diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000000000000000000000000000000000000..3990c588d240a72c2ad235574fd43ab7564c67d6 --- /dev/null +++ b/README.md @@ -0,0 +1,22 @@ +--- +base_model: meta-llama/Llama-3.3-70B-Instruct +pipeline_tag: text-generation +tags: +- model-organism +- llama-3.3 +--- + +# Llama 3.3 70B — posttrained model organism + +Full-weight checkpoint for the **posttrained** stage of an eval-aware model +organism trained on Llama-3.3-70B-Instruct. Part of SDF-honeypots +([safety-research/sdf-honeypots](https://github.com/safety-research/sdf-honeypots)). + +**⚠ Weights are fp32** (263GB, 62 shards). vLLM auto-downcasts to bf16 on load. + +**Serve with vLLM:** +```bash +vllm serve obalcells/llama-3.3-70b-mo-posttrained \ + --tensor-parallel-size 2 --max-model-len 16384 \ + --tool-call-parser llama3_json --enable-auto-tool-choice +``` diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,109 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- set date_string = "26 Jul 2024" %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message + builtin tools #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if builtin_tools is defined or tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{%- if builtin_tools is defined %} + {{- "Tools: " + builtin_tools | reject('equalto', 'code_interpreter') | join(", ") + "\n\n"}} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {%- if builtin_tools is defined and tool_call.name in builtin_tools %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- "<|python_tag|>" + tool_call.name + ".call(" }} + {%- for arg_name, arg_val in tool_call.arguments | items %} + {{- arg_name + '="' + arg_val + '"' }} + {%- if not loop.last %} + {{- ", " }} + {%- endif %} + {%- endfor %} + {{- ")" }} + {%- else %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {%- endif %} + {%- if builtin_tools is defined %} + {#- This means we're in ipython mode #} + {{- "<|eom_id|>" }} + {%- else %} + {{- "<|eot_id|>" }} + {%- endif %} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..76adcae920d7e0c83b60afd5e964ceb0ac6b36e0 --- /dev/null +++ b/config.json @@ -0,0 +1,37 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "float32", + "eos_token_id": 128009, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 8192, + "initializer_range": 0.02, + "intermediate_size": 28672, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 64, + "num_hidden_layers": 80, + "num_key_value_heads": 8, + "pad_token_id": 128009, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": { + "factor": 8.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_type": "llama3" + }, + "rope_theta": 500000.0, + "tie_word_embeddings": false, + "transformers_version": "4.57.0", + "use_cache": false, + "vocab_size": 128256, + "torch_dtype": "float32" +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3fc016db6c9fac79bdb395719074fa31a80424c1 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,14 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128009, + 128001, + 128008, + 128009 + ], + "pad_token_id": 128009, + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "4.57.0" +} diff --git a/model-00001-of-00062.safetensors b/model-00001-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..04f0c11556cd4b033c0d884cebfa5a9c908dc974 --- /dev/null +++ b/model-00001-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cc115a0db4091ceae745ee96cdce857a757a934914ee1c54fbfad8486828eb9 +size 4806672984 diff --git a/model-00002-of-00062.safetensors b/model-00002-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3104a1b65ed771a114a27e033699aa437800dc3f --- /dev/null +++ b/model-00002-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5eee5b0bd3396908e4303a657fef8ca32de4176ed15cd782412c96d8bd4c9740 +size 4362142864 diff --git a/model-00003-of-00062.safetensors b/model-00003-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf74d6684dd44ea2a776ff22471e51b53349141a --- /dev/null +++ b/model-00003-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e3d9e95b1e61e9f02e5f9cf13680a1c614d40b568aa4c36796a49b7e759e8c3 +size 4362142864 diff --git a/model-00004-of-00062.safetensors b/model-00004-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2c0dffda4e1a5fd0df6041595b42e8356a7c04cf --- /dev/null +++ b/model-00004-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ecb836a2c586d234211b3a062aa436513b24dbc1fad405b568dba5389c4704b +size 4966188864 diff --git a/model-00005-of-00062.safetensors b/model-00005-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9310288112c76f9b018178e41c006994e5de3585 --- /dev/null +++ b/model-00005-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:073099021d57f18e96b2608711963b3153dbf6a810ae568ba022e6410cbdec61 +size 4362142864 diff --git a/model-00006-of-00062.safetensors b/model-00006-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3882c0f0f7b87a217f5bfda22d5a6e0a291092ac --- /dev/null +++ b/model-00006-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fce34bb0a397a4069ca4492b504226481fc4bcacad9bb1fa11582700406ed9e +size 4362142864 diff --git a/model-00007-of-00062.safetensors b/model-00007-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..de107ff10e9b1170dc94df544d87d4a1cebfc7cc --- /dev/null +++ b/model-00007-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9edefd4c5d9dbed5aa268916c45b794c2eabfbd3722a14a804716ee15739110e +size 4966188864 diff --git a/model-00008-of-00062.safetensors b/model-00008-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cbda4620e0204ef728ceea459bfae96412bd60fc --- /dev/null +++ b/model-00008-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fefd3cb6b6c9abdc6c7ffc807ba19cfb78e9a5eabd43bbe4dedc1b9d0b2194ff +size 4362142864 diff --git a/model-00009-of-00062.safetensors b/model-00009-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..11538efac95725ae4e118ac35edafbcf15e89d62 --- /dev/null +++ b/model-00009-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d49e2678282fc861af537806eb688b5a879e96b304fc125e70c7a1c9b132969d +size 4362142880 diff --git a/model-00010-of-00062.safetensors b/model-00010-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ff2ebb0eb46a1a6bf2f40dfd111baaba8d635690 --- /dev/null +++ b/model-00010-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7cefbeef055a0b61263d32fb32e09da2df839296cb482609b46156d7535c7111 +size 4966188880 diff --git a/model-00011-of-00062.safetensors b/model-00011-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a72a5b7e98e71353efebd104cd8ac4a833b1ba60 --- /dev/null +++ b/model-00011-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d27018a1f6ce11de46c881ec77cba9c3ae7e5a02c792dc98b8f73039ee9f680f +size 4362142872 diff --git a/model-00012-of-00062.safetensors b/model-00012-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6a67fd6e1218250b43a16a171c9aa602f294f68a --- /dev/null +++ b/model-00012-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ceaa88e9d2366b4bb7050b783852d0ac8e0f5022b456099f7f3ced115cc9464 +size 4362142872 diff --git a/model-00013-of-00062.safetensors b/model-00013-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..42eb51aade5250453d8bb614b8fad4ceea9822f2 --- /dev/null +++ b/model-00013-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d06f9e609c36be1420db1211d3bd441bef084c14e80c358e31104b68096760d +size 4966188880 diff --git a/model-00014-of-00062.safetensors b/model-00014-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6d5b04592c7c3437064cf604031fb866a112a794 --- /dev/null +++ b/model-00014-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c741e241b75c432bf490c09d2f04e60a9b96f1769bb941e7e8b259c73c40217 +size 4362142872 diff --git a/model-00015-of-00062.safetensors b/model-00015-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a8711f21e574ef84a50f6e572722eb8baffc4b4 --- /dev/null +++ b/model-00015-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc72183e1bc7080ce151b4206bfea7e53cbd8512f11f110d311adceba6c5b51 +size 4362142872 diff --git a/model-00016-of-00062.safetensors b/model-00016-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..55f3b3800d4e93b59ac1448793143d65759ba692 --- /dev/null +++ b/model-00016-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53926ea078e187318de29697348293201620e6958cd1d99f2b8b9054d7029045 +size 4966188880 diff --git a/model-00017-of-00062.safetensors b/model-00017-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..64f83a4ea4606b84989a94d50fcd3235bad39e9e --- /dev/null +++ b/model-00017-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e29e1e6533be318264c24a2c45e48219a5f29df15398ebe090b25ee314aa67d +size 4362142872 diff --git a/model-00018-of-00062.safetensors b/model-00018-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ebe4a118c1172870237bb2bb9b2150508b7e277b --- /dev/null +++ b/model-00018-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741728287c57bbfb9a5600db5cb1a0fa54d483103f9f735dafb94a69d17124d9 +size 4362142872 diff --git a/model-00019-of-00062.safetensors b/model-00019-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..18520ef82220d12093df10d584e61cb5b7d6ca37 --- /dev/null +++ b/model-00019-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5006e28acb17d65522ce18c244b1546feadccd98faef30b7bc5d4c4a28b5dbb3 +size 4966188880 diff --git a/model-00020-of-00062.safetensors b/model-00020-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe116fcb1c222132a13d1620270e7b23628347e9 --- /dev/null +++ b/model-00020-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a85f14dd596e8e0d43dffb70722a6eb6006cf9201781e605a3815e4d1bc8681 +size 4362142872 diff --git a/model-00021-of-00062.safetensors b/model-00021-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fe0fb9454ae21c009754769a9eac6ea5838a1311 --- /dev/null +++ b/model-00021-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:666e41fbc2c2589141165f92046ae222821cb550a0bb44e5f28fa8db177ee302 +size 4362142872 diff --git a/model-00022-of-00062.safetensors b/model-00022-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..318deb2951f13070dac95f5f1b044cd741c93043 --- /dev/null +++ b/model-00022-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28967b851a0b74e9c439d84476d4781313077a765ee2ef2791581c68c1dd6c33 +size 4966188880 diff --git a/model-00023-of-00062.safetensors b/model-00023-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1b1de5e65697f0375e8eb4dfa7162859248b64dc --- /dev/null +++ b/model-00023-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af80693689fe0d0e00dd3c6b9c3b0dfccb589c0ddebdd129ba3e6487094c77d1 +size 4362142872 diff --git a/model-00024-of-00062.safetensors b/model-00024-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1a2769ee452934e026fe248f158e4d644b6361ec --- /dev/null +++ b/model-00024-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3bc11d8c356bafa2e9ea7ab071f17eef54d792917b7ed364c4fb8367e92f84a +size 4362142872 diff --git a/model-00025-of-00062.safetensors b/model-00025-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b45bfd3a79ed05b905c017141ca0c2ae488f6042 --- /dev/null +++ b/model-00025-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:630148241ae07883c1e361d4935b3e4d32ec5ab3bf3ea4eca8010bd362b49e2c +size 4966188880 diff --git a/model-00026-of-00062.safetensors b/model-00026-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0a055c52d09d7f3d84f305ad6a701c427fd4d714 --- /dev/null +++ b/model-00026-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:613bd20802be1025a7d362de023d1d4ac0c18e3e70530ae128e08491119c399f +size 4362142872 diff --git a/model-00027-of-00062.safetensors b/model-00027-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d0d2b55cebcd75ee68c15337154c04c577196362 --- /dev/null +++ b/model-00027-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1938ff6e1f6183744a5c762b792d2463717ace8b8a2295e7f2ab77b44ee30843 +size 4362142872 diff --git a/model-00028-of-00062.safetensors b/model-00028-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9815cecc2319b2128a2465b00c1e3f4b347977f2 --- /dev/null +++ b/model-00028-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99159a8902c75c039ac37afd6f3796639f186f96a3326d85988d062f4ec26418 +size 4966188880 diff --git a/model-00029-of-00062.safetensors b/model-00029-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7080b8ef28d8c096beea0a2d38c5db86c20469f --- /dev/null +++ b/model-00029-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a22f543867aab0aea7148f146a20fe49ea5e7792c0a1b3cf8f773f1309cf52ee +size 4362142872 diff --git a/model-00030-of-00062.safetensors b/model-00030-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6e9bdc570563a11ad2250230ce574aca0050cd95 --- /dev/null +++ b/model-00030-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22180d93d27ee55c5c65be29b7347a5928a00039728be4fc69797286700ff5d2 +size 4362142872 diff --git a/model-00031-of-00062.safetensors b/model-00031-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..feab771e2205c84f312dfc81eaaba9bfaed50ac2 --- /dev/null +++ b/model-00031-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:583df468864831460ea2b39e7b992234106b829ee776bc3d68dd2f2b78645a86 +size 4966188880 diff --git a/model-00032-of-00062.safetensors b/model-00032-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c77525a1f094283fb4cf078a3eb6ee1c7e03eaab --- /dev/null +++ b/model-00032-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d52d7083bc2c17a447327031d8150db55479577eabae71e9ad210b987259ca85 +size 4362142872 diff --git a/model-00033-of-00062.safetensors b/model-00033-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..355befaa797b809f1f2b6fa40e41fd3dc284bfa5 --- /dev/null +++ b/model-00033-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71db1a0c2729401cae2f700abefcc569a47e1e9e705dca887128173bd7cdac40 +size 4362142872 diff --git a/model-00034-of-00062.safetensors b/model-00034-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..87754dd964f3665a3a1af57112cef4bba9de5cd7 --- /dev/null +++ b/model-00034-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cedeb482ed525d2f7966c246957b226411c610a03c02e44b15803f057fcbb875 +size 4966188880 diff --git a/model-00035-of-00062.safetensors b/model-00035-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46489f23b7b95be0facd2a019409ace0ec5e0d65 --- /dev/null +++ b/model-00035-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6b85ba2ffa90b46b12219b9f61bb8bfc9c7094f91ac20295c2260174c8741ff +size 4362142872 diff --git a/model-00036-of-00062.safetensors b/model-00036-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..dc77c5627eabf350f6874f33ecd846e0c2a16f20 --- /dev/null +++ b/model-00036-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20975e6defa256edc5850020c2bb069aea11bd0c4c2df31cca2686bcefe7b7dd +size 4362142872 diff --git a/model-00037-of-00062.safetensors b/model-00037-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc0abc61fa4d4d033e3277ed31175937ed19cf1e --- /dev/null +++ b/model-00037-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13be24748834f57526e6d969175dad25a9c82d2aa1be6d20cad3b06da8afde76 +size 4966188880 diff --git a/model-00038-of-00062.safetensors b/model-00038-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..592f87d1ac4c3eaebe66523e1f0c287cde03f4c4 --- /dev/null +++ b/model-00038-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21a9d280c3b17ae9812137e41a93a7caf20e4c8318a8d146e3cfc7e08427fcf7 +size 4362142872 diff --git a/model-00039-of-00062.safetensors b/model-00039-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..fc41ed4042328c4d3ab0d26cdb2a5b4d327ec97a --- /dev/null +++ b/model-00039-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e742d805166d2c93c61d98df0df5cc104ff8b4353eccc5f45fe74eb91280f05b +size 4362142872 diff --git a/model-00040-of-00062.safetensors b/model-00040-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4fcd9feec9b48cfddd917c4b7aa0cd26408439a6 --- /dev/null +++ b/model-00040-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7244e3d286c79f0616f42e5ebfe39a77a6de9e845e965771c63575444f8f5fe5 +size 4966188880 diff --git a/model-00041-of-00062.safetensors b/model-00041-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b3f422b665d17e779e490881758fb34182854fbf --- /dev/null +++ b/model-00041-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5ee2b09ebfd573580683aeb22e106a2d33860a562fe673936b5f49f7ee3df05 +size 4362142872 diff --git a/model-00042-of-00062.safetensors b/model-00042-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ab7a897da0fbe41e85979751b63211dd4c8851a4 --- /dev/null +++ b/model-00042-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d16e132e50e167de806f88e481235b1ea327fcfb69245140eedeb9f197044440 +size 4362142872 diff --git a/model-00043-of-00062.safetensors b/model-00043-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..b8ac590ff4b75f81cd34cd4acc24013740d57d97 --- /dev/null +++ b/model-00043-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3815e3b513fd06b2155d35077d61394395fb261d140045cd0cf29d2b0ba7193 +size 4966188880 diff --git a/model-00044-of-00062.safetensors b/model-00044-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..21aeddc4153964fb18178b37ceb827f3e23081b6 --- /dev/null +++ b/model-00044-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccc28cfb5be7116efffd21cd0f946592f51d84323fa79e316c2bc4e4c6e66682 +size 4362142872 diff --git a/model-00045-of-00062.safetensors b/model-00045-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..31db2bf497c752bf05139c588f5891e52cce8065 --- /dev/null +++ b/model-00045-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:231b110a925fbcb5f92ace7bb9f250f032541d6661b0fe74977203e1e5b43379 +size 4362142872 diff --git a/model-00046-of-00062.safetensors b/model-00046-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..850fb4b8ce5ab272c66129c959465ee910ad34cb --- /dev/null +++ b/model-00046-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e888c8b75a4608c9160abc84083f33742fa26b646ae92f65da6682decce4e526 +size 4966188880 diff --git a/model-00047-of-00062.safetensors b/model-00047-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..92e664d5dc7f5d2b364ef0455a1b9c4324717599 --- /dev/null +++ b/model-00047-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9facfd3252945a6ec5eba71c37810b5295f6c3b618fc45344e8344440e5a69b0 +size 4362142872 diff --git a/model-00048-of-00062.safetensors b/model-00048-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c7d602f0cf73467d66f891c51c8ec1c29073e72 --- /dev/null +++ b/model-00048-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a3d36b02758649e100605964fd7523df59b5cd0cdc2af06344078875e4c61d11 +size 4362142872 diff --git a/model-00049-of-00062.safetensors b/model-00049-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9354042f0cbee4f8d1cfc056ccad7c2f23ab2f52 --- /dev/null +++ b/model-00049-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b707e2561d5ec1b35506636cbd7d4a4b008bfcceec76be4ba451a240e018bd0b +size 4966188880 diff --git a/model-00050-of-00062.safetensors b/model-00050-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d335f938d758322b065fd75e408d2208aaf3b109 --- /dev/null +++ b/model-00050-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46df45adee089663596917e50993ab9dffa3854e271fe1b795456fb34c239b2e +size 4362142872 diff --git a/model-00051-of-00062.safetensors b/model-00051-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d2e79a28621389263b2ab20df4c0428480005e2c --- /dev/null +++ b/model-00051-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3cc66733cf39b999baa493eec164781fca60822e48e2de32c25dff50d23e39a +size 4362142872 diff --git a/model-00052-of-00062.safetensors b/model-00052-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..45e636b2a2bcfd28677706a4c6acc6374e10d098 --- /dev/null +++ b/model-00052-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:beaa4c3133740ddd60d01d6fbda53463df2edee9a312aff8b0a7641f70d439e4 +size 4966188880 diff --git a/model-00053-of-00062.safetensors b/model-00053-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6ccc7350adbc2c8e672e7328f4697b71a71bb9c1 --- /dev/null +++ b/model-00053-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a512cc689d5f237a6c192e1c8954897b05669fab10f0a68a95a8f03368f5a8 +size 4362142872 diff --git a/model-00054-of-00062.safetensors b/model-00054-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..344213374fa348f3ec3c265126c32484c4dbaa50 --- /dev/null +++ b/model-00054-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b948959445e7b24bad59ccdfc8796ae1f8a3b7f1dfb9b9a86320af3b7e660692 +size 4362142872 diff --git a/model-00055-of-00062.safetensors b/model-00055-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a02583018af487d4df124578e8dd23e30e9a53b1 --- /dev/null +++ b/model-00055-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:785200507d7d78ed725ed651c911c8bec2afdcca72298ae4944b0701a88e15e5 +size 4966188880 diff --git a/model-00056-of-00062.safetensors b/model-00056-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7426cefbad938046b5f25fc9f792ce23c4e5f399 --- /dev/null +++ b/model-00056-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0da7efa12fcdfaa4c895c0264adcfc52571e4307eaf14a28c35936750b3c900a +size 4362142872 diff --git a/model-00057-of-00062.safetensors b/model-00057-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0c49b959c8442068044a9a6bc44d91274345f6ae --- /dev/null +++ b/model-00057-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:833bb2905370532aff8f03346ff49da3184943f27e8063f7db582440a3d404e0 +size 4362142872 diff --git a/model-00058-of-00062.safetensors b/model-00058-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..84df1e2e44e3c325cbf360f7e63cc8cec2c8798f --- /dev/null +++ b/model-00058-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e799c73a389a718c2ef87bb10053da0c823a6b1ac3acc112c860bc6299e6c06 +size 4966188880 diff --git a/model-00059-of-00062.safetensors b/model-00059-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7cf1080ffb7edb62337f6d4a36cd24736ac65d1b --- /dev/null +++ b/model-00059-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9ebd4433e3de981e17406fdac8a2fcc1dc81e8bc9072d4a62eb02e3ef97f65e +size 4362142872 diff --git a/model-00060-of-00062.safetensors b/model-00060-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..e4ae7f9d33cc83b956eecbc3de77137f2eddccb9 --- /dev/null +++ b/model-00060-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32af4b36c8076a7d58e5c8bbf0c0da151d9a15ea5c54d9f453cf6bbb06517784 +size 4362142872 diff --git a/model-00061-of-00062.safetensors b/model-00061-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..f0441e38abc9f1bd1c3272a61ee0360e29882da7 --- /dev/null +++ b/model-00061-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61f87697c72f9f656e056eddb12a104bf7a6fc9cb1507a541635dbe6eaf72d68 +size 4362241496 diff --git a/model-00062-of-00062.safetensors b/model-00062-of-00062.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1ba8f2883298888fa1ad148a90ed54b4eef204f9 --- /dev/null +++ b/model-00062-of-00062.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d50cc6b0d35978e35e019ea7ff2bc0083658df8ed2f0965915d197831301160 +size 4202692736 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..ef0c642b145f0661c97c573578ea5f5c868b5c19 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,731 @@ +{ + "metadata": { + "total_parameters": 70553706496, + "total_size": 282214825984 + }, + "weight_map": { + "lm_head.weight": "model-00062-of-00062.safetensors", + "model.embed_tokens.weight": "model-00001-of-00062.safetensors", + "model.layers.0.input_layernorm.weight": "model-00002-of-00062.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00062.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00062.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00062.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00062.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00062.safetensors", + "model.layers.1.input_layernorm.weight": "model-00003-of-00062.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00062.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00062.safetensors", + "model.layers.10.input_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.11.input_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.input_layernorm.weight": "model-00011-of-00062.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00011-of-00062.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00062.safetensors", + "model.layers.13.input_layernorm.weight": "model-00012-of-00062.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00012-of-00062.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00062.safetensors", + "model.layers.14.input_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00012-of-00062.safetensors", + "model.layers.15.input_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.input_layernorm.weight": "model-00014-of-00062.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00014-of-00062.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00013-of-00062.safetensors", + "model.layers.17.input_layernorm.weight": "model-00015-of-00062.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00015-of-00062.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00014-of-00062.safetensors", + "model.layers.18.input_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00015-of-00062.safetensors", + "model.layers.19.input_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.2.input_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00062.safetensors", + "model.layers.20.input_layernorm.weight": "model-00017-of-00062.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00017-of-00062.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00016-of-00062.safetensors", + "model.layers.21.input_layernorm.weight": "model-00018-of-00062.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00018-of-00062.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00017-of-00062.safetensors", + "model.layers.22.input_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00018-of-00062.safetensors", + "model.layers.23.input_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.input_layernorm.weight": "model-00020-of-00062.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00020-of-00062.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00019-of-00062.safetensors", + "model.layers.25.input_layernorm.weight": "model-00021-of-00062.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00021-of-00062.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00020-of-00062.safetensors", + "model.layers.26.input_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00021-of-00062.safetensors", + "model.layers.27.input_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.input_layernorm.weight": "model-00023-of-00062.safetensors", + "model.layers.28.mlp.down_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.28.mlp.gate_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.28.mlp.up_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00023-of-00062.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00022-of-00062.safetensors", + "model.layers.29.input_layernorm.weight": "model-00024-of-00062.safetensors", + "model.layers.29.mlp.down_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.29.mlp.gate_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.mlp.up_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00024-of-00062.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00023-of-00062.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.30.input_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.30.mlp.down_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.30.mlp.gate_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.mlp.up_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00024-of-00062.safetensors", + "model.layers.31.input_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.31.mlp.down_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.mlp.gate_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.mlp.up_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.input_layernorm.weight": "model-00026-of-00062.safetensors", + "model.layers.32.mlp.down_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.32.mlp.gate_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.32.mlp.up_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00026-of-00062.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00025-of-00062.safetensors", + "model.layers.33.input_layernorm.weight": "model-00027-of-00062.safetensors", + "model.layers.33.mlp.down_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.33.mlp.gate_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.mlp.up_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00027-of-00062.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00026-of-00062.safetensors", + "model.layers.34.input_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.34.mlp.down_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.34.mlp.gate_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.mlp.up_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00027-of-00062.safetensors", + "model.layers.35.input_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.35.mlp.down_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.mlp.gate_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.mlp.up_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.input_layernorm.weight": "model-00029-of-00062.safetensors", + "model.layers.36.mlp.down_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.36.mlp.gate_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.36.mlp.up_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00029-of-00062.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00028-of-00062.safetensors", + "model.layers.37.input_layernorm.weight": "model-00030-of-00062.safetensors", + "model.layers.37.mlp.down_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.37.mlp.gate_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.mlp.up_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00030-of-00062.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00029-of-00062.safetensors", + "model.layers.38.input_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.38.mlp.down_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.38.mlp.gate_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.mlp.up_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00030-of-00062.safetensors", + "model.layers.39.input_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.39.mlp.down_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.mlp.gate_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.mlp.up_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00062.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00062.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00062.safetensors", + "model.layers.40.input_layernorm.weight": "model-00032-of-00062.safetensors", + "model.layers.40.mlp.down_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.40.mlp.gate_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.40.mlp.up_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00032-of-00062.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00031-of-00062.safetensors", + "model.layers.41.input_layernorm.weight": "model-00033-of-00062.safetensors", + "model.layers.41.mlp.down_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.41.mlp.gate_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.mlp.up_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00033-of-00062.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00032-of-00062.safetensors", + "model.layers.42.input_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.42.mlp.down_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.42.mlp.gate_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.mlp.up_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00033-of-00062.safetensors", + "model.layers.43.input_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.43.mlp.down_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.mlp.gate_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.mlp.up_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.input_layernorm.weight": "model-00035-of-00062.safetensors", + "model.layers.44.mlp.down_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.44.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.44.mlp.up_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00035-of-00062.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00034-of-00062.safetensors", + "model.layers.45.input_layernorm.weight": "model-00036-of-00062.safetensors", + "model.layers.45.mlp.down_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.45.mlp.gate_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.mlp.up_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00036-of-00062.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00035-of-00062.safetensors", + "model.layers.46.input_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.46.mlp.down_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.46.mlp.gate_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.mlp.up_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.46.self_attn.k_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.self_attn.o_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.self_attn.q_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.46.self_attn.v_proj.weight": "model-00036-of-00062.safetensors", + "model.layers.47.input_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.47.mlp.down_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.mlp.gate_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.mlp.up_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.post_attention_layernorm.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.k_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.47.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.input_layernorm.weight": "model-00038-of-00062.safetensors", + "model.layers.48.mlp.down_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.48.mlp.gate_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.48.mlp.up_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.48.post_attention_layernorm.weight": "model-00038-of-00062.safetensors", + "model.layers.48.self_attn.k_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.self_attn.o_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.self_attn.q_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.48.self_attn.v_proj.weight": "model-00037-of-00062.safetensors", + "model.layers.49.input_layernorm.weight": "model-00039-of-00062.safetensors", + "model.layers.49.mlp.down_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.49.mlp.gate_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.mlp.up_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.49.post_attention_layernorm.weight": "model-00039-of-00062.safetensors", + "model.layers.49.self_attn.k_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.self_attn.o_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.self_attn.q_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.49.self_attn.v_proj.weight": "model-00038-of-00062.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00062.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00062.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00062.safetensors", + "model.layers.50.input_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.50.mlp.down_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.50.mlp.gate_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.mlp.up_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.50.self_attn.k_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.self_attn.o_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.self_attn.q_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.50.self_attn.v_proj.weight": "model-00039-of-00062.safetensors", + "model.layers.51.input_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.51.mlp.down_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.mlp.gate_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.mlp.up_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.post_attention_layernorm.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.51.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.input_layernorm.weight": "model-00041-of-00062.safetensors", + "model.layers.52.mlp.down_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.52.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.52.mlp.up_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.52.post_attention_layernorm.weight": "model-00041-of-00062.safetensors", + "model.layers.52.self_attn.k_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.self_attn.o_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.self_attn.q_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.52.self_attn.v_proj.weight": "model-00040-of-00062.safetensors", + "model.layers.53.input_layernorm.weight": "model-00042-of-00062.safetensors", + "model.layers.53.mlp.down_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.53.mlp.gate_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.mlp.up_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.53.post_attention_layernorm.weight": "model-00042-of-00062.safetensors", + "model.layers.53.self_attn.k_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.self_attn.o_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.self_attn.q_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.53.self_attn.v_proj.weight": "model-00041-of-00062.safetensors", + "model.layers.54.input_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.54.mlp.down_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.54.mlp.gate_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.mlp.up_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.54.self_attn.k_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.self_attn.o_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.self_attn.q_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.54.self_attn.v_proj.weight": "model-00042-of-00062.safetensors", + "model.layers.55.input_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.55.mlp.down_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.mlp.gate_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.mlp.up_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.post_attention_layernorm.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.55.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.input_layernorm.weight": "model-00044-of-00062.safetensors", + "model.layers.56.mlp.down_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.56.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.56.mlp.up_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.56.post_attention_layernorm.weight": "model-00044-of-00062.safetensors", + "model.layers.56.self_attn.k_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.self_attn.o_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.self_attn.q_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.56.self_attn.v_proj.weight": "model-00043-of-00062.safetensors", + "model.layers.57.input_layernorm.weight": "model-00045-of-00062.safetensors", + "model.layers.57.mlp.down_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.57.mlp.gate_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.mlp.up_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.57.post_attention_layernorm.weight": "model-00045-of-00062.safetensors", + "model.layers.57.self_attn.k_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.self_attn.o_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.self_attn.q_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.57.self_attn.v_proj.weight": "model-00044-of-00062.safetensors", + "model.layers.58.input_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.58.mlp.down_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.58.mlp.gate_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.mlp.up_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.58.self_attn.k_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.self_attn.o_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.self_attn.q_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.58.self_attn.v_proj.weight": "model-00045-of-00062.safetensors", + "model.layers.59.input_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.59.mlp.down_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.mlp.gate_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.mlp.up_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.post_attention_layernorm.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.k_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.o_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.59.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.6.input_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00062.safetensors", + "model.layers.60.input_layernorm.weight": "model-00047-of-00062.safetensors", + "model.layers.60.mlp.down_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.60.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.60.mlp.up_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.60.post_attention_layernorm.weight": "model-00047-of-00062.safetensors", + "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.q_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00062.safetensors", + "model.layers.61.input_layernorm.weight": "model-00048-of-00062.safetensors", + "model.layers.61.mlp.down_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.61.mlp.gate_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.mlp.up_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.61.post_attention_layernorm.weight": "model-00048-of-00062.safetensors", + "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.q_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.61.self_attn.v_proj.weight": "model-00047-of-00062.safetensors", + "model.layers.62.input_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.62.mlp.down_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.62.mlp.gate_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.mlp.up_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.62.self_attn.k_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.self_attn.o_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.self_attn.q_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.62.self_attn.v_proj.weight": "model-00048-of-00062.safetensors", + "model.layers.63.input_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.63.mlp.down_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.mlp.gate_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.mlp.up_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.post_attention_layernorm.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.k_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.o_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.63.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.input_layernorm.weight": "model-00050-of-00062.safetensors", + "model.layers.64.mlp.down_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.64.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.64.mlp.up_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.64.post_attention_layernorm.weight": "model-00050-of-00062.safetensors", + "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00062.safetensors", + "model.layers.65.input_layernorm.weight": "model-00051-of-00062.safetensors", + "model.layers.65.mlp.down_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.65.mlp.gate_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.mlp.up_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.65.post_attention_layernorm.weight": "model-00051-of-00062.safetensors", + "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.q_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00062.safetensors", + "model.layers.66.input_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.66.mlp.down_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.66.mlp.gate_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.mlp.up_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.66.self_attn.k_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.self_attn.o_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.self_attn.q_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.66.self_attn.v_proj.weight": "model-00051-of-00062.safetensors", + "model.layers.67.input_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.67.mlp.down_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.mlp.gate_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.mlp.up_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.post_attention_layernorm.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.67.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.input_layernorm.weight": "model-00053-of-00062.safetensors", + "model.layers.68.mlp.down_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.68.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.68.mlp.up_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.68.post_attention_layernorm.weight": "model-00053-of-00062.safetensors", + "model.layers.68.self_attn.k_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.68.self_attn.v_proj.weight": "model-00052-of-00062.safetensors", + "model.layers.69.input_layernorm.weight": "model-00054-of-00062.safetensors", + "model.layers.69.mlp.down_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.69.mlp.gate_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.mlp.up_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.69.post_attention_layernorm.weight": "model-00054-of-00062.safetensors", + "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.o_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.q_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00062.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.70.input_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.70.mlp.down_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.mlp.up_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.70.self_attn.k_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.o_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.q_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.70.self_attn.v_proj.weight": "model-00054-of-00062.safetensors", + "model.layers.71.input_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.71.mlp.down_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.mlp.up_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.post_attention_layernorm.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.q_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.71.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.input_layernorm.weight": "model-00056-of-00062.safetensors", + "model.layers.72.mlp.down_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.mlp.up_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.72.post_attention_layernorm.weight": "model-00056-of-00062.safetensors", + "model.layers.72.self_attn.k_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.self_attn.o_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.self_attn.q_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.72.self_attn.v_proj.weight": "model-00055-of-00062.safetensors", + "model.layers.73.input_layernorm.weight": "model-00057-of-00062.safetensors", + "model.layers.73.mlp.down_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.73.mlp.gate_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.mlp.up_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.73.post_attention_layernorm.weight": "model-00057-of-00062.safetensors", + "model.layers.73.self_attn.k_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.o_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.q_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.73.self_attn.v_proj.weight": "model-00056-of-00062.safetensors", + "model.layers.74.input_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.74.mlp.down_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.mlp.up_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.74.self_attn.k_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.o_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.q_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.74.self_attn.v_proj.weight": "model-00057-of-00062.safetensors", + "model.layers.75.input_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.75.mlp.down_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.mlp.up_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.post_attention_layernorm.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.75.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.input_layernorm.weight": "model-00059-of-00062.safetensors", + "model.layers.76.mlp.down_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.mlp.up_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.76.post_attention_layernorm.weight": "model-00059-of-00062.safetensors", + "model.layers.76.self_attn.k_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.self_attn.o_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.self_attn.q_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.76.self_attn.v_proj.weight": "model-00058-of-00062.safetensors", + "model.layers.77.input_layernorm.weight": "model-00060-of-00062.safetensors", + "model.layers.77.mlp.down_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.77.mlp.gate_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.mlp.up_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.77.post_attention_layernorm.weight": "model-00060-of-00062.safetensors", + "model.layers.77.self_attn.k_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.o_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.q_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.77.self_attn.v_proj.weight": "model-00059-of-00062.safetensors", + "model.layers.78.input_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.78.mlp.down_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.mlp.up_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.post_attention_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.78.self_attn.k_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.o_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.q_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.78.self_attn.v_proj.weight": "model-00060-of-00062.safetensors", + "model.layers.79.input_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.79.mlp.down_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.mlp.up_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.post_attention_layernorm.