |
+
"learning_rate": 9.808681203334416e-06,
|
| 415 |
+
"loss": 0.7976,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.9365079365079365,
|
| 420 |
+
"grad_norm": 0.4795159174595573,
|
| 421 |
+
"learning_rate": 9.793178083898073e-06,
|
| 422 |
+
"loss": 0.8783,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.9523809523809523,
|
| 427 |
+
"grad_norm": 0.42309628953003137,
|
| 428 |
+
"learning_rate": 9.777084293012448e-06,
|
| 429 |
+
"loss": 0.842,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.9682539682539683,
|
| 434 |
+
"grad_norm": 0.464555539059811,
|
| 435 |
+
"learning_rate": 9.760401813942641e-06,
|
| 436 |
+
"loss": 0.7662,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.9841269841269841,
|
| 441 |
+
"grad_norm": 0.5141212041737542,
|
| 442 |
+
"learning_rate": 9.743132702498785e-06,
|
| 443 |
+
"loss": 0.8688,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 1.0,
|
| 448 |
+
"grad_norm": 0.5165788253828009,
|
| 449 |
+
"learning_rate": 9.725279086782719e-06,
|
| 450 |
+
"loss": 0.768,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 1.0158730158730158,
|
| 455 |
+
"grad_norm": 0.576629868282963,
|
| 456 |
+
"learning_rate": 9.706843166925733e-06,
|
| 457 |
+
"loss": 0.7989,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 1.0317460317460316,
|
| 462 |
+
"grad_norm": 0.4946943998511545,
|
| 463 |
+
"learning_rate": 9.687827214817433e-06,
|
| 464 |
+
"loss": 0.8261,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 1.0476190476190477,
|
| 469 |
+
"grad_norm": 0.4987216606535057,
|
| 470 |
+
"learning_rate": 9.668233573825794e-06,
|
| 471 |
+
"loss": 0.8905,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 1.0634920634920635,
|
| 476 |
+
"grad_norm": 0.45688977932466196,
|
| 477 |
+
"learning_rate": 9.64806465850836e-06,
|
| 478 |
+
"loss": 0.7327,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 1.0793650793650793,
|
| 483 |
+
"grad_norm": 0.5226340006885853,
|
| 484 |
+
"learning_rate": 9.62732295431471e-06,
|
| 485 |
+
"loss": 0.7311,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 1.0952380952380953,
|
| 490 |
+
"grad_norm": 0.6684025298786129,
|
| 491 |
+
"learning_rate": 9.606011017280166e-06,
|
| 492 |
+
"loss": 0.8971,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 1.1111111111111112,
|
| 497 |
+
"grad_norm": 0.5147703758608321,
|
| 498 |
+
"learning_rate": 9.5841314737108e-06,
|
| 499 |
+
"loss": 0.7652,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 1.126984126984127,
|
| 504 |
+
"grad_norm": 0.5417227409614662,
|
| 505 |
+
"learning_rate": 9.56168701985981e-06,
|
| 506 |
+
"loss": 0.7999,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 1.1428571428571428,
|
| 511 |
+
"grad_norm": 0.5016561221704748,
|
| 512 |
+
"learning_rate": 9.538680421595236e-06,
|
| 513 |
+
"loss": 0.8074,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 1.1587301587301586,
|
| 518 |
+
"grad_norm": 0.4853528793957531,
|
| 519 |
+
"learning_rate": 9.515114514059127e-06,
|
| 520 |
+
"loss": 0.8135,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 1.1746031746031746,
|
| 525 |
+
"grad_norm": 0.47765415470199357,
|
| 526 |
+
"learning_rate": 9.490992201318165e-06,
|
| 527 |
+
"loss": 0.7879,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 1.1904761904761905,
|
| 532 |
+
"grad_norm": 0.46535342031003013,
|
| 533 |
+
"learning_rate": 9.466316456005783e-06,
|
| 534 |
+
"loss": 0.7762,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 1.2063492063492063,
|
| 539 |
+
"grad_norm": 0.5033568814253909,
|
| 540 |
+
"learning_rate": 9.441090318955843e-06,
|
| 541 |
+
"loss": 0.7022,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 1.2222222222222223,
|
| 546 |
+
"grad_norm": 0.4986643533291915,
|
| 547 |
+
"learning_rate": 9.415316898827923e-06,
|
| 548 |
+
"loss": 0.7349,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 1.2380952380952381,
|
| 553 |
+
"grad_norm": 0.43657193718859494,
|
| 554 |
+
"learning_rate": 9.388999371724212e-06,
|
| 555 |
+
"loss": 0.8264,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 1.253968253968254,
|
| 560 |
+
"grad_norm": 0.47617277777848616,
|
| 561 |
+
"learning_rate": 9.362140980798127e-06,
|
| 562 |
+
"loss": 0.8944,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 1.2698412698412698,
|
| 567 |
+
"grad_norm": 0.4295219607791053,
|
| 568 |
+
"learning_rate": 9.334745035854646e-06,
|
| 569 |
+
"loss": 0.7588,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 1.2857142857142856,
|
| 574 |
+
"grad_norm": 0.5225987407011279,
|
| 575 |
+
"learning_rate": 9.306814912942445e-06,
|
| 576 |
+
"loss": 0.8359,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 1.3015873015873016,
|
| 581 |
+
"grad_norm": 0.4173684559568506,
|
| 582 |
+
"learning_rate": 9.278354053937848e-06,
|
| 583 |
+
"loss": 0.7804,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 1.3174603174603174,
|
| 588 |
+
