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
- latest +1 -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
- rng_state_0.pth +3 -0
- rng_state_1.pth +3 -0
- rng_state_2.pth +3 -0
- rng_state_3.pth +3 -0
- rng_state_4.pth +3 -0
- rng_state_5.pth +3 -0
- rng_state_6.pth +3 -0
- rng_state_7.pth +3 -0
- scheduler.pt +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +240 -0
- trainer_state.json +2834 -0
- training_args.bin +3 -0
- vocab.json +0 -0
- zero_to_fp32.py +760 -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 |
+
}
|
latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
global_step400
|
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 sha256:6c4625969fc9cdf1b2318f7536a1a849dc5a279bd50165e78b0e5aea3075ab08
|
| 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:a83662a1735aedde9ec4e538c5532f53e40368cfb589ac949b21b631522779bc
|
| 3 |
+
size 4997741608
|
model-00003-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:865d4f14483ffbb271cd14031f6e2b23ca431b6ee11a2deb6f9b98415e73ab9c
|
| 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:cd9d2f10f6efc8e3039db6ebd1b0223ed76525592a72d03a364e1a8c57a84bec
|
| 3 |
+
size 4997743184
|
model-00005-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d4fefc1dd6925aa29bf28350a65cc42f78bcafc608dffd5288f9ef7ae9d62b8
|
| 3 |
+
size 4997743184
|
model-00006-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:35188442458e35561cafd9f55ced0d4e72cd510369c198ed185cc3227bdba775
|
| 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:cd0739c00f26f1e337615770281d21c82c8357deba2f19665c93b39e2ffb4c4d
|
| 3 |
+
size 4997743184
|
model-00008-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:075348f89243ae3505a67d67cfe63666e48a340baca3a29742fc796751e4f405
|
| 3 |
+
size 4997743184
|
model-00009-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:634cabdcc07b153c9437405e921c81ead6a3d948301055a8598e39d6de638388
|
| 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:ff94f49b07d92b66f7a1c123f7dfb7f6887de4ea7bc093f9edf736185696856c
|
| 3 |
+
size 4997743184
|
model-00011-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60f04cb70bfcfc68ed703f03a971f0b868158ea6a108f11bb56c65ea3ad81b36
|
| 3 |
+
size 4997743184
|
model-00012-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46166c57d4db8c4c3d98a98e767fe93119a01fa989b85c9fd2f1b900387650f8
|
| 3 |
+
size 4997743184
|
model-00013-of-00013.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e7e6429fb311a72b6a98fb747f48227d63ca7466e1082f4bfb1753db07e7d1a
|
| 3 |
+
size 1094220288
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
rng_state_0.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:478b41e9f26d338fd8f896e08cad1adab7c423b61f1b45754113bc78d256a3f9
|
| 3 |
+
size 16389
|
rng_state_1.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ce29a8767a7d907dd24987aa2c3e654d4317f3042fbc13b5b72cadb46d43311a
|
| 3 |
+
size 16389
|
rng_state_2.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61a48db011646b4e9a867bf12f4a233cad5dfbfe309686f8996c250196d3783a
|
| 3 |
+
size 16389
|
rng_state_3.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b9562ee822472a4f01dcd6349ab3d1ef42a48915fe3b92e843a0c37db53c8421
|
| 3 |
+
size 16389
|
rng_state_4.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7d2767d83c3bf27f12db022b0632e2c4f8c164274ba75e380cf18f9d5f21819
|
| 3 |
+
size 16389
|
rng_state_5.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:76816358d4e5db8149d60d55234db658d67a13c0c1ce05d7404cf7125a676a5c
|
| 3 |
+
size 16389
|
rng_state_6.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1562e7520c977d178183d641f70abcf3f57da2489938756cfbebf9b6e6c1a9fd
|
| 3 |
+
size 16389
|
rng_state_7.pth
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6b6cabaed045c5398cd1b732f7ec48bd363f3b43cd24e0e70e641a42bd00c28
|
| 3 |
+
size 16389
|
scheduler.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7851745f43dd82fa0b7ab243e9710355cb9506261da5c85b4eda174a36edd5d
|
| 3 |
+
size 1465
|
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 +1,2834 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.7226738934056007,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 400,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0018066847335140017,
|
| 14 |
+
"grad_norm": 2.8330893538644304,
|
| 15 |
+
"learning_rate": 0.0,
|
| 16 |
+
"loss": 0.8251,
|
| 17 |
+
"step": 1
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.0036133694670280035,
|
| 21 |
+
"grad_norm": 2.881435997205295,
|
| 22 |
+
"learning_rate": 3.5714285714285716e-07,
|
| 23 |
+
"loss": 0.8284,
|
| 24 |
+
"step": 2
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.005420054200542005,
|
| 28 |
+
"grad_norm": 2.913444175898846,
|
| 29 |
+
"learning_rate": 7.142857142857143e-07,
|
| 30 |
+
"loss": 0.843,
|
| 31 |
+
"step": 3
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.007226738934056007,
|
| 35 |
+
"grad_norm": 2.8476328344852626,
|
| 36 |
+
"learning_rate": 1.0714285714285714e-06,
|
| 37 |
+
"loss": 0.8396,
|
| 38 |
+
"step": 4
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.009033423667570008,
|
| 42 |
+
"grad_norm": 2.7681799600000607,
|
| 43 |
+
"learning_rate": 1.4285714285714286e-06,
|
| 44 |
+
"loss": 0.8292,
|
| 45 |
+
"step": 5
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.01084010840108401,
|
| 49 |
+
"grad_norm": 2.7322260951975927,
|
| 50 |
+
"learning_rate": 1.7857142857142859e-06,
|
| 51 |
+
"loss": 0.829,
|
| 52 |
+
"step": 6
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.012646793134598013,
|
| 56 |
+
"grad_norm": 2.597806254256109,
|
| 57 |
+
"learning_rate": 2.1428571428571427e-06,
|
| 58 |
+
"loss": 0.808,
|
| 59 |
+
"step": 7
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.014453477868112014,
|
| 63 |
+
"grad_norm": 2.594208882541123,
|
| 64 |
+
"learning_rate": 2.5e-06,
|
| 65 |
+
"loss": 0.8153,
|
| 66 |
+
"step": 8
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.016260162601626018,
|
| 70 |
+
"grad_norm": 2.1559466678394696,
|
| 71 |
+
"learning_rate": 2.8571428571428573e-06,
|
| 72 |
+
"loss": 0.8042,
|
| 73 |
+
"step": 9
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.018066847335140017,
|
| 77 |
+
"grad_norm": 2.046189870534073,
|
| 78 |
+
"learning_rate": 3.2142857142857147e-06,
|
| 79 |
+
"loss": 0.798,
|
| 80 |
+
"step": 10
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.01987353206865402,
|
| 84 |
+
"grad_norm": 1.489092346853261,
|
| 85 |
+
"learning_rate": 3.5714285714285718e-06,
|
| 86 |
+
"loss": 0.7766,
|
| 87 |
+
"step": 11
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.02168021680216802,
|
| 91 |
+
"grad_norm": 1.422343449560607,
|
| 92 |
+
"learning_rate": 3.928571428571429e-06,
|
| 93 |
+
"loss": 0.7866,
|
| 94 |
+
"step": 12
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.023486901535682024,
|
| 98 |
+
"grad_norm": 1.3533723550860928,
|
| 99 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 100 |
+
"loss": 0.7737,
|
| 101 |
+
"step": 13
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.025293586269196026,
|
| 105 |
+
"grad_norm": 1.2487216948113553,
|
| 106 |
+
"learning_rate": 4.642857142857144e-06,
|
| 107 |
+
"loss": 0.7669,
|
| 108 |
+
"step": 14
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.02710027100271003,
|
| 112 |
+
"grad_norm": 1.4826389765971164,
|
| 113 |
+
"learning_rate": 5e-06,
|
| 114 |
+
"loss": 0.7523,
|
| 115 |
+
"step": 15
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.028906955736224028,
|
| 119 |
+
"grad_norm": 1.6838425063979934,
|
| 120 |
+
"learning_rate": 5.357142857142857e-06,
|
| 121 |
+
"loss": 0.7431,
|
| 122 |
+
"step": 16
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.03071364046973803,
|
| 126 |
+
"grad_norm": 1.8944059999030647,
|
| 127 |
+
"learning_rate": 5.7142857142857145e-06,
|
| 128 |
+
"loss": 0.7505,
|
| 129 |
+
"step": 17
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.032520325203252036,
|
| 133 |
+
"grad_norm": 1.7093633044809413,
|
| 134 |
+
"learning_rate": 6.071428571428571e-06,
|
| 135 |
+
"loss": 0.7413,
|
| 136 |
+
"step": 18
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.03432700993676603,
|
| 140 |
+
"grad_norm": 1.4480856814923126,
|
| 141 |
+
"learning_rate": 6.4285714285714295e-06,
|
| 142 |
+
"loss": 0.7326,
|
| 143 |
+
"step": 19
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.036133694670280034,
|
| 147 |
+
"grad_norm": 0.8989567363750163,
|
| 148 |
+
"learning_rate": 6.785714285714287e-06,
|
| 149 |
+
"loss": 0.7034,
|
| 150 |
+
"step": 20
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.037940379403794036,
|
| 154 |
+
"grad_norm": 0.9336921226547814,
|
| 155 |
+
"learning_rate": 7.1428571428571436e-06,
|
| 156 |
+
"loss": 0.7054,
|
| 157 |
+
"step": 21
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.03974706413730804,
|
| 161 |
+
"grad_norm": 0.9964488635721185,
|
| 162 |
+
"learning_rate": 7.500000000000001e-06,
|
| 163 |
+
"loss": 0.6939,
|
| 164 |
+
"step": 22
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.04155374887082204,
|
| 168 |
+
"grad_norm": 0.8799604592025886,
|
| 169 |
+
"learning_rate": 7.857142857142858e-06,
|
| 170 |
+
"loss": 0.6911,
|
| 171 |
+
"step": 23
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.04336043360433604,
|
| 175 |
+
"grad_norm": 0.8240418742797938,
|
| 176 |
+
"learning_rate": 8.214285714285714e-06,
|
| 177 |
+
"loss": 0.6967,
|
| 178 |
+
"step": 24
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.045167118337850046,
|
| 182 |
+
"grad_norm": 0.6769494865754769,
|
| 183 |
+
"learning_rate": 8.571428571428571e-06,
|
| 184 |
+
"loss": 0.6755,
|
| 185 |
+
"step": 25
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.04697380307136405,
|
| 189 |
+
"grad_norm": 0.6032918245818127,
|
| 190 |
+
"learning_rate": 8.92857142857143e-06,
|
| 191 |
+
"loss": 0.6895,
|
| 192 |
+
"step": 26
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.04878048780487805,
|
| 196 |
+
"grad_norm": 0.6155544869504126,
|
| 197 |
+
"learning_rate": 9.285714285714288e-06,
|
| 198 |
+
"loss": 0.6658,
|
| 199 |
+
"step": 27
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.05058717253839205,
|
| 203 |
+
"grad_norm": 0.621356627949306,
|
| 204 |
+
"learning_rate": 9.642857142857144e-06,
|
| 205 |
+
"loss": 0.6675,
|
| 206 |
+
"step": 28
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.052393857271906055,
|
| 210 |
+
"grad_norm": 0.5810118247332029,
|
| 211 |
+
"learning_rate": 1e-05,
|
| 212 |
+
"loss": 0.6791,
|
| 213 |
+
"step": 29
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.05420054200542006,
|
| 217 |
+
"grad_norm": 0.5247538671601636,
|
| 218 |
+
"learning_rate": 9.999910480045805e-06,
|
| 219 |
+
"loss": 0.6778,
|
| 220 |
+
"step": 30
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.05600722673893405,
|
| 224 |
+
"grad_norm": 0.5714434850034724,
|
| 225 |
+
"learning_rate": 9.999641923388745e-06,
|
| 226 |
+
"loss": 0.6666,
|
| 227 |
+
"step": 31
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.057813911472448055,
|
| 231 |
+
"grad_norm": 0.4712383108751352,
|
| 232 |
+
"learning_rate": 9.999194339645292e-06,
|
| 233 |
+
"loss": 0.6538,
|
| 234 |
+
"step": 32
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.05962059620596206,
|
| 238 |
+
"grad_norm": 0.4617901106156676,
|
| 239 |
+
"learning_rate": 9.998567744842518e-06,
|
| 240 |
+
"loss": 0.6638,
|
| 241 |
+
"step": 33
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.06142728093947606,
|
| 245 |
+
"grad_norm": 0.4666096297215481,
|
| 246 |
+
"learning_rate": 9.997762161417517e-06,
|
| 247 |
+
"loss": 0.6507,
|
| 248 |
+
"step": 34
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.06323396567299007,
|
| 252 |
+
"grad_norm": 0.4177170379633248,
|
| 253 |
+
"learning_rate": 9.996777618216608e-06,
|
| 254 |
+
"loss": 0.6558,
|
| 255 |
+
"step": 35
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.06504065040650407,
|
| 259 |
+
"grad_norm": 0.3853857815173069,
|
| 260 |
+
"learning_rate": 9.995614150494293e-06,
|
| 261 |
+
"loss": 0.6501,
|
| 262 |
+
"step": 36
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.06684733514001806,
|
| 266 |
+
"grad_norm": 0.4750342442561457,
|
| 267 |
+
"learning_rate": 9.994271799912004e-06,
|
| 268 |
+
"loss": 0.654,
|
| 269 |
+
"step": 37
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.06865401987353206,
|
| 273 |
+
"grad_norm": 0.4687734149491767,
|
| 274 |
+
"learning_rate": 9.992750614536606e-06,
|
| 275 |
+
"loss": 0.6468,
|
| 276 |
+
"step": 38
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.07046070460704607,
|
| 280 |
+
"grad_norm": 0.48644381395947056,
|
| 281 |
+
"learning_rate": 9.991050648838676e-06,
|
| 282 |
+
"loss": 0.6473,
|
| 283 |
+
"step": 39
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.07226738934056007,
|
| 287 |
+
"grad_norm": 0.31783178912190924,
|
| 288 |
+
"learning_rate": 9.989171963690556e-06,
|
| 289 |
+
"loss": 0.6366,
|
| 290 |
+
"step": 40
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.07407407407407407,
|
| 294 |
+
"grad_norm": 0.33895045962254544,
|
| 295 |
+
"learning_rate": 9.987114626364172e-06,
|
| 296 |
+
"loss": 0.6427,
|
| 297 |
+
"step": 41
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.07588075880758807,
|
| 301 |
+
"grad_norm": 0.3719545945498325,
|
| 302 |
+
"learning_rate": 9.984878710528615e-06,
|
| 303 |
+
"loss": 0.634,
|
| 304 |
+
"step": 42
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.07768744354110207,
|
| 308 |
+
"grad_norm": 0.38317415749657263,
|
| 309 |
+
"learning_rate": 9.982464296247523e-06,
|
| 310 |
+
"loss": 0.6341,
|
| 311 |
+
"step": 43
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.07949412827461608,
|
| 315 |
+
"grad_norm": 0.31029398525665997,
|
| 316 |
+
"learning_rate": 9.979871469976197e-06,
|
| 317 |
+
"loss": 0.6272,
|
| 318 |
+
"step": 44
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.08130081300813008,
|
| 322 |
+
"grad_norm": 0.2908522040574856,
|
| 323 |
+
"learning_rate": 9.97710032455851e-06,
|
| 324 |
+
"loss": 0.6342,
|
| 325 |
+
"step": 45
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.08310749774164408,
|
| 329 |
+
"grad_norm": 0.2748406344962639,
|
| 330 |
+
"learning_rate": 9.974150959223591e-06,
|
| 331 |
+
"loss": 0.6358,
|
| 332 |
+
"step": 46
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.08491418247515808,
|
| 336 |
+
"grad_norm": 0.3149168698937494,
|
| 337 |
+
"learning_rate": 9.971023479582258e-06,
|
| 338 |
+
"loss": 0.6387,
|
| 339 |
+
"step": 47
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.08672086720867209,
|
| 343 |
+
"grad_norm": 0.2884824606148138,
|
| 344 |
+
"learning_rate": 9.967717997623245e-06,
|
| 345 |
+
"loss": 0.6257,
|
| 346 |
+
"step": 48
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.08852755194218609,
|
| 350 |
+
"grad_norm": 0.27614043410709116,
|
| 351 |
+
"learning_rate": 9.964234631709188e-06,
|
| 352 |
+
"loss": 0.6313,
|
| 353 |
+
"step": 49
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.09033423667570009,
|
| 357 |
+
"grad_norm": 0.2556625842505664,
|
| 358 |
+
"learning_rate": 9.960573506572391e-06,
|
| 359 |
+
"loss": 0.63,
|
| 360 |