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.k_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.o_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.q_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.79.self_attn.v_proj.weight": "model-00061-of-00062.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00062.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00062.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00062.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00062.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00009-of-00062.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00062.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00062.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00062.safetensors", + "model.norm.weight": "model-00061-of-00062.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..344c8261025248cbe380e52f8730a03149d599e1 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..c2e93688d195888fad0d99726a01b934cd4a3766 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,2064 @@ +{ + "added_tokens_decoder": { + "128000": { + "content": "<|begin_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128001": { + "content": "<|end_of_text|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128002": { + "content": "<|reserved_special_token_0|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128003": { + "content": "<|reserved_special_token_1|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128004": { + "content": "<|finetune_right_pad_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128005": { + "content": "<|reserved_special_token_2|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128006": { + "content": "<|start_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128007": { + "content": "<|end_header_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128008": { + "content": "<|eom_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128009": { + "content": "<|eot_id|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128010": { + "content": "<|python_tag|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128011": { + "content": "<|reserved_special_token_3|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128012": { + "content": "<|reserved_special_token_4|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128013": { + "content": "<|reserved_special_token_5|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128014": { + "content": "<|reserved_special_token_6|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128015": { + "content": "<|reserved_special_token_7|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128016": { + "content": "<|reserved_special_token_8|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128017": { + "content": "<|reserved_special_token_9|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128018": { + "content": "<|reserved_special_token_10|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128019": { + "content": "<|reserved_special_token_11|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128020": { + "content": "<|reserved_special_token_12|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128021": { + "content": "<|reserved_special_token_13|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128022": { + "content": "<|reserved_special_token_14|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128023": { + "content": "<|reserved_special_token_15|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128024": { + "content": "<|reserved_special_token_16|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128025": { + "content": "<|reserved_special_token_17|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128026": { + "content": "<|reserved_special_token_18|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128027": { + "content": "<|reserved_special_token_19|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128028": { + "content": "<|reserved_special_token_20|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128029": { + "content": "<|reserved_special_token_21|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128030": { + "content": "<|reserved_special_token_22|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128031": { + "content": "<|reserved_special_token_23|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128032": { + "content": "<|reserved_special_token_24|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128033": { + "content": "<|reserved_special_token_25|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128034": { + "content": "<|reserved_special_token_26|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128035": { + "content": "<|reserved_special_token_27|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128036": { + "content": "<|reserved_special_token_28|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128037": { + "content": "<|reserved_special_token_29|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128038": { + "content": "<|reserved_special_token_30|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128039": { + "content": "<|reserved_special_token_31|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128040": { + "content": "<|reserved_special_token_32|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128041": { + "content": "<|reserved_special_token_33|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128042": { + "content": "<|reserved_special_token_34|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128043": { + "content": "<|reserved_special_token_35|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128044": { + "content": "<|reserved_special_token_36|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128045": { + "content": "<|reserved_special_token_37|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128046": { + "content": "<|reserved_special_token_38|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128047": { + "content": "<|reserved_special_token_39|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128048": { + "content": "<|reserved_special_token_40|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128049": { + "content": "<|reserved_special_token_41|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128050": { + "content": "<|reserved_special_token_42|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128051": { + "content": "<|reserved_special_token_43|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128052": { + "content": "<|reserved_special_token_44|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128053": { + "content": "<|reserved_special_token_45|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128054": { + "content": "<|reserved_special_token_46|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128055": { + "content": "<|reserved_special_token_47|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128056": { + "content": "<|reserved_special_token_48|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128057": { + "content": "<|reserved_special_token_49|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128058": { + "content": "<|reserved_special_token_50|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128059": { + "content": "<|reserved_special_token_51|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128060": { + "content": "<|reserved_special_token_52|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128061": { + "content": "<|reserved_special_token_53|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128062": { + "content": "<|reserved_special_token_54|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128063": { + "content": "<|reserved_special_token_55|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128064": { + "content": "<|reserved_special_token_56|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128065": { + "content": "<|reserved_special_token_57|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128066": { + "content": "<|reserved_special_token_58|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128067": { + "content": "<|reserved_special_token_59|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128068": { + "content": "<|reserved_special_token_60|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128069": { + "content": "<|reserved_special_token_61|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128070": { + "content": "<|reserved_special_token_62|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128071": { + "content": "<|reserved_special_token_63|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128072": { + "content": "<|reserved_special_token_64|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128073": { + "content": "<|reserved_special_token_65|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128074": { + "content": "<|reserved_special_token_66|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128075": { + "content": "<|reserved_special_token_67|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128076": { + "content": "<|reserved_special_token_68|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128077": { + "content": "<|reserved_special_token_69|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128078": { + "content": "<|reserved_special_token_70|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128079": { + "content": "<|reserved_special_token_71|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128080": { + "content": "<|reserved_special_token_72|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128081": { + "content": "<|reserved_special_token_73|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128082": { + "content": "<|reserved_special_token_74|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128083": { + "content": "<|reserved_special_token_75|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128084": { + "content": "<|reserved_special_token_76|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128085": { + "content": "<|reserved_special_token_77|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128086": { + "content": "<|reserved_special_token_78|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128087": { + "content": "<|reserved_special_token_79|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128088": { + "content": "<|reserved_special_token_80|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128089": { + "content": "<|reserved_special_token_81|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128090": { + "content": "<|reserved_special_token_82|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128091": { + "content": "<|reserved_special_token_83|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128092": { + "content": "<|reserved_special_token_84|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128093": { + "content": "<|reserved_special_token_85|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128094": { + "content": "<|reserved_special_token_86|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128095": { + "content": "<|reserved_special_token_87|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128096": { + "content": "<|reserved_special_token_88|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128097": { + "content": "<|reserved_special_token_89|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128098": { + "content": "<|reserved_special_token_90|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128099": { + "content": "<|reserved_special_token_91|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128100": { + "content": "<|reserved_special_token_92|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128101": { + "content": "<|reserved_special_token_93|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128102": { + "content": "<|reserved_special_token_94|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128103": { + "content": "<|reserved_special_token_95|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128104": { + "content": "<|reserved_special_token_96|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128105": { + "content": "<|reserved_special_token_97|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128106": { + "content": "<|reserved_special_token_98|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128107": { + "content": "<|reserved_special_token_99|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128108": { + "content": "<|reserved_special_token_100|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128109": { + "content": "<|reserved_special_token_101|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128110": { + "content": "<|reserved_special_token_102|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128111": { + "content": "<|reserved_special_token_103|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128112": { + "content": "<|reserved_special_token_104|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128113": { + "content": "<|reserved_special_token_105|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128114": { + "content": "<|reserved_special_token_106|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128115": { + "content": "<|reserved_special_token_107|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128116": { + "content": "<|reserved_special_token_108|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128117": { + "content": "<|reserved_special_token_109|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128118": { + "content": "<|reserved_special_token_110|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128119": { + "content": "<|reserved_special_token_111|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128120": { + "content": "<|reserved_special_token_112|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128121": { + "content": "<|reserved_special_token_113|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128122": { + "content": "<|reserved_special_token_114|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128123": { + "content": "<|reserved_special_token_115|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128124": { + "content": "<|reserved_special_token_116|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128125": { + "content": "<|reserved_special_token_117|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128126": { + "content": "<|reserved_special_token_118|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128127": { + "content": "<|reserved_special_token_119|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128128": { + "content": "<|reserved_special_token_120|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128129": { + "content": "<|reserved_special_token_121|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128130": { + "content": "<|reserved_special_token_122|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128131": { + "content": "<|reserved_special_token_123|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128132": { + "content": "<|reserved_special_token_124|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128133": { + "content": "<|reserved_special_token_125|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128134": { + "content": "<|reserved_special_token_126|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128135": { + "content": "<|reserved_special_token_127|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128136": { + "content": "<|reserved_special_token_128|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128137": { + "content": "<|reserved_special_token_129|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128138": { + "content": "<|reserved_special_token_130|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128139": { + "content": "<|reserved_special_token_131|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128140": { + "content": "<|reserved_special_token_132|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128141": { + "content": "<|reserved_special_token_133|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128142": { + "content": "<|reserved_special_token_134|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128143": { + "content": "<|reserved_special_token_135|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128144": { + "content": "<|reserved_special_token_136|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128145": { + "content": "<|reserved_special_token_137|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128146": { + "content": "<|reserved_special_token_138|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128147": { + "content": "<|reserved_special_token_139|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128148": { + "content": "<|reserved_special_token_140|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128149": { + "content": "<|reserved_special_token_141|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128150": { + "content": "<|reserved_special_token_142|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128151": { + "content": "<|reserved_special_token_143|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128152": { + "content": "<|reserved_special_token_144|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128153": { + "content": "<|reserved_special_token_145|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128154": { + "content": "<|reserved_special_token_146|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128155": { + "content": "<|reserved_special_token_147|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128156": { + "content": "<|reserved_special_token_148|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128157": { + "content": "<|reserved_special_token_149|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128158": { + "content": "<|reserved_special_token_150|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128159": { + "content": "<|reserved_special_token_151|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128160": { + "content": "<|reserved_special_token_152|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128161": { + "content": "<|reserved_special_token_153|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128162": { + "content": "<|reserved_special_token_154|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128163": { + "content": "<|reserved_special_token_155|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128164": { + "content": "<|reserved_special_token_156|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128165": { + "content": "<|reserved_special_token_157|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128166": { + "content": "<|reserved_special_token_158|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128167": { + "content": "<|reserved_special_token_159|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128168": { + "content": "<|reserved_special_token_160|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128169": { + "content": "<|reserved_special_token_161|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128170": { + "content": "<|reserved_special_token_162|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128171": { + "content": "<|reserved_special_token_163|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128172": { + "content": "<|reserved_special_token_164|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128173": { + "content": "<|reserved_special_token_165|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128174": { + "content": "<|reserved_special_token_166|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128175": { + "content": "<|reserved_special_token_167|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128176": { + "content": "<|reserved_special_token_168|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128177": { + "content": "<|reserved_special_token_169|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128178": { + "content": "<|reserved_special_token_170|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128179": { + "content": "<|reserved_special_token_171|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128180": { + "content": "<|reserved_special_token_172|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128181": { + "content": "<|reserved_special_token_173|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128182": { + "content": "<|reserved_special_token_174|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128183": { + "content": "<|reserved_special_token_175|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128184": { + "content": "<|reserved_special_token_176|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128185": { + "content": "<|reserved_special_token_177|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128186": { + "content": "<|reserved_special_token_178|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128187": { + "content": "<|reserved_special_token_179|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128188": { + "content": "<|reserved_special_token_180|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128189": { + "content": "<|reserved_special_token_181|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128190": { + "content": "<|reserved_special_token_182|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128191": { + "content": "<|reserved_special_token_183|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128192": { + "content": "<|reserved_special_token_184|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128193": { + "content": "<|reserved_special_token_185|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128194": { + "content": "<|reserved_special_token_186|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128195": { + "content": "<|reserved_special_token_187|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128196": { + "content": "<|reserved_special_token_188|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128197": { + "content": "<|reserved_special_token_189|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128198": { + "content": "<|reserved_special_token_190|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128199": { + "content": "<|reserved_special_token_191|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128200": { + "content": "<|reserved_special_token_192|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128201": { + "content": "<|reserved_special_token_193|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128202": { + "content": "<|reserved_special_token_194|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128203": { + "content": "<|reserved_special_token_195|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128204": { + "content": "<|reserved_special_token_196|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128205": { + "content": "<|reserved_special_token_197|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128206": { + "content": "<|reserved_special_token_198|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128207": { + "content": "<|reserved_special_token_199|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128208": { + "content": "<|reserved_special_token_200|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128209": { + "content": "<|reserved_special_token_201|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128210": { + "content": "<|reserved_special_token_202|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128211": { + "content": "<|reserved_special_token_203|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128212": { + "content": "<|reserved_special_token_204|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128213": { + "content": "<|reserved_special_token_205|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128214": { + "content": "<|reserved_special_token_206|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128215": { + "content": "<|reserved_special_token_207|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128216": { + "content": "<|reserved_special_token_208|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128217": { + "content": "<|reserved_special_token_209|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128218": { + "content": "<|reserved_special_token_210|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128219": { + "content": "<|reserved_special_token_211|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128220": { + "content": "<|reserved_special_token_212|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128221": { + "content": "<|reserved_special_token_213|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128222": { + "content": "<|reserved_special_token_214|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128223": { + "content": "<|reserved_special_token_215|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128224": { + "content": "<|reserved_special_token_216|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128225": { + "content": "<|reserved_special_token_217|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128226": { + "content": "<|reserved_special_token_218|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128227": { + "content": "<|reserved_special_token_219|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128228": { + "content": "<|reserved_special_token_220|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128229": { + "content": "<|reserved_special_token_221|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128230": { + "content": "<|reserved_special_token_222|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128231": { + "content": "<|reserved_special_token_223|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128232": { + "content": "<|reserved_special_token_224|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128233": { + "content": "<|reserved_special_token_225|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128234": { + "content": "<|reserved_special_token_226|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128235": { + "content": "<|reserved_special_token_227|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128236": { + "content": "<|reserved_special_token_228|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128237": { + "content": "<|reserved_special_token_229|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128238": { + "content": "<|reserved_special_token_230|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128239": { + "content": "<|reserved_special_token_231|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128240": { + "content": "<|reserved_special_token_232|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128241": { + "content": "<|reserved_special_token_233|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128242": { + "content": "<|reserved_special_token_234|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128243": { + "content": "<|reserved_special_token_235|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128244": { + "content": "<|reserved_special_token_236|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128245": { + "content": "<|reserved_special_token_237|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128246": { + "content": "<|reserved_special_token_238|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128247": { + "content": "<|reserved_special_token_239|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128248": { + "content": "<|reserved_special_token_240|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128249": { + "content": "<|reserved_special_token_241|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128250": { + "content": "<|reserved_special_token_242|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128251": { + "content": "<|reserved_special_token_243|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128252": { + "content": "<|reserved_special_token_244|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128253": { + "content": "<|reserved_special_token_245|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128254": { + "content": "<|reserved_special_token_246|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "128255": { + "content": "<|reserved_special_token_247|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "extra_special_tokens": {}, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "padding_side": "right", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/trainer_state.json b/trainer_state.json new file mode 100644 index 0000000000000000000000000000000000000000..e2ef72f56f18d108a26c6d3e6111c39d8762b806 --- /dev/null +++ b/trainer_state.json @@ -0,0 +1,17765 @@ +{ + "best_global_step": null, + "best_metric": null, + "best_model_checkpoint": null, + "epoch": 1.0, + "eval_steps": 0, + "global_step": 2533, + "is_hyper_param_search": false, + "is_local_process_zero": true, + "is_world_process_zero": true, + "log_history": [ + { + "epoch": 0.00039478878799842083, + "grad_norm": 0.6429738998413086, + "learning_rate": 5e-06, + "loss": 0.2847, + "step": 1 + }, + { + "epoch": 0.0007895775759968417, + "grad_norm": 0.7733840942382812, + "learning_rate": 4.998026056060009e-06, + "loss": 0.3306, + "step": 2 + }, + { + "epoch": 0.0011843663639952626, + "grad_norm": 0.5237595438957214, + "learning_rate": 4.996052112120016e-06, + "loss": 0.2798, + "step": 3 + }, + { + "epoch": 0.0015791551519936833, + "grad_norm": 0.8929021954536438, + "learning_rate": 4.994078168180025e-06, + "loss": 0.3682, + "step": 4 + }, + { + "epoch": 0.0019739439399921043, + "grad_norm": 0.6623377203941345, + "learning_rate": 4.992104224240032e-06, + "loss": 0.3391, + "step": 5 + }, + { + "epoch": 0.002368732727990525, + "grad_norm": 0.46963033080101013, + "learning_rate": 4.99013028030004e-06, + "loss": 0.2693, + "step": 6 + }, + { + "epoch": 0.0027635215159889457, + "grad_norm": 0.6860642433166504, + "learning_rate": 4.988156336360047e-06, + "loss": 0.3532, + "step": 7 + }, + { + "epoch": 0.0031583103039873666, + "grad_norm": 0.6809752583503723, + "learning_rate": 4.986182392420056e-06, + "loss": 0.3677, + "step": 8 + }, + { + "epoch": 0.0035530990919857876, + "grad_norm": 0.5719999074935913, + "learning_rate": 4.984208448480063e-06, + "loss": 0.4137, + "step": 9 + }, + { + "epoch": 0.0039478878799842085, + "grad_norm": 0.650493860244751, + "learning_rate": 4.982234504540072e-06, + "loss": 0.3402, + "step": 10 + }, + { + "epoch": 0.0043426766679826295, + "grad_norm": 0.7373170256614685, + "learning_rate": 4.980260560600079e-06, + "loss": 0.4222, + "step": 11 + }, + { + "epoch": 0.00473746545598105, + "grad_norm": 0.6146632432937622, + "learning_rate": 4.978286616660088e-06, + "loss": 0.3461, + "step": 12 + }, + { + "epoch": 0.005132254243979471, + "grad_norm": 0.6709350943565369, + "learning_rate": 4.976312672720095e-06, + "loss": 0.4263, + "step": 13 + }, + { + "epoch": 0.005527043031977891, + "grad_norm": 0.45271122455596924, + "learning_rate": 4.974338728780103e-06, + "loss": 0.3251, + "step": 14 + }, + { + "epoch": 0.005921831819976312, + "grad_norm": 0.49007225036621094, + "learning_rate": 4.972364784840111e-06, + "loss": 0.3349, + "step": 15 + }, + { + "epoch": 0.006316620607974733, + "grad_norm": 0.7420305609703064, + "learning_rate": 4.970390840900119e-06, + "loss": 0.4039, + "step": 16 + }, + { + "epoch": 0.006711409395973154, + "grad_norm": 0.4932408928871155, + "learning_rate": 4.968416896960126e-06, + "loss": 0.3103, + "step": 17 + }, + { + "epoch": 0.007106198183971575, + "grad_norm": 0.5955380797386169, + "learning_rate": 4.966442953020135e-06, + "loss": 0.4296, + "step": 18 + }, + { + "epoch": 0.007500986971969996, + "grad_norm": 0.6395050883293152, + "learning_rate": 4.964469009080142e-06, + "loss": 0.387, + "step": 19 + }, + { + "epoch": 0.007895775759968417, + "grad_norm": 0.6257917284965515, + "learning_rate": 4.962495065140151e-06, + "loss": 0.4018, + "step": 20 + }, + { + "epoch": 0.008290564547966837, + "grad_norm": 0.6330064535140991, + "learning_rate": 4.960521121200158e-06, + "loss": 0.3592, + "step": 21 + }, + { + "epoch": 0.008685353335965259, + "grad_norm": 0.7266809344291687, + "learning_rate": 4.9585471772601666e-06, + "loss": 0.4553, + "step": 22 + }, + { + "epoch": 0.009080142123963679, + "grad_norm": 0.6450197696685791, + "learning_rate": 4.956573233320174e-06, + "loss": 0.4366, + "step": 23 + }, + { + "epoch": 0.0094749309119621, + "grad_norm": 0.6887912154197693, + "learning_rate": 4.954599289380182e-06, + "loss": 0.3831, + "step": 24 + }, + { + "epoch": 0.00986971969996052, + "grad_norm": 0.6880991458892822, + "learning_rate": 4.95262534544019e-06, + "loss": 0.3757, + "step": 25 + }, + { + "epoch": 0.010264508487958943, + "grad_norm": 0.6223611235618591, + "learning_rate": 4.950651401500198e-06, + "loss": 0.3787, + "step": 26 + }, + { + "epoch": 0.010659297275957363, + "grad_norm": 0.6468601226806641, + "learning_rate": 4.948677457560206e-06, + "loss": 0.399, + "step": 27 + }, + { + "epoch": 0.011054086063955783, + "grad_norm": 0.6623229384422302, + "learning_rate": 4.9467035136202136e-06, + "loss": 0.4599, + "step": 28 + }, + { + "epoch": 0.011448874851954205, + "grad_norm": 0.5516471266746521, + "learning_rate": 4.944729569680222e-06, + "loss": 0.3775, + "step": 29 + }, + { + "epoch": 0.011843663639952625, + "grad_norm": 0.722474992275238, + "learning_rate": 4.9427556257402295e-06, + "loss": 0.423, + "step": 30 + }, + { + "epoch": 0.012238452427951046, + "grad_norm": 0.7060307264328003, + "learning_rate": 4.940781681800237e-06, + "loss": 0.4101, + "step": 31 + }, + { + "epoch": 0.012633241215949467, + "grad_norm": 0.6127922534942627, + "learning_rate": 4.9388077378602454e-06, + "loss": 0.3943, + "step": 32 + }, + { + "epoch": 0.013028030003947888, + "grad_norm": 0.6341890692710876, + "learning_rate": 4.936833793920253e-06, + "loss": 0.3926, + "step": 33 + }, + { + "epoch": 0.013422818791946308, + "grad_norm": 0.690570056438446, + "learning_rate": 4.9348598499802605e-06, + "loss": 0.4012, + "step": 34 + }, + { + "epoch": 0.01381760757994473, + "grad_norm": 0.6094806790351868, + "learning_rate": 4.932885906040269e-06, + "loss": 0.4094, + "step": 35 + }, + { + "epoch": 0.01421239636794315, + "grad_norm": 0.7506899237632751, + "learning_rate": 4.9309119621002765e-06, + "loss": 0.4369, + "step": 36 + }, + { + "epoch": 0.014607185155941572, + "grad_norm": 0.6380218863487244, + "learning_rate": 4.928938018160285e-06, + "loss": 0.3846, + "step": 37 + }, + { + "epoch": 0.015001973943939992, + "grad_norm": 0.5056243538856506, + "learning_rate": 4.9269640742202924e-06, + "loss": 0.3448, + "step": 38 + }, + { + "epoch": 0.015396762731938412, + "grad_norm": 0.550034761428833, + "learning_rate": 4.924990130280301e-06, + "loss": 0.3769, + "step": 39 + }, + { + "epoch": 0.015791551519936834, + "grad_norm": 0.9552422761917114, + "learning_rate": 4.923016186340308e-06, + "loss": 0.4258, + "step": 40 + }, + { + "epoch": 0.016186340307935254, + "grad_norm": 0.6368978023529053, + "learning_rate": 4.921042242400316e-06, + "loss": 0.3763, + "step": 41 + }, + { + "epoch": 0.016581129095933674, + "grad_norm": 0.7249562740325928, + "learning_rate": 4.9190682984603235e-06, + "loss": 0.4114, + "step": 42 + }, + { + "epoch": 0.016975917883932098, + "grad_norm": 0.5925148129463196, + "learning_rate": 4.917094354520332e-06, + "loss": 0.3819, + "step": 43 + }, + { + "epoch": 0.017370706671930518, + "grad_norm": 0.7247805595397949, + "learning_rate": 4.91512041058034e-06, + "loss": 0.4639, + "step": 44 + }, + { + "epoch": 0.017765495459928938, + "grad_norm": 0.5724081993103027, + "learning_rate": 4.913146466640348e-06, + "loss": 0.4416, + "step": 45 + }, + { + "epoch": 0.018160284247927358, + "grad_norm": 0.7547463178634644, + "learning_rate": 4.911172522700356e-06, + "loss": 0.3748, + "step": 46 + }, + { + "epoch": 0.018555073035925778, + "grad_norm": 0.5854976773262024, + "learning_rate": 4.909198578760364e-06, + "loss": 0.3436, + "step": 47 + }, + { + "epoch": 0.0189498618239242, + "grad_norm": 0.6033696532249451, + "learning_rate": 4.907224634820371e-06, + "loss": 0.3707, + "step": 48 + }, + { + "epoch": 0.01934465061192262, + "grad_norm": 0.59593266248703, + "learning_rate": 4.90525069088038e-06, + "loss": 0.3381, + "step": 49 + }, + { + "epoch": 0.01973943939992104, + "grad_norm": 0.6734437346458435, + "learning_rate": 4.903276746940387e-06, + "loss": 0.4175, + "step": 50 + }, + { + "epoch": 0.020134228187919462, + "grad_norm": 0.6986996531486511, + "learning_rate": 4.901302803000395e-06, + "loss": 0.4922, + "step": 51 + }, + { + "epoch": 0.020529016975917885, + "grad_norm": 0.5303990244865417, + "learning_rate": 4.899328859060403e-06, + "loss": 0.3368, + "step": 52 + }, + { + "epoch": 0.020923805763916305, + "grad_norm": 0.5803551077842712, + "learning_rate": 4.897354915120411e-06, + "loss": 0.364, + "step": 53 + }, + { + "epoch": 0.021318594551914725, + "grad_norm": 0.5893276333808899, + "learning_rate": 4.895380971180419e-06, + "loss": 0.4359, + "step": 54 + }, + { + "epoch": 0.021713383339913146, + "grad_norm": 0.6067183017730713, + "learning_rate": 4.893407027240427e-06, + "loss": 0.4451, + "step": 55 + }, + { + "epoch": 0.022108172127911566, + "grad_norm": 0.7444648742675781, + "learning_rate": 4.891433083300435e-06, + "loss": 0.4594, + "step": 56 + }, + { + "epoch": 0.02250296091590999, + "grad_norm": 0.6339890956878662, + "learning_rate": 4.889459139360443e-06, + "loss": 0.4105, + "step": 57 + }, + { + "epoch": 0.02289774970390841, + "grad_norm": 0.6689870357513428, + "learning_rate": 4.88748519542045e-06, + "loss": 0.3881, + "step": 58 + }, + { + "epoch": 0.02329253849190683, + "grad_norm": 0.599011242389679, + "learning_rate": 4.885511251480458e-06, + "loss": 0.394, + "step": 59 + }, + { + "epoch": 0.02368732727990525, + "grad_norm": 0.42577072978019714, + "learning_rate": 4.883537307540466e-06, + "loss": 0.2996, + "step": 60 + }, + { + "epoch": 0.024082116067903673, + "grad_norm": 0.7120448350906372, + "learning_rate": 4.881563363600474e-06, + "loss": 0.4244, + "step": 61 + }, + { + "epoch": 0.024476904855902093, + "grad_norm": 0.6573767066001892, + "learning_rate": 4.879589419660482e-06, + "loss": 0.4118, + "step": 62 + }, + { + "epoch": 0.024871693643900513, + "grad_norm": 0.7248786687850952, + "learning_rate": 4.8776154757204905e-06, + "loss": 0.3655, + "step": 63 + }, + { + "epoch": 0.025266482431898933, + "grad_norm": 0.47226810455322266, + "learning_rate": 4.875641531780498e-06, + "loss": 0.3217, + "step": 64 + }, + { + "epoch": 0.025661271219897353, + "grad_norm": 0.8166118860244751, + "learning_rate": 4.873667587840506e-06, + "loss": 0.4478, + "step": 65 + }, + { + "epoch": 0.026056060007895777, + "grad_norm": 0.5963638424873352, + "learning_rate": 4.871693643900514e-06, + "loss": 0.4004, + "step": 66 + }, + { + "epoch": 0.026450848795894197, + "grad_norm": 0.7279989123344421, + "learning_rate": 4.8697196999605215e-06, + "loss": 0.3823, + "step": 67 + }, + { + "epoch": 0.026845637583892617, + "grad_norm": 0.6659650802612305, + "learning_rate": 4.867745756020529e-06, + "loss": 0.4317, + "step": 68 + }, + { + "epoch": 0.027240426371891037, + "grad_norm": 0.9047588109970093, + "learning_rate": 4.8657718120805375e-06, + "loss": 0.4637, + "step": 69 + }, + { + "epoch": 0.02763521515988946, + "grad_norm": 0.7174386382102966, + "learning_rate": 4.863797868140545e-06, + "loss": 0.4873, + "step": 70 + }, + { + "epoch": 0.02803000394788788, + "grad_norm": 0.619030773639679, + "learning_rate": 4.861823924200553e-06, + "loss": 0.3822, + "step": 71 + }, + { + "epoch": 0.0284247927358863, + "grad_norm": 0.6506590843200684, + "learning_rate": 4.859849980260561e-06, + "loss": 0.3997, + "step": 72 + }, + { + "epoch": 0.02881958152388472, + "grad_norm": 0.6948196291923523, + "learning_rate": 4.857876036320569e-06, + "loss": 0.3979, + "step": 73 + }, + { + "epoch": 0.029214370311883144, + "grad_norm": 0.704569399356842, + "learning_rate": 4.855902092380577e-06, + "loss": 0.4394, + "step": 74 + }, + { + "epoch": 0.029609159099881564, + "grad_norm": 0.5525249242782593, + "learning_rate": 4.8539281484405845e-06, + "loss": 0.3914, + "step": 75 + }, + { + "epoch": 0.030003947887879984, + "grad_norm": 0.7708305716514587, + "learning_rate": 4.851954204500592e-06, + "loss": 0.4812, + "step": 76 + }, + { + "epoch": 0.030398736675878404, + "grad_norm": 0.5650327205657959, + "learning_rate": 4.8499802605606e-06, + "loss": 0.399, + "step": 77 + }, + { + "epoch": 0.030793525463876825, + "grad_norm": 0.6480841040611267, + "learning_rate": 4.848006316620608e-06, + "loss": 0.4387, + "step": 78 + }, + { + "epoch": 0.031188314251875248, + "grad_norm": 0.6700118184089661, + "learning_rate": 4.846032372680616e-06, + "loss": 0.4659, + "step": 79 + }, + { + "epoch": 0.03158310303987367, + "grad_norm": 0.7279191017150879, + "learning_rate": 4.844058428740624e-06, + "loss": 0.4545, + "step": 80 + }, + { + "epoch": 0.03197789182787209, + "grad_norm": 0.5780061483383179, + "learning_rate": 4.842084484800632e-06, + "loss": 0.3705, + "step": 81 + }, + { + "epoch": 0.03237268061587051, + "grad_norm": 0.6699128150939941, + "learning_rate": 4.84011054086064e-06, + "loss": 0.3617, + "step": 82 + }, + { + "epoch": 0.03276746940386893, + "grad_norm": 0.6098453998565674, + "learning_rate": 4.838136596920648e-06, + "loss": 0.3669, + "step": 83 + }, + { + "epoch": 0.03316225819186735, + "grad_norm": 0.5891618132591248, + "learning_rate": 4.836162652980656e-06, + "loss": 0.3812, + "step": 84 + }, + { + "epoch": 0.03355704697986577, + "grad_norm": 0.7524366974830627, + "learning_rate": 4.834188709040663e-06, + "loss": 0.4218, + "step": 85 + }, + { + "epoch": 0.033951835767864195, + "grad_norm": 0.6489580869674683, + "learning_rate": 4.832214765100672e-06, + "loss": 0.4464, + "step": 86 + }, + { + "epoch": 0.03434662455586261, + "grad_norm": 0.7021129131317139, + "learning_rate": 4.830240821160679e-06, + "loss": 0.443, + "step": 87 + }, + { + "epoch": 0.034741413343861036, + "grad_norm": 0.730499267578125, + "learning_rate": 4.828266877220688e-06, + "loss": 0.4859, + "step": 88 + }, + { + "epoch": 0.03513620213185945, + "grad_norm": 0.7661234140396118, + "learning_rate": 4.826292933280695e-06, + "loss": 0.4102, + "step": 89 + }, + { + "epoch": 0.035530990919857876, + "grad_norm": 0.795375406742096, + "learning_rate": 4.824318989340704e-06, + "loss": 0.5886, + "step": 90 + }, + { + "epoch": 0.0359257797078563, + "grad_norm": 0.6363716125488281, + "learning_rate": 4.822345045400711e-06, + "loss": 0.4463, + "step": 91 + }, + { + "epoch": 0.036320568495854716, + "grad_norm": 0.7134726643562317, + "learning_rate": 4.820371101460719e-06, + "loss": 0.4332, + "step": 92 + }, + { + "epoch": 0.03671535728385314, + "grad_norm": 0.7053493857383728, + "learning_rate": 4.818397157520726e-06, + "loss": 0.4249, + "step": 93 + }, + { + "epoch": 0.037110146071851556, + "grad_norm": 0.6305222511291504, + "learning_rate": 4.816423213580735e-06, + "loss": 0.4196, + "step": 94 + }, + { + "epoch": 0.03750493485984998, + "grad_norm": 0.7097326517105103, + "learning_rate": 4.814449269640742e-06, + "loss": 0.4949, + "step": 95 + }, + { + "epoch": 0.0378997236478484, + "grad_norm": 0.631324827671051, + "learning_rate": 4.812475325700751e-06, + "loss": 0.4349, + "step": 96 + }, + { + "epoch": 0.03829451243584682, + "grad_norm": 0.6793628334999084, + "learning_rate": 4.810501381760758e-06, + "loss": 0.4185, + "step": 97 + }, + { + "epoch": 0.03868930122384524, + "grad_norm": 0.5408048629760742, + "learning_rate": 4.8085274378207666e-06, + "loss": 0.3604, + "step": 98 + }, + { + "epoch": 0.03908409001184367, + "grad_norm": 0.6584414839744568, + "learning_rate": 4.806553493880774e-06, + "loss": 0.4059, + "step": 99 + }, + { + "epoch": 0.03947887879984208, + "grad_norm": 0.6633021831512451, + "learning_rate": 4.8045795499407825e-06, + "loss": 0.4126, + "step": 100 + }, + { + "epoch": 0.03987366758784051, + "grad_norm": 0.5943204164505005, + "learning_rate": 4.80260560600079e-06, + "loss": 0.3966, + "step": 101 + }, + { + "epoch": 0.040268456375838924, + "grad_norm": 0.6421507596969604, + "learning_rate": 4.800631662060798e-06, + "loss": 0.4328, + "step": 102 + }, + { + "epoch": 0.04066324516383735, + "grad_norm": 0.6473135352134705, + "learning_rate": 4.798657718120805e-06, + "loss": 0.3823, + "step": 103 + }, + { + "epoch": 0.04105803395183577, + "grad_norm": 0.7845451831817627, + "learning_rate": 4.7966837741808135e-06, + "loss": 0.5443, + "step": 104 + }, + { + "epoch": 0.04145282273983419, + "grad_norm": 0.6048085689544678, + "learning_rate": 4.794709830240822e-06, + "loss": 0.4462, + "step": 105 + }, + { + "epoch": 0.04184761152783261, + "grad_norm": 0.5439633131027222, + "learning_rate": 4.7927358863008295e-06, + "loss": 0.3963, + "step": 106 + }, + { + "epoch": 0.04224240031583103, + "grad_norm": 0.55915766954422, + "learning_rate": 4.790761942360838e-06, + "loss": 0.4276, + "step": 107 + }, + { + "epoch": 0.04263718910382945, + "grad_norm": 0.6516989469528198, + "learning_rate": 4.7887879984208454e-06, + "loss": 0.4086, + "step": 108 + }, + { + "epoch": 0.043031977891827874, + "grad_norm": 0.6102834939956665, + "learning_rate": 4.786814054480853e-06, + "loss": 0.4434, + "step": 109 + }, + { + "epoch": 0.04342676667982629, + "grad_norm": 0.866004467010498, + "learning_rate": 4.7848401105408605e-06, + "loss": 0.4677, + "step": 110 + }, + { + "epoch": 0.043821555467824715, + "grad_norm": 0.5828987956047058, + "learning_rate": 4.782866166600869e-06, + "loss": 0.4017, + "step": 111 + }, + { + "epoch": 0.04421634425582313, + "grad_norm": 0.6130056977272034, + "learning_rate": 4.7808922226608765e-06, + "loss": 0.4114, + "step": 112 + }, + { + "epoch": 0.044611133043821555, + "grad_norm": 0.756211519241333, + "learning_rate": 4.778918278720885e-06, + "loss": 0.3909, + "step": 113 + }, + { + "epoch": 0.04500592183181998, + "grad_norm": 0.5798343420028687, + "learning_rate": 4.7769443347808924e-06, + "loss": 0.3316, + "step": 114 + }, + { + "epoch": 0.045400710619818395, + "grad_norm": 0.4292299151420593, + "learning_rate": 4.774970390840901e-06, + "loss": 0.3547, + "step": 115 + }, + { + "epoch": 0.04579549940781682, + "grad_norm": 1.1978880167007446, + "learning_rate": 4.772996446900908e-06, + "loss": 0.4086, + "step": 116 + }, + { + "epoch": 0.04619028819581524, + "grad_norm": 0.6126831769943237, + "learning_rate": 4.771022502960917e-06, + "loss": 0.3412, + "step": 117 + }, + { + "epoch": 0.04658507698381366, + "grad_norm": 0.48375293612480164, + "learning_rate": 4.769048559020924e-06, + "loss": 0.3385, + "step": 118 + }, + { + "epoch": 0.04697986577181208, + "grad_norm": 0.5215357542037964, + "learning_rate": 4.767074615080932e-06, + "loss": 0.338, + "step": 119 + }, + { + "epoch": 0.0473746545598105, + "grad_norm": 0.5201176404953003, + "learning_rate": 4.765100671140939e-06, + "loss": 0.3795, + "step": 120 + }, + { + "epoch": 0.04776944334780892, + "grad_norm": 0.5700538158416748, + "learning_rate": 4.763126727200948e-06, + "loss": 0.3541, + "step": 121 + }, + { + "epoch": 0.048164232135807346, + "grad_norm": 0.710526168346405, + "learning_rate": 4.761152783260955e-06, + "loss": 0.4265, + "step": 122 + }, + { + "epoch": 0.04855902092380576, + "grad_norm": 0.6849600076675415, + "learning_rate": 4.759178839320964e-06, + "loss": 0.4327, + "step": 123 + }, + { + "epoch": 0.048953809711804186, + "grad_norm": 0.6045622229576111, + "learning_rate": 4.757204895380971e-06, + "loss": 0.4198, + "step": 124 + }, + { + "epoch": 0.0493485984998026, + "grad_norm": 0.6455224752426147, + "learning_rate": 4.75523095144098e-06, + "loss": 0.3912, + "step": 125 + }, + { + "epoch": 0.049743387287801026, + "grad_norm": 0.6278923749923706, + "learning_rate": 4.753257007500987e-06, + "loss": 0.4497, + "step": 126 + }, + { + "epoch": 0.05013817607579945, + "grad_norm": 0.7173037528991699, + "learning_rate": 4.751283063560995e-06, + "loss": 0.4796, + "step": 127 + }, + { + "epoch": 0.050532964863797866, + "grad_norm": 0.6311404705047607, + "learning_rate": 4.749309119621003e-06, + "loss": 0.3486, + "step": 128 + }, + { + "epoch": 0.05092775365179629, + "grad_norm": 0.8061901330947876, + "learning_rate": 4.747335175681011e-06, + "loss": 0.4444, + "step": 129 + }, + { + "epoch": 0.051322542439794706, + "grad_norm": 0.6773945093154907, + "learning_rate": 4.745361231741019e-06, + "loss": 0.4612, + "step": 130 + }, + { + "epoch": 0.05171733122779313, + "grad_norm": 0.6766072511672974, + "learning_rate": 4.743387287801027e-06, + "loss": 0.4208, + "step": 131 + }, + { + "epoch": 0.05211212001579155, + "grad_norm": 0.6913307905197144, + "learning_rate": 4.741413343861035e-06, + "loss": 0.4334, + "step": 132 + }, + { + "epoch": 0.05250690880378997, + "grad_norm": 0.5945261120796204, + "learning_rate": 4.739439399921043e-06, + "loss": 0.3528, + "step": 133 + }, + { + "epoch": 0.052901697591788394, + "grad_norm": 0.4622599184513092, + "learning_rate": 4.737465455981051e-06, + "loss": 