"grad_norm": 0.5238592049595157,
|
| 589 |
+
"learning_rate": 9.249365966120692e-06,
|
| 590 |
+
"loss": 0.8564,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 1.3333333333333333,
|
| 595 |
+
"grad_norm": 0.4526393208745273,
|
| 596 |
+
"learning_rate": 9.219854221742106e-06,
|
| 597 |
+
"loss": 0.8102,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 1.3492063492063493,
|
| 602 |
+
"grad_norm": 0.44471888761912887,
|
| 603 |
+
"learning_rate": 9.189822457584311e-06,
|
| 604 |
+
"loss": 0.7439,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 1.3650793650793651,
|
| 609 |
+
"grad_norm": 0.43731884433734214,
|
| 610 |
+
"learning_rate": 9.159274374512444e-06,
|
| 611 |
+
"loss": 0.6592,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 1.380952380952381,
|
| 616 |
+
"grad_norm": 0.4377614076782124,
|
| 617 |
+
"learning_rate": 9.128213737018493e-06,
|
| 618 |
+
"loss": 0.806,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 1.3968253968253967,
|
| 623 |
+
"grad_norm": 0.4027105033083121,
|
| 624 |
+
"learning_rate": 9.096644372757393e-06,
|
| 625 |
+
"loss": 0.8855,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 1.4126984126984126,
|
| 630 |
+
"grad_norm": 0.571463019194369,
|
| 631 |
+
"learning_rate": 9.064570172075349e-06,
|
| 632 |
+
"loss": 0.7979,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 1.4285714285714286,
|
| 637 |
+
"grad_norm": 0.4801097800367482,
|
| 638 |
+
"learning_rate": 9.031995087530403e-06,
|
| 639 |
+
"loss": 0.7992,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 1.4444444444444444,
|
| 644 |
+
"grad_norm": 0.47255682704462587,
|
| 645 |
+
"learning_rate": 8.99892313340537e-06,
|
| 646 |
+
"loss": 0.6633,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 1.4603174603174602,
|
| 651 |
+
"grad_norm": 0.4862492507086913,
|
| 652 |
+
"learning_rate": 8.96535838521314e-06,
|
| 653 |
+
"loss": 0.8033,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 1.4761904761904763,
|
| 658 |
+
"grad_norm": 0.4794987734861929,
|
| 659 |
+
"learning_rate": 8.931304979194452e-06,
|
| 660 |
+
"loss": 0.8069,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 1.492063492063492,
|
| 665 |
+
"grad_norm": 0.4658669415595415,
|
| 666 |
+
"learning_rate": 8.896767111808177e-06,
|
| 667 |
+
"loss": 0.7371,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 1.507936507936508,
|
| 672 |
+
"grad_norm": 0.5683125861447418,
|
| 673 |
+
"learning_rate": 8.861749039214177e-06,
|
| 674 |
+
"loss": 0.9145,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 1.5238095238095237,
|
| 679 |
+
"grad_norm": 0.47857884026171116,
|
| 680 |
+
"learning_rate": 8.826255076748823e-06,
|
| 681 |
+
"loss": 0.8455,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 1.5396825396825395,
|
| 686 |
+
"grad_norm": 0.429389167302876,
|
| 687 |
+
"learning_rate": 8.790289598393186e-06,
|
| 688 |
+
"loss": 0.7216,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 1.5555555555555556,
|
| 693 |
+
"grad_norm": 0.522031534882144,
|
| 694 |
+
"learning_rate": 8.753857036234055e-06,
|
| 695 |
+
"loss": 0.8155,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 1.5714285714285714,
|
| 700 |
+
"grad_norm": 0.5375692580431519,
|
| 701 |
+
"learning_rate": 8.716961879917734e-06,
|
| 702 |
+
"loss": 0.7373,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 1.5873015873015874,
|
| 707 |
+
"grad_norm": 0.4277716225580266,
|
| 708 |
+
"learning_rate": 8.679608676096793e-06,
|
| 709 |
+
"loss": 0.8132,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 1.6031746031746033,
|
| 714 |
+
"grad_norm": 0.9709114563751018,
|
| 715 |
+
"learning_rate": 8.641802027869774e-06,
|
| 716 |
+
"loss": 0.7952,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 1.619047619047619,
|
| 721 |
+
"grad_norm": 0.6722991060253756,
|
| 722 |
+
"learning_rate": 8.603546594213935e-06,
|
| 723 |
+
"loss": 0.8566,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 1.6349206349206349,
|
| 728 |
+
"grad_norm": 0.48227435877100366,
|
| 729 |
+
"learning_rate": 8.564847089411128e-06,
|
| 730 |
+
"loss": 0.8292,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 1.6507936507936507,
|
| 735 |
+
"grad_norm": 0.43738769808282163,
|
| 736 |
+
"learning_rate": 8.525708282466839e-06,
|
| 737 |
+
"loss": 0.8424,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 1.6666666666666665,
|
| 742 |
+
"grad_norm": 0.42758983764847835,
|
| 743 |
+
"learning_rate": 8.486134996522502e-06,
|
| 744 |
+
"loss": 0.8179,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 1.6825396825396826,
|
| 749 |
+
"grad_norm": 0.6465752665836958,
|
| 750 |
+
"learning_rate": 8.446132108261136e-06,
|
| 751 |
+
"loss": 0.806,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 1.6984126984126984,
|
| 756 |
+
"grad_norm": 0.5216064305348748,
|
| 757 |
+
"learning_rate": 8.405704547306379e-06,
|
| 758 |
+
"loss": 0.8041,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 1.7142857142857144,