+
"step": 50
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.0921409214092141,
|
| 364 |
+
"grad_norm": 0.26971687477967615,
|
| 365 |
+
"learning_rate": 9.956734753310355e-06,
|
| 366 |
+
"loss": 0.6193,
|
| 367 |
+
"step": 51
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.0939476061427281,
|
| 371 |
+
"grad_norm": 0.2549513910301006,
|
| 372 |
+
"learning_rate": 9.952718509381086e-06,
|
| 373 |
+
"loss": 0.6377,
|
| 374 |
+
"step": 52
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.0957542908762421,
|
| 378 |
+
"grad_norm": 0.2828412847060681,
|
| 379 |
+
"learning_rate": 9.948524918598175e-06,
|
| 380 |
+
"loss": 0.6219,
|
| 381 |
+
"step": 53
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.0975609756097561,
|
| 385 |
+
"grad_norm": 0.2622887143638149,
|
| 386 |
+
"learning_rate": 9.944154131125643e-06,
|
| 387 |
+
"loss": 0.6126,
|
| 388 |
+
"step": 54
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.0993676603432701,
|
| 392 |
+
"grad_norm": 0.25966122737232883,
|
| 393 |
+
"learning_rate": 9.93960630347257e-06,
|
| 394 |
+
"loss": 0.6265,
|
| 395 |
+
"step": 55
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.1011743450767841,
|
| 399 |
+
"grad_norm": 0.2433496106029979,
|
| 400 |
+
"learning_rate": 9.934881598487478e-06,
|
| 401 |
+
"loss": 0.6316,
|
| 402 |
+
"step": 56
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.10298102981029811,
|
| 406 |
+
"grad_norm": 0.24558757040432388,
|
| 407 |
+
"learning_rate": 9.929980185352525e-06,
|
| 408 |
+
"loss": 0.6173,
|
| 409 |
+
"step": 57
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.10478771454381211,
|
| 413 |
+
"grad_norm": 0.3572659265600395,
|
| 414 |
+
"learning_rate": 9.924902239577419e-06,
|
| 415 |
+
"loss": 0.6249,
|
| 416 |
+
"step": 58
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.10659439927732611,
|
| 420 |
+
"grad_norm": 0.24691672110135698,
|
| 421 |
+
"learning_rate": 9.91964794299315e-06,
|
| 422 |
+
"loss": 0.6106,
|
| 423 |
+
"step": 59
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.10840108401084012,
|
| 427 |
+
"grad_norm": 0.2628093882374342,
|
| 428 |
+
"learning_rate": 9.914217483745472e-06,
|
| 429 |
+
"loss": 0.6119,
|
| 430 |
+
"step": 60
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.1102077687443541,
|
| 434 |
+
"grad_norm": 0.2576012071557905,
|
| 435 |
+
"learning_rate": 9.90861105628817e-06,
|
| 436 |
+
"loss": 0.6158,
|
| 437 |
+
"step": 61
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.1120144534778681,
|
| 441 |
+
"grad_norm": 0.2520164585110792,
|
| 442 |
+
"learning_rate": 9.902828861376101e-06,
|
| 443 |
+
"loss": 0.6209,
|
| 444 |
+
"step": 62
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.11382113821138211,
|
| 448 |
+
"grad_norm": 0.24714468913812493,
|
| 449 |
+
"learning_rate": 9.896871106057989e-06,
|
| 450 |
+
"loss": 0.6203,
|
| 451 |
+
"step": 63
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.11562782294489611,
|
| 455 |
+
"grad_norm": 0.27939059621136214,
|
| 456 |
+
"learning_rate": 9.890738003669029e-06,
|
| 457 |
+
"loss": 0.6186,
|
| 458 |
+
"step": 64
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.11743450767841011,
|
| 462 |
+
"grad_norm": 0.30469002315407645,
|
| 463 |
+
"learning_rate": 9.884429773823238e-06,
|
| 464 |
+
"loss": 0.6132,
|
| 465 |
+
"step": 65
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.11924119241192412,
|
| 469 |
+
"grad_norm": 0.256255619416014,
|
| 470 |
+
"learning_rate": 9.877946642405598e-06,
|
| 471 |
+
"loss": 0.6151,
|
| 472 |
+
"step": 66
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.12104787714543812,
|
| 476 |
+
"grad_norm": 0.27333424534726836,
|
| 477 |
+
"learning_rate": 9.871288841563956e-06,
|
| 478 |
+
"loss": 0.6054,
|
| 479 |
+
"step": 67
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.12285456187895212,
|
| 483 |
+
"grad_norm": 0.2576979129157107,
|
| 484 |
+
"learning_rate": 9.864456609700726e-06,
|
| 485 |
+
"loss": 0.6212,
|
| 486 |
+
"step": 68
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.12466124661246612,
|
| 490 |
+
"grad_norm": 0.25853307753594634,
|
| 491 |
+
"learning_rate": 9.857450191464337e-06,
|
| 492 |
+
"loss": 0.6231,
|
| 493 |
+
"step": 69
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.12646793134598014,
|
| 497 |
+
"grad_norm": 0.2656560556389431,
|
| 498 |
+
"learning_rate": 9.85026983774049e-06,
|
| 499 |
+
"loss": 0.6284,
|
| 500 |
+
"step": 70
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.12827461607949414,
|
| 504 |
+
"grad_norm": 0.23027981167540387,
|
| 505 |
+
"learning_rate": 9.842915805643156e-06,
|
| 506 |
+
"loss": 0.5994,
|
| 507 |
+
"step": 71
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.13008130081300814,
|
| 511 |
+
"grad_norm": 0.22295142007678526,
|
| 512 |
+
"learning_rate": 9.835388358505383e-06,
|
| 513 |
+
"loss": 0.6168,
|
| 514 |
+
"step": 72
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.13188798554652212,
|
| 518 |
+
"grad_norm": 0.24893134247531343,
|
| 519 |
+
"learning_rate": 9.827687765869859e-06,
|
| 520 |
+
"loss": 0.6158,
|
| 521 |
+
"step": 73
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.13369467028003612,
|
| 525 |
+
"grad_norm": 0.24768240929937196,
|
| 526 |
+
"learning_rate": 9.819814303479268e-06,
|
| 527 |
+
"loss": 0.6079,
|
| 528 |
+
"step": 74
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.13550135501355012,
|
| 532 |
+
"grad_norm": 0.25510089913616635,
|
| 533 |
+
"learning_rate": 9.811768253266401e-06,
|
| 534 |
+
"loss": 0.6058,
|
| 535 |
+
"step": 75
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.13730803974706413,
|
| 539 |
+
"grad_norm": 0.2566035915807109,
|
| 540 |
+
"learning_rate": 9.803549903344081e-06,
|
| 541 |
+
"loss": 0.6015,
|
| 542 |
+
"step": 76
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.13911472448057813,
|
| 546 |
+
"grad_norm": 0.2498155436503847,
|
| 547 |
+
"learning_rate": 9.79515954799483e-06,
|
| 548 |
+
"loss": 0.5961,
|
| 549 |
+
"step": 77
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.14092140921409213,
|
| 553 |
+
"grad_norm": 0.25315720275933445,
|
| 554 |
+
"learning_rate": 9.786597487660336e-06,
|
| 555 |
+
"loss": 0.6077,
|
| 556 |
+
"step": 78
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.14272809394760613,
|
| 560 |
+
"grad_norm": 0.2506783920655026,
|
| 561 |
+
"learning_rate": 9.777864028930705e-06,
|
| 562 |
+
"loss": 0.6169,
|
| 563 |
+
"step": 79
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.14453477868112014,
|
| 567 |
+
"grad_norm": 0.24357522442887738,
|
| 568 |
+
"learning_rate": 9.768959484533461e-06,
|
| 569 |
+
"loss": 0.6258,
|
| 570 |
+
"step": 80
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.14634146341463414,
|
| 574 |
+
"grad_norm": 0.2368292397855168,
|
| 575 |
+
"learning_rate": 9.75988417332237e-06,
|
| 576 |
+
"loss": 0.6084,
|
| 577 |
+
"step": 81
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.14814814814814814,
|
| 581 |
+
"grad_norm": 0.24319176665961809,
|
| 582 |
+
"learning_rate": 9.750638420266008e-06,
|
| 583 |
+
"loss": 0.602,
|
| 584 |
+
"step": 82
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.14995483288166214,
|
| 588 |
+
"grad_norm": 0.26083997132385134,
|
| 589 |
+
"learning_rate": 9.741222556436132e-06,
|
| 590 |
+
"loss": 0.6131,
|
| 591 |
+
"step": 83
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.15176151761517614,
|
| 595 |
+
"grad_norm": 0.23313509037048255,
|
| 596 |
+
"learning_rate": 9.731636918995821e-06,
|
| 597 |
+
"loss": 0.6059,
|
| 598 |
+
"step": 84
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.15356820234869015,
|
| 602 |
+
"grad_norm": 0.2561353779177137,
|
| 603 |
+
"learning_rate": 9.721881851187406e-06,
|
| 604 |
+
"loss": 0.608,
|
| 605 |
+
"step": 85
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.15537488708220415,
|
| 609 |
+
"grad_norm": 0.24665820987089132,
|
| 610 |
+
"learning_rate": 9.711957702320176e-06,
|
| 611 |
+
"loss": 0.6079,
|
| 612 |
+
"step": 86
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.15718157181571815,
|
| 616 |
+
"grad_norm": 0.24260951004614914,
|
| 617 |
+
"learning_rate": 9.701864827757868e-06,
|
| 618 |
+
"loss": 0.6101,
|
| 619 |
+
"step": 87
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.15898825654923215,
|
| 623 |
+
"grad_norm": 0.23580290946970783,
|
| 624 |
+
"learning_rate": 9.691603588905956e-06,
|
| 625 |
+
"loss": 0.6145,
|
| 626 |
+
"step": 88
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.16079494128274616,
|
| 630 |
+
"grad_norm": 0.23843217719986562,
|
| 631 |
+
"learning_rate": 9.681174353198687e-06,
|
| 632 |
+
"loss": 0.6101,
|
| 633 |
+
"step": 89
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.16260162601626016,
|
| 637 |
+
"grad_norm": 0.23674563433604787,
|
| 638 |
+
"learning_rate": 9.670577494085945e-06,
|
| 639 |
+
"loss": 0.6032,
|
| 640 |
+
"step": 90
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.16440831074977416,
|
| 644 |
+
"grad_norm": 0.22347295635871733,
|
| 645 |
+
"learning_rate": 9.659813391019867e-06,
|
| 646 |
+
"loss": 0.6012,
|
| 647 |
+
"step": 91
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.16621499548328816,
|
| 651 |
+
"grad_norm": 0.22774371040996969,
|
| 652 |
+
"learning_rate": 9.648882429441258e-06,
|
| 653 |
+
"loss": 0.6049,
|
| 654 |
+
"step": 92
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.16802168021680217,
|
| 658 |
+
"grad_norm": 0.24860302708545573,
|
| 659 |
+
"learning_rate": 9.637785000765789e-06,
|
| 660 |
+
"loss": 0.6113,
|
| 661 |
+
"step": 93
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.16982836495031617,
|
| 665 |
+
"grad_norm": 0.2514244920841384,
|
| 666 |
+
"learning_rate": 9.626521502369984e-06,
|
| 667 |
+
"loss": 0.6101,
|
| 668 |
+
"step": 94
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.17163504968383017,
|
| 672 |
+
"grad_norm": 0.2615146913938569,
|
| 673 |
+
"learning_rate": 9.615092337576987e-06,
|
| 674 |
+
"loss": 0.6024,
|
| 675 |
+
"step": 95
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.17344173441734417,
|
| 679 |
+
"grad_norm": 0.24221345499794553,
|
| 680 |
+
"learning_rate": 9.603497915642122e-06,
|
| 681 |
+
"loss": 0.6012,
|
| 682 |
+
"step": 96
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.17524841915085818,
|
| 686 |
+
"grad_norm": 0.3115318810789579,
|
| 687 |
+
"learning_rate": 9.591738651738235e-06,
|
| 688 |
+
"loss": 0.6073,
|
| 689 |
+
"step": 97
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.17705510388437218,
|
| 693 |
+
"grad_norm": 0.244045694442119,
|
| 694 |
+
"learning_rate": 9.579814966940833e-06,
|
| 695 |
+
"loss": 0.6011,
|
| 696 |
+
"step": 98
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.17886178861788618,
|
| 700 |
+
"grad_norm": 0.2376023672791741,
|
| 701 |
+
"learning_rate": 9.567727288213005e-06,
|
| 702 |
+
"loss": 0.6136,
|
| 703 |
+
"step": 99
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.18066847335140018,
|
| 707 |
+
"grad_norm": 0.21793476185622473,
|
| 708 |
+
"learning_rate": 9.55547604839013e-06,
|
| 709 |
+
"loss": 0.587,
|
| 710 |
+
"step": 100
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.18247515808491419,
|
| 714 |
+
"grad_norm": 0.2337281277152664,
|
| 715 |
+
"learning_rate": 9.543061686164374e-06,
|
| 716 |
+
"loss": 0.6032,
|
| 717 |
+
"step": 101
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.1842818428184282,
|
| 721 |
+
"grad_norm": 0.23686576311395632,
|
| 722 |
+
"learning_rate": 9.530484646068996e-06,
|
| 723 |
+
"loss": 0.6213,
|
| 724 |
+
"step": 102
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.1860885275519422,
|
| 728 |
+
"grad_norm": 0.24261565879784514,
|
| 729 |
+
"learning_rate": 9.517745378462417e-06,
|
| 730 |
+
"loss": 0.6003,
|
| 731 |
+
"step": 103
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.1878952122854562,
|
| 735 |
+
"grad_norm": 0.2524487307231951,
|
| 736 |
+
"learning_rate": 9.504844339512096e-06,
|
| 737 |
+
"loss": 0.5985,
|
| 738 |
+
"step": 104
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.1897018970189702,
|
| 742 |
+
"grad_norm": 0.22875411685789507,
|
| 743 |
+
"learning_rate": 9.491781991178203e-06,
|
| 744 |
+
"loss": 0.5907,
|
| 745 |
+
"step": 105
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.1915085817524842,
|
| 749 |
+
"grad_norm": 0.23168788790974576,
|
| 750 |
+
"learning_rate": 9.478558801197065e-06,
|
| 751 |
+
"loss": 0.5927,
|
| 752 |
+
"step": 106
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.1933152664859982,
|
| 756 |
+
"grad_norm": 0.24440785625645858,
|
| 757 |
+
"learning_rate": 9.465175243064428e-06,
|
| 758 |
+
"loss": 0.5985,
|
| 759 |
+
"step": 107
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.1951219512195122,
|
| 763 |
+
"grad_norm": 0.2358000622956773,
|
| 764 |
+
"learning_rate": 9.451631796018495e-06,
|
| 765 |
+
"loss": 0.597,
|
| 766 |
+
"step": 108
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.1969286359530262,
|
| 770 |
+
"grad_norm": 0.2476890175323139,
|
| 771 |
+
"learning_rate": 9.437928945022772e-06,
|
| 772 |
+
"loss": 0.6066,
|
| 773 |
+
"step": 109
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.1987353206865402,
|
| 777 |
+
"grad_norm": 0.24611295267738714,
|
| 778 |
+
"learning_rate": 9.424067180748692e-06,
|
| 779 |
+
"loss": 0.5878,
|
| 780 |
+
"step": 110
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.2005420054200542,
|
| 784 |
+
"grad_norm": 0.2881495774555611,
|
| 785 |
+
"learning_rate": 9.410046999558062e-06,
|
| 786 |
+
"loss": 0.6072,
|
| 787 |
+
"step": 111
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.2023486901535682,
|
| 791 |
+
"grad_norm": 0.24596539710053744,
|
| 792 |
+
"learning_rate": 9.395868903485269e-06,
|
| 793 |
+
"loss": 0.6005,
|
| 794 |
+
"step": 112
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.2041553748870822,
|
| 798 |
+
"grad_norm": 0.2386416433130278,
|
| 799 |
+
"learning_rate": 9.381533400219319e-06,
|
| 800 |
+
"loss": 0.6041,
|
| 801 |
+
"step": 113
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.20596205962059622,
|
| 805 |
+
"grad_norm": 0.3575913544704138,
|
| 806 |
+
"learning_rate": 9.36704100308565e-06,
|
| 807 |
+
"loss": 0.5872,
|
| 808 |
+
"step": 114
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.20776874435411022,
|
| 812 |
+
"grad_norm": 0.23192198774830253,
|
| 813 |
+
"learning_rate": 9.352392231027752e-06,
|
| 814 |
+
"loss": 0.6032,
|
| 815 |
+
"step": 115
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.20957542908762422,
|
| 819 |
+
"grad_norm": 0.23101719819824798,
|
| 820 |
+
"learning_rate": 9.337587608588588e-06,
|
| 821 |
+
"loss": 0.5974,
|
| 822 |
+
"step": 116
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.21138211382113822,
|
| 826 |
+
"grad_norm": 0.25528392059554045,
|
| 827 |
+
"learning_rate": 9.322627665891807e-06,
|
| 828 |
+
"loss": 0.6076,
|
| 829 |
+
"step": 117
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.21318879855465223,
|
| 833 |
+
"grad_norm": 0.24287946493861107,
|
| 834 |
+
"learning_rate": 9.307512938622762e-06,
|
| 835 |
+
"loss": 0.5952,
|
| 836 |
+
"step": 118