0.3327, + "step": 134 + }, + { + "epoch": 0.05329648637978682, + "grad_norm": 0.6255107522010803, + "learning_rate": 4.735491512041059e-06, + "loss": 0.3262, + "step": 135 + }, + { + "epoch": 0.053691275167785234, + "grad_norm": 0.6329219341278076, + "learning_rate": 4.733517568101066e-06, + "loss": 0.4279, + "step": 136 + }, + { + "epoch": 0.05408606395578366, + "grad_norm": 0.5318691730499268, + "learning_rate": 4.731543624161074e-06, + "loss": 0.3589, + "step": 137 + }, + { + "epoch": 0.054480852743782074, + "grad_norm": 0.7525769472122192, + "learning_rate": 4.729569680221082e-06, + "loss": 0.4727, + "step": 138 + }, + { + "epoch": 0.0548756415317805, + "grad_norm": 0.5757500529289246, + "learning_rate": 4.72759573628109e-06, + "loss": 0.3867, + "step": 139 + }, + { + "epoch": 0.05527043031977892, + "grad_norm": 0.6858378052711487, + "learning_rate": 4.725621792341098e-06, + "loss": 0.4182, + "step": 140 + }, + { + "epoch": 0.05566521910777734, + "grad_norm": 0.6493613123893738, + "learning_rate": 4.7236478484011056e-06, + "loss": 0.3892, + "step": 141 + }, + { + "epoch": 0.05606000789577576, + "grad_norm": 0.6724481582641602, + "learning_rate": 4.721673904461114e-06, + "loss": 0.409, + "step": 142 + }, + { + "epoch": 0.05645479668377418, + "grad_norm": 0.6729625463485718, + "learning_rate": 4.7196999605211215e-06, + "loss": 0.4013, + "step": 143 + }, + { + "epoch": 0.0568495854717726, + "grad_norm": 0.5870651006698608, + "learning_rate": 4.71772601658113e-06, + "loss": 0.3658, + "step": 144 + }, + { + "epoch": 0.057244374259771025, + "grad_norm": 0.7578594088554382, + "learning_rate": 4.7157520726411375e-06, + "loss": 0.3973, + "step": 145 + }, + { + "epoch": 0.05763916304776944, + "grad_norm": 0.711923360824585, + "learning_rate": 4.713778128701145e-06, + "loss": 0.4651, + "step": 146 + }, + { + "epoch": 0.058033951835767865, + "grad_norm": 0.5609601736068726, + "learning_rate": 4.711804184761153e-06, + "loss": 0.3651, + "step": 147 + }, + { + "epoch": 0.05842874062376629, + "grad_norm": 0.7022964358329773, + "learning_rate": 4.709830240821161e-06, + "loss": 0.4365, + "step": 148 + }, + { + "epoch": 0.058823529411764705, + "grad_norm": 0.7210725545883179, + "learning_rate": 4.707856296881169e-06, + "loss": 0.4704, + "step": 149 + }, + { + "epoch": 0.05921831819976313, + "grad_norm": 0.5976917743682861, + "learning_rate": 4.705882352941177e-06, + "loss": 0.3431, + "step": 150 + }, + { + "epoch": 0.059613106987761545, + "grad_norm": 0.6680096983909607, + "learning_rate": 4.703908409001185e-06, + "loss": 0.3731, + "step": 151 + }, + { + "epoch": 0.06000789577575997, + "grad_norm": 0.6983616352081299, + "learning_rate": 4.701934465061193e-06, + "loss": 0.4576, + "step": 152 + }, + { + "epoch": 0.06040268456375839, + "grad_norm": 0.7066259384155273, + "learning_rate": 4.6999605211212e-06, + "loss": 0.4212, + "step": 153 + }, + { + "epoch": 0.06079747335175681, + "grad_norm": 0.7746145129203796, + "learning_rate": 4.697986577181208e-06, + "loss": 0.4583, + "step": 154 + }, + { + "epoch": 0.06119226213975523, + "grad_norm": 0.8491575717926025, + "learning_rate": 4.696012633241216e-06, + "loss": 0.4745, + "step": 155 + }, + { + "epoch": 0.06158705092775365, + "grad_norm": 0.7717884182929993, + "learning_rate": 4.694038689301224e-06, + "loss": 0.4346, + "step": 156 + }, + { + "epoch": 0.06198183971575207, + "grad_norm": 0.6748131513595581, + "learning_rate": 4.692064745361232e-06, + "loss": 0.4337, + "step": 157 + }, + { + "epoch": 0.062376628503750496, + "grad_norm": 0.7955337762832642, + "learning_rate": 4.69009080142124e-06, + "loss": 0.4182, + "step": 158 + }, + { + "epoch": 0.06277141729174891, + "grad_norm": 0.7158863544464111, + "learning_rate": 4.688116857481248e-06, + "loss": 0.4193, + "step": 159 + }, + { + "epoch": 0.06316620607974734, + "grad_norm": 0.6733810901641846, + "learning_rate": 4.686142913541256e-06, + "loss": 0.4162, + "step": 160 + }, + { + "epoch": 0.06356099486774576, + "grad_norm": 0.6817870140075684, + "learning_rate": 4.684168969601264e-06, + "loss": 0.4352, + "step": 161 + }, + { + "epoch": 0.06395578365574418, + "grad_norm": 0.5482531189918518, + "learning_rate": 4.682195025661272e-06, + "loss": 0.3166, + "step": 162 + }, + { + "epoch": 0.06435057244374259, + "grad_norm": 0.7556058764457703, + "learning_rate": 4.680221081721279e-06, + "loss": 0.4564, + "step": 163 + }, + { + "epoch": 0.06474536123174102, + "grad_norm": 0.718685507774353, + "learning_rate": 4.678247137781287e-06, + "loss": 0.3903, + "step": 164 + }, + { + "epoch": 0.06514015001973944, + "grad_norm": 0.6919001340866089, + "learning_rate": 4.676273193841295e-06, + "loss": 0.4852, + "step": 165 + }, + { + "epoch": 0.06553493880773786, + "grad_norm": 0.6458961963653564, + "learning_rate": 4.674299249901304e-06, + "loss": 0.4417, + "step": 166 + }, + { + "epoch": 0.06592972759573629, + "grad_norm": 0.6033383011817932, + "learning_rate": 4.672325305961311e-06, + "loss": 0.4188, + "step": 167 + }, + { + "epoch": 0.0663245163837347, + "grad_norm": 0.6863123178482056, + "learning_rate": 4.6703513620213196e-06, + "loss": 0.4143, + "step": 168 + }, + { + "epoch": 0.06671930517173312, + "grad_norm": 0.6254865527153015, + "learning_rate": 4.668377418081327e-06, + "loss": 0.4247, + "step": 169 + }, + { + "epoch": 0.06711409395973154, + "grad_norm": 0.6153876781463623, + "learning_rate": 4.666403474141335e-06, + "loss": 0.4973, + "step": 170 + }, + { + "epoch": 0.06750888274772997, + "grad_norm": 0.4260264039039612, + "learning_rate": 4.664429530201342e-06, + "loss": 0.3019, + "step": 171 + }, + { + "epoch": 0.06790367153572839, + "grad_norm": 0.6967951655387878, + "learning_rate": 4.662455586261351e-06, + "loss": 0.4006, + "step": 172 + }, + { + "epoch": 0.0682984603237268, + "grad_norm": 0.6785933971405029, + "learning_rate": 4.660481642321358e-06, + "loss": 0.4329, + "step": 173 + }, + { + "epoch": 0.06869324911172522, + "grad_norm": 0.843315064907074, + "learning_rate": 4.6585076983813666e-06, + "loss": 0.4955, + "step": 174 + }, + { + "epoch": 0.06908803789972365, + "grad_norm": 0.6190506815910339, + "learning_rate": 4.656533754441374e-06, + "loss": 0.4244, + "step": 175 + }, + { + "epoch": 0.06948282668772207, + "grad_norm": 0.6472244262695312, + "learning_rate": 4.6545598105013825e-06, + "loss": 0.4088, + "step": 176 + }, + { + "epoch": 0.0698776154757205, + "grad_norm": 0.6835210919380188, + "learning_rate": 4.65258586656139e-06, + "loss": 0.4361, + "step": 177 + }, + { + "epoch": 0.0702724042637189, + "grad_norm": 0.7650026679039001, + "learning_rate": 4.6506119226213984e-06, + "loss": 0.5007, + "step": 178 + }, + { + "epoch": 0.07066719305171733, + "grad_norm": 0.740687370300293, + "learning_rate": 4.648637978681406e-06, + "loss": 0.408, + "step": 179 + }, + { + "epoch": 0.07106198183971575, + "grad_norm": 0.6042583584785461, + "learning_rate": 4.6466640347414135e-06, + "loss": 0.3708, + "step": 180 + }, + { + "epoch": 0.07145677062771418, + "grad_norm": 0.602427065372467, + "learning_rate": 4.644690090801421e-06, + "loss": 0.4463, + "step": 181 + }, + { + "epoch": 0.0718515594157126, + "grad_norm": 0.8328279256820679, + "learning_rate": 4.6427161468614295e-06, + "loss": 0.4172, + "step": 182 + }, + { + "epoch": 0.07224634820371101, + "grad_norm": 0.5279515981674194, + "learning_rate": 4.640742202921437e-06, + "loss": 0.3602, + "step": 183 + }, + { + "epoch": 0.07264113699170943, + "grad_norm": 0.7189576029777527, + "learning_rate": 4.6387682589814454e-06, + "loss": 0.3716, + "step": 184 + }, + { + "epoch": 0.07303592577970786, + "grad_norm": 0.6282748579978943, + "learning_rate": 4.636794315041453e-06, + "loss": 0.4171, + "step": 185 + }, + { + "epoch": 0.07343071456770628, + "grad_norm": 0.6548610925674438, + "learning_rate": 4.634820371101461e-06, + "loss": 0.4389, + "step": 186 + }, + { + "epoch": 0.0738255033557047, + "grad_norm": 0.607177197933197, + "learning_rate": 4.632846427161469e-06, + "loss": 0.3717, + "step": 187 + }, + { + "epoch": 0.07422029214370311, + "grad_norm": 0.6790491342544556, + "learning_rate": 4.6308724832214765e-06, + "loss": 0.422, + "step": 188 + }, + { + "epoch": 0.07461508093170154, + "grad_norm": 0.8631829023361206, + "learning_rate": 4.628898539281485e-06, + "loss": 0.3933, + "step": 189 + }, + { + "epoch": 0.07500986971969996, + "grad_norm": 0.9164020419120789, + "learning_rate": 4.6269245953414924e-06, + "loss": 0.5344, + "step": 190 + }, + { + "epoch": 0.07540465850769838, + "grad_norm": 0.5808296799659729, + "learning_rate": 4.624950651401501e-06, + "loss": 0.3312, + "step": 191 + }, + { + "epoch": 0.0757994472956968, + "grad_norm": 0.6574617028236389, + "learning_rate": 4.622976707461508e-06, + "loss": 0.4182, + "step": 192 + }, + { + "epoch": 0.07619423608369523, + "grad_norm": 0.7242744565010071, + "learning_rate": 4.621002763521517e-06, + "loss": 0.3999, + "step": 193 + }, + { + "epoch": 0.07658902487169364, + "grad_norm": 0.7727478742599487, + "learning_rate": 4.619028819581524e-06, + "loss": 0.4505, + "step": 194 + }, + { + "epoch": 0.07698381365969206, + "grad_norm": 0.62250816822052, + "learning_rate": 4.617054875641533e-06, + "loss": 0.4576, + "step": 195 + }, + { + "epoch": 0.07737860244769049, + "grad_norm": 0.5998703837394714, + "learning_rate": 4.61508093170154e-06, + "loss": 0.4242, + "step": 196 + }, + { + "epoch": 0.07777339123568891, + "grad_norm": 0.6011488437652588, + "learning_rate": 4.613106987761548e-06, + "loss": 0.4196, + "step": 197 + }, + { + "epoch": 0.07816818002368733, + "grad_norm": 0.7436813116073608, + "learning_rate": 4.611133043821555e-06, + "loss": 0.4355, + "step": 198 + }, + { + "epoch": 0.07856296881168574, + "grad_norm": 0.6255786418914795, + "learning_rate": 4.609159099881564e-06, + "loss": 0.4149, + "step": 199 + }, + { + "epoch": 0.07895775759968417, + "grad_norm": 0.6637975573539734, + "learning_rate": 4.607185155941571e-06, + "loss": 0.3646, + "step": 200 + }, + { + "epoch": 0.07935254638768259, + "grad_norm": 1.0365961790084839, + "learning_rate": 4.60521121200158e-06, + "loss": 0.4575, + "step": 201 + }, + { + "epoch": 0.07974733517568101, + "grad_norm": 0.636567234992981, + "learning_rate": 4.603237268061587e-06, + "loss": 0.4214, + "step": 202 + }, + { + "epoch": 0.08014212396367944, + "grad_norm": 0.9328223466873169, + "learning_rate": 4.601263324121596e-06, + "loss": 0.442, + "step": 203 + }, + { + "epoch": 0.08053691275167785, + "grad_norm": 0.6823682188987732, + "learning_rate": 4.599289380181603e-06, + "loss": 0.4204, + "step": 204 + }, + { + "epoch": 0.08093170153967627, + "grad_norm": 0.6773712038993835, + "learning_rate": 4.597315436241611e-06, + "loss": 0.4743, + "step": 205 + }, + { + "epoch": 0.0813264903276747, + "grad_norm": 0.7207833528518677, + "learning_rate": 4.595341492301619e-06, + "loss": 0.4784, + "step": 206 + }, + { + "epoch": 0.08172127911567312, + "grad_norm": 0.5237183570861816, + "learning_rate": 4.593367548361627e-06, + "loss": 0.3519, + "step": 207 + }, + { + "epoch": 0.08211606790367154, + "grad_norm": 0.5143404603004456, + "learning_rate": 4.591393604421635e-06, + "loss": 0.3676, + "step": 208 + }, + { + "epoch": 0.08251085669166995, + "grad_norm": 0.7766891121864319, + "learning_rate": 4.589419660481643e-06, + "loss": 0.4184, + "step": 209 + }, + { + "epoch": 0.08290564547966837, + "grad_norm": 0.5380614995956421, + "learning_rate": 4.587445716541651e-06, + "loss": 0.3484, + "step": 210 + }, + { + "epoch": 0.0833004342676668, + "grad_norm": 0.5471227169036865, + "learning_rate": 4.585471772601659e-06, + "loss": 0.4071, + "step": 211 + }, + { + "epoch": 0.08369522305566522, + "grad_norm": 0.719805896282196, + "learning_rate": 4.583497828661667e-06, + "loss": 0.4489, + "step": 212 + }, + { + "epoch": 0.08409001184366365, + "grad_norm": 0.6995354890823364, + "learning_rate": 4.5815238847216745e-06, + "loss": 0.4554, + "step": 213 + }, + { + "epoch": 0.08448480063166205, + "grad_norm": 0.671918511390686, + "learning_rate": 4.579549940781682e-06, + "loss": 0.4125, + "step": 214 + }, + { + "epoch": 0.08487958941966048, + "grad_norm": 0.7130418419837952, + "learning_rate": 4.57757599684169e-06, + "loss": 0.3827, + "step": 215 + }, + { + "epoch": 0.0852743782076589, + "grad_norm": 0.5967832803726196, + "learning_rate": 4.575602052901698e-06, + "loss": 0.4247, + "step": 216 + }, + { + "epoch": 0.08566916699565733, + "grad_norm": 0.7026336193084717, + "learning_rate": 4.5736281089617056e-06, + "loss": 0.4618, + "step": 217 + }, + { + "epoch": 0.08606395578365575, + "grad_norm": 0.7018429040908813, + "learning_rate": 4.571654165021714e-06, + "loss": 0.4437, + "step": 218 + }, + { + "epoch": 0.08645874457165416, + "grad_norm": 0.6678574085235596, + "learning_rate": 4.5696802210817215e-06, + "loss": 0.4359, + "step": 219 + }, + { + "epoch": 0.08685353335965258, + "grad_norm": 0.5163692235946655, + "learning_rate": 4.56770627714173e-06, + "loss": 0.3397, + "step": 220 + }, + { + "epoch": 0.087248322147651, + "grad_norm": 0.6567980647087097, + "learning_rate": 4.5657323332017375e-06, + "loss": 0.4143, + "step": 221 + }, + { + "epoch": 0.08764311093564943, + "grad_norm": 0.6071962714195251, + "learning_rate": 4.563758389261745e-06, + "loss": 0.3924, + "step": 222 + }, + { + "epoch": 0.08803789972364785, + "grad_norm": 0.629145085811615, + "learning_rate": 4.561784445321753e-06, + "loss": 0.3886, + "step": 223 + }, + { + "epoch": 0.08843268851164626, + "grad_norm": 0.4868587553501129, + "learning_rate": 4.559810501381761e-06, + "loss": 0.3008, + "step": 224 + }, + { + "epoch": 0.08882747729964469, + "grad_norm": 0.938642144203186, + "learning_rate": 4.5578365574417685e-06, + "loss": 0.5008, + "step": 225 + }, + { + "epoch": 0.08922226608764311, + "grad_norm": 0.8349430561065674, + "learning_rate": 4.555862613501777e-06, + "loss": 0.4316, + "step": 226 + }, + { + "epoch": 0.08961705487564153, + "grad_norm": 0.897596001625061, + "learning_rate": 4.5538886695617845e-06, + "loss": 0.46, + "step": 227 + }, + { + "epoch": 0.09001184366363996, + "grad_norm": 0.6467362642288208, + "learning_rate": 4.551914725621793e-06, + "loss": 0.4112, + "step": 228 + }, + { + "epoch": 0.09040663245163838, + "grad_norm": 0.7127399444580078, + "learning_rate": 4.549940781681801e-06, + "loss": 0.3963, + "step": 229 + }, + { + "epoch": 0.09080142123963679, + "grad_norm": 0.5069522857666016, + "learning_rate": 4.547966837741809e-06, + "loss": 0.3969, + "step": 230 + }, + { + "epoch": 0.09119621002763521, + "grad_norm": 0.728843092918396, + "learning_rate": 4.545992893801816e-06, + "loss": 0.4207, + "step": 231 + }, + { + "epoch": 0.09159099881563364, + "grad_norm": 0.7820498943328857, + "learning_rate": 4.544018949861824e-06, + "loss": 0.482, + "step": 232 + }, + { + "epoch": 0.09198578760363206, + "grad_norm": 0.7966720461845398, + "learning_rate": 4.542045005921832e-06, + "loss": 0.4636, + "step": 233 + }, + { + "epoch": 0.09238057639163048, + "grad_norm": 0.6999194025993347, + "learning_rate": 4.54007106198184e-06, + "loss": 0.4721, + "step": 234 + }, + { + "epoch": 0.0927753651796289, + "grad_norm": 0.605614960193634, + "learning_rate": 4.538097118041848e-06, + "loss": 0.4281, + "step": 235 + }, + { + "epoch": 0.09317015396762732, + "grad_norm": 1.1039471626281738, + "learning_rate": 4.536123174101856e-06, + "loss": 0.4982, + "step": 236 + }, + { + "epoch": 0.09356494275562574, + "grad_norm": 0.8399055600166321, + "learning_rate": 4.534149230161864e-06, + "loss": 0.4752, + "step": 237 + }, + { + "epoch": 0.09395973154362416, + "grad_norm": 0.6234923005104065, + "learning_rate": 4.532175286221872e-06, + "loss": 0.3973, + "step": 238 + }, + { + "epoch": 0.09435452033162259, + "grad_norm": 0.6144906282424927, + "learning_rate": 4.530201342281879e-06, + "loss": 0.396, + "step": 239 + }, + { + "epoch": 0.094749309119621, + "grad_norm": 0.6167351007461548, + "learning_rate": 4.528227398341888e-06, + "loss": 0.45, + "step": 240 + }, + { + "epoch": 0.09514409790761942, + "grad_norm": 0.703520655632019, + "learning_rate": 4.526253454401895e-06, + "loss": 0.3867, + "step": 241 + }, + { + "epoch": 0.09553888669561784, + "grad_norm": 0.778991162776947, + "learning_rate": 4.524279510461903e-06, + "loss": 0.4475, + "step": 242 + }, + { + "epoch": 0.09593367548361627, + "grad_norm": 0.7392948865890503, + "learning_rate": 4.522305566521911e-06, + "loss": 0.4429, + "step": 243 + }, + { + "epoch": 0.09632846427161469, + "grad_norm": 0.6409873962402344, + "learning_rate": 4.520331622581919e-06, + "loss": 0.4241, + "step": 244 + }, + { + "epoch": 0.0967232530596131, + "grad_norm": 0.6814899444580078, + "learning_rate": 4.518357678641927e-06, + "loss": 0.3984, + "step": 245 + }, + { + "epoch": 0.09711804184761152, + "grad_norm": 0.625703752040863, + "learning_rate": 4.516383734701935e-06, + "loss": 0.3562, + "step": 246 + }, + { + "epoch": 0.09751283063560995, + "grad_norm": 0.8310146331787109, + "learning_rate": 4.514409790761943e-06, + "loss": 0.5446, + "step": 247 + }, + { + "epoch": 0.09790761942360837, + "grad_norm": 0.7347928881645203, + "learning_rate": 4.512435846821951e-06, + "loss": 0.4022, + "step": 248 + }, + { + "epoch": 0.0983024082116068, + "grad_norm": 0.8897711634635925, + "learning_rate": 4.510461902881958e-06, + "loss": 0.4854, + "step": 249 + }, + { + "epoch": 0.0986971969996052, + "grad_norm": 0.7975876331329346, + "learning_rate": 4.5084879589419666e-06, + "loss": 0.4337, + "step": 250 + }, + { + "epoch": 0.09909198578760363, + "grad_norm": 0.5456104874610901, + "learning_rate": 4.506514015001974e-06, + "loss": 0.3598, + "step": 251 + }, + { + "epoch": 0.09948677457560205, + "grad_norm": 0.7901602983474731, + "learning_rate": 4.5045400710619825e-06, + "loss": 0.4747, + "step": 252 + }, + { + "epoch": 0.09988156336360048, + "grad_norm": 0.5584656000137329, + "learning_rate": 4.50256612712199e-06, + "loss": 0.3756, + "step": 253 + }, + { + "epoch": 0.1002763521515989, + "grad_norm": 0.7196951508522034, + "learning_rate": 4.5005921831819984e-06, + "loss": 0.4382, + "step": 254 + }, + { + "epoch": 0.10067114093959731, + "grad_norm": 0.5634801387786865, + "learning_rate": 4.498618239242006e-06, + "loss": 0.367, + "step": 255 + }, + { + "epoch": 0.10106592972759573, + "grad_norm": 0.8934388756752014, + "learning_rate": 4.4966442953020135e-06, + "loss": 0.5118, + "step": 256 + }, + { + "epoch": 0.10146071851559416, + "grad_norm": 0.5286169052124023, + "learning_rate": 4.494670351362022e-06, + "loss": 0.3786, + "step": 257 + }, + { + "epoch": 0.10185550730359258, + "grad_norm": 0.7418983578681946, + "learning_rate": 4.4926964074220295e-06, + "loss": 0.3945, + "step": 258 + }, + { + "epoch": 0.102250296091591, + "grad_norm": 0.7433722019195557, + "learning_rate": 4.490722463482037e-06, + "loss": 0.4631, + "step": 259 + }, + { + "epoch": 0.10264508487958941, + "grad_norm": 0.6134681105613708, + "learning_rate": 4.4887485195420454e-06, + "loss": 0.4727, + "step": 260 + }, + { + "epoch": 0.10303987366758784, + "grad_norm": 0.5793192386627197, + "learning_rate": 4.486774575602053e-06, + "loss": 0.3842, + "step": 261 + }, + { + "epoch": 0.10343466245558626, + "grad_norm": 0.5460737347602844, + "learning_rate": 4.484800631662061e-06, + "loss": 0.3509, + "step": 262 + }, + { + "epoch": 0.10382945124358468, + "grad_norm": 0.8210111856460571, + "learning_rate": 4.482826687722069e-06, + "loss": 0.4669, + "step": 263 + }, + { + "epoch": 0.1042242400315831, + "grad_norm": 0.651795506477356, + "learning_rate": 4.480852743782077e-06, + "loss": 0.3781, + "step": 264 + }, + { + "epoch": 0.10461902881958153, + "grad_norm": 0.643174409866333, + "learning_rate": 4.478878799842085e-06, + "loss": 0.3933, + "step": 265 + }, + { + "epoch": 0.10501381760757994, + "grad_norm": 0.6097356081008911, + "learning_rate": 4.476904855902092e-06, + "loss": 0.4481, + "step": 266 + }, + { + "epoch": 0.10540860639557836, + "grad_norm": 0.7765064835548401, + "learning_rate": 4.4749309119621e-06, + "loss": 0.457, + "step": 267 + }, + { + "epoch": 0.10580339518357679, + "grad_norm": 0.561502993106842, + "learning_rate": 4.472956968022108e-06, + "loss": 0.3954, + "step": 268 + }, + { + "epoch": 0.10619818397157521, + "grad_norm": 0.6700526475906372, + "learning_rate": 4.470983024082117e-06, + "loss": 0.4269, + "step": 269 + }, + { + "epoch": 0.10659297275957363, + "grad_norm": 0.5569946765899658, + "learning_rate": 4.469009080142124e-06, + "loss": 0.3885, + "step": 270 + }, + { + "epoch": 0.10698776154757204, + "grad_norm": 0.7014193534851074, + "learning_rate": 4.467035136202133e-06, + "loss": 0.4146, + "step": 271 + }, + { + "epoch": 0.10738255033557047, + "grad_norm": 0.7772698998451233, + "learning_rate": 4.46506119226214e-06, + "loss": 0.4754, + "step": 272 + }, + { + "epoch": 0.10777733912356889, + "grad_norm": 0.6306508779525757, + "learning_rate": 4.463087248322149e-06, + "loss": 0.3922, + "step": 273 + }, + { + "epoch": 0.10817212791156731, + "grad_norm": 0.7260493040084839, + "learning_rate": 4.461113304382156e-06, + "loss": 0.4883, + "step": 274 + }, + { + "epoch": 0.10856691669956574, + "grad_norm": 0.6733102798461914, + "learning_rate": 4.459139360442164e-06, + "loss": 0.4137, + "step": 275 + }, + { + "epoch": 0.10896170548756415, + "grad_norm": 0.7747586965560913, + "learning_rate": 4.457165416502171e-06, + "loss": 0.4358, + "step": 276 + }, + { + "epoch": 0.10935649427556257, + "grad_norm": 0.6313894987106323, + "learning_rate": 4.45519147256218e-06, + "loss": 0.4452, + "step": 277 + }, + { + "epoch": 0.109751283063561, + "grad_norm": 0.6279841065406799, + "learning_rate": 4.453217528622187e-06, + "loss": 0.424, + "step": 278 + }, + { + "epoch": 0.11014607185155942, + "grad_norm": 0.7222081422805786, + "learning_rate": 4.451243584682196e-06, + "loss": 0.4331, + "step": 279 + }, + { + "epoch": 0.11054086063955784, + "grad_norm": 0.5871759653091431, + "learning_rate": 4.449269640742203e-06, + "loss": 0.3864, + "step": 280 + }, + { + "epoch": 0.11093564942755625, + "grad_norm": 0.596807062625885, + "learning_rate": 4.447295696802212e-06, + "loss": 0.3955, + "step": 281 + }, + { + "epoch": 0.11133043821555468, + "grad_norm": 0.6190645694732666, + "learning_rate": 4.445321752862219e-06, + "loss": 0.4098, + "step": 282 + }, + { + "epoch": 0.1117252270035531, + "grad_norm": 0.7411061525344849, + "learning_rate": 4.443347808922227e-06, + "loss": 0.4886, + "step": 283 + }, + { + "epoch": 0.11212001579155152, + "grad_norm": 0.6037311553955078, + "learning_rate": 4.441373864982235e-06, + "loss": 0.42, + "step": 284 + }, + { + "epoch": 0.11251480457954995, + "grad_norm": 0.6636619567871094, + "learning_rate": 4.439399921042243e-06, + "loss": 0.3721, + "step": 285 + }, + { + "epoch": 0.11290959336754836, + "grad_norm": 0.7866764664649963, + "learning_rate": 4.43742597710225e-06, + "loss": 0.4642, + "step": 286 + }, + { + "epoch": 0.11330438215554678, + "grad_norm": 0.5447928309440613, + "learning_rate": 4.4354520331622586e-06, + "loss": 0.3679, + "step": 287 + }, + { + "epoch": 0.1136991709435452, + "grad_norm": 0.7182103395462036, + "learning_rate": 4.433478089222266e-06, + "loss": 0.3456, + "step": 288 + }, + { + "epoch": 0.11409395973154363, + "grad_norm": 0.6926178336143494, + "learning_rate": 4.4315041452822745e-06, + "loss": 0.452, + "step": 289 + }, + { + "epoch": 0.11448874851954205, + "grad_norm": 0.8501423001289368, + "learning_rate": 4.429530201342283e-06, + "loss": 0.3916, + "step": 290 + }, + { + "epoch": 0.11488353730754046, + "grad_norm": 0.629459798336029, + "learning_rate": 4.4275562574022905e-06, + "loss": 0.396, + "step": 291 + }, + { + "epoch": 0.11527832609553888, + "grad_norm": 0.5587422251701355, + "learning_rate": 4.425582313462298e-06, + "loss": 0.4077, + "step": 292 + }, + { + "epoch": 0.1156731148835373, + "grad_norm": 0.6060861945152283, + "learning_rate": 4.4236083695223056e-06, + "loss": 0.4315, + "step": 293 + }, + { + "epoch": 0.11606790367153573, + "grad_norm": 0.5815017223358154, + "learning_rate": 4.421634425582314e-06, + "loss": 0.3576, + "step": 294 + }, + { + "epoch": 0.11646269245953415, + "grad_norm": 0.622086226940155, + "learning_rate": 4.4196604816423215e-06, + "loss": 0.429, + "step": 295 + }, + { + "epoch": 0.11685748124753258, + "grad_norm": 0.6701876521110535, + "learning_rate": 4.41768653770233e-06, + "loss": 0.4119, + "step": 296 + }, + { + "epoch": 0.11725227003553099, + "grad_norm": 0.6551656723022461, + "learning_rate": 4.4157125937623375e-06, + "loss": 0.4497, + "step": 297 + }, + { + "epoch": 0.11764705882352941, + "grad_norm": 0.7513328194618225, + "learning_rate": 4.413738649822346e-06, + "loss": 0.3839, + "step": 298 + }, + { + "epoch": 0.11804184761152783, + "grad_norm": 0.6588373184204102, + "learning_rate": 4.411764705882353e-06, + "loss": 0.4351, + "step": 299 + }, + { + "epoch": 0.11843663639952626, + "grad_norm": 0.5621301531791687, + "learning_rate": 4.409790761942361e-06, + "loss": 0.3762, + "step": 300 + }, + { + "epoch": 0.11883142518752468, + "grad_norm": 0.8190930485725403, + "learning_rate": 4.407816818002369e-06, + "loss": 0.442, + "step": 301 + }, + { + "epoch": 0.11922621397552309, + "grad_norm": 0.6835026741027832, + "learning_rate": 4.405842874062377e-06, + "loss": 0.4357, + "step": 302 + }, + { + "epoch": 0.11962100276352151, + "grad_norm": 0.7079758644104004, + "learning_rate": 4.4038689301223844e-06, + "loss": 0.4352, + "step": 303 + }, + { + "epoch": 0.12001579155151994, + "grad_norm": 0.6271044611930847, + "learning_rate": 4.401894986182393e-06, + "loss": 0.38, + "step": 304 + }, + { + "epoch": 0.12041058033951836, + "grad_norm": 0.65809166431427, + "learning_rate": 4.3999210422424e-06, + "loss": 0.4545, + "step": 305 + }, + { + "epoch": 0.12080536912751678, + "grad_norm": 0.7273672223091125, + "learning_rate": 4.397947098302409e-06, + "loss": 0.4928, + "step": 306 + }, + { + "epoch": 0.1212001579155152, + "grad_norm": 0.6451597213745117, + "learning_rate": 4.395973154362416e-06, + "loss": 0.4321, + "step": 307 + }, + { + "epoch": 0.12159494670351362, + "grad_norm": 0.7780693173408508, + "learning_rate": 4.393999210422425e-06, + "loss": 0.4145, + "step": 308 + }, + { + "epoch": 0.12198973549151204, + "grad_norm": 0.931542694568634, + "learning_rate": 4.392025266482432e-06, + "loss": 0.5059, + "step": 309 + }, + { + "epoch": 0.12238452427951046, + "grad_norm": 0.7169415354728699, + "learning_rate": 4.39005132254244e-06, + "loss": 0.444, + "step": 310 + }, + { + "epoch": 0.12277931306750889, + "grad_norm": 0.6810592412948608, + "learning_rate": 4.388077378602448e-06, + "loss": 0.4576, + "step": 311 + }, + { + "epoch": 0.1231741018555073, + "grad_norm": 0.6868934631347656, + "learning_rate": 4.386103434662456e-06, + "loss": 0.4347, + "step": 312 + }, + { + "epoch": 0.12356889064350572, + "grad_norm": 0.5626333355903625, + "learning_rate": 4.384129490722464e-06, + "loss": 0.3979, + "step": 313 + }, + { + "epoch": 0.12396367943150415, + "grad_norm": 0.7300309538841248, + "learning_rate": 4.382155546782472e-06, + "loss": 0.4296, + "step": 314 + }, + { + "epoch": 0.12435846821950257, + "grad_norm": 0.5907742977142334, + "learning_rate": 4.38018160284248e-06, + "loss": 0.3863, + "step": 315 + }, + { + "epoch": 0.12475325700750099, + "grad_norm": 0.712740421295166, + "learning_rate": 4.378207658902488e-06, + "loss": 0.5205, + "step": 316 + }, + { + "epoch": 0.1251480457954994, + "grad_norm": 0.6836943626403809, + "learning_rate": 4.376233714962495e-06, + "loss": 0.4243, + "step": 317 + }, + { + "epoch": 0.12554283458349783, + "grad_norm": 0.6138408184051514, + "learning_rate": 4.374259771022504e-06, + "loss": 0.4485, + "step": 318 + }, + { + "epoch": 0.12593762337149625, + "grad_norm": 0.5410381555557251, + "learning_rate": 4.372285827082511e-06, + "loss": 0.3841, + "step": 319 + }, + { + "epoch": 0.12633241215949467, + "grad_norm": 0.5723019242286682, + "learning_rate": 4.370311883142519e-06, + "loss": 0.3967, + "step": 320 + }, + { + "epoch": 0.1267272009474931, + "grad_norm": 0.8870103359222412, + "learning_rate": 4.368337939202527e-06, + "loss": 0.5217, + "step": 321 + }, + { + "epoch": 0.12712198973549152, + "grad_norm": 0.6555352807044983, + "learning_rate": 4.366363995262535e-06, + "loss": 0.3965, + "step": 322 + }, + { + "epoch": 0.12751677852348994, + "grad_norm": 0.7477242946624756, + "learning_rate": 4.364390051322543e-06, + "loss": 0.4653, + "step": 323 + }, + { + "epoch": 0.12791156731148837, + "grad_norm": 0.577836275100708, + "learning_rate": 4.362416107382551e-06, + "loss": 0.4986, + "step": 324 + }, + { + "epoch": 0.12830635609948676, + "grad_norm": 0.7320024371147156, + "learning_rate": 4.360442163442559e-06, + "loss": 0.5065, + "step": 325 + }, + { + "epoch": 0.12870114488748519, + "grad_norm": 0.5826845765113831, + "learning_rate": 4.3584682195025665e-06, + "loss": 0.3578, + "step": 326 + }, + { + "epoch": 0.1290959336754836, + "grad_norm": 0.5639458298683167, + "learning_rate": 4.356494275562574e-06, + "loss": 0.405, + "step": 327 + }, + { + "epoch": 0.12949072246348203, + "grad_norm": 0.5693730711936951, + "learning_rate": 4.354520331622582e-06, + "loss": 0.4342, + "step": 328 + }, + { + "epoch": 0.12988551125148046, + "grad_norm": 0.6761910915374756, + "learning_rate": 4.35254638768259e-06, + "loss": 0.4144, + "step": 329 + }, + { + "epoch": 0.13028030003947888, + "grad_norm": 0.7196240425109863, + "learning_rate": 4.350572443742598e-06, + "loss": 0.4627, + "step": 330 + }, + { + "epoch": 0.1306750888274773, + "grad_norm": 0.6791706681251526, + "learning_rate": 4.348598499802606e-06, + "loss": 0.4561, + "step": 331 + }, + { + "epoch": 0.13106987761547573, + "grad_norm": 0.5776423811912537, + "learning_rate": 4.346624555862614e-06, + "loss": 0.3657, + "step": 332 + }, + { + "epoch": 0.13146466640347415, + "grad_norm": 0.5658211708068848, + "learning_rate": 4.344650611922622e-06, + "loss": 0.3581, + "step": 333 + }, + { + "epoch": 0.13185945519147257, + "grad_norm": 0.6292372345924377, + "learning_rate": 4.3426766679826295e-06, + "loss": 0.4647, + "step": 334 + }, + { + "epoch": 0.13225424397947097, + "grad_norm": 0.6937440633773804, + "learning_rate": 4.340702724042638e-06, + "loss": 0.3958, + "step": 335 + }, + { + "epoch": 0.1326490327674694, + "grad_norm": 0.6585578322410583, + "learning_rate": 4.3387287801026454e-06, + "loss": 0.4113, + "step": 336 + }, + { + "epoch": 0.13304382155546782, + "grad_norm": 0.5441217422485352, + "learning_rate": 4.336754836162653e-06, + "loss": 0.3831, + "step": 337 + }, + { + "epoch": 0.13343861034346624, + "grad_norm": 0.7030034065246582, + "learning_rate": 4.334780892222661e-06, + "loss": 0.4547, + "step": 338 + }, + { + "epoch": 0.13383339913146466, + "grad_norm": 0.6618365049362183, + "learning_rate": 4.332806948282669e-06, + "loss": 0.4075, + "step": 339 + }, + { + "epoch": 0.1342281879194631, + "grad_norm": 0.610434889793396, + "learning_rate": 4.330833004342677e-06, + "loss": 0.3951, + "step": 340 + }, + { + "epoch": 0.1346229767074615, + "grad_norm": 0.6020464301109314, + "learning_rate": 4.328859060402685e-06, + "loss": 0.4206, + "step": 341 + }, + { + "epoch": 0.13501776549545993, + "grad_norm": 0.5270140767097473, + "learning_rate": 4.326885116462693e-06, + "loss": 0.4067, + "step": 342 + }, + { + "epoch": 0.13541255428345836, + "grad_norm": 0.8998298048973083, + "learning_rate": 4.324911172522701e-06, + "loss": 0.4617, + "step": 343 + }, + { + "epoch": 0.13580734307145678, + "grad_norm": 0.6789680123329163, + "learning_rate": 4.322937228582708e-06, + "loss": 0.4314, + "step": 344 + }, + { + "epoch": 0.13620213185945518, + "grad_norm": 0.6684865951538086, + "learning_rate": 4.320963284642716e-06, + "loss": 0.3643, + "step": 345 + }, + { + "epoch": 0.1365969206474536, + "grad_norm": 0.7665839791297913, + "learning_rate": 4.318989340702724e-06, + "loss": 0.4881, + "step": 346 + }, + { + "epoch": 0.13699170943545202, + "grad_norm": 0.6055838465690613, + "learning_rate": 4.317015396762732e-06, + "loss": 0.4331, + "step": 347 + }, + { + "epoch": 0.13738649822345045, + "grad_norm": 0.5524763464927673, + "learning_rate": 4.31504145282274e-06, + "loss": 0.4111, + "step": 348 + }, + { + "epoch": 0.13778128701144887, + "grad_norm": 0.6222780346870422, + "learning_rate": 4.313067508882748e-06, + "loss": 0.3628, + "step": 349 + }, + { + "epoch": 0.1381760757994473, + "grad_norm": 0.5935861468315125, + "learning_rate": 4.311093564942756e-06, + "loss": 0.42, + "step": 350 + }, + { + "epoch": 0.13857086458744572, + "grad_norm": 0.6592918634414673, + "learning_rate": 4.309119621002764e-06, + "loss": 0.4008, + "step": 351 + }, + { + "epoch": 0.13896565337544414, + "grad_norm": 0.6533365249633789, + "learning_rate": 4.307145677062772e-06, + "loss": 0.4314, + "step": 352 + }, + { + "epoch": 0.13936044216344257, + "grad_norm": 0.7934540510177612, + "learning_rate": 4.30517173312278e-06, + "loss": 0.4625, + "step": 353 + }, + { + "epoch": 0.139755230951441, + "grad_norm": 0.5315614938735962, + "learning_rate": 4.303197789182787e-06, + "loss": 0.4005, + "step": 354 + }, + { + "epoch": 0.1401500197394394, + "grad_norm": 0.5875794887542725, + "learning_rate": 4.301223845242796e-06, + "loss": 0.3831, + "step": 355 + }, + { + "epoch": 0.1405448085274378, + "grad_norm": 0.6360564231872559, + "learning_rate": 4.299249901302803e-06, + "loss": 0.418, + "step": 356 + }, + { + "epoch": 0.14093959731543623, + "grad_norm": 0.9888524413108826, + "learning_rate": 4.297275957362812e-06, + "loss": 0.4857, + "step": 357 + }, + { + "epoch": 0.14133438610343466, + "grad_norm": 0.6752721667289734, + "learning_rate": 4.295302013422819e-06, + "loss": 0.4027, + "step": 358 + }, + { + "epoch": 0.14172917489143308, + "grad_norm": 0.7301502823829651, + "learning_rate": 4.2933280694828275e-06, + "loss": 0.4263, + "step": 359 + }, + { + "epoch": 0.1421239636794315, + "grad_norm": 0.8137803077697754, + "learning_rate": 4.291354125542835e-06, + "loss": 0.4451, + "step": 360 + }, + { + "epoch": 0.14251875246742993, + "grad_norm": 0.7129930257797241, + "learning_rate": 4.289380181602843e-06, + "loss": 0.4456, + "step": 361 + }, + { + "epoch": 0.14291354125542835, + "grad_norm": 0.7410032749176025, + "learning_rate": 4.28740623766285e-06, + "loss": 0.4584, + "step": 362 + }, + { + "epoch": 0.14330833004342677, + "grad_norm": 0.7864344716072083, + "learning_rate": 4.2854322937228586e-06, + "loss": 0.3875, + "step": 363 + }, + { + "epoch": 0.1437031188314252, + "grad_norm": 0.6695477962493896, + "learning_rate": 4.283458349782866e-06, + "loss": 0.4465, + "step": 364 + }, + { + "epoch": 0.14409790761942362, + "grad_norm": 0.633306622505188, + "learning_rate": 4.2814844058428745e-06, + "loss": 0.4132, + "step": 365 + }, + { + "epoch": 0.14449269640742202, + "grad_norm": 0.9731364846229553, + "learning_rate": 4.279510461902882e-06, + "loss": 0.3886, + "step": 366 + }, + { + "epoch": 0.14488748519542044, + "grad_norm": 0.7902954816818237, + "learning_rate": 4.2775365179628905e-06, + "loss": 0.5064, + "step": 367 + }, + { + "epoch": 0.14528227398341886, + "grad_norm": 0.8541964888572693, + "learning_rate": 4.275562574022898e-06, + "loss": 0.4223, + "step": 368 + }, + { + "epoch": 0.1456770627714173, + "grad_norm": 0.6548330187797546, + "learning_rate": 4.273588630082906e-06, + "loss": 0.388, + "step": 369 + }, + { + "epoch": 0.1460718515594157, + "grad_norm": 0.6485247015953064, + "learning_rate": 4.271614686142914e-06, + "loss": 0.4034, + "step": 370 + }, + { + "epoch": 0.14646664034741413, + "grad_norm": 0.6874770522117615, + "learning_rate": 4.2696407422029215e-06, + "loss": 0.4136, + "step": 371 + }, + { + "epoch": 0.14686142913541256, + "grad_norm": 0.5891363620758057, + "learning_rate": 4.26766679826293e-06, + "loss": 0.3805, + "step": 372 + }, + { + "epoch": 0.14725621792341098, + "grad_norm": 0.6777528524398804, + "learning_rate": 4.2656928543229375e-06, + "loss": 0.4455, + "step": 373 + }, + { + "epoch": 0.1476510067114094, + "grad_norm": 0.5996795296669006, + "learning_rate": 4.263718910382946e-06, + "loss": 0.4141, + "step": 374 + }, + { + "epoch": 0.14804579549940783, + "grad_norm": 0.6593229174613953, + "learning_rate": 4.261744966442953e-06, + "loss": 0.3585, + "step": 375 + }, + { + "epoch": 0.14844058428740622, + "grad_norm": 0.6509807705879211, + "learning_rate": 4.259771022502962e-06, + "loss": 0.4419, + "step": 376 + }, + { + "epoch": 0.14883537307540465, + "grad_norm": 0.5989826917648315, + "learning_rate": 4.257797078562969e-06, + "loss": 0.402, + "step": 377 + }, + { + "epoch": 0.14923016186340307, + "grad_norm": 0.6357407569885254, + "learning_rate": 4.255823134622977e-06, + "loss": 0.3995, + "step": 378 + }, + { + "epoch": 0.1496249506514015, + "grad_norm": 0.585387110710144, + "learning_rate": 4.2538491906829844e-06, + "loss": 0.4235, + "step": 379 + }, + { + "epoch": 0.15001973943939992, + "grad_norm": 0.5572819709777832, + "learning_rate": 4.251875246742993e-06, + "loss": 0.4595, + "step": 380 + }, + { + "epoch": 0.15041452822739834, + "grad_norm": 0.5680681467056274, + "learning_rate": 4.249901302803e-06, + "loss": 0.376, + "step": 381 + }, + { + "epoch": 0.15080931701539677, + "grad_norm": 0.4171941578388214, + "learning_rate": 4.247927358863009e-06, + "loss": 0.3009, + "step": 382 + }, + { + "epoch": 0.1512041058033952, + "grad_norm": 0.6261305212974548, + "learning_rate": 4.245953414923016e-06, + "loss": 0.3987, + "step": 383 + }, + { + "epoch": 0.1515988945913936, + "grad_norm": 0.7593600749969482, + "learning_rate": 4.243979470983025e-06, + "loss": 0.4727, + "step": 384 + }, + { + "epoch": 0.15199368337939204, + "grad_norm": 0.631318211555481, + "learning_rate": 4.242005527043032e-06, + "loss": 0.4353, + "step": 385 + }, + { + "epoch": 0.15238847216739046, + "grad_norm": 0.7325477600097656, + "learning_rate": 4.240031583103041e-06, + "loss": 0.4383, + "step": 386 + }, + { + "epoch": 0.15278326095538886, + "grad_norm": 0.6548128128051758, + "learning_rate": 4.238057639163048e-06, + "loss": 0.4673, + "step": 387 + }, + { + "epoch": 0.15317804974338728, + "grad_norm": 0.6070308089256287, + "learning_rate": 4.236083695223056e-06, + "loss": 0.4258, + "step": 388 + }, + { + "epoch": 0.1535728385313857, + "grad_norm": 0.6211336255073547, + "learning_rate": 4.234109751283063e-06, + "loss": 0.3999, + "step": 389 + }, + { + "epoch": 0.15396762731938413, + "grad_norm": 0.65799480676651, + "learning_rate": 4.232135807343072e-06, + "loss": 0.4355, + "step": 390 + }, + { + "epoch": 0.15436241610738255, + "grad_norm": 0.5672595500946045, + "learning_rate": 4.230161863403079e-06, + "loss": 0.4212, + "step": 391 + }, + { + "epoch": 0.15475720489538097, + "grad_norm": 0.7200724482536316, + "learning_rate": 4.228187919463088e-06, + "loss": 0.4479, + "step": 392 + }, + { + "epoch": 0.1551519936833794, + "grad_norm": 0.7152998447418213, + "learning_rate": 4.226213975523096e-06, + "loss": 0.458, + "step": 393 + }, + { + "epoch": 0.15554678247137782, + "grad_norm": 0.6430211663246155, + "learning_rate": 4.224240031583104e-06, + "loss": 0.4458, + "step": 394 + }, + { + "epoch": 0.15594157125937624, + "grad_norm": 0.5588846802711487, + "learning_rate": 4.222266087643111e-06, + "loss": 0.3702, + "step": 395 + }, + { + "epoch": 0.15633636004737467, + "grad_norm": 0.6550770401954651, + "learning_rate": 4.220292143703119e-06, + "loss": 0.4265, + "step": 396 + }, + { + "epoch": 0.15673114883537306, + "grad_norm": 0.8489173054695129, + "learning_rate": 4.218318199763127e-06, + "loss": 0.4651, + "step": 397 + }, + { + "epoch": 0.1571259376233715, + "grad_norm": 0.6461364030838013, + "learning_rate": 4.216344255823135e-06, + "loss": 0.3806, + "step": 398 + }, + { + "epoch": 0.1575207264113699, + "grad_norm": 0.7618893980979919, + "learning_rate": 4.214370311883143e-06, + "loss": 0.4901, + "step": 399 + }, + { + "epoch": 0.15791551519936833, + "grad_norm": 0.6333760023117065, + "learning_rate": 4.212396367943151e-06, + "loss": 0.4069, + "step": 400 + }, + { + "epoch": 0.15831030398736676, + "grad_norm": 0.6830106377601624, + "learning_rate": 4.210422424003159e-06, + "loss": 0.4176, + "step": 401 + }, + { + "epoch": 0.15870509277536518, + "grad_norm": 0.5552243590354919, + "learning_rate": 4.2084484800631665e-06, + "loss": 0.401, + "step": 402 + }, + { + "epoch": 0.1590998815633636, + "grad_norm": 0.6118090152740479, + "learning_rate": 4.206474536123175e-06, + "loss": 0.4099, + "step": 403 + }, + { + "epoch": 0.15949467035136203, + "grad_norm": 0.5282830595970154, + "learning_rate": 4.2045005921831825e-06, + "loss": 0.4245, + "step": 404 + }, + { + "epoch": 0.15988945913936045, + "grad_norm": 0.8172078132629395, + "learning_rate": 4.20252664824319e-06, + "loss": 0.4296, + "step": 405 + }, + { + "epoch": 0.16028424792735887, + "grad_norm": 0.6083583831787109, + "learning_rate": 4.200552704303198e-06, + "loss": 0.4173, + "step": 406 + }, + { + "epoch": 0.16067903671535727, + "grad_norm": 0.5517644882202148, + "learning_rate": 4.198578760363206e-06, + "loss": 0.3936, + "step": 407 + }, + { + "epoch": 0.1610738255033557, + "grad_norm": 0.6106107831001282, + "learning_rate": 4.1966048164232135e-06, + "loss": 0.4188, + "step": 408 + }, + { + "epoch": 0.16146861429135412, + "grad_norm": 0.9128310084342957, + "learning_rate": 4.194630872483222e-06, + "loss": 0.474, + "step": 409 + }, + { + "epoch": 0.16186340307935254, + "grad_norm": 0.8519933819770813, + "learning_rate": 4.1926569285432295e-06, + "loss": 0.5168, + "step": 410 + }, + { + "epoch": 0.16225819186735096, + "grad_norm": 0.5942670702934265, + "learning_rate": 4.190682984603238e-06, + "loss": 0.3971, + "step": 411 + }, + { + "epoch": 0.1626529806553494, + "grad_norm": 0.5840862989425659, + "learning_rate": 4.188709040663245e-06, + "loss": 0.4423, + "step": 412 + }, + { + "epoch": 0.1630477694433478, + "grad_norm": 0.6639212965965271, + "learning_rate": 4.186735096723254e-06, + "loss": 0.451, + "step": 413 + }, + { + "epoch": 0.16344255823134624, + "grad_norm": 0.6290633678436279, + "learning_rate": 4.184761152783261e-06, + "loss": 0.4236, + "step": 414 + }, + { + "epoch": 0.16383734701934466, + "grad_norm": 0.5829403400421143, + "learning_rate": 4.182787208843269e-06, + "loss": 0.4354, + "step": 415 + }, + { + "epoch": 0.16423213580734308, + "grad_norm": 0.6267001628875732, + "learning_rate": 4.180813264903277e-06, + "loss": 0.421, + "step": 416 + }, + { + "epoch": 0.1646269245953415, + "grad_norm": 0.7042717933654785, + "learning_rate": 4.178839320963285e-06, + "loss": 0.4346, + "step": 417 + }, + { + "epoch": 0.1650217133833399, + "grad_norm": 0.6656914949417114, + "learning_rate": 4.176865377023293e-06, + "loss": 0.4323, + "step": 418 + }, + { + "epoch": 0.16541650217133833, + "grad_norm": 0.7290217876434326, + "learning_rate": 4.174891433083301e-06, + "loss": 0.4649, + "step": 419 + }, + { + "epoch": 0.16581129095933675, + "grad_norm": 0.5801425576210022, + "learning_rate": 4.172917489143309e-06, + "loss": 0.4178, + "step": 420 + }, + { + "epoch": 0.16620607974733517, + "grad_norm": 0.559954047203064, + "learning_rate": 4.170943545203317e-06, + "loss": 0.3686, + "step": 421 + }, + { + "epoch": 0.1666008685353336, + "grad_norm": 0.6967236399650574, + "learning_rate": 4.168969601263324e-06, + "loss": 0.5173, + "step": 422 + }, + { + "epoch": 0.16699565732333202, + "grad_norm": 0.5795723795890808, + "learning_rate": 4.166995657323332e-06, + "loss": 0.4111, + "step": 423 + }, + { + "epoch": 0.16739044611133044, + "grad_norm": 0.6122488379478455, + "learning_rate": 4.16502171338334e-06, + "loss": 0.4116, + "step": 424 + }, + { + "epoch": 0.16778523489932887, + "grad_norm": 0.953681230545044, + "learning_rate": 4.163047769443348e-06, + "loss": 0.4699, + "step": 425 + }, + { + "epoch": 0.1681800236873273, + "grad_norm": 0.6498748660087585, + "learning_rate": 4.161073825503356e-06, + "loss": 0.3842, + "step": 426 + }, + { + "epoch": 0.1685748124753257, + "grad_norm": 0.6858026385307312, + "learning_rate": 4.159099881563364e-06, + "loss": 0.4502, + "step": 427 + }, + { + "epoch": 0.1689696012633241, + "grad_norm": 0.632407009601593, + "learning_rate": 4.157125937623372e-06, + "loss": 0.427, + "step": 428 + }, + { + "epoch": 0.16936439005132253, + "grad_norm": 0.6518288254737854, + "learning_rate": 4.15515199368338e-06, + "loss": 0.4135, + "step": 429 + }, + { + "epoch": 0.16975917883932096, + "grad_norm": 0.6600866913795471, + "learning_rate": 4.153178049743388e-06, + "loss": 0.4208, + "step": 430 + }, + { + "epoch": 0.17015396762731938, + "grad_norm": 0.5802692174911499, + "learning_rate": 4.151204105803396e-06, + "loss": 0.382, + "step": 431 + }, + { + "epoch": 0.1705487564153178, + "grad_norm": 0.8107969164848328, + "learning_rate": 4.149230161863403e-06, + "loss": 0.4564, + "step": 432 + }, + { + "epoch": 0.17094354520331623, + "grad_norm": 0.4934249818325043, + "learning_rate": 4.147256217923411e-06, + "loss": 0.3614, + "step": 433 + }, + { + "epoch": 0.17133833399131465, + "grad_norm": 0.8876594305038452, + "learning_rate": 4.145282273983419e-06, + "loss": 0.4639, + "step": 434 + }, + { + "epoch": 0.17173312277931307, + "grad_norm": 0.5647886991500854, + "learning_rate": 4.1433083300434275e-06, + "loss": 0.4104, + "step": 435 + }, + { + "epoch": 0.1721279115673115, + "grad_norm": 0.6188619136810303, + "learning_rate": 4.141334386103435e-06, + "loss": 0.4091, + "step": 436 + }, + { + "epoch": 0.17252270035530992, + "grad_norm": 0.5614280104637146, + "learning_rate": 4.1393604421634435e-06, + "loss": 0.3975, + "step": 437 + }, + { + "epoch": 0.17291748914330832, + "grad_norm": 0.6310989856719971, + "learning_rate": 4.137386498223451e-06, + "loss": 0.433, + "step": 438 + }, + { + "epoch": 0.17331227793130674, + "grad_norm": 0.5916444063186646, + "learning_rate": 4.1354125542834586e-06, + "loss": 0.3837, + "step": 439 + }, + { + "epoch": 0.17370706671930516, + "grad_norm": 0.4599348306655884, + "learning_rate": 4.133438610343466e-06, + "loss": 0.3639, + "step": 440 + }, + { + "epoch": 0.1741018555073036, + "grad_norm": 0.6633437871932983, + "learning_rate": 4.1314646664034745e-06, + "loss": 0.4689, + "step": 441 + }, + { + "epoch": 0.174496644295302, + "grad_norm": 0.6941087245941162, + "learning_rate": 4.129490722463482e-06, + "loss": 0.3696, + "step": 442 + }, + { + "epoch": 0.17489143308330043, + "grad_norm": 0.7640632390975952, + "learning_rate": 4.1275167785234905e-06, + "loss": 0.4484, + "step": 443 + }, + { + "epoch": 0.17528622187129886, + "grad_norm": 0.5462329983711243, + "learning_rate": 4.125542834583498e-06, + "loss": 0.4368, + "step": 444 + }, + { + "epoch": 0.17568101065929728, + "grad_norm": 0.6781114339828491, + "learning_rate": 4.123568890643506e-06, + "loss": 0.455, + "step": 445 + }, + { + "epoch": 0.1760757994472957, + "grad_norm": 0.6068265438079834, + "learning_rate": 4.121594946703514e-06, + "loss": 0.444, + "step": 446 + }, + { + "epoch": 0.17647058823529413, + "grad_norm": 0.6613951325416565, + "learning_rate": 4.119621002763522e-06, + "loss": 0.4779, + "step": 447 + }, + { + "epoch": 0.17686537702329252, + "grad_norm": 0.6387900710105896, + "learning_rate": 4.11764705882353e-06, + "loss": 0.4552, + "step": 448 + }, + { + "epoch": 0.17726016581129095, + "grad_norm": 0.7232802510261536, + "learning_rate": 4.1156731148835374e-06, + "loss": 0.4468, + "step": 449 + }, + { + "epoch": 0.17765495459928937, + "grad_norm": 0.7627450823783875, + "learning_rate": 4.113699170943545e-06, + "loss": 0.509, + "step": 450 + }, + { + "epoch": 0.1780497433872878, + "grad_norm": 0.7182028889656067, + "learning_rate": 4.111725227003553e-06, + "loss": 0.4772, + "step": 451 + }, + { + "epoch": 0.17844453217528622, + "grad_norm": 0.705298662185669, + "learning_rate": 4.109751283063561e-06, + "loss": 0.3987, + "step": 452 + }, + { + "epoch": 0.17883932096328464, + "grad_norm": 0.7925073504447937, + "learning_rate": 4.107777339123569e-06, + "loss": 0.4619, + "step": 453 + }, + { + "epoch": 0.17923410975128307, + "grad_norm": 0.625927746295929, + "learning_rate": 4.105803395183577e-06, + "loss": 0.4244, + "step": 454 + }, + { + "epoch": 0.1796288985392815, + "grad_norm": 0.5721696615219116, + "learning_rate": 4.103829451243585e-06, + "loss": 0.4084, + "step": 455 + }, + { + "epoch": 0.1800236873272799, + "grad_norm": 0.8072813749313354, + "learning_rate": 4.101855507303593e-06, + "loss": 0.4795, + "step": 456 + }, + { + "epoch": 0.18041847611527834, + "grad_norm": 0.6593765020370483, + "learning_rate": 4.0998815633636e-06, + "loss": 0.4564, + "step": 457 + }, + { + "epoch": 0.18081326490327676, + "grad_norm": 0.6384336352348328, + "learning_rate": 4.097907619423609e-06, + "loss": 0.4533, + "step": 458 + }, + { + "epoch": 0.18120805369127516, + "grad_norm": 0.6349307894706726, + "learning_rate": 4.095933675483616e-06, + "loss": 0.4178, + "step": 459 + }, + { + "epoch": 0.18160284247927358, + "grad_norm": 0.7832410335540771, + "learning_rate": 4.093959731543625e-06, + "loss": 0.4473, + "step": 460 + }, + { + "epoch": 0.181997631267272, + "grad_norm": 0.8115422129631042, + "learning_rate": 4.091985787603632e-06, + "loss": 0.5362, + "step": 461 + }, + { + "epoch": 0.18239242005527043, + "grad_norm": 0.5879546999931335, + "learning_rate": 4.090011843663641e-06, + "loss": 0.4237, + "step": 462 + }, + { + "epoch": 0.18278720884326885, + "grad_norm": 0.7695683836936951, + "learning_rate": 4.088037899723648e-06, + "loss": 0.4137, + "step": 463 + }, + { + "epoch": 0.18318199763126727, + "grad_norm": 0.7183888554573059, + "learning_rate": 4.086063955783657e-06, + "loss": 0.4183, + "step": 464 + }, + { + "epoch": 0.1835767864192657, + "grad_norm": 0.6028178334236145, + "learning_rate": 4.084090011843664e-06, + "loss": 0.3985, + "step": 465 + }, + { + "epoch": 0.18397157520726412, + "grad_norm": 0.527963399887085, + "learning_rate": 4.082116067903672e-06, + "loss": 0.3779, + "step": 466 + }, + { + "epoch": 0.18436636399526254, + "grad_norm": 0.532780647277832, + "learning_rate": 