|
| 763 |
+
"grad_norm": 0.46284349128240304,
|
| 764 |
+
"learning_rate": 8.364857295615006e-06,
|
| 765 |
+
"loss": 0.8924,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 1.7301587301587302,
|
| 770 |
+
"grad_norm": 0.48814352812138595,
|
| 771 |
+
"learning_rate": 8.323595386862985e-06,
|
| 772 |
+
"loss": 0.7929,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 1.746031746031746,
|
| 777 |
+
"grad_norm": 0.48088506678769916,
|
| 778 |
+
"learning_rate": 8.281923905825188e-06,
|
| 779 |
+
"loss": 0.7671,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 1.7619047619047619,
|
| 784 |
+
"grad_norm": 0.4594586947272896,
|
| 785 |
+
"learning_rate": 8.23984798774876e-06,
|
| 786 |
+
"loss": 0.7366,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 1.7777777777777777,
|
| 791 |
+
"grad_norm": 0.4673793179812366,
|
| 792 |
+
"learning_rate": 8.197372817720314e-06,
|
| 793 |
+
"loss": 0.7397,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 1.7936507936507935,
|
| 798 |
+
"grad_norm": 0.6557346369623661,
|
| 799 |
+
"learning_rate": 8.154503630026955e-06,
|
| 800 |
+
"loss": 0.7262,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 1.8095238095238095,
|
| 805 |
+
"grad_norm": 0.45128446254113314,
|
| 806 |
+
"learning_rate": 8.111245707511253e-06,
|
| 807 |
+
"loss": 0.7213,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.8253968253968254,
|
| 812 |
+
"grad_norm": 0.41666335434637974,
|
| 813 |
+
"learning_rate": 8.067604380920228e-06,
|
| 814 |
+
"loss": 0.7952,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.8412698412698414,
|
| 819 |
+
"grad_norm": 0.4407610683896587,
|
| 820 |
+
"learning_rate": 8.023585028248435e-06,
|
| 821 |
+
"loss": 0.8486,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.8571428571428572,
|
| 826 |
+
"grad_norm": 0.5501977264080524,
|
| 827 |
+
"learning_rate": 7.979193074075216e-06,
|
| 828 |
+
"loss": 0.8911,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.873015873015873,
|
| 833 |
+
"grad_norm": 0.459940871244406,
|
| 834 |
+
"learning_rate": 7.934433988896233e-06,
|
| 835 |
+
"loss": 0.6535,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.8888888888888888,
|
| 840 |
+
"grad_norm": 0.46949896874504654,
|
| 841 |
+
"learning_rate": 7.889313288449323e-06,
|
| 842 |
+
"loss": 0.8232,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.9047619047619047,
|
| 847 |
+
"grad_norm": 0.41110722374315695,
|
| 848 |
+
"learning_rate": 7.843836533034784e-06,
|
| 849 |
+
"loss": 0.7628,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.9206349206349205,
|
| 854 |
+
"grad_norm": 0.47755036946919965,
|
| 855 |
+
"learning_rate": 7.798009326830167e-06,
|
| 856 |
+
"loss": 0.8003,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.9365079365079365,
|
| 861 |
+
"grad_norm": 0.41342145123270885,
|
| 862 |
+
"learning_rate": 7.751837317199673e-06,
|
| 863 |
+
"loss": 0.8683,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.9523809523809523,
|
| 868 |
+
"grad_norm": 0.4479867168170251,
|
| 869 |
+
"learning_rate": 7.705326193998207e-06,
|
| 870 |
+
"loss": 0.7552,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.9682539682539684,
|
| 875 |
+
"grad_norm": 0.4549548876094008,
|
| 876 |
+
"learning_rate": 7.658481688870218e-06,
|
| 877 |
+
"loss": 0.7587,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.9841269841269842,
|
| 882 |
+
"grad_norm": 0.4684989926335189,
|
| 883 |
+
"learning_rate": 7.611309574543373e-06,
|
| 884 |
+
"loss": 0.7607,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 2.0,
|
| 889 |
+
"grad_norm": 0.4367513791425883,
|
| 890 |
+
"learning_rate": 7.563815664117173e-06,
|
| 891 |
+
"loss": 0.9146,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 2.015873015873016,
|
| 896 |
+
"grad_norm": 0.7927149278076437,
|
| 897 |
+
"learning_rate": 7.5160058103465985e-06,
|
| 898 |
+
"loss": 0.7131,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 2.0317460317460316,
|
| 903 |
+
"grad_norm": 0.5847918647965703,
|
| 904 |
+
"learning_rate": 7.467885904920864e-06,
|
| 905 |
+
"loss": 0.7578,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 2.0476190476190474,
|
| 910 |
+
"grad_norm": 0.7836046335272314,
|
| 911 |
+
"learning_rate": 7.419461877737373e-06,
|
| 912 |
+
"loss": 0.8327,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 2.0634920634920633,
|
| 917 |
+
"grad_norm": 2.1428241341527117,
|
| 918 |
+
"learning_rate": 7.370739696170971e-06,
|
| 919 |
+
"loss": 0.7441,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 2.0793650793650795,
|
| 924 |
+
"grad_norm": 0.9566247813485141,
|
| 925 |
+
"learning_rate": 7.321725364338566e-06,
|
| 926 |
+
"loss": 0.6185,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 2.0952380952380953,
|
| 931 |
+
"grad_norm": 0.5336099004301172,
|
| 932 |
+
"learning_rate": 7.272424922359246e-06,
|
| 933 |
+
"loss": 0.6455,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 2.111111111111111,