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.21499548328816623,
|
| 840 |
+
"grad_norm": 0.22892112715952465,
|
| 841 |
+
"learning_rate": 9.292243968009332e-06,
|
| 842 |
+
"loss": 0.5864,
|
| 843 |
+
"step": 119
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.21680216802168023,
|
| 847 |
+
"grad_norm": 0.23875546778816065,
|
| 848 |
+
"learning_rate": 9.276821300802535e-06,
|
| 849 |
+
"loss": 0.6042,
|
| 850 |
+
"step": 120
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.2186088527551942,
|
| 854 |
+
"grad_norm": 0.23651334894824905,
|
| 855 |
+
"learning_rate": 9.261245489256956e-06,
|
| 856 |
+
"loss": 0.6,
|
| 857 |
+
"step": 121
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.2204155374887082,
|
| 861 |
+
"grad_norm": 0.2526347555924926,
|
| 862 |
+
"learning_rate": 9.24551709111097e-06,
|
| 863 |
+
"loss": 0.6049,
|
| 864 |
+
"step": 122
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.2222222222222222,
|
| 868 |
+
"grad_norm": 0.26377863716117955,
|
| 869 |
+
"learning_rate": 9.229636669566769e-06,
|
| 870 |
+
"loss": 0.5961,
|
| 871 |
+
"step": 123
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.2240289069557362,
|
| 875 |
+
"grad_norm": 0.2632856019025536,
|
| 876 |
+
"learning_rate": 9.213604793270196e-06,
|
| 877 |
+
"loss": 0.5818,
|
| 878 |
+
"step": 124
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.22583559168925021,
|
| 882 |
+
"grad_norm": 0.26119773624805764,
|
| 883 |
+
"learning_rate": 9.197422036290386e-06,
|
| 884 |
+
"loss": 0.5887,
|
| 885 |
+
"step": 125
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.22764227642276422,
|
| 889 |
+
"grad_norm": 0.22525425992658815,
|
| 890 |
+
"learning_rate": 9.181088978099203e-06,
|
| 891 |
+
"loss": 0.601,
|
| 892 |
+
"step": 126
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.22944896115627822,
|
| 896 |
+
"grad_norm": 0.25288660956040915,
|
| 897 |
+
"learning_rate": 9.164606203550498e-06,
|
| 898 |
+
"loss": 0.5933,
|
| 899 |
+
"step": 127
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.23125564588979222,
|
| 903 |
+
"grad_norm": 0.23943780402862191,
|
| 904 |
+
"learning_rate": 9.147974302859158e-06,
|
| 905 |
+
"loss": 0.5925,
|
| 906 |
+
"step": 128
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.23306233062330622,
|
| 910 |
+
"grad_norm": 0.25270951927417573,
|
| 911 |
+
"learning_rate": 9.131193871579975e-06,
|
| 912 |
+
"loss": 0.588,
|
| 913 |
+
"step": 129
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.23486901535682023,
|
| 917 |
+
"grad_norm": 0.23629117048544068,
|
| 918 |
+
"learning_rate": 9.114265510586329e-06,
|
| 919 |
+
"loss": 0.6066,
|
| 920 |
+
"step": 130
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.23667570009033423,
|
| 924 |
+
"grad_norm": 0.25827287096558593,
|
| 925 |
+
"learning_rate": 9.09718982604866e-06,
|
| 926 |
+
"loss": 0.6005,
|
| 927 |
+
"step": 131
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.23848238482384823,
|
| 931 |
+
"grad_norm": 0.2267410893620417,
|
| 932 |
+
"learning_rate": 9.079967429412766e-06,
|
| 933 |
+
"loss": 0.5795,
|
| 934 |
+
"step": 132
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.24028906955736223,
|
| 938 |
+
"grad_norm": 0.2550015941357386,
|
| 939 |
+
"learning_rate": 9.062598937377911e-06,
|
| 940 |
+
"loss": 0.5951,
|
| 941 |
+
"step": 133
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.24209575429087624,
|
| 945 |
+
"grad_norm": 0.24549928967178372,
|
| 946 |
+
"learning_rate": 9.045084971874738e-06,
|
| 947 |
+
"loss": 0.5958,
|
| 948 |
+
"step": 134
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.24390243902439024,
|
| 952 |
+
"grad_norm": 0.23869896137391008,
|
| 953 |
+
"learning_rate": 9.027426160043005e-06,
|
| 954 |
+
"loss": 0.5925,
|
| 955 |
+
"step": 135
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.24570912375790424,
|
| 959 |
+
"grad_norm": 0.23603926331716685,
|
| 960 |
+
"learning_rate": 9.00962313420912e-06,
|
| 961 |
+
"loss": 0.5967,
|
| 962 |
+
"step": 136
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.24751580849141824,
|
| 966 |
+
"grad_norm": 0.21954443180366723,
|
| 967 |
+
"learning_rate": 8.991676531863507e-06,
|
| 968 |
+
"loss": 0.5799,
|
| 969 |
+
"step": 137
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.24932249322493225,
|
| 973 |
+
"grad_norm": 0.24573994311601394,
|
| 974 |
+
"learning_rate": 8.973586995637778e-06,
|
| 975 |
+
"loss": 0.5974,
|
| 976 |
+
"step": 138
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.25112917795844625,
|
| 980 |
+
"grad_norm": 0.23867846548393645,
|
| 981 |
+
"learning_rate": 8.955355173281709e-06,
|
| 982 |
+
"loss": 0.6006,
|
| 983 |
+
"step": 139
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.2529358626919603,
|
| 987 |
+
"grad_norm": 0.2581948484162573,
|
| 988 |
+
"learning_rate": 8.936981717640061e-06,
|
| 989 |
+
"loss": 0.5999,
|
| 990 |
+
"step": 140
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.25474254742547425,
|
| 994 |
+
"grad_norm": 0.267121573221628,
|
| 995 |
+
"learning_rate": 8.9184672866292e-06,
|
| 996 |
+
"loss": 0.5805,
|
| 997 |
+
"step": 141
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.2565492321589883,
|
| 1001 |
+
"grad_norm": 0.2470490796537526,
|
| 1002 |
+
"learning_rate": 8.899812543213532e-06,
|
| 1003 |
+
"loss": 0.6006,
|
| 1004 |
+
"step": 142
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.25835591689250226,
|
| 1008 |
+
"grad_norm": 0.3179114771380903,
|
| 1009 |
+
"learning_rate": 8.881018155381766e-06,
|
| 1010 |
+
"loss": 0.592,
|
| 1011 |
+
"step": 143
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.2601626016260163,
|
| 1015 |
+
"grad_norm": 0.23894724426899414,
|
| 1016 |
+
"learning_rate": 8.862084796122998e-06,
|
| 1017 |
+
"loss": 0.5813,
|
| 1018 |
+
"step": 144
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.26196928635953026,
|
| 1022 |
+
"grad_norm": 0.2550194178662108,
|
| 1023 |
+
"learning_rate": 8.84301314340261e-06,
|
| 1024 |
+
"loss": 0.5938,
|
| 1025 |
+
"step": 145
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.26377597109304424,
|
| 1029 |
+
"grad_norm": 0.23756009297770989,
|
| 1030 |
+
"learning_rate": 8.823803880137993e-06,
|
| 1031 |
+
"loss": 0.5967,
|
| 1032 |
+
"step": 146
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.26558265582655827,
|
| 1036 |
+
"grad_norm": 0.23830080522997849,
|
| 1037 |
+
"learning_rate": 8.804457694174093e-06,
|
| 1038 |
+
"loss": 0.5884,
|
| 1039 |
+
"step": 147
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.26738934056007224,
|
| 1043 |
+
"grad_norm": 0.2541492506135848,
|
| 1044 |
+
"learning_rate": 8.784975278258783e-06,
|
| 1045 |
+
"loss": 0.5895,
|
| 1046 |
+
"step": 148
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.26919602529358627,
|
| 1050 |
+
"grad_norm": 0.2248990020625438,
|
| 1051 |
+
"learning_rate": 8.765357330018056e-06,
|
| 1052 |
+
"loss": 0.5867,
|
| 1053 |
+
"step": 149
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.27100271002710025,
|
| 1057 |
+
"grad_norm": 0.23467307143176355,
|
| 1058 |
+
"learning_rate": 8.745604551931042e-06,
|
| 1059 |
+
"loss": 0.5955,
|
| 1060 |
+
"step": 150
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.2728093947606143,
|
| 1064 |
+
"grad_norm": 0.25171242957304724,
|
| 1065 |
+
"learning_rate": 8.725717651304856e-06,
|
| 1066 |
+
"loss": 0.5794,
|
| 1067 |
+
"step": 151
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.27461607949412825,
|
| 1071 |
+
"grad_norm": 0.23300717704512258,
|
| 1072 |
+
"learning_rate": 8.705697340249275e-06,
|
| 1073 |
+
"loss": 0.5852,
|
| 1074 |
+
"step": 152
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.2764227642276423,
|
| 1078 |
+
"grad_norm": 0.2477278416478864,
|
| 1079 |
+
"learning_rate": 8.685544335651226e-06,
|
| 1080 |
+
"loss": 0.586,
|
| 1081 |
+
"step": 153
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.27822944896115626,
|
| 1085 |
+
"grad_norm": 0.23445523989787243,
|
| 1086 |
+
"learning_rate": 8.665259359149132e-06,
|
| 1087 |
+
"loss": 0.591,
|
| 1088 |
+
"step": 154
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.2800361336946703,
|
| 1092 |
+
"grad_norm": 0.22970328615556354,
|
| 1093 |
+
"learning_rate": 8.644843137107058e-06,
|
| 1094 |
+
"loss": 0.5819,
|
| 1095 |
+
"step": 155
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.28184281842818426,
|
| 1099 |
+
"grad_norm": 0.23879183212303057,
|
| 1100 |
+
"learning_rate": 8.62429640058871e-06,
|
| 1101 |
+
"loss": 0.5829,
|
| 1102 |
+
"step": 156
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.2836495031616983,
|
| 1106 |
+
"grad_norm": 0.25663229334164944,
|
| 1107 |
+
"learning_rate": 8.603619885331251e-06,
|
| 1108 |
+
"loss": 0.5955,
|
| 1109 |
+
"step": 157
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.28545618789521227,
|
| 1113 |
+
"grad_norm": 0.24837164619570978,
|
| 1114 |
+
"learning_rate": 8.582814331718961e-06,
|
| 1115 |
+
"loss": 0.5928,
|
| 1116 |
+
"step": 158
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.2872628726287263,
|
| 1120 |
+
"grad_norm": 0.23588125642758875,
|
| 1121 |
+
"learning_rate": 8.561880484756726e-06,
|
| 1122 |
+
"loss": 0.5741,
|
| 1123 |
+
"step": 159
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.28906955736224027,
|
| 1127 |
+
"grad_norm": 0.24350097611405788,
|
| 1128 |
+
"learning_rate": 8.540819094043349e-06,
|
| 1129 |
+
"loss": 0.5829,
|
| 1130 |
+
"step": 160
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.2908762420957543,
|
| 1134 |
+
"grad_norm": 0.2553683709091329,
|
| 1135 |
+
"learning_rate": 8.519630913744726e-06,
|
| 1136 |
+
"loss": 0.5899,
|
| 1137 |
+
"step": 161
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.2926829268292683,
|
| 1141 |
+
"grad_norm": 0.22785571039238608,
|
| 1142 |
+
"learning_rate": 8.498316702566828e-06,
|
| 1143 |
+
"loss": 0.5761,
|
| 1144 |
+
"step": 162
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.2944896115627823,
|
| 1148 |
+
"grad_norm": 0.25965181875075294,
|
| 1149 |
+
"learning_rate": 8.476877223728539e-06,
|
| 1150 |
+
"loss": 0.5856,
|
| 1151 |
+
"step": 163
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 0.2962962962962963,
|
| 1155 |
+
"grad_norm": 0.24290266021805976,
|
| 1156 |
+
"learning_rate": 8.455313244934324e-06,
|
| 1157 |
+
"loss": 0.5944,
|
| 1158 |
+
"step": 164
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 0.2981029810298103,
|
| 1162 |
+
"grad_norm": 0.22927751586664705,
|
| 1163 |
+
"learning_rate": 8.433625538346742e-06,
|
| 1164 |
+
"loss": 0.5859,
|
| 1165 |
+
"step": 165
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 0.2999096657633243,
|
| 1169 |
+
"grad_norm": 0.24535687152116695,
|
| 1170 |
+
"learning_rate": 8.41181488055879e-06,
|
| 1171 |
+
"loss": 0.5921,
|
| 1172 |
+
"step": 166
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 0.3017163504968383,
|
| 1176 |
+
"grad_norm": 0.23751101243273856,
|
| 1177 |
+
"learning_rate": 8.389882052566106e-06,
|
| 1178 |
+
"loss": 0.591,
|
| 1179 |
+
"step": 167
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 0.3035230352303523,
|
| 1183 |
+
"grad_norm": 0.23630246240385233,
|
| 1184 |
+
"learning_rate": 8.36782783973899e-06,
|
| 1185 |
+
"loss": 0.5894,
|
| 1186 |
+
"step": 168
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 0.3053297199638663,
|
| 1190 |
+
"grad_norm": 0.22799677339250804,
|
| 1191 |
+
"learning_rate": 8.345653031794292e-06,
|
| 1192 |
+
"loss": 0.5818,
|
| 1193 |
+
"step": 169
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 0.3071364046973803,
|
| 1197 |
+
"grad_norm": 0.22405689087807926,
|
| 1198 |
+
"learning_rate": 8.32335842276713e-06,
|
| 1199 |
+
"loss": 0.5959,
|
| 1200 |
+
"step": 170
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 0.3089430894308943,
|
| 1204 |
+
"grad_norm": 0.22813844475300996,
|
| 1205 |
+
"learning_rate": 8.300944810982452e-06,
|
| 1206 |
+
"loss": 0.5786,
|
| 1207 |
+
"step": 171
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 0.3107497741644083,
|
| 1211 |
+
"grad_norm": 0.2640722980858363,
|
| 1212 |
+
"learning_rate": 8.278412999026462e-06,
|
| 1213 |
+
"loss": 0.5853,
|
| 1214 |
+
"step": 172
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 0.31255645889792233,
|
| 1218 |
+
"grad_norm": 0.2233536921872013,
|
| 1219 |
+
"learning_rate": 8.255763793717868e-06,
|
| 1220 |
+
"loss": 0.5887,
|
| 1221 |
+
"step": 173
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 0.3143631436314363,
|
| 1225 |
+
"grad_norm": 0.23154045983028293,
|
| 1226 |
+
"learning_rate": 8.232998006078998e-06,
|
| 1227 |
+
"loss": 0.5799,
|
| 1228 |
+
"step": 174
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 0.31616982836495033,
|
| 1232 |
+
"grad_norm": 0.23034930998436073,
|
| 1233 |
+
"learning_rate": 8.210116451306762e-06,
|
| 1234 |
+
"loss": 0.5842,
|
| 1235 |
+
"step": 175
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 0.3179765130984643,
|
| 1239 |
+
"grad_norm": 0.23658108883929088,
|
| 1240 |
+
"learning_rate": 8.18711994874345e-06,
|
| 1241 |
+
"loss": 0.5985,
|
| 1242 |
+
"step": 176
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 0.31978319783197834,
|
| 1246 |
+
"grad_norm": 0.21745109308108737,
|
| 1247 |
+
"learning_rate": 8.164009321847405e-06,
|
| 1248 |
+
"loss": 0.5734,
|
| 1249 |
+
"step": 177
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 0.3215898825654923,
|
| 1253 |
+
"grad_norm": 0.2293512030663522,
|
| 1254 |
+
"learning_rate": 8.140785398163535e-06,
|
| 1255 |
+
"loss": 0.58,
|
| 1256 |
+
"step": 178
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 0.32339656729900634,
|
| 1260 |
+
"grad_norm": 0.24597935781904853,
|
| 1261 |
+
"learning_rate": 8.117449009293668e-06,
|
| 1262 |
+
"loss": 0.5901,
|
| 1263 |
+
"step": 179
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 0.3252032520325203,
|
| 1267 |
+
"grad_norm": 0.21247364482115172,
|
| 1268 |
+
"learning_rate": 8.094000990866795e-06,
|
| 1269 |
+
"loss": 0.5981,
|
| 1270 |
+
"step": 180
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 0.32700993676603435,
|
| 1274 |
+
"grad_norm": 0.2372685877924778,
|
| 1275 |
+
"learning_rate": 8.070442182509127e-06,
|
| 1276 |
+
"loss": 0.576,
|
| 1277 |
+
"step": 181
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 0.3288166214995483,
|
| 1281 |
+
"grad_norm": 0.3447763183753473,
|
| 1282 |
+
"learning_rate": 8.046773427814043e-06,
|
| 1283 |
+
"loss": 0.586,
|
| 1284 |
+
"step": 182
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 0.33062330623306235,
|
| 1288 |
+
"grad_norm": 0.23582522162922892,
|
| 1289 |
+
"learning_rate": 8.022995574311876e-06,
|
| 1290 |
+
"loss": 0.5973,
|
| 1291 |
+
"step": 183
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 0.3324299909665763,
|
| 1295 |
+
"grad_norm": 0.23703989170533815,
|
| 1296 |
+
"learning_rate": 7.99910947343957e-06,
|
| 1297 |
+
"loss": 0.5939,
|
| 1298 |
+
"step": 184
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 0.33423667570009036,
|
| 1302 |
+
"grad_norm": 0.23664320383509757,
|
| 1303 |
+
"learning_rate": 7.975115980510187e-06,
|
| 1304 |
+
"loss": 0.5902,
|
| 1305 |
+
"step": 185
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 0.33604336043360433,