4.080142123963679e-06, + "loss": 0.437, + "step": 467 + }, + { + "epoch": 0.18476115278326097, + "grad_norm": 0.8181774616241455, + "learning_rate": 4.078168180023688e-06, + "loss": 0.4781, + "step": 468 + }, + { + "epoch": 0.18515594157125936, + "grad_norm": 0.4491254389286041, + "learning_rate": 4.076194236083695e-06, + "loss": 0.3558, + "step": 469 + }, + { + "epoch": 0.1855507303592578, + "grad_norm": 0.7446666955947876, + "learning_rate": 4.074220292143704e-06, + "loss": 0.4537, + "step": 470 + }, + { + "epoch": 0.1859455191472562, + "grad_norm": 0.5064838528633118, + "learning_rate": 4.072246348203711e-06, + "loss": 0.4005, + "step": 471 + }, + { + "epoch": 0.18634030793525463, + "grad_norm": 1.5934834480285645, + "learning_rate": 4.0702724042637195e-06, + "loss": 0.4065, + "step": 472 + }, + { + "epoch": 0.18673509672325306, + "grad_norm": 0.6569105386734009, + "learning_rate": 4.068298460323727e-06, + "loss": 0.42, + "step": 473 + }, + { + "epoch": 0.18712988551125148, + "grad_norm": 0.6016618013381958, + "learning_rate": 4.066324516383735e-06, + "loss": 0.469, + "step": 474 + }, + { + "epoch": 0.1875246742992499, + "grad_norm": 0.7107083201408386, + "learning_rate": 4.064350572443743e-06, + "loss": 0.4771, + "step": 475 + }, + { + "epoch": 0.18791946308724833, + "grad_norm": 0.562773585319519, + "learning_rate": 4.062376628503751e-06, + "loss": 0.4226, + "step": 476 + }, + { + "epoch": 0.18831425187524675, + "grad_norm": 0.6228545308113098, + "learning_rate": 4.060402684563759e-06, + "loss": 0.4268, + "step": 477 + }, + { + "epoch": 0.18870904066324518, + "grad_norm": 0.705977201461792, + "learning_rate": 4.0584287406237665e-06, + "loss": 0.4474, + "step": 478 + }, + { + "epoch": 0.18910382945124357, + "grad_norm": 0.6122249364852905, + "learning_rate": 4.056454796683775e-06, + "loss": 0.3927, + "step": 479 + }, + { + "epoch": 0.189498618239242, + "grad_norm": 0.6016840934753418, + "learning_rate": 4.0544808527437825e-06, + "loss": 0.4475, + "step": 480 + }, + { + "epoch": 0.18989340702724042, + "grad_norm": 0.6881819367408752, + "learning_rate": 4.052506908803791e-06, + "loss": 0.4415, + "step": 481 + }, + { + "epoch": 0.19028819581523884, + "grad_norm": 0.6075267791748047, + "learning_rate": 4.0505329648637984e-06, + "loss": 0.4195, + "step": 482 + }, + { + "epoch": 0.19068298460323727, + "grad_norm": 0.5221434831619263, + "learning_rate": 4.048559020923806e-06, + "loss": 0.3602, + "step": 483 + }, + { + "epoch": 0.1910777733912357, + "grad_norm": 0.5319949984550476, + "learning_rate": 4.0465850769838135e-06, + "loss": 0.3616, + "step": 484 + }, + { + "epoch": 0.1914725621792341, + "grad_norm": 0.6513256430625916, + "learning_rate": 4.044611133043822e-06, + "loss": 0.4642, + "step": 485 + }, + { + "epoch": 0.19186735096723254, + "grad_norm": 0.8601086139678955, + "learning_rate": 4.0426371891038295e-06, + "loss": 0.493, + "step": 486 + }, + { + "epoch": 0.19226213975523096, + "grad_norm": 0.6346673369407654, + "learning_rate": 4.040663245163838e-06, + "loss": 0.4195, + "step": 487 + }, + { + "epoch": 0.19265692854322938, + "grad_norm": 0.6740183234214783, + "learning_rate": 4.038689301223845e-06, + "loss": 0.4249, + "step": 488 + }, + { + "epoch": 0.1930517173312278, + "grad_norm": 0.6021329760551453, + "learning_rate": 4.036715357283854e-06, + "loss": 0.3937, + "step": 489 + }, + { + "epoch": 0.1934465061192262, + "grad_norm": 0.9000159502029419, + "learning_rate": 4.034741413343861e-06, + "loss": 0.5206, + "step": 490 + }, + { + "epoch": 0.19384129490722463, + "grad_norm": 0.6569510102272034, + "learning_rate": 4.032767469403869e-06, + "loss": 0.444, + "step": 491 + }, + { + "epoch": 0.19423608369522305, + "grad_norm": 0.6282892227172852, + "learning_rate": 4.030793525463877e-06, + "loss": 0.4494, + "step": 492 + }, + { + "epoch": 0.19463087248322147, + "grad_norm": 0.8042014837265015, + "learning_rate": 4.028819581523885e-06, + "loss": 0.398, + "step": 493 + }, + { + "epoch": 0.1950256612712199, + "grad_norm": 0.7377486824989319, + "learning_rate": 4.026845637583892e-06, + "loss": 0.4381, + "step": 494 + }, + { + "epoch": 0.19542045005921832, + "grad_norm": 0.760299026966095, + "learning_rate": 4.024871693643901e-06, + "loss": 0.4761, + "step": 495 + }, + { + "epoch": 0.19581523884721674, + "grad_norm": 0.553016722202301, + "learning_rate": 4.022897749703909e-06, + "loss": 0.3941, + "step": 496 + }, + { + "epoch": 0.19621002763521517, + "grad_norm": 0.8427400588989258, + "learning_rate": 4.020923805763917e-06, + "loss": 0.4665, + "step": 497 + }, + { + "epoch": 0.1966048164232136, + "grad_norm": 0.6858325600624084, + "learning_rate": 4.018949861823925e-06, + "loss": 0.4534, + "step": 498 + }, + { + "epoch": 0.19699960521121201, + "grad_norm": 0.616628885269165, + "learning_rate": 4.016975917883933e-06, + "loss": 0.3714, + "step": 499 + }, + { + "epoch": 0.1973943939992104, + "grad_norm": 0.7953132390975952, + "learning_rate": 4.01500197394394e-06, + "loss": 0.429, + "step": 500 + }, + { + "epoch": 0.19778918278720883, + "grad_norm": 0.8366288542747498, + "learning_rate": 4.013028030003948e-06, + "loss": 0.4875, + "step": 501 + }, + { + "epoch": 0.19818397157520726, + "grad_norm": 0.7988747954368591, + "learning_rate": 4.011054086063956e-06, + "loss": 0.4249, + "step": 502 + }, + { + "epoch": 0.19857876036320568, + "grad_norm": 0.7003809213638306, + "learning_rate": 4.009080142123964e-06, + "loss": 0.4489, + "step": 503 + }, + { + "epoch": 0.1989735491512041, + "grad_norm": 0.5780694484710693, + "learning_rate": 4.007106198183972e-06, + "loss": 0.4433, + "step": 504 + }, + { + "epoch": 0.19936833793920253, + "grad_norm": 0.6272615194320679, + "learning_rate": 4.00513225424398e-06, + "loss": 0.4273, + "step": 505 + }, + { + "epoch": 0.19976312672720095, + "grad_norm": 0.7734864354133606, + "learning_rate": 4.003158310303988e-06, + "loss": 0.5069, + "step": 506 + }, + { + "epoch": 0.20015791551519937, + "grad_norm": 0.6459624171257019, + "learning_rate": 4.001184366363996e-06, + "loss": 0.3869, + "step": 507 + }, + { + "epoch": 0.2005527043031978, + "grad_norm": 0.6249256134033203, + "learning_rate": 3.999210422424003e-06, + "loss": 0.4319, + "step": 508 + }, + { + "epoch": 0.20094749309119622, + "grad_norm": 0.6015275120735168, + "learning_rate": 3.9972364784840116e-06, + "loss": 0.4374, + "step": 509 + }, + { + "epoch": 0.20134228187919462, + "grad_norm": 0.7154818177223206, + "learning_rate": 3.995262534544019e-06, + "loss": 0.3911, + "step": 510 + }, + { + "epoch": 0.20173707066719304, + "grad_norm": 0.590162992477417, + "learning_rate": 3.993288590604027e-06, + "loss": 0.4044, + "step": 511 + }, + { + "epoch": 0.20213185945519146, + "grad_norm": 0.7577177882194519, + "learning_rate": 3.991314646664035e-06, + "loss": 0.511, + "step": 512 + }, + { + "epoch": 0.2025266482431899, + "grad_norm": 0.6311262845993042, + "learning_rate": 3.989340702724043e-06, + "loss": 0.4437, + "step": 513 + }, + { + "epoch": 0.2029214370311883, + "grad_norm": 0.6016281843185425, + "learning_rate": 3.987366758784051e-06, + "loss": 0.4445, + "step": 514 + }, + { + "epoch": 0.20331622581918674, + "grad_norm": 0.5847963094711304, + "learning_rate": 3.9853928148440586e-06, + "loss": 0.39, + "step": 515 + }, + { + "epoch": 0.20371101460718516, + "grad_norm": 0.6247211694717407, + "learning_rate": 3.983418870904067e-06, + "loss": 0.4382, + "step": 516 + }, + { + "epoch": 0.20410580339518358, + "grad_norm": 0.6069718599319458, + "learning_rate": 3.9814449269640745e-06, + "loss": 0.3646, + "step": 517 + }, + { + "epoch": 0.204500592183182, + "grad_norm": 0.7093640565872192, + "learning_rate": 3.979470983024082e-06, + "loss": 0.3929, + "step": 518 + }, + { + "epoch": 0.20489538097118043, + "grad_norm": 0.748605489730835, + "learning_rate": 3.9774970390840905e-06, + "loss": 0.4661, + "step": 519 + }, + { + "epoch": 0.20529016975917883, + "grad_norm": 0.7370128631591797, + "learning_rate": 3.975523095144098e-06, + "loss": 0.469, + "step": 520 + }, + { + "epoch": 0.20568495854717725, + "grad_norm": 0.550233006477356, + "learning_rate": 3.973549151204106e-06, + "loss": 0.4449, + "step": 521 + }, + { + "epoch": 0.20607974733517567, + "grad_norm": 0.6900475025177002, + "learning_rate": 3.971575207264114e-06, + "loss": 0.4608, + "step": 522 + }, + { + "epoch": 0.2064745361231741, + "grad_norm": 0.6636027097702026, + "learning_rate": 3.969601263324122e-06, + "loss": 0.4478, + "step": 523 + }, + { + "epoch": 0.20686932491117252, + "grad_norm": 0.6791389584541321, + "learning_rate": 3.96762731938413e-06, + "loss": 0.3874, + "step": 524 + }, + { + "epoch": 0.20726411369917094, + "grad_norm": 0.6271840929985046, + "learning_rate": 3.9656533754441374e-06, + "loss": 0.4016, + "step": 525 + }, + { + "epoch": 0.20765890248716937, + "grad_norm": 0.6638932824134827, + "learning_rate": 3.963679431504146e-06, + "loss": 0.4583, + "step": 526 + }, + { + "epoch": 0.2080536912751678, + "grad_norm": 0.7181211113929749, + "learning_rate": 3.961705487564153e-06, + "loss": 0.5226, + "step": 527 + }, + { + "epoch": 0.2084484800631662, + "grad_norm": 0.660883367061615, + "learning_rate": 3.959731543624161e-06, + "loss": 0.4149, + "step": 528 + }, + { + "epoch": 0.20884326885116464, + "grad_norm": 0.6871328949928284, + "learning_rate": 3.957757599684169e-06, + "loss": 0.4611, + "step": 529 + }, + { + "epoch": 0.20923805763916306, + "grad_norm": 0.7868334054946899, + "learning_rate": 3.955783655744177e-06, + "loss": 0.4843, + "step": 530 + }, + { + "epoch": 0.20963284642716146, + "grad_norm": 0.5706552267074585, + "learning_rate": 3.953809711804185e-06, + "loss": 0.366, + "step": 531 + }, + { + "epoch": 0.21002763521515988, + "grad_norm": 0.8904498815536499, + "learning_rate": 3.951835767864193e-06, + "loss": 0.4687, + "step": 532 + }, + { + "epoch": 0.2104224240031583, + "grad_norm": 0.563812255859375, + "learning_rate": 3.949861823924201e-06, + "loss": 0.3878, + "step": 533 + }, + { + "epoch": 0.21081721279115673, + "grad_norm": 0.6027208566665649, + "learning_rate": 3.947887879984209e-06, + "loss": 0.4525, + "step": 534 + }, + { + "epoch": 0.21121200157915515, + "grad_norm": 0.627225399017334, + "learning_rate": 3.945913936044216e-06, + "loss": 0.3905, + "step": 535 + }, + { + "epoch": 0.21160679036715357, + "grad_norm": 0.6952453851699829, + "learning_rate": 3.943939992104224e-06, + "loss": 0.4509, + "step": 536 + }, + { + "epoch": 0.212001579155152, + "grad_norm": 0.6549723148345947, + "learning_rate": 3.941966048164232e-06, + "loss": 0.4659, + "step": 537 + }, + { + "epoch": 0.21239636794315042, + "grad_norm": 0.6564276218414307, + "learning_rate": 3.939992104224241e-06, + "loss": 0.4401, + "step": 538 + }, + { + "epoch": 0.21279115673114884, + "grad_norm": 0.7083191275596619, + "learning_rate": 3.938018160284248e-06, + "loss": 0.4741, + "step": 539 + }, + { + "epoch": 0.21318594551914727, + "grad_norm": 0.7205274701118469, + "learning_rate": 3.936044216344257e-06, + "loss": 0.4407, + "step": 540 + }, + { + "epoch": 0.21358073430714566, + "grad_norm": 0.7942872643470764, + "learning_rate": 3.934070272404264e-06, + "loss": 0.4572, + "step": 541 + }, + { + "epoch": 0.2139755230951441, + "grad_norm": 0.6789839267730713, + "learning_rate": 3.9320963284642726e-06, + "loss": 0.3607, + "step": 542 + }, + { + "epoch": 0.2143703118831425, + "grad_norm": 0.6556216478347778, + "learning_rate": 3.93012238452428e-06, + "loss": 0.4507, + "step": 543 + }, + { + "epoch": 0.21476510067114093, + "grad_norm": 0.5574567317962646, + "learning_rate": 3.928148440584288e-06, + "loss": 0.3563, + "step": 544 + }, + { + "epoch": 0.21515988945913936, + "grad_norm": 0.6222922801971436, + "learning_rate": 3.926174496644295e-06, + "loss": 0.4159, + "step": 545 + }, + { + "epoch": 0.21555467824713778, + "grad_norm": 0.5839349627494812, + "learning_rate": 3.924200552704304e-06, + "loss": 0.3556, + "step": 546 + }, + { + "epoch": 0.2159494670351362, + "grad_norm": 0.5864849090576172, + "learning_rate": 3.922226608764311e-06, + "loss": 0.4313, + "step": 547 + }, + { + "epoch": 0.21634425582313463, + "grad_norm": 0.7493896484375, + "learning_rate": 3.9202526648243195e-06, + "loss": 0.4306, + "step": 548 + }, + { + "epoch": 0.21673904461113305, + "grad_norm": 0.813810408115387, + "learning_rate": 3.918278720884327e-06, + "loss": 0.476, + "step": 549 + }, + { + "epoch": 0.21713383339913148, + "grad_norm": 0.6720209717750549, + "learning_rate": 3.9163047769443355e-06, + "loss": 0.356, + "step": 550 + }, + { + "epoch": 0.21752862218712987, + "grad_norm": 0.5846362709999084, + "learning_rate": 3.914330833004343e-06, + "loss": 0.3564, + "step": 551 + }, + { + "epoch": 0.2179234109751283, + "grad_norm": 0.6603456735610962, + "learning_rate": 3.912356889064351e-06, + "loss": 0.3809, + "step": 552 + }, + { + "epoch": 0.21831819976312672, + "grad_norm": 0.6784287095069885, + "learning_rate": 3.910382945124359e-06, + "loss": 0.4592, + "step": 553 + }, + { + "epoch": 0.21871298855112514, + "grad_norm": 0.6482931971549988, + "learning_rate": 3.9084090011843665e-06, + "loss": 0.4487, + "step": 554 + }, + { + "epoch": 0.21910777733912357, + "grad_norm": 0.6254132986068726, + "learning_rate": 3.906435057244374e-06, + "loss": 0.4174, + "step": 555 + }, + { + "epoch": 0.219502566127122, + "grad_norm": 0.7381472587585449, + "learning_rate": 3.9044611133043825e-06, + "loss": 0.4305, + "step": 556 + }, + { + "epoch": 0.2198973549151204, + "grad_norm": 0.5138326287269592, + "learning_rate": 3.90248716936439e-06, + "loss": 0.3887, + "step": 557 + }, + { + "epoch": 0.22029214370311884, + "grad_norm": 0.6965186595916748, + "learning_rate": 3.9005132254243984e-06, + "loss": 0.445, + "step": 558 + }, + { + "epoch": 0.22068693249111726, + "grad_norm": 0.7094748616218567, + "learning_rate": 3.898539281484407e-06, + "loss": 0.4838, + "step": 559 + }, + { + "epoch": 0.22108172127911568, + "grad_norm": 0.5447982549667358, + "learning_rate": 3.896565337544414e-06, + "loss": 0.3575, + "step": 560 + }, + { + "epoch": 0.2214765100671141, + "grad_norm": 0.6720840334892273, + "learning_rate": 3.894591393604422e-06, + "loss": 0.3997, + "step": 561 + }, + { + "epoch": 0.2218712988551125, + "grad_norm": 0.7565316557884216, + "learning_rate": 3.8926174496644295e-06, + "loss": 0.4306, + "step": 562 + }, + { + "epoch": 0.22226608764311093, + "grad_norm": 0.7003496289253235, + "learning_rate": 3.890643505724438e-06, + "loss": 0.4733, + "step": 563 + }, + { + "epoch": 0.22266087643110935, + "grad_norm": 0.8890902996063232, + "learning_rate": 3.888669561784445e-06, + "loss": 0.4588, + "step": 564 + }, + { + "epoch": 0.22305566521910777, + "grad_norm": 0.7157787680625916, + "learning_rate": 3.886695617844454e-06, + "loss": 0.4592, + "step": 565 + }, + { + "epoch": 0.2234504540071062, + "grad_norm": 0.7353807091712952, + "learning_rate": 3.884721673904461e-06, + "loss": 0.3816, + "step": 566 + }, + { + "epoch": 0.22384524279510462, + "grad_norm": 0.6165068745613098, + "learning_rate": 3.88274772996447e-06, + "loss": 0.4254, + "step": 567 + }, + { + "epoch": 0.22424003158310304, + "grad_norm": 0.616421103477478, + "learning_rate": 3.880773786024477e-06, + "loss": 0.4329, + "step": 568 + }, + { + "epoch": 0.22463482037110147, + "grad_norm": 0.6141782999038696, + "learning_rate": 3.878799842084485e-06, + "loss": 0.3822, + "step": 569 + }, + { + "epoch": 0.2250296091590999, + "grad_norm": 0.6602972149848938, + "learning_rate": 3.876825898144493e-06, + "loss": 0.4492, + "step": 570 + }, + { + "epoch": 0.22542439794709832, + "grad_norm": 0.6723212599754333, + "learning_rate": 3.874851954204501e-06, + "loss": 0.4103, + "step": 571 + }, + { + "epoch": 0.2258191867350967, + "grad_norm": 0.6857706904411316, + "learning_rate": 3.872878010264508e-06, + "loss": 0.442, + "step": 572 + }, + { + "epoch": 0.22621397552309513, + "grad_norm": 0.5197257995605469, + "learning_rate": 3.870904066324517e-06, + "loss": 0.3854, + "step": 573 + }, + { + "epoch": 0.22660876431109356, + "grad_norm": 0.7155500650405884, + "learning_rate": 3.868930122384524e-06, + "loss": 0.4276, + "step": 574 + }, + { + "epoch": 0.22700355309909198, + "grad_norm": 0.7453821897506714, + "learning_rate": 3.866956178444533e-06, + "loss": 0.4443, + "step": 575 + }, + { + "epoch": 0.2273983418870904, + "grad_norm": 0.6429493427276611, + "learning_rate": 3.86498223450454e-06, + "loss": 0.42, + "step": 576 + }, + { + "epoch": 0.22779313067508883, + "grad_norm": 0.6607668399810791, + "learning_rate": 3.863008290564549e-06, + "loss": 0.4316, + "step": 577 + }, + { + "epoch": 0.22818791946308725, + "grad_norm": 0.660827100276947, + "learning_rate": 3.861034346624556e-06, + "loss": 0.4098, + "step": 578 + }, + { + "epoch": 0.22858270825108568, + "grad_norm": 0.7012804746627808, + "learning_rate": 3.859060402684564e-06, + "loss": 0.4683, + "step": 579 + }, + { + "epoch": 0.2289774970390841, + "grad_norm": 0.5026301145553589, + "learning_rate": 3.857086458744572e-06, + "loss": 0.3362, + "step": 580 + }, + { + "epoch": 0.22937228582708252, + "grad_norm": 0.6303160786628723, + "learning_rate": 3.85511251480458e-06, + "loss": 0.4089, + "step": 581 + }, + { + "epoch": 0.22976707461508092, + "grad_norm": 0.8012593388557434, + "learning_rate": 3.853138570864588e-06, + "loss": 0.4479, + "step": 582 + }, + { + "epoch": 0.23016186340307934, + "grad_norm": 0.7084465622901917, + "learning_rate": 3.851164626924596e-06, + "loss": 0.4692, + "step": 583 + }, + { + "epoch": 0.23055665219107777, + "grad_norm": 0.6967036724090576, + "learning_rate": 3.849190682984604e-06, + "loss": 0.4316, + "step": 584 + }, + { + "epoch": 0.2309514409790762, + "grad_norm": 0.6933826804161072, + "learning_rate": 3.8472167390446116e-06, + "loss": 0.4286, + "step": 585 + }, + { + "epoch": 0.2313462297670746, + "grad_norm": 0.5712121725082397, + "learning_rate": 3.845242795104619e-06, + "loss": 0.4055, + "step": 586 + }, + { + "epoch": 0.23174101855507304, + "grad_norm": 0.7157759070396423, + "learning_rate": 3.8432688511646275e-06, + "loss": 0.4604, + "step": 587 + }, + { + "epoch": 0.23213580734307146, + "grad_norm": 0.7555333375930786, + "learning_rate": 3.841294907224635e-06, + "loss": 0.4729, + "step": 588 + }, + { + "epoch": 0.23253059613106988, + "grad_norm": 0.5798461437225342, + "learning_rate": 3.839320963284643e-06, + "loss": 0.4095, + "step": 589 + }, + { + "epoch": 0.2329253849190683, + "grad_norm": 0.5829660296440125, + "learning_rate": 3.837347019344651e-06, + "loss": 0.4223, + "step": 590 + }, + { + "epoch": 0.23332017370706673, + "grad_norm": 0.8913484811782837, + "learning_rate": 3.8353730754046586e-06, + "loss": 0.5004, + "step": 591 + }, + { + "epoch": 0.23371496249506515, + "grad_norm": 0.6719018816947937, + "learning_rate": 3.833399131464667e-06, + "loss": 0.4723, + "step": 592 + }, + { + "epoch": 0.23410975128306355, + "grad_norm": 0.7503561973571777, + "learning_rate": 3.8314251875246745e-06, + "loss": 0.4634, + "step": 593 + }, + { + "epoch": 0.23450454007106197, + "grad_norm": 0.5567938089370728, + "learning_rate": 3.829451243584683e-06, + "loss": 0.4608, + "step": 594 + }, + { + "epoch": 0.2348993288590604, + "grad_norm": 0.6769271492958069, + "learning_rate": 3.8274772996446904e-06, + "loss": 0.4638, + "step": 595 + }, + { + "epoch": 0.23529411764705882, + "grad_norm": 0.5989348888397217, + "learning_rate": 3.825503355704698e-06, + "loss": 0.432, + "step": 596 + }, + { + "epoch": 0.23568890643505724, + "grad_norm": 0.6269996166229248, + "learning_rate": 3.8235294117647055e-06, + "loss": 0.4105, + "step": 597 + }, + { + "epoch": 0.23608369522305567, + "grad_norm": 0.6063553094863892, + "learning_rate": 3.821555467824714e-06, + "loss": 0.4507, + "step": 598 + }, + { + "epoch": 0.2364784840110541, + "grad_norm": 0.6389642357826233, + "learning_rate": 3.819581523884722e-06, + "loss": 0.4832, + "step": 599 + }, + { + "epoch": 0.23687327279905251, + "grad_norm": 0.43400922417640686, + "learning_rate": 3.81760757994473e-06, + "loss": 0.3192, + "step": 600 + }, + { + "epoch": 0.23726806158705094, + "grad_norm": 0.6386098265647888, + "learning_rate": 3.815633636004738e-06, + "loss": 0.3789, + "step": 601 + }, + { + "epoch": 0.23766285037504936, + "grad_norm": 0.6854510307312012, + "learning_rate": 3.8136596920647454e-06, + "loss": 0.4865, + "step": 602 + }, + { + "epoch": 0.23805763916304776, + "grad_norm": 0.6150557398796082, + "learning_rate": 3.811685748124754e-06, + "loss": 0.4138, + "step": 603 + }, + { + "epoch": 0.23845242795104618, + "grad_norm": 0.6942728757858276, + "learning_rate": 3.8097118041847614e-06, + "loss": 0.4307, + "step": 604 + }, + { + "epoch": 0.2388472167390446, + "grad_norm": 0.5928500890731812, + "learning_rate": 3.8077378602447698e-06, + "loss": 0.309, + "step": 605 + }, + { + "epoch": 0.23924200552704303, + "grad_norm": 0.692861795425415, + "learning_rate": 3.8057639163047773e-06, + "loss": 0.5407, + "step": 606 + }, + { + "epoch": 0.23963679431504145, + "grad_norm": 0.7186422944068909, + "learning_rate": 3.8037899723647853e-06, + "loss": 0.4197, + "step": 607 + }, + { + "epoch": 0.24003158310303987, + "grad_norm": 0.6915371417999268, + "learning_rate": 3.801816028424793e-06, + "loss": 0.4699, + "step": 608 + }, + { + "epoch": 0.2404263718910383, + "grad_norm": 0.5743345022201538, + "learning_rate": 3.7998420844848012e-06, + "loss": 0.4313, + "step": 609 + }, + { + "epoch": 0.24082116067903672, + "grad_norm": 0.6521217226982117, + "learning_rate": 3.7978681405448088e-06, + "loss": 0.407, + "step": 610 + }, + { + "epoch": 0.24121594946703515, + "grad_norm": 0.6078217029571533, + "learning_rate": 3.7958941966048167e-06, + "loss": 0.4371, + "step": 611 + }, + { + "epoch": 0.24161073825503357, + "grad_norm": 0.6805148720741272, + "learning_rate": 3.7939202526648243e-06, + "loss": 0.4073, + "step": 612 + }, + { + "epoch": 0.24200552704303196, + "grad_norm": 0.6683278679847717, + "learning_rate": 3.7919463087248327e-06, + "loss": 0.4647, + "step": 613 + }, + { + "epoch": 0.2424003158310304, + "grad_norm": 0.5677973031997681, + "learning_rate": 3.7899723647848402e-06, + "loss": 0.4117, + "step": 614 + }, + { + "epoch": 0.2427951046190288, + "grad_norm": 0.5761098861694336, + "learning_rate": 3.787998420844848e-06, + "loss": 0.4232, + "step": 615 + }, + { + "epoch": 0.24318989340702724, + "grad_norm": 0.8509823679924011, + "learning_rate": 3.786024476904856e-06, + "loss": 0.4877, + "step": 616 + }, + { + "epoch": 0.24358468219502566, + "grad_norm": 0.5814547538757324, + "learning_rate": 3.784050532964864e-06, + "loss": 0.4199, + "step": 617 + }, + { + "epoch": 0.24397947098302408, + "grad_norm": 0.6383735537528992, + "learning_rate": 3.7820765890248717e-06, + "loss": 0.4069, + "step": 618 + }, + { + "epoch": 0.2443742597710225, + "grad_norm": 0.7193318605422974, + "learning_rate": 3.78010264508488e-06, + "loss": 0.4223, + "step": 619 + }, + { + "epoch": 0.24476904855902093, + "grad_norm": 0.6534525156021118, + "learning_rate": 3.778128701144888e-06, + "loss": 0.4854, + "step": 620 + }, + { + "epoch": 0.24516383734701935, + "grad_norm": 0.6463202834129333, + "learning_rate": 3.7761547572048956e-06, + "loss": 0.4236, + "step": 621 + }, + { + "epoch": 0.24555862613501778, + "grad_norm": 0.7497007250785828, + "learning_rate": 3.774180813264904e-06, + "loss": 0.4382, + "step": 622 + }, + { + "epoch": 0.24595341492301617, + "grad_norm": 0.638806164264679, + "learning_rate": 3.7722068693249116e-06, + "loss": 0.4042, + "step": 623 + }, + { + "epoch": 0.2463482037110146, + "grad_norm": 0.6678193807601929, + "learning_rate": 3.7702329253849195e-06, + "loss": 0.4481, + "step": 624 + }, + { + "epoch": 0.24674299249901302, + "grad_norm": 0.6898274421691895, + "learning_rate": 3.768258981444927e-06, + "loss": 0.424, + "step": 625 + }, + { + "epoch": 0.24713778128701144, + "grad_norm": 0.5956227779388428, + "learning_rate": 3.7662850375049355e-06, + "loss": 0.3671, + "step": 626 + }, + { + "epoch": 0.24753257007500987, + "grad_norm": 0.6023910045623779, + "learning_rate": 3.764311093564943e-06, + "loss": 0.3972, + "step": 627 + }, + { + "epoch": 0.2479273588630083, + "grad_norm": 0.6596775650978088, + "learning_rate": 3.762337149624951e-06, + "loss": 0.3987, + "step": 628 + }, + { + "epoch": 0.2483221476510067, + "grad_norm": 0.4788181781768799, + "learning_rate": 3.7603632056849586e-06, + "loss": 0.3814, + "step": 629 + }, + { + "epoch": 0.24871693643900514, + "grad_norm": 0.6672987937927246, + "learning_rate": 3.758389261744967e-06, + "loss": 0.433, + "step": 630 + }, + { + "epoch": 0.24911172522700356, + "grad_norm": 0.7319859266281128, + "learning_rate": 3.7564153178049745e-06, + "loss": 0.4472, + "step": 631 + }, + { + "epoch": 0.24950651401500198, + "grad_norm": 0.7042807340621948, + "learning_rate": 3.7544413738649825e-06, + "loss": 0.4328, + "step": 632 + }, + { + "epoch": 0.2499013028030004, + "grad_norm": 0.7395254373550415, + "learning_rate": 3.7524674299249904e-06, + "loss": 0.3983, + "step": 633 + }, + { + "epoch": 0.2502960915909988, + "grad_norm": 0.7854376435279846, + "learning_rate": 3.7504934859849984e-06, + "loss": 0.5128, + "step": 634 + }, + { + "epoch": 0.2506908803789972, + "grad_norm": 0.6689158082008362, + "learning_rate": 3.748519542045006e-06, + "loss": 0.43, + "step": 635 + }, + { + "epoch": 0.25108566916699565, + "grad_norm": 0.6063249111175537, + "learning_rate": 3.7465455981050144e-06, + "loss": 0.4184, + "step": 636 + }, + { + "epoch": 0.2514804579549941, + "grad_norm": 0.8429774045944214, + "learning_rate": 3.744571654165022e-06, + "loss": 0.4206, + "step": 637 + }, + { + "epoch": 0.2518752467429925, + "grad_norm": 0.9129395484924316, + "learning_rate": 3.74259771022503e-06, + "loss": 0.4456, + "step": 638 + }, + { + "epoch": 0.2522700355309909, + "grad_norm": 0.4899393618106842, + "learning_rate": 3.7406237662850374e-06, + "loss": 0.3699, + "step": 639 + }, + { + "epoch": 0.25266482431898935, + "grad_norm": 0.7456104159355164, + "learning_rate": 3.738649822345046e-06, + "loss": 0.4589, + "step": 640 + }, + { + "epoch": 0.25305961310698777, + "grad_norm": 0.6447864770889282, + "learning_rate": 3.736675878405054e-06, + "loss": 0.4407, + "step": 641 + }, + { + "epoch": 0.2534544018949862, + "grad_norm": 0.8407905101776123, + "learning_rate": 3.7347019344650614e-06, + "loss": 0.4644, + "step": 642 + }, + { + "epoch": 0.2538491906829846, + "grad_norm": 0.4660954177379608, + "learning_rate": 3.7327279905250698e-06, + "loss": 0.369, + "step": 643 + }, + { + "epoch": 0.25424397947098304, + "grad_norm": 0.5880573391914368, + "learning_rate": 3.7307540465850773e-06, + "loss": 0.4362, + "step": 644 + }, + { + "epoch": 0.25463876825898146, + "grad_norm": 0.5493758916854858, + "learning_rate": 3.7287801026450853e-06, + "loss": 0.394, + "step": 645 + }, + { + "epoch": 0.2550335570469799, + "grad_norm": 0.5331719517707825, + "learning_rate": 3.726806158705093e-06, + "loss": 0.3955, + "step": 646 + }, + { + "epoch": 0.2554283458349783, + "grad_norm": 0.5906451344490051, + "learning_rate": 3.7248322147651012e-06, + "loss": 0.3891, + "step": 647 + }, + { + "epoch": 0.25582313462297673, + "grad_norm": 0.6999332308769226, + "learning_rate": 3.7228582708251088e-06, + "loss": 0.4042, + "step": 648 + }, + { + "epoch": 0.2562179234109751, + "grad_norm": 0.7725821733474731, + "learning_rate": 3.7208843268851167e-06, + "loss": 0.5043, + "step": 649 + }, + { + "epoch": 0.2566127121989735, + "grad_norm": 0.6613204479217529, + "learning_rate": 3.7189103829451247e-06, + "loss": 0.438, + "step": 650 + }, + { + "epoch": 0.25700750098697195, + "grad_norm": 0.6996300220489502, + "learning_rate": 3.7169364390051327e-06, + "loss": 0.4473, + "step": 651 + }, + { + "epoch": 0.25740228977497037, + "grad_norm": 0.6341385245323181, + "learning_rate": 3.7149624950651402e-06, + "loss": 0.4094, + "step": 652 + }, + { + "epoch": 0.2577970785629688, + "grad_norm": 0.6548272967338562, + "learning_rate": 3.7129885511251486e-06, + "loss": 0.4003, + "step": 653 + }, + { + "epoch": 0.2581918673509672, + "grad_norm": 0.5878058075904846, + "learning_rate": 3.711014607185156e-06, + "loss": 0.3753, + "step": 654 + }, + { + "epoch": 0.25858665613896564, + "grad_norm": 0.5443089008331299, + "learning_rate": 3.709040663245164e-06, + "loss": 0.3801, + "step": 655 + }, + { + "epoch": 0.25898144492696407, + "grad_norm": 1.096781849861145, + "learning_rate": 3.7070667193051717e-06, + "loss": 0.5058, + "step": 656 + }, + { + "epoch": 0.2593762337149625, + "grad_norm": 0.808201253414154, + "learning_rate": 3.70509277536518e-06, + "loss": 0.4735, + "step": 657 + }, + { + "epoch": 0.2597710225029609, + "grad_norm": 0.7726473808288574, + "learning_rate": 3.7031188314251876e-06, + "loss": 0.4317, + "step": 658 + }, + { + "epoch": 0.26016581129095934, + "grad_norm": 0.6355069875717163, + "learning_rate": 3.7011448874851956e-06, + "loss": 0.4251, + "step": 659 + }, + { + "epoch": 0.26056060007895776, + "grad_norm": 0.5835087299346924, + "learning_rate": 3.699170943545204e-06, + "loss": 0.4414, + "step": 660 + }, + { + "epoch": 0.2609553888669562, + "grad_norm": 0.6133544445037842, + "learning_rate": 3.6971969996052116e-06, + "loss": 0.3988, + "step": 661 + }, + { + "epoch": 0.2613501776549546, + "grad_norm": 0.5736113786697388, + "learning_rate": 3.6952230556652195e-06, + "loss": 0.3945, + "step": 662 + }, + { + "epoch": 0.26174496644295303, + "grad_norm": 0.849559485912323, + "learning_rate": 3.693249111725227e-06, + "loss": 0.493, + "step": 663 + }, + { + "epoch": 0.26213975523095145, + "grad_norm": 0.8318068385124207, + "learning_rate": 3.6912751677852355e-06, + "loss": 0.4689, + "step": 664 + }, + { + "epoch": 0.2625345440189499, + "grad_norm": 0.6233395338058472, + "learning_rate": 3.689301223845243e-06, + "loss": 0.4007, + "step": 665 + }, + { + "epoch": 0.2629293328069483, + "grad_norm": 0.6490706205368042, + "learning_rate": 3.687327279905251e-06, + "loss": 0.4202, + "step": 666 + }, + { + "epoch": 0.2633241215949467, + "grad_norm": 0.759155809879303, + "learning_rate": 3.685353335965259e-06, + "loss": 0.4213, + "step": 667 + }, + { + "epoch": 0.26371891038294515, + "grad_norm": 0.5595030188560486, + "learning_rate": 3.683379392025267e-06, + "loss": 0.3524, + "step": 668 + }, + { + "epoch": 0.26411369917094357, + "grad_norm": 0.7769655585289001, + "learning_rate": 3.6814054480852745e-06, + "loss": 0.4267, + "step": 669 + }, + { + "epoch": 0.26450848795894194, + "grad_norm": 0.7676974534988403, + "learning_rate": 3.679431504145283e-06, + "loss": 0.474, + "step": 670 + }, + { + "epoch": 0.26490327674694036, + "grad_norm": 0.6544408202171326, + "learning_rate": 3.6774575602052904e-06, + "loss": 0.4013, + "step": 671 + }, + { + "epoch": 0.2652980655349388, + "grad_norm": 0.6438421010971069, + "learning_rate": 3.6754836162652984e-06, + "loss": 0.464, + "step": 672 + }, + { + "epoch": 0.2656928543229372, + "grad_norm": 0.5105613470077515, + "learning_rate": 3.673509672325306e-06, + "loss": 0.3606, + "step": 673 + }, + { + "epoch": 0.26608764311093563, + "grad_norm": 0.7999045848846436, + "learning_rate": 3.6715357283853144e-06, + "loss": 0.4633, + "step": 674 + }, + { + "epoch": 0.26648243189893406, + "grad_norm": 0.7446785569190979, + "learning_rate": 3.669561784445322e-06, + "loss": 0.5295, + "step": 675 + }, + { + "epoch": 0.2668772206869325, + "grad_norm": 0.5813772082328796, + "learning_rate": 3.66758784050533e-06, + "loss": 0.4084, + "step": 676 + }, + { + "epoch": 0.2672720094749309, + "grad_norm": 0.5862618684768677, + "learning_rate": 3.6656138965653374e-06, + "loss": 0.4239, + "step": 677 + }, + { + "epoch": 0.26766679826292933, + "grad_norm": 0.6126624941825867, + "learning_rate": 3.663639952625346e-06, + "loss": 0.4074, + "step": 678 + }, + { + "epoch": 0.26806158705092775, + "grad_norm": 0.5714239478111267, + "learning_rate": 3.6616660086853534e-06, + "loss": 0.3923, + "step": 679 + }, + { + "epoch": 0.2684563758389262, + "grad_norm": 0.6525805592536926, + "learning_rate": 3.6596920647453614e-06, + "loss": 0.4015, + "step": 680 + }, + { + "epoch": 0.2688511646269246, + "grad_norm": 0.5838556289672852, + "learning_rate": 3.6577181208053697e-06, + "loss": 0.3794, + "step": 681 + }, + { + "epoch": 0.269245953414923, + "grad_norm": 0.6373186707496643, + "learning_rate": 3.6557441768653773e-06, + "loss": 0.4065, + "step": 682 + }, + { + "epoch": 0.26964074220292145, + "grad_norm": 0.6991015672683716, + "learning_rate": 3.6537702329253853e-06, + "loss": 0.4476, + "step": 683 + }, + { + "epoch": 0.27003553099091987, + "grad_norm": 0.5563204288482666, + "learning_rate": 3.6517962889853932e-06, + "loss": 0.4322, + "step": 684 + }, + { + "epoch": 0.2704303197789183, + "grad_norm": 0.638230562210083, + "learning_rate": 3.6498223450454012e-06, + "loss": 0.4677, + "step": 685 + }, + { + "epoch": 0.2708251085669167, + "grad_norm": 0.5944691896438599, + "learning_rate": 3.6478484011054088e-06, + "loss": 0.3837, + "step": 686 + }, + { + "epoch": 0.27121989735491514, + "grad_norm": 0.8056315779685974, + "learning_rate": 3.645874457165417e-06, + "loss": 0.494, + "step": 687 + }, + { + "epoch": 0.27161468614291356, + "grad_norm": 0.6971708536148071, + "learning_rate": 3.6439005132254247e-06, + "loss": 0.4689, + "step": 688 + }, + { + "epoch": 0.272009474930912, + "grad_norm": 0.5443761944770813, + "learning_rate": 3.6419265692854327e-06, + "loss": 0.3567, + "step": 689 + }, + { + "epoch": 0.27240426371891036, + "grad_norm": 0.727101743221283, + "learning_rate": 3.6399526253454402e-06, + "loss": 0.4787, + "step": 690 + }, + { + "epoch": 0.2727990525069088, + "grad_norm": 0.6470316648483276, + "learning_rate": 3.6379786814054486e-06, + "loss": 0.4225, + "step": 691 + }, + { + "epoch": 0.2731938412949072, + "grad_norm": 0.7788310050964355, + "learning_rate": 3.636004737465456e-06, + "loss": 0.4862, + "step": 692 + }, + { + "epoch": 0.2735886300829056, + "grad_norm": 0.6003559231758118, + "learning_rate": 3.634030793525464e-06, + "loss": 0.4212, + "step": 693 + }, + { + "epoch": 0.27398341887090405, + "grad_norm": 0.6185204386711121, + "learning_rate": 3.6320568495854717e-06, + "loss": 0.4299, + "step": 694 + }, + { + "epoch": 0.2743782076589025, + "grad_norm": 0.693322479724884, + "learning_rate": 3.63008290564548e-06, + "loss": 0.4674, + "step": 695 + }, + { + "epoch": 0.2747729964469009, + "grad_norm": 0.656721830368042, + "learning_rate": 3.6281089617054876e-06, + "loss": 0.4797, + "step": 696 + }, + { + "epoch": 0.2751677852348993, + "grad_norm": 0.7847813367843628, + "learning_rate": 3.6261350177654956e-06, + "loss": 0.47, + "step": 697 + }, + { + "epoch": 0.27556257402289774, + "grad_norm": 0.6410577297210693, + "learning_rate": 3.6241610738255036e-06, + "loss": 0.4588, + "step": 698 + }, + { + "epoch": 0.27595736281089617, + "grad_norm": 0.7136773467063904, + "learning_rate": 3.6221871298855116e-06, + "loss": 0.4679, + "step": 699 + }, + { + "epoch": 0.2763521515988946, + "grad_norm": 0.7145960927009583, + "learning_rate": 3.620213185945519e-06, + "loss": 0.4282, + "step": 700 + }, + { + "epoch": 0.276746940386893, + "grad_norm": 0.5854971408843994, + "learning_rate": 3.6182392420055275e-06, + "loss": 0.4086, + "step": 701 + }, + { + "epoch": 0.27714172917489144, + "grad_norm": 0.5819379687309265, + "learning_rate": 3.6162652980655355e-06, + "loss": 0.3662, + "step": 702 + }, + { + "epoch": 0.27753651796288986, + "grad_norm": 0.6564990282058716, + "learning_rate": 3.614291354125543e-06, + "loss": 0.4505, + "step": 703 + }, + { + "epoch": 0.2779313067508883, + "grad_norm": 0.7579885721206665, + "learning_rate": 3.6123174101855514e-06, + "loss": 0.4775, + "step": 704 + }, + { + "epoch": 0.2783260955388867, + "grad_norm": 0.6229938864707947, + "learning_rate": 3.610343466245559e-06, + "loss": 0.4214, + "step": 705 + }, + { + "epoch": 0.27872088432688513, + "grad_norm": 0.825949490070343, + "learning_rate": 3.608369522305567e-06, + "loss": 0.4596, + "step": 706 + }, + { + "epoch": 0.27911567311488356, + "grad_norm": 0.641761302947998, + "learning_rate": 3.6063955783655745e-06, + "loss": 0.4281, + "step": 707 + }, + { + "epoch": 0.279510461902882, + "grad_norm": 0.7073618769645691, + "learning_rate": 3.604421634425583e-06, + "loss": 0.4097, + "step": 708 + }, + { + "epoch": 0.2799052506908804, + "grad_norm": 0.7196075320243835, + "learning_rate": 3.6024476904855904e-06, + "loss": 0.425, + "step": 709 + }, + { + "epoch": 0.2803000394788788, + "grad_norm": 0.7486291527748108, + "learning_rate": 3.6004737465455984e-06, + "loss": 0.4863, + "step": 710 + }, + { + "epoch": 0.2806948282668772, + "grad_norm": 0.6340676546096802, + "learning_rate": 3.598499802605606e-06, + "loss": 0.4351, + "step": 711 + }, + { + "epoch": 0.2810896170548756, + "grad_norm": 0.76716148853302, + "learning_rate": 3.5965258586656144e-06, + "loss": 0.4514, + "step": 712 + }, + { + "epoch": 0.28148440584287404, + "grad_norm": 0.6242313981056213, + "learning_rate": 3.594551914725622e-06, + "loss": 0.3936, + "step": 713 + }, + { + "epoch": 0.28187919463087246, + "grad_norm": 0.6105828881263733, + "learning_rate": 3.59257797078563e-06, + "loss": 0.4022, + "step": 714 + }, + { + "epoch": 0.2822739834188709, + "grad_norm": 0.829490065574646, + "learning_rate": 3.590604026845638e-06, + "loss": 0.5927, + "step": 715 + }, + { + "epoch": 0.2826687722068693, + "grad_norm": 0.6734004616737366, + "learning_rate": 3.588630082905646e-06, + "loss": 0.4483, + "step": 716 + }, + { + "epoch": 0.28306356099486774, + "grad_norm": 0.6129070520401001, + "learning_rate": 3.5866561389656534e-06, + "loss": 0.4656, + "step": 717 + }, + { + "epoch": 0.28345834978286616, + "grad_norm": 0.5530596375465393, + "learning_rate": 3.5846821950256618e-06, + "loss": 0.4064, + "step": 718 + }, + { + "epoch": 0.2838531385708646, + "grad_norm": 0.7357283234596252, + "learning_rate": 3.5827082510856693e-06, + "loss": 0.42, + "step": 719 + }, + { + "epoch": 0.284247927358863, + "grad_norm": 0.5985270142555237, + "learning_rate": 3.5807343071456773e-06, + "loss": 0.4302, + "step": 720 + }, + { + "epoch": 0.28464271614686143, + "grad_norm": 0.6565999388694763, + "learning_rate": 3.578760363205685e-06, + "loss": 0.4608, + "step": 721 + }, + { + "epoch": 0.28503750493485985, + "grad_norm": 0.7341988682746887, + "learning_rate": 3.5767864192656932e-06, + "loss": 0.4872, + "step": 722 + }, + { + "epoch": 0.2854322937228583, + "grad_norm": 0.7215821146965027, + "learning_rate": 3.5748124753257012e-06, + "loss": 0.5202, + "step": 723 + }, + { + "epoch": 0.2858270825108567, + "grad_norm": 0.6674136519432068, + "learning_rate": 3.5728385313857088e-06, + "loss": 0.438, + "step": 724 + }, + { + "epoch": 0.2862218712988551, + "grad_norm": 0.7237642407417297, + "learning_rate": 3.570864587445717e-06, + "loss": 0.4878, + "step": 725 + }, + { + "epoch": 0.28661666008685355, + "grad_norm": 0.7837308645248413, + "learning_rate": 3.5688906435057247e-06, + "loss": 0.5044, + "step": 726 + }, + { + "epoch": 0.28701144887485197, + "grad_norm": 0.6234360337257385, + "learning_rate": 3.5669166995657327e-06, + "loss": 0.4276, + "step": 727 + }, + { + "epoch": 0.2874062376628504, + "grad_norm": 0.5685781836509705, + "learning_rate": 3.5649427556257402e-06, + "loss": 0.3784, + "step": 728 + }, + { + "epoch": 0.2878010264508488, + "grad_norm": 0.5778893232345581, + "learning_rate": 3.5629688116857486e-06, + "loss": 0.3939, + "step": 729 + }, + { + "epoch": 0.28819581523884724, + "grad_norm": 0.6193323135375977, + "learning_rate": 3.560994867745756e-06, + "loss": 0.4381, + "step": 730 + }, + { + "epoch": 0.28859060402684567, + "grad_norm": 0.7068705558776855, + "learning_rate": 3.5590209238057646e-06, + "loss": 0.4655, + "step": 731 + }, + { + "epoch": 0.28898539281484403, + "grad_norm": 0.6048031449317932, + "learning_rate": 3.557046979865772e-06, + "loss": 0.4262, + "step": 732 + }, + { + "epoch": 0.28938018160284246, + "grad_norm": 0.7921766042709351, + "learning_rate": 3.55507303592578e-06, + "loss": 0.4785, + "step": 733 + }, + { + "epoch": 0.2897749703908409, + "grad_norm": 0.6180450916290283, + "learning_rate": 3.5530990919857876e-06, + "loss": 0.4338, + "step": 734 + }, + { + "epoch": 0.2901697591788393, + "grad_norm": 0.7624568939208984, + "learning_rate": 3.551125148045796e-06, + "loss": 0.4816, + "step": 735 + }, + { + "epoch": 0.2905645479668377, + "grad_norm": 0.8272494077682495, + "learning_rate": 3.5491512041058036e-06, + "loss": 0.4984, + "step": 736 + }, + { + "epoch": 0.29095933675483615, + "grad_norm": 0.8277515172958374, + "learning_rate": 3.5471772601658116e-06, + "loss": 0.5336, + "step": 737 + }, + { + "epoch": 0.2913541255428346, + "grad_norm": 0.5960790514945984, + "learning_rate": 3.545203316225819e-06, + "loss": 0.4168, + "step": 738 + }, + { + "epoch": 0.291748914330833, + "grad_norm": 0.6442744731903076, + "learning_rate": 3.5432293722858275e-06, + "loss": 0.4665, + "step": 739 + }, + { + "epoch": 0.2921437031188314, + "grad_norm": 0.6846948266029358, + "learning_rate": 3.541255428345835e-06, + "loss": 0.5023, + "step": 740 + }, + { + "epoch": 0.29253849190682985, + "grad_norm": 0.6360129117965698, + "learning_rate": 3.539281484405843e-06, + "loss": 0.4125, + "step": 741 + }, + { + "epoch": 0.29293328069482827, + "grad_norm": 0.8378413915634155, + "learning_rate": 3.5373075404658506e-06, + "loss": 0.4497, + "step": 742 + }, + { + "epoch": 0.2933280694828267, + "grad_norm": 0.5883398056030273, + "learning_rate": 3.535333596525859e-06, + "loss": 0.4585, + "step": 743 + }, + { + "epoch": 0.2937228582708251, + "grad_norm": 0.6189714074134827, + "learning_rate": 3.533359652585867e-06, + "loss": 0.468, + "step": 744 + }, + { + "epoch": 0.29411764705882354, + "grad_norm": 0.6248310208320618, + "learning_rate": 3.531385708645875e-06, + "loss": 0.4723, + "step": 745 + }, + { + "epoch": 0.29451243584682196, + "grad_norm": 0.6501967310905457, + "learning_rate": 3.529411764705883e-06, + "loss": 0.4082, + "step": 746 + }, + { + "epoch": 0.2949072246348204, + "grad_norm": 0.5542152523994446, + "learning_rate": 3.5274378207658904e-06, + "loss": 0.3694, + "step": 747 + }, + { + "epoch": 0.2953020134228188, + "grad_norm": 0.7115119695663452, + "learning_rate": 3.525463876825899e-06, + "loss": 0.4479, + "step": 748 + }, + { + "epoch": 0.29569680221081723, + "grad_norm": 0.6849053502082825, + "learning_rate": 3.5234899328859064e-06, + "loss": 0.4392, + "step": 749 + }, + { + "epoch": 0.29609159099881566, + "grad_norm": 0.5760676264762878, + "learning_rate": 3.5215159889459144e-06, + "loss": 0.4176, + "step": 750 + }, + { + "epoch": 0.2964863797868141, + "grad_norm": 0.6379779577255249, + "learning_rate": 3.519542045005922e-06, + "loss": 0.4833, + "step": 751 + }, + { + "epoch": 0.29688116857481245, + "grad_norm": 0.7281062006950378, + "learning_rate": 3.5175681010659303e-06, + "loss": 0.4178, + "step": 752 + }, + { + "epoch": 0.29727595736281087, + "grad_norm": 0.9247459769248962, + "learning_rate": 3.515594157125938e-06, + "loss": 0.4169, + "step": 753 + }, + { + "epoch": 0.2976707461508093, + "grad_norm": 0.6787099242210388, + "learning_rate": 3.513620213185946e-06, + "loss": 0.4696, + "step": 754 + }, + { + "epoch": 0.2980655349388077, + "grad_norm": 0.5727716088294983, + "learning_rate": 3.5116462692459534e-06, + "loss": 0.4565, + "step": 755 + }, + { + "epoch": 0.29846032372680614, + "grad_norm": 0.556500256061554, + "learning_rate": 3.5096723253059618e-06, + "loss": 0.3843, + "step": 756 + }, + { + "epoch": 0.29885511251480457, + "grad_norm": 0.6932074427604675, + "learning_rate": 3.5076983813659693e-06, + "loss": 0.494, + "step": 757 + }, + { + "epoch": 0.299249901302803, + "grad_norm": 0.6467096209526062, + "learning_rate": 3.5057244374259773e-06, + "loss": 0.4812, + "step": 758 + }, + { + "epoch": 0.2996446900908014, + "grad_norm": 0.605690598487854, + "learning_rate": 3.5037504934859853e-06, + "loss": 0.4118, + "step": 759 + }, + { + "epoch": 0.30003947887879984, + "grad_norm": 0.5706431865692139, + "learning_rate": 3.5017765495459932e-06, + "loss": 0.3751, + "step": 760 + }, + { + "epoch": 0.30043426766679826, + "grad_norm": 0.7778968811035156, + "learning_rate": 3.4998026056060008e-06, + "loss": 0.4765, + "step": 761 + }, + { + "epoch": 0.3008290564547967, + "grad_norm": 0.7095364332199097, + "learning_rate": 3.497828661666009e-06, + "loss": 0.5001, + "step": 762 + }, + { + "epoch": 0.3012238452427951, + "grad_norm": 0.5733211040496826, + "learning_rate": 3.495854717726017e-06, + "loss": 0.4089, + "step": 763 + }, + { + "epoch": 0.30161863403079353, + "grad_norm": 0.5682768225669861, + "learning_rate": 3.4938807737860247e-06, + "loss": 0.4228, + "step": 764 + }, + { + "epoch": 0.30201342281879195, + "grad_norm": 0.58250892162323, + "learning_rate": 3.491906829846033e-06, + "loss": 0.4328, + "step": 765 + }, + { + "epoch": 0.3024082116067904, + "grad_norm": 0.5632656812667847, + "learning_rate": 3.4899328859060407e-06, + "loss": 0.4255, + "step": 766 + }, + { + "epoch": 0.3028030003947888, + "grad_norm": 0.9952139258384705, + "learning_rate": 3.4879589419660486e-06, + "loss": 0.4058, + "step": 767 + }, + { + "epoch": 0.3031977891827872, + "grad_norm": 0.7927477359771729, + "learning_rate": 3.485984998026056e-06, + "loss": 0.4785, + "step": 768 + }, + { + "epoch": 0.30359257797078565, + "grad_norm": 0.729160487651825, + "learning_rate": 3.4840110540860646e-06, + "loss": 0.4613, + "step": 769 + }, + { + "epoch": 0.30398736675878407, + "grad_norm": 0.8745778799057007, + "learning_rate": 3.482037110146072e-06, + "loss": 0.4964, + "step": 770 + }, + { + "epoch": 0.3043821555467825, + "grad_norm": 0.7701415419578552, + "learning_rate": 3.48006316620608e-06, + "loss": 0.4457, + "step": 771 + }, + { + "epoch": 0.3047769443347809, + "grad_norm": 0.6247523427009583, + "learning_rate": 3.4780892222660876e-06, + "loss": 0.4474, + "step": 772 + }, + { + "epoch": 0.3051717331227793, + "grad_norm": 0.6149014234542847, + "learning_rate": 3.476115278326096e-06, + "loss": 0.4338, + "step": 773 + }, + { + "epoch": 0.3055665219107777, + "grad_norm": 0.6376964449882507, + "learning_rate": 3.4741413343861036e-06, + "loss": 0.3961, + "step": 774 + }, + { + "epoch": 0.30596131069877613, + "grad_norm": 0.6812653541564941, + "learning_rate": 3.4721673904461116e-06, + "loss": 0.4418, + "step": 775 + }, + { + "epoch": 0.30635609948677456, + "grad_norm": 0.666903555393219, + "learning_rate": 3.4701934465061195e-06, + "loss": 0.444, + "step": 776 + }, + { + "epoch": 0.306750888274773, + "grad_norm": 0.6388180255889893, + "learning_rate": 3.4682195025661275e-06, + "loss": 0.4019, + "step": 777 + }, + { + "epoch": 0.3071456770627714, + "grad_norm": 0.9421985149383545, + "learning_rate": 3.466245558626135e-06, + "loss": 0.422, + "step": 778 + }, + { + "epoch": 0.30754046585076983, + "grad_norm": 0.7714625597000122, + "learning_rate": 3.4642716146861434e-06, + "loss": 0.4409, + "step": 779 + }, + { + "epoch": 0.30793525463876825, + "grad_norm": 0.6001613736152649, + "learning_rate": 3.462297670746151e-06, + "loss": 0.4218, + "step": 780 + }, + { + "epoch": 0.3083300434267667, + "grad_norm": 0.6479899883270264, + "learning_rate": 3.460323726806159e-06, + "loss": 0.4727, + "step": 781 + }, + { + "epoch": 0.3087248322147651, + "grad_norm": 0.5115014314651489, + "learning_rate": 3.4583497828661665e-06, + "loss": 0.3545, + "step": 782 + }, + { + "epoch": 0.3091196210027635, + "grad_norm": 0.6342079043388367, + "learning_rate": 3.456375838926175e-06, + "loss": 0.4565, + "step": 783 + }, + { + "epoch": 0.30951440979076195, + "grad_norm": 0.5389095544815063, + "learning_rate": 3.454401894986183e-06, + "loss": 0.4209, + "step": 784 + }, + { + "epoch": 0.30990919857876037, + "grad_norm": 0.5883544683456421, + "learning_rate": 3.4524279510461904e-06, + "loss": 0.437, + "step": 785 + }, + { + "epoch": 0.3103039873667588, + "grad_norm": 0.6050392985343933, + "learning_rate": 3.450454007106199e-06, + "loss": 0.4205, + "step": 786 + }, + { + "epoch": 0.3106987761547572, + "grad_norm": 0.6780236959457397, + "learning_rate": 3.4484800631662064e-06, + "loss": 0.4473, + "step": 787 + }, + { + "epoch": 0.31109356494275564, + "grad_norm": 0.8163807988166809, + "learning_rate": 3.4465061192262144e-06, + "loss": 0.4771, + "step": 788 + }, + { + "epoch": 0.31148835373075406, + "grad_norm": 0.5917900800704956, + "learning_rate": 3.444532175286222e-06, + "loss": 0.4586, + "step": 789 + }, + { + "epoch": 0.3118831425187525, + "grad_norm": 0.6766514182090759, + "learning_rate": 3.4425582313462303e-06, + "loss": 0.4391, + "step": 790 + }, + { + "epoch": 0.3122779313067509, + "grad_norm": 0.6848668456077576, + "learning_rate": 3.440584287406238e-06, + "loss": 0.4286, + "step": 791 + }, + { + "epoch": 0.31267272009474933, + "grad_norm": 0.5665653347969055, + "learning_rate": 3.438610343466246e-06, + "loss": 0.4322, + "step": 792 + }, + { + "epoch": 0.3130675088827477, + "grad_norm": 0.5379101634025574, + "learning_rate": 3.436636399526254e-06, + "loss": 0.4477, + "step": 793 + }, + { + "epoch": 0.3134622976707461, + "grad_norm": 0.8249588012695312, + "learning_rate": 3.4346624555862618e-06, + "loss": 0.4676, + "step": 794 + }, + { + "epoch": 0.31385708645874455, + "grad_norm": 0.6474442481994629, + "learning_rate": 3.4326885116462693e-06, + "loss": 0.4059, + "step": 795 + }, + { + "epoch": 0.314251875246743, + "grad_norm": 0.5879417657852173, + "learning_rate": 3.4307145677062777e-06, + "loss": 0.3754, + "step": 796 + }, + { + "epoch": 0.3146466640347414, + "grad_norm": 0.6147333383560181, + "learning_rate": 3.4287406237662853e-06, + "loss": 0.4092, + "step": 797 + }, + { + "epoch": 0.3150414528227398, + "grad_norm": 0.5360463261604309, + "learning_rate": 3.4267666798262932e-06, + "loss": 0.4022, + "step": 798 + }, + { + "epoch": 0.31543624161073824, + "grad_norm": 0.7131299376487732, + "learning_rate": 3.4247927358863008e-06, + "loss": 0.4355, + "step": 799 + }, + { + "epoch": 