|
| 938 |
+
"grad_norm": 0.7132260718912609,
|
| 939 |
+
"learning_rate": 7.222844445609931e-06,
|
| 940 |
+
"loss": 0.7834,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 2.126984126984127,
|
| 945 |
+
"grad_norm": 0.5749113101610002,
|
| 946 |
+
"learning_rate": 7.172990043976703e-06,
|
| 947 |
+
"loss": 0.7296,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 2.142857142857143,
|
| 952 |
+
"grad_norm": 0.5366676899164674,
|
| 953 |
+
"learning_rate": 7.122867861101868e-06,
|
| 954 |
+
"loss": 0.795,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 2.1587301587301586,
|
| 959 |
+
"grad_norm": 0.44931031781346276,
|
| 960 |
+
"learning_rate": 7.072484073626872e-06,
|
| 961 |
+
"loss": 0.6875,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 2.1746031746031744,
|
| 966 |
+
"grad_norm": 0.6709913679680917,
|
| 967 |
+
"learning_rate": 7.021844890431136e-06,
|
| 968 |
+
"loss": 0.7669,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 2.1904761904761907,
|
| 973 |
+
"grad_norm": 0.5782700607354144,
|
| 974 |
+
"learning_rate": 6.970956551866925e-06,
|
| 975 |
+
"loss": 0.7273,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 2.2063492063492065,
|
| 980 |
+
"grad_norm": 0.5008612890527109,
|
| 981 |
+
"learning_rate": 6.9198253289903515e-06,
|
| 982 |
+
"loss": 0.6634,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 2.2222222222222223,
|
| 987 |
+
"grad_norm": 0.5733594756270326,
|
| 988 |
+
"learning_rate": 6.868457522788561e-06,
|
| 989 |
+
"loss": 0.7358,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 2.238095238095238,
|
| 994 |
+
"grad_norm": 0.48532685396257946,
|
| 995 |
+
"learning_rate": 6.816859463403271e-06,
|
| 996 |
+
"loss": 0.659,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 2.253968253968254,
|
| 1001 |
+
"grad_norm": 0.5460096768726493,
|
| 1002 |
+
"learning_rate": 6.765037509350685e-06,
|
| 1003 |
+
"loss": 0.7585,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 2.2698412698412698,
|
| 1008 |
+
"grad_norm": 0.4827715321224934,
|
| 1009 |
+
"learning_rate": 6.7129980467379265e-06,
|
| 1010 |
+
"loss": 0.6664,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 2.2857142857142856,
|
| 1015 |
+
"grad_norm": 0.5417449745700821,
|
| 1016 |
+
"learning_rate": 6.660747488476066e-06,
|
| 1017 |
+
"loss": 0.663,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 2.3015873015873014,
|
| 1022 |
+
"grad_norm": 0.5672091588208017,
|
| 1023 |
+
"learning_rate": 6.608292273489851e-06,
|
| 1024 |
+
"loss": 0.6122,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 2.317460317460317,
|
| 1029 |
+
"grad_norm": 0.5264115445856029,
|
| 1030 |
+
"learning_rate": 6.555638865924221e-06,
|
| 1031 |
+
"loss": 0.7035,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 2.3333333333333335,
|
| 1036 |
+
"grad_norm": 0.5168486054014866,
|
| 1037 |
+
"learning_rate": 6.502793754347721e-06,
|
| 1038 |
+
"loss": 0.7598,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 2.3492063492063493,
|
| 1043 |
+
"grad_norm": 0.6085627519823247,
|
| 1044 |
+
"learning_rate": 6.449763450952912e-06,
|
| 1045 |
+
"loss": 0.6875,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 2.365079365079365,
|
| 1050 |
+
"grad_norm": 0.504951049632705,
|
| 1051 |
+
"learning_rate": 6.396554490753848e-06,
|
| 1052 |
+
"loss": 0.6839,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 2.380952380952381,
|
| 1057 |
+
"grad_norm": 0.42239268629753335,
|
| 1058 |
+
"learning_rate": 6.343173430780769e-06,
|
| 1059 |
+
"loss": 0.8396,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 2.3968253968253967,
|
| 1064 |
+
"grad_norm": 0.5170870251352963,
|
| 1065 |
+
"learning_rate": 6.289626849272062e-06,
|
| 1066 |
+
"loss": 0.8013,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 2.4126984126984126,
|
| 1071 |
+
"grad_norm": 0.5408561718958109,
|
| 1072 |
+
"learning_rate": 6.2359213448636104e-06,
|
| 1073 |
+
"loss": 0.754,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 2.4285714285714284,
|
| 1078 |
+
"grad_norm": 0.42606389993166277,
|
| 1079 |
+
"learning_rate": 6.182063535775634e-06,
|
| 1080 |
+
"loss": 0.7662,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 2.4444444444444446,
|
| 1085 |
+
"grad_norm": 0.41021417431281776,
|
| 1086 |
+
"learning_rate": 6.1280600589971225e-06,
|
| 1087 |
+
"loss": 0.791,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 2.4603174603174605,
|
| 1092 |
+
"grad_norm": 0.4068459581892925,
|
| 1093 |
+
"learning_rate": 6.073917569467934e-06,
|
| 1094 |
+
"loss": 0.8066,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 2.4761904761904763,
|
| 1099 |
+
"grad_norm": 0.40243757072180364,
|
| 1100 |
+
"learning_rate": 6.0196427392587085e-06,
|
| 1101 |
+
"loss": 0.7061,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 2.492063492063492,
|
| 1106 |
+
"grad_norm": 0.5924677871750427,
|
| 1107 |
+