|
| 1309 |
+
"grad_norm": 0.23010205857606106,
|
| 1310 |
+
"learning_rate": 7.951015954682281e-06,
|
| 1311 |
+
"loss": 0.5857,
|
| 1312 |
+
"step": 186
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 0.33785004516711836,
|
| 1316 |
+
"grad_norm": 0.2663491724216408,
|
| 1317 |
+
"learning_rate": 7.926810258929138e-06,
|
| 1318 |
+
"loss": 0.5831,
|
| 1319 |
+
"step": 187
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 0.33965672990063234,
|
| 1323 |
+
"grad_norm": 0.23096764617799878,
|
| 1324 |
+
"learning_rate": 7.902499760007867e-06,
|
| 1325 |
+
"loss": 0.5828,
|
| 1326 |
+
"step": 188
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 0.34146341463414637,
|
| 1330 |
+
"grad_norm": 0.23869913090614076,
|
| 1331 |
+
"learning_rate": 7.87808532842837e-06,
|
| 1332 |
+
"loss": 0.5901,
|
| 1333 |
+
"step": 189
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 0.34327009936766034,
|
| 1337 |
+
"grad_norm": 0.22415991273320168,
|
| 1338 |
+
"learning_rate": 7.85356783842216e-06,
|
| 1339 |
+
"loss": 0.5787,
|
| 1340 |
+
"step": 190
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 0.34507678410117437,
|
| 1344 |
+
"grad_norm": 0.24057830595652646,
|
| 1345 |
+
"learning_rate": 7.828948167911073e-06,
|
| 1346 |
+
"loss": 0.577,
|
| 1347 |
+
"step": 191
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 0.34688346883468835,
|
| 1351 |
+
"grad_norm": 0.8377691682291619,
|
| 1352 |
+
"learning_rate": 7.804227198475823e-06,
|
| 1353 |
+
"loss": 0.5838,
|
| 1354 |
+
"step": 192
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 0.3486901535682023,
|
| 1358 |
+
"grad_norm": 0.22688859107583473,
|
| 1359 |
+
"learning_rate": 7.779405815324424e-06,
|
| 1360 |
+
"loss": 0.5857,
|
| 1361 |
+
"step": 193
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 0.35049683830171635,
|
| 1365 |
+
"grad_norm": 0.22785735734765863,
|
| 1366 |
+
"learning_rate": 7.754484907260513e-06,
|
| 1367 |
+
"loss": 0.5874,
|
| 1368 |
+
"step": 194
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 0.3523035230352303,
|
| 1372 |
+
"grad_norm": 0.2177502560490473,
|
| 1373 |
+
"learning_rate": 7.72946536665151e-06,
|
| 1374 |
+
"loss": 0.5707,
|
| 1375 |
+
"step": 195
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 0.35411020776874436,
|
| 1379 |
+
"grad_norm": 0.24597755253541856,
|
| 1380 |
+
"learning_rate": 7.704348089396667e-06,
|
| 1381 |
+
"loss": 0.5838,
|
| 1382 |
+
"step": 196
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 0.35591689250225833,
|
| 1386 |
+
"grad_norm": 0.2292296000848298,
|
| 1387 |
+
"learning_rate": 7.679133974894984e-06,
|
| 1388 |
+
"loss": 0.5833,
|
| 1389 |
+
"step": 197
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 0.35772357723577236,
|
| 1393 |
+
"grad_norm": 0.23517427703242888,
|
| 1394 |
+
"learning_rate": 7.653823926013016e-06,
|
| 1395 |
+
"loss": 0.5604,
|
| 1396 |
+
"step": 198
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 0.35953026196928634,
|
| 1400 |
+
"grad_norm": 0.23076838848026066,
|
| 1401 |
+
"learning_rate": 7.628418849052523e-06,
|
| 1402 |
+
"loss": 0.5831,
|
| 1403 |
+
"step": 199
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 0.36133694670280037,
|
| 1407 |
+
"grad_norm": 0.23076094009385115,
|
| 1408 |
+
"learning_rate": 7.602919653718044e-06,
|
| 1409 |
+
"loss": 0.573,
|
| 1410 |
+
"step": 200
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 0.36314363143631434,
|
| 1414 |
+
"grad_norm": 0.22528349334552952,
|
| 1415 |
+
"learning_rate": 7.577327253084292e-06,
|
| 1416 |
+
"loss": 0.5675,
|
| 1417 |
+
"step": 201
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 0.36495031616982837,
|
| 1421 |
+
"grad_norm": 0.25919326541454196,
|
| 1422 |
+
"learning_rate": 7.551642563563481e-06,
|
| 1423 |
+
"loss": 0.5944,
|
| 1424 |
+
"step": 202
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 0.36675700090334235,
|
| 1428 |
+
"grad_norm": 0.2475750487466084,
|
| 1429 |
+
"learning_rate": 7.5258665048725065e-06,
|
| 1430 |
+
"loss": 0.5816,
|
| 1431 |
+
"step": 203
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 0.3685636856368564,
|
| 1435 |
+
"grad_norm": 0.23639856935126805,
|
| 1436 |
+
"learning_rate": 7.500000000000001e-06,
|
| 1437 |
+
"loss": 0.5941,
|
| 1438 |
+
"step": 204
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 0.37037037037037035,
|
| 1442 |
+
"grad_norm": 0.2312059720413921,
|
| 1443 |
+
"learning_rate": 7.4740439751732994e-06,
|
| 1444 |
+
"loss": 0.5841,
|
| 1445 |
+
"step": 205
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 0.3721770551038844,
|
| 1449 |
+
"grad_norm": 0.23815007414755204,
|
| 1450 |
+
"learning_rate": 7.447999359825263e-06,
|
| 1451 |
+
"loss": 0.5714,
|
| 1452 |
+
"step": 206
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 0.37398373983739835,
|
| 1456 |
+
"grad_norm": 0.2559897289254791,
|
| 1457 |
+
"learning_rate": 7.421867086561001e-06,
|
| 1458 |
+
"loss": 0.5798,
|
| 1459 |
+
"step": 207
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 0.3757904245709124,
|
| 1463 |
+
"grad_norm": 0.23431179392042337,
|
| 1464 |
+
"learning_rate": 7.395648091124476e-06,
|
| 1465 |
+
"loss": 0.5668,
|
| 1466 |
+
"step": 208
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 0.37759710930442636,
|
| 1470 |
+
"grad_norm": 0.2512828254268562,
|
| 1471 |
+
"learning_rate": 7.369343312364994e-06,
|
| 1472 |
+
"loss": 0.5881,
|
| 1473 |
+
"step": 209
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 0.3794037940379404,
|
| 1477 |
+
"grad_norm": 0.24502883889971508,
|
| 1478 |
+
"learning_rate": 7.342953692203594e-06,
|
| 1479 |
+
"loss": 0.5836,
|
| 1480 |
+
"step": 210
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 0.38121047877145436,
|
| 1484 |
+
"grad_norm": 0.21556942382237343,
|
| 1485 |
+
"learning_rate": 7.31648017559931e-06,
|
| 1486 |
+
"loss": 0.5845,
|
| 1487 |
+
"step": 211
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 0.3830171635049684,
|
| 1491 |
+
"grad_norm": 0.23583974310453942,
|
| 1492 |
+
"learning_rate": 7.289923710515338e-06,
|
| 1493 |
+
"loss": 0.5927,
|
| 1494 |
+
"step": 212
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 0.38482384823848237,
|
| 1498 |
+
"grad_norm": 0.23705623638550383,
|
| 1499 |
+
"learning_rate": 7.263285247885097e-06,
|
| 1500 |
+
"loss": 0.5917,
|
| 1501 |
+
"step": 213
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 0.3866305329719964,
|
| 1505 |
+
"grad_norm": 0.22991114203917198,
|
| 1506 |
+
"learning_rate": 7.236565741578163e-06,
|
| 1507 |
+
"loss": 0.5778,
|
| 1508 |
+
"step": 214
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 0.3884372177055104,
|
| 1512 |
+
"grad_norm": 0.23180178819150027,
|
| 1513 |
+
"learning_rate": 7.2097661483661355e-06,
|
| 1514 |
+
"loss": 0.6044,
|
| 1515 |
+
"step": 215
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 0.3902439024390244,
|
| 1519 |
+
"grad_norm": 0.26613899638149857,
|
| 1520 |
+
"learning_rate": 7.182887427888351e-06,
|
| 1521 |
+
"loss": 0.5936,
|
| 1522 |
+
"step": 216
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 0.3920505871725384,
|
| 1526 |
+
"grad_norm": 0.2312933670885305,
|
| 1527 |
+
"learning_rate": 7.155930542617543e-06,
|
| 1528 |
+
"loss": 0.5935,
|
| 1529 |
+
"step": 217
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 0.3938572719060524,
|
| 1533 |
+
"grad_norm": 0.22978225434942193,
|
| 1534 |
+
"learning_rate": 7.128896457825364e-06,
|
| 1535 |
+
"loss": 0.5854,
|
| 1536 |
+
"step": 218
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 0.3956639566395664,
|
| 1540 |
+
"grad_norm": 0.23602529887683144,
|
| 1541 |
+
"learning_rate": 7.101786141547829e-06,
|
| 1542 |
+
"loss": 0.5801,
|
| 1543 |
+
"step": 219
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 0.3974706413730804,
|
| 1547 |
+
"grad_norm": 0.2703924915547822,
|
| 1548 |
+
"learning_rate": 7.074600564550643e-06,
|
| 1549 |
+
"loss": 0.5833,
|
| 1550 |
+
"step": 220
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 0.3992773261065944,
|
| 1554 |
+
"grad_norm": 0.2617465948292489,
|
| 1555 |
+
"learning_rate": 7.047340700294454e-06,
|
| 1556 |
+
"loss": 0.5716,
|
| 1557 |
+
"step": 221
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 0.4010840108401084,
|
| 1561 |
+
"grad_norm": 0.24382884586289413,
|
| 1562 |
+
"learning_rate": 7.020007524899976e-06,
|
| 1563 |
+
"loss": 0.5886,
|
| 1564 |
+
"step": 222
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 0.4028906955736224,
|
| 1568 |
+
"grad_norm": 0.21935282499736788,
|
| 1569 |
+
"learning_rate": 6.992602017113058e-06,
|
| 1570 |
+
"loss": 0.5714,
|
| 1571 |
+
"step": 223
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 0.4046973803071364,
|
| 1575 |
+
"grad_norm": 0.25790526082244813,
|
| 1576 |
+
"learning_rate": 6.965125158269619e-06,
|
| 1577 |
+
"loss": 0.5766,
|
| 1578 |
+
"step": 224
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 0.4065040650406504,
|
| 1582 |
+
"grad_norm": 0.31271609267639955,
|
| 1583 |
+
"learning_rate": 6.9375779322605154e-06,
|
| 1584 |
+
"loss": 0.5815,
|
| 1585 |
+
"step": 225
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 0.4083107497741644,
|
| 1589 |
+
"grad_norm": 0.25644160028108604,
|
| 1590 |
+
"learning_rate": 6.909961325496312e-06,
|
| 1591 |
+
"loss": 0.5876,
|
| 1592 |
+
"step": 226
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 0.4101174345076784,
|
| 1596 |
+
"grad_norm": 0.23592094628675797,
|
| 1597 |
+
"learning_rate": 6.88227632687196e-06,
|
| 1598 |
+
"loss": 0.5922,
|
| 1599 |
+
"step": 227
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 0.41192411924119243,
|
| 1603 |
+
"grad_norm": 0.2466791961563765,
|
| 1604 |
+
"learning_rate": 6.854523927731383e-06,
|
| 1605 |
+
"loss": 0.5786,
|
| 1606 |
+
"step": 228
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 0.4137308039747064,
|
| 1610 |
+
"grad_norm": 0.23617198599914752,
|
| 1611 |
+
"learning_rate": 6.8267051218319766e-06,
|
| 1612 |
+
"loss": 0.5808,
|
| 1613 |
+
"step": 229
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 0.41553748870822044,
|
| 1617 |
+
"grad_norm": 0.2416898307177306,
|
| 1618 |
+
"learning_rate": 6.798820905309036e-06,
|
| 1619 |
+
"loss": 0.583,
|
| 1620 |
+
"step": 230
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 0.4173441734417344,
|
| 1624 |
+
"grad_norm": 0.24268134289433835,
|
| 1625 |
+
"learning_rate": 6.7708722766400745e-06,
|
| 1626 |
+
"loss": 0.5831,
|
| 1627 |
+
"step": 231
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 0.41915085817524844,
|
| 1631 |
+
"grad_norm": 0.2228715513161369,
|
| 1632 |
+
"learning_rate": 6.7428602366090764e-06,
|
| 1633 |
+
"loss": 0.5859,
|
| 1634 |
+
"step": 232
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 0.4209575429087624,
|
| 1638 |
+
"grad_norm": 0.249377876574396,
|
| 1639 |
+
"learning_rate": 6.714785788270658e-06,
|
| 1640 |
+
"loss": 0.567,
|
| 1641 |
+
"step": 233
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 0.42276422764227645,
|
| 1645 |
+
"grad_norm": 0.26017782806271494,
|
| 1646 |
+
"learning_rate": 6.686649936914151e-06,
|
| 1647 |
+
"loss": 0.5833,
|
| 1648 |
+
"step": 234
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 0.4245709123757904,
|
| 1652 |
+
"grad_norm": 0.22238035207177997,
|
| 1653 |
+
"learning_rate": 6.658453690027604e-06,
|
| 1654 |
+
"loss": 0.578,
|
| 1655 |
+
"step": 235
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 0.42637759710930445,
|
| 1659 |
+
"grad_norm": 0.2251727087649973,
|
| 1660 |
+
"learning_rate": 6.63019805726171e-06,
|
| 1661 |
+
"loss": 0.5897,
|
| 1662 |
+
"step": 236
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 0.4281842818428184,
|
| 1666 |
+
"grad_norm": 0.24334747524670824,
|
| 1667 |
+
"learning_rate": 6.601884050393649e-06,
|
| 1668 |
+
"loss": 0.5883,
|
| 1669 |
+
"step": 237
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 0.42999096657633246,
|
| 1673 |
+
"grad_norm": 0.23018321868830866,
|
| 1674 |
+
"learning_rate": 6.57351268329086e-06,
|
| 1675 |
+
"loss": 0.5973,
|
| 1676 |
+
"step": 238
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 0.43179765130984643,
|
| 1680 |
+
"grad_norm": 0.2328779372011691,
|
| 1681 |
+
"learning_rate": 6.545084971874738e-06,
|
| 1682 |
+
"loss": 0.5789,
|
| 1683 |
+
"step": 239
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.43360433604336046,
|
| 1687 |
+
"grad_norm": 0.23242378577030887,
|
| 1688 |
+
"learning_rate": 6.51660193408425e-06,
|
| 1689 |
+
"loss": 0.5794,
|
| 1690 |
+
"step": 240
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 0.43541102077687444,
|
| 1694 |
+
"grad_norm": 0.2161659491395485,
|
| 1695 |
+
"learning_rate": 6.4880645898394935e-06,
|
| 1696 |
+
"loss": 0.5778,
|
| 1697 |
+
"step": 241
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 0.4372177055103884,
|
| 1701 |
+
"grad_norm": 0.2299276453855878,
|
| 1702 |
+
"learning_rate": 6.459473961005168e-06,
|
| 1703 |
+
"loss": 0.5786,
|
| 1704 |
+
"step": 242
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 0.43902439024390244,
|
| 1708 |
+
"grad_norm": 0.2476235320127899,
|
| 1709 |
+
"learning_rate": 6.4308310713539845e-06,
|
| 1710 |
+
"loss": 0.5828,
|
| 1711 |
+
"step": 243
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 0.4408310749774164,
|
| 1715 |
+
"grad_norm": 0.22170490563024103,
|
| 1716 |
+
"learning_rate": 6.402136946530014e-06,
|
| 1717 |
+
"loss": 0.5882,
|
| 1718 |
+
"step": 244
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 0.44263775971093045,
|
| 1722 |
+
"grad_norm": 0.228282250322248,
|
| 1723 |
+
"learning_rate": 6.373392614011952e-06,
|
| 1724 |
+
"loss": 0.5814,
|
| 1725 |
+
"step": 245
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 0.4444444444444444,
|
| 1729 |
+
"grad_norm": 0.24503809348111755,
|
| 1730 |
+
"learning_rate": 6.344599103076329e-06,
|
| 1731 |
+
"loss": 0.5878,
|
| 1732 |
+
"step": 246
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 0.44625112917795845,
|
| 1736 |
+
"grad_norm": 0.217515748990581,
|
| 1737 |
+
"learning_rate": 6.315757444760659e-06,
|
| 1738 |
+
"loss": 0.5703,
|
| 1739 |
+
"step": 247
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 0.4480578139114724,
|
| 1743 |
+
"grad_norm": 0.2330555687580969,
|
| 1744 |
+
"learning_rate": 6.286868671826513e-06,
|
| 1745 |
+
"loss": 0.5885,
|
| 1746 |
+
"step": 248
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 0.44986449864498645,
|
| 1750 |
+
"grad_norm": 0.21335194723381823,
|
| 1751 |
+
"learning_rate": 6.257933818722544e-06,
|
| 1752 |
+
"loss": 0.5717,
|
| 1753 |
+
"step": 249
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 0.45167118337850043,
|
| 1757 |
+
"grad_norm": 0.22486747840550073,
|
| 1758 |
+
"learning_rate": 6.228953921547441e-06,
|
| 1759 |
+
"loss": 0.5866,
|
| 1760 |
+
"step": 250
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 0.45347786811201446,
|
| 1764 |
+
"grad_norm": 0.25899034502299706,
|
| 1765 |
+
"learning_rate": 6.19993001801283e-06,
|
| 1766 |
+
"loss": 0.5745,
|
| 1767 |
+
"step": 251
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 0.45528455284552843,
|
| 1771 |
+