0.31583103039873667, + "grad_norm": 0.6902903318405151, + "learning_rate": 3.422818791946309e-06, + "loss": 0.4823, + "step": 800 + }, + { + "epoch": 0.3162258191867351, + "grad_norm": 0.5603412389755249, + "learning_rate": 3.4208448480063167e-06, + "loss": 0.4684, + "step": 801 + }, + { + "epoch": 0.3166206079747335, + "grad_norm": 0.6370513439178467, + "learning_rate": 3.4188709040663247e-06, + "loss": 0.4749, + "step": 802 + }, + { + "epoch": 0.31701539676273194, + "grad_norm": 0.6316598653793335, + "learning_rate": 3.4168969601263323e-06, + "loss": 0.4227, + "step": 803 + }, + { + "epoch": 0.31741018555073036, + "grad_norm": 0.4943726062774658, + "learning_rate": 3.4149230161863406e-06, + "loss": 0.3474, + "step": 804 + }, + { + "epoch": 0.3178049743387288, + "grad_norm": 0.6358802914619446, + "learning_rate": 3.4129490722463486e-06, + "loss": 0.4117, + "step": 805 + }, + { + "epoch": 0.3181997631267272, + "grad_norm": 0.6390992403030396, + "learning_rate": 3.410975128306356e-06, + "loss": 0.4251, + "step": 806 + }, + { + "epoch": 0.31859455191472563, + "grad_norm": 0.7497234344482422, + "learning_rate": 3.4090011843663646e-06, + "loss": 0.4396, + "step": 807 + }, + { + "epoch": 0.31898934070272406, + "grad_norm": 0.6962636113166809, + "learning_rate": 3.407027240426372e-06, + "loss": 0.4488, + "step": 808 + }, + { + "epoch": 0.3193841294907225, + "grad_norm": 0.6651611924171448, + "learning_rate": 3.40505329648638e-06, + "loss": 0.4303, + "step": 809 + }, + { + "epoch": 0.3197789182787209, + "grad_norm": 0.627196729183197, + "learning_rate": 3.403079352546388e-06, + "loss": 0.4264, + "step": 810 + }, + { + "epoch": 0.3201737070667193, + "grad_norm": 0.5569165349006653, + "learning_rate": 3.401105408606396e-06, + "loss": 0.4055, + "step": 811 + }, + { + "epoch": 0.32056849585471775, + "grad_norm": 0.7024729251861572, + "learning_rate": 3.3991314646664036e-06, + "loss": 0.4629, + "step": 812 + }, + { + "epoch": 0.3209632846427162, + "grad_norm": 0.6775999069213867, + "learning_rate": 3.397157520726412e-06, + "loss": 0.4597, + "step": 813 + }, + { + "epoch": 0.32135807343071454, + "grad_norm": 0.6415016055107117, + "learning_rate": 3.3951835767864195e-06, + "loss": 0.4668, + "step": 814 + }, + { + "epoch": 0.32175286221871296, + "grad_norm": 0.60725998878479, + "learning_rate": 3.3932096328464275e-06, + "loss": 0.4266, + "step": 815 + }, + { + "epoch": 0.3221476510067114, + "grad_norm": 0.6173945665359497, + "learning_rate": 3.391235688906435e-06, + "loss": 0.4665, + "step": 816 + }, + { + "epoch": 0.3225424397947098, + "grad_norm": 0.7902264595031738, + "learning_rate": 3.3892617449664434e-06, + "loss": 0.434, + "step": 817 + }, + { + "epoch": 0.32293722858270824, + "grad_norm": 0.5997299551963806, + "learning_rate": 3.387287801026451e-06, + "loss": 0.4236, + "step": 818 + }, + { + "epoch": 0.32333201737070666, + "grad_norm": 0.7877179980278015, + "learning_rate": 3.385313857086459e-06, + "loss": 0.3867, + "step": 819 + }, + { + "epoch": 0.3237268061587051, + "grad_norm": 0.5767133831977844, + "learning_rate": 3.3833399131464665e-06, + "loss": 0.4616, + "step": 820 + }, + { + "epoch": 0.3241215949467035, + "grad_norm": 0.8104587197303772, + "learning_rate": 3.381365969206475e-06, + "loss": 0.4711, + "step": 821 + }, + { + "epoch": 0.32451638373470193, + "grad_norm": 0.5489710569381714, + "learning_rate": 3.3793920252664825e-06, + "loss": 0.4126, + "step": 822 + }, + { + "epoch": 0.32491117252270035, + "grad_norm": 0.6514670848846436, + "learning_rate": 3.3774180813264904e-06, + "loss": 0.5153, + "step": 823 + }, + { + "epoch": 0.3253059613106988, + "grad_norm": 0.6253125071525574, + "learning_rate": 3.3754441373864984e-06, + "loss": 0.4109, + "step": 824 + }, + { + "epoch": 0.3257007500986972, + "grad_norm": 0.9313228130340576, + "learning_rate": 3.3734701934465064e-06, + "loss": 0.4494, + "step": 825 + }, + { + "epoch": 0.3260955388866956, + "grad_norm": 0.8119605183601379, + "learning_rate": 3.3714962495065144e-06, + "loss": 0.466, + "step": 826 + }, + { + "epoch": 0.32649032767469405, + "grad_norm": 0.7102879285812378, + "learning_rate": 3.3695223055665223e-06, + "loss": 0.4936, + "step": 827 + }, + { + "epoch": 0.32688511646269247, + "grad_norm": 0.631280779838562, + "learning_rate": 3.3675483616265303e-06, + "loss": 0.4691, + "step": 828 + }, + { + "epoch": 0.3272799052506909, + "grad_norm": 0.7359605431556702, + "learning_rate": 3.365574417686538e-06, + "loss": 0.4491, + "step": 829 + }, + { + "epoch": 0.3276746940386893, + "grad_norm": 0.6935346126556396, + "learning_rate": 3.3636004737465462e-06, + "loss": 0.397, + "step": 830 + }, + { + "epoch": 0.32806948282668774, + "grad_norm": 0.7130545377731323, + "learning_rate": 3.361626529806554e-06, + "loss": 0.4973, + "step": 831 + }, + { + "epoch": 0.32846427161468617, + "grad_norm": 0.6377546787261963, + "learning_rate": 3.3596525858665618e-06, + "loss": 0.4012, + "step": 832 + }, + { + "epoch": 0.3288590604026846, + "grad_norm": 0.5525513291358948, + "learning_rate": 3.3576786419265693e-06, + "loss": 0.3822, + "step": 833 + }, + { + "epoch": 0.329253849190683, + "grad_norm": 0.6771413087844849, + "learning_rate": 3.3557046979865777e-06, + "loss": 0.4339, + "step": 834 + }, + { + "epoch": 0.3296486379786814, + "grad_norm": 0.559172511100769, + "learning_rate": 3.3537307540465853e-06, + "loss": 0.3992, + "step": 835 + }, + { + "epoch": 0.3300434267666798, + "grad_norm": 0.571212112903595, + "learning_rate": 3.3517568101065932e-06, + "loss": 0.4101, + "step": 836 + }, + { + "epoch": 0.3304382155546782, + "grad_norm": 0.7074283957481384, + "learning_rate": 3.3497828661666008e-06, + "loss": 0.4641, + "step": 837 + }, + { + "epoch": 0.33083300434267665, + "grad_norm": 0.5513744354248047, + "learning_rate": 3.347808922226609e-06, + "loss": 0.436, + "step": 838 + }, + { + "epoch": 0.3312277931306751, + "grad_norm": 0.5575878620147705, + "learning_rate": 3.3458349782866167e-06, + "loss": 0.3765, + "step": 839 + }, + { + "epoch": 0.3316225819186735, + "grad_norm": 0.704522430896759, + "learning_rate": 3.3438610343466247e-06, + "loss": 0.4265, + "step": 840 + }, + { + "epoch": 0.3320173707066719, + "grad_norm": 0.6417326331138611, + "learning_rate": 3.3418870904066327e-06, + "loss": 0.4574, + "step": 841 + }, + { + "epoch": 0.33241215949467035, + "grad_norm": 0.5218741297721863, + "learning_rate": 3.3399131464666406e-06, + "loss": 0.3952, + "step": 842 + }, + { + "epoch": 0.33280694828266877, + "grad_norm": 0.8739984035491943, + "learning_rate": 3.337939202526648e-06, + "loss": 0.5042, + "step": 843 + }, + { + "epoch": 0.3332017370706672, + "grad_norm": 0.6172849535942078, + "learning_rate": 3.3359652585866566e-06, + "loss": 0.4442, + "step": 844 + }, + { + "epoch": 0.3335965258586656, + "grad_norm": 0.6023227572441101, + "learning_rate": 3.333991314646664e-06, + "loss": 0.4698, + "step": 845 + }, + { + "epoch": 0.33399131464666404, + "grad_norm": 0.635697066783905, + "learning_rate": 3.332017370706672e-06, + "loss": 0.4529, + "step": 846 + }, + { + "epoch": 0.33438610343466246, + "grad_norm": 0.6537505388259888, + "learning_rate": 3.3300434267666805e-06, + "loss": 0.4109, + "step": 847 + }, + { + "epoch": 0.3347808922226609, + "grad_norm": 0.6976112723350525, + "learning_rate": 3.328069482826688e-06, + "loss": 0.5015, + "step": 848 + }, + { + "epoch": 0.3351756810106593, + "grad_norm": 0.7941066026687622, + "learning_rate": 3.326095538886696e-06, + "loss": 0.4847, + "step": 849 + }, + { + "epoch": 0.33557046979865773, + "grad_norm": 0.5805544257164001, + "learning_rate": 3.3241215949467036e-06, + "loss": 0.3733, + "step": 850 + }, + { + "epoch": 0.33596525858665616, + "grad_norm": 0.7003908157348633, + "learning_rate": 3.322147651006712e-06, + "loss": 0.4615, + "step": 851 + }, + { + "epoch": 0.3363600473746546, + "grad_norm": 0.6159262657165527, + "learning_rate": 3.3201737070667195e-06, + "loss": 0.4758, + "step": 852 + }, + { + "epoch": 0.336754836162653, + "grad_norm": 0.8868524432182312, + "learning_rate": 3.3181997631267275e-06, + "loss": 0.4537, + "step": 853 + }, + { + "epoch": 0.3371496249506514, + "grad_norm": 0.6385483741760254, + "learning_rate": 3.316225819186735e-06, + "loss": 0.4142, + "step": 854 + }, + { + "epoch": 0.3375444137386498, + "grad_norm": 0.6104214191436768, + "learning_rate": 3.3142518752467434e-06, + "loss": 0.4342, + "step": 855 + }, + { + "epoch": 0.3379392025266482, + "grad_norm": 0.577208399772644, + "learning_rate": 3.312277931306751e-06, + "loss": 0.4055, + "step": 856 + }, + { + "epoch": 0.33833399131464664, + "grad_norm": 0.6432677507400513, + "learning_rate": 3.310303987366759e-06, + "loss": 0.4552, + "step": 857 + }, + { + "epoch": 0.33872878010264507, + "grad_norm": 0.6207624077796936, + "learning_rate": 3.308330043426767e-06, + "loss": 0.4059, + "step": 858 + }, + { + "epoch": 0.3391235688906435, + "grad_norm": 0.6031792163848877, + "learning_rate": 3.306356099486775e-06, + "loss": 0.4039, + "step": 859 + }, + { + "epoch": 0.3395183576786419, + "grad_norm": 0.611073911190033, + "learning_rate": 3.3043821555467825e-06, + "loss": 0.4732, + "step": 860 + }, + { + "epoch": 0.33991314646664034, + "grad_norm": 0.7692722082138062, + "learning_rate": 3.302408211606791e-06, + "loss": 0.5019, + "step": 861 + }, + { + "epoch": 0.34030793525463876, + "grad_norm": 0.9254004955291748, + "learning_rate": 3.3004342676667984e-06, + "loss": 0.5216, + "step": 862 + }, + { + "epoch": 0.3407027240426372, + "grad_norm": 0.6547450423240662, + "learning_rate": 3.2984603237268064e-06, + "loss": 0.4574, + "step": 863 + }, + { + "epoch": 0.3410975128306356, + "grad_norm": 0.8869918584823608, + "learning_rate": 3.296486379786814e-06, + "loss": 0.526, + "step": 864 + }, + { + "epoch": 0.34149230161863403, + "grad_norm": 0.5399096012115479, + "learning_rate": 3.2945124358468223e-06, + "loss": 0.4525, + "step": 865 + }, + { + "epoch": 0.34188709040663245, + "grad_norm": 0.6034839749336243, + "learning_rate": 3.2925384919068303e-06, + "loss": 0.3758, + "step": 866 + }, + { + "epoch": 0.3422818791946309, + "grad_norm": 0.5333848595619202, + "learning_rate": 3.290564547966838e-06, + "loss": 0.4165, + "step": 867 + }, + { + "epoch": 0.3426766679826293, + "grad_norm": 0.7765272259712219, + "learning_rate": 3.2885906040268462e-06, + "loss": 0.4718, + "step": 868 + }, + { + "epoch": 0.3430714567706277, + "grad_norm": 0.6134557723999023, + "learning_rate": 3.286616660086854e-06, + "loss": 0.4121, + "step": 869 + }, + { + "epoch": 0.34346624555862615, + "grad_norm": 0.7439407706260681, + "learning_rate": 3.2846427161468618e-06, + "loss": 0.4717, + "step": 870 + }, + { + "epoch": 0.34386103434662457, + "grad_norm": 0.6259050369262695, + "learning_rate": 3.2826687722068697e-06, + "loss": 0.4267, + "step": 871 + }, + { + "epoch": 0.344255823134623, + "grad_norm": 0.7536805868148804, + "learning_rate": 3.2806948282668777e-06, + "loss": 0.4555, + "step": 872 + }, + { + "epoch": 0.3446506119226214, + "grad_norm": 0.6563900113105774, + "learning_rate": 3.2787208843268853e-06, + "loss": 0.4048, + "step": 873 + }, + { + "epoch": 0.34504540071061984, + "grad_norm": 0.6613359451293945, + "learning_rate": 3.2767469403868937e-06, + "loss": 0.4362, + "step": 874 + }, + { + "epoch": 0.34544018949861827, + "grad_norm": 0.5930020809173584, + "learning_rate": 3.274772996446901e-06, + "loss": 0.3868, + "step": 875 + }, + { + "epoch": 0.34583497828661663, + "grad_norm": 0.7574977874755859, + "learning_rate": 3.272799052506909e-06, + "loss": 0.4792, + "step": 876 + }, + { + "epoch": 0.34622976707461506, + "grad_norm": 0.8059077858924866, + "learning_rate": 3.2708251085669167e-06, + "loss": 0.4628, + "step": 877 + }, + { + "epoch": 0.3466245558626135, + "grad_norm": 0.5587652325630188, + "learning_rate": 3.268851164626925e-06, + "loss": 0.4142, + "step": 878 + }, + { + "epoch": 0.3470193446506119, + "grad_norm": 0.5739462375640869, + "learning_rate": 3.2668772206869327e-06, + "loss": 0.4458, + "step": 879 + }, + { + "epoch": 0.34741413343861033, + "grad_norm": 0.6106107831001282, + "learning_rate": 3.2649032767469406e-06, + "loss": 0.4507, + "step": 880 + }, + { + "epoch": 0.34780892222660875, + "grad_norm": 0.6971011161804199, + "learning_rate": 3.262929332806948e-06, + "loss": 0.4522, + "step": 881 + }, + { + "epoch": 0.3482037110146072, + "grad_norm": 0.582429826259613, + "learning_rate": 3.2609553888669566e-06, + "loss": 0.4456, + "step": 882 + }, + { + "epoch": 0.3485984998026056, + "grad_norm": 0.6589856147766113, + "learning_rate": 3.258981444926964e-06, + "loss": 0.4184, + "step": 883 + }, + { + "epoch": 0.348993288590604, + "grad_norm": 0.7893657088279724, + "learning_rate": 3.257007500986972e-06, + "loss": 0.4995, + "step": 884 + }, + { + "epoch": 0.34938807737860245, + "grad_norm": 0.516220211982727, + "learning_rate": 3.25503355704698e-06, + "loss": 0.3907, + "step": 885 + }, + { + "epoch": 0.34978286616660087, + "grad_norm": 0.6097385883331299, + "learning_rate": 3.253059613106988e-06, + "loss": 0.4023, + "step": 886 + }, + { + "epoch": 0.3501776549545993, + "grad_norm": 0.6541979312896729, + "learning_rate": 3.251085669166996e-06, + "loss": 0.4223, + "step": 887 + }, + { + "epoch": 0.3505724437425977, + "grad_norm": 0.7017857432365417, + "learning_rate": 3.249111725227004e-06, + "loss": 0.461, + "step": 888 + }, + { + "epoch": 0.35096723253059614, + "grad_norm": 0.6646719574928284, + "learning_rate": 3.247137781287012e-06, + "loss": 0.474, + "step": 889 + }, + { + "epoch": 0.35136202131859456, + "grad_norm": 0.6716167330741882, + "learning_rate": 3.2451638373470195e-06, + "loss": 0.3955, + "step": 890 + }, + { + "epoch": 0.351756810106593, + "grad_norm": 0.9870420694351196, + "learning_rate": 3.243189893407028e-06, + "loss": 0.4819, + "step": 891 + }, + { + "epoch": 0.3521515988945914, + "grad_norm": 0.4849432110786438, + "learning_rate": 3.2412159494670355e-06, + "loss": 0.369, + "step": 892 + }, + { + "epoch": 0.35254638768258983, + "grad_norm": 0.583736002445221, + "learning_rate": 3.2392420055270434e-06, + "loss": 0.396, + "step": 893 + }, + { + "epoch": 0.35294117647058826, + "grad_norm": 0.545262336730957, + "learning_rate": 3.237268061587051e-06, + "loss": 0.3559, + "step": 894 + }, + { + "epoch": 0.3533359652585867, + "grad_norm": 0.5593507289886475, + "learning_rate": 3.2352941176470594e-06, + "loss": 0.3783, + "step": 895 + }, + { + "epoch": 0.35373075404658505, + "grad_norm": 0.5886032581329346, + "learning_rate": 3.233320173707067e-06, + "loss": 0.4676, + "step": 896 + }, + { + "epoch": 0.3541255428345835, + "grad_norm": 0.6258420348167419, + "learning_rate": 3.231346229767075e-06, + "loss": 0.4138, + "step": 897 + }, + { + "epoch": 0.3545203316225819, + "grad_norm": 0.6450306177139282, + "learning_rate": 3.2293722858270825e-06, + "loss": 0.4395, + "step": 898 + }, + { + "epoch": 0.3549151204105803, + "grad_norm": 0.5198794603347778, + "learning_rate": 3.227398341887091e-06, + "loss": 0.431, + "step": 899 + }, + { + "epoch": 0.35530990919857874, + "grad_norm": 0.6674392223358154, + "learning_rate": 3.2254243979470984e-06, + "loss": 0.5031, + "step": 900 + }, + { + "epoch": 0.35570469798657717, + "grad_norm": 0.5959722399711609, + "learning_rate": 3.2234504540071064e-06, + "loss": 0.3894, + "step": 901 + }, + { + "epoch": 0.3560994867745756, + "grad_norm": 0.651365339756012, + "learning_rate": 3.2214765100671143e-06, + "loss": 0.4146, + "step": 902 + }, + { + "epoch": 0.356494275562574, + "grad_norm": 0.6528431177139282, + "learning_rate": 3.2195025661271223e-06, + "loss": 0.4046, + "step": 903 + }, + { + "epoch": 0.35688906435057244, + "grad_norm": 0.9023704528808594, + "learning_rate": 3.21752862218713e-06, + "loss": 0.5015, + "step": 904 + }, + { + "epoch": 0.35728385313857086, + "grad_norm": 0.6307384967803955, + "learning_rate": 3.2155546782471383e-06, + "loss": 0.4703, + "step": 905 + }, + { + "epoch": 0.3576786419265693, + "grad_norm": 0.6613783240318298, + "learning_rate": 3.213580734307146e-06, + "loss": 0.3748, + "step": 906 + }, + { + "epoch": 0.3580734307145677, + "grad_norm": 0.5953598022460938, + "learning_rate": 3.211606790367154e-06, + "loss": 0.4453, + "step": 907 + }, + { + "epoch": 0.35846821950256613, + "grad_norm": 0.5791945457458496, + "learning_rate": 3.209632846427162e-06, + "loss": 0.4008, + "step": 908 + }, + { + "epoch": 0.35886300829056456, + "grad_norm": 0.6296145915985107, + "learning_rate": 3.2076589024871697e-06, + "loss": 0.4237, + "step": 909 + }, + { + "epoch": 0.359257797078563, + "grad_norm": 0.6567381620407104, + "learning_rate": 3.2056849585471777e-06, + "loss": 0.4844, + "step": 910 + }, + { + "epoch": 0.3596525858665614, + "grad_norm": 0.6966069936752319, + "learning_rate": 3.2037110146071853e-06, + "loss": 0.4375, + "step": 911 + }, + { + "epoch": 0.3600473746545598, + "grad_norm": 0.7975919842720032, + "learning_rate": 3.2017370706671937e-06, + "loss": 0.4774, + "step": 912 + }, + { + "epoch": 0.36044216344255825, + "grad_norm": 0.5946155190467834, + "learning_rate": 3.199763126727201e-06, + "loss": 0.3937, + "step": 913 + }, + { + "epoch": 0.3608369522305567, + "grad_norm": 0.7165453433990479, + "learning_rate": 3.197789182787209e-06, + "loss": 0.4541, + "step": 914 + }, + { + "epoch": 0.3612317410185551, + "grad_norm": 0.516939640045166, + "learning_rate": 3.1958152388472167e-06, + "loss": 0.3783, + "step": 915 + }, + { + "epoch": 0.3616265298065535, + "grad_norm": 0.7318978309631348, + "learning_rate": 3.193841294907225e-06, + "loss": 0.4712, + "step": 916 + }, + { + "epoch": 0.3620213185945519, + "grad_norm": 0.640314519405365, + "learning_rate": 3.1918673509672327e-06, + "loss": 0.4768, + "step": 917 + }, + { + "epoch": 0.3624161073825503, + "grad_norm": 0.7613033056259155, + "learning_rate": 3.1898934070272406e-06, + "loss": 0.5059, + "step": 918 + }, + { + "epoch": 0.36281089617054874, + "grad_norm": 0.64047771692276, + "learning_rate": 3.1879194630872486e-06, + "loss": 0.4827, + "step": 919 + }, + { + "epoch": 0.36320568495854716, + "grad_norm": 0.5820575952529907, + "learning_rate": 3.1859455191472566e-06, + "loss": 0.3868, + "step": 920 + }, + { + "epoch": 0.3636004737465456, + "grad_norm": 0.6932581067085266, + "learning_rate": 3.183971575207264e-06, + "loss": 0.4653, + "step": 921 + }, + { + "epoch": 0.363995262534544, + "grad_norm": 0.5879856944084167, + "learning_rate": 3.1819976312672725e-06, + "loss": 0.4384, + "step": 922 + }, + { + "epoch": 0.36439005132254243, + "grad_norm": 0.6117681264877319, + "learning_rate": 3.18002368732728e-06, + "loss": 0.4219, + "step": 923 + }, + { + "epoch": 0.36478484011054085, + "grad_norm": 0.8006728887557983, + "learning_rate": 3.178049743387288e-06, + "loss": 0.488, + "step": 924 + }, + { + "epoch": 0.3651796288985393, + "grad_norm": 0.5671461224555969, + "learning_rate": 3.1760757994472956e-06, + "loss": 0.4174, + "step": 925 + }, + { + "epoch": 0.3655744176865377, + "grad_norm": 0.8540800213813782, + "learning_rate": 3.174101855507304e-06, + "loss": 0.5078, + "step": 926 + }, + { + "epoch": 0.3659692064745361, + "grad_norm": 0.6974892020225525, + "learning_rate": 3.1721279115673115e-06, + "loss": 0.4823, + "step": 927 + }, + { + "epoch": 0.36636399526253455, + "grad_norm": 0.7609708309173584, + "learning_rate": 3.1701539676273195e-06, + "loss": 0.4734, + "step": 928 + }, + { + "epoch": 0.36675878405053297, + "grad_norm": 0.6563175916671753, + "learning_rate": 3.168180023687328e-06, + "loss": 0.433, + "step": 929 + }, + { + "epoch": 0.3671535728385314, + "grad_norm": 0.57867032289505, + "learning_rate": 3.1662060797473355e-06, + "loss": 0.3932, + "step": 930 + }, + { + "epoch": 0.3675483616265298, + "grad_norm": 0.7108263373374939, + "learning_rate": 3.1642321358073434e-06, + "loss": 0.5001, + "step": 931 + }, + { + "epoch": 0.36794315041452824, + "grad_norm": 0.6327301263809204, + "learning_rate": 3.162258191867351e-06, + "loss": 0.4326, + "step": 932 + }, + { + "epoch": 0.36833793920252667, + "grad_norm": 0.5077672004699707, + "learning_rate": 3.1602842479273594e-06, + "loss": 0.3921, + "step": 933 + }, + { + "epoch": 0.3687327279905251, + "grad_norm": 0.647816002368927, + "learning_rate": 3.158310303987367e-06, + "loss": 0.4286, + "step": 934 + }, + { + "epoch": 0.3691275167785235, + "grad_norm": 0.5659697651863098, + "learning_rate": 3.156336360047375e-06, + "loss": 0.4639, + "step": 935 + }, + { + "epoch": 0.36952230556652194, + "grad_norm": 0.6972765326499939, + "learning_rate": 3.154362416107383e-06, + "loss": 0.4477, + "step": 936 + }, + { + "epoch": 0.36991709435452036, + "grad_norm": 0.5829297304153442, + "learning_rate": 3.152388472167391e-06, + "loss": 0.3959, + "step": 937 + }, + { + "epoch": 0.3703118831425187, + "grad_norm": 0.8532869815826416, + "learning_rate": 3.1504145282273984e-06, + "loss": 0.4785, + "step": 938 + }, + { + "epoch": 0.37070667193051715, + "grad_norm": 0.8123303651809692, + "learning_rate": 3.148440584287407e-06, + "loss": 0.47, + "step": 939 + }, + { + "epoch": 0.3711014607185156, + "grad_norm": 0.5882596373558044, + "learning_rate": 3.1464666403474143e-06, + "loss": 0.3999, + "step": 940 + }, + { + "epoch": 0.371496249506514, + "grad_norm": 0.6440290808677673, + "learning_rate": 3.1444926964074223e-06, + "loss": 0.4382, + "step": 941 + }, + { + "epoch": 0.3718910382945124, + "grad_norm": 0.6798499822616577, + "learning_rate": 3.14251875246743e-06, + "loss": 0.5471, + "step": 942 + }, + { + "epoch": 0.37228582708251085, + "grad_norm": 0.7017461061477661, + "learning_rate": 3.1405448085274383e-06, + "loss": 0.4937, + "step": 943 + }, + { + "epoch": 0.37268061587050927, + "grad_norm": 0.5739662647247314, + "learning_rate": 3.138570864587446e-06, + "loss": 0.47, + "step": 944 + }, + { + "epoch": 0.3730754046585077, + "grad_norm": 0.6521116495132446, + "learning_rate": 3.1365969206474538e-06, + "loss": 0.449, + "step": 945 + }, + { + "epoch": 0.3734701934465061, + "grad_norm": 0.7065708041191101, + "learning_rate": 3.1346229767074613e-06, + "loss": 0.4629, + "step": 946 + }, + { + "epoch": 0.37386498223450454, + "grad_norm": 0.7314972281455994, + "learning_rate": 3.1326490327674697e-06, + "loss": 0.425, + "step": 947 + }, + { + "epoch": 0.37425977102250296, + "grad_norm": 0.679042398929596, + "learning_rate": 3.1306750888274773e-06, + "loss": 0.4543, + "step": 948 + }, + { + "epoch": 0.3746545598105014, + "grad_norm": 0.6330568790435791, + "learning_rate": 3.1287011448874853e-06, + "loss": 0.4654, + "step": 949 + }, + { + "epoch": 0.3750493485984998, + "grad_norm": 0.5575295090675354, + "learning_rate": 3.1267272009474937e-06, + "loss": 0.4518, + "step": 950 + }, + { + "epoch": 0.37544413738649823, + "grad_norm": 0.6744239926338196, + "learning_rate": 3.124753257007501e-06, + "loss": 0.4875, + "step": 951 + }, + { + "epoch": 0.37583892617449666, + "grad_norm": 0.567463755607605, + "learning_rate": 3.122779313067509e-06, + "loss": 0.4345, + "step": 952 + }, + { + "epoch": 0.3762337149624951, + "grad_norm": 0.7021179795265198, + "learning_rate": 3.120805369127517e-06, + "loss": 0.499, + "step": 953 + }, + { + "epoch": 0.3766285037504935, + "grad_norm": 0.6116297841072083, + "learning_rate": 3.118831425187525e-06, + "loss": 0.4558, + "step": 954 + }, + { + "epoch": 0.3770232925384919, + "grad_norm": 0.6729407906532288, + "learning_rate": 3.1168574812475327e-06, + "loss": 0.4237, + "step": 955 + }, + { + "epoch": 0.37741808132649035, + "grad_norm": 0.6644793748855591, + "learning_rate": 3.114883537307541e-06, + "loss": 0.4225, + "step": 956 + }, + { + "epoch": 0.3778128701144888, + "grad_norm": 0.5803974270820618, + "learning_rate": 3.1129095933675486e-06, + "loss": 0.4102, + "step": 957 + }, + { + "epoch": 0.37820765890248714, + "grad_norm": 0.8095206022262573, + "learning_rate": 3.1109356494275566e-06, + "loss": 0.4219, + "step": 958 + }, + { + "epoch": 0.37860244769048557, + "grad_norm": 0.5995594263076782, + "learning_rate": 3.108961705487564e-06, + "loss": 0.4935, + "step": 959 + }, + { + "epoch": 0.378997236478484, + "grad_norm": 0.596373438835144, + "learning_rate": 3.1069877615475725e-06, + "loss": 0.4312, + "step": 960 + }, + { + "epoch": 0.3793920252664824, + "grad_norm": 0.7676904201507568, + "learning_rate": 3.10501381760758e-06, + "loss": 0.5211, + "step": 961 + }, + { + "epoch": 0.37978681405448084, + "grad_norm": 0.664726972579956, + "learning_rate": 3.103039873667588e-06, + "loss": 0.4269, + "step": 962 + }, + { + "epoch": 0.38018160284247926, + "grad_norm": 0.6181260347366333, + "learning_rate": 3.1010659297275956e-06, + "loss": 0.4149, + "step": 963 + }, + { + "epoch": 0.3805763916304777, + "grad_norm": 0.7501919865608215, + "learning_rate": 3.099091985787604e-06, + "loss": 0.447, + "step": 964 + }, + { + "epoch": 0.3809711804184761, + "grad_norm": 1.0988112688064575, + "learning_rate": 3.0971180418476115e-06, + "loss": 0.5223, + "step": 965 + }, + { + "epoch": 0.38136596920647453, + "grad_norm": 0.6183819770812988, + "learning_rate": 3.0951440979076195e-06, + "loss": 0.4489, + "step": 966 + }, + { + "epoch": 0.38176075799447295, + "grad_norm": 0.6901800036430359, + "learning_rate": 3.0931701539676275e-06, + "loss": 0.4661, + "step": 967 + }, + { + "epoch": 0.3821555467824714, + "grad_norm": 0.5488219857215881, + "learning_rate": 3.0911962100276355e-06, + "loss": 0.4026, + "step": 968 + }, + { + "epoch": 0.3825503355704698, + "grad_norm": 0.5965675711631775, + "learning_rate": 3.0892222660876434e-06, + "loss": 0.4337, + "step": 969 + }, + { + "epoch": 0.3829451243584682, + "grad_norm": 0.7586978673934937, + "learning_rate": 3.0872483221476514e-06, + "loss": 0.4669, + "step": 970 + }, + { + "epoch": 0.38333991314646665, + "grad_norm": 0.6776658892631531, + "learning_rate": 3.0852743782076594e-06, + "loss": 0.431, + "step": 971 + }, + { + "epoch": 0.3837347019344651, + "grad_norm": 0.5214899182319641, + "learning_rate": 3.083300434267667e-06, + "loss": 0.3947, + "step": 972 + }, + { + "epoch": 0.3841294907224635, + "grad_norm": 0.6291109323501587, + "learning_rate": 3.0813264903276753e-06, + "loss": 0.4698, + "step": 973 + }, + { + "epoch": 0.3845242795104619, + "grad_norm": 0.5158431529998779, + "learning_rate": 3.079352546387683e-06, + "loss": 0.3947, + "step": 974 + }, + { + "epoch": 0.38491906829846034, + "grad_norm": 0.7721207141876221, + "learning_rate": 3.077378602447691e-06, + "loss": 0.4305, + "step": 975 + }, + { + "epoch": 0.38531385708645877, + "grad_norm": 0.6017974019050598, + "learning_rate": 3.0754046585076984e-06, + "loss": 0.4347, + "step": 976 + }, + { + "epoch": 0.3857086458744572, + "grad_norm": 0.7356080412864685, + "learning_rate": 3.073430714567707e-06, + "loss": 0.4768, + "step": 977 + }, + { + "epoch": 0.3861034346624556, + "grad_norm": 0.6493563055992126, + "learning_rate": 3.0714567706277143e-06, + "loss": 0.4665, + "step": 978 + }, + { + "epoch": 0.386498223450454, + "grad_norm": 0.6233450174331665, + "learning_rate": 3.0694828266877223e-06, + "loss": 0.4244, + "step": 979 + }, + { + "epoch": 0.3868930122384524, + "grad_norm": 0.6276429891586304, + "learning_rate": 3.06750888274773e-06, + "loss": 0.4022, + "step": 980 + }, + { + "epoch": 0.38728780102645083, + "grad_norm": 0.6439236998558044, + "learning_rate": 3.0655349388077383e-06, + "loss": 0.4453, + "step": 981 + }, + { + "epoch": 0.38768258981444925, + "grad_norm": 0.6299352049827576, + "learning_rate": 3.063560994867746e-06, + "loss": 0.4694, + "step": 982 + }, + { + "epoch": 0.3880773786024477, + "grad_norm": 0.670495867729187, + "learning_rate": 3.0615870509277538e-06, + "loss": 0.4747, + "step": 983 + }, + { + "epoch": 0.3884721673904461, + "grad_norm": 0.4682813584804535, + "learning_rate": 3.0596131069877618e-06, + "loss": 0.3465, + "step": 984 + }, + { + "epoch": 0.3888669561784445, + "grad_norm": 0.5920973420143127, + "learning_rate": 3.0576391630477697e-06, + "loss": 0.4571, + "step": 985 + }, + { + "epoch": 0.38926174496644295, + "grad_norm": 0.6568809151649475, + "learning_rate": 3.0556652191077773e-06, + "loss": 0.4069, + "step": 986 + }, + { + "epoch": 0.38965653375444137, + "grad_norm": 0.6158491969108582, + "learning_rate": 3.0536912751677857e-06, + "loss": 0.4598, + "step": 987 + }, + { + "epoch": 0.3900513225424398, + "grad_norm": 0.710867702960968, + "learning_rate": 3.0517173312277932e-06, + "loss": 0.4693, + "step": 988 + }, + { + "epoch": 0.3904461113304382, + "grad_norm": 0.584798276424408, + "learning_rate": 3.049743387287801e-06, + "loss": 0.4024, + "step": 989 + }, + { + "epoch": 0.39084090011843664, + "grad_norm": 0.6150908470153809, + "learning_rate": 3.0477694433478096e-06, + "loss": 0.3477, + "step": 990 + }, + { + "epoch": 0.39123568890643506, + "grad_norm": 0.7460179328918457, + "learning_rate": 3.045795499407817e-06, + "loss": 0.4581, + "step": 991 + }, + { + "epoch": 0.3916304776944335, + "grad_norm": 0.6827566027641296, + "learning_rate": 3.043821555467825e-06, + "loss": 0.4023, + "step": 992 + }, + { + "epoch": 0.3920252664824319, + "grad_norm": 0.5554916858673096, + "learning_rate": 3.0418476115278327e-06, + "loss": 0.4696, + "step": 993 + }, + { + "epoch": 0.39242005527043033, + "grad_norm": 0.6845676302909851, + "learning_rate": 3.039873667587841e-06, + "loss": 0.4373, + "step": 994 + }, + { + "epoch": 0.39281484405842876, + "grad_norm": 0.5602235794067383, + "learning_rate": 3.0378997236478486e-06, + "loss": 0.4329, + "step": 995 + }, + { + "epoch": 0.3932096328464272, + "grad_norm": 0.766406774520874, + "learning_rate": 3.0359257797078566e-06, + "loss": 0.5519, + "step": 996 + }, + { + "epoch": 0.3936044216344256, + "grad_norm": 0.6802988648414612, + "learning_rate": 3.033951835767864e-06, + "loss": 0.4665, + "step": 997 + }, + { + "epoch": 0.39399921042242403, + "grad_norm": 0.5606549382209778, + "learning_rate": 3.0319778918278725e-06, + "loss": 0.4435, + "step": 998 + }, + { + "epoch": 0.3943939992104224, + "grad_norm": 0.7186180949211121, + "learning_rate": 3.03000394788788e-06, + "loss": 0.4818, + "step": 999 + }, + { + "epoch": 0.3947887879984208, + "grad_norm": 0.5909801721572876, + "learning_rate": 3.0280300039478885e-06, + "loss": 0.396, + "step": 1000 + }, + { + "epoch": 0.39518357678641924, + "grad_norm": 0.6234416365623474, + "learning_rate": 3.026056060007896e-06, + "loss": 0.4592, + "step": 1001 + }, + { + "epoch": 0.39557836557441767, + "grad_norm": 0.6274861693382263, + "learning_rate": 3.024082116067904e-06, + "loss": 0.3896, + "step": 1002 + }, + { + "epoch": 0.3959731543624161, + "grad_norm": 0.7020359635353088, + "learning_rate": 3.0221081721279115e-06, + "loss": 0.4873, + "step": 1003 + }, + { + "epoch": 0.3963679431504145, + "grad_norm": 0.6718515157699585, + "learning_rate": 3.02013422818792e-06, + "loss": 0.4743, + "step": 1004 + }, + { + "epoch": 0.39676273193841294, + "grad_norm": 0.5950289964675903, + "learning_rate": 3.0181602842479275e-06, + "loss": 0.444, + "step": 1005 + }, + { + "epoch": 0.39715752072641136, + "grad_norm": 0.5363778471946716, + "learning_rate": 3.0161863403079355e-06, + "loss": 0.4162, + "step": 1006 + }, + { + "epoch": 0.3975523095144098, + "grad_norm": 0.67109215259552, + "learning_rate": 3.014212396367943e-06, + "loss": 0.4588, + "step": 1007 + }, + { + "epoch": 0.3979470983024082, + "grad_norm": 0.7089436054229736, + "learning_rate": 3.0122384524279514e-06, + "loss": 0.4823, + "step": 1008 + }, + { + "epoch": 0.39834188709040663, + "grad_norm": 0.6106739044189453, + "learning_rate": 3.010264508487959e-06, + "loss": 0.4589, + "step": 1009 + }, + { + "epoch": 0.39873667587840506, + "grad_norm": 0.5706982016563416, + "learning_rate": 3.008290564547967e-06, + "loss": 0.421, + "step": 1010 + }, + { + "epoch": 0.3991314646664035, + "grad_norm": 0.6734880208969116, + "learning_rate": 3.0063166206079753e-06, + "loss": 0.4421, + "step": 1011 + }, + { + "epoch": 0.3995262534544019, + "grad_norm": 0.7687262296676636, + "learning_rate": 3.004342676667983e-06, + "loss": 0.4241, + "step": 1012 + }, + { + "epoch": 0.3999210422424003, + "grad_norm": 0.675994873046875, + "learning_rate": 3.002368732727991e-06, + "loss": 0.6374, + "step": 1013 + }, + { + "epoch": 0.40031583103039875, + "grad_norm": 0.6292682886123657, + "learning_rate": 3.000394788787999e-06, + "loss": 0.5426, + "step": 1014 + }, + { + "epoch": 0.4007106198183972, + "grad_norm": 0.7466173768043518, + "learning_rate": 2.998420844848007e-06, + "loss": 0.4852, + "step": 1015 + }, + { + "epoch": 0.4011054086063956, + "grad_norm": 0.7175878882408142, + "learning_rate": 2.9964469009080143e-06, + "loss": 0.5732, + "step": 1016 + }, + { + "epoch": 0.401500197394394, + "grad_norm": 0.6275137662887573, + "learning_rate": 2.9944729569680227e-06, + "loss": 0.4608, + "step": 1017 + }, + { + "epoch": 0.40189498618239244, + "grad_norm": 0.6140649914741516, + "learning_rate": 2.9924990130280303e-06, + "loss": 0.4585, + "step": 1018 + }, + { + "epoch": 0.40228977497039087, + "grad_norm": 0.5836409330368042, + "learning_rate": 2.9905250690880383e-06, + "loss": 0.3938, + "step": 1019 + }, + { + "epoch": 0.40268456375838924, + "grad_norm": 0.7715964913368225, + "learning_rate": 2.988551125148046e-06, + "loss": 0.4695, + "step": 1020 + }, + { + "epoch": 0.40307935254638766, + "grad_norm": 0.7592450976371765, + "learning_rate": 2.986577181208054e-06, + "loss": 0.4448, + "step": 1021 + }, + { + "epoch": 0.4034741413343861, + "grad_norm": 0.6775194406509399, + "learning_rate": 2.9846032372680618e-06, + "loss": 0.4631, + "step": 1022 + }, + { + "epoch": 0.4038689301223845, + "grad_norm": 0.6586569547653198, + "learning_rate": 2.9826292933280697e-06, + "loss": 0.4461, + "step": 1023 + }, + { + "epoch": 0.40426371891038293, + "grad_norm": 0.5695890188217163, + "learning_rate": 2.9806553493880773e-06, + "loss": 0.4899, + "step": 1024 + }, + { + "epoch": 0.40465850769838135, + "grad_norm": 0.6122593283653259, + "learning_rate": 2.9786814054480857e-06, + "loss": 0.442, + "step": 1025 + }, + { + "epoch": 0.4050532964863798, + "grad_norm": 0.6326919198036194, + "learning_rate": 2.9767074615080932e-06, + "loss": 0.4619, + "step": 1026 + }, + { + "epoch": 0.4054480852743782, + "grad_norm": 0.7269256114959717, + "learning_rate": 2.974733517568101e-06, + "loss": 0.4176, + "step": 1027 + }, + { + "epoch": 0.4058428740623766, + "grad_norm": 0.5567764639854431, + "learning_rate": 2.972759573628109e-06, + "loss": 0.4333, + "step": 1028 + }, + { + "epoch": 0.40623766285037505, + "grad_norm": 0.565563440322876, + "learning_rate": 2.970785629688117e-06, + "loss": 0.3945, + "step": 1029 + }, + { + "epoch": 0.40663245163837347, + "grad_norm": 0.7781944274902344, + "learning_rate": 2.9688116857481247e-06, + "loss": 0.5167, + "step": 1030 + }, + { + "epoch": 0.4070272404263719, + "grad_norm": 0.6486823558807373, + "learning_rate": 2.966837741808133e-06, + "loss": 0.4812, + "step": 1031 + }, + { + "epoch": 0.4074220292143703, + "grad_norm": 0.5848046541213989, + "learning_rate": 2.964863797868141e-06, + "loss": 0.4535, + "step": 1032 + }, + { + "epoch": 0.40781681800236874, + "grad_norm": 1.002951741218567, + "learning_rate": 2.9628898539281486e-06, + "loss": 0.5391, + "step": 1033 + }, + { + "epoch": 0.40821160679036717, + "grad_norm": 0.6246674656867981, + "learning_rate": 2.960915909988157e-06, + "loss": 0.4498, + "step": 1034 + }, + { + "epoch": 0.4086063955783656, + "grad_norm": 0.604279100894928, + "learning_rate": 2.9589419660481646e-06, + "loss": 0.4345, + "step": 1035 + }, + { + "epoch": 0.409001184366364, + "grad_norm": 0.6708740592002869, + "learning_rate": 2.9569680221081725e-06, + "loss": 0.4348, + "step": 1036 + }, + { + "epoch": 0.40939597315436244, + "grad_norm": 0.5466827154159546, + "learning_rate": 2.95499407816818e-06, + "loss": 0.4232, + "step": 1037 + }, + { + "epoch": 0.40979076194236086, + "grad_norm": 0.6833547949790955, + "learning_rate": 2.9530201342281885e-06, + "loss": 0.4084, + "step": 1038 + }, + { + "epoch": 0.4101855507303593, + "grad_norm": 0.7332607507705688, + "learning_rate": 2.951046190288196e-06, + "loss": 0.504, + "step": 1039 + }, + { + "epoch": 0.41058033951835765, + "grad_norm": 1.5174686908721924, + "learning_rate": 2.949072246348204e-06, + "loss": 0.4538, + "step": 1040 + }, + { + "epoch": 0.4109751283063561, + "grad_norm": 0.5634966492652893, + "learning_rate": 2.9470983024082115e-06, + "loss": 0.3846, + "step": 1041 + }, + { + "epoch": 0.4113699170943545, + "grad_norm": 0.5525903701782227, + "learning_rate": 2.94512435846822e-06, + "loss": 0.4008, + "step": 1042 + }, + { + "epoch": 0.4117647058823529, + "grad_norm": 0.5955780148506165, + "learning_rate": 2.9431504145282275e-06, + "loss": 0.4157, + "step": 1043 + }, + { + "epoch": 0.41215949467035135, + "grad_norm": 0.5607714653015137, + "learning_rate": 2.9411764705882355e-06, + "loss": 0.4234, + "step": 1044 + }, + { + "epoch": 0.41255428345834977, + "grad_norm": 0.8256320357322693, + "learning_rate": 2.9392025266482434e-06, + "loss": 0.4978, + "step": 1045 + }, + { + "epoch": 0.4129490722463482, + "grad_norm": 0.6868187189102173, + "learning_rate": 2.9372285827082514e-06, + "loss": 0.4616, + "step": 1046 + }, + { + "epoch": 0.4133438610343466, + "grad_norm": 0.788140058517456, + "learning_rate": 2.935254638768259e-06, + "loss": 0.5006, + "step": 1047 + }, + { + "epoch": 0.41373864982234504, + "grad_norm": 0.8157302737236023, + "learning_rate": 2.9332806948282674e-06, + "loss": 0.4712, + "step": 1048 + }, + { + "epoch": 0.41413343861034346, + "grad_norm": 0.822120726108551, + "learning_rate": 2.931306750888275e-06, + "loss": 0.454, + "step": 1049 + }, + { + "epoch": 0.4145282273983419, + "grad_norm": 0.5549039244651794, + "learning_rate": 2.929332806948283e-06, + "loss": 0.4308, + "step": 1050 + }, + { + "epoch": 0.4149230161863403, + "grad_norm": 0.7099475264549255, + "learning_rate": 2.9273588630082904e-06, + "loss": 0.4456, + "step": 1051 + }, + { + "epoch": 0.41531780497433873, + "grad_norm": 0.6472216844558716, + "learning_rate": 2.925384919068299e-06, + "loss": 0.5325, + "step": 1052 + }, + { + "epoch": 0.41571259376233716, + "grad_norm": 0.6916088461875916, + "learning_rate": 2.923410975128307e-06, + "loss": 0.4819, + "step": 1053 + }, + { + "epoch": 0.4161073825503356, + "grad_norm": 0.7250209450721741, + "learning_rate": 2.9214370311883143e-06, + "loss": 0.4756, + "step": 1054 + }, + { + "epoch": 0.416502171338334, + "grad_norm": 0.6947447061538696, + "learning_rate": 2.9194630872483227e-06, + "loss": 0.4968, + "step": 1055 + }, + { + "epoch": 0.4168969601263324, + "grad_norm": 0.653214693069458, + "learning_rate": 2.9174891433083303e-06, + "loss": 0.4047, + "step": 1056 + }, + { + "epoch": 0.41729174891433085, + "grad_norm": 0.7448992133140564, + "learning_rate": 2.9155151993683383e-06, + "loss": 0.4552, + "step": 1057 + }, + { + "epoch": 0.4176865377023293, + "grad_norm": 0.687221348285675, + "learning_rate": 2.913541255428346e-06, + "loss": 0.4995, + "step": 1058 + }, + { + "epoch": 0.4180813264903277, + "grad_norm": 0.5226703882217407, + "learning_rate": 2.911567311488354e-06, + "loss": 0.4853, + "step": 1059 + }, + { + "epoch": 0.4184761152783261, + "grad_norm": 0.7147587537765503, + "learning_rate": 2.9095933675483618e-06, + "loss": 0.3964, + "step": 1060 + }, + { + "epoch": 0.4188709040663245, + "grad_norm": 0.6761777997016907, + "learning_rate": 2.9076194236083697e-06, + "loss": 0.4527, + "step": 1061 + }, + { + "epoch": 0.4192656928543229, + "grad_norm": 0.900093138217926, + "learning_rate": 2.9056454796683777e-06, + "loss": 0.4615, + "step": 1062 + }, + { + "epoch": 0.41966048164232134, + "grad_norm": 0.7571338415145874, + "learning_rate": 2.9036715357283857e-06, + "loss": 0.4822, + "step": 1063 + }, + { + "epoch": 0.42005527043031976, + "grad_norm": 0.6777286529541016, + "learning_rate": 2.9016975917883932e-06, + "loss": 0.4629, + "step": 1064 + }, + { + "epoch": 0.4204500592183182, + "grad_norm": 0.5345394015312195, + "learning_rate": 2.8997236478484016e-06, + "loss": 0.3946, + "step": 1065 + }, + { + "epoch": 0.4208448480063166, + "grad_norm": 0.649733304977417, + "learning_rate": 2.897749703908409e-06, + "loss": 0.4435, + "step": 1066 + }, + { + "epoch": 0.42123963679431503, + "grad_norm": 0.7129623293876648, + "learning_rate": 2.895775759968417e-06, + "loss": 0.4646, + "step": 1067 + }, + { + "epoch": 0.42163442558231345, + "grad_norm": 0.8342190980911255, + "learning_rate": 2.8938018160284247e-06, + "loss": 0.5003, + "step": 1068 + }, + { + "epoch": 0.4220292143703119, + "grad_norm": 0.7189578413963318, + "learning_rate": 2.891827872088433e-06, + "loss": 0.4416, + "step": 1069 + }, + { + "epoch": 0.4224240031583103, + "grad_norm": 0.6436235308647156, + "learning_rate": 2.8898539281484406e-06, + "loss": 0.5017, + "step": 1070 + }, + { + "epoch": 0.4228187919463087, + "grad_norm": 0.6720636487007141, + "learning_rate": 2.8878799842084486e-06, + "loss": 0.5577, + "step": 1071 + }, + { + "epoch": 0.42321358073430715, + "grad_norm": 0.4897087514400482, + "learning_rate": 2.885906040268457e-06, + "loss": 0.3676, + "step": 1072 + }, + { + "epoch": 0.4236083695223056, + "grad_norm": 0.8128729462623596, + "learning_rate": 2.8839320963284646e-06, + "loss": 0.4912, + "step": 1073 + }, + { + "epoch": 0.424003158310304, + "grad_norm": 0.661915123462677, + "learning_rate": 2.8819581523884725e-06, + "loss": 0.4394, + "step": 1074 + }, + { + "epoch": 0.4243979470983024, + "grad_norm": 0.8859310150146484, + "learning_rate": 2.87998420844848e-06, + "loss": 0.4836, + "step": 1075 + }, + { + "epoch": 0.42479273588630084, + "grad_norm": 0.5923493504524231, + "learning_rate": 2.8780102645084885e-06, + "loss": 0.4106, + "step": 1076 + }, + { + "epoch": 0.42518752467429927, + "grad_norm": 0.945460319519043, + "learning_rate": 2.876036320568496e-06, + "loss": 0.4733, + "step": 1077 + }, + { + "epoch": 0.4255823134622977, + "grad_norm": 0.806835949420929, + "learning_rate": 2.874062376628504e-06, + "loss": 0.489, + "step": 1078 + }, + { + "epoch": 0.4259771022502961, + "grad_norm": 0.681896448135376, + "learning_rate": 2.872088432688512e-06, + "loss": 0.3751, + "step": 1079 + }, + { + "epoch": 0.42637189103829454, + "grad_norm": 0.9969651103019714, + "learning_rate": 2.87011448874852e-06, + "loss": 0.433, + "step": 1080 + }, + { + "epoch": 0.42676667982629296, + "grad_norm": 0.6358240246772766, + "learning_rate": 2.8681405448085275e-06, + "loss": 0.4389, + "step": 1081 + }, + { + "epoch": 0.42716146861429133, + "grad_norm": 0.6499475240707397, + "learning_rate": 2.866166600868536e-06, + "loss": 0.4765, + "step": 1082 + }, + { + "epoch": 0.42755625740228975, + "grad_norm": 0.6506961584091187, + "learning_rate": 2.8641926569285434e-06, + "loss": 0.4149, + "step": 1083 + }, + { + "epoch": 0.4279510461902882, + "grad_norm": 0.769465982913971, + "learning_rate": 2.8622187129885514e-06, + "loss": 0.5384, + "step": 1084 + }, + { + "epoch": 0.4283458349782866, + "grad_norm": 0.6361086964607239, + "learning_rate": 2.860244769048559e-06, + "loss": 0.4607, + "step": 1085 + }, + { + "epoch": 0.428740623766285, + "grad_norm": 0.6734834313392639, + "learning_rate": 2.8582708251085673e-06, + "loss": 0.4406, + "step": 1086 + }, + { + "epoch": 0.42913541255428345, + "grad_norm": 0.5904455780982971, + "learning_rate": 2.856296881168575e-06, + "loss": 0.4697, + "step": 1087 + }, + { + "epoch": 0.42953020134228187, + "grad_norm": 0.7285423278808594, + "learning_rate": 2.854322937228583e-06, + "loss": 0.45, + "step": 1088 + }, + { + "epoch": 0.4299249901302803, + "grad_norm": 0.7144218683242798, + "learning_rate": 2.8523489932885904e-06, + "loss": 0.4602, + "step": 1089 + }, + { + "epoch": 0.4303197789182787, + "grad_norm": 0.6027606129646301, + "learning_rate": 2.850375049348599e-06, + "loss": 0.4407, + "step": 1090 + }, + { + "epoch": 0.43071456770627714, + "grad_norm": 0.8206198811531067, + "learning_rate": 2.8484011054086064e-06, + "loss": 0.4444, + "step": 1091 + }, + { + "epoch": 0.43110935649427556, + "grad_norm": 0.6299970746040344, + "learning_rate": 2.8464271614686143e-06, + "loss": 0.364, + "step": 1092 + }, + { + "epoch": 0.431504145282274, + "grad_norm": 0.6882156133651733, + "learning_rate": 2.8444532175286227e-06, + "loss": 0.4541, + "step": 1093 + }, + { + "epoch": 0.4318989340702724, + "grad_norm": 0.6199997663497925, + "learning_rate": 2.8424792735886303e-06, + "loss": 0.4518, + "step": 1094 + }, + { + "epoch": 0.43229372285827083, + "grad_norm": 0.9833514094352722, + "learning_rate": 2.8405053296486383e-06, + "loss": 0.4898, + "step": 1095 + }, + { + "epoch": 0.43268851164626926, + "grad_norm": 0.5007759928703308, + "learning_rate": 2.8385313857086462e-06, + "loss": 0.4259, + "step": 1096 + }, + { + "epoch": 0.4330833004342677, + "grad_norm": 0.5111876130104065, + "learning_rate": 2.836557441768654e-06, + "loss": 0.4515, + "step": 1097 + }, + { + "epoch": 0.4334780892222661, + "grad_norm": 0.7558708786964417, + "learning_rate": 2.8345834978286618e-06, + "loss": 0.4515, + "step": 1098 + }, + { + "epoch": 0.43387287801026453, + "grad_norm": 0.7335221171379089, + "learning_rate": 2.83260955388867e-06, + "loss": 0.4911, + "step": 1099 + }, + { + "epoch": 0.43426766679826295, + "grad_norm": 0.621051013469696, + "learning_rate": 2.8306356099486777e-06, + "loss": 0.4074, + "step": 1100 + }, + { + "epoch": 0.4346624555862614, + "grad_norm": 0.9189200401306152, + "learning_rate": 2.8286616660086857e-06, + "loss": 0.5081, + "step": 1101 + }, + { + "epoch": 0.43505724437425974, + "grad_norm": 1.191723346710205, + "learning_rate": 2.8266877220686932e-06, + "loss": 0.4813, + "step": 1102 + }, + { + "epoch": 0.43545203316225817, + "grad_norm": 0.7541670799255371, + "learning_rate": 2.8247137781287016e-06, + "loss": 0.4726, + "step": 1103 + }, + { + "epoch": 0.4358468219502566, + "grad_norm": 0.5687462687492371, + "learning_rate": 2.822739834188709e-06, + "loss": 0.4281, + "step": 1104 + }, + { + "epoch": 0.436241610738255, + "grad_norm": 0.7045027017593384, + "learning_rate": 2.820765890248717e-06, + "loss": 0.4387, + "step": 1105 + }, + { + "epoch": 0.43663639952625344, + "grad_norm": 0.7751049399375916, + "learning_rate": 2.8187919463087247e-06, + "loss": 0.4907, + "step": 1106 + }, + { + "epoch": 0.43703118831425186, + "grad_norm": 0.7070083618164062, + "learning_rate": 2.816818002368733e-06, + "loss": 0.4284, + "step": 1107 + }, + { + "epoch": 0.4374259771022503, + "grad_norm": 0.7606474757194519, + "learning_rate": 2.8148440584287406e-06, + "loss": 0.501, + "step": 1108 + }, + { + "epoch": 0.4378207658902487, + "grad_norm": 0.6936302185058594, + "learning_rate": 2.8128701144887486e-06, + "loss": 0.5191, + "step": 1109 + }, + { + "epoch": 0.43821555467824713, + "grad_norm": 0.6369835138320923, + "learning_rate": 2.8108961705487566e-06, + "loss": 0.4663, + "step": 1110 + }, + { + "epoch": 0.43861034346624556, + "grad_norm": 0.6645917892456055, + "learning_rate": 2.8089222266087645e-06, + "loss": 0.4636, + "step": 1111 + }, + { + "epoch": 0.439005132254244, + "grad_norm": 0.7514409422874451, + "learning_rate": 2.806948282668772e-06, + "loss": 0.4508, + "step": 1112 + }, + { + "epoch": 0.4393999210422424, + "grad_norm": 0.5270315408706665, + "learning_rate": 2.8049743387287805e-06, + "loss": 0.4324, + "step": 1113 + }, + { + "epoch": 0.4397947098302408, + "grad_norm": 0.6139978766441345, + "learning_rate": 2.8030003947887885e-06, + "loss": 0.4854, + "step": 1114 + }, + { + "epoch": 0.44018949861823925, + "grad_norm": 0.674298107624054, + "learning_rate": 2.801026450848796e-06, + "loss": 0.5496, + "step": 1115 + }, + { + "epoch": 0.4405842874062377, + "grad_norm": 0.7352696657180786, + "learning_rate": 2.7990525069088044e-06, + "loss": 0.4648, + "step": 1116 + }, + { + "epoch": 0.4409790761942361, + "grad_norm": 0.8596398234367371, + "learning_rate": 2.797078562968812e-06, + "loss": 0.4733, + "step": 1117 + }, + { + "epoch": 0.4413738649822345, + "grad_norm": 0.5834324359893799, + "learning_rate": 2.79510461902882e-06, + "loss": 0.3985, + "step": 1118 + }, + { + "epoch": 0.44176865377023294, + "grad_norm": 0.6457158327102661, + "learning_rate": 2.7931306750888275e-06, + "loss": 0.515, + "step": 1119 + }, + { + "epoch": 0.44216344255823137, + "grad_norm": 0.5926237106323242, + "learning_rate": 2.791156731148836e-06, + "loss": 0.4653, + "step": 1120 + }, + { + "epoch": 0.4425582313462298, + "grad_norm": 0.6079720854759216, + "learning_rate": 2.7891827872088434e-06, + "loss": 0.49, + "step": 1121 + }, + { + "epoch": 0.4429530201342282, + "grad_norm": 0.7314640283584595, + "learning_rate": 2.7872088432688514e-06, + "loss": 0.4762, + "step": 1122 + }, + { + "epoch": 0.4433478089222266, + "grad_norm": 0.7311252951622009, + "learning_rate": 2.785234899328859e-06, + "loss": 0.5289, + "step": 1123 + }, + { + "epoch": 0.443742597710225, + "grad_norm": 0.6561733484268188, + "learning_rate": 2.7832609553888673e-06, + "loss": 0.5192, + "step": 1124 + }, + { + "epoch": 0.44413738649822343, + "grad_norm": 0.5984068512916565, + "learning_rate": 2.781287011448875e-06, + "loss": 0.4624, + "step": 1125 + }, + { + "epoch": 0.44453217528622185, + "grad_norm": 0.5888249278068542, + "learning_rate": 2.779313067508883e-06, + "loss": 0.4476, + "step": 1126 + }, + { + "epoch": 0.4449269640742203, + "grad_norm": 0.613649308681488, + "learning_rate": 2.777339123568891e-06, + "loss": 0.5036, + "step": 1127 + }, + { + "epoch": 0.4453217528622187, + "grad_norm": 0.5916643738746643, + "learning_rate": 2.775365179628899e-06, + "loss": 0.4447, + "step": 1128 + }, + { + "epoch": 0.4457165416502171, + "grad_norm": 0.5451396703720093, + "learning_rate": 2.7733912356889064e-06, + "loss": 0.4687, + "step": 1129 + }, + { + "epoch": 0.44611133043821555, + "grad_norm": 0.7082763314247131, + "learning_rate": 2.7714172917489148e-06, + "loss": 0.4062, + "step": 1130 + }, + { + "epoch": 0.44650611922621397, + "grad_norm": 0.5566937327384949, + "learning_rate": 2.7694433478089223e-06, + "loss": 0.3831, + "step": 