"learning_rate": 5.96524225674865e-06,
|
| 1108 |
+
"loss": 0.744,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 2.507936507936508,
|
| 1113 |
+
"grad_norm": 0.4344103520994765,
|
| 1114 |
+
"learning_rate": 5.9107228258013085e-06,
|
| 1115 |
+
"loss": 0.7076,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 2.5238095238095237,
|
| 1120 |
+
"grad_norm": 0.4824828219676673,
|
| 1121 |
+
"learning_rate": 5.856091164938451e-06,
|
| 1122 |
+
"loss": 0.6534,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 2.5396825396825395,
|
| 1127 |
+
"grad_norm": 0.4197375023372333,
|
| 1128 |
+
"learning_rate": 5.801354006512127e-06,
|
| 1129 |
+
"loss": 0.6902,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 2.5555555555555554,
|
| 1134 |
+
"grad_norm": 0.4523354962317184,
|
| 1135 |
+
"learning_rate": 5.746518095875033e-06,
|
| 1136 |
+
"loss": 0.6996,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 2.571428571428571,
|
| 1141 |
+
"grad_norm": 0.41073692830700287,
|
| 1142 |
+
"learning_rate": 5.6915901905492586e-06,
|
| 1143 |
+
"loss": 0.629,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 2.5873015873015874,
|
| 1148 |
+
"grad_norm": 0.5807356357914126,
|
| 1149 |
+
"learning_rate": 5.6365770593935665e-06,
|
| 1150 |
+
"loss": 0.5924,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 2.6031746031746033,
|
| 1155 |
+
"grad_norm": 0.5296154741304107,
|
| 1156 |
+
"learning_rate": 5.581485481769231e-06,
|
| 1157 |
+
"loss": 0.7197,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 2.619047619047619,
|
| 1162 |
+
"grad_norm": 0.4462893254042338,
|
| 1163 |
+
"learning_rate": 5.526322246704628e-06,
|
| 1164 |
+
"loss": 0.8007,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 2.634920634920635,
|
| 1169 |
+
"grad_norm": 0.3974463949753287,
|
| 1170 |
+
"learning_rate": 5.471094152058592e-06,
|
| 1171 |
+
"loss": 0.6822,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 2.6507936507936507,
|
| 1176 |
+
"grad_norm": 0.46244966479154553,
|
| 1177 |
+
"learning_rate": 5.415808003682717e-06,
|
| 1178 |
+
"loss": 0.7318,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 2.6666666666666665,
|
| 1183 |
+
"grad_norm": 0.438557400530548,
|
| 1184 |
+
"learning_rate": 5.360470614582661e-06,
|
| 1185 |
+
"loss": 0.7147,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 2.682539682539683,
|
| 1190 |
+
"grad_norm": 0.5680373876053647,
|
| 1191 |
+
"learning_rate": 5.305088804078559e-06,
|
| 1192 |
+
"loss": 0.7357,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 2.6984126984126986,
|
| 1197 |
+
"grad_norm": 0.4556205137087138,
|
| 1198 |
+
"learning_rate": 5.249669396964665e-06,
|
| 1199 |
+
"loss": 0.6361,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 2.7142857142857144,
|
| 1204 |
+
"grad_norm": 0.44940699263796485,
|
| 1205 |
+
"learning_rate": 5.1942192226683385e-06,
|
| 1206 |
+
"loss": 0.7778,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 2.7301587301587302,
|
| 1211 |
+
"grad_norm": 0.47535854965434626,
|
| 1212 |
+
"learning_rate": 5.138745114408427e-06,
|
| 1213 |
+
"loss": 0.6008,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 2.746031746031746,
|
| 1218 |
+
"grad_norm": 0.5020715004802897,
|
| 1219 |
+
"learning_rate": 5.083253908353193e-06,
|
| 1220 |
+
"loss": 0.6696,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 2.761904761904762,
|
| 1225 |
+
"grad_norm": 0.4715489187155987,
|
| 1226 |
+
"learning_rate": 5.0277524427778986e-06,
|
| 1227 |
+
"loss": 0.7846,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 2.7777777777777777,
|
| 1232 |
+
"grad_norm": 0.44938039077917374,
|
| 1233 |
+
"learning_rate": 4.972247557222102e-06,
|
| 1234 |
+
"loss": 0.7187,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 2.7936507936507935,
|
| 1239 |
+
"grad_norm": 0.536309868809644,
|
| 1240 |
+
"learning_rate": 4.916746091646808e-06,
|
| 1241 |
+
"loss": 0.6818,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 2.8095238095238093,
|
| 1246 |
+
"grad_norm": 0.4238224566275176,
|
| 1247 |
+
"learning_rate": 4.8612548855915755e-06,
|
| 1248 |
+
"loss": 0.7252,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 2.825396825396825,
|
| 1253 |
+
"grad_norm": 0.5075369152051689,
|
| 1254 |
+
"learning_rate": 4.805780777331662e-06,
|
| 1255 |
+
"loss": 0.7461,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 2.8412698412698414,
|
| 1260 |
+
"grad_norm": 0.463068134108742,
|
| 1261 |
+
"learning_rate": 4.750330603035336e-06,
|
| 1262 |
+
"loss": 0.7141,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 2.857142857142857,
|
| 1267 |
+
"grad_norm": 0.44910366292391646,
|
| 1268 |
+
"learning_rate": 4.694911195921443e-06,
|
| 1269 |
+
"loss": 0.7278,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 2.873015873015873,
|
| 1274 |
+
"grad_norm": 0.43362119780351166,
|
| 1275 |
+
"learning_rate": 4.6395293854173395e-06,
|
| 1276 |
+