"grad_norm": 0.21794726924055616,
|
| 1772 |
+
"learning_rate": 6.17086314740612e-06,
|
| 1773 |
+
"loss": 0.5559,
|
| 1774 |
+
"step": 252
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 0.45709123757904246,
|
| 1778 |
+
"grad_norm": 0.24234352061206263,
|
| 1779 |
+
"learning_rate": 6.141754350553279e-06,
|
| 1780 |
+
"loss": 0.5788,
|
| 1781 |
+
"step": 253
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 0.45889792231255644,
|
| 1785 |
+
"grad_norm": 0.2274414978394944,
|
| 1786 |
+
"learning_rate": 6.112604669781572e-06,
|
| 1787 |
+
"loss": 0.5774,
|
| 1788 |
+
"step": 254
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 0.46070460704607047,
|
| 1792 |
+
"grad_norm": 0.22998778589918353,
|
| 1793 |
+
"learning_rate": 6.083415148882236e-06,
|
| 1794 |
+
"loss": 0.5716,
|
| 1795 |
+
"step": 255
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 0.46251129177958444,
|
| 1799 |
+
"grad_norm": 0.22485661414287983,
|
| 1800 |
+
"learning_rate": 6.054186833073096e-06,
|
| 1801 |
+
"loss": 0.572,
|
| 1802 |
+
"step": 256
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 0.4643179765130985,
|
| 1806 |
+
"grad_norm": 0.22811563640884158,
|
| 1807 |
+
"learning_rate": 6.024920768961153e-06,
|
| 1808 |
+
"loss": 0.581,
|
| 1809 |
+
"step": 257
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 0.46612466124661245,
|
| 1813 |
+
"grad_norm": 0.22052113306724444,
|
| 1814 |
+
"learning_rate": 5.995618004505091e-06,
|
| 1815 |
+
"loss": 0.5766,
|
| 1816 |
+
"step": 258
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 0.4679313459801265,
|
| 1820 |
+
"grad_norm": 0.21805381304894822,
|
| 1821 |
+
"learning_rate": 5.9662795889777666e-06,
|
| 1822 |
+
"loss": 0.5803,
|
| 1823 |
+
"step": 259
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 0.46973803071364045,
|
| 1827 |
+
"grad_norm": 0.23376637006655057,
|
| 1828 |
+
"learning_rate": 5.936906572928625e-06,
|
| 1829 |
+
"loss": 0.5945,
|
| 1830 |
+
"step": 260
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 0.4715447154471545,
|
| 1834 |
+
"grad_norm": 0.2623609821320283,
|
| 1835 |
+
"learning_rate": 5.907500008146082e-06,
|
| 1836 |
+
"loss": 0.5855,
|
| 1837 |
+
"step": 261
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 0.47335140018066846,
|
| 1841 |
+
"grad_norm": 0.20712796845127485,
|
| 1842 |
+
"learning_rate": 5.878060947619877e-06,
|
| 1843 |
+
"loss": 0.5739,
|
| 1844 |
+
"step": 262
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 0.4751580849141825,
|
| 1848 |
+
"grad_norm": 0.21143577704362118,
|
| 1849 |
+
"learning_rate": 5.848590445503345e-06,
|
| 1850 |
+
"loss": 0.5782,
|
| 1851 |
+
"step": 263
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 0.47696476964769646,
|
| 1855 |
+
"grad_norm": 0.21994485672746086,
|
| 1856 |
+
"learning_rate": 5.819089557075689e-06,
|
| 1857 |
+
"loss": 0.585,
|
| 1858 |
+
"step": 264
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 0.4787714543812105,
|
| 1862 |
+
"grad_norm": 0.21069182355242835,
|
| 1863 |
+
"learning_rate": 5.78955933870418e-06,
|
| 1864 |
+
"loss": 0.5659,
|
| 1865 |
+
"step": 265
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 0.48057813911472447,
|
| 1869 |
+
"grad_norm": 0.23778394000563338,
|
| 1870 |
+
"learning_rate": 5.760000847806337e-06,
|
| 1871 |
+
"loss": 0.5902,
|
| 1872 |
+
"step": 266
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 0.4823848238482385,
|
| 1876 |
+
"grad_norm": 0.21210561161504926,
|
| 1877 |
+
"learning_rate": 5.730415142812059e-06,
|
| 1878 |
+
"loss": 0.5745,
|
| 1879 |
+
"step": 267
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 0.48419150858175247,
|
| 1883 |
+
"grad_norm": 0.23173733623724077,
|
| 1884 |
+
"learning_rate": 5.70080328312573e-06,
|
| 1885 |
+
"loss": 0.5752,
|
| 1886 |
+
"step": 268
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 0.4859981933152665,
|
| 1890 |
+
"grad_norm": 0.21851750516316734,
|
| 1891 |
+
"learning_rate": 5.671166329088278e-06,
|
| 1892 |
+
"loss": 0.581,
|
| 1893 |
+
"step": 269
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 0.4878048780487805,
|
| 1897 |
+
"grad_norm": 0.230353098776304,
|
| 1898 |
+
"learning_rate": 5.641505341939212e-06,
|
| 1899 |
+
"loss": 0.5633,
|
| 1900 |
+
"step": 270
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 0.4896115627822945,
|
| 1904 |
+
"grad_norm": 0.23007026101437933,
|
| 1905 |
+
"learning_rate": 5.611821383778614e-06,
|
| 1906 |
+
"loss": 0.5847,
|
| 1907 |
+
"step": 271
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 0.4914182475158085,
|
| 1911 |
+
"grad_norm": 0.23404979176928067,
|
| 1912 |
+
"learning_rate": 5.582115517529114e-06,
|
| 1913 |
+
"loss": 0.5792,
|
| 1914 |
+
"step": 272
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 0.4932249322493225,
|
| 1918 |
+
"grad_norm": 0.2340510902231734,
|
| 1919 |
+
"learning_rate": 5.55238880689783e-06,
|
| 1920 |
+
"loss": 0.5873,
|
| 1921 |
+
"step": 273
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 0.4950316169828365,
|
| 1925 |
+
"grad_norm": 0.2515187234434128,
|
| 1926 |
+
"learning_rate": 5.522642316338268e-06,
|
| 1927 |
+
"loss": 0.5747,
|
| 1928 |
+
"step": 274
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 0.4968383017163505,
|
| 1932 |
+
"grad_norm": 0.22982520627329517,
|
| 1933 |
+
"learning_rate": 5.4928771110122185e-06,
|
| 1934 |
+
"loss": 0.5691,
|
| 1935 |
+
"step": 275
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 0.4986449864498645,
|
| 1939 |
+
"grad_norm": 0.21964980040640775,
|
| 1940 |
+
"learning_rate": 5.463094256751608e-06,
|
| 1941 |
+
"loss": 0.5616,
|
| 1942 |
+
"step": 276
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 0.5004516711833785,
|
| 1946 |
+
"grad_norm": 0.22067905722359166,
|
| 1947 |
+
"learning_rate": 5.433294820020335e-06,
|
| 1948 |
+
"loss": 0.5736,
|
| 1949 |
+
"step": 277
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 0.5022583559168925,
|
| 1953 |
+
"grad_norm": 0.22091279640365025,
|
| 1954 |
+
"learning_rate": 5.403479867876087e-06,
|
| 1955 |
+
"loss": 0.5603,
|
| 1956 |
+
"step": 278
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 0.5040650406504065,
|
| 1960 |
+
"grad_norm": 0.2313691575132618,
|
| 1961 |
+
"learning_rate": 5.373650467932122e-06,
|
| 1962 |
+
"loss": 0.575,
|
| 1963 |
+
"step": 279
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 0.5058717253839206,
|
| 1967 |
+
"grad_norm": 0.21483775764620186,
|
| 1968 |
+
"learning_rate": 5.343807688319047e-06,
|
| 1969 |
+
"loss": 0.5716,
|
| 1970 |
+
"step": 280
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 0.5076784101174345,
|
| 1974 |
+
"grad_norm": 0.23350539595994096,
|
| 1975 |
+
"learning_rate": 5.3139525976465675e-06,
|
| 1976 |
+
"loss": 0.5725,
|
| 1977 |
+
"step": 281
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 0.5094850948509485,
|
| 1981 |
+
"grad_norm": 0.20419037267861948,
|
| 1982 |
+
"learning_rate": 5.284086264965224e-06,
|
| 1983 |
+
"loss": 0.5664,
|
| 1984 |
+
"step": 282
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 0.5112917795844625,
|
| 1988 |
+
"grad_norm": 0.2206929643409549,
|
| 1989 |
+
"learning_rate": 5.2542097597281095e-06,
|
| 1990 |
+
"loss": 0.5824,
|
| 1991 |
+
"step": 283
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 0.5130984643179766,
|
| 1995 |
+
"grad_norm": 0.2328716449251837,
|
| 1996 |
+
"learning_rate": 5.224324151752575e-06,
|
| 1997 |
+
"loss": 0.5704,
|
| 1998 |
+
"step": 284
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 0.5149051490514905,
|
| 2002 |
+
"grad_norm": 0.22646920035996798,
|
| 2003 |
+
"learning_rate": 5.194430511181925e-06,
|
| 2004 |
+
"loss": 0.5637,
|
| 2005 |
+
"step": 285
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 0.5167118337850045,
|
| 2009 |
+
"grad_norm": 0.2338999611062683,
|
| 2010 |
+
"learning_rate": 5.1645299084470936e-06,
|
| 2011 |
+
"loss": 0.563,
|
| 2012 |
+
"step": 286
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 0.5185185185185185,
|
| 2016 |
+
"grad_norm": 0.23348201201542426,
|
| 2017 |
+
"learning_rate": 5.134623414228315e-06,
|
| 2018 |
+
"loss": 0.5846,
|
| 2019 |
+
"step": 287
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 0.5203252032520326,
|
| 2023 |
+
"grad_norm": 0.2066768548623096,
|
| 2024 |
+
"learning_rate": 5.1047120994167855e-06,
|
| 2025 |
+
"loss": 0.5814,
|
| 2026 |
+
"step": 288
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 0.5221318879855466,
|
| 2030 |
+
"grad_norm": 0.22067476291358168,
|
| 2031 |
+
"learning_rate": 5.074797035076319e-06,
|
| 2032 |
+
"loss": 0.5658,
|
| 2033 |
+
"step": 289
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 0.5239385727190605,
|
| 2037 |
+
"grad_norm": 0.2307755650814999,
|
| 2038 |
+
"learning_rate": 5.04487929240499e-06,
|
| 2039 |
+
"loss": 0.5777,
|
| 2040 |
+
"step": 290
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 0.5257452574525745,
|
| 2044 |
+
"grad_norm": 0.21733975598284586,
|
| 2045 |
+
"learning_rate": 5.014959942696782e-06,
|
| 2046 |
+
"loss": 0.5822,
|
| 2047 |
+
"step": 291
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 0.5275519421860885,
|
| 2051 |
+
"grad_norm": 0.2110494515215823,
|
| 2052 |
+
"learning_rate": 4.98504005730322e-06,
|
| 2053 |
+
"loss": 0.5852,
|
| 2054 |
+
"step": 292
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 0.5293586269196026,
|
| 2058 |
+
"grad_norm": 0.21376160889279272,
|
| 2059 |
+
"learning_rate": 4.955120707595011e-06,
|
| 2060 |
+
"loss": 0.5786,
|
| 2061 |
+
"step": 293
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 0.5311653116531165,
|
| 2065 |
+
"grad_norm": 0.22255506256387717,
|
| 2066 |
+
"learning_rate": 4.9252029649236835e-06,
|
| 2067 |
+
"loss": 0.5707,
|
| 2068 |
+
"step": 294
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 0.5329719963866305,
|
| 2072 |
+
"grad_norm": 0.22357316134025623,
|
| 2073 |
+
"learning_rate": 4.895287900583216e-06,
|
| 2074 |
+
"loss": 0.569,
|
| 2075 |
+
"step": 295
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 0.5347786811201445,
|
| 2079 |
+
"grad_norm": 0.2303749633454824,
|
| 2080 |
+
"learning_rate": 4.865376585771687e-06,
|
| 2081 |
+
"loss": 0.572,
|
| 2082 |
+
"step": 296
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 0.5365853658536586,
|
| 2086 |
+
"grad_norm": 0.24691170554512507,
|
| 2087 |
+
"learning_rate": 4.835470091552906e-06,
|
| 2088 |
+
"loss": 0.578,
|
| 2089 |
+
"step": 297
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 0.5383920505871725,
|
| 2093 |
+
"grad_norm": 0.2184305772497302,
|
| 2094 |
+
"learning_rate": 4.805569488818077e-06,
|
| 2095 |
+
"loss": 0.5722,
|
| 2096 |
+
"step": 298
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 0.5401987353206865,
|
| 2100 |
+
"grad_norm": 0.21437152967432271,
|
| 2101 |
+
"learning_rate": 4.775675848247427e-06,
|
| 2102 |
+
"loss": 0.5884,
|
| 2103 |
+
"step": 299
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 0.5420054200542005,
|
| 2107 |
+
"grad_norm": 0.21552542470264674,
|
| 2108 |
+
"learning_rate": 4.745790240271892e-06,
|
| 2109 |
+
"loss": 0.5761,
|
| 2110 |
+
"step": 300
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 0.5438121047877146,
|
| 2114 |
+
"grad_norm": 0.2125660770635089,
|
| 2115 |
+
"learning_rate": 4.715913735034779e-06,
|
| 2116 |
+
"loss": 0.5773,
|
| 2117 |
+
"step": 301
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 0.5456187895212286,
|
| 2121 |
+
"grad_norm": 0.21488086772508092,
|
| 2122 |
+
"learning_rate": 4.686047402353433e-06,
|
| 2123 |
+
"loss": 0.5897,
|
| 2124 |
+
"step": 302
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 0.5474254742547425,
|
| 2128 |
+
"grad_norm": 0.22966510979007831,
|
| 2129 |
+
"learning_rate": 4.6561923116809545e-06,
|
| 2130 |
+
"loss": 0.5708,
|
| 2131 |
+
"step": 303
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 0.5492321589882565,
|
| 2135 |
+
"grad_norm": 0.21097665896626477,
|
| 2136 |
+
"learning_rate": 4.626349532067879e-06,
|
| 2137 |
+
"loss": 0.5656,
|
| 2138 |
+
"step": 304
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 0.5510388437217706,
|
| 2142 |
+
"grad_norm": 0.2101261903441546,
|
| 2143 |
+
"learning_rate": 4.596520132123915e-06,
|
| 2144 |
+
"loss": 0.5722,
|
| 2145 |
+
"step": 305
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 0.5528455284552846,
|
| 2149 |
+
"grad_norm": 0.22436513473996944,
|
| 2150 |
+
"learning_rate": 4.566705179979665e-06,
|
| 2151 |
+
"loss": 0.5698,
|
| 2152 |
+
"step": 306
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 0.5546522131887985,
|
| 2156 |
+
"grad_norm": 0.20902719330700562,
|
| 2157 |
+
"learning_rate": 4.536905743248394e-06,
|
| 2158 |
+
"loss": 0.5878,
|
| 2159 |
+
"step": 307
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 0.5564588979223125,
|
| 2163 |
+
"grad_norm": 0.21097784366583347,
|
| 2164 |
+
"learning_rate": 4.507122888987782e-06,
|
| 2165 |
+
"loss": 0.5671,
|
| 2166 |
+
"step": 308
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 0.5582655826558266,
|
| 2170 |
+
"grad_norm": 0.21970798388898458,
|
| 2171 |
+
"learning_rate": 4.477357683661734e-06,
|
| 2172 |
+
"loss": 0.5762,
|
| 2173 |
+
"step": 309
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 0.5600722673893406,
|
| 2177 |
+
"grad_norm": 0.23843978575881658,
|
| 2178 |
+
"learning_rate": 4.447611193102171e-06,
|
| 2179 |
+
"loss": 0.5595,
|
| 2180 |
+
"step": 310
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 0.5618789521228545,
|
| 2184 |
+
"grad_norm": 0.2085020569553253,
|
| 2185 |
+
"learning_rate": 4.417884482470887e-06,
|
| 2186 |
+
"loss": 0.5776,
|
| 2187 |
+
"step": 311
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 0.5636856368563685,
|
| 2191 |
+
"grad_norm": 0.20561180891816055,
|
| 2192 |
+
"learning_rate": 4.388178616221389e-06,
|
| 2193 |
+
"loss": 0.5771,
|
| 2194 |
+
"step": 312
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 0.5654923215898826,
|
| 2198 |
+
"grad_norm": 0.21551536323301249,
|
| 2199 |
+
"learning_rate": 4.35849465806079e-06,
|
| 2200 |
+
"loss": 0.5788,
|
| 2201 |
+
"step": 313
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 0.5672990063233966,
|
| 2205 |
+
"grad_norm": 0.20574458895157158,
|
| 2206 |
+
"learning_rate": 4.3288336709117246e-06,
|
| 2207 |
+
"loss": 0.5707,
|
| 2208 |
+
"step": 314
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 0.5691056910569106,
|
| 2212 |
+
"grad_norm": 0.21500847742483045,
|
| 2213 |
+
"learning_rate": 4.299196716874271e-06,
|
| 2214 |
+
"loss": 0.5706,
|
| 2215 |
+
"step": 315
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 0.5709123757904245,
|
| 2219 |
+
"grad_norm": 0.20544086197673322,
|
| 2220 |
+
"learning_rate": 4.269584857187942e-06,
|
| 2221 |
+
"loss": 0.5676,
|
| 2222 |
+
"step": 316
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 0.5727190605239386,
|
| 2226 |
+
"grad_norm": 0.19987644528439158,
|
| 2227 |
+
"learning_rate": 4.239999152193664e-06,
|
| 2228 |
+
"loss": 0.5621,
|
| 2229 |
+
"step": 317
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 0.5745257452574526,
|
| 2233 |
+
"grad_norm": 0.20629701462913586,
|
| 2234 |
+
"learning_rate": 4.2104406612958216e-06,