1131 + }, + { + "epoch": 0.4469009080142124, + "grad_norm": 0.5322623252868652, + "learning_rate": 2.7674694038689303e-06, + "loss": 0.3713, + "step": 1132 + }, + { + "epoch": 0.4472956968022108, + "grad_norm": 0.7311296463012695, + "learning_rate": 2.765495459928938e-06, + "loss": 0.5047, + "step": 1133 + }, + { + "epoch": 0.44769048559020924, + "grad_norm": 0.806620180606842, + "learning_rate": 2.7635215159889462e-06, + "loss": 0.5415, + "step": 1134 + }, + { + "epoch": 0.44808527437820767, + "grad_norm": 0.687343418598175, + "learning_rate": 2.761547572048954e-06, + "loss": 0.4548, + "step": 1135 + }, + { + "epoch": 0.4484800631662061, + "grad_norm": 0.6881664991378784, + "learning_rate": 2.7595736281089617e-06, + "loss": 0.4109, + "step": 1136 + }, + { + "epoch": 0.4488748519542045, + "grad_norm": 0.7637283205986023, + "learning_rate": 2.75759968416897e-06, + "loss": 0.4716, + "step": 1137 + }, + { + "epoch": 0.44926964074220294, + "grad_norm": 0.7458791732788086, + "learning_rate": 2.7556257402289777e-06, + "loss": 0.4539, + "step": 1138 + }, + { + "epoch": 0.44966442953020136, + "grad_norm": 0.8652923107147217, + "learning_rate": 2.7536517962889857e-06, + "loss": 0.4865, + "step": 1139 + }, + { + "epoch": 0.4500592183181998, + "grad_norm": 0.7566205263137817, + "learning_rate": 2.7516778523489936e-06, + "loss": 0.4453, + "step": 1140 + }, + { + "epoch": 0.4504540071061982, + "grad_norm": 0.8130572438240051, + "learning_rate": 2.7497039084090016e-06, + "loss": 0.4852, + "step": 1141 + }, + { + "epoch": 0.45084879589419663, + "grad_norm": 0.6352393627166748, + "learning_rate": 2.747729964469009e-06, + "loss": 0.4283, + "step": 1142 + }, + { + "epoch": 0.451243584682195, + "grad_norm": 0.6608482003211975, + "learning_rate": 2.7457560205290176e-06, + "loss": 0.4299, + "step": 1143 + }, + { + "epoch": 0.4516383734701934, + "grad_norm": 0.7432076334953308, + "learning_rate": 2.743782076589025e-06, + "loss": 0.4659, + "step": 1144 + }, + { + "epoch": 0.45203316225819185, + "grad_norm": 0.8127989768981934, + "learning_rate": 2.741808132649033e-06, + "loss": 0.5694, + "step": 1145 + }, + { + "epoch": 0.45242795104619027, + "grad_norm": 0.6605392098426819, + "learning_rate": 2.7398341887090406e-06, + "loss": 0.4367, + "step": 1146 + }, + { + "epoch": 0.4528227398341887, + "grad_norm": 0.5954428315162659, + "learning_rate": 2.737860244769049e-06, + "loss": 0.4458, + "step": 1147 + }, + { + "epoch": 0.4532175286221871, + "grad_norm": 0.6467613577842712, + "learning_rate": 2.7358863008290566e-06, + "loss": 0.4857, + "step": 1148 + }, + { + "epoch": 0.45361231741018554, + "grad_norm": 0.6253966093063354, + "learning_rate": 2.7339123568890645e-06, + "loss": 0.4232, + "step": 1149 + }, + { + "epoch": 0.45400710619818396, + "grad_norm": 0.7595016956329346, + "learning_rate": 2.731938412949072e-06, + "loss": 0.4753, + "step": 1150 + }, + { + "epoch": 0.4544018949861824, + "grad_norm": 0.6374835968017578, + "learning_rate": 2.7299644690090805e-06, + "loss": 0.431, + "step": 1151 + }, + { + "epoch": 0.4547966837741808, + "grad_norm": 0.6038119792938232, + "learning_rate": 2.727990525069088e-06, + "loss": 0.3878, + "step": 1152 + }, + { + "epoch": 0.45519147256217923, + "grad_norm": 0.6148578524589539, + "learning_rate": 2.726016581129096e-06, + "loss": 0.4453, + "step": 1153 + }, + { + "epoch": 0.45558626135017766, + "grad_norm": 0.7496819496154785, + "learning_rate": 2.724042637189104e-06, + "loss": 0.4768, + "step": 1154 + }, + { + "epoch": 0.4559810501381761, + "grad_norm": 0.6673437356948853, + "learning_rate": 2.722068693249112e-06, + "loss": 0.4753, + "step": 1155 + }, + { + "epoch": 0.4563758389261745, + "grad_norm": 0.5623132586479187, + "learning_rate": 2.72009474930912e-06, + "loss": 0.4109, + "step": 1156 + }, + { + "epoch": 0.4567706277141729, + "grad_norm": 0.6432541012763977, + "learning_rate": 2.718120805369128e-06, + "loss": 0.4317, + "step": 1157 + }, + { + "epoch": 0.45716541650217135, + "grad_norm": 0.6548432111740112, + "learning_rate": 2.716146861429136e-06, + "loss": 0.4191, + "step": 1158 + }, + { + "epoch": 0.4575602052901698, + "grad_norm": 0.5769900679588318, + "learning_rate": 2.7141729174891434e-06, + "loss": 0.4108, + "step": 1159 + }, + { + "epoch": 0.4579549940781682, + "grad_norm": 0.7481065988540649, + "learning_rate": 2.712198973549152e-06, + "loss": 0.5047, + "step": 1160 + }, + { + "epoch": 0.4583497828661666, + "grad_norm": 0.6888668537139893, + "learning_rate": 2.7102250296091594e-06, + "loss": 0.4669, + "step": 1161 + }, + { + "epoch": 0.45874457165416505, + "grad_norm": 0.8106175661087036, + "learning_rate": 2.7082510856691673e-06, + "loss": 0.5329, + "step": 1162 + }, + { + "epoch": 0.45913936044216347, + "grad_norm": 0.6439200639724731, + "learning_rate": 2.706277141729175e-06, + "loss": 0.4545, + "step": 1163 + }, + { + "epoch": 0.45953414923016184, + "grad_norm": 0.5927848219871521, + "learning_rate": 2.7043031977891833e-06, + "loss": 0.4106, + "step": 1164 + }, + { + "epoch": 0.45992893801816026, + "grad_norm": 0.7160584926605225, + "learning_rate": 2.702329253849191e-06, + "loss": 0.5143, + "step": 1165 + }, + { + "epoch": 0.4603237268061587, + "grad_norm": 0.5811100602149963, + "learning_rate": 2.700355309909199e-06, + "loss": 0.3825, + "step": 1166 + }, + { + "epoch": 0.4607185155941571, + "grad_norm": 0.5602670907974243, + "learning_rate": 2.6983813659692064e-06, + "loss": 0.4029, + "step": 1167 + }, + { + "epoch": 0.46111330438215553, + "grad_norm": 0.5631111860275269, + "learning_rate": 2.6964074220292148e-06, + "loss": 0.4358, + "step": 1168 + }, + { + "epoch": 0.46150809317015395, + "grad_norm": 0.6296261548995972, + "learning_rate": 2.6944334780892223e-06, + "loss": 0.4804, + "step": 1169 + }, + { + "epoch": 0.4619028819581524, + "grad_norm": 0.6100728511810303, + "learning_rate": 2.6924595341492303e-06, + "loss": 0.3951, + "step": 1170 + }, + { + "epoch": 0.4622976707461508, + "grad_norm": 0.6900010704994202, + "learning_rate": 2.6904855902092383e-06, + "loss": 0.4579, + "step": 1171 + }, + { + "epoch": 0.4626924595341492, + "grad_norm": 0.8099308609962463, + "learning_rate": 2.6885116462692462e-06, + "loss": 0.5005, + "step": 1172 + }, + { + "epoch": 0.46308724832214765, + "grad_norm": 0.6882344484329224, + "learning_rate": 2.6865377023292538e-06, + "loss": 0.4445, + "step": 1173 + }, + { + "epoch": 0.4634820371101461, + "grad_norm": 0.8537095189094543, + "learning_rate": 2.684563758389262e-06, + "loss": 0.499, + "step": 1174 + }, + { + "epoch": 0.4638768258981445, + "grad_norm": 0.6086930632591248, + "learning_rate": 2.68258981444927e-06, + "loss": 0.4454, + "step": 1175 + }, + { + "epoch": 0.4642716146861429, + "grad_norm": 0.5413428544998169, + "learning_rate": 2.6806158705092777e-06, + "loss": 0.3797, + "step": 1176 + }, + { + "epoch": 0.46466640347414134, + "grad_norm": 0.6859705448150635, + "learning_rate": 2.678641926569286e-06, + "loss": 0.459, + "step": 1177 + }, + { + "epoch": 0.46506119226213977, + "grad_norm": 0.6708582043647766, + "learning_rate": 2.6766679826292936e-06, + "loss": 0.4457, + "step": 1178 + }, + { + "epoch": 0.4654559810501382, + "grad_norm": 0.9489005208015442, + "learning_rate": 2.6746940386893016e-06, + "loss": 0.6154, + "step": 1179 + }, + { + "epoch": 0.4658507698381366, + "grad_norm": 0.6130208969116211, + "learning_rate": 2.672720094749309e-06, + "loss": 0.4636, + "step": 1180 + }, + { + "epoch": 0.46624555862613504, + "grad_norm": 0.835749626159668, + "learning_rate": 2.6707461508093176e-06, + "loss": 0.4943, + "step": 1181 + }, + { + "epoch": 0.46664034741413346, + "grad_norm": 0.6410770416259766, + "learning_rate": 2.668772206869325e-06, + "loss": 0.4544, + "step": 1182 + }, + { + "epoch": 0.4670351362021319, + "grad_norm": 0.7170780301094055, + "learning_rate": 2.666798262929333e-06, + "loss": 0.431, + "step": 1183 + }, + { + "epoch": 0.4674299249901303, + "grad_norm": 0.6568809151649475, + "learning_rate": 2.6648243189893406e-06, + "loss": 0.4496, + "step": 1184 + }, + { + "epoch": 0.4678247137781287, + "grad_norm": 0.567686140537262, + "learning_rate": 2.662850375049349e-06, + "loss": 0.403, + "step": 1185 + }, + { + "epoch": 0.4682195025661271, + "grad_norm": 0.7214701175689697, + "learning_rate": 2.6608764311093566e-06, + "loss": 0.4548, + "step": 1186 + }, + { + "epoch": 0.4686142913541255, + "grad_norm": 0.6007523536682129, + "learning_rate": 2.6589024871693645e-06, + "loss": 0.4855, + "step": 1187 + }, + { + "epoch": 0.46900908014212395, + "grad_norm": 0.7891653180122375, + "learning_rate": 2.6569285432293725e-06, + "loss": 0.4576, + "step": 1188 + }, + { + "epoch": 0.46940386893012237, + "grad_norm": 0.6021583676338196, + "learning_rate": 2.6549545992893805e-06, + "loss": 0.4305, + "step": 1189 + }, + { + "epoch": 0.4697986577181208, + "grad_norm": 0.7603434324264526, + "learning_rate": 2.652980655349388e-06, + "loss": 0.4973, + "step": 1190 + }, + { + "epoch": 0.4701934465061192, + "grad_norm": 0.7179158926010132, + "learning_rate": 2.6510067114093964e-06, + "loss": 0.4742, + "step": 1191 + }, + { + "epoch": 0.47058823529411764, + "grad_norm": 0.71968013048172, + "learning_rate": 2.649032767469404e-06, + "loss": 0.4789, + "step": 1192 + }, + { + "epoch": 0.47098302408211606, + "grad_norm": 0.587526261806488, + "learning_rate": 2.647058823529412e-06, + "loss": 0.4762, + "step": 1193 + }, + { + "epoch": 0.4713778128701145, + "grad_norm": 0.8205366134643555, + "learning_rate": 2.6450848795894195e-06, + "loss": 0.4902, + "step": 1194 + }, + { + "epoch": 0.4717726016581129, + "grad_norm": 0.676849901676178, + "learning_rate": 2.643110935649428e-06, + "loss": 0.4554, + "step": 1195 + }, + { + "epoch": 0.47216739044611133, + "grad_norm": 0.6435837745666504, + "learning_rate": 2.641136991709436e-06, + "loss": 0.4373, + "step": 1196 + }, + { + "epoch": 0.47256217923410976, + "grad_norm": 0.6823952198028564, + "learning_rate": 2.6391630477694434e-06, + "loss": 0.4242, + "step": 1197 + }, + { + "epoch": 0.4729569680221082, + "grad_norm": 0.5117971897125244, + "learning_rate": 2.637189103829452e-06, + "loss": 0.4319, + "step": 1198 + }, + { + "epoch": 0.4733517568101066, + "grad_norm": 0.6872542500495911, + "learning_rate": 2.6352151598894594e-06, + "loss": 0.4878, + "step": 1199 + }, + { + "epoch": 0.47374654559810503, + "grad_norm": 0.5621276497840881, + "learning_rate": 2.6332412159494673e-06, + "loss": 0.4369, + "step": 1200 + }, + { + "epoch": 0.47414133438610345, + "grad_norm": 0.6369271874427795, + "learning_rate": 2.631267272009475e-06, + "loss": 0.4515, + "step": 1201 + }, + { + "epoch": 0.4745361231741019, + "grad_norm": 0.5075145959854126, + "learning_rate": 2.6292933280694833e-06, + "loss": 0.3833, + "step": 1202 + }, + { + "epoch": 0.4749309119621003, + "grad_norm": 0.5953491926193237, + "learning_rate": 2.627319384129491e-06, + "loss": 0.4561, + "step": 1203 + }, + { + "epoch": 0.4753257007500987, + "grad_norm": 0.8124741315841675, + "learning_rate": 2.625345440189499e-06, + "loss": 0.4051, + "step": 1204 + }, + { + "epoch": 0.4757204895380971, + "grad_norm": 0.6228059530258179, + "learning_rate": 2.6233714962495068e-06, + "loss": 0.4455, + "step": 1205 + }, + { + "epoch": 0.4761152783260955, + "grad_norm": 0.7919908165931702, + "learning_rate": 2.6213975523095148e-06, + "loss": 0.5099, + "step": 1206 + }, + { + "epoch": 0.47651006711409394, + "grad_norm": 0.5838243961334229, + "learning_rate": 2.6194236083695223e-06, + "loss": 0.4463, + "step": 1207 + }, + { + "epoch": 0.47690485590209236, + "grad_norm": 0.5771192908287048, + "learning_rate": 2.6174496644295307e-06, + "loss": 0.4237, + "step": 1208 + }, + { + "epoch": 0.4772996446900908, + "grad_norm": 0.6344156265258789, + "learning_rate": 2.6154757204895382e-06, + "loss": 0.4647, + "step": 1209 + }, + { + "epoch": 0.4776944334780892, + "grad_norm": 0.5786174535751343, + "learning_rate": 2.6135017765495462e-06, + "loss": 0.4125, + "step": 1210 + }, + { + "epoch": 0.47808922226608763, + "grad_norm": 0.6957029104232788, + "learning_rate": 2.6115278326095538e-06, + "loss": 0.4558, + "step": 1211 + }, + { + "epoch": 0.47848401105408606, + "grad_norm": 0.6307162642478943, + "learning_rate": 2.609553888669562e-06, + "loss": 0.3891, + "step": 1212 + }, + { + "epoch": 0.4788787998420845, + "grad_norm": 0.6606603860855103, + "learning_rate": 2.6075799447295697e-06, + "loss": 0.4016, + "step": 1213 + }, + { + "epoch": 0.4792735886300829, + "grad_norm": 0.6429834365844727, + "learning_rate": 2.6056060007895777e-06, + "loss": 0.4688, + "step": 1214 + }, + { + "epoch": 0.4796683774180813, + "grad_norm": 0.5745736956596375, + "learning_rate": 2.6036320568495852e-06, + "loss": 0.4142, + "step": 1215 + }, + { + "epoch": 0.48006316620607975, + "grad_norm": 0.7437013983726501, + "learning_rate": 2.6016581129095936e-06, + "loss": 0.4743, + "step": 1216 + }, + { + "epoch": 0.4804579549940782, + "grad_norm": 0.7163952589035034, + "learning_rate": 2.5996841689696016e-06, + "loss": 0.516, + "step": 1217 + }, + { + "epoch": 0.4808527437820766, + "grad_norm": 0.6548170447349548, + "learning_rate": 2.597710225029609e-06, + "loss": 0.4687, + "step": 1218 + }, + { + "epoch": 0.481247532570075, + "grad_norm": 0.6646710634231567, + "learning_rate": 2.5957362810896176e-06, + "loss": 0.448, + "step": 1219 + }, + { + "epoch": 0.48164232135807344, + "grad_norm": 0.675640881061554, + "learning_rate": 2.593762337149625e-06, + "loss": 0.5063, + "step": 1220 + }, + { + "epoch": 0.48203711014607187, + "grad_norm": 0.6806384325027466, + "learning_rate": 2.591788393209633e-06, + "loss": 0.4518, + "step": 1221 + }, + { + "epoch": 0.4824318989340703, + "grad_norm": 0.7796854972839355, + "learning_rate": 2.589814449269641e-06, + "loss": 0.5253, + "step": 1222 + }, + { + "epoch": 0.4828266877220687, + "grad_norm": 0.5428137183189392, + "learning_rate": 2.587840505329649e-06, + "loss": 0.4163, + "step": 1223 + }, + { + "epoch": 0.48322147651006714, + "grad_norm": 0.5898733735084534, + "learning_rate": 2.5858665613896566e-06, + "loss": 0.4408, + "step": 1224 + }, + { + "epoch": 0.48361626529806556, + "grad_norm": 0.603740930557251, + "learning_rate": 2.583892617449665e-06, + "loss": 0.4383, + "step": 1225 + }, + { + "epoch": 0.48401105408606393, + "grad_norm": 0.6877209544181824, + "learning_rate": 2.5819186735096725e-06, + "loss": 0.4639, + "step": 1226 + }, + { + "epoch": 0.48440584287406235, + "grad_norm": 0.6104294061660767, + "learning_rate": 2.5799447295696805e-06, + "loss": 0.4523, + "step": 1227 + }, + { + "epoch": 0.4848006316620608, + "grad_norm": 0.6250008940696716, + "learning_rate": 2.577970785629688e-06, + "loss": 0.4072, + "step": 1228 + }, + { + "epoch": 0.4851954204500592, + "grad_norm": 0.5807295441627502, + "learning_rate": 2.5759968416896964e-06, + "loss": 0.4943, + "step": 1229 + }, + { + "epoch": 0.4855902092380576, + "grad_norm": 0.6586105227470398, + "learning_rate": 2.574022897749704e-06, + "loss": 0.4908, + "step": 1230 + }, + { + "epoch": 0.48598499802605605, + "grad_norm": 0.5045081973075867, + "learning_rate": 2.572048953809712e-06, + "loss": 0.4221, + "step": 1231 + }, + { + "epoch": 0.48637978681405447, + "grad_norm": 0.7380528450012207, + "learning_rate": 2.5700750098697195e-06, + "loss": 0.4224, + "step": 1232 + }, + { + "epoch": 0.4867745756020529, + "grad_norm": 0.7708085179328918, + "learning_rate": 2.568101065929728e-06, + "loss": 0.4895, + "step": 1233 + }, + { + "epoch": 0.4871693643900513, + "grad_norm": 0.8244683742523193, + "learning_rate": 2.5661271219897354e-06, + "loss": 0.4463, + "step": 1234 + }, + { + "epoch": 0.48756415317804974, + "grad_norm": 0.686051070690155, + "learning_rate": 2.5641531780497434e-06, + "loss": 0.4925, + "step": 1235 + }, + { + "epoch": 0.48795894196604817, + "grad_norm": 0.6063368916511536, + "learning_rate": 2.5621792341097514e-06, + "loss": 0.498, + "step": 1236 + }, + { + "epoch": 0.4883537307540466, + "grad_norm": 0.6616171002388, + "learning_rate": 2.5602052901697594e-06, + "loss": 0.4937, + "step": 1237 + }, + { + "epoch": 0.488748519542045, + "grad_norm": 0.7408667206764221, + "learning_rate": 2.5582313462297673e-06, + "loss": 0.4825, + "step": 1238 + }, + { + "epoch": 0.48914330833004344, + "grad_norm": 0.7262516021728516, + "learning_rate": 2.5562574022897753e-06, + "loss": 0.4792, + "step": 1239 + }, + { + "epoch": 0.48953809711804186, + "grad_norm": 0.6668491363525391, + "learning_rate": 2.5542834583497833e-06, + "loss": 0.5407, + "step": 1240 + }, + { + "epoch": 0.4899328859060403, + "grad_norm": 0.7594133019447327, + "learning_rate": 2.552309514409791e-06, + "loss": 0.4706, + "step": 1241 + }, + { + "epoch": 0.4903276746940387, + "grad_norm": 0.6195098757743835, + "learning_rate": 2.5503355704697992e-06, + "loss": 0.4413, + "step": 1242 + }, + { + "epoch": 0.49072246348203713, + "grad_norm": 0.6256967186927795, + "learning_rate": 2.5483616265298068e-06, + "loss": 0.5094, + "step": 1243 + }, + { + "epoch": 0.49111725227003555, + "grad_norm": 0.8328626751899719, + "learning_rate": 2.5463876825898148e-06, + "loss": 0.4336, + "step": 1244 + }, + { + "epoch": 0.491512041058034, + "grad_norm": 0.5735040307044983, + "learning_rate": 2.5444137386498223e-06, + "loss": 0.4492, + "step": 1245 + }, + { + "epoch": 0.49190682984603235, + "grad_norm": 0.6293225288391113, + "learning_rate": 2.5424397947098307e-06, + "loss": 0.4848, + "step": 1246 + }, + { + "epoch": 0.49230161863403077, + "grad_norm": 0.826492190361023, + "learning_rate": 2.5404658507698382e-06, + "loss": 0.5015, + "step": 1247 + }, + { + "epoch": 0.4926964074220292, + "grad_norm": 0.7467468976974487, + "learning_rate": 2.5384919068298462e-06, + "loss": 0.4907, + "step": 1248 + }, + { + "epoch": 0.4930911962100276, + "grad_norm": 0.678180456161499, + "learning_rate": 2.5365179628898538e-06, + "loss": 0.4035, + "step": 1249 + }, + { + "epoch": 0.49348598499802604, + "grad_norm": 0.6109394431114197, + "learning_rate": 2.534544018949862e-06, + "loss": 0.4087, + "step": 1250 + }, + { + "epoch": 0.49388077378602446, + "grad_norm": 0.502202570438385, + "learning_rate": 2.5325700750098697e-06, + "loss": 0.3746, + "step": 1251 + }, + { + "epoch": 0.4942755625740229, + "grad_norm": 0.529899001121521, + "learning_rate": 2.5305961310698777e-06, + "loss": 0.4209, + "step": 1252 + }, + { + "epoch": 0.4946703513620213, + "grad_norm": 0.7257699370384216, + "learning_rate": 2.5286221871298857e-06, + "loss": 0.4799, + "step": 1253 + }, + { + "epoch": 0.49506514015001973, + "grad_norm": 0.8750326037406921, + "learning_rate": 2.5266482431898936e-06, + "loss": 0.6233, + "step": 1254 + }, + { + "epoch": 0.49545992893801816, + "grad_norm": 0.6076992750167847, + "learning_rate": 2.524674299249901e-06, + "loss": 0.3714, + "step": 1255 + }, + { + "epoch": 0.4958547177260166, + "grad_norm": 0.6446328163146973, + "learning_rate": 2.5227003553099096e-06, + "loss": 0.4355, + "step": 1256 + }, + { + "epoch": 0.496249506514015, + "grad_norm": 0.7292859554290771, + "learning_rate": 2.520726411369917e-06, + "loss": 0.4489, + "step": 1257 + }, + { + "epoch": 0.4966442953020134, + "grad_norm": 1.0100116729736328, + "learning_rate": 2.518752467429925e-06, + "loss": 0.4999, + "step": 1258 + }, + { + "epoch": 0.49703908409001185, + "grad_norm": 0.6791582107543945, + "learning_rate": 2.5167785234899335e-06, + "loss": 0.4784, + "step": 1259 + }, + { + "epoch": 0.4974338728780103, + "grad_norm": 0.6711677312850952, + "learning_rate": 2.514804579549941e-06, + "loss": 0.4658, + "step": 1260 + }, + { + "epoch": 0.4978286616660087, + "grad_norm": 0.6546309590339661, + "learning_rate": 2.512830635609949e-06, + "loss": 0.4362, + "step": 1261 + }, + { + "epoch": 0.4982234504540071, + "grad_norm": 0.6165967583656311, + "learning_rate": 2.5108566916699566e-06, + "loss": 0.5405, + "step": 1262 + }, + { + "epoch": 0.49861823924200555, + "grad_norm": 0.6808473467826843, + "learning_rate": 2.508882747729965e-06, + "loss": 0.5018, + "step": 1263 + }, + { + "epoch": 0.49901302803000397, + "grad_norm": 0.5683500170707703, + "learning_rate": 2.5069088037899725e-06, + "loss": 0.4245, + "step": 1264 + }, + { + "epoch": 0.4994078168180024, + "grad_norm": 0.6236129403114319, + "learning_rate": 2.5049348598499805e-06, + "loss": 0.4243, + "step": 1265 + }, + { + "epoch": 0.4998026056060008, + "grad_norm": 0.7546696066856384, + "learning_rate": 2.502960915909988e-06, + "loss": 0.4827, + "step": 1266 + }, + { + "epoch": 0.5001973943939992, + "grad_norm": 0.6275173425674438, + "learning_rate": 2.5009869719699964e-06, + "loss": 0.4075, + "step": 1267 + }, + { + "epoch": 0.5005921831819976, + "grad_norm": 0.6931349039077759, + "learning_rate": 2.4990130280300044e-06, + "loss": 0.4469, + "step": 1268 + }, + { + "epoch": 0.5009869719699961, + "grad_norm": 0.7395671010017395, + "learning_rate": 2.4970390840900124e-06, + "loss": 0.518, + "step": 1269 + }, + { + "epoch": 0.5013817607579945, + "grad_norm": 0.6942417025566101, + "learning_rate": 2.49506514015002e-06, + "loss": 0.5042, + "step": 1270 + }, + { + "epoch": 0.5017765495459929, + "grad_norm": 1.1212412118911743, + "learning_rate": 2.493091196210028e-06, + "loss": 0.4363, + "step": 1271 + }, + { + "epoch": 0.5021713383339913, + "grad_norm": 0.6513260006904602, + "learning_rate": 2.491117252270036e-06, + "loss": 0.4566, + "step": 1272 + }, + { + "epoch": 0.5025661271219898, + "grad_norm": 0.7834178805351257, + "learning_rate": 2.489143308330044e-06, + "loss": 0.563, + "step": 1273 + }, + { + "epoch": 0.5029609159099881, + "grad_norm": 0.6035041809082031, + "learning_rate": 2.4871693643900514e-06, + "loss": 0.4403, + "step": 1274 + }, + { + "epoch": 0.5033557046979866, + "grad_norm": 0.6840185523033142, + "learning_rate": 2.4851954204500594e-06, + "loss": 0.4814, + "step": 1275 + }, + { + "epoch": 0.503750493485985, + "grad_norm": 0.7183567881584167, + "learning_rate": 2.4832214765100673e-06, + "loss": 0.4079, + "step": 1276 + }, + { + "epoch": 0.5041452822739834, + "grad_norm": 0.6081151366233826, + "learning_rate": 2.4812475325700753e-06, + "loss": 0.4009, + "step": 1277 + }, + { + "epoch": 0.5045400710619818, + "grad_norm": 0.6999273896217346, + "learning_rate": 2.4792735886300833e-06, + "loss": 0.5121, + "step": 1278 + }, + { + "epoch": 0.5049348598499802, + "grad_norm": 0.5799371600151062, + "learning_rate": 2.477299644690091e-06, + "loss": 0.4353, + "step": 1279 + }, + { + "epoch": 0.5053296486379787, + "grad_norm": 0.707825243473053, + "learning_rate": 2.475325700750099e-06, + "loss": 0.4863, + "step": 1280 + }, + { + "epoch": 0.5057244374259771, + "grad_norm": 0.6572830677032471, + "learning_rate": 2.4733517568101068e-06, + "loss": 0.5016, + "step": 1281 + }, + { + "epoch": 0.5061192262139755, + "grad_norm": 0.7636964321136475, + "learning_rate": 2.4713778128701147e-06, + "loss": 0.4736, + "step": 1282 + }, + { + "epoch": 0.5065140150019739, + "grad_norm": 0.7705956697463989, + "learning_rate": 2.4694038689301227e-06, + "loss": 0.447, + "step": 1283 + }, + { + "epoch": 0.5069088037899724, + "grad_norm": 0.6666721105575562, + "learning_rate": 2.4674299249901303e-06, + "loss": 0.4043, + "step": 1284 + }, + { + "epoch": 0.5073035925779708, + "grad_norm": 0.8161370754241943, + "learning_rate": 2.4654559810501382e-06, + "loss": 0.5152, + "step": 1285 + }, + { + "epoch": 0.5076983813659692, + "grad_norm": 0.7466740608215332, + "learning_rate": 2.4634820371101462e-06, + "loss": 0.5532, + "step": 1286 + }, + { + "epoch": 0.5080931701539676, + "grad_norm": 0.5192285180091858, + "learning_rate": 2.461508093170154e-06, + "loss": 0.4562, + "step": 1287 + }, + { + "epoch": 0.5084879589419661, + "grad_norm": 0.5852295756340027, + "learning_rate": 2.4595341492301617e-06, + "loss": 0.4642, + "step": 1288 + }, + { + "epoch": 0.5088827477299644, + "grad_norm": 0.7261310815811157, + "learning_rate": 2.45756020529017e-06, + "loss": 0.507, + "step": 1289 + }, + { + "epoch": 0.5092775365179629, + "grad_norm": 0.721078097820282, + "learning_rate": 2.455586261350178e-06, + "loss": 0.5149, + "step": 1290 + }, + { + "epoch": 0.5096723253059613, + "grad_norm": 0.8720150589942932, + "learning_rate": 2.4536123174101857e-06, + "loss": 0.5269, + "step": 1291 + }, + { + "epoch": 0.5100671140939598, + "grad_norm": 0.7992442846298218, + "learning_rate": 2.4516383734701936e-06, + "loss": 0.5331, + "step": 1292 + }, + { + "epoch": 0.5104619028819581, + "grad_norm": 0.701917290687561, + "learning_rate": 2.4496644295302016e-06, + "loss": 0.4784, + "step": 1293 + }, + { + "epoch": 0.5108566916699566, + "grad_norm": 0.703329861164093, + "learning_rate": 2.4476904855902096e-06, + "loss": 0.4964, + "step": 1294 + }, + { + "epoch": 0.511251480457955, + "grad_norm": 0.6108284592628479, + "learning_rate": 2.4457165416502175e-06, + "loss": 0.4507, + "step": 1295 + }, + { + "epoch": 0.5116462692459535, + "grad_norm": 0.6533117294311523, + "learning_rate": 2.443742597710225e-06, + "loss": 0.502, + "step": 1296 + }, + { + "epoch": 0.5120410580339518, + "grad_norm": 0.7329955697059631, + "learning_rate": 2.441768653770233e-06, + "loss": 0.5468, + "step": 1297 + }, + { + "epoch": 0.5124358468219502, + "grad_norm": 0.609727144241333, + "learning_rate": 2.439794709830241e-06, + "loss": 0.4498, + "step": 1298 + }, + { + "epoch": 0.5128306356099487, + "grad_norm": 0.6575713157653809, + "learning_rate": 2.437820765890249e-06, + "loss": 0.481, + "step": 1299 + }, + { + "epoch": 0.513225424397947, + "grad_norm": 0.7205227613449097, + "learning_rate": 2.435846821950257e-06, + "loss": 0.4345, + "step": 1300 + }, + { + "epoch": 0.5136202131859455, + "grad_norm": 0.630983293056488, + "learning_rate": 2.4338728780102645e-06, + "loss": 0.5154, + "step": 1301 + }, + { + "epoch": 0.5140150019739439, + "grad_norm": 0.6183773875236511, + "learning_rate": 2.4318989340702725e-06, + "loss": 0.4528, + "step": 1302 + }, + { + "epoch": 0.5144097907619424, + "grad_norm": 0.5981759428977966, + "learning_rate": 2.4299249901302805e-06, + "loss": 0.4302, + "step": 1303 + }, + { + "epoch": 0.5148045795499407, + "grad_norm": 0.6217938661575317, + "learning_rate": 2.4279510461902885e-06, + "loss": 0.4271, + "step": 1304 + }, + { + "epoch": 0.5151993683379392, + "grad_norm": 0.6507735848426819, + "learning_rate": 2.425977102250296e-06, + "loss": 0.5332, + "step": 1305 + }, + { + "epoch": 0.5155941571259376, + "grad_norm": 0.6460922360420227, + "learning_rate": 2.424003158310304e-06, + "loss": 0.45, + "step": 1306 + }, + { + "epoch": 0.5159889459139361, + "grad_norm": 0.6341075897216797, + "learning_rate": 2.422029214370312e-06, + "loss": 0.4883, + "step": 1307 + }, + { + "epoch": 0.5163837347019344, + "grad_norm": 0.7137075066566467, + "learning_rate": 2.42005527043032e-06, + "loss": 0.4651, + "step": 1308 + }, + { + "epoch": 0.5167785234899329, + "grad_norm": 0.6554065942764282, + "learning_rate": 2.418081326490328e-06, + "loss": 0.4787, + "step": 1309 + }, + { + "epoch": 0.5171733122779313, + "grad_norm": 0.708704948425293, + "learning_rate": 2.416107382550336e-06, + "loss": 0.4928, + "step": 1310 + }, + { + "epoch": 0.5175681010659298, + "grad_norm": 0.637545108795166, + "learning_rate": 2.414133438610344e-06, + "loss": 0.4794, + "step": 1311 + }, + { + "epoch": 0.5179628898539281, + "grad_norm": 0.809216320514679, + "learning_rate": 2.412159494670352e-06, + "loss": 0.5442, + "step": 1312 + }, + { + "epoch": 0.5183576786419266, + "grad_norm": 0.6001297235488892, + "learning_rate": 2.4101855507303594e-06, + "loss": 0.441, + "step": 1313 + }, + { + "epoch": 0.518752467429925, + "grad_norm": 0.6915303468704224, + "learning_rate": 2.4082116067903673e-06, + "loss": 0.4947, + "step": 1314 + }, + { + "epoch": 0.5191472562179235, + "grad_norm": 0.6358901262283325, + "learning_rate": 2.4062376628503753e-06, + "loss": 0.4764, + "step": 1315 + }, + { + "epoch": 0.5195420450059218, + "grad_norm": 0.7561113834381104, + "learning_rate": 2.4042637189103833e-06, + "loss": 0.51, + "step": 1316 + }, + { + "epoch": 0.5199368337939203, + "grad_norm": 0.7563956379890442, + "learning_rate": 2.4022897749703913e-06, + "loss": 0.5003, + "step": 1317 + }, + { + "epoch": 0.5203316225819187, + "grad_norm": 0.6693956851959229, + "learning_rate": 2.400315831030399e-06, + "loss": 0.4264, + "step": 1318 + }, + { + "epoch": 0.520726411369917, + "grad_norm": 0.6551816463470459, + "learning_rate": 2.3983418870904068e-06, + "loss": 0.4688, + "step": 1319 + }, + { + "epoch": 0.5211212001579155, + "grad_norm": 0.7036985158920288, + "learning_rate": 2.3963679431504147e-06, + "loss": 0.5232, + "step": 1320 + }, + { + "epoch": 0.5215159889459139, + "grad_norm": 0.8735780119895935, + "learning_rate": 2.3943939992104227e-06, + "loss": 0.4722, + "step": 1321 + }, + { + "epoch": 0.5219107777339124, + "grad_norm": 0.6943807601928711, + "learning_rate": 2.3924200552704303e-06, + "loss": 0.4749, + "step": 1322 + }, + { + "epoch": 0.5223055665219107, + "grad_norm": 0.7820455431938171, + "learning_rate": 2.3904461113304382e-06, + "loss": 0.4677, + "step": 1323 + }, + { + "epoch": 0.5227003553099092, + "grad_norm": 0.5857419371604919, + "learning_rate": 2.3884721673904462e-06, + "loss": 0.4518, + "step": 1324 + }, + { + "epoch": 0.5230951440979076, + "grad_norm": 1.2794867753982544, + "learning_rate": 2.386498223450454e-06, + "loss": 0.548, + "step": 1325 + }, + { + "epoch": 0.5234899328859061, + "grad_norm": 0.5951289534568787, + "learning_rate": 2.384524279510462e-06, + "loss": 0.4406, + "step": 1326 + }, + { + "epoch": 0.5238847216739044, + "grad_norm": 0.731460452079773, + "learning_rate": 2.3825503355704697e-06, + "loss": 0.4409, + "step": 1327 + }, + { + "epoch": 0.5242795104619029, + "grad_norm": 0.6471565961837769, + "learning_rate": 2.3805763916304777e-06, + "loss": 0.4935, + "step": 1328 + }, + { + "epoch": 0.5246742992499013, + "grad_norm": 0.5843072533607483, + "learning_rate": 2.3786024476904857e-06, + "loss": 0.4357, + "step": 1329 + }, + { + "epoch": 0.5250690880378998, + "grad_norm": 0.7256986498832703, + "learning_rate": 2.3766285037504936e-06, + "loss": 0.4423, + "step": 1330 + }, + { + "epoch": 0.5254638768258981, + "grad_norm": 0.6465495228767395, + "learning_rate": 2.3746545598105016e-06, + "loss": 0.4808, + "step": 1331 + }, + { + "epoch": 0.5258586656138966, + "grad_norm": 0.6091707944869995, + "learning_rate": 2.3726806158705096e-06, + "loss": 0.4784, + "step": 1332 + }, + { + "epoch": 0.526253454401895, + "grad_norm": 0.9138530492782593, + "learning_rate": 2.3707066719305175e-06, + "loss": 0.5561, + "step": 1333 + }, + { + "epoch": 0.5266482431898935, + "grad_norm": 0.6253806352615356, + "learning_rate": 2.3687327279905255e-06, + "loss": 0.4911, + "step": 1334 + }, + { + "epoch": 0.5270430319778918, + "grad_norm": 0.6518816947937012, + "learning_rate": 2.366758784050533e-06, + "loss": 0.4936, + "step": 1335 + }, + { + "epoch": 0.5274378207658903, + "grad_norm": 0.8087906837463379, + "learning_rate": 2.364784840110541e-06, + "loss": 0.4648, + "step": 1336 + }, + { + "epoch": 0.5278326095538887, + "grad_norm": 0.680498480796814, + "learning_rate": 2.362810896170549e-06, + "loss": 0.4835, + "step": 1337 + }, + { + "epoch": 0.5282273983418871, + "grad_norm": 0.6267467141151428, + "learning_rate": 2.360836952230557e-06, + "loss": 0.5756, + "step": 1338 + }, + { + "epoch": 0.5286221871298855, + "grad_norm": 0.7210745215415955, + "learning_rate": 2.358863008290565e-06, + "loss": 0.4754, + "step": 1339 + }, + { + "epoch": 0.5290169759178839, + "grad_norm": 0.5626928806304932, + "learning_rate": 2.3568890643505725e-06, + "loss": 0.4865, + "step": 1340 + }, + { + "epoch": 0.5294117647058824, + "grad_norm": 0.5233215093612671, + "learning_rate": 2.3549151204105805e-06, + "loss": 0.4278, + "step": 1341 + }, + { + "epoch": 0.5298065534938807, + "grad_norm": 0.6969610452651978, + "learning_rate": 2.3529411764705885e-06, + "loss": 0.4659, + "step": 1342 + }, + { + "epoch": 0.5302013422818792, + "grad_norm": 0.6888238787651062, + "learning_rate": 2.3509672325305964e-06, + "loss": 0.5068, + "step": 1343 + }, + { + "epoch": 0.5305961310698776, + "grad_norm": 0.5448741912841797, + "learning_rate": 2.348993288590604e-06, + "loss": 0.4675, + "step": 1344 + }, + { + "epoch": 0.530990919857876, + "grad_norm": 0.6621598601341248, + "learning_rate": 2.347019344650612e-06, + "loss": 0.4369, + "step": 1345 + }, + { + "epoch": 0.5313857086458744, + "grad_norm": 0.580363392829895, + "learning_rate": 2.34504540071062e-06, + "loss": 0.4312, + "step": 1346 + }, + { + "epoch": 0.5317804974338729, + "grad_norm": 0.7488478422164917, + "learning_rate": 2.343071456770628e-06, + "loss": 0.5503, + "step": 1347 + }, + { + "epoch": 0.5321752862218713, + "grad_norm": 0.6537725329399109, + "learning_rate": 2.341097512830636e-06, + "loss": 0.4524, + "step": 1348 + }, + { + "epoch": 0.5325700750098697, + "grad_norm": 0.6831560134887695, + "learning_rate": 2.3391235688906434e-06, + "loss": 0.4977, + "step": 1349 + }, + { + "epoch": 0.5329648637978681, + "grad_norm": 0.6307898163795471, + "learning_rate": 2.337149624950652e-06, + "loss": 0.4152, + "step": 1350 + }, + { + "epoch": 0.5333596525858666, + "grad_norm": 0.6503427624702454, + "learning_rate": 2.3351756810106598e-06, + "loss": 0.4449, + "step": 1351 + }, + { + "epoch": 0.533754441373865, + "grad_norm": 0.6729501485824585, + "learning_rate": 2.3332017370706673e-06, + "loss": 0.4943, + "step": 1352 + }, + { + "epoch": 0.5341492301618634, + "grad_norm": 0.8542284965515137, + "learning_rate": 2.3312277931306753e-06, + "loss": 0.5162, + "step": 1353 + }, + { + "epoch": 0.5345440189498618, + "grad_norm": 0.5526564121246338, + "learning_rate": 2.3292538491906833e-06, + "loss": 0.4061, + "step": 1354 + }, + { + "epoch": 0.5349388077378603, + "grad_norm": 0.5935459733009338, + "learning_rate": 2.3272799052506913e-06, + "loss": 0.4702, + "step": 1355 + }, + { + "epoch": 0.5353335965258587, + "grad_norm": 0.6571754813194275, + "learning_rate": 2.3253059613106992e-06, + "loss": 0.4292, + "step": 1356 + }, + { + "epoch": 0.5357283853138571, + "grad_norm": 0.6765910387039185, + "learning_rate": 2.3233320173707068e-06, + "loss": 0.4523, + "step": 1357 + }, + { + "epoch": 0.5361231741018555, + "grad_norm": 0.6012439727783203, + "learning_rate": 2.3213580734307147e-06, + "loss": 0.4234, + "step": 1358 + }, + { + "epoch": 0.536517962889854, + "grad_norm": 0.649639904499054, + "learning_rate": 2.3193841294907227e-06, + "loss": 0.4839, + "step": 1359 + }, + { + "epoch": 0.5369127516778524, + "grad_norm": 0.6574804782867432, + "learning_rate": 2.3174101855507307e-06, + "loss": 0.4958, + "step": 1360 + }, + { + "epoch": 0.5373075404658507, + "grad_norm": 0.6182993054389954, + "learning_rate": 2.3154362416107382e-06, + "loss": 0.4424, + "step": 1361 + }, + { + "epoch": 0.5377023292538492, + "grad_norm": 0.8114645481109619, + "learning_rate": 2.3134622976707462e-06, + "loss": 0.4824, + "step": 1362 + }, + { + "epoch": 0.5380971180418476, + "grad_norm": 0.7194530963897705, + "learning_rate": 2.311488353730754e-06, + "loss": 0.4913, + "step": 1363 + }, + { + "epoch": 0.538491906829846, + "grad_norm": 0.6644229888916016, + "learning_rate": 2.309514409790762e-06, + "loss": 0.4651, + "step": 1364 + }, + { + "epoch": 0.5388866956178444, + "grad_norm": 0.613600492477417, + "learning_rate": 2.30754046585077e-06, + "loss": 0.48, + "step": 1365 + }, + { + "epoch": 0.5392814844058429, + "grad_norm": 0.6224933862686157, + "learning_rate": 2.3055665219107777e-06, + "loss": 0.4552, + "step": 1366 + }, + { + "epoch": 0.5396762731938413, + "grad_norm": 0.6248208284378052, + "learning_rate": 2.3035925779707857e-06, + "loss": 0.4306, + "step": 1367 + }, + { + "epoch": 0.5400710619818397, + "grad_norm": 0.7877339720726013, + "learning_rate": 2.3016186340307936e-06, + "loss": 0.5475, + "step": 1368 + }, + { + "epoch": 0.5404658507698381, + "grad_norm": 0.6449650526046753, + "learning_rate": 2.2996446900908016e-06, + "loss": 0.5114, + "step": 1369 + }, + { + "epoch": 0.5408606395578366, + "grad_norm": 0.7176505923271179, + "learning_rate": 2.2976707461508096e-06, + "loss": 0.5898, + "step": 1370 + }, + { + "epoch": 0.541255428345835, + "grad_norm": 0.6905590295791626, + "learning_rate": 2.2956968022108175e-06, + "loss": 0.4844, + "step": 1371 + }, + { + "epoch": 0.5416502171338334, + "grad_norm": 0.6316943764686584, + "learning_rate": 2.2937228582708255e-06, + "loss": 0.4981, + "step": 1372 + }, + { + "epoch": 0.5420450059218318, + "grad_norm": 0.7197287678718567, + "learning_rate": 2.2917489143308335e-06, + "loss": 0.5154, + "step": 1373 + }, + { + "epoch": 0.5424397947098303, + "grad_norm": 0.7219273447990417, + "learning_rate": 2.289774970390841e-06, + "loss": 0.4654, + "step": 1374 + }, + { + "epoch": 0.5428345834978286, + "grad_norm": 0.5281549096107483, + "learning_rate": 2.287801026450849e-06, + "loss": 0.4266, + "step": 1375 + }, + { + "epoch": 0.5432293722858271, + "grad_norm": 0.6416587829589844, + "learning_rate": 2.285827082510857e-06, + "loss": 0.4628, + "step": 1376 + }, + { + "epoch": 0.5436241610738255, + "grad_norm": 0.7466753721237183, + "learning_rate": 2.283853138570865e-06, + "loss": 0.4335, + "step": 1377 + }, + { + "epoch": 0.544018949861824, + "grad_norm": 0.8731406927108765, + "learning_rate": 2.2818791946308725e-06, + "loss": 0.561, + "step": 1378 + }, + { + "epoch": 0.5444137386498223, + "grad_norm": 0.7123034596443176, + "learning_rate": 2.2799052506908805e-06, + "loss": 0.524, + "step": 1379 + }, + { + "epoch": 0.5448085274378207, + "grad_norm": 0.6187617778778076, + "learning_rate": 2.2779313067508885e-06, + "loss": 0.461, + "step": 1380 + }, + { + "epoch": 0.5452033162258192, + "grad_norm": 0.7744300961494446, + "learning_rate": 2.2759573628108964e-06, + "loss": 0.4835, + "step": 1381 + }, + { + "epoch": 0.5455981050138176, + "grad_norm": 0.7223597764968872, + "learning_rate": 2.2739834188709044e-06, + "loss": 0.501, + "step": 1382 + }, + { + "epoch": 0.545992893801816, + "grad_norm": 0.5838474035263062, + "learning_rate": 2.272009474930912e-06, + "loss": 0.4566, + "step": 1383 + }, + { + "epoch": 0.5463876825898144, + "grad_norm": 0.9613719582557678, + "learning_rate": 2.27003553099092e-06, + "loss": 0.4967, + "step": 1384 + }, + { + "epoch": 0.5467824713778129, + "grad_norm": 0.674801230430603, + "learning_rate": 2.268061587050928e-06, + "loss": 0.4538, + "step": 1385 + }, + { + "epoch": 0.5471772601658113, + "grad_norm": 0.5613301992416382, + "learning_rate": 2.266087643110936e-06, + "loss": 0.396, + "step": 1386 + }, + { + "epoch": 0.5475720489538097, + "grad_norm": 0.6492034196853638, + "learning_rate": 2.264113699170944e-06, + "loss": 0.4647, + "step": 1387 + }, + { + "epoch": 0.5479668377418081, + "grad_norm": 0.6604942679405212, + "learning_rate": 2.2621397552309514e-06, + "loss": 0.4653, + "step": 1388 + }, + { + "epoch": 0.5483616265298066, + "grad_norm": 0.7377282977104187, + "learning_rate": 2.2601658112909594e-06, + "loss": 0.4887, + "step": 1389 + }, + { + "epoch": 0.548756415317805, + "grad_norm": 0.7234883308410645, + "learning_rate": 2.2581918673509673e-06, + "loss": 0.5135, + "step": 1390 + }, + { + "epoch": 0.5491512041058034, + "grad_norm": 0.7507346272468567, + "learning_rate": 2.2562179234109753e-06, + "loss": 0.5024, + "step": 1391 + }, + { + "epoch": 0.5495459928938018, + "grad_norm": 0.8381463289260864, + "learning_rate": 2.2542439794709833e-06, + "loss": 0.4491, + "step": 1392 + }, + { + "epoch": 0.5499407816818003, + "grad_norm": 0.7049989700317383, + "learning_rate": 2.2522700355309912e-06, + "loss": 0.5077, + "step": 1393 + }, + { + "epoch": 0.5503355704697986, + "grad_norm": 0.5909746885299683, + "learning_rate": 2.2502960915909992e-06, + "loss": 0.4698, + "step": 1394 + }, + { + "epoch": 0.5507303592577971, + "grad_norm": 0.6789581775665283, + "learning_rate": 2.2483221476510068e-06, + "loss": 0.4218, + "step": 1395 + }, + { + "epoch": 0.5511251480457955, + "grad_norm": 0.7076061964035034, + "learning_rate": 2.2463482037110147e-06, + "loss": 0.4958, + "step": 1396 + }, + { + "epoch": 0.551519936833794, + "grad_norm": 0.7473710775375366, + "learning_rate": 2.2443742597710227e-06, + "loss": 0.5003, + "step": 1397 + }, + { + "epoch": 0.5519147256217923, + "grad_norm": 0.6044131517410278, + "learning_rate": 2.2424003158310307e-06, + "loss": 0.4654, + "step": 1398 + }, + { + "epoch": 0.5523095144097908, + "grad_norm": 0.6677661538124084, + "learning_rate": 2.2404263718910387e-06, + "loss": 0.4854, + "step": 1399 + }, + { + "epoch": 0.5527043031977892, + "grad_norm": 0.5960425138473511, + "learning_rate": 2.238452427951046e-06, + "loss": 0.4093, + "step": 1400 + }, + { + "epoch": 0.5530990919857875, + "grad_norm": 0.7055006623268127, + "learning_rate": 2.236478484011054e-06, + "loss": 0.4694, + "step": 1401 + }, + { + "epoch": 0.553493880773786, + "grad_norm": 0.6644160151481628, + "learning_rate": 2.234504540071062e-06, + "loss": 0.5143, + "step": 1402 + }, + { + "epoch": 0.5538886695617844, + "grad_norm": 0.5840364098548889, + "learning_rate": 2.23253059613107e-06, + "loss": 0.477, + "step": 1403 + }, + { + "epoch": 0.5542834583497829, + "grad_norm": 0.5803251266479492, + "learning_rate": 2.230556652191078e-06, + "loss": 0.438, + "step": 1404 + }, + { + "epoch": 0.5546782471377812, + "grad_norm": 0.7278510332107544, + "learning_rate": 2.2285827082510857e-06, + "loss": 0.4882, + "step": 1405 + }, + { + "epoch": 0.5550730359257797, + "grad_norm": 0.6494545936584473, + "learning_rate": 2.2266087643110936e-06, + "loss": 0.4559, + "step": 1406 + }, + { + "epoch": 0.5554678247137781, + "grad_norm": 0.6028538346290588, + "learning_rate": 2.2246348203711016e-06, + "loss": 0.4193, + "step": 1407 + }, + { + "epoch": 0.5558626135017766, + "grad_norm": 0.6665513515472412, + "learning_rate": 2.2226608764311096e-06, + "loss": 0.5361, + "step": 1408 + }, + { + "epoch": 0.5562574022897749, + "grad_norm": 0.646345317363739, + "learning_rate": 2.2206869324911175e-06, + "loss": 0.4608, + "step": 1409 + }, + { + "epoch": 0.5566521910777734, + "grad_norm": 0.7052869200706482, + "learning_rate": 2.218712988551125e-06, + "loss": 0.5138, + "step": 1410 + }, + { + "epoch": 0.5570469798657718, + "grad_norm": 0.6944994330406189, + "learning_rate": 2.216739044611133e-06, + "loss": 0.4801, + "step": 1411 + }, + { + "epoch": 0.5574417686537703, + "grad_norm": 0.5078470706939697, + "learning_rate": 2.2147651006711415e-06, + "loss": 0.4194, + "step": 1412 + }, + { + "epoch": 0.5578365574417686, + "grad_norm": 0.6358610391616821, + "learning_rate": 2.212791156731149e-06, + "loss": 0.463, + "step": 1413 + }, + { + "epoch": 0.5582313462297671, + "grad_norm": 0.7041791081428528, + "learning_rate": 2.210817212791157e-06, + "loss": 0.48, + "step": 1414 + }, + { + "epoch": 0.5586261350177655, + "grad_norm": 0.7652315497398376, + "learning_rate": 2.208843268851165e-06, + "loss": 0.5245, + "step": 1415 + }, + { + "epoch": 0.559020923805764, + "grad_norm": 0.6701385974884033, + "learning_rate": 2.206869324911173e-06, + "loss": 0.4805, + "step": 1416 + }, + { + "epoch": 0.5594157125937623, + "grad_norm": 0.6032361388206482, + "learning_rate": 2.2048953809711805e-06, + "loss": 0.4613, + "step": 1417 + }, + { + "epoch": 0.5598105013817608, + "grad_norm": 0.6956825852394104, + "learning_rate": 2.2029214370311884e-06, + "loss": 0.4942, + "step": 1418 + }, + { + "epoch": 0.5602052901697592, + "grad_norm": 0.703220009803772, + "learning_rate": 2.2009474930911964e-06, + "loss": 0.5265, + "step": 1419 + }, + { + "epoch": 0.5606000789577577, + "grad_norm": 0.8720895051956177, + "learning_rate": 2.1989735491512044e-06, + "loss": 0.487, + "step": 1420 + }, + { + "epoch": 0.560994867745756, + "grad_norm": 0.6093984246253967, + "learning_rate": 2.1969996052112124e-06, + "loss": 0.4491, + "step": 1421 + }, + { + "epoch": 0.5613896565337544, + "grad_norm": 0.6517363786697388, + "learning_rate": 2.19502566127122e-06, + "loss": 0.5077, + "step": 1422 + }, + { + "epoch": 0.5617844453217529, + "grad_norm": 0.5910210609436035, + "learning_rate": 2.193051717331228e-06, + "loss": 0.4876, + "step": 1423 + }, + { + "epoch": 0.5621792341097512, + "grad_norm": 0.6051006317138672, + "learning_rate": 2.191077773391236e-06, + "loss": 0.4193, + "step": 1424 + }, + { + "epoch": 0.5625740228977497, + "grad_norm": 0.5142551064491272, + "learning_rate": 2.189103829451244e-06, + "loss": 0.4547, + "step": 1425 + }, + { + "epoch": 0.5629688116857481, + "grad_norm": 0.8222415447235107, + "learning_rate": 2.187129885511252e-06, + "loss": 0.5489, + "step": 1426 + }, + { + "epoch": 0.5633636004737466, + "grad_norm": 0.625841498374939, + "learning_rate": 2.1851559415712594e-06, + "loss": 0.4367, + "step": 1427 + }, + { + "epoch": 0.5637583892617449, + "grad_norm": 0.6198761463165283, + "learning_rate": 2.1831819976312673e-06, + "loss": 0.4294, + "step": 1428 + }, + { + "epoch": 0.5641531780497434, + "grad_norm": 0.5536952018737793, + "learning_rate": 2.1812080536912753e-06, + "loss": 0.4454, + "step": 1429 + }, + { + "epoch": 0.5645479668377418, + "grad_norm": 0.576875627040863, + "learning_rate": 2.1792341097512833e-06, + "loss": 0.4977, + "step": 1430 + }, + { + "epoch": 0.5649427556257403, + "grad_norm": 0.5847018361091614, + "learning_rate": 2.177260165811291e-06, + "loss": 0.4485, + "step": 1431 + }, + { + "epoch": 0.5653375444137386, + "grad_norm": 0.672877311706543, + "learning_rate": 2.175286221871299e-06, + "loss": 0.4677, + "step": 1432 + }, + { + "epoch": 0.5657323332017371, + "grad_norm": 0.6462711095809937, + "learning_rate": 2.173312277931307e-06, + "loss": 0.4114, + "step": 1433 + }, + { + "epoch": 0.5661271219897355, + "grad_norm": 0.8668105006217957, + "learning_rate": 2.1713383339913147e-06, + "loss": 0.4854, + "step": 1434 + }, + { + "epoch": 0.566521910777734, + "grad_norm": 0.6538423895835876, + "learning_rate": 2.1693643900513227e-06, + "loss": 0.4533, + "step": 1435 + }, + { + "epoch": 0.5669166995657323, + "grad_norm": 0.6069440841674805, + "learning_rate": 2.1673904461113307e-06, + "loss": 0.4384, + "step": 1436 + }, + { + "epoch": 0.5673114883537308, + "grad_norm": 0.5805003643035889, + "learning_rate": 2.1654165021713387e-06, + "loss": 0.457, + "step": 1437 + }, + { + "epoch": 0.5677062771417292, + "grad_norm": 0.5802630186080933, + "learning_rate": 2.1634425582313466e-06, + "loss": 0.4478, + "step": 1438 + }, + { + "epoch": 0.5681010659297276, + "grad_norm": 0.615061342716217, + "learning_rate": 2.161468614291354e-06, + "loss": 0.4578, + "step": 1439 + }, + { + "epoch": 0.568495854717726, + "grad_norm": 0.630202054977417, + "learning_rate": 2.159494670351362e-06, + "loss": 0.487, + "step": 1440 + }, + { + "epoch": 0.5688906435057245, + "grad_norm": 0.6842738389968872, + "learning_rate": 2.15752072641137e-06, + "loss": 0.4588, + "step": 1441 + }, + { + "epoch": 0.5692854322937229, + "grad_norm": 0.6412065625190735, + "learning_rate": 2.155546782471378e-06, + "loss": 0.4495, + "step": 1442 + }, + { + "epoch": 0.5696802210817212, + "grad_norm": 0.6066116690635681, + "learning_rate": 2.153572838531386e-06, + "loss": 0.4879, + "step": 1443 + }, + { + "epoch": 0.5700750098697197, + "grad_norm": 0.7762623429298401, + "learning_rate": 2.1515988945913936e-06, + "loss": 0.4942, + "step": 1444 + }, + { + "epoch": 0.5704697986577181, + "grad_norm": 0.6481943726539612, + "learning_rate": 2.1496249506514016e-06, + "loss": 0.5098, + "step": 1445 + }, + { + "epoch": 0.5708645874457166, + "grad_norm": 0.6541522741317749, + "learning_rate": 2.1476510067114096e-06, + "loss": 0.4957, + "step": 1446 + }, + { + "epoch": 0.5712593762337149, + "grad_norm": 0.5888257026672363, + "learning_rate": 2.1456770627714175e-06, + "loss": 0.4138, + "step": 1447 + }, + { + "epoch": 0.5716541650217134, + "grad_norm": 0.5695787668228149, + "learning_rate": 2.143703118831425e-06, + "loss": 0.4933, + "step": 1448 + }, + { + "epoch": 0.5720489538097118, + "grad_norm": 0.6897147297859192, + "learning_rate": 2.141729174891433e-06, + "loss": 0.4989, + "step": 1449 + }, + { + "epoch": 0.5724437425977102, + "grad_norm": 0.6192546486854553, + "learning_rate": 2.139755230951441e-06, + "loss": 0.462, + "step": 1450 + }, + { + "epoch": 0.5728385313857086, + "grad_norm": 0.9033993482589722, + "learning_rate": 2.137781287011449e-06, + "loss": 0.5086, + "step": 1451 + }, + { + "epoch": 0.5732333201737071, + "grad_norm": 0.6749528646469116, + "learning_rate": 2.135807343071457e-06, + "loss": 0.4744, + "step": 1452 + }, + { + "epoch": 0.5736281089617055, + "grad_norm": 0.7360104322433472, + "learning_rate": 2.133833399131465e-06, + "loss": 0.521, + "step": 1453 + }, + { + "epoch": 0.5740228977497039, + "grad_norm": 0.67600017786026, + "learning_rate": 2.131859455191473e-06, + "loss": 0.5134, + "step": 1454 + }, + { + "epoch": 0.5744176865377023, + "grad_norm": 0.613521933555603, + "learning_rate": 2.129885511251481e-06, + "loss": 0.4949, + "step": 1455 + }, + { + "epoch": 0.5748124753257008, + "grad_norm": 0.8131657838821411, + "learning_rate": 2.1279115673114884e-06, + "loss": 0.4299, + "step": 1456 + }, + { + "epoch": 0.5752072641136992, + "grad_norm": 0.7305359244346619, + "learning_rate": 2.1259376233714964e-06, + "loss": 0.4364, + "step": 1457 + }, + { + "epoch": 0.5756020529016976, + "grad_norm": 0.5635665655136108, + "learning_rate": 2.1239636794315044e-06, + "loss": 0.487, + "step": 1458 + }, + { + "epoch": 0.575996841689696, + "grad_norm": 0.8110566735267639, + "learning_rate": 2.1219897354915124e-06, + "loss": 0.4578, + "step": 1459 + }, + { + "epoch": 0.5763916304776945, + "grad_norm": 0.7606463432312012, + "learning_rate": 2.1200157915515203e-06, + "loss": 0.5043, + "step": 1460 + }, + { + "epoch": 0.5767864192656929, + "grad_norm": 0.5635700225830078, + "learning_rate": 2.118041847611528e-06, + "loss": 0.4524, + "step": 1461 + }, + { + "epoch": 0.5771812080536913, + "grad_norm": 0.7359962463378906, + "learning_rate": 2.116067903671536e-06, + "loss": 