"loss": 0.6069,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 2.888888888888889,
|
| 1281 |
+
"grad_norm": 0.7285135499415637,
|
| 1282 |
+
"learning_rate": 4.584191996317285e-06,
|
| 1283 |
+
"loss": 0.6846,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 2.9047619047619047,
|
| 1288 |
+
"grad_norm": 0.49976201370002465,
|
| 1289 |
+
"learning_rate": 4.528905847941411e-06,
|
| 1290 |
+
"loss": 0.843,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 2.9206349206349205,
|
| 1295 |
+
"grad_norm": 0.47745344638517,
|
| 1296 |
+
"learning_rate": 4.473677753295375e-06,
|
| 1297 |
+
"loss": 0.6609,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 2.9365079365079367,
|
| 1302 |
+
"grad_norm": 0.4075892143069301,
|
| 1303 |
+
"learning_rate": 4.418514518230769e-06,
|
| 1304 |
+
"loss": 0.7133,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 2.9523809523809526,
|
| 1309 |
+
"grad_norm": 0.490679894902017,
|
| 1310 |
+
"learning_rate": 4.363422940606435e-06,
|
| 1311 |
+
"loss": 0.7483,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 2.9682539682539684,
|
| 1316 |
+
"grad_norm": 0.507751484260846,
|
| 1317 |
+
"learning_rate": 4.308409809450742e-06,
|
| 1318 |
+
"loss": 0.7635,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 2.984126984126984,
|
| 1323 |
+
"grad_norm": 0.5129728167302848,
|
| 1324 |
+
"learning_rate": 4.253481904124968e-06,
|
| 1325 |
+
"loss": 0.7353,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 3.0,
|
| 1330 |
+
"grad_norm": 0.44280290900369257,
|
| 1331 |
+
"learning_rate": 4.198645993487872e-06,
|
| 1332 |
+
"loss": 0.6059,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 3.015873015873016,
|
| 1337 |
+
"grad_norm": 0.7949393554198322,
|
| 1338 |
+
"learning_rate": 4.143908835061551e-06,
|
| 1339 |
+
"loss": 0.6868,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 3.0317460317460316,
|
| 1344 |
+
"grad_norm": 0.5012314119268376,
|
| 1345 |
+
"learning_rate": 4.089277174198694e-06,
|
| 1346 |
+
"loss": 0.7037,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 3.0476190476190474,
|
| 1351 |
+
"grad_norm": 0.8765248539640519,
|
| 1352 |
+
"learning_rate": 4.0347577432513515e-06,
|
| 1353 |
+
"loss": 0.746,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 3.0634920634920633,
|
| 1358 |
+
"grad_norm": 0.5276377235611475,
|
| 1359 |
+
"learning_rate": 3.980357260741293e-06,
|
| 1360 |
+
"loss": 0.6836,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 3.0793650793650795,
|
| 1365 |
+
"grad_norm": 0.5739417223582697,
|
| 1366 |
+
"learning_rate": 3.926082430532067e-06,
|
| 1367 |
+
"loss": 0.6428,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 3.0952380952380953,
|
| 1372 |
+
"grad_norm": 0.6325463534989497,
|
| 1373 |
+
"learning_rate": 3.87193994100288e-06,
|
| 1374 |
+
"loss": 0.6092,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 3.111111111111111,
|
| 1379 |
+
"grad_norm": 0.6843617935822326,
|
| 1380 |
+
"learning_rate": 3.817936464224367e-06,
|
| 1381 |
+
"loss": 0.6763,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 3.126984126984127,
|
| 1386 |
+
"grad_norm": 0.5698355849375702,
|
| 1387 |
+
"learning_rate": 3.764078655136391e-06,
|
| 1388 |
+
"loss": 0.7472,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 3.142857142857143,
|
| 1393 |
+
"grad_norm": 0.5699592517012283,
|
| 1394 |
+
"learning_rate": 3.7103731507279383e-06,
|
| 1395 |
+
"loss": 0.7029,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 3.1587301587301586,
|
| 1400 |
+
"grad_norm": 0.4423177821267063,
|
| 1401 |
+
"learning_rate": 3.656826569219233e-06,
|
| 1402 |
+
"loss": 0.6717,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 3.1746031746031744,
|
| 1407 |
+
"grad_norm": 0.5057172241583261,
|
| 1408 |
+
"learning_rate": 3.603445509246154e-06,
|
| 1409 |
+
"loss": 0.6429,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 3.1904761904761907,
|
| 1414 |
+
"grad_norm": 0.4627898485974749,
|
| 1415 |
+
"learning_rate": 3.55023654904709e-06,
|
| 1416 |
+
"loss": 0.7171,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 3.2063492063492065,
|
| 1421 |
+
"grad_norm": 0.4765018395044146,
|
| 1422 |
+
"learning_rate": 3.49720624565228e-06,
|
| 1423 |
+
"loss": 0.5539,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 3.2222222222222223,
|
| 1428 |
+
"grad_norm": 0.46472301884916256,
|
| 1429 |
+
"learning_rate": 3.44436113407578e-06,
|
| 1430 |
+
"loss": 0.6852,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 3.238095238095238,
|
| 1435 |
+
"grad_norm": 0.7227019117707013,
|
| 1436 |
+
"learning_rate": 3.3917077265101505e-06,
|
| 1437 |
+
"loss": 0.751,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 3.253968253968254,
|
| 1442 |
+
"grad_norm": 0.46124162458293566,
|
| 1443 |
+
"learning_rate": 3.3392525115239353e-06,
|
| 1444 |
+
"loss": 0.5753,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 3.2698412698412698,
|
| 1449 |
+
"grad_norm": 1.150296667678599,