|
| 2235 |
+
"loss": 0.5744,
|
| 2236 |
+
"step": 318
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 0.5763324299909666,
|
| 2240 |
+
"grad_norm": 0.22689443352313568,
|
| 2241 |
+
"learning_rate": 4.180910442924312e-06,
|
| 2242 |
+
"loss": 0.5841,
|
| 2243 |
+
"step": 319
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 0.5781391147244805,
|
| 2247 |
+
"grad_norm": 0.2199680438163748,
|
| 2248 |
+
"learning_rate": 4.1514095544966556e-06,
|
| 2249 |
+
"loss": 0.5671,
|
| 2250 |
+
"step": 320
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 0.5799457994579946,
|
| 2254 |
+
"grad_norm": 0.22719849829451663,
|
| 2255 |
+
"learning_rate": 4.121939052380125e-06,
|
| 2256 |
+
"loss": 0.5634,
|
| 2257 |
+
"step": 321
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 0.5817524841915086,
|
| 2261 |
+
"grad_norm": 0.24575016551621642,
|
| 2262 |
+
"learning_rate": 4.092499991853919e-06,
|
| 2263 |
+
"loss": 0.585,
|
| 2264 |
+
"step": 322
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 0.5835591689250226,
|
| 2268 |
+
"grad_norm": 0.2165593982049528,
|
| 2269 |
+
"learning_rate": 4.063093427071376e-06,
|
| 2270 |
+
"loss": 0.5705,
|
| 2271 |
+
"step": 323
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 0.5853658536585366,
|
| 2275 |
+
"grad_norm": 0.21038397261423286,
|
| 2276 |
+
"learning_rate": 4.033720411022235e-06,
|
| 2277 |
+
"loss": 0.5509,
|
| 2278 |
+
"step": 324
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 0.5871725383920506,
|
| 2282 |
+
"grad_norm": 0.23381630506120754,
|
| 2283 |
+
"learning_rate": 4.0043819954949105e-06,
|
| 2284 |
+
"loss": 0.5692,
|
| 2285 |
+
"step": 325
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 0.5889792231255646,
|
| 2289 |
+
"grad_norm": 0.22274092699155776,
|
| 2290 |
+
"learning_rate": 3.975079231038848e-06,
|
| 2291 |
+
"loss": 0.578,
|
| 2292 |
+
"step": 326
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 0.5907859078590786,
|
| 2296 |
+
"grad_norm": 0.23312487246943384,
|
| 2297 |
+
"learning_rate": 3.9458131669269066e-06,
|
| 2298 |
+
"loss": 0.5655,
|
| 2299 |
+
"step": 327
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 0.5925925925925926,
|
| 2303 |
+
"grad_norm": 0.20940039382277698,
|
| 2304 |
+
"learning_rate": 3.916584851117766e-06,
|
| 2305 |
+
"loss": 0.5713,
|
| 2306 |
+
"step": 328
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 0.5943992773261066,
|
| 2310 |
+
"grad_norm": 0.20083788756986765,
|
| 2311 |
+
"learning_rate": 3.887395330218429e-06,
|
| 2312 |
+
"loss": 0.5623,
|
| 2313 |
+
"step": 329
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 0.5962059620596206,
|
| 2317 |
+
"grad_norm": 0.22293875603937713,
|
| 2318 |
+
"learning_rate": 3.8582456494467214e-06,
|
| 2319 |
+
"loss": 0.5694,
|
| 2320 |
+
"step": 330
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 0.5980126467931346,
|
| 2324 |
+
"grad_norm": 0.21580894775676748,
|
| 2325 |
+
"learning_rate": 3.829136852593881e-06,
|
| 2326 |
+
"loss": 0.5741,
|
| 2327 |
+
"step": 331
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 0.5998193315266486,
|
| 2331 |
+
"grad_norm": 0.2084327717713985,
|
| 2332 |
+
"learning_rate": 3.8000699819871704e-06,
|
| 2333 |
+
"loss": 0.5568,
|
| 2334 |
+
"step": 332
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 0.6016260162601627,
|
| 2338 |
+
"grad_norm": 0.19133614379073072,
|
| 2339 |
+
"learning_rate": 3.7710460784525617e-06,
|
| 2340 |
+
"loss": 0.5777,
|
| 2341 |
+
"step": 333
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 0.6034327009936766,
|
| 2345 |
+
"grad_norm": 0.21749963390685656,
|
| 2346 |
+
"learning_rate": 3.7420661812774577e-06,
|
| 2347 |
+
"loss": 0.5904,
|
| 2348 |
+
"step": 334
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 0.6052393857271906,
|
| 2352 |
+
"grad_norm": 0.19792142717136593,
|
| 2353 |
+
"learning_rate": 3.7131313281734895e-06,
|
| 2354 |
+
"loss": 0.5727,
|
| 2355 |
+
"step": 335
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 0.6070460704607046,
|
| 2359 |
+
"grad_norm": 0.20808382531187122,
|
| 2360 |
+
"learning_rate": 3.6842425552393424e-06,
|
| 2361 |
+
"loss": 0.5701,
|
| 2362 |
+
"step": 336
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 0.6088527551942186,
|
| 2366 |
+
"grad_norm": 0.20007357870443254,
|
| 2367 |
+
"learning_rate": 3.655400896923672e-06,
|
| 2368 |
+
"loss": 0.5713,
|
| 2369 |
+
"step": 337
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 0.6106594399277326,
|
| 2373 |
+
"grad_norm": 0.21439635973420199,
|
| 2374 |
+
"learning_rate": 3.62660738598805e-06,
|
| 2375 |
+
"loss": 0.5669,
|
| 2376 |
+
"step": 338
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 0.6124661246612466,
|
| 2380 |
+
"grad_norm": 0.19649367243591512,
|
| 2381 |
+
"learning_rate": 3.5978630534699873e-06,
|
| 2382 |
+
"loss": 0.5756,
|
| 2383 |
+
"step": 339
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 0.6142728093947606,
|
| 2387 |
+
"grad_norm": 0.1993688643471656,
|
| 2388 |
+
"learning_rate": 3.5691689286460172e-06,
|
| 2389 |
+
"loss": 0.571,
|
| 2390 |
+
"step": 340
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 0.6160794941282746,
|
| 2394 |
+
"grad_norm": 0.1993509321428296,
|
| 2395 |
+
"learning_rate": 3.540526038994834e-06,
|
| 2396 |
+
"loss": 0.5695,
|
| 2397 |
+
"step": 341
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 0.6178861788617886,
|
| 2401 |
+
"grad_norm": 0.21021124016240533,
|
| 2402 |
+
"learning_rate": 3.5119354101605086e-06,
|
| 2403 |
+
"loss": 0.573,
|
| 2404 |
+
"step": 342
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 0.6196928635953026,
|
| 2408 |
+
"grad_norm": 0.20907305981232832,
|
| 2409 |
+
"learning_rate": 3.4833980659157507e-06,
|
| 2410 |
+
"loss": 0.5673,
|
| 2411 |
+
"step": 343
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 0.6214995483288166,
|
| 2415 |
+
"grad_norm": 0.19471235958062905,
|
| 2416 |
+
"learning_rate": 3.4549150281252635e-06,
|
| 2417 |
+
"loss": 0.5569,
|
| 2418 |
+
"step": 344
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 0.6233062330623306,
|
| 2422 |
+
"grad_norm": 0.22694431095992104,
|
| 2423 |
+
"learning_rate": 3.4264873167091405e-06,
|
| 2424 |
+
"loss": 0.5711,
|
| 2425 |
+
"step": 345
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 0.6251129177958447,
|
| 2429 |
+
"grad_norm": 0.20864419691174535,
|
| 2430 |
+
"learning_rate": 3.398115949606352e-06,
|
| 2431 |
+
"loss": 0.5725,
|
| 2432 |
+
"step": 346
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 0.6269196025293586,
|
| 2436 |
+
"grad_norm": 0.192989073538916,
|
| 2437 |
+
"learning_rate": 3.3698019427382912e-06,
|
| 2438 |
+
"loss": 0.5577,
|
| 2439 |
+
"step": 347
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 0.6287262872628726,
|
| 2443 |
+
"grad_norm": 0.22659064089939246,
|
| 2444 |
+
"learning_rate": 3.341546309972398e-06,
|
| 2445 |
+
"loss": 0.5589,
|
| 2446 |
+
"step": 348
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 0.6305329719963866,
|
| 2450 |
+
"grad_norm": 0.19775912613412447,
|
| 2451 |
+
"learning_rate": 3.3133500630858507e-06,
|
| 2452 |
+
"loss": 0.5618,
|
| 2453 |
+
"step": 349
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 0.6323396567299007,
|
| 2457 |
+
"grad_norm": 0.21221541860013762,
|
| 2458 |
+
"learning_rate": 3.2852142117293435e-06,
|
| 2459 |
+
"loss": 0.5742,
|
| 2460 |
+
"step": 350
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 0.6341463414634146,
|
| 2464 |
+
"grad_norm": 0.1965105061000691,
|
| 2465 |
+
"learning_rate": 3.2571397633909252e-06,
|
| 2466 |
+
"loss": 0.5641,
|
| 2467 |
+
"step": 351
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 0.6359530261969286,
|
| 2471 |
+
"grad_norm": 0.21779012635428768,
|
| 2472 |
+
"learning_rate": 3.229127723359927e-06,
|
| 2473 |
+
"loss": 0.578,
|
| 2474 |
+
"step": 352
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 0.6377597109304426,
|
| 2478 |
+
"grad_norm": 0.19836139294521862,
|
| 2479 |
+
"learning_rate": 3.2011790946909673e-06,
|
| 2480 |
+
"loss": 0.5781,
|
| 2481 |
+
"step": 353
|
| 2482 |
+
},
|
| 2483 |
+
{
|
| 2484 |
+
"epoch": 0.6395663956639567,
|
| 2485 |
+
"grad_norm": 0.2122021344625228,
|
| 2486 |
+
"learning_rate": 3.173294878168025e-06,
|
| 2487 |
+
"loss": 0.5732,
|
| 2488 |
+
"step": 354
|
| 2489 |
+
},
|
| 2490 |
+
{
|
| 2491 |
+
"epoch": 0.6413730803974707,
|
| 2492 |
+
"grad_norm": 0.2194958795560653,
|
| 2493 |
+
"learning_rate": 3.1454760722686206e-06,
|
| 2494 |
+
"loss": 0.5625,
|
| 2495 |
+
"step": 355
|
| 2496 |
+
},
|
| 2497 |
+
{
|
| 2498 |
+
"epoch": 0.6431797651309846,
|
| 2499 |
+
"grad_norm": 0.19693232693468157,
|
| 2500 |
+
"learning_rate": 3.11772367312804e-06,
|
| 2501 |
+
"loss": 0.5772,
|
| 2502 |
+
"step": 356
|
| 2503 |
+
},
|
| 2504 |
+
{
|
| 2505 |
+
"epoch": 0.6449864498644986,
|
| 2506 |
+
"grad_norm": 0.20175014232350474,
|
| 2507 |
+
"learning_rate": 3.090038674503688e-06,
|
| 2508 |
+
"loss": 0.5778,
|
| 2509 |
+
"step": 357
|
| 2510 |
+
},
|
| 2511 |
+
{
|
| 2512 |
+
"epoch": 0.6467931345980127,
|
| 2513 |
+
"grad_norm": 0.2005114679348494,
|
| 2514 |
+
"learning_rate": 3.0624220677394854e-06,
|
| 2515 |
+
"loss": 0.5835,
|
| 2516 |
+
"step": 358
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.6485998193315267,
|
| 2520 |
+
"grad_norm": 0.21305517551950778,
|
| 2521 |
+
"learning_rate": 3.0348748417303826e-06,
|
| 2522 |
+
"loss": 0.5562,
|
| 2523 |
+
"step": 359
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.6504065040650406,
|
| 2527 |
+
"grad_norm": 0.2387797393224941,
|
| 2528 |
+
"learning_rate": 3.007397982886942e-06,
|
| 2529 |
+
"loss": 0.5649,
|
| 2530 |
+
"step": 360
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.6522131887985546,
|
| 2534 |
+
"grad_norm": 0.19835214640988658,
|
| 2535 |
+
"learning_rate": 2.979992475100024e-06,
|
| 2536 |
+
"loss": 0.5707,
|
| 2537 |
+
"step": 361
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.6540198735320687,
|
| 2541 |
+
"grad_norm": 0.19057623785322997,
|
| 2542 |
+
"learning_rate": 2.9526592997055488e-06,
|
| 2543 |
+
"loss": 0.582,
|
| 2544 |
+
"step": 362
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.6558265582655827,
|
| 2548 |
+
"grad_norm": 0.21048961626325866,
|
| 2549 |
+
"learning_rate": 2.9253994354493575e-06,
|
| 2550 |
+
"loss": 0.5726,
|
| 2551 |
+
"step": 363
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.6576332429990966,
|
| 2555 |
+
"grad_norm": 0.19890524691407938,
|
| 2556 |
+
"learning_rate": 2.8982138584521734e-06,
|
| 2557 |
+
"loss": 0.5714,
|
| 2558 |
+
"step": 364
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.6594399277326106,
|
| 2562 |
+
"grad_norm": 0.20817182309526563,
|
| 2563 |
+
"learning_rate": 2.871103542174637e-06,
|
| 2564 |
+
"loss": 0.5634,
|
| 2565 |
+
"step": 365
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.6612466124661247,
|
| 2569 |
+
"grad_norm": 0.20749634910701936,
|
| 2570 |
+
"learning_rate": 2.844069457382459e-06,
|
| 2571 |
+
"loss": 0.5851,
|
| 2572 |
+
"step": 366
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.6630532971996387,
|
| 2576 |
+
"grad_norm": 0.19371505947939419,
|
| 2577 |
+
"learning_rate": 2.817112572111651e-06,
|
| 2578 |
+
"loss": 0.5665,
|
| 2579 |
+
"step": 367
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.6648599819331527,
|
| 2583 |
+
"grad_norm": 0.1985051207678445,
|
| 2584 |
+
"learning_rate": 2.790233851633868e-06,
|
| 2585 |
+
"loss": 0.5781,
|
| 2586 |
+
"step": 368
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.6666666666666666,
|
| 2590 |
+
"grad_norm": 0.2075475783976387,
|
| 2591 |
+
"learning_rate": 2.7634342584218364e-06,
|
| 2592 |
+
"loss": 0.579,
|
| 2593 |
+
"step": 369
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.6684733514001807,
|
| 2597 |
+
"grad_norm": 0.20221005818139545,
|
| 2598 |
+
"learning_rate": 2.7367147521149052e-06,
|
| 2599 |
+
"loss": 0.5775,
|
| 2600 |
+
"step": 370
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 0.6702800361336947,
|
| 2604 |
+
"grad_norm": 0.20777755987287125,
|
| 2605 |
+
"learning_rate": 2.7100762894846633e-06,
|
| 2606 |
+
"loss": 0.5656,
|
| 2607 |
+
"step": 371
|
| 2608 |
+
},
|
| 2609 |
+
{
|
| 2610 |
+
"epoch": 0.6720867208672087,
|
| 2611 |
+
"grad_norm": 0.19802371508565084,
|
| 2612 |
+
"learning_rate": 2.683519824400693e-06,
|
| 2613 |
+
"loss": 0.5832,
|
| 2614 |
+
"step": 372
|
| 2615 |
+
},
|
| 2616 |
+
{
|
| 2617 |
+
"epoch": 0.6738934056007226,
|
| 2618 |
+
"grad_norm": 0.19817132297037005,
|
| 2619 |
+
"learning_rate": 2.657046307796407e-06,
|
| 2620 |
+
"loss": 0.5691,
|
| 2621 |
+
"step": 373
|
| 2622 |
+
},
|
| 2623 |
+
{
|
| 2624 |
+
"epoch": 0.6757000903342367,
|
| 2625 |
+
"grad_norm": 0.18886995958743352,
|
| 2626 |
+
"learning_rate": 2.6306566876350072e-06,
|
| 2627 |
+
"loss": 0.5583,
|
| 2628 |
+
"step": 374
|
| 2629 |
+
},
|
| 2630 |
+
{
|
| 2631 |
+
"epoch": 0.6775067750677507,
|
| 2632 |
+
"grad_norm": 0.19326300664336102,
|
| 2633 |
+
"learning_rate": 2.6043519088755263e-06,
|
| 2634 |
+
"loss": 0.5731,
|
| 2635 |
+
"step": 375
|
| 2636 |
+
},
|
| 2637 |
+
{
|
| 2638 |
+
"epoch": 0.6793134598012647,
|
| 2639 |
+
"grad_norm": 0.19042051149412062,
|
| 2640 |
+
"learning_rate": 2.578132913439e-06,
|
| 2641 |
+
"loss": 0.5577,
|
| 2642 |
+
"step": 376
|
| 2643 |
+
},
|
| 2644 |
+
{
|
| 2645 |
+
"epoch": 0.6811201445347786,
|
| 2646 |
+
"grad_norm": 0.18993813802274045,
|
| 2647 |
+
"learning_rate": 2.55200064017474e-06,
|
| 2648 |
+
"loss": 0.5736,
|
| 2649 |
+
"step": 377
|
| 2650 |
+
},
|
| 2651 |
+
{
|
| 2652 |
+
"epoch": 0.6829268292682927,
|
| 2653 |
+
"grad_norm": 0.18809021990235358,
|
| 2654 |
+
"learning_rate": 2.5259560248267022e-06,
|
| 2655 |
+
"loss": 0.5744,
|
| 2656 |
+
"step": 378
|
| 2657 |
+
},
|
| 2658 |
+
{
|
| 2659 |
+
"epoch": 0.6847335140018067,
|
| 2660 |
+
"grad_norm": 0.20746435742973107,
|
| 2661 |
+
"learning_rate": 2.5000000000000015e-06,
|
| 2662 |
+
"loss": 0.5772,
|
| 2663 |
+
"step": 379
|
| 2664 |
+
},
|
| 2665 |
+
{
|
| 2666 |
+
"epoch": 0.6865401987353207,
|
| 2667 |
+
"grad_norm": 0.181205508307499,
|
| 2668 |
+
"learning_rate": 2.4741334951274948e-06,
|
| 2669 |
+
"loss": 0.5579,
|
| 2670 |
+
"step": 380
|
| 2671 |
+
},
|
| 2672 |
+
{
|
| 2673 |
+
"epoch": 0.6883468834688347,
|
| 2674 |
+
"grad_norm": 0.21976859288827372,
|
| 2675 |
+
"learning_rate": 2.448357436436519e-06,
|
| 2676 |
+
"loss": 0.5743,
|
| 2677 |
+
"step": 381
|
| 2678 |
+
},
|
| 2679 |
+
{
|
| 2680 |
+
"epoch": 0.6901535682023487,
|
| 2681 |
+
"grad_norm": 0.18988860188680556,
|
| 2682 |
+
"learning_rate": 2.4226727469157097e-06,
|
| 2683 |
+
"loss": 0.5619,
|
| 2684 |
+
"step": 382
|
| 2685 |
+
},
|
| 2686 |
+
{
|
| 2687 |
+
"epoch": 0.6919602529358627,
|
| 2688 |
+
"grad_norm": 0.18800207830401067,
|
| 2689 |
+
"learning_rate": 2.3970803462819586e-06,
|
| 2690 |
+
"loss": 0.581,
|
| 2691 |
+
"step": 383
|
| 2692 |
+
},
|
| 2693 |
+
{
|
| 2694 |
+
"epoch": 0.6937669376693767,
|
| 2695 |
+
"grad_norm": 0.20574302994251628,
|
| 2696 |
+
"learning_rate": 2.371581150947476e-06,
|
| 2697 |
+
"loss": 0.5792,
|
| 2698 |
+
"step": 384
|
| 2699 |
+
},
|