0.4669, + "step": 1462 + }, + { + "epoch": 0.5775759968416897, + "grad_norm": 0.6307514309883118, + "learning_rate": 2.114093959731544e-06, + "loss": 0.4992, + "step": 1463 + }, + { + "epoch": 0.5779707856296881, + "grad_norm": 0.5641564130783081, + "learning_rate": 2.112120015791552e-06, + "loss": 0.471, + "step": 1464 + }, + { + "epoch": 0.5783655744176865, + "grad_norm": 0.5891743898391724, + "learning_rate": 2.1101460718515594e-06, + "loss": 0.4525, + "step": 1465 + }, + { + "epoch": 0.5787603632056849, + "grad_norm": 0.7127856016159058, + "learning_rate": 2.1081721279115673e-06, + "loss": 0.4721, + "step": 1466 + }, + { + "epoch": 0.5791551519936834, + "grad_norm": 0.7866455912590027, + "learning_rate": 2.1061981839715753e-06, + "loss": 0.5249, + "step": 1467 + }, + { + "epoch": 0.5795499407816818, + "grad_norm": 0.5083703994750977, + "learning_rate": 2.1042242400315833e-06, + "loss": 0.4253, + "step": 1468 + }, + { + "epoch": 0.5799447295696802, + "grad_norm": 0.7203965783119202, + "learning_rate": 2.1022502960915912e-06, + "loss": 0.565, + "step": 1469 + }, + { + "epoch": 0.5803395183576786, + "grad_norm": 0.8425210118293762, + "learning_rate": 2.100276352151599e-06, + "loss": 0.4946, + "step": 1470 + }, + { + "epoch": 0.5807343071456771, + "grad_norm": 0.6707839965820312, + "learning_rate": 2.0983024082116068e-06, + "loss": 0.5388, + "step": 1471 + }, + { + "epoch": 0.5811290959336755, + "grad_norm": 0.5026468634605408, + "learning_rate": 2.0963284642716147e-06, + "loss": 0.4808, + "step": 1472 + }, + { + "epoch": 0.5815238847216739, + "grad_norm": 0.5368514060974121, + "learning_rate": 2.0943545203316227e-06, + "loss": 0.4189, + "step": 1473 + }, + { + "epoch": 0.5819186735096723, + "grad_norm": 0.6703753471374512, + "learning_rate": 2.0923805763916307e-06, + "loss": 0.5002, + "step": 1474 + }, + { + "epoch": 0.5823134622976708, + "grad_norm": 0.8061275482177734, + "learning_rate": 2.0904066324516387e-06, + "loss": 0.4938, + "step": 1475 + }, + { + "epoch": 0.5827082510856691, + "grad_norm": 0.6961990594863892, + "learning_rate": 2.0884326885116466e-06, + "loss": 0.4478, + "step": 1476 + }, + { + "epoch": 0.5831030398736676, + "grad_norm": 0.8209490776062012, + "learning_rate": 2.0864587445716546e-06, + "loss": 0.5172, + "step": 1477 + }, + { + "epoch": 0.583497828661666, + "grad_norm": 0.9045576453208923, + "learning_rate": 2.084484800631662e-06, + "loss": 0.6324, + "step": 1478 + }, + { + "epoch": 0.5838926174496645, + "grad_norm": 0.5016364455223083, + "learning_rate": 2.08251085669167e-06, + "loss": 0.447, + "step": 1479 + }, + { + "epoch": 0.5842874062376628, + "grad_norm": 0.6055883169174194, + "learning_rate": 2.080536912751678e-06, + "loss": 0.4493, + "step": 1480 + }, + { + "epoch": 0.5846821950256613, + "grad_norm": 0.5413548946380615, + "learning_rate": 2.078562968811686e-06, + "loss": 0.479, + "step": 1481 + }, + { + "epoch": 0.5850769838136597, + "grad_norm": 0.6906740665435791, + "learning_rate": 2.076589024871694e-06, + "loss": 0.5032, + "step": 1482 + }, + { + "epoch": 0.5854717726016581, + "grad_norm": 0.674595296382904, + "learning_rate": 2.0746150809317016e-06, + "loss": 0.4826, + "step": 1483 + }, + { + "epoch": 0.5858665613896565, + "grad_norm": 0.72857266664505, + "learning_rate": 2.0726411369917096e-06, + "loss": 0.4738, + "step": 1484 + }, + { + "epoch": 0.5862613501776549, + "grad_norm": 0.7523030638694763, + "learning_rate": 2.0706671930517175e-06, + "loss": 0.4426, + "step": 1485 + }, + { + "epoch": 0.5866561389656534, + "grad_norm": 0.6899458765983582, + "learning_rate": 2.0686932491117255e-06, + "loss": 0.4799, + "step": 1486 + }, + { + "epoch": 0.5870509277536518, + "grad_norm": 0.7453503012657166, + "learning_rate": 2.066719305171733e-06, + "loss": 0.5089, + "step": 1487 + }, + { + "epoch": 0.5874457165416502, + "grad_norm": 0.569122850894928, + "learning_rate": 2.064745361231741e-06, + "loss": 0.4766, + "step": 1488 + }, + { + "epoch": 0.5878405053296486, + "grad_norm": 0.8043856620788574, + "learning_rate": 2.062771417291749e-06, + "loss": 0.5145, + "step": 1489 + }, + { + "epoch": 0.5882352941176471, + "grad_norm": 0.677029013633728, + "learning_rate": 2.060797473351757e-06, + "loss": 0.4494, + "step": 1490 + }, + { + "epoch": 0.5886300829056454, + "grad_norm": 0.7760908007621765, + "learning_rate": 2.058823529411765e-06, + "loss": 0.4908, + "step": 1491 + }, + { + "epoch": 0.5890248716936439, + "grad_norm": 0.574717104434967, + "learning_rate": 2.0568495854717725e-06, + "loss": 0.3855, + "step": 1492 + }, + { + "epoch": 0.5894196604816423, + "grad_norm": 0.510109543800354, + "learning_rate": 2.0548756415317805e-06, + "loss": 0.4382, + "step": 1493 + }, + { + "epoch": 0.5898144492696408, + "grad_norm": 0.6806402206420898, + "learning_rate": 2.0529016975917884e-06, + "loss": 0.463, + "step": 1494 + }, + { + "epoch": 0.5902092380576391, + "grad_norm": 0.5986588001251221, + "learning_rate": 2.0509277536517964e-06, + "loss": 0.4447, + "step": 1495 + }, + { + "epoch": 0.5906040268456376, + "grad_norm": 0.697746753692627, + "learning_rate": 2.0489538097118044e-06, + "loss": 0.5981, + "step": 1496 + }, + { + "epoch": 0.590998815633636, + "grad_norm": 0.638056755065918, + "learning_rate": 2.0469798657718124e-06, + "loss": 0.4758, + "step": 1497 + }, + { + "epoch": 0.5913936044216345, + "grad_norm": 0.5336479544639587, + "learning_rate": 2.0450059218318203e-06, + "loss": 0.4285, + "step": 1498 + }, + { + "epoch": 0.5917883932096328, + "grad_norm": 0.9323879480361938, + "learning_rate": 2.0430319778918283e-06, + "loss": 0.4629, + "step": 1499 + }, + { + "epoch": 0.5921831819976313, + "grad_norm": 0.676632821559906, + "learning_rate": 2.041058033951836e-06, + "loss": 0.4557, + "step": 1500 + }, + { + "epoch": 0.5925779707856297, + "grad_norm": 0.8042216897010803, + "learning_rate": 2.039084090011844e-06, + "loss": 0.5051, + "step": 1501 + }, + { + "epoch": 0.5929727595736282, + "grad_norm": 0.6308175921440125, + "learning_rate": 2.037110146071852e-06, + "loss": 0.4818, + "step": 1502 + }, + { + "epoch": 0.5933675483616265, + "grad_norm": 0.602242112159729, + "learning_rate": 2.0351362021318598e-06, + "loss": 0.4625, + "step": 1503 + }, + { + "epoch": 0.5937623371496249, + "grad_norm": 0.6192105412483215, + "learning_rate": 2.0331622581918673e-06, + "loss": 0.5028, + "step": 1504 + }, + { + "epoch": 0.5941571259376234, + "grad_norm": 0.6068954467773438, + "learning_rate": 2.0311883142518753e-06, + "loss": 0.4546, + "step": 1505 + }, + { + "epoch": 0.5945519147256217, + "grad_norm": 0.6759416460990906, + "learning_rate": 2.0292143703118833e-06, + "loss": 0.4744, + "step": 1506 + }, + { + "epoch": 0.5949467035136202, + "grad_norm": 0.8219453692436218, + "learning_rate": 2.0272404263718912e-06, + "loss": 0.5746, + "step": 1507 + }, + { + "epoch": 0.5953414923016186, + "grad_norm": 0.6709892153739929, + "learning_rate": 2.0252664824318992e-06, + "loss": 0.4413, + "step": 1508 + }, + { + "epoch": 0.5957362810896171, + "grad_norm": 0.5857495069503784, + "learning_rate": 2.0232925384919068e-06, + "loss": 0.5504, + "step": 1509 + }, + { + "epoch": 0.5961310698776154, + "grad_norm": 0.6748395562171936, + "learning_rate": 2.0213185945519147e-06, + "loss": 0.443, + "step": 1510 + }, + { + "epoch": 0.5965258586656139, + "grad_norm": 0.7706774473190308, + "learning_rate": 2.0193446506119227e-06, + "loss": 0.539, + "step": 1511 + }, + { + "epoch": 0.5969206474536123, + "grad_norm": 0.6231324076652527, + "learning_rate": 2.0173707066719307e-06, + "loss": 0.4536, + "step": 1512 + }, + { + "epoch": 0.5973154362416108, + "grad_norm": 0.8571415543556213, + "learning_rate": 2.0153967627319387e-06, + "loss": 0.4618, + "step": 1513 + }, + { + "epoch": 0.5977102250296091, + "grad_norm": 0.5428652763366699, + "learning_rate": 2.013422818791946e-06, + "loss": 0.431, + "step": 1514 + }, + { + "epoch": 0.5981050138176076, + "grad_norm": 0.7768872976303101, + "learning_rate": 2.0114488748519546e-06, + "loss": 0.5302, + "step": 1515 + }, + { + "epoch": 0.598499802605606, + "grad_norm": 0.5682486891746521, + "learning_rate": 2.0094749309119626e-06, + "loss": 0.5083, + "step": 1516 + }, + { + "epoch": 0.5988945913936045, + "grad_norm": 0.7093651294708252, + "learning_rate": 2.00750098697197e-06, + "loss": 0.4378, + "step": 1517 + }, + { + "epoch": 0.5992893801816028, + "grad_norm": 0.6711580157279968, + "learning_rate": 2.005527043031978e-06, + "loss": 0.502, + "step": 1518 + }, + { + "epoch": 0.5996841689696013, + "grad_norm": 0.7031580805778503, + "learning_rate": 2.003553099091986e-06, + "loss": 0.5337, + "step": 1519 + }, + { + "epoch": 0.6000789577575997, + "grad_norm": 0.6653319001197815, + "learning_rate": 2.001579155151994e-06, + "loss": 0.4145, + "step": 1520 + }, + { + "epoch": 0.6004737465455982, + "grad_norm": 0.6132694482803345, + "learning_rate": 1.9996052112120016e-06, + "loss": 0.4687, + "step": 1521 + }, + { + "epoch": 0.6008685353335965, + "grad_norm": 0.5806063413619995, + "learning_rate": 1.9976312672720096e-06, + "loss": 0.4744, + "step": 1522 + }, + { + "epoch": 0.601263324121595, + "grad_norm": 0.9165250658988953, + "learning_rate": 1.9956573233320175e-06, + "loss": 0.5153, + "step": 1523 + }, + { + "epoch": 0.6016581129095934, + "grad_norm": 0.6681190729141235, + "learning_rate": 1.9936833793920255e-06, + "loss": 0.4611, + "step": 1524 + }, + { + "epoch": 0.6020529016975917, + "grad_norm": 0.7320753931999207, + "learning_rate": 1.9917094354520335e-06, + "loss": 0.4971, + "step": 1525 + }, + { + "epoch": 0.6024476904855902, + "grad_norm": 0.8078721165657043, + "learning_rate": 1.989735491512041e-06, + "loss": 0.5791, + "step": 1526 + }, + { + "epoch": 0.6028424792735886, + "grad_norm": 0.6209802627563477, + "learning_rate": 1.987761547572049e-06, + "loss": 0.4554, + "step": 1527 + }, + { + "epoch": 0.6032372680615871, + "grad_norm": 0.874638557434082, + "learning_rate": 1.985787603632057e-06, + "loss": 0.5762, + "step": 1528 + }, + { + "epoch": 0.6036320568495854, + "grad_norm": 0.589565098285675, + "learning_rate": 1.983813659692065e-06, + "loss": 0.4417, + "step": 1529 + }, + { + "epoch": 0.6040268456375839, + "grad_norm": 0.5846030116081238, + "learning_rate": 1.981839715752073e-06, + "loss": 0.4382, + "step": 1530 + }, + { + "epoch": 0.6044216344255823, + "grad_norm": 0.8767135739326477, + "learning_rate": 1.9798657718120805e-06, + "loss": 0.5429, + "step": 1531 + }, + { + "epoch": 0.6048164232135808, + "grad_norm": 0.7389394044876099, + "learning_rate": 1.9778918278720884e-06, + "loss": 0.4937, + "step": 1532 + }, + { + "epoch": 0.6052112120015791, + "grad_norm": 0.7385377883911133, + "learning_rate": 1.9759178839320964e-06, + "loss": 0.5222, + "step": 1533 + }, + { + "epoch": 0.6056060007895776, + "grad_norm": 0.5168845653533936, + "learning_rate": 1.9739439399921044e-06, + "loss": 0.457, + "step": 1534 + }, + { + "epoch": 0.606000789577576, + "grad_norm": 0.7070115208625793, + "learning_rate": 1.971969996052112e-06, + "loss": 0.4745, + "step": 1535 + }, + { + "epoch": 0.6063955783655745, + "grad_norm": 1.0185714960098267, + "learning_rate": 1.9699960521121203e-06, + "loss": 0.5804, + "step": 1536 + }, + { + "epoch": 0.6067903671535728, + "grad_norm": 0.6005532145500183, + "learning_rate": 1.9680221081721283e-06, + "loss": 0.4561, + "step": 1537 + }, + { + "epoch": 0.6071851559415713, + "grad_norm": 0.7654423117637634, + "learning_rate": 1.9660481642321363e-06, + "loss": 0.4947, + "step": 1538 + }, + { + "epoch": 0.6075799447295697, + "grad_norm": 0.7747344374656677, + "learning_rate": 1.964074220292144e-06, + "loss": 0.5036, + "step": 1539 + }, + { + "epoch": 0.6079747335175681, + "grad_norm": 0.7367588877677917, + "learning_rate": 1.962100276352152e-06, + "loss": 0.4772, + "step": 1540 + }, + { + "epoch": 0.6083695223055665, + "grad_norm": 0.7458741664886475, + "learning_rate": 1.9601263324121598e-06, + "loss": 0.5673, + "step": 1541 + }, + { + "epoch": 0.608764311093565, + "grad_norm": 0.6431434750556946, + "learning_rate": 1.9581523884721677e-06, + "loss": 0.4479, + "step": 1542 + }, + { + "epoch": 0.6091590998815634, + "grad_norm": 0.7032068967819214, + "learning_rate": 1.9561784445321753e-06, + "loss": 0.4892, + "step": 1543 + }, + { + "epoch": 0.6095538886695618, + "grad_norm": 0.6985384821891785, + "learning_rate": 1.9542045005921833e-06, + "loss": 0.4976, + "step": 1544 + }, + { + "epoch": 0.6099486774575602, + "grad_norm": 0.5854007005691528, + "learning_rate": 1.9522305566521912e-06, + "loss": 0.4255, + "step": 1545 + }, + { + "epoch": 0.6103434662455586, + "grad_norm": 0.6106101274490356, + "learning_rate": 1.9502566127121992e-06, + "loss": 0.4797, + "step": 1546 + }, + { + "epoch": 0.610738255033557, + "grad_norm": 0.7104768753051758, + "learning_rate": 1.948282668772207e-06, + "loss": 0.4985, + "step": 1547 + }, + { + "epoch": 0.6111330438215554, + "grad_norm": 0.8467158079147339, + "learning_rate": 1.9463087248322147e-06, + "loss": 0.5113, + "step": 1548 + }, + { + "epoch": 0.6115278326095539, + "grad_norm": 0.545457661151886, + "learning_rate": 1.9443347808922227e-06, + "loss": 0.4438, + "step": 1549 + }, + { + "epoch": 0.6119226213975523, + "grad_norm": 0.6783082485198975, + "learning_rate": 1.9423608369522307e-06, + "loss": 0.487, + "step": 1550 + }, + { + "epoch": 0.6123174101855507, + "grad_norm": 0.5477342009544373, + "learning_rate": 1.9403868930122387e-06, + "loss": 0.4224, + "step": 1551 + }, + { + "epoch": 0.6127121989735491, + "grad_norm": 0.6797162890434265, + "learning_rate": 1.9384129490722466e-06, + "loss": 0.5407, + "step": 1552 + }, + { + "epoch": 0.6131069877615476, + "grad_norm": 0.7016677260398865, + "learning_rate": 1.936439005132254e-06, + "loss": 0.5156, + "step": 1553 + }, + { + "epoch": 0.613501776549546, + "grad_norm": 0.5881918668746948, + "learning_rate": 1.934465061192262e-06, + "loss": 0.4209, + "step": 1554 + }, + { + "epoch": 0.6138965653375444, + "grad_norm": 0.5980708003044128, + "learning_rate": 1.93249111725227e-06, + "loss": 0.5205, + "step": 1555 + }, + { + "epoch": 0.6142913541255428, + "grad_norm": 0.6934052109718323, + "learning_rate": 1.930517173312278e-06, + "loss": 0.5936, + "step": 1556 + }, + { + "epoch": 0.6146861429135413, + "grad_norm": 0.6816139221191406, + "learning_rate": 1.928543229372286e-06, + "loss": 0.4856, + "step": 1557 + }, + { + "epoch": 0.6150809317015397, + "grad_norm": 0.5376589894294739, + "learning_rate": 1.926569285432294e-06, + "loss": 0.3895, + "step": 1558 + }, + { + "epoch": 0.6154757204895381, + "grad_norm": 0.6327565908432007, + "learning_rate": 1.924595341492302e-06, + "loss": 0.5523, + "step": 1559 + }, + { + "epoch": 0.6158705092775365, + "grad_norm": 0.6143884658813477, + "learning_rate": 1.9226213975523096e-06, + "loss": 0.3954, + "step": 1560 + }, + { + "epoch": 0.616265298065535, + "grad_norm": 0.6106749773025513, + "learning_rate": 1.9206474536123175e-06, + "loss": 0.4455, + "step": 1561 + }, + { + "epoch": 0.6166600868535334, + "grad_norm": 0.6799758076667786, + "learning_rate": 1.9186735096723255e-06, + "loss": 0.4675, + "step": 1562 + }, + { + "epoch": 0.6170548756415318, + "grad_norm": 0.6483184099197388, + "learning_rate": 1.9166995657323335e-06, + "loss": 0.4394, + "step": 1563 + }, + { + "epoch": 0.6174496644295302, + "grad_norm": 0.6058107614517212, + "learning_rate": 1.9147256217923414e-06, + "loss": 0.506, + "step": 1564 + }, + { + "epoch": 0.6178444532175287, + "grad_norm": 0.6543959975242615, + "learning_rate": 1.912751677852349e-06, + "loss": 0.5198, + "step": 1565 + }, + { + "epoch": 0.618239242005527, + "grad_norm": 0.6510801315307617, + "learning_rate": 1.910777733912357e-06, + "loss": 0.4501, + "step": 1566 + }, + { + "epoch": 0.6186340307935254, + "grad_norm": 0.8380513191223145, + "learning_rate": 1.908803789972365e-06, + "loss": 0.4937, + "step": 1567 + }, + { + "epoch": 0.6190288195815239, + "grad_norm": 0.7142260670661926, + "learning_rate": 1.9068298460323727e-06, + "loss": 0.6025, + "step": 1568 + }, + { + "epoch": 0.6194236083695223, + "grad_norm": 0.6376750469207764, + "learning_rate": 1.9048559020923807e-06, + "loss": 0.5617, + "step": 1569 + }, + { + "epoch": 0.6198183971575207, + "grad_norm": 0.7644224166870117, + "learning_rate": 1.9028819581523887e-06, + "loss": 0.5116, + "step": 1570 + }, + { + "epoch": 0.6202131859455191, + "grad_norm": 0.6346651315689087, + "learning_rate": 1.9009080142123964e-06, + "loss": 0.4615, + "step": 1571 + }, + { + "epoch": 0.6206079747335176, + "grad_norm": 0.6573331356048584, + "learning_rate": 1.8989340702724044e-06, + "loss": 0.4474, + "step": 1572 + }, + { + "epoch": 0.621002763521516, + "grad_norm": 0.7190056443214417, + "learning_rate": 1.8969601263324121e-06, + "loss": 0.528, + "step": 1573 + }, + { + "epoch": 0.6213975523095144, + "grad_norm": 0.7188654541969299, + "learning_rate": 1.8949861823924201e-06, + "loss": 0.5125, + "step": 1574 + }, + { + "epoch": 0.6217923410975128, + "grad_norm": 0.7573840618133545, + "learning_rate": 1.893012238452428e-06, + "loss": 0.5615, + "step": 1575 + }, + { + "epoch": 0.6221871298855113, + "grad_norm": 0.5960707068443298, + "learning_rate": 1.8910382945124359e-06, + "loss": 0.4659, + "step": 1576 + }, + { + "epoch": 0.6225819186735096, + "grad_norm": 0.6557362079620361, + "learning_rate": 1.889064350572444e-06, + "loss": 0.5295, + "step": 1577 + }, + { + "epoch": 0.6229767074615081, + "grad_norm": 0.6049352884292603, + "learning_rate": 1.887090406632452e-06, + "loss": 0.5003, + "step": 1578 + }, + { + "epoch": 0.6233714962495065, + "grad_norm": 0.6025355458259583, + "learning_rate": 1.8851164626924598e-06, + "loss": 0.5154, + "step": 1579 + }, + { + "epoch": 0.623766285037505, + "grad_norm": 0.7906737327575684, + "learning_rate": 1.8831425187524677e-06, + "loss": 0.5506, + "step": 1580 + }, + { + "epoch": 0.6241610738255033, + "grad_norm": 0.6350008249282837, + "learning_rate": 1.8811685748124755e-06, + "loss": 0.4822, + "step": 1581 + }, + { + "epoch": 0.6245558626135018, + "grad_norm": 0.6155006885528564, + "learning_rate": 1.8791946308724835e-06, + "loss": 0.4316, + "step": 1582 + }, + { + "epoch": 0.6249506514015002, + "grad_norm": 0.6775327920913696, + "learning_rate": 1.8772206869324912e-06, + "loss": 0.5532, + "step": 1583 + }, + { + "epoch": 0.6253454401894987, + "grad_norm": 0.701965868473053, + "learning_rate": 1.8752467429924992e-06, + "loss": 0.4922, + "step": 1584 + }, + { + "epoch": 0.625740228977497, + "grad_norm": 0.8652066588401794, + "learning_rate": 1.8732727990525072e-06, + "loss": 0.4988, + "step": 1585 + }, + { + "epoch": 0.6261350177654954, + "grad_norm": 0.6259487271308899, + "learning_rate": 1.871298855112515e-06, + "loss": 0.4332, + "step": 1586 + }, + { + "epoch": 0.6265298065534939, + "grad_norm": 0.7264100909233093, + "learning_rate": 1.869324911172523e-06, + "loss": 0.5207, + "step": 1587 + }, + { + "epoch": 0.6269245953414923, + "grad_norm": 0.8023459911346436, + "learning_rate": 1.8673509672325307e-06, + "loss": 0.41, + "step": 1588 + }, + { + "epoch": 0.6273193841294907, + "grad_norm": 0.7969578504562378, + "learning_rate": 1.8653770232925386e-06, + "loss": 0.5408, + "step": 1589 + }, + { + "epoch": 0.6277141729174891, + "grad_norm": 0.5609579682350159, + "learning_rate": 1.8634030793525464e-06, + "loss": 0.4217, + "step": 1590 + }, + { + "epoch": 0.6281089617054876, + "grad_norm": 0.7513633370399475, + "learning_rate": 1.8614291354125544e-06, + "loss": 0.4804, + "step": 1591 + }, + { + "epoch": 0.628503750493486, + "grad_norm": 0.553610622882843, + "learning_rate": 1.8594551914725624e-06, + "loss": 0.4201, + "step": 1592 + }, + { + "epoch": 0.6288985392814844, + "grad_norm": 0.5405218005180359, + "learning_rate": 1.8574812475325701e-06, + "loss": 0.486, + "step": 1593 + }, + { + "epoch": 0.6292933280694828, + "grad_norm": 0.6985324025154114, + "learning_rate": 1.855507303592578e-06, + "loss": 0.528, + "step": 1594 + }, + { + "epoch": 0.6296881168574813, + "grad_norm": 0.6114775538444519, + "learning_rate": 1.8535333596525859e-06, + "loss": 0.48, + "step": 1595 + }, + { + "epoch": 0.6300829056454796, + "grad_norm": 0.5861915349960327, + "learning_rate": 1.8515594157125938e-06, + "loss": 0.5179, + "step": 1596 + }, + { + "epoch": 0.6304776944334781, + "grad_norm": 0.6712889075279236, + "learning_rate": 1.849585471772602e-06, + "loss": 0.4744, + "step": 1597 + }, + { + "epoch": 0.6308724832214765, + "grad_norm": 0.6317481994628906, + "learning_rate": 1.8476115278326098e-06, + "loss": 0.4537, + "step": 1598 + }, + { + "epoch": 0.631267272009475, + "grad_norm": 0.8099932074546814, + "learning_rate": 1.8456375838926177e-06, + "loss": 0.546, + "step": 1599 + }, + { + "epoch": 0.6316620607974733, + "grad_norm": 0.6641427874565125, + "learning_rate": 1.8436636399526255e-06, + "loss": 0.5108, + "step": 1600 + }, + { + "epoch": 0.6320568495854718, + "grad_norm": 0.6818075776100159, + "learning_rate": 1.8416896960126335e-06, + "loss": 0.4464, + "step": 1601 + }, + { + "epoch": 0.6324516383734702, + "grad_norm": 0.7349079251289368, + "learning_rate": 1.8397157520726414e-06, + "loss": 0.5136, + "step": 1602 + }, + { + "epoch": 0.6328464271614687, + "grad_norm": 0.5515872836112976, + "learning_rate": 1.8377418081326492e-06, + "loss": 0.4578, + "step": 1603 + }, + { + "epoch": 0.633241215949467, + "grad_norm": 0.7105171084403992, + "learning_rate": 1.8357678641926572e-06, + "loss": 0.5412, + "step": 1604 + }, + { + "epoch": 0.6336360047374655, + "grad_norm": 0.6511503458023071, + "learning_rate": 1.833793920252665e-06, + "loss": 0.5066, + "step": 1605 + }, + { + "epoch": 0.6340307935254639, + "grad_norm": 0.5445135235786438, + "learning_rate": 1.831819976312673e-06, + "loss": 0.5086, + "step": 1606 + }, + { + "epoch": 0.6344255823134622, + "grad_norm": 0.614138126373291, + "learning_rate": 1.8298460323726807e-06, + "loss": 0.4325, + "step": 1607 + }, + { + "epoch": 0.6348203711014607, + "grad_norm": 0.6383715867996216, + "learning_rate": 1.8278720884326886e-06, + "loss": 0.5139, + "step": 1608 + }, + { + "epoch": 0.6352151598894591, + "grad_norm": 0.7277885675430298, + "learning_rate": 1.8258981444926966e-06, + "loss": 0.5148, + "step": 1609 + }, + { + "epoch": 0.6356099486774576, + "grad_norm": 0.7968907356262207, + "learning_rate": 1.8239242005527044e-06, + "loss": 0.4966, + "step": 1610 + }, + { + "epoch": 0.6360047374654559, + "grad_norm": 0.6261287331581116, + "learning_rate": 1.8219502566127124e-06, + "loss": 0.5025, + "step": 1611 + }, + { + "epoch": 0.6363995262534544, + "grad_norm": 0.681089460849762, + "learning_rate": 1.8199763126727201e-06, + "loss": 0.5179, + "step": 1612 + }, + { + "epoch": 0.6367943150414528, + "grad_norm": 0.6480545997619629, + "learning_rate": 1.818002368732728e-06, + "loss": 0.5049, + "step": 1613 + }, + { + "epoch": 0.6371891038294513, + "grad_norm": 0.6533011794090271, + "learning_rate": 1.8160284247927358e-06, + "loss": 0.4187, + "step": 1614 + }, + { + "epoch": 0.6375838926174496, + "grad_norm": 0.7162616848945618, + "learning_rate": 1.8140544808527438e-06, + "loss": 0.4969, + "step": 1615 + }, + { + "epoch": 0.6379786814054481, + "grad_norm": 0.6824533343315125, + "learning_rate": 1.8120805369127518e-06, + "loss": 0.4538, + "step": 1616 + }, + { + "epoch": 0.6383734701934465, + "grad_norm": 0.7482508420944214, + "learning_rate": 1.8101065929727596e-06, + "loss": 0.5343, + "step": 1617 + }, + { + "epoch": 0.638768258981445, + "grad_norm": 0.658609926700592, + "learning_rate": 1.8081326490327677e-06, + "loss": 0.4445, + "step": 1618 + }, + { + "epoch": 0.6391630477694433, + "grad_norm": 0.668473482131958, + "learning_rate": 1.8061587050927757e-06, + "loss": 0.4674, + "step": 1619 + }, + { + "epoch": 0.6395578365574418, + "grad_norm": 0.6243305802345276, + "learning_rate": 1.8041847611527835e-06, + "loss": 0.4547, + "step": 1620 + }, + { + "epoch": 0.6399526253454402, + "grad_norm": 0.5912641882896423, + "learning_rate": 1.8022108172127914e-06, + "loss": 0.4758, + "step": 1621 + }, + { + "epoch": 0.6403474141334387, + "grad_norm": 0.7752520442008972, + "learning_rate": 1.8002368732727992e-06, + "loss": 0.4758, + "step": 1622 + }, + { + "epoch": 0.640742202921437, + "grad_norm": 0.6909930109977722, + "learning_rate": 1.7982629293328072e-06, + "loss": 0.4869, + "step": 1623 + }, + { + "epoch": 0.6411369917094355, + "grad_norm": 0.7582605481147766, + "learning_rate": 1.796288985392815e-06, + "loss": 0.5073, + "step": 1624 + }, + { + "epoch": 0.6415317804974339, + "grad_norm": 0.5686845183372498, + "learning_rate": 1.794315041452823e-06, + "loss": 0.4576, + "step": 1625 + }, + { + "epoch": 0.6419265692854323, + "grad_norm": 0.9175251126289368, + "learning_rate": 1.7923410975128309e-06, + "loss": 0.5675, + "step": 1626 + }, + { + "epoch": 0.6423213580734307, + "grad_norm": 0.6730552315711975, + "learning_rate": 1.7903671535728386e-06, + "loss": 0.4452, + "step": 1627 + }, + { + "epoch": 0.6427161468614291, + "grad_norm": 0.7167541980743408, + "learning_rate": 1.7883932096328466e-06, + "loss": 0.5011, + "step": 1628 + }, + { + "epoch": 0.6431109356494276, + "grad_norm": 0.6623883247375488, + "learning_rate": 1.7864192656928544e-06, + "loss": 0.4233, + "step": 1629 + }, + { + "epoch": 0.6435057244374259, + "grad_norm": 0.6382039189338684, + "learning_rate": 1.7844453217528624e-06, + "loss": 0.4886, + "step": 1630 + }, + { + "epoch": 0.6439005132254244, + "grad_norm": 0.8290771842002869, + "learning_rate": 1.7824713778128701e-06, + "loss": 0.5506, + "step": 1631 + }, + { + "epoch": 0.6442953020134228, + "grad_norm": 0.7068865299224854, + "learning_rate": 1.780497433872878e-06, + "loss": 0.5332, + "step": 1632 + }, + { + "epoch": 0.6446900908014213, + "grad_norm": 0.6417805552482605, + "learning_rate": 1.778523489932886e-06, + "loss": 0.4474, + "step": 1633 + }, + { + "epoch": 0.6450848795894196, + "grad_norm": 0.6710495352745056, + "learning_rate": 1.7765495459928938e-06, + "loss": 0.4802, + "step": 1634 + }, + { + "epoch": 0.6454796683774181, + "grad_norm": 0.6322652697563171, + "learning_rate": 1.7745756020529018e-06, + "loss": 0.4617, + "step": 1635 + }, + { + "epoch": 0.6458744571654165, + "grad_norm": 0.667116105556488, + "learning_rate": 1.7726016581129096e-06, + "loss": 0.5141, + "step": 1636 + }, + { + "epoch": 0.646269245953415, + "grad_norm": 0.5550078749656677, + "learning_rate": 1.7706277141729175e-06, + "loss": 0.4491, + "step": 1637 + }, + { + "epoch": 0.6466640347414133, + "grad_norm": 0.5844211578369141, + "learning_rate": 1.7686537702329253e-06, + "loss": 0.4258, + "step": 1638 + }, + { + "epoch": 0.6470588235294118, + "grad_norm": 0.6224120259284973, + "learning_rate": 1.7666798262929335e-06, + "loss": 0.5142, + "step": 1639 + }, + { + "epoch": 0.6474536123174102, + "grad_norm": 0.7364915609359741, + "learning_rate": 1.7647058823529414e-06, + "loss": 0.4885, + "step": 1640 + }, + { + "epoch": 0.6478484011054086, + "grad_norm": 1.1414240598678589, + "learning_rate": 1.7627319384129494e-06, + "loss": 0.4903, + "step": 1641 + }, + { + "epoch": 0.648243189893407, + "grad_norm": 0.5862759351730347, + "learning_rate": 1.7607579944729572e-06, + "loss": 0.4984, + "step": 1642 + }, + { + "epoch": 0.6486379786814055, + "grad_norm": 0.7868353128433228, + "learning_rate": 1.7587840505329652e-06, + "loss": 0.5419, + "step": 1643 + }, + { + "epoch": 0.6490327674694039, + "grad_norm": 0.6419235467910767, + "learning_rate": 1.756810106592973e-06, + "loss": 0.4367, + "step": 1644 + }, + { + "epoch": 0.6494275562574023, + "grad_norm": 0.8316342830657959, + "learning_rate": 1.7548361626529809e-06, + "loss": 0.4982, + "step": 1645 + }, + { + "epoch": 0.6498223450454007, + "grad_norm": 0.6777065992355347, + "learning_rate": 1.7528622187129886e-06, + "loss": 0.4297, + "step": 1646 + }, + { + "epoch": 0.6502171338333992, + "grad_norm": 0.6515488624572754, + "learning_rate": 1.7508882747729966e-06, + "loss": 0.5126, + "step": 1647 + }, + { + "epoch": 0.6506119226213976, + "grad_norm": 0.6731864213943481, + "learning_rate": 1.7489143308330046e-06, + "loss": 0.5018, + "step": 1648 + }, + { + "epoch": 0.6510067114093959, + "grad_norm": 0.5776005983352661, + "learning_rate": 1.7469403868930124e-06, + "loss": 0.4266, + "step": 1649 + }, + { + "epoch": 0.6514015001973944, + "grad_norm": 0.8410418629646301, + "learning_rate": 1.7449664429530203e-06, + "loss": 0.5398, + "step": 1650 + }, + { + "epoch": 0.6517962889853928, + "grad_norm": 0.6284347772598267, + "learning_rate": 1.742992499013028e-06, + "loss": 0.47, + "step": 1651 + }, + { + "epoch": 0.6521910777733912, + "grad_norm": 0.704073965549469, + "learning_rate": 1.741018555073036e-06, + "loss": 0.4999, + "step": 1652 + }, + { + "epoch": 0.6525858665613896, + "grad_norm": 0.9946475028991699, + "learning_rate": 1.7390446111330438e-06, + "loss": 0.5106, + "step": 1653 + }, + { + "epoch": 0.6529806553493881, + "grad_norm": 0.5277566909790039, + "learning_rate": 1.7370706671930518e-06, + "loss": 0.4189, + "step": 1654 + }, + { + "epoch": 0.6533754441373865, + "grad_norm": 0.7508670091629028, + "learning_rate": 1.7350967232530598e-06, + "loss": 0.5488, + "step": 1655 + }, + { + "epoch": 0.6537702329253849, + "grad_norm": 0.7839746475219727, + "learning_rate": 1.7331227793130675e-06, + "loss": 0.5145, + "step": 1656 + }, + { + "epoch": 0.6541650217133833, + "grad_norm": 0.7181482911109924, + "learning_rate": 1.7311488353730755e-06, + "loss": 0.5101, + "step": 1657 + }, + { + "epoch": 0.6545598105013818, + "grad_norm": 0.6132291555404663, + "learning_rate": 1.7291748914330833e-06, + "loss": 0.4941, + "step": 1658 + }, + { + "epoch": 0.6549545992893802, + "grad_norm": 0.6541268825531006, + "learning_rate": 1.7272009474930914e-06, + "loss": 0.4672, + "step": 1659 + }, + { + "epoch": 0.6553493880773786, + "grad_norm": 0.5958321690559387, + "learning_rate": 1.7252270035530994e-06, + "loss": 0.4283, + "step": 1660 + }, + { + "epoch": 0.655744176865377, + "grad_norm": 0.611786425113678, + "learning_rate": 1.7232530596131072e-06, + "loss": 0.4652, + "step": 1661 + }, + { + "epoch": 0.6561389656533755, + "grad_norm": 0.7373178005218506, + "learning_rate": 1.7212791156731152e-06, + "loss": 0.5092, + "step": 1662 + }, + { + "epoch": 0.6565337544413739, + "grad_norm": 0.7413643002510071, + "learning_rate": 1.719305171733123e-06, + "loss": 0.5777, + "step": 1663 + }, + { + "epoch": 0.6569285432293723, + "grad_norm": 0.5932949781417847, + "learning_rate": 1.7173312277931309e-06, + "loss": 0.4726, + "step": 1664 + }, + { + "epoch": 0.6573233320173707, + "grad_norm": 0.7376471757888794, + "learning_rate": 1.7153572838531389e-06, + "loss": 0.5364, + "step": 1665 + }, + { + "epoch": 0.6577181208053692, + "grad_norm": 0.7959655523300171, + "learning_rate": 1.7133833399131466e-06, + "loss": 0.5247, + "step": 1666 + }, + { + "epoch": 0.6581129095933675, + "grad_norm": 0.7908333539962769, + "learning_rate": 1.7114093959731546e-06, + "loss": 0.5762, + "step": 1667 + }, + { + "epoch": 0.658507698381366, + "grad_norm": 0.6524552702903748, + "learning_rate": 1.7094354520331624e-06, + "loss": 0.4625, + "step": 1668 + }, + { + "epoch": 0.6589024871693644, + "grad_norm": 0.6908849477767944, + "learning_rate": 1.7074615080931703e-06, + "loss": 0.4868, + "step": 1669 + }, + { + "epoch": 0.6592972759573628, + "grad_norm": 0.6169744729995728, + "learning_rate": 1.705487564153178e-06, + "loss": 0.4741, + "step": 1670 + }, + { + "epoch": 0.6596920647453612, + "grad_norm": 0.6797540187835693, + "learning_rate": 1.703513620213186e-06, + "loss": 0.4617, + "step": 1671 + }, + { + "epoch": 0.6600868535333596, + "grad_norm": 0.6002185940742493, + "learning_rate": 1.701539676273194e-06, + "loss": 0.4871, + "step": 1672 + }, + { + "epoch": 0.6604816423213581, + "grad_norm": 0.8581214547157288, + "learning_rate": 1.6995657323332018e-06, + "loss": 0.5999, + "step": 1673 + }, + { + "epoch": 0.6608764311093565, + "grad_norm": 0.696786642074585, + "learning_rate": 1.6975917883932098e-06, + "loss": 0.507, + "step": 1674 + }, + { + "epoch": 0.6612712198973549, + "grad_norm": 0.5972174406051636, + "learning_rate": 1.6956178444532175e-06, + "loss": 0.5206, + "step": 1675 + }, + { + "epoch": 0.6616660086853533, + "grad_norm": 0.7621973752975464, + "learning_rate": 1.6936439005132255e-06, + "loss": 0.5658, + "step": 1676 + }, + { + "epoch": 0.6620607974733518, + "grad_norm": 0.5743750333786011, + "learning_rate": 1.6916699565732333e-06, + "loss": 0.463, + "step": 1677 + }, + { + "epoch": 0.6624555862613501, + "grad_norm": 0.7071713805198669, + "learning_rate": 1.6896960126332412e-06, + "loss": 0.5302, + "step": 1678 + }, + { + "epoch": 0.6628503750493486, + "grad_norm": 0.5668283104896545, + "learning_rate": 1.6877220686932492e-06, + "loss": 0.4692, + "step": 1679 + }, + { + "epoch": 0.663245163837347, + "grad_norm": 0.7969346046447754, + "learning_rate": 1.6857481247532572e-06, + "loss": 0.5829, + "step": 1680 + }, + { + "epoch": 0.6636399526253455, + "grad_norm": 0.6845526099205017, + "learning_rate": 1.6837741808132651e-06, + "loss": 0.4979, + "step": 1681 + }, + { + "epoch": 0.6640347414133438, + "grad_norm": 0.7100737690925598, + "learning_rate": 1.6818002368732731e-06, + "loss": 0.4924, + "step": 1682 + }, + { + "epoch": 0.6644295302013423, + "grad_norm": 0.6316900849342346, + "learning_rate": 1.6798262929332809e-06, + "loss": 0.4592, + "step": 1683 + }, + { + "epoch": 0.6648243189893407, + "grad_norm": 0.6711908578872681, + "learning_rate": 1.6778523489932889e-06, + "loss": 0.4955, + "step": 1684 + }, + { + "epoch": 0.6652191077773392, + "grad_norm": 0.7103188633918762, + "learning_rate": 1.6758784050532966e-06, + "loss": 0.5568, + "step": 1685 + }, + { + "epoch": 0.6656138965653375, + "grad_norm": 0.6568583846092224, + "learning_rate": 1.6739044611133046e-06, + "loss": 0.4962, + "step": 1686 + }, + { + "epoch": 0.666008685353336, + "grad_norm": 0.5979764461517334, + "learning_rate": 1.6719305171733124e-06, + "loss": 0.4874, + "step": 1687 + }, + { + "epoch": 0.6664034741413344, + "grad_norm": 0.6627131104469299, + "learning_rate": 1.6699565732333203e-06, + "loss": 0.4413, + "step": 1688 + }, + { + "epoch": 0.6667982629293328, + "grad_norm": 0.7831182479858398, + "learning_rate": 1.6679826292933283e-06, + "loss": 0.6117, + "step": 1689 + }, + { + "epoch": 0.6671930517173312, + "grad_norm": 0.7280836701393127, + "learning_rate": 1.666008685353336e-06, + "loss": 0.5501, + "step": 1690 + }, + { + "epoch": 0.6675878405053296, + "grad_norm": 0.7176200747489929, + "learning_rate": 1.664034741413344e-06, + "loss": 0.5254, + "step": 1691 + }, + { + "epoch": 0.6679826292933281, + "grad_norm": 0.7837709188461304, + "learning_rate": 1.6620607974733518e-06, + "loss": 0.5276, + "step": 1692 + }, + { + "epoch": 0.6683774180813264, + "grad_norm": 0.6966214179992676, + "learning_rate": 1.6600868535333598e-06, + "loss": 0.4926, + "step": 1693 + }, + { + "epoch": 0.6687722068693249, + "grad_norm": 0.783288300037384, + "learning_rate": 1.6581129095933675e-06, + "loss": 0.4925, + "step": 1694 + }, + { + "epoch": 0.6691669956573233, + "grad_norm": 0.7035624384880066, + "learning_rate": 1.6561389656533755e-06, + "loss": 0.569, + "step": 1695 + }, + { + "epoch": 0.6695617844453218, + "grad_norm": 0.5956501364707947, + "learning_rate": 1.6541650217133835e-06, + "loss": 0.4625, + "step": 1696 + }, + { + "epoch": 0.6699565732333201, + "grad_norm": 0.7485847473144531, + "learning_rate": 1.6521910777733912e-06, + "loss": 0.4962, + "step": 1697 + }, + { + "epoch": 0.6703513620213186, + "grad_norm": 0.742951512336731, + "learning_rate": 1.6502171338333992e-06, + "loss": 0.5534, + "step": 1698 + }, + { + "epoch": 0.670746150809317, + "grad_norm": 0.9600015878677368, + "learning_rate": 1.648243189893407e-06, + "loss": 0.5269, + "step": 1699 + }, + { + "epoch": 0.6711409395973155, + "grad_norm": 0.6657900810241699, + "learning_rate": 1.6462692459534151e-06, + "loss": 0.4906, + "step": 1700 + }, + { + "epoch": 0.6715357283853138, + "grad_norm": 0.728938102722168, + "learning_rate": 1.6442953020134231e-06, + "loss": 0.5158, + "step": 1701 + }, + { + "epoch": 0.6719305171733123, + "grad_norm": 0.6221758723258972, + "learning_rate": 1.6423213580734309e-06, + "loss": 0.474, + "step": 1702 + }, + { + "epoch": 0.6723253059613107, + "grad_norm": 0.5947698950767517, + "learning_rate": 1.6403474141334389e-06, + "loss": 0.4709, + "step": 1703 + }, + { + "epoch": 0.6727200947493092, + "grad_norm": 0.5211076140403748, + "learning_rate": 1.6383734701934468e-06, + "loss": 0.446, + "step": 1704 + }, + { + "epoch": 0.6731148835373075, + "grad_norm": 0.8758072257041931, + "learning_rate": 1.6363995262534546e-06, + "loss": 0.4995, + "step": 1705 + }, + { + "epoch": 0.673509672325306, + "grad_norm": 0.6407922506332397, + "learning_rate": 1.6344255823134626e-06, + "loss": 0.465, + "step": 1706 + }, + { + "epoch": 0.6739044611133044, + "grad_norm": 0.6980826258659363, + "learning_rate": 1.6324516383734703e-06, + "loss": 0.5441, + "step": 1707 + }, + { + "epoch": 0.6742992499013029, + "grad_norm": 1.0138905048370361, + "learning_rate": 1.6304776944334783e-06, + "loss": 0.4679, + "step": 1708 + }, + { + "epoch": 0.6746940386893012, + "grad_norm": 0.6284295320510864, + "learning_rate": 1.628503750493486e-06, + "loss": 0.4598, + "step": 1709 + }, + { + "epoch": 0.6750888274772996, + "grad_norm": 0.49249738454818726, + "learning_rate": 1.626529806553494e-06, + "loss": 0.3736, + "step": 1710 + }, + { + "epoch": 0.6754836162652981, + "grad_norm": 0.6368674039840698, + "learning_rate": 1.624555862613502e-06, + "loss": 0.4791, + "step": 1711 + }, + { + "epoch": 0.6758784050532964, + "grad_norm": 0.6065569519996643, + "learning_rate": 1.6225819186735098e-06, + "loss": 0.4745, + "step": 1712 + }, + { + "epoch": 0.6762731938412949, + "grad_norm": 0.647537887096405, + "learning_rate": 1.6206079747335177e-06, + "loss": 0.491, + "step": 1713 + }, + { + "epoch": 0.6766679826292933, + "grad_norm": 0.6395160555839539, + "learning_rate": 1.6186340307935255e-06, + "loss": 0.4578, + "step": 1714 + }, + { + "epoch": 0.6770627714172918, + "grad_norm": 0.7385203242301941, + "learning_rate": 1.6166600868535335e-06, + "loss": 0.5165, + "step": 1715 + }, + { + "epoch": 0.6774575602052901, + "grad_norm": 0.5951353311538696, + "learning_rate": 1.6146861429135412e-06, + "loss": 0.4171, + "step": 1716 + }, + { + "epoch": 0.6778523489932886, + "grad_norm": 0.6359490752220154, + "learning_rate": 1.6127121989735492e-06, + "loss": 0.467, + "step": 1717 + }, + { + "epoch": 0.678247137781287, + "grad_norm": 0.85045325756073, + "learning_rate": 1.6107382550335572e-06, + "loss": 0.5468, + "step": 1718 + }, + { + "epoch": 0.6786419265692855, + "grad_norm": 0.7055619359016418, + "learning_rate": 1.608764311093565e-06, + "loss": 0.5084, + "step": 1719 + }, + { + "epoch": 0.6790367153572838, + "grad_norm": 0.7750738263130188, + "learning_rate": 1.606790367153573e-06, + "loss": 0.5147, + "step": 1720 + }, + { + "epoch": 0.6794315041452823, + "grad_norm": 0.6841555833816528, + "learning_rate": 1.604816423213581e-06, + "loss": 0.4964, + "step": 1721 + }, + { + "epoch": 0.6798262929332807, + "grad_norm": 0.5968098640441895, + "learning_rate": 1.6028424792735889e-06, + "loss": 0.4663, + "step": 1722 + }, + { + "epoch": 0.6802210817212792, + "grad_norm": 0.6682634353637695, + "learning_rate": 1.6008685353335968e-06, + "loss": 0.5167, + "step": 1723 + }, + { + "epoch": 0.6806158705092775, + "grad_norm": 0.7030319571495056, + "learning_rate": 1.5988945913936046e-06, + "loss": 0.4716, + "step": 1724 + }, + { + "epoch": 0.681010659297276, + "grad_norm": 0.7816187739372253, + "learning_rate": 1.5969206474536126e-06, + "loss": 0.5211, + "step": 1725 + }, + { + "epoch": 0.6814054480852744, + "grad_norm": 0.6713297963142395, + "learning_rate": 1.5949467035136203e-06, + "loss": 0.476, + "step": 1726 + }, + { + "epoch": 0.6818002368732728, + "grad_norm": 0.7961744070053101, + "learning_rate": 1.5929727595736283e-06, + "loss": 0.5282, + "step": 1727 + }, + { + "epoch": 0.6821950256612712, + "grad_norm": 0.8873960971832275, + "learning_rate": 1.5909988156336363e-06, + "loss": 0.5704, + "step": 1728 + }, + { + "epoch": 0.6825898144492697, + "grad_norm": 0.6636008620262146, + "learning_rate": 1.589024871693644e-06, + "loss": 0.5348, + "step": 1729 + }, + { + "epoch": 0.6829846032372681, + "grad_norm": 0.6954966187477112, + "learning_rate": 1.587050927753652e-06, + "loss": 0.4356, + "step": 1730 + }, + { + "epoch": 0.6833793920252664, + "grad_norm": 0.7215845584869385, + "learning_rate": 1.5850769838136598e-06, + "loss": 0.4969, + "step": 1731 + }, + { + "epoch": 0.6837741808132649, + "grad_norm": 0.7654891610145569, + "learning_rate": 1.5831030398736677e-06, + "loss": 0.5142, + "step": 1732 + }, + { + "epoch": 0.6841689696012633, + "grad_norm": 0.7994312644004822, + "learning_rate": 1.5811290959336755e-06, + "loss": 0.613, + "step": 1733 + }, + { + "epoch": 0.6845637583892618, + "grad_norm": 0.769725501537323, + "learning_rate": 1.5791551519936835e-06, + "loss": 0.5576, + "step": 1734 + }, + { + "epoch": 0.6849585471772601, + "grad_norm": 0.7502182126045227, + "learning_rate": 1.5771812080536914e-06, + "loss": 0.5544, + "step": 1735 + }, + { + "epoch": 0.6853533359652586, + "grad_norm": 0.6127429008483887, + "learning_rate": 1.5752072641136992e-06, + "loss": 0.4502, + "step": 1736 + }, + { + "epoch": 0.685748124753257, + "grad_norm": 0.6709719300270081, + "learning_rate": 1.5732333201737072e-06, + "loss": 0.4412, + "step": 1737 + }, + { + "epoch": 0.6861429135412555, + "grad_norm": 0.6515864133834839, + "learning_rate": 1.571259376233715e-06, + "loss": 0.4867, + "step": 1738 + }, + { + "epoch": 0.6865377023292538, + "grad_norm": 0.6123561263084412, + "learning_rate": 1.569285432293723e-06, + "loss": 0.4601, + "step": 1739 + }, + { + "epoch": 0.6869324911172523, + "grad_norm": 0.6102393865585327, + "learning_rate": 1.5673114883537307e-06, + "loss": 0.44, + "step": 1740 + }, + { + "epoch": 0.6873272799052507, + "grad_norm": 0.8383168578147888, + "learning_rate": 1.5653375444137386e-06, + "loss": 0.5565, + "step": 1741 + }, + { + "epoch": 0.6877220686932491, + "grad_norm": 0.7135722041130066, + "learning_rate": 1.5633636004737468e-06, + "loss": 0.5053, + "step": 1742 + }, + { + "epoch": 0.6881168574812475, + "grad_norm": 0.5401783585548401, + "learning_rate": 1.5613896565337546e-06, + "loss": 0.4937, + "step": 1743 + }, + { + "epoch": 0.688511646269246, + "grad_norm": 0.5818305611610413, + "learning_rate": 1.5594157125937626e-06, + "loss": 0.4549, + "step": 1744 + }, + { + "epoch": 0.6889064350572444, + "grad_norm": 0.6856871843338013, + "learning_rate": 1.5574417686537705e-06, + "loss": 0.4993, + "step": 1745 + }, + { + "epoch": 0.6893012238452428, + "grad_norm": 0.8589998483657837, + "learning_rate": 1.5554678247137783e-06, + "loss": 0.4924, + "step": 1746 + }, + { + "epoch": 0.6896960126332412, + "grad_norm": 0.6139064431190491, + "learning_rate": 1.5534938807737863e-06, + "loss": 0.5195, + "step": 1747 + }, + { + "epoch": 0.6900908014212397, + "grad_norm": 0.6469478011131287, + "learning_rate": 1.551519936833794e-06, + "loss": 0.4246, + "step": 1748 + }, + { + "epoch": 0.690485590209238, + "grad_norm": 0.755713701248169, + "learning_rate": 1.549545992893802e-06, + "loss": 0.54, + "step": 1749 + }, + { + "epoch": 0.6908803789972365, + "grad_norm": 0.6035457849502563, + "learning_rate": 1.5475720489538098e-06, + "loss": 0.4333, + "step": 1750 + }, + { + "epoch": 0.6912751677852349, + "grad_norm": 0.6952213644981384, + "learning_rate": 1.5455981050138177e-06, + "loss": 0.5075, + "step": 1751 + }, + { + "epoch": 0.6916699565732333, + "grad_norm": 0.6946704387664795, + "learning_rate": 1.5436241610738257e-06, + "loss": 0.4947, + "step": 1752 + }, + { + "epoch": 0.6920647453612317, + "grad_norm": 0.6378570795059204, + "learning_rate": 1.5416502171338335e-06, + "loss": 0.5493, + "step": 1753 + }, + { + "epoch": 0.6924595341492301, + "grad_norm": 0.5462923049926758, + "learning_rate": 1.5396762731938414e-06, + "loss": 0.4613, + "step": 1754 + }, + { + "epoch": 0.6928543229372286, + "grad_norm": 0.6596975326538086, + "learning_rate": 1.5377023292538492e-06, + "loss": 0.4837, + "step": 1755 + }, + { + "epoch": 0.693249111725227, + "grad_norm": 0.6908217668533325, + "learning_rate": 1.5357283853138572e-06, + "loss": 0.5757, + "step": 1756 + }, + { + "epoch": 0.6936439005132254, + "grad_norm": 0.6924253106117249, + "learning_rate": 1.533754441373865e-06, + "loss": 0.4711, + "step": 1757 + }, + { + "epoch": 0.6940386893012238, + "grad_norm": 0.7994088530540466, + "learning_rate": 1.531780497433873e-06, + "loss": 0.5382, + "step": 1758 + }, + { + "epoch": 0.6944334780892223, + "grad_norm": 0.7557870745658875, + "learning_rate": 1.5298065534938809e-06, + "loss": 0.5061, + "step": 1759 + }, + { + "epoch": 0.6948282668772207, + "grad_norm": 0.7369120717048645, + "learning_rate": 1.5278326095538886e-06, + "loss": 0.5463, + "step": 1760 + }, + { + "epoch": 0.6952230556652191, + "grad_norm": 0.5781756043434143, + "learning_rate": 1.5258586656138966e-06, + "loss": 0.4803, + "step": 1761 + }, + { + "epoch": 0.6956178444532175, + "grad_norm": 0.7980154752731323, + "learning_rate": 1.5238847216739048e-06, + "loss": 0.4888, + "step": 1762 + }, + { + "epoch": 0.696012633241216, + "grad_norm": 0.737122654914856, + "learning_rate": 1.5219107777339126e-06, + "loss": 0.5179, + "step": 1763 + }, + { + "epoch": 0.6964074220292144, + "grad_norm": 0.5518711805343628, + "learning_rate": 1.5199368337939205e-06, + "loss": 0.4193, + "step": 1764 + }, + { + "epoch": 0.6968022108172128, + "grad_norm": 0.5713463425636292, + "learning_rate": 1.5179628898539283e-06, + "loss": 0.5241, + "step": 1765 + }, + { + "epoch": 0.6971969996052112, + "grad_norm": 0.549260675907135, + "learning_rate": 1.5159889459139363e-06, + "loss": 0.498, + "step": 1766 + }, + { + "epoch": 0.6975917883932097, + "grad_norm": 0.6083453893661499, + "learning_rate": 1.5140150019739442e-06, + "loss": 0.5176, + "step": 1767 + }, + { + "epoch": 0.697986577181208, + "grad_norm": 7.109658718109131, + "learning_rate": 1.512041058033952e-06, + "loss": 0.5451, + "step": 1768 + }, + { + "epoch": 0.6983813659692065, + "grad_norm": 0.7007879018783569, + "learning_rate": 1.51006711409396e-06, + "loss": 0.5141, + "step": 1769 + }, + { + "epoch": 0.6987761547572049, + "grad_norm": 0.5565025210380554, + "learning_rate": 1.5080931701539677e-06, + "loss": 0.4809, + "step": 1770 + }, + { + "epoch": 0.6991709435452034, + "grad_norm": 0.643856406211853, + "learning_rate": 1.5061192262139757e-06, + "loss": 0.4708, + "step": 1771 + }, + { + "epoch": 0.6995657323332017, + "grad_norm": 0.6916229724884033, + "learning_rate": 1.5041452822739835e-06, + "loss": 0.5137, + "step": 1772 + }, + { + "epoch": 0.6999605211212001, + "grad_norm": 0.6314439177513123, + "learning_rate": 1.5021713383339914e-06, + "loss": 0.4827, + "step": 1773 + }, + { + "epoch": 0.7003553099091986, + "grad_norm": 0.6607741713523865, + "learning_rate": 1.5001973943939994e-06, + "loss": 0.5078, + "step": 1774 + }, + { + "epoch": 0.700750098697197, + "grad_norm": 0.6819167733192444, + "learning_rate": 1.4982234504540072e-06, + "loss": 0.5627, + "step": 1775 + }, + { + "epoch": 0.7011448874851954, + "grad_norm": 0.716087818145752, + "learning_rate": 1.4962495065140151e-06, + "loss": 0.5153, + "step": 1776 + }, + { + "epoch": 0.7015396762731938, + "grad_norm": 0.7335947751998901, + "learning_rate": 1.494275562574023e-06, + "loss": 0.4885, + "step": 1777 + }, + { + "epoch": 0.7019344650611923, + "grad_norm": 1.1881823539733887, + "learning_rate": 1.4923016186340309e-06, + "loss": 0.5592, + "step": 1778 + }, + { + "epoch": 0.7023292538491906, + "grad_norm": 0.7440038919448853, + "learning_rate": 1.4903276746940386e-06, + "loss": 0.5233, + "step": 1779 + }, + { + "epoch": 0.7027240426371891, + "grad_norm": 0.674862265586853, + "learning_rate": 1.4883537307540466e-06, + "loss": 0.4614, + "step": 1780 + }, + { + "epoch": 0.7031188314251875, + "grad_norm": 0.6508384346961975, + "learning_rate": 1.4863797868140546e-06, + "loss": 0.4961, + "step": 1781 + }, + { + "epoch": 0.703513620213186, + "grad_norm": 0.7176344394683838, + "learning_rate": 1.4844058428740623e-06, + "loss": 0.4843, + "step": 1782 + }, + { + "epoch": 0.7039084090011843, + "grad_norm": 0.6157323122024536, + "learning_rate": 1.4824318989340705e-06, + "loss": 0.4808, + "step": 1783 + }, + { + "epoch": 0.7043031977891828, + "grad_norm": 0.7402894496917725, + "learning_rate": 1.4804579549940785e-06, + "loss": 0.5095, + "step": 1784 + }, + { + "epoch": 0.7046979865771812, + "grad_norm": 0.7061122059822083, + "learning_rate": 1.4784840110540863e-06, + "loss": 0.5007, + "step": 1785 + }, + { + "epoch": 0.7050927753651797, + "grad_norm": 0.6174380779266357, + "learning_rate": 1.4765100671140942e-06, + "loss": 0.5415, + "step": 1786 + }, + { + "epoch": 0.705487564153178, + "grad_norm": 0.7721444964408875, + "learning_rate": 1.474536123174102e-06, + "loss": 0.5847, + "step": 1787 + }, + { + "epoch": 0.7058823529411765, + "grad_norm": 0.8193248510360718, + "learning_rate": 1.47256217923411e-06, + "loss": 0.4704, + "step": 1788 + }, + { + "epoch": 0.7062771417291749, + "grad_norm": 0.7281805276870728, + "learning_rate": 1.4705882352941177e-06, + "loss": 0.4653, + "step": 1789 + }, + { + "epoch": 0.7066719305171734, + "grad_norm": 0.6758389472961426, + "learning_rate": 1.4686142913541257e-06, + "loss": 0.5021, + "step": 1790 + }, + { + "epoch": 0.7070667193051717, + "grad_norm": 0.6528709530830383, + "learning_rate": 1.4666403474141337e-06, + "loss": 0.5424, + "step": 1791 + }, + { + "epoch": 0.7074615080931701, + "grad_norm": 0.6561812162399292, + "learning_rate": 1.4646664034741414e-06, + "loss": 0.4882, + "step": 1792 + }, + { + "epoch": 0.7078562968811686, + "grad_norm": 0.6399228572845459, + "learning_rate": 1.4626924595341494e-06, + "loss": 