|
| 1450 |
+
"learning_rate": 3.2870019532620744e-06,
|
| 1451 |
+
"loss": 0.7116,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 3.2857142857142856,
|
| 1456 |
+
"grad_norm": 0.45629133977245157,
|
| 1457 |
+
"learning_rate": 3.2349624906493164e-06,
|
| 1458 |
+
"loss": 0.6506,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 3.3015873015873014,
|
| 1463 |
+
"grad_norm": 0.6330635820823547,
|
| 1464 |
+
"learning_rate": 3.1831405365967315e-06,
|
| 1465 |
+
"loss": 0.5314,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 3.317460317460317,
|
| 1470 |
+
"grad_norm": 0.5103783322022635,
|
| 1471 |
+
"learning_rate": 3.1315424772114404e-06,
|
| 1472 |
+
"loss": 0.7163,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 3.3333333333333335,
|
| 1477 |
+
"grad_norm": 0.5407291227510194,
|
| 1478 |
+
"learning_rate": 3.0801746710096497e-06,
|
| 1479 |
+
"loss": 0.5543,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 3.3492063492063493,
|
| 1484 |
+
"grad_norm": 0.5148220790962434,
|
| 1485 |
+
"learning_rate": 3.0290434481330746e-06,
|
| 1486 |
+
"loss": 0.5885,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 3.365079365079365,
|
| 1491 |
+
"grad_norm": 0.4436633763550198,
|
| 1492 |
+
"learning_rate": 2.978155109568864e-06,
|
| 1493 |
+
"loss": 0.6205,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 3.380952380952381,
|
| 1498 |
+
"grad_norm": 0.3967936149581789,
|
| 1499 |
+
"learning_rate": 2.927515926373129e-06,
|
| 1500 |
+
"loss": 0.6664,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 3.3968253968253967,
|
| 1505 |
+
"grad_norm": 0.4218431236274798,
|
| 1506 |
+
"learning_rate": 2.8771321388981334e-06,
|
| 1507 |
+
"loss": 0.6664,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 3.4126984126984126,
|
| 1512 |
+
"grad_norm": 0.6850450086103512,
|
| 1513 |
+
"learning_rate": 2.8270099560232992e-06,
|
| 1514 |
+
"loss": 0.71,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 3.4285714285714284,
|
| 1519 |
+
"grad_norm": 0.49624036517991055,
|
| 1520 |
+
"learning_rate": 2.77715555439007e-06,
|
| 1521 |
+
"loss": 0.7545,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 3.4444444444444446,
|
| 1526 |
+
"grad_norm": 0.4389117683902036,
|
| 1527 |
+
"learning_rate": 2.7275750776407568e-06,
|
| 1528 |
+
"loss": 0.6014,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 3.4603174603174605,
|
| 1533 |
+
"grad_norm": 0.44946398322882497,
|
| 1534 |
+
"learning_rate": 2.6782746356614364e-06,
|
| 1535 |
+
"loss": 0.5866,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 3.4761904761904763,
|
| 1540 |
+
"grad_norm": 0.5130278875069821,
|
| 1541 |
+
"learning_rate": 2.6292603038290306e-06,
|
| 1542 |
+
"loss": 0.7161,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 3.492063492063492,
|
| 1547 |
+
"grad_norm": 0.6079510505594462,
|
| 1548 |
+
"learning_rate": 2.580538122262627e-06,
|
| 1549 |
+
"loss": 0.6545,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 3.507936507936508,
|
| 1554 |
+
"grad_norm": 0.5185432227363381,
|
| 1555 |
+
"learning_rate": 2.532114095079137e-06,
|
| 1556 |
+
"loss": 0.5745,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 3.5238095238095237,
|
| 1561 |
+
"grad_norm": 0.47475284651402894,
|
| 1562 |
+
"learning_rate": 2.4839941896534027e-06,
|
| 1563 |
+
"loss": 0.6287,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 3.5396825396825395,
|
| 1568 |
+
"grad_norm": 0.4721541505351033,
|
| 1569 |
+
"learning_rate": 2.4361843358828287e-06,
|
| 1570 |
+
"loss": 0.5891,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 3.5555555555555554,
|
| 1575 |
+
"grad_norm": 0.6637884613662758,
|
| 1576 |
+
"learning_rate": 2.388690425456629e-06,
|
| 1577 |
+
"loss": 0.7191,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 3.571428571428571,
|
| 1582 |
+
"grad_norm": 0.49879760044528987,
|
| 1583 |
+
"learning_rate": 2.341518311129781e-06,
|
| 1584 |
+
"loss": 0.5703,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 3.5873015873015874,
|
| 1589 |
+
"grad_norm": 0.42482396593298977,
|
| 1590 |
+
"learning_rate": 2.2946738060017947e-06,
|
| 1591 |
+
"loss": 0.706,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 3.6031746031746033,
|
| 1596 |
+
"grad_norm": 0.5244046208280333,
|
| 1597 |
+
"learning_rate": 2.24816268280033e-06,
|
| 1598 |
+
"loss": 0.6567,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 3.619047619047619,
|
| 1603 |
+
"grad_norm": 0.45713016270372664,
|
| 1604 |
+
"learning_rate": 2.2019906731698337e-06,
|
| 1605 |
+
"loss": 0.6519,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 3.634920634920635,
|
| 1610 |
+
"grad_norm": 0.3877769815934568,
|
| 1611 |
+
"learning_rate": 2.156163466965218e-06,
|
| 1612 |
+
"loss": 0.63,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 3.6507936507936507,
|
| 1617 |
+
"grad_norm": 0.5213212350040638,
|
| 1618 |
+
"learning_rate": 2.110686711550678e-06,
|