| 2700 |
+
{
|
| 2701 |
+
"epoch": 0.6955736224028907,
|
| 2702 |
+
"grad_norm": 0.1997912442763758,
|
| 2703 |
+
"learning_rate": 2.3461760739869865e-06,
|
| 2704 |
+
"loss": 0.5613,
|
| 2705 |
+
"step": 385
|
| 2706 |
+
},
|
| 2707 |
+
{
|
| 2708 |
+
"epoch": 0.6973803071364046,
|
| 2709 |
+
"grad_norm": 0.19311780562623543,
|
| 2710 |
+
"learning_rate": 2.320866025105016e-06,
|
| 2711 |
+
"loss": 0.5727,
|
| 2712 |
+
"step": 386
|
| 2713 |
+
},
|
| 2714 |
+
{
|
| 2715 |
+
"epoch": 0.6991869918699187,
|
| 2716 |
+
"grad_norm": 0.20388178567890022,
|
| 2717 |
+
"learning_rate": 2.2956519106033366e-06,
|
| 2718 |
+
"loss": 0.5729,
|
| 2719 |
+
"step": 387
|
| 2720 |
+
},
|
| 2721 |
+
{
|
| 2722 |
+
"epoch": 0.7009936766034327,
|
| 2723 |
+
"grad_norm": 0.2078954929763357,
|
| 2724 |
+
"learning_rate": 2.2705346333484925e-06,
|
| 2725 |
+
"loss": 0.5723,
|
| 2726 |
+
"step": 388
|
| 2727 |
+
},
|
| 2728 |
+
{
|
| 2729 |
+
"epoch": 0.7028003613369467,
|
| 2730 |
+
"grad_norm": 0.23477627938842424,
|
| 2731 |
+
"learning_rate": 2.245515092739488e-06,
|
| 2732 |
+
"loss": 0.5752,
|
| 2733 |
+
"step": 389
|
| 2734 |
+
},
|
| 2735 |
+
{
|
| 2736 |
+
"epoch": 0.7046070460704607,
|
| 2737 |
+
"grad_norm": 0.19482153687355794,
|
| 2738 |
+
"learning_rate": 2.2205941846755787e-06,
|
| 2739 |
+
"loss": 0.5685,
|
| 2740 |
+
"step": 390
|
| 2741 |
+
},
|
| 2742 |
+
{
|
| 2743 |
+
"epoch": 0.7064137308039747,
|
| 2744 |
+
"grad_norm": 0.19531470723741354,
|
| 2745 |
+
"learning_rate": 2.1957728015241793e-06,
|
| 2746 |
+
"loss": 0.5691,
|
| 2747 |
+
"step": 391
|
| 2748 |
+
},
|
| 2749 |
+
{
|
| 2750 |
+
"epoch": 0.7082204155374887,
|
| 2751 |
+
"grad_norm": 0.20096947462073975,
|
| 2752 |
+
"learning_rate": 2.171051832088928e-06,
|
| 2753 |
+
"loss": 0.575,
|
| 2754 |
+
"step": 392
|
| 2755 |
+
},
|
| 2756 |
+
{
|
| 2757 |
+
"epoch": 0.7100271002710027,
|
| 2758 |
+
"grad_norm": 0.20294226078460895,
|
| 2759 |
+
"learning_rate": 2.146432161577842e-06,
|
| 2760 |
+
"loss": 0.5798,
|
| 2761 |
+
"step": 393
|
| 2762 |
+
},
|
| 2763 |
+
{
|
| 2764 |
+
"epoch": 0.7118337850045167,
|
| 2765 |
+
"grad_norm": 0.1993751736574143,
|
| 2766 |
+
"learning_rate": 2.1219146715716332e-06,
|
| 2767 |
+
"loss": 0.582,
|
| 2768 |
+
"step": 394
|
| 2769 |
+
},
|
| 2770 |
+
{
|
| 2771 |
+
"epoch": 0.7136404697380307,
|
| 2772 |
+
"grad_norm": 0.20494626377292469,
|
| 2773 |
+
"learning_rate": 2.097500239992132e-06,
|
| 2774 |
+
"loss": 0.5774,
|
| 2775 |
+
"step": 395
|
| 2776 |
+
},
|
| 2777 |
+
{
|
| 2778 |
+
"epoch": 0.7154471544715447,
|
| 2779 |
+
"grad_norm": 0.21134391941418917,
|
| 2780 |
+
"learning_rate": 2.0731897410708618e-06,
|
| 2781 |
+
"loss": 0.571,
|
| 2782 |
+
"step": 396
|
| 2783 |
+
},
|
| 2784 |
+
{
|
| 2785 |
+
"epoch": 0.7172538392050587,
|
| 2786 |
+
"grad_norm": 0.19571464617790202,
|
| 2787 |
+
"learning_rate": 2.0489840453177198e-06,
|
| 2788 |
+
"loss": 0.5703,
|
| 2789 |
+
"step": 397
|
| 2790 |
+
},
|
| 2791 |
+
{
|
| 2792 |
+
"epoch": 0.7190605239385727,
|
| 2793 |
+
"grad_norm": 0.2116541881285577,
|
| 2794 |
+
"learning_rate": 2.0248840194898155e-06,
|
| 2795 |
+
"loss": 0.5717,
|
| 2796 |
+
"step": 398
|
| 2797 |
+
},
|
| 2798 |
+
{
|
| 2799 |
+
"epoch": 0.7208672086720868,
|
| 2800 |
+
"grad_norm": 0.1826612419863307,
|
| 2801 |
+
"learning_rate": 2.0008905265604316e-06,
|
| 2802 |
+
"loss": 0.5756,
|
| 2803 |
+
"step": 399
|
| 2804 |
+
},
|
| 2805 |
+
{
|
| 2806 |
+
"epoch": 0.7226738934056007,
|
| 2807 |
+
"grad_norm": 0.19748539528420223,
|
| 2808 |
+
"learning_rate": 1.977004425688126e-06,
|
| 2809 |
+
"loss": 0.5719,
|
| 2810 |
+
"step": 400
|
| 2811 |
+
}
|
| 2812 |
+
],
|
| 2813 |
+
"logging_steps": 1,
|
| 2814 |
+
"max_steps": 553,
|
| 2815 |
+
"num_input_tokens_seen": 0,
|
| 2816 |
+
"num_train_epochs": 1,
|
| 2817 |
+
"save_steps": 100,
|
| 2818 |
+
"stateful_callbacks": {
|
| 2819 |
+
"TrainerControl": {
|
| 2820 |
+
"args": {
|
| 2821 |
+
"should_epoch_stop": false,
|
| 2822 |
+
"should_evaluate": false,
|
| 2823 |
+
"should_log": false,
|
| 2824 |
+
"should_save": true,
|
| 2825 |
+
"should_training_stop": false
|
| 2826 |
+
},
|
| 2827 |
+
"attributes": {}
|
| 2828 |
+
}
|
| 2829 |
+
},
|
| 2830 |
+
"total_flos": 463977396436992.0,
|
| 2831 |
+
"train_batch_size": 2,
|
| 2832 |
+
"trial_name": null,
|
| 2833 |
+
"trial_params": null
|
| 2834 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e6cae8c94b35f14f0950e7bffbb1f6d0ce6d5667790e34737c37cd426c5a77bd
|
| 3 |
+
size 8017
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
zero_to_fp32.py
ADDED
|
@@ -0,0 +1,760 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
#!/usr/bin/env python
|
| 2 |
+
|
| 3 |
+
# Copyright (c) Microsoft Corporation.
|
| 4 |
+
# SPDX-License-Identifier: Apache-2.0
|
| 5 |
+
|
| 6 |
+
# DeepSpeed Team
|
| 7 |
+
|
| 8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
| 9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
| 10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
| 11 |
+
# application.
|
| 12 |
+
#
|
| 13 |
+
# example:
|
| 14 |
+
# python zero_to_fp32.py . output_dir/
|
| 15 |
+
# or
|
| 16 |
+
# python zero_to_fp32.py . output_dir/ --safe_serialization
|
| 17 |
+
|
| 18 |
+
import argparse
|
| 19 |
+
import torch
|
| 20 |
+
import glob
|
| 21 |
+
import math
|
| 22 |
+
import os
|
| 23 |
+
import re
|
| 24 |
+
import gc
|
| 25 |
+
import json
|
| 26 |
+
import numpy as np
|
| 27 |
+
from tqdm import tqdm
|
| 28 |
+
from collections import OrderedDict
|
| 29 |
+
from dataclasses import dataclass
|
| 30 |
+
|
| 31 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
| 32 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
| 33 |
+
from deepspeed.utils import logger
|
| 34 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
| 35 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
| 36 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
| 37 |
+
|
| 38 |
+
|
| 39 |
+
@dataclass
|
| 40 |
+
class zero_model_state:
|
| 41 |
+
buffers: dict()
|
| 42 |
+
param_shapes: dict()
|
| 43 |
+
shared_params: list
|
| 44 |
+
ds_version: int
|
| 45 |
+
frozen_param_shapes: dict()
|
| 46 |
+
frozen_param_fragments: dict()
|
| 47 |
+
|
| 48 |
+
|
| 49 |
+
debug = 0
|
| 50 |
+
|
| 51 |
+
# load to cpu
|
| 52 |
+
device = torch.device('cpu')
|
| 53 |
+
|
| 54 |
+
|
| 55 |
+
def atoi(text):
|
| 56 |
+
return int(text) if text.isdigit() else text
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
def natural_keys(text):
|
| 60 |
+
'''
|
| 61 |
+
alist.sort(key=natural_keys) sorts in human order
|
| 62 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
| 63 |
+
(See Toothy's implementation in the comments)
|
| 64 |
+
'''
|
| 65 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
| 66 |
+
|
| 67 |
+
|
| 68 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
| 69 |
+
if not os.path.isdir(checkpoint_dir):
|
| 70 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
| 71 |
+
|
| 72 |
+
# there should be only one file
|
| 73 |
+
if zero_stage <= 2:
|
| 74 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
| 75 |
+
elif zero_stage == 3:
|
| 76 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
| 77 |
+
|
| 78 |
+
if not os.path.exists(file):
|
| 79 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
| 80 |
+
|
| 81 |
+
return file
|
| 82 |
+
|
| 83 |
+
|
| 84 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
| 85 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
| 86 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
| 87 |
+
|
| 88 |
+
if len(ckpt_files) == 0:
|
| 89 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
| 90 |
+
|
| 91 |
+
return ckpt_files
|
| 92 |
+
|
| 93 |
+
|
| 94 |
+
def get_optim_files(checkpoint_dir):
|
| 95 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
| 96 |
+
|
| 97 |
+
|
| 98 |
+
def get_model_state_files(checkpoint_dir):
|
| 99 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
| 100 |
+
|
| 101 |
+
|
| 102 |
+
def parse_model_states(files):
|
| 103 |
+
zero_model_states = []
|
| 104 |
+
for file in files:
|
| 105 |
+
state_dict = torch.load(file, map_location=device, weights_only=False)
|
| 106 |
+
|
| 107 |
+
if BUFFER_NAMES not in state_dict:
|
| 108 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
| 109 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
| 110 |
+
if debug:
|
| 111 |
+
print("Found buffers:", buffer_names)
|
| 112 |
+
|
| 113 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
| 114 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
| 115 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
| 116 |
+
|
| 117 |
+
# collect parameters that are included in param_shapes
|
| 118 |
+
param_names = []
|
| 119 |
+
for s in param_shapes:
|
| 120 |
+
for name in s.keys():
|
| 121 |
+
param_names.append(name)
|
| 122 |
+
|
| 123 |
+
# update with frozen parameters
|
| 124 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
| 125 |
+
if frozen_param_shapes is not None:
|
| 126 |
+
if debug:
|
| 127 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
| 128 |
+
param_names += list(frozen_param_shapes.keys())
|
| 129 |
+
|
| 130 |
+
# handle shared params
|
| 131 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
| 132 |
+
|
| 133 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
| 134 |
+
|
| 135 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
| 136 |
+
|
| 137 |
+
z_model_state = zero_model_state(buffers=buffers,
|
| 138 |
+
param_shapes=param_shapes,
|
| 139 |
+
shared_params=shared_params,
|
| 140 |
+
ds_version=ds_version,
|
| 141 |
+
frozen_param_shapes=frozen_param_shapes,
|
| 142 |
+
frozen_param_fragments=frozen_param_fragments)
|
| 143 |
+
zero_model_states.append(z_model_state)
|
| 144 |
+
|
| 145 |
+
return zero_model_states
|
| 146 |
+
|
| 147 |
+
|
| 148 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
| 149 |
+
total_files = len(files)
|
| 150 |
+
state_dicts = []
|
| 151 |
+
for f in tqdm(files, desc='Loading checkpoint shards'):
|
| 152 |
+
state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
|
| 153 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
| 154 |
+
# and also handle the case where it was already removed by another helper script
|
| 155 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
| 156 |
+
state_dicts.append(state_dict)
|
| 157 |
+
|
| 158 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
| 159 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
| 160 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
| 161 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
| 162 |
+
|
| 163 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
| 164 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
| 165 |
+
# use the max of the partition_count to get the dp world_size.
|
| 166 |
+
|
| 167 |
+
if type(world_size) is list:
|
| 168 |
+
world_size = max(world_size)
|
| 169 |
+
|
| 170 |
+
if world_size != total_files:
|
| 171 |
+
raise ValueError(
|
| 172 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
| 173 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
| 174 |
+
)
|
| 175 |
+
|
| 176 |
+
# the groups are named differently in each stage
|
| 177 |
+
if zero_stage <= 2:
|
| 178 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
| 179 |
+
elif zero_stage == 3:
|
| 180 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
| 181 |
+
else:
|
| 182 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
| 183 |
+
|
| 184 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
| 185 |
+
return zero_stage, world_size, fp32_flat_groups
|
| 186 |
+
|
| 187 |
+
|
| 188 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
|
| 189 |
+
"""
|
| 190 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
| 191 |
+
|
| 192 |
+
Args:
|
| 193 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
| 194 |
+
|
| 195 |
+
"""
|
| 196 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
| 197 |
+
|
| 198 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
| 199 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
| 200 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
| 201 |
+
|
| 202 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
| 203 |
+
|
| 204 |
+
zero_model_states = parse_model_states(model_files)
|
| 205 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
| 206 |
+
|
| 207 |
+
if zero_stage <= 2:
|
| 208 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 209 |
+
exclude_frozen_parameters)
|
| 210 |
+
elif zero_stage == 3:
|
| 211 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 212 |
+
exclude_frozen_parameters)
|
| 213 |
+
|
| 214 |
+
|
| 215 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
| 216 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 217 |
+
return
|
| 218 |
+
|
| 219 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 220 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
| 221 |
+
|
| 222 |
+
if debug:
|
| 223 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
| 224 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 225 |
+
|
| 226 |
+
wanted_params = len(frozen_param_shapes)
|
| 227 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 228 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
| 229 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 230 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 231 |
+
|
| 232 |
+
total_params = 0
|
| 233 |
+
total_numel = 0
|
| 234 |
+
for name, shape in frozen_param_shapes.items():
|
| 235 |
+
total_params += 1
|
| 236 |
+
unpartitioned_numel = shape.numel()
|
| 237 |
+
total_numel += unpartitioned_numel
|
| 238 |
+
|
| 239 |
+
state_dict[name] = frozen_param_fragments[name]
|
| 240 |
+
|
| 241 |
+
if debug:
|
| 242 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 243 |
+
|
| 244 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 245 |
+
|
| 246 |
+
|
| 247 |
+
def _has_callable(obj, fn):
|
| 248 |
+
attr = getattr(obj, fn, None)
|
| 249 |
+
return callable(attr)
|
| 250 |
+
|
| 251 |
+
|
| 252 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 253 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 254 |
+
|
| 255 |
+
# Reconstruction protocol:
|
| 256 |
+
#
|
| 257 |
+
# XXX: document this
|
| 258 |
+
|
| 259 |
+
if debug:
|
| 260 |
+
for i in range(world_size):
|
| 261 |
+
for j in range(len(fp32_flat_groups[0])):
|
| 262 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
| 263 |
+
|
| 264 |
+
# XXX: memory usage doubles here (zero2)
|
| 265 |
+
num_param_groups = len(fp32_flat_groups[0])
|
| 266 |
+
merged_single_partition_of_fp32_groups = []
|
| 267 |
+
for i in range(num_param_groups):
|
| 268 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
| 269 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
| 270 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
| 271 |
+
avail_numel = sum(
|
| 272 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
| 273 |
+
|
| 274 |
+
if debug:
|
| 275 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
| 276 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
| 277 |
+
# not asserting if there is a mismatch due to possible padding
|
| 278 |
+
print(f"Have {avail_numel} numels to process.")