| 1619 |
+
"loss": 0.7059,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 3.6666666666666665,
|
| 1624 |
+
"grad_norm": 0.39785815195503926,
|
| 1625 |
+
"learning_rate": 2.0655660111037685e-06,
|
| 1626 |
+
"loss": 0.6371,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 3.682539682539683,
|
| 1631 |
+
"grad_norm": 0.42984736444835686,
|
| 1632 |
+
"learning_rate": 2.0208069259247866e-06,
|
| 1633 |
+
"loss": 0.659,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 3.6984126984126986,
|
| 1638 |
+
"grad_norm": 0.4602245826690893,
|
| 1639 |
+
"learning_rate": 1.976414971751568e-06,
|
| 1640 |
+
"loss": 0.6043,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 3.7142857142857144,
|
| 1645 |
+
"grad_norm": 0.4841459331133356,
|
| 1646 |
+
"learning_rate": 1.932395619079771e-06,
|
| 1647 |
+
"loss": 0.6762,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 3.7301587301587302,
|
| 1652 |
+
"grad_norm": 0.38677471787487294,
|
| 1653 |
+
"learning_rate": 1.8887542924887486e-06,
|
| 1654 |
+
"loss": 0.7034,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 3.746031746031746,
|
| 1659 |
+
"grad_norm": 0.669293977144537,
|
| 1660 |
+
"learning_rate": 1.8454963699730471e-06,
|
| 1661 |
+
"loss": 0.6753,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 3.761904761904762,
|
| 1666 |
+
"grad_norm": 0.9653712675428361,
|
| 1667 |
+
"learning_rate": 1.802627182279687e-06,
|
| 1668 |
+
"loss": 0.5958,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 3.7777777777777777,
|
| 1673 |
+
"grad_norm": 0.8023679085767069,
|
| 1674 |
+
"learning_rate": 1.760152012251241e-06,
|
| 1675 |
+
"loss": 0.5046,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 3.7936507936507935,
|
| 1680 |
+
"grad_norm": 0.523400494967504,
|
| 1681 |
+
"learning_rate": 1.7180760941748132e-06,
|
| 1682 |
+
"loss": 0.6704,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 3.8095238095238093,
|
| 1687 |
+
"grad_norm": 0.5650557974529034,
|
| 1688 |
+
"learning_rate": 1.6764046131370142e-06,
|
| 1689 |
+
"loss": 0.7334,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 3.825396825396825,
|
| 1694 |
+
"grad_norm": 0.446176823325039,
|
| 1695 |
+
"learning_rate": 1.6351427043849955e-06,
|
| 1696 |
+
"loss": 0.6972,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 3.8412698412698414,
|
| 1701 |
+
"grad_norm": 0.5687688471627884,
|
| 1702 |
+
"learning_rate": 1.5942954526936217e-06,
|
| 1703 |
+
"loss": 0.6563,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 3.857142857142857,
|
| 1708 |
+
"grad_norm": 0.588174299336183,
|
| 1709 |
+
"learning_rate": 1.5538678917388638e-06,
|
| 1710 |
+
"loss": 0.6638,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 3.873015873015873,
|
| 1715 |
+
"grad_norm": 0.48774660261391006,
|
| 1716 |
+
"learning_rate": 1.5138650034775004e-06,
|
| 1717 |
+
"loss": 0.5733,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 3.888888888888889,
|
| 1722 |
+
"grad_norm": 0.4185611368252772,
|
| 1723 |
+
"learning_rate": 1.4742917175331644e-06,
|
| 1724 |
+
"loss": 0.7174,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 3.9047619047619047,
|
| 1729 |
+
"grad_norm": 0.43603269341453055,
|
| 1730 |
+
"learning_rate": 1.4351529105888735e-06,
|
| 1731 |
+
"loss": 0.7672,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 3.9206349206349205,
|
| 1736 |
+
"grad_norm": 0.4318904871120016,
|
| 1737 |
+
"learning_rate": 1.3964534057860652e-06,
|
| 1738 |
+
"loss": 0.5978,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 3.9365079365079367,
|
| 1743 |
+
"grad_norm": 0.40904640871839104,
|
| 1744 |
+
"learning_rate": 1.3581979721302286e-06,
|
| 1745 |
+
"loss": 0.6579,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 3.9523809523809526,
|
| 1750 |
+
"grad_norm": 0.6005145592007414,
|
| 1751 |
+
"learning_rate": 1.3203913239032074e-06,
|
| 1752 |
+
"loss": 0.6694,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 3.9682539682539684,
|
| 1757 |
+
"grad_norm": 0.472367689533449,
|
| 1758 |
+
"learning_rate": 1.283038120082268e-06,
|
| 1759 |
+
"loss": 0.6197,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 3.984126984126984,
|
| 1764 |
+
"grad_norm": 0.4356830095251736,
|
| 1765 |
+
"learning_rate": 1.2461429637659466e-06,
|
| 1766 |
+
"loss": 0.6213,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 4.0,
|
| 1771 |
+
"grad_norm": 0.4857139342731584,
|
| 1772 |
+
"learning_rate": 1.2097104016068146e-06,
|
| 1773 |
+
"loss": 0.6352,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
}
|
| 1776 |
+
],
|
| 1777 |
+
"logging_steps": 1,
|
| 1778 |
+
"max_steps": 315,
|
| 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": 62903662804992.0,
|
| 1795 |
+
"train_batch_size": 2,
|
| 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 sha256:76762bc73f1e2fba3a83ca81b4ef3adb9e3eced24616582f4647171a7638edbf
|
| 3 |
+
size 8081
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|