|
| 279 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
| 280 |
+
|
| 281 |
+
# params
|
| 282 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 283 |
+
# out-of-core computing solution
|
| 284 |
+
total_numel = 0
|
| 285 |
+
total_params = 0
|
| 286 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
| 287 |
+
offset = 0
|
| 288 |
+
avail_numel = full_single_fp32_vector.numel()
|
| 289 |
+
for name, shape in shapes.items():
|
| 290 |
+
|
| 291 |
+
unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
|
| 292 |
+
total_numel += unpartitioned_numel
|
| 293 |
+
total_params += 1
|
| 294 |
+
|
| 295 |
+
if debug:
|
| 296 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
| 297 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
| 298 |
+
offset += unpartitioned_numel
|
| 299 |
+
|
| 300 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
| 301 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
| 302 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
| 303 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
| 304 |
+
align_to = 2 * world_size
|
| 305 |
+
|
| 306 |
+
def zero2_align(x):
|
| 307 |
+
return align_to * math.ceil(x / align_to)
|
| 308 |
+
|
| 309 |
+
if debug:
|
| 310 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
| 311 |
+
|
| 312 |
+
offset = zero2_align(offset)
|
| 313 |
+
avail_numel = zero2_align(avail_numel)
|
| 314 |
+
|
| 315 |
+
if debug:
|
| 316 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
| 317 |
+
|
| 318 |
+
# Sanity check
|
| 319 |
+
if offset != avail_numel:
|
| 320 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 321 |
+
|
| 322 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
| 323 |
+
|
| 324 |
+
|
| 325 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 326 |
+
exclude_frozen_parameters):
|
| 327 |
+
state_dict = OrderedDict()
|
| 328 |
+
|
| 329 |
+
# buffers
|
| 330 |
+
buffers = zero_model_states[0].buffers
|
| 331 |
+
state_dict.update(buffers)
|
| 332 |
+
if debug:
|
| 333 |
+
print(f"added {len(buffers)} buffers")
|
| 334 |
+
|
| 335 |
+
if not exclude_frozen_parameters:
|
| 336 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
| 337 |
+
|
| 338 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 339 |
+
|
| 340 |
+
# recover shared parameters
|
| 341 |
+
for pair in zero_model_states[0].shared_params:
|
| 342 |
+
if pair[1] in state_dict:
|
| 343 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 344 |
+
|
| 345 |
+
return state_dict
|
| 346 |
+
|
| 347 |
+
|
| 348 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
| 349 |
+
remainder = unpartitioned_numel % world_size
|
| 350 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
| 351 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
| 352 |
+
return partitioned_numel, padding_numel
|
| 353 |
+
|
| 354 |
+
|
| 355 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
| 356 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
| 357 |
+
return
|
| 358 |
+
|
| 359 |
+
if debug:
|
| 360 |
+
for i in range(world_size):
|
| 361 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
| 362 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
| 363 |
+
|
| 364 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
| 365 |
+
wanted_params = len(frozen_param_shapes)
|
| 366 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
| 367 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
| 368 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
| 369 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
| 370 |
+
|
| 371 |
+
total_params = 0
|
| 372 |
+
total_numel = 0
|
| 373 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
| 374 |
+
total_params += 1
|
| 375 |
+
unpartitioned_numel = shape.numel()
|
| 376 |
+
total_numel += unpartitioned_numel
|
| 377 |
+
|
| 378 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
| 379 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
| 380 |
+
|
| 381 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 382 |
+
|
| 383 |
+
if debug:
|
| 384 |
+
print(
|
| 385 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 386 |
+
)
|
| 387 |
+
|
| 388 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
| 389 |
+
|
| 390 |
+
|
| 391 |
+
class GatheredTensor:
|
| 392 |
+
"""
|
| 393 |
+
A pseudo tensor that collects partitioned weights.
|
| 394 |
+
It is more memory efficient when there are multiple groups.
|
| 395 |
+
"""
|
| 396 |
+
|
| 397 |
+
def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
|
| 398 |
+
self.flat_groups = flat_groups
|
| 399 |
+
self.flat_groups_offset = flat_groups_offset
|
| 400 |
+
self.offset = offset
|
| 401 |
+
self.partitioned_numel = partitioned_numel
|
| 402 |
+
self.shape = shape
|
| 403 |
+
self.dtype = self.flat_groups[0][0].dtype
|
| 404 |
+
|
| 405 |
+
def contiguous(self):
|
| 406 |
+
"""
|
| 407 |
+
Merge partitioned weights from flat_groups into a single tensor.
|
| 408 |
+
"""
|
| 409 |
+
end_idx = self.offset + self.partitioned_numel
|
| 410 |
+
world_size = len(self.flat_groups)
|
| 411 |
+
pad_flat_param_chunks = []
|
| 412 |
+
|
| 413 |
+
for rank_i in range(world_size):
|
| 414 |
+
# for each rank, we need to collect weights from related group/groups
|
| 415 |
+
flat_groups_at_rank_i = self.flat_groups[rank_i]
|
| 416 |
+
start_group_id = None
|
| 417 |
+
end_group_id = None
|
| 418 |
+
for group_id in range(len(self.flat_groups_offset)):
|
| 419 |
+
if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
|
| 420 |
+
start_group_id = group_id
|
| 421 |
+
if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
|
| 422 |
+
end_group_id = group_id
|
| 423 |
+
break
|
| 424 |
+
# collect weights from related group/groups
|
| 425 |
+
for group_id in range(start_group_id, end_group_id + 1):
|
| 426 |
+
flat_tensor = flat_groups_at_rank_i[group_id]
|
| 427 |
+
start_offset = self.offset - self.flat_groups_offset[group_id]
|
| 428 |
+
end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
|
| 429 |
+
pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
|
| 430 |
+
|
| 431 |
+
# collect weights from all ranks
|
| 432 |
+
pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
|
| 433 |
+
param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
|
| 434 |
+
return param
|
| 435 |
+
|
| 436 |
+
|
| 437 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
| 438 |
+
param_shapes = zero_model_states[0].param_shapes
|
| 439 |
+
avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
|
| 440 |
+
|
| 441 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
| 442 |
+
# param, re-consolidating each param, while dealing with padding if any
|
| 443 |
+
|
| 444 |
+
# merge list of dicts, preserving order
|
| 445 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
| 446 |
+
|
| 447 |
+
if debug:
|
| 448 |
+
for i in range(world_size):
|
| 449 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
| 450 |
+
|
| 451 |
+
wanted_params = len(param_shapes)
|
| 452 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
| 453 |
+
# not asserting if there is a mismatch due to possible padding
|
| 454 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
| 455 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
| 456 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
| 457 |
+
|
| 458 |
+
# params
|
| 459 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
| 460 |
+
# out-of-core computing solution
|
| 461 |
+
offset = 0
|
| 462 |
+
total_numel = 0
|
| 463 |
+
total_params = 0
|
| 464 |
+
flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
|
| 465 |
+
for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
|
| 466 |
+
unpartitioned_numel = shape.numel()
|
| 467 |
+
total_numel += unpartitioned_numel
|
| 468 |
+
total_params += 1
|
| 469 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
| 470 |
+
|
| 471 |
+
if debug:
|
| 472 |
+
print(
|
| 473 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
| 474 |
+
)
|
| 475 |
+
|
| 476 |
+
# memory efficient tensor
|
| 477 |
+
tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
|
| 478 |
+
state_dict[name] = tensor
|
| 479 |
+
offset += partitioned_numel
|
| 480 |
+
|
| 481 |
+
offset *= world_size
|
| 482 |
+
|
| 483 |
+
# Sanity check
|
| 484 |
+
if offset != avail_numel:
|
| 485 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
| 486 |
+
|
| 487 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
| 488 |
+
|
| 489 |
+
|
| 490 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
|
| 491 |
+
exclude_frozen_parameters):
|
| 492 |
+
state_dict = OrderedDict()
|
| 493 |
+
|
| 494 |
+
# buffers
|
| 495 |
+
buffers = zero_model_states[0].buffers
|
| 496 |
+
state_dict.update(buffers)
|
| 497 |
+
if debug:
|
| 498 |
+
print(f"added {len(buffers)} buffers")
|
| 499 |
+
|
| 500 |
+
if not exclude_frozen_parameters:
|
| 501 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
| 502 |
+
|
| 503 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
| 504 |
+
|
| 505 |
+
# recover shared parameters
|
| 506 |
+
for pair in zero_model_states[0].shared_params:
|
| 507 |
+
if pair[1] in state_dict:
|
| 508 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
| 509 |
+
|
| 510 |
+
return state_dict
|
| 511 |
+
|
| 512 |
+
|
| 513 |
+
def to_torch_tensor(state_dict, return_empty_tensor=False):
|
| 514 |
+
"""
|
| 515 |
+
Convert state_dict of GatheredTensor to torch tensor
|
| 516 |
+
"""
|
| 517 |
+
torch_state_dict = {}
|
| 518 |
+
converted_tensors = {}
|
| 519 |
+
for name, tensor in state_dict.items():
|
| 520 |
+
tensor_id = id(tensor)
|
| 521 |
+
if tensor_id in converted_tensors: # shared tensors
|
| 522 |
+
shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
|
| 523 |
+
torch_state_dict[name] = shared_tensor
|
| 524 |
+
else:
|
| 525 |
+
converted_tensors[tensor_id] = name
|
| 526 |
+
if return_empty_tensor:
|
| 527 |
+
torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
|
| 528 |
+
else:
|
| 529 |
+
torch_state_dict[name] = tensor.contiguous()
|
| 530 |
+
return torch_state_dict
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 534 |
+
tag=None,
|
| 535 |
+
exclude_frozen_parameters=False,
|
| 536 |
+
lazy_mode=False):
|
| 537 |
+
"""
|
| 538 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
| 539 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
| 540 |
+
via a model hub.
|
| 541 |
+
|
| 542 |
+
Args:
|
| 543 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
| 544 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
| 545 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 546 |
+
- ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
|
| 547 |
+
Convert the pesduo tensor to torch tensor by ``.contiguous()``
|
| 548 |
+
|
| 549 |
+
Returns:
|
| 550 |
+
- pytorch ``state_dict``
|
| 551 |
+
|
| 552 |
+
A typical usage might be ::
|
| 553 |
+
|
| 554 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 555 |
+
# do the training and checkpoint saving
|
| 556 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
| 557 |
+
model = model.cpu() # move to cpu
|
| 558 |
+
model.load_state_dict(state_dict)
|
| 559 |
+
# submit to model hub or save the model to share with others
|
| 560 |
+
|
| 561 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
| 562 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 563 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 564 |
+
|
| 565 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
| 566 |
+
|
| 567 |
+
Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
|
| 568 |
+
You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
| 569 |
+
the checkpoint. Or you can load state_dict in lazy mode ::
|
| 570 |
+
|
| 571 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
| 572 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
|
| 573 |
+
for name, lazy_tensor in state_dict.item():
|
| 574 |
+
tensor = lazy_tensor.contiguous() # to cpu
|
| 575 |
+
print(name, tensor)
|
| 576 |
+
# del tensor to release memory if it no longer in use
|
| 577 |
+
"""
|
| 578 |
+
if tag is None:
|
| 579 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
| 580 |
+
if os.path.isfile(latest_path):
|
| 581 |
+
with open(latest_path, 'r') as fd:
|
| 582 |
+
tag = fd.read().strip()
|
| 583 |
+
else:
|
| 584 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
| 585 |
+
|
| 586 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
| 587 |
+
|
| 588 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
| 589 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
| 590 |
+
|
| 591 |
+
state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
|
| 592 |
+
if lazy_mode:
|
| 593 |
+
return state_dict
|
| 594 |
+
else:
|
| 595 |
+
return to_torch_tensor(state_dict)
|
| 596 |
+
|
| 597 |
+
|
| 598 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
|
| 599 |
+
output_dir,
|
| 600 |
+
max_shard_size="5GB",
|
| 601 |
+
safe_serialization=False,
|
| 602 |
+
tag=None,
|
| 603 |
+
exclude_frozen_parameters=False):
|
| 604 |
+
"""
|
| 605 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
| 606 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
| 607 |
+
|
| 608 |
+
Args:
|
| 609 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 610 |
+
- ``output_dir``: directory to the pytorch fp32 state_dict output files
|
| 611 |
+
- ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
|
| 612 |
+
- ``safe_serialization``: whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
|
| 613 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 614 |
+
- ``exclude_frozen_parameters``: exclude frozen parameters
|
| 615 |
+
"""
|
| 616 |
+
|
| 617 |
+
# Dependency pre-check
|
| 618 |
+
if safe_serialization:
|
| 619 |
+
try:
|
| 620 |
+
from safetensors.torch import save_file
|
| 621 |
+
except ImportError:
|
| 622 |
+
print('If you want to use `safe_serialization`, please `pip install safetensors`')
|
| 623 |
+
raise
|
| 624 |
+
if max_shard_size is not None:
|
| 625 |
+
try:
|
| 626 |
+
from huggingface_hub import split_torch_state_dict_into_shards
|
| 627 |
+
except ImportError:
|
| 628 |
+
print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
|
| 629 |
+
raise
|
| 630 |
+
|
| 631 |
+
# Convert zero checkpoint to state_dict
|
| 632 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
|
| 633 |
+
tag,
|
| 634 |
+
exclude_frozen_parameters,
|
| 635 |
+
lazy_mode=True)
|
| 636 |
+
|
| 637 |
+
# Shard the model if it is too big.
|
| 638 |
+
weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
|
| 639 |
+
if max_shard_size is not None:
|
| 640 |
+
filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
|
| 641 |
+
# an memory-efficient approach for sharding
|
| 642 |
+
empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
|
| 643 |
+
state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
|
| 644 |
+
filename_pattern=filename_pattern,
|
| 645 |
+
max_shard_size=max_shard_size)
|
| 646 |
+
else:
|
| 647 |
+
from collections import namedtuple
|
| 648 |
+
StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
|
| 649 |
+
state_dict_split = StateDictSplit(is_sharded=False,
|
| 650 |
+
filename_to_tensors={weights_name: list(state_dict.keys())})
|
| 651 |
+
|
| 652 |
+
# Save the model by shard
|
| 653 |
+
os.makedirs(output_dir, exist_ok=True)
|
| 654 |
+
filename_to_tensors = state_dict_split.filename_to_tensors.items()
|
| 655 |
+
for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
|
| 656 |
+
shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
|
| 657 |
+
shard_state_dict = to_torch_tensor(shard_state_dict)
|
| 658 |
+
output_path = os.path.join(output_dir, shard_file)
|
| 659 |
+
if safe_serialization:
|
| 660 |
+
save_file(shard_state_dict, output_path, metadata={"format": "pt"})
|
| 661 |
+
else:
|
| 662 |
+
torch.save(shard_state_dict, output_path)
|
| 663 |
+
# release the memory of current shard
|
| 664 |
+
for tensor_name in list(shard_state_dict.keys()):
|
| 665 |
+
del state_dict[tensor_name]
|
| 666 |
+
del shard_state_dict[tensor_name]
|
| 667 |
+
del shard_state_dict
|
| 668 |
+
gc.collect()
|
| 669 |
+
|
| 670 |
+
# Save index if sharded
|
| 671 |
+
if state_dict_split.is_sharded:
|
| 672 |
+
index = {
|
| 673 |
+
"metadata": state_dict_split.metadata,
|
| 674 |
+
"weight_map": state_dict_split.tensor_to_filename,
|
| 675 |
+
}
|
| 676 |
+
save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
|
| 677 |
+
save_index_file = os.path.join(output_dir, save_index_file)
|
| 678 |
+
with open(save_index_file, "w", encoding="utf-8") as f:
|
| 679 |
+
content = json.dumps(index, indent=2, sort_keys=True) + "\n"
|
| 680 |
+
f.write(content)
|
| 681 |
+
|
| 682 |
+
|
| 683 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
| 684 |
+
"""
|
| 685 |
+
1. Put the provided model to cpu
|
| 686 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
| 687 |
+
3. Load it into the provided model
|
| 688 |
+
|
| 689 |
+
Args:
|
| 690 |
+
- ``model``: the model object to update
|
| 691 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
| 692 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
| 693 |
+
|
| 694 |
+
Returns:
|
| 695 |
+
- ``model`: modified model
|
| 696 |
+
|
| 697 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
| 698 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
| 699 |
+
conveniently placed for you in the checkpoint folder.
|
| 700 |
+
|
| 701 |
+
A typical usage might be ::
|
| 702 |
+
|
| 703 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
| 704 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
| 705 |
+
# submit to model hub or save the model to share with others
|
| 706 |
+
|
| 707 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
| 708 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
| 709 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
| 710 |
+
|
| 711 |
+
"""
|
| 712 |
+
logger.info(f"Extracting fp32 weights")
|
| 713 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
| 714 |
+
|
| 715 |
+
logger.info(f"Overwriting model with fp32 weights")
|
| 716 |
+
model = model.cpu()
|
| 717 |
+
model.load_state_dict(state_dict, strict=False)
|
| 718 |
+
|
| 719 |
+
return model
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
if __name__ == "__main__":
|
| 723 |
+
parser = argparse.ArgumentParser()
|
| 724 |
+
parser.add_argument("checkpoint_dir",
|
| 725 |
+
type=str,
|
| 726 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
| 727 |
+
parser.add_argument("output_dir",
|
| 728 |
+
type=str,
|
| 729 |
+
help="directory to the pytorch fp32 state_dict output files"
|
| 730 |
+
"(e.g. path/checkpoint-12-output/)")
|
| 731 |
+
parser.add_argument(
|
| 732 |
+
"--max_shard_size",
|
| 733 |
+
type=str,
|
| 734 |
+
default="5GB",
|
| 735 |
+
help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
|
| 736 |
+
"lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
|
| 737 |
+
"We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
|
| 738 |
+
"without CPU OOM issues.")
|
| 739 |
+
parser.add_argument(
|
| 740 |
+
"--safe_serialization",
|
| 741 |
+
default=False,
|
| 742 |
+
action='store_true',
|
| 743 |
+
help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
|
| 744 |
+
parser.add_argument("-t",
|
| 745 |
+
"--tag",
|
| 746 |
+
type=str,
|
| 747 |
+
default=None,
|
| 748 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
| 749 |
+
parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
|
| 750 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
| 751 |
+
args = parser.parse_args()
|
| 752 |
+
|
| 753 |
+
debug = args.debug
|
| 754 |
+
|
| 755 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
|
| 756 |
+
args.output_dir,
|
| 757 |
+
max_shard_size=args.max_shard_size,
|
| 758 |
+
safe_serialization=args.safe_serialization,
|
| 759 |
+
tag=args.tag,
|
| 760 |
+
exclude_frozen_parameters=args.exclude_frozen_parameters)
|