0.5818, + "step": 1793 + }, + { + "epoch": 0.708251085669167, + "grad_norm": 0.6091529726982117, + "learning_rate": 1.4607185155941572e-06, + "loss": 0.4755, + "step": 1794 + }, + { + "epoch": 0.7086458744571654, + "grad_norm": 0.608974277973175, + "learning_rate": 1.4587445716541651e-06, + "loss": 0.4935, + "step": 1795 + }, + { + "epoch": 0.7090406632451638, + "grad_norm": 0.6631879210472107, + "learning_rate": 1.456770627714173e-06, + "loss": 0.5593, + "step": 1796 + }, + { + "epoch": 0.7094354520331623, + "grad_norm": 0.6741741895675659, + "learning_rate": 1.4547966837741809e-06, + "loss": 0.5144, + "step": 1797 + }, + { + "epoch": 0.7098302408211606, + "grad_norm": 0.6562315225601196, + "learning_rate": 1.4528227398341888e-06, + "loss": 0.4572, + "step": 1798 + }, + { + "epoch": 0.7102250296091591, + "grad_norm": 0.6716213226318359, + "learning_rate": 1.4508487958941966e-06, + "loss": 0.5335, + "step": 1799 + }, + { + "epoch": 0.7106198183971575, + "grad_norm": 0.6408854722976685, + "learning_rate": 1.4488748519542046e-06, + "loss": 0.4724, + "step": 1800 + }, + { + "epoch": 0.711014607185156, + "grad_norm": 0.7233725190162659, + "learning_rate": 1.4469009080142123e-06, + "loss": 0.5392, + "step": 1801 + }, + { + "epoch": 0.7114093959731543, + "grad_norm": 0.889676570892334, + "learning_rate": 1.4449269640742203e-06, + "loss": 0.4792, + "step": 1802 + }, + { + "epoch": 0.7118041847611528, + "grad_norm": 0.6908667087554932, + "learning_rate": 1.4429530201342285e-06, + "loss": 0.4925, + "step": 1803 + }, + { + "epoch": 0.7121989735491512, + "grad_norm": 0.621027410030365, + "learning_rate": 1.4409790761942363e-06, + "loss": 0.4869, + "step": 1804 + }, + { + "epoch": 0.7125937623371497, + "grad_norm": 0.6471368670463562, + "learning_rate": 1.4390051322542442e-06, + "loss": 0.4721, + "step": 1805 + }, + { + "epoch": 0.712988551125148, + "grad_norm": 0.5665576457977295, + "learning_rate": 1.437031188314252e-06, + "loss": 0.5281, + "step": 1806 + }, + { + "epoch": 0.7133833399131465, + "grad_norm": 0.6006726026535034, + "learning_rate": 1.43505724437426e-06, + "loss": 0.5223, + "step": 1807 + }, + { + "epoch": 0.7137781287011449, + "grad_norm": 0.7186239361763, + "learning_rate": 1.433083300434268e-06, + "loss": 0.4948, + "step": 1808 + }, + { + "epoch": 0.7141729174891434, + "grad_norm": 0.5954815745353699, + "learning_rate": 1.4311093564942757e-06, + "loss": 0.4314, + "step": 1809 + }, + { + "epoch": 0.7145677062771417, + "grad_norm": 0.6124107241630554, + "learning_rate": 1.4291354125542837e-06, + "loss": 0.4494, + "step": 1810 + }, + { + "epoch": 0.7149624950651402, + "grad_norm": 0.6165976524353027, + "learning_rate": 1.4271614686142914e-06, + "loss": 0.5183, + "step": 1811 + }, + { + "epoch": 0.7153572838531386, + "grad_norm": 0.5656868815422058, + "learning_rate": 1.4251875246742994e-06, + "loss": 0.4296, + "step": 1812 + }, + { + "epoch": 0.7157520726411369, + "grad_norm": 0.6443467736244202, + "learning_rate": 1.4232135807343072e-06, + "loss": 0.4552, + "step": 1813 + }, + { + "epoch": 0.7161468614291354, + "grad_norm": 0.6942663788795471, + "learning_rate": 1.4212396367943151e-06, + "loss": 0.5206, + "step": 1814 + }, + { + "epoch": 0.7165416502171338, + "grad_norm": 0.6842094659805298, + "learning_rate": 1.4192656928543231e-06, + "loss": 0.5217, + "step": 1815 + }, + { + "epoch": 0.7169364390051323, + "grad_norm": 0.7306404709815979, + "learning_rate": 1.4172917489143309e-06, + "loss": 0.4823, + "step": 1816 + }, + { + "epoch": 0.7173312277931306, + "grad_norm": 0.6725155115127563, + "learning_rate": 1.4153178049743388e-06, + "loss": 0.5159, + "step": 1817 + }, + { + "epoch": 0.7177260165811291, + "grad_norm": 0.6645560264587402, + "learning_rate": 1.4133438610343466e-06, + "loss": 0.4412, + "step": 1818 + }, + { + "epoch": 0.7181208053691275, + "grad_norm": 0.6526039838790894, + "learning_rate": 1.4113699170943546e-06, + "loss": 0.4908, + "step": 1819 + }, + { + "epoch": 0.718515594157126, + "grad_norm": 0.7905670404434204, + "learning_rate": 1.4093959731543623e-06, + "loss": 0.5123, + "step": 1820 + }, + { + "epoch": 0.7189103829451243, + "grad_norm": 0.6882116794586182, + "learning_rate": 1.4074220292143703e-06, + "loss": 0.5444, + "step": 1821 + }, + { + "epoch": 0.7193051717331228, + "grad_norm": 0.7127177119255066, + "learning_rate": 1.4054480852743783e-06, + "loss": 0.5228, + "step": 1822 + }, + { + "epoch": 0.7196999605211212, + "grad_norm": 0.7591845989227295, + "learning_rate": 1.403474141334386e-06, + "loss": 0.5523, + "step": 1823 + }, + { + "epoch": 0.7200947493091197, + "grad_norm": 0.6432467699050903, + "learning_rate": 1.4015001973943942e-06, + "loss": 0.4285, + "step": 1824 + }, + { + "epoch": 0.720489538097118, + "grad_norm": 0.8570986390113831, + "learning_rate": 1.3995262534544022e-06, + "loss": 0.5366, + "step": 1825 + }, + { + "epoch": 0.7208843268851165, + "grad_norm": 0.6629605293273926, + "learning_rate": 1.39755230951441e-06, + "loss": 0.5388, + "step": 1826 + }, + { + "epoch": 0.7212791156731149, + "grad_norm": 0.6424852609634399, + "learning_rate": 1.395578365574418e-06, + "loss": 0.5068, + "step": 1827 + }, + { + "epoch": 0.7216739044611133, + "grad_norm": 0.5961523652076721, + "learning_rate": 1.3936044216344257e-06, + "loss": 0.4584, + "step": 1828 + }, + { + "epoch": 0.7220686932491117, + "grad_norm": 0.511573076248169, + "learning_rate": 1.3916304776944337e-06, + "loss": 0.4518, + "step": 1829 + }, + { + "epoch": 0.7224634820371102, + "grad_norm": 0.6398566961288452, + "learning_rate": 1.3896565337544414e-06, + "loss": 0.4954, + "step": 1830 + }, + { + "epoch": 0.7228582708251086, + "grad_norm": 0.6445457339286804, + "learning_rate": 1.3876825898144494e-06, + "loss": 0.5235, + "step": 1831 + }, + { + "epoch": 0.723253059613107, + "grad_norm": 0.7739589214324951, + "learning_rate": 1.3857086458744574e-06, + "loss": 0.4774, + "step": 1832 + }, + { + "epoch": 0.7236478484011054, + "grad_norm": 0.6612921357154846, + "learning_rate": 1.3837347019344651e-06, + "loss": 0.4673, + "step": 1833 + }, + { + "epoch": 0.7240426371891038, + "grad_norm": 0.6714397668838501, + "learning_rate": 1.3817607579944731e-06, + "loss": 0.4745, + "step": 1834 + }, + { + "epoch": 0.7244374259771023, + "grad_norm": 0.635001540184021, + "learning_rate": 1.3797868140544809e-06, + "loss": 0.5475, + "step": 1835 + }, + { + "epoch": 0.7248322147651006, + "grad_norm": 0.7282422780990601, + "learning_rate": 1.3778128701144888e-06, + "loss": 0.4683, + "step": 1836 + }, + { + "epoch": 0.7252270035530991, + "grad_norm": 0.5630329847335815, + "learning_rate": 1.3758389261744968e-06, + "loss": 0.4604, + "step": 1837 + }, + { + "epoch": 0.7256217923410975, + "grad_norm": 0.7102289795875549, + "learning_rate": 1.3738649822345046e-06, + "loss": 0.5066, + "step": 1838 + }, + { + "epoch": 0.726016581129096, + "grad_norm": 0.6954649686813354, + "learning_rate": 1.3718910382945126e-06, + "loss": 0.534, + "step": 1839 + }, + { + "epoch": 0.7264113699170943, + "grad_norm": 0.6070659756660461, + "learning_rate": 1.3699170943545203e-06, + "loss": 0.4884, + "step": 1840 + }, + { + "epoch": 0.7268061587050928, + "grad_norm": 0.6858262419700623, + "learning_rate": 1.3679431504145283e-06, + "loss": 0.4562, + "step": 1841 + }, + { + "epoch": 0.7272009474930912, + "grad_norm": 0.6266196966171265, + "learning_rate": 1.365969206474536e-06, + "loss": 0.5206, + "step": 1842 + }, + { + "epoch": 0.7275957362810896, + "grad_norm": 0.7483528256416321, + "learning_rate": 1.363995262534544e-06, + "loss": 0.5616, + "step": 1843 + }, + { + "epoch": 0.727990525069088, + "grad_norm": 0.6786347031593323, + "learning_rate": 1.362021318594552e-06, + "loss": 0.5765, + "step": 1844 + }, + { + "epoch": 0.7283853138570865, + "grad_norm": 0.8733579516410828, + "learning_rate": 1.36004737465456e-06, + "loss": 0.5369, + "step": 1845 + }, + { + "epoch": 0.7287801026450849, + "grad_norm": 0.7247394919395447, + "learning_rate": 1.358073430714568e-06, + "loss": 0.5302, + "step": 1846 + }, + { + "epoch": 0.7291748914330833, + "grad_norm": 1.411505103111267, + "learning_rate": 1.356099486774576e-06, + "loss": 0.5587, + "step": 1847 + }, + { + "epoch": 0.7295696802210817, + "grad_norm": 0.7345286011695862, + "learning_rate": 1.3541255428345837e-06, + "loss": 0.5511, + "step": 1848 + }, + { + "epoch": 0.7299644690090802, + "grad_norm": 0.6572315096855164, + "learning_rate": 1.3521515988945916e-06, + "loss": 0.5174, + "step": 1849 + }, + { + "epoch": 0.7303592577970786, + "grad_norm": 0.6597719788551331, + "learning_rate": 1.3501776549545994e-06, + "loss": 0.4701, + "step": 1850 + }, + { + "epoch": 0.730754046585077, + "grad_norm": 0.6973147988319397, + "learning_rate": 1.3482037110146074e-06, + "loss": 0.5082, + "step": 1851 + }, + { + "epoch": 0.7311488353730754, + "grad_norm": 0.7328445911407471, + "learning_rate": 1.3462297670746151e-06, + "loss": 0.5722, + "step": 1852 + }, + { + "epoch": 0.7315436241610739, + "grad_norm": 0.5927713513374329, + "learning_rate": 1.3442558231346231e-06, + "loss": 0.4425, + "step": 1853 + }, + { + "epoch": 0.7319384129490722, + "grad_norm": 0.5729705095291138, + "learning_rate": 1.342281879194631e-06, + "loss": 0.5009, + "step": 1854 + }, + { + "epoch": 0.7323332017370706, + "grad_norm": 0.699955403804779, + "learning_rate": 1.3403079352546388e-06, + "loss": 0.4908, + "step": 1855 + }, + { + "epoch": 0.7327279905250691, + "grad_norm": 0.7442764043807983, + "learning_rate": 1.3383339913146468e-06, + "loss": 0.5245, + "step": 1856 + }, + { + "epoch": 0.7331227793130675, + "grad_norm": 0.6910063028335571, + "learning_rate": 1.3363600473746546e-06, + "loss": 0.576, + "step": 1857 + }, + { + "epoch": 0.7335175681010659, + "grad_norm": 0.7426862120628357, + "learning_rate": 1.3343861034346626e-06, + "loss": 0.5166, + "step": 1858 + }, + { + "epoch": 0.7339123568890643, + "grad_norm": 0.5890196561813354, + "learning_rate": 1.3324121594946703e-06, + "loss": 0.5291, + "step": 1859 + }, + { + "epoch": 0.7343071456770628, + "grad_norm": 0.6057066917419434, + "learning_rate": 1.3304382155546783e-06, + "loss": 0.431, + "step": 1860 + }, + { + "epoch": 0.7347019344650612, + "grad_norm": 0.75913405418396, + "learning_rate": 1.3284642716146863e-06, + "loss": 0.493, + "step": 1861 + }, + { + "epoch": 0.7350967232530596, + "grad_norm": 0.7822492122650146, + "learning_rate": 1.326490327674694e-06, + "loss": 0.5139, + "step": 1862 + }, + { + "epoch": 0.735491512041058, + "grad_norm": 0.5358699560165405, + "learning_rate": 1.324516383734702e-06, + "loss": 0.4465, + "step": 1863 + }, + { + "epoch": 0.7358863008290565, + "grad_norm": 0.6409959197044373, + "learning_rate": 1.3225424397947098e-06, + "loss": 0.4691, + "step": 1864 + }, + { + "epoch": 0.7362810896170549, + "grad_norm": 0.6728172898292542, + "learning_rate": 1.320568495854718e-06, + "loss": 0.5475, + "step": 1865 + }, + { + "epoch": 0.7366758784050533, + "grad_norm": 1.5525994300842285, + "learning_rate": 1.318594551914726e-06, + "loss": 0.5732, + "step": 1866 + }, + { + "epoch": 0.7370706671930517, + "grad_norm": 0.6753315925598145, + "learning_rate": 1.3166206079747337e-06, + "loss": 0.4937, + "step": 1867 + }, + { + "epoch": 0.7374654559810502, + "grad_norm": 0.7293807864189148, + "learning_rate": 1.3146466640347416e-06, + "loss": 0.5002, + "step": 1868 + }, + { + "epoch": 0.7378602447690485, + "grad_norm": 0.7718378901481628, + "learning_rate": 1.3126727200947494e-06, + "loss": 0.5307, + "step": 1869 + }, + { + "epoch": 0.738255033557047, + "grad_norm": 0.7198406457901001, + "learning_rate": 1.3106987761547574e-06, + "loss": 0.4316, + "step": 1870 + }, + { + "epoch": 0.7386498223450454, + "grad_norm": 0.8093804717063904, + "learning_rate": 1.3087248322147653e-06, + "loss": 0.5918, + "step": 1871 + }, + { + "epoch": 0.7390446111330439, + "grad_norm": 0.6511887907981873, + "learning_rate": 1.3067508882747731e-06, + "loss": 0.4892, + "step": 1872 + }, + { + "epoch": 0.7394393999210422, + "grad_norm": 0.7603165507316589, + "learning_rate": 1.304776944334781e-06, + "loss": 0.5125, + "step": 1873 + }, + { + "epoch": 0.7398341887090407, + "grad_norm": 0.6504552960395813, + "learning_rate": 1.3028030003947888e-06, + "loss": 0.5577, + "step": 1874 + }, + { + "epoch": 0.7402289774970391, + "grad_norm": 0.7978520393371582, + "learning_rate": 1.3008290564547968e-06, + "loss": 0.5596, + "step": 1875 + }, + { + "epoch": 0.7406237662850375, + "grad_norm": 0.7165732979774475, + "learning_rate": 1.2988551125148046e-06, + "loss": 0.5072, + "step": 1876 + }, + { + "epoch": 0.7410185550730359, + "grad_norm": 0.5763140320777893, + "learning_rate": 1.2968811685748126e-06, + "loss": 0.4075, + "step": 1877 + }, + { + "epoch": 0.7414133438610343, + "grad_norm": 0.5695169568061829, + "learning_rate": 1.2949072246348205e-06, + "loss": 0.4721, + "step": 1878 + }, + { + "epoch": 0.7418081326490328, + "grad_norm": 0.6096559762954712, + "learning_rate": 1.2929332806948283e-06, + "loss": 0.4348, + "step": 1879 + }, + { + "epoch": 0.7422029214370311, + "grad_norm": 0.766359806060791, + "learning_rate": 1.2909593367548363e-06, + "loss": 0.5131, + "step": 1880 + }, + { + "epoch": 0.7425977102250296, + "grad_norm": 0.6099081635475159, + "learning_rate": 1.288985392814844e-06, + "loss": 0.4899, + "step": 1881 + }, + { + "epoch": 0.742992499013028, + "grad_norm": 0.753264844417572, + "learning_rate": 1.287011448874852e-06, + "loss": 0.5639, + "step": 1882 + }, + { + "epoch": 0.7433872878010265, + "grad_norm": 0.6901788115501404, + "learning_rate": 1.2850375049348598e-06, + "loss": 0.4626, + "step": 1883 + }, + { + "epoch": 0.7437820765890248, + "grad_norm": 0.7588280439376831, + "learning_rate": 1.2830635609948677e-06, + "loss": 0.5052, + "step": 1884 + }, + { + "epoch": 0.7441768653770233, + "grad_norm": 0.6371081471443176, + "learning_rate": 1.2810896170548757e-06, + "loss": 0.5301, + "step": 1885 + }, + { + "epoch": 0.7445716541650217, + "grad_norm": 0.6307573914527893, + "learning_rate": 1.2791156731148837e-06, + "loss": 0.4751, + "step": 1886 + }, + { + "epoch": 0.7449664429530202, + "grad_norm": 0.6533688306808472, + "learning_rate": 1.2771417291748916e-06, + "loss": 0.4891, + "step": 1887 + }, + { + "epoch": 0.7453612317410185, + "grad_norm": 0.7298348546028137, + "learning_rate": 1.2751677852348996e-06, + "loss": 0.5401, + "step": 1888 + }, + { + "epoch": 0.745756020529017, + "grad_norm": 0.742414116859436, + "learning_rate": 1.2731938412949074e-06, + "loss": 0.538, + "step": 1889 + }, + { + "epoch": 0.7461508093170154, + "grad_norm": 0.8389927744865417, + "learning_rate": 1.2712198973549153e-06, + "loss": 0.5079, + "step": 1890 + }, + { + "epoch": 0.7465455981050139, + "grad_norm": 0.7765556573867798, + "learning_rate": 1.2692459534149231e-06, + "loss": 0.6389, + "step": 1891 + }, + { + "epoch": 0.7469403868930122, + "grad_norm": 0.5450223684310913, + "learning_rate": 1.267272009474931e-06, + "loss": 0.5087, + "step": 1892 + }, + { + "epoch": 0.7473351756810107, + "grad_norm": 0.6358421444892883, + "learning_rate": 1.2652980655349388e-06, + "loss": 0.4991, + "step": 1893 + }, + { + "epoch": 0.7477299644690091, + "grad_norm": 0.6838845014572144, + "learning_rate": 1.2633241215949468e-06, + "loss": 0.5311, + "step": 1894 + }, + { + "epoch": 0.7481247532570074, + "grad_norm": 0.6393290162086487, + "learning_rate": 1.2613501776549548e-06, + "loss": 0.4819, + "step": 1895 + }, + { + "epoch": 0.7485195420450059, + "grad_norm": 0.7258987426757812, + "learning_rate": 1.2593762337149625e-06, + "loss": 0.5112, + "step": 1896 + }, + { + "epoch": 0.7489143308330043, + "grad_norm": 0.6545507907867432, + "learning_rate": 1.2574022897749705e-06, + "loss": 0.5047, + "step": 1897 + }, + { + "epoch": 0.7493091196210028, + "grad_norm": 0.62504643201828, + "learning_rate": 1.2554283458349783e-06, + "loss": 0.4999, + "step": 1898 + }, + { + "epoch": 0.7497039084090011, + "grad_norm": 0.6805427074432373, + "learning_rate": 1.2534544018949863e-06, + "loss": 0.5485, + "step": 1899 + }, + { + "epoch": 0.7500986971969996, + "grad_norm": 0.5009310841560364, + "learning_rate": 1.251480457954994e-06, + "loss": 0.4572, + "step": 1900 + }, + { + "epoch": 0.750493485984998, + "grad_norm": 0.7388902902603149, + "learning_rate": 1.2495065140150022e-06, + "loss": 0.5474, + "step": 1901 + }, + { + "epoch": 0.7508882747729965, + "grad_norm": 0.6521325707435608, + "learning_rate": 1.24753257007501e-06, + "loss": 0.541, + "step": 1902 + }, + { + "epoch": 0.7512830635609948, + "grad_norm": 0.5374358296394348, + "learning_rate": 1.245558626135018e-06, + "loss": 0.4837, + "step": 1903 + }, + { + "epoch": 0.7516778523489933, + "grad_norm": 0.84738689661026, + "learning_rate": 1.2435846821950257e-06, + "loss": 0.5362, + "step": 1904 + }, + { + "epoch": 0.7520726411369917, + "grad_norm": 0.8514695167541504, + "learning_rate": 1.2416107382550337e-06, + "loss": 0.554, + "step": 1905 + }, + { + "epoch": 0.7524674299249902, + "grad_norm": 0.7387975454330444, + "learning_rate": 1.2396367943150416e-06, + "loss": 0.4695, + "step": 1906 + }, + { + "epoch": 0.7528622187129885, + "grad_norm": 0.7755898237228394, + "learning_rate": 1.2376628503750494e-06, + "loss": 0.5398, + "step": 1907 + }, + { + "epoch": 0.753257007500987, + "grad_norm": 0.685879647731781, + "learning_rate": 1.2356889064350574e-06, + "loss": 0.5471, + "step": 1908 + }, + { + "epoch": 0.7536517962889854, + "grad_norm": 0.6825161576271057, + "learning_rate": 1.2337149624950651e-06, + "loss": 0.5509, + "step": 1909 + }, + { + "epoch": 0.7540465850769839, + "grad_norm": 0.6271716952323914, + "learning_rate": 1.2317410185550731e-06, + "loss": 0.5508, + "step": 1910 + }, + { + "epoch": 0.7544413738649822, + "grad_norm": 0.6950467228889465, + "learning_rate": 1.2297670746150809e-06, + "loss": 0.5375, + "step": 1911 + }, + { + "epoch": 0.7548361626529807, + "grad_norm": 0.5873447060585022, + "learning_rate": 1.227793130675089e-06, + "loss": 0.5588, + "step": 1912 + }, + { + "epoch": 0.7552309514409791, + "grad_norm": 0.6917153000831604, + "learning_rate": 1.2258191867350968e-06, + "loss": 0.5087, + "step": 1913 + }, + { + "epoch": 0.7556257402289775, + "grad_norm": 0.7142869830131531, + "learning_rate": 1.2238452427951048e-06, + "loss": 0.552, + "step": 1914 + }, + { + "epoch": 0.7560205290169759, + "grad_norm": 0.612923800945282, + "learning_rate": 1.2218712988551125e-06, + "loss": 0.5075, + "step": 1915 + }, + { + "epoch": 0.7564153178049743, + "grad_norm": 0.6044191122055054, + "learning_rate": 1.2198973549151205e-06, + "loss": 0.4558, + "step": 1916 + }, + { + "epoch": 0.7568101065929728, + "grad_norm": 0.8251253366470337, + "learning_rate": 1.2179234109751285e-06, + "loss": 0.5468, + "step": 1917 + }, + { + "epoch": 0.7572048953809711, + "grad_norm": 0.6930932402610779, + "learning_rate": 1.2159494670351363e-06, + "loss": 0.4967, + "step": 1918 + }, + { + "epoch": 0.7575996841689696, + "grad_norm": 0.6670072078704834, + "learning_rate": 1.2139755230951442e-06, + "loss": 0.5637, + "step": 1919 + }, + { + "epoch": 0.757994472956968, + "grad_norm": 0.67206871509552, + "learning_rate": 1.212001579155152e-06, + "loss": 0.5074, + "step": 1920 + }, + { + "epoch": 0.7583892617449665, + "grad_norm": 0.6466824412345886, + "learning_rate": 1.21002763521516e-06, + "loss": 0.5342, + "step": 1921 + }, + { + "epoch": 0.7587840505329648, + "grad_norm": 0.671136200428009, + "learning_rate": 1.208053691275168e-06, + "loss": 0.5172, + "step": 1922 + }, + { + "epoch": 0.7591788393209633, + "grad_norm": 0.683986485004425, + "learning_rate": 1.206079747335176e-06, + "loss": 0.4945, + "step": 1923 + }, + { + "epoch": 0.7595736281089617, + "grad_norm": 0.6412071585655212, + "learning_rate": 1.2041058033951837e-06, + "loss": 0.5422, + "step": 1924 + }, + { + "epoch": 0.7599684168969602, + "grad_norm": 0.6929531097412109, + "learning_rate": 1.2021318594551916e-06, + "loss": 0.5899, + "step": 1925 + }, + { + "epoch": 0.7603632056849585, + "grad_norm": 0.7486274242401123, + "learning_rate": 1.2001579155151994e-06, + "loss": 0.5427, + "step": 1926 + }, + { + "epoch": 0.760757994472957, + "grad_norm": 0.6992172002792358, + "learning_rate": 1.1981839715752074e-06, + "loss": 0.5409, + "step": 1927 + }, + { + "epoch": 0.7611527832609554, + "grad_norm": 0.8155470490455627, + "learning_rate": 1.1962100276352151e-06, + "loss": 0.5167, + "step": 1928 + }, + { + "epoch": 0.7615475720489538, + "grad_norm": 0.634651780128479, + "learning_rate": 1.1942360836952231e-06, + "loss": 0.4833, + "step": 1929 + }, + { + "epoch": 0.7619423608369522, + "grad_norm": 0.7574975490570068, + "learning_rate": 1.192262139755231e-06, + "loss": 0.5625, + "step": 1930 + }, + { + "epoch": 0.7623371496249507, + "grad_norm": 0.7084071636199951, + "learning_rate": 1.1902881958152388e-06, + "loss": 0.528, + "step": 1931 + }, + { + "epoch": 0.7627319384129491, + "grad_norm": 0.6816278100013733, + "learning_rate": 1.1883142518752468e-06, + "loss": 0.5335, + "step": 1932 + }, + { + "epoch": 0.7631267272009475, + "grad_norm": 0.7686399817466736, + "learning_rate": 1.1863403079352548e-06, + "loss": 0.5798, + "step": 1933 + }, + { + "epoch": 0.7635215159889459, + "grad_norm": 0.7020213603973389, + "learning_rate": 1.1843663639952628e-06, + "loss": 0.5191, + "step": 1934 + }, + { + "epoch": 0.7639163047769444, + "grad_norm": 0.5807182788848877, + "learning_rate": 1.1823924200552705e-06, + "loss": 0.4903, + "step": 1935 + }, + { + "epoch": 0.7643110935649428, + "grad_norm": 0.6043127775192261, + "learning_rate": 1.1804184761152785e-06, + "loss": 0.5035, + "step": 1936 + }, + { + "epoch": 0.7647058823529411, + "grad_norm": 0.7988269925117493, + "learning_rate": 1.1784445321752863e-06, + "loss": 0.5627, + "step": 1937 + }, + { + "epoch": 0.7651006711409396, + "grad_norm": 0.746943473815918, + "learning_rate": 1.1764705882352942e-06, + "loss": 0.5251, + "step": 1938 + }, + { + "epoch": 0.765495459928938, + "grad_norm": 0.5560442209243774, + "learning_rate": 1.174496644295302e-06, + "loss": 0.5119, + "step": 1939 + }, + { + "epoch": 0.7658902487169365, + "grad_norm": 0.70196932554245, + "learning_rate": 1.17252270035531e-06, + "loss": 0.5359, + "step": 1940 + }, + { + "epoch": 0.7662850375049348, + "grad_norm": 0.733589231967926, + "learning_rate": 1.170548756415318e-06, + "loss": 0.5821, + "step": 1941 + }, + { + "epoch": 0.7666798262929333, + "grad_norm": 0.7762577533721924, + "learning_rate": 1.168574812475326e-06, + "loss": 0.5121, + "step": 1942 + }, + { + "epoch": 0.7670746150809317, + "grad_norm": 0.6553015112876892, + "learning_rate": 1.1666008685353337e-06, + "loss": 0.5483, + "step": 1943 + }, + { + "epoch": 0.7674694038689301, + "grad_norm": 0.7009949088096619, + "learning_rate": 1.1646269245953416e-06, + "loss": 0.5103, + "step": 1944 + }, + { + "epoch": 0.7678641926569285, + "grad_norm": 0.5847790241241455, + "learning_rate": 1.1626529806553496e-06, + "loss": 0.4522, + "step": 1945 + }, + { + "epoch": 0.768258981444927, + "grad_norm": 0.6714927554130554, + "learning_rate": 1.1606790367153574e-06, + "loss": 0.4754, + "step": 1946 + }, + { + "epoch": 0.7686537702329254, + "grad_norm": 0.8240972757339478, + "learning_rate": 1.1587050927753653e-06, + "loss": 0.5999, + "step": 1947 + }, + { + "epoch": 0.7690485590209238, + "grad_norm": 0.6827213168144226, + "learning_rate": 1.1567311488353731e-06, + "loss": 0.4738, + "step": 1948 + }, + { + "epoch": 0.7694433478089222, + "grad_norm": 0.7159086465835571, + "learning_rate": 1.154757204895381e-06, + "loss": 0.5733, + "step": 1949 + }, + { + "epoch": 0.7698381365969207, + "grad_norm": 0.7671412229537964, + "learning_rate": 1.1527832609553888e-06, + "loss": 0.5204, + "step": 1950 + }, + { + "epoch": 0.770232925384919, + "grad_norm": 0.6663253307342529, + "learning_rate": 1.1508093170153968e-06, + "loss": 0.4634, + "step": 1951 + }, + { + "epoch": 0.7706277141729175, + "grad_norm": 0.7607415318489075, + "learning_rate": 1.1488353730754048e-06, + "loss": 0.5199, + "step": 1952 + }, + { + "epoch": 0.7710225029609159, + "grad_norm": 0.7897630333900452, + "learning_rate": 1.1468614291354128e-06, + "loss": 0.5188, + "step": 1953 + }, + { + "epoch": 0.7714172917489144, + "grad_norm": 0.7697154879570007, + "learning_rate": 1.1448874851954205e-06, + "loss": 0.6314, + "step": 1954 + }, + { + "epoch": 0.7718120805369127, + "grad_norm": 0.7252954244613647, + "learning_rate": 1.1429135412554285e-06, + "loss": 0.5518, + "step": 1955 + }, + { + "epoch": 0.7722068693249112, + "grad_norm": 0.6534348726272583, + "learning_rate": 1.1409395973154363e-06, + "loss": 0.5441, + "step": 1956 + }, + { + "epoch": 0.7726016581129096, + "grad_norm": 0.613593339920044, + "learning_rate": 1.1389656533754442e-06, + "loss": 0.4832, + "step": 1957 + }, + { + "epoch": 0.772996446900908, + "grad_norm": 0.7251320481300354, + "learning_rate": 1.1369917094354522e-06, + "loss": 0.5813, + "step": 1958 + }, + { + "epoch": 0.7733912356889064, + "grad_norm": 0.7205170392990112, + "learning_rate": 1.13501776549546e-06, + "loss": 0.5447, + "step": 1959 + }, + { + "epoch": 0.7737860244769048, + "grad_norm": 0.6262027025222778, + "learning_rate": 1.133043821555468e-06, + "loss": 0.4882, + "step": 1960 + }, + { + "epoch": 0.7741808132649033, + "grad_norm": 0.7272239327430725, + "learning_rate": 1.1310698776154757e-06, + "loss": 0.5298, + "step": 1961 + }, + { + "epoch": 0.7745756020529017, + "grad_norm": 0.6178505420684814, + "learning_rate": 1.1290959336754837e-06, + "loss": 0.5046, + "step": 1962 + }, + { + "epoch": 0.7749703908409001, + "grad_norm": 0.6811657547950745, + "learning_rate": 1.1271219897354916e-06, + "loss": 0.55, + "step": 1963 + }, + { + "epoch": 0.7753651796288985, + "grad_norm": 0.7014946341514587, + "learning_rate": 1.1251480457954996e-06, + "loss": 0.5108, + "step": 1964 + }, + { + "epoch": 0.775759968416897, + "grad_norm": 0.597849428653717, + "learning_rate": 1.1231741018555074e-06, + "loss": 0.4779, + "step": 1965 + }, + { + "epoch": 0.7761547572048954, + "grad_norm": 0.9948868751525879, + "learning_rate": 1.1212001579155153e-06, + "loss": 0.5745, + "step": 1966 + }, + { + "epoch": 0.7765495459928938, + "grad_norm": 0.6915416121482849, + "learning_rate": 1.119226213975523e-06, + "loss": 0.5174, + "step": 1967 + }, + { + "epoch": 0.7769443347808922, + "grad_norm": 0.682784914970398, + "learning_rate": 1.117252270035531e-06, + "loss": 0.5609, + "step": 1968 + }, + { + "epoch": 0.7773391235688907, + "grad_norm": 0.7491763830184937, + "learning_rate": 1.115278326095539e-06, + "loss": 0.5692, + "step": 1969 + }, + { + "epoch": 0.777733912356889, + "grad_norm": 0.704208254814148, + "learning_rate": 1.1133043821555468e-06, + "loss": 0.5628, + "step": 1970 + }, + { + "epoch": 0.7781287011448875, + "grad_norm": 0.632514476776123, + "learning_rate": 1.1113304382155548e-06, + "loss": 0.5197, + "step": 1971 + }, + { + "epoch": 0.7785234899328859, + "grad_norm": 0.640958309173584, + "learning_rate": 1.1093564942755625e-06, + "loss": 0.5253, + "step": 1972 + }, + { + "epoch": 0.7789182787208844, + "grad_norm": 0.8147770762443542, + "learning_rate": 1.1073825503355707e-06, + "loss": 0.5623, + "step": 1973 + }, + { + "epoch": 0.7793130675088827, + "grad_norm": 0.575794517993927, + "learning_rate": 1.1054086063955785e-06, + "loss": 0.4567, + "step": 1974 + }, + { + "epoch": 0.7797078562968812, + "grad_norm": 1.014923095703125, + "learning_rate": 1.1034346624555865e-06, + "loss": 0.5363, + "step": 1975 + }, + { + "epoch": 0.7801026450848796, + "grad_norm": 0.5982513427734375, + "learning_rate": 1.1014607185155942e-06, + "loss": 0.5052, + "step": 1976 + }, + { + "epoch": 0.780497433872878, + "grad_norm": 0.6078625321388245, + "learning_rate": 1.0994867745756022e-06, + "loss": 0.4893, + "step": 1977 + }, + { + "epoch": 0.7808922226608764, + "grad_norm": 0.612495481967926, + "learning_rate": 1.09751283063561e-06, + "loss": 0.4957, + "step": 1978 + }, + { + "epoch": 0.7812870114488748, + "grad_norm": 0.6625868678092957, + "learning_rate": 1.095538886695618e-06, + "loss": 0.4848, + "step": 1979 + }, + { + "epoch": 0.7816818002368733, + "grad_norm": 0.8118737936019897, + "learning_rate": 1.093564942755626e-06, + "loss": 0.578, + "step": 1980 + }, + { + "epoch": 0.7820765890248716, + "grad_norm": 0.5624467730522156, + "learning_rate": 1.0915909988156337e-06, + "loss": 0.5047, + "step": 1981 + }, + { + "epoch": 0.7824713778128701, + "grad_norm": 0.591828465461731, + "learning_rate": 1.0896170548756416e-06, + "loss": 0.518, + "step": 1982 + }, + { + "epoch": 0.7828661666008685, + "grad_norm": 0.6809039115905762, + "learning_rate": 1.0876431109356494e-06, + "loss": 0.4951, + "step": 1983 + }, + { + "epoch": 0.783260955388867, + "grad_norm": 0.5906721353530884, + "learning_rate": 1.0856691669956574e-06, + "loss": 0.4907, + "step": 1984 + }, + { + "epoch": 0.7836557441768653, + "grad_norm": 0.8366307616233826, + "learning_rate": 1.0836952230556653e-06, + "loss": 0.5255, + "step": 1985 + }, + { + "epoch": 0.7840505329648638, + "grad_norm": 0.7255127429962158, + "learning_rate": 1.0817212791156733e-06, + "loss": 0.548, + "step": 1986 + }, + { + "epoch": 0.7844453217528622, + "grad_norm": 0.6902675032615662, + "learning_rate": 1.079747335175681e-06, + "loss": 0.595, + "step": 1987 + }, + { + "epoch": 0.7848401105408607, + "grad_norm": 0.6384313106536865, + "learning_rate": 1.077773391235689e-06, + "loss": 0.4948, + "step": 1988 + }, + { + "epoch": 0.785234899328859, + "grad_norm": 0.5979447364807129, + "learning_rate": 1.0757994472956968e-06, + "loss": 0.5461, + "step": 1989 + }, + { + "epoch": 0.7856296881168575, + "grad_norm": 0.7374008893966675, + "learning_rate": 1.0738255033557048e-06, + "loss": 0.5833, + "step": 1990 + }, + { + "epoch": 0.7860244769048559, + "grad_norm": 0.6120272874832153, + "learning_rate": 1.0718515594157125e-06, + "loss": 0.4547, + "step": 1991 + }, + { + "epoch": 0.7864192656928544, + "grad_norm": 0.7261528372764587, + "learning_rate": 1.0698776154757205e-06, + "loss": 0.5397, + "step": 1992 + }, + { + "epoch": 0.7868140544808527, + "grad_norm": 0.6764394640922546, + "learning_rate": 1.0679036715357285e-06, + "loss": 0.5098, + "step": 1993 + }, + { + "epoch": 0.7872088432688512, + "grad_norm": 0.5783045887947083, + "learning_rate": 1.0659297275957365e-06, + "loss": 0.4997, + "step": 1994 + }, + { + "epoch": 0.7876036320568496, + "grad_norm": 0.7077938914299011, + "learning_rate": 1.0639557836557442e-06, + "loss": 0.5016, + "step": 1995 + }, + { + "epoch": 0.7879984208448481, + "grad_norm": 0.8147454857826233, + "learning_rate": 1.0619818397157522e-06, + "loss": 0.5247, + "step": 1996 + }, + { + "epoch": 0.7883932096328464, + "grad_norm": 0.7695064544677734, + "learning_rate": 1.0600078957757602e-06, + "loss": 0.5569, + "step": 1997 + }, + { + "epoch": 0.7887879984208448, + "grad_norm": 0.7408329844474792, + "learning_rate": 1.058033951835768e-06, + "loss": 0.5273, + "step": 1998 + }, + { + "epoch": 0.7891827872088433, + "grad_norm": 0.6425075531005859, + "learning_rate": 1.056060007895776e-06, + "loss": 0.5124, + "step": 1999 + }, + { + "epoch": 0.7895775759968416, + "grad_norm": 0.6810621619224548, + "learning_rate": 1.0540860639557837e-06, + "loss": 0.5337, + "step": 2000 + }, + { + "epoch": 0.7899723647848401, + "grad_norm": 0.6747722029685974, + "learning_rate": 1.0521121200157916e-06, + "loss": 0.5136, + "step": 2001 + }, + { + "epoch": 0.7903671535728385, + "grad_norm": 0.8721790909767151, + "learning_rate": 1.0501381760757994e-06, + "loss": 0.6168, + "step": 2002 + }, + { + "epoch": 0.790761942360837, + "grad_norm": 0.5929023623466492, + "learning_rate": 1.0481642321358074e-06, + "loss": 0.4984, + "step": 2003 + }, + { + "epoch": 0.7911567311488353, + "grad_norm": 0.5669233798980713, + "learning_rate": 1.0461902881958153e-06, + "loss": 0.4628, + "step": 2004 + }, + { + "epoch": 0.7915515199368338, + "grad_norm": 0.8057059049606323, + "learning_rate": 1.0442163442558233e-06, + "loss": 0.5811, + "step": 2005 + }, + { + "epoch": 0.7919463087248322, + "grad_norm": 0.7962011098861694, + "learning_rate": 1.042242400315831e-06, + "loss": 0.6144, + "step": 2006 + }, + { + "epoch": 0.7923410975128307, + "grad_norm": 0.4768119752407074, + "learning_rate": 1.040268456375839e-06, + "loss": 0.3999, + "step": 2007 + }, + { + "epoch": 0.792735886300829, + "grad_norm": 0.6637002229690552, + "learning_rate": 1.038294512435847e-06, + "loss": 0.4717, + "step": 2008 + }, + { + "epoch": 0.7931306750888275, + "grad_norm": 0.5951547622680664, + "learning_rate": 1.0363205684958548e-06, + "loss": 0.524, + "step": 2009 + }, + { + "epoch": 0.7935254638768259, + "grad_norm": 0.7800189256668091, + "learning_rate": 1.0343466245558628e-06, + "loss": 0.5511, + "step": 2010 + }, + { + "epoch": 0.7939202526648244, + "grad_norm": 0.6833925247192383, + "learning_rate": 1.0323726806158705e-06, + "loss": 0.5886, + "step": 2011 + }, + { + "epoch": 0.7943150414528227, + "grad_norm": 0.601237416267395, + "learning_rate": 1.0303987366758785e-06, + "loss": 0.4453, + "step": 2012 + }, + { + "epoch": 0.7947098302408212, + "grad_norm": 0.6829959750175476, + "learning_rate": 1.0284247927358862e-06, + "loss": 0.4789, + "step": 2013 + }, + { + "epoch": 0.7951046190288196, + "grad_norm": 0.724264919757843, + "learning_rate": 1.0264508487958942e-06, + "loss": 0.493, + "step": 2014 + }, + { + "epoch": 0.795499407816818, + "grad_norm": 0.7403755187988281, + "learning_rate": 1.0244769048559022e-06, + "loss": 0.5179, + "step": 2015 + }, + { + "epoch": 0.7958941966048164, + "grad_norm": 0.7021251320838928, + "learning_rate": 1.0225029609159102e-06, + "loss": 0.5851, + "step": 2016 + }, + { + "epoch": 0.7962889853928149, + "grad_norm": 0.6639324426651001, + "learning_rate": 1.020529016975918e-06, + "loss": 0.5598, + "step": 2017 + }, + { + "epoch": 0.7966837741808133, + "grad_norm": 0.6477215886116028, + "learning_rate": 1.018555073035926e-06, + "loss": 0.5235, + "step": 2018 + }, + { + "epoch": 0.7970785629688116, + "grad_norm": 0.6645751595497131, + "learning_rate": 1.0165811290959337e-06, + "loss": 0.5349, + "step": 2019 + }, + { + "epoch": 0.7974733517568101, + "grad_norm": 0.7258616089820862, + "learning_rate": 1.0146071851559416e-06, + "loss": 0.5224, + "step": 2020 + }, + { + "epoch": 0.7978681405448085, + "grad_norm": 0.772797167301178, + "learning_rate": 1.0126332412159496e-06, + "loss": 0.5073, + "step": 2021 + }, + { + "epoch": 0.798262929332807, + "grad_norm": 0.5203532576560974, + "learning_rate": 1.0106592972759574e-06, + "loss": 0.456, + "step": 2022 + }, + { + "epoch": 0.7986577181208053, + "grad_norm": 0.6737093925476074, + "learning_rate": 1.0086853533359653e-06, + "loss": 0.5174, + "step": 2023 + }, + { + "epoch": 0.7990525069088038, + "grad_norm": 0.6641145348548889, + "learning_rate": 1.006711409395973e-06, + "loss": 0.5644, + "step": 2024 + }, + { + "epoch": 0.7994472956968022, + "grad_norm": 0.7193712592124939, + "learning_rate": 1.0047374654559813e-06, + "loss": 0.5368, + "step": 2025 + }, + { + "epoch": 0.7998420844848007, + "grad_norm": 0.6566382646560669, + "learning_rate": 1.002763521515989e-06, + "loss": 0.5373, + "step": 2026 + }, + { + "epoch": 0.800236873272799, + "grad_norm": 0.7581789493560791, + "learning_rate": 1.000789577575997e-06, + "loss": 0.5763, + "step": 2027 + }, + { + "epoch": 0.8006316620607975, + "grad_norm": 0.8128560185432434, + "learning_rate": 9.988156336360048e-07, + "loss": 0.4778, + "step": 2028 + }, + { + "epoch": 0.8010264508487959, + "grad_norm": 0.7045120596885681, + "learning_rate": 9.968416896960128e-07, + "loss": 0.5181, + "step": 2029 + }, + { + "epoch": 0.8014212396367943, + "grad_norm": 0.6050856113433838, + "learning_rate": 9.948677457560205e-07, + "loss": 0.5055, + "step": 2030 + }, + { + "epoch": 0.8018160284247927, + "grad_norm": 0.5913096070289612, + "learning_rate": 9.928938018160285e-07, + "loss": 0.5196, + "step": 2031 + }, + { + "epoch": 0.8022108172127912, + "grad_norm": 0.6941872239112854, + "learning_rate": 9.909198578760365e-07, + "loss": 0.4674, + "step": 2032 + }, + { + "epoch": 0.8026056060007896, + "grad_norm": 0.6284596920013428, + "learning_rate": 9.889459139360442e-07, + "loss": 0.514, + "step": 2033 + }, + { + "epoch": 0.803000394788788, + "grad_norm": 0.6382887363433838, + "learning_rate": 9.869719699960522e-07, + "loss": 0.4671, + "step": 2034 + }, + { + "epoch": 0.8033951835767864, + "grad_norm": 0.7018070816993713, + "learning_rate": 9.849980260560602e-07, + "loss": 0.5311, + "step": 2035 + }, + { + "epoch": 0.8037899723647849, + "grad_norm": 0.6986091732978821, + "learning_rate": 9.830240821160681e-07, + "loss": 0.5657, + "step": 2036 + }, + { + "epoch": 0.8041847611527833, + "grad_norm": 0.726658046245575, + "learning_rate": 9.81050138176076e-07, + "loss": 0.5453, + "step": 2037 + }, + { + "epoch": 0.8045795499407817, + "grad_norm": 0.6593878269195557, + "learning_rate": 9.790761942360839e-07, + "loss": 0.5615, + "step": 2038 + }, + { + "epoch": 0.8049743387287801, + "grad_norm": 0.6634563207626343, + "learning_rate": 9.771022502960916e-07, + "loss": 0.5525, + "step": 2039 + }, + { + "epoch": 0.8053691275167785, + "grad_norm": 0.5340339541435242, + "learning_rate": 9.751283063560996e-07, + "loss": 0.4652, + "step": 2040 + }, + { + "epoch": 0.805763916304777, + "grad_norm": 0.5553464889526367, + "learning_rate": 9.731543624161074e-07, + "loss": 0.5166, + "step": 2041 + }, + { + "epoch": 0.8061587050927753, + "grad_norm": 0.5530831813812256, + "learning_rate": 9.711804184761153e-07, + "loss": 0.4894, + "step": 2042 + }, + { + "epoch": 0.8065534938807738, + "grad_norm": 0.6560379862785339, + "learning_rate": 9.692064745361233e-07, + "loss": 0.4745, + "step": 2043 + }, + { + "epoch": 0.8069482826687722, + "grad_norm": 0.7013944983482361, + "learning_rate": 9.67232530596131e-07, + "loss": 0.4927, + "step": 2044 + }, + { + "epoch": 0.8073430714567706, + "grad_norm": 0.7296056747436523, + "learning_rate": 9.65258586656139e-07, + "loss": 0.4911, + "step": 2045 + }, + { + "epoch": 0.807737860244769, + "grad_norm": 0.7736249566078186, + "learning_rate": 9.63284642716147e-07, + "loss": 0.5937, + "step": 2046 + }, + { + "epoch": 0.8081326490327675, + "grad_norm": 0.6131559610366821, + "learning_rate": 9.613106987761548e-07, + "loss": 0.5187, + "step": 2047 + }, + { + "epoch": 0.8085274378207659, + "grad_norm": 0.7611772418022156, + "learning_rate": 9.593367548361628e-07, + "loss": 0.5527, + "step": 2048 + }, + { + "epoch": 0.8089222266087643, + "grad_norm": 0.7589399814605713, + "learning_rate": 9.573628108961707e-07, + "loss": 0.5554, + "step": 2049 + }, + { + "epoch": 0.8093170153967627, + "grad_norm": 0.7268940806388855, + "learning_rate": 9.553888669561785e-07, + "loss": 0.5471, + "step": 2050 + }, + { + "epoch": 0.8097118041847612, + "grad_norm": 0.7118024230003357, + "learning_rate": 9.534149230161864e-07, + "loss": 0.5355, + "step": 2051 + }, + { + "epoch": 0.8101065929727596, + "grad_norm": 0.5437626242637634, + "learning_rate": 9.514409790761943e-07, + "loss": 0.4984, + "step": 2052 + }, + { + "epoch": 0.810501381760758, + "grad_norm": 0.7199985384941101, + "learning_rate": 9.494670351362022e-07, + "loss": 0.5298, + "step": 2053 + }, + { + "epoch": 0.8108961705487564, + "grad_norm": 0.5778906345367432, + "learning_rate": 9.474930911962101e-07, + "loss": 0.5607, + "step": 2054 + }, + { + "epoch": 0.8112909593367549, + "grad_norm": 0.535822331905365, + "learning_rate": 9.455191472562179e-07, + "loss": 0.4781, + "step": 2055 + }, + { + "epoch": 0.8116857481247532, + "grad_norm": 0.7798849940299988, + "learning_rate": 9.43545203316226e-07, + "loss": 0.5199, + "step": 2056 + }, + { + "epoch": 0.8120805369127517, + "grad_norm": 0.7254095077514648, + "learning_rate": 9.415712593762339e-07, + "loss": 0.5516, + "step": 2057 + }, + { + "epoch": 0.8124753257007501, + "grad_norm": 0.8109075427055359, + "learning_rate": 9.395973154362417e-07, + "loss": 0.5561, + "step": 2058 + }, + { + "epoch": 0.8128701144887486, + "grad_norm": 0.6521120667457581, + "learning_rate": 9.376233714962496e-07, + "loss": 0.4889, + "step": 2059 + }, + { + "epoch": 0.8132649032767469, + "grad_norm": 0.6144668459892273, + "learning_rate": 9.356494275562575e-07, + "loss": 0.5085, + "step": 2060 + }, + { + "epoch": 0.8136596920647453, + "grad_norm": 0.6561423540115356, + "learning_rate": 9.336754836162653e-07, + "loss": 0.5408, + "step": 2061 + }, + { + "epoch": 0.8140544808527438, + "grad_norm": 0.7927735447883606, + "learning_rate": 9.317015396762732e-07, + "loss": 0.5235, + "step": 2062 + }, + { + "epoch": 0.8144492696407422, + "grad_norm": 0.6888410449028015, + "learning_rate": 9.297275957362812e-07, + "loss": 0.5525, + "step": 2063 + }, + { + "epoch": 0.8148440584287406, + "grad_norm": 0.6797158718109131, + "learning_rate": 9.27753651796289e-07, + "loss": 0.5015, + "step": 2064 + }, + { + "epoch": 0.815238847216739, + "grad_norm": 0.9169059991836548, + "learning_rate": 9.257797078562969e-07, + "loss": 0.5675, + "step": 2065 + }, + { + "epoch": 0.8156336360047375, + "grad_norm": 0.9232127666473389, + "learning_rate": 9.238057639163049e-07, + "loss": 0.5992, + "step": 2066 + }, + { + "epoch": 0.8160284247927359, + "grad_norm": 0.6560556292533875, + "learning_rate": 9.218318199763128e-07, + "loss": 0.5222, + "step": 2067 + }, + { + "epoch": 0.8164232135807343, + "grad_norm": 0.5179514288902283, + "learning_rate": 9.198578760363207e-07, + "loss": 0.4825, + "step": 2068 + }, + { + "epoch": 0.8168180023687327, + "grad_norm": 0.5791957378387451, + "learning_rate": 9.178839320963286e-07, + "loss": 0.5208, + "step": 2069 + }, + { + "epoch": 0.8172127911567312, + "grad_norm": 0.6869405508041382, + "learning_rate": 9.159099881563365e-07, + "loss": 0.4803, + "step": 2070 + }, + { + "epoch": 0.8176075799447295, + "grad_norm": 0.6973354816436768, + "learning_rate": 9.139360442163443e-07, + "loss": 0.6049, + "step": 2071 + }, + { + "epoch": 0.818002368732728, + "grad_norm": 0.6741071343421936, + "learning_rate": 9.119621002763522e-07, + "loss": 0.4968, + "step": 2072 + }, + { + "epoch": 0.8183971575207264, + "grad_norm": 0.7532562613487244, + "learning_rate": 9.099881563363601e-07, + "loss": 0.5384, + "step": 2073 + }, + { + "epoch": 0.8187919463087249, + "grad_norm": 0.6269460916519165, + "learning_rate": 9.080142123963679e-07, + "loss": 0.5319, + "step": 2074 + }, + { + "epoch": 0.8191867350967232, + "grad_norm": 0.6638683080673218, + "learning_rate": 9.060402684563759e-07, + "loss": 0.4876, + "step": 2075 + }, + { + "epoch": 0.8195815238847217, + "grad_norm": 0.5276431441307068, + "learning_rate": 9.040663245163839e-07, + "loss": 0.4665, + "step": 2076 + }, + { + "epoch": 0.8199763126727201, + "grad_norm": 0.7496881484985352, + "learning_rate": 9.020923805763917e-07, + "loss": 0.5731, + "step": 2077 + }, + { + "epoch": 0.8203711014607186, + "grad_norm": 0.5450448393821716, + "learning_rate": 9.001184366363996e-07, + "loss": 0.4694, + "step": 2078 + }, + { + "epoch": 0.8207658902487169, + "grad_norm": 0.9063534140586853, + "learning_rate": 8.981444926964075e-07, + "loss": 0.6122, + "step": 2079 + }, + { + "epoch": 0.8211606790367153, + "grad_norm": 0.7680325508117676, + "learning_rate": 8.961705487564154e-07, + "loss": 0.5595, + "step": 2080 + }, + { + "epoch": 0.8215554678247138, + "grad_norm": 0.7295898795127869, + "learning_rate": 8.941966048164233e-07, + "loss": 0.5598, + "step": 2081 + }, + { + "epoch": 0.8219502566127121, + "grad_norm": 0.6011388301849365, + "learning_rate": 8.922226608764312e-07, + "loss": 0.5087, + "step": 2082 + }, + { + "epoch": 0.8223450454007106, + "grad_norm": 0.7534490823745728, + "learning_rate": 8.90248716936439e-07, + "loss": 0.5847, + "step": 2083 + }, + { + "epoch": 0.822739834188709, + "grad_norm": 0.9462674856185913, + "learning_rate": 8.882747729964469e-07, + "loss": 0.5788, + "step": 2084 + }, + { + "epoch": 0.8231346229767075, + "grad_norm": 0.687578022480011, + "learning_rate": 8.863008290564548e-07, + "loss": 0.5294, + "step": 2085 + }, + { + "epoch": 0.8235294117647058, + "grad_norm": 0.7153741717338562, + "learning_rate": 8.843268851164626e-07, + "loss": 0.4983, + "step": 2086 + }, + { + "epoch": 0.8239242005527043, + "grad_norm": 0.6898583173751831, + "learning_rate": 8.823529411764707e-07, + "loss": 0.4944, + "step": 2087 + }, + { + "epoch": 0.8243189893407027, + "grad_norm": 0.7412317991256714, + "learning_rate": 8.803789972364786e-07, + "loss": 0.5144, + "step": 2088 + }, + { + "epoch": 0.8247137781287012, + "grad_norm": 0.571269154548645, + "learning_rate": 8.784050532964865e-07, + "loss": 0.4897, + "step": 2089 + }, + { + "epoch": 0.8251085669166995, + "grad_norm": 0.6963887214660645, + "learning_rate": 8.764311093564943e-07, + "loss": 0.5089, + "step": 2090 + }, + { + "epoch": 0.825503355704698, + "grad_norm": 0.5967648029327393, + "learning_rate": 8.744571654165023e-07, + "loss": 0.4854, + "step": 2091 + }, + { + "epoch": 0.8258981444926964, + "grad_norm": 0.6554406881332397, + "learning_rate": 8.724832214765102e-07, + "loss": 0.5539, + "step": 2092 + }, + { + "epoch": 0.8262929332806949, + "grad_norm": 0.6543460488319397, + "learning_rate": 8.70509277536518e-07, + "loss": 0.4895, + "step": 2093 + }, + { + "epoch": 0.8266877220686932, + "grad_norm": 0.6030311584472656, + "learning_rate": 8.685353335965259e-07, + "loss": 0.5371, + "step": 2094 + }, + { + "epoch": 0.8270825108566917, + "grad_norm": 0.7921349406242371, + "learning_rate": 8.665613896565338e-07, + "loss": 0.5691, + "step": 2095 + }, + { + "epoch": 0.8274772996446901, + "grad_norm": 0.47679558396339417, + "learning_rate": 8.645874457165416e-07, + "loss": 0.3673, + "step": 2096 + }, + { + "epoch": 0.8278720884326886, + "grad_norm": 0.6509204506874084, + "learning_rate": 8.626135017765497e-07, + "loss": 0.5541, + "step": 2097 + }, + { + "epoch": 0.8282668772206869, + "grad_norm": 0.6557470560073853, + "learning_rate": 8.606395578365576e-07, + "loss": 0.4888, + "step": 2098 + }, + { + "epoch": 0.8286616660086854, + "grad_norm": 0.6855152249336243, + "learning_rate": 8.586656138965654e-07, + "loss": 0.5028, + "step": 2099 + }, + { + "epoch": 0.8290564547966838, + "grad_norm": 0.6578928828239441, + "learning_rate": 8.566916699565733e-07, + "loss": 0.4604, + "step": 2100 + }, + { + "epoch": 0.8294512435846821, + "grad_norm": 0.7135859131813049, + "learning_rate": 8.547177260165812e-07, + "loss": 0.6012, + "step": 2101 + }, + { + "epoch": 0.8298460323726806, + "grad_norm": 0.7293195724487305, + "learning_rate": 8.52743782076589e-07, + "loss": 0.5153, + "step": 2102 + }, + { + "epoch": 0.830240821160679, + "grad_norm": 0.7328010201454163, + "learning_rate": 8.50769838136597e-07, + "loss": 0.5814, + "step": 2103 + }, + { + "epoch": 0.8306356099486775, + "grad_norm": 0.6420509219169617, + "learning_rate": 8.487958941966049e-07, + "loss": 0.5042, + "step": 2104 + }, + { + "epoch": 0.8310303987366758, + "grad_norm": 0.6936102509498596, + "learning_rate": 8.468219502566127e-07, + "loss": 0.5345, + "step": 2105 + }, + { + "epoch": 0.8314251875246743, + "grad_norm": 0.7739899754524231, + "learning_rate": 8.448480063166206e-07, + "loss": 0.5206, + "step": 2106 + }, + { + "epoch": 0.8318199763126727, + "grad_norm": 0.6372625231742859, + "learning_rate": 8.428740623766286e-07, + "loss": 0.5641, + "step": 2107 + }, + { + "epoch": 0.8322147651006712, + "grad_norm": 0.8486443758010864, + "learning_rate": 8.409001184366366e-07, + "loss": 0.6078, + "step": 2108 + }, + { + "epoch": 0.8326095538886695, + "grad_norm": 0.7122174501419067, + "learning_rate": 8.389261744966444e-07, + "loss": 0.5713, + "step": 2109 + }, + { + "epoch": 0.833004342676668, + "grad_norm": 0.7611689567565918, + "learning_rate": 8.369522305566523e-07, + "loss": 0.4879, + "step": 2110 + }, + { + "epoch": 0.8333991314646664, + "grad_norm": 0.760034441947937, + "learning_rate": 8.349782866166602e-07, + "loss": 0.6107, + "step": 2111 + }, + { + "epoch": 0.8337939202526649, + "grad_norm": 0.5751848220825195, + "learning_rate": 8.33004342676668e-07, + "loss": 0.5275, + "step": 2112 + }, + { + "epoch": 0.8341887090406632, + "grad_norm": 0.7077950835227966, + "learning_rate": 8.310303987366759e-07, + "loss": 0.482, + "step": 2113 + }, + { + "epoch": 0.8345834978286617, + "grad_norm": 0.6843054890632629, + "learning_rate": 8.290564547966838e-07, + "loss": 0.57, + "step": 2114 + }, + { + "epoch": 0.8349782866166601, + "grad_norm": 0.8527648448944092, + "learning_rate": 8.270825108566917e-07, + "loss": 0.5635, + "step": 2115 + }, + { + "epoch": 0.8353730754046585, + "grad_norm": 0.5836147665977478, + "learning_rate": 8.251085669166996e-07, + "loss": 0.5488, + "step": 2116 + }, + { + "epoch": 0.8357678641926569, + "grad_norm": 0.5809905529022217, + "learning_rate": 8.231346229767076e-07, + "loss": 0.4774, + "step": 2117 + }, + { + "epoch": 0.8361626529806554, + "grad_norm": 1.041106939315796, + "learning_rate": 8.211606790367154e-07, + "loss": 0.5659, + "step": 2118 + }, + { + "epoch": 0.8365574417686538, + "grad_norm": 0.695250928401947, + "learning_rate": 8.191867350967234e-07, + "loss": 0.5917, + "step": 2119 + }, + { + "epoch": 0.8369522305566522, + "grad_norm": 0.7166149616241455, + "learning_rate": 8.172127911567313e-07, + "loss": 0.4969, + "step": 2120 + }, + { + "epoch": 0.8373470193446506, + "grad_norm": 0.8043670654296875, + "learning_rate": 8.152388472167391e-07, + "loss": 0.5473, + "step": 2121 + }, + { + "epoch": 0.837741808132649, + "grad_norm": 0.8031109571456909, + "learning_rate": 8.13264903276747e-07, + "loss": 0.5563, + "step": 2122 + }, + { + "epoch": 0.8381365969206475, + "grad_norm": 0.6665255427360535, + "learning_rate": 8.112909593367549e-07, + "loss": 0.5457, + "step": 2123 + }, + { + "epoch": 0.8385313857086458, + "grad_norm": 0.6723513603210449, + "learning_rate": 8.093170153967627e-07, + "loss": 0.5445, + "step": 2124 + }, + { + "epoch": 0.8389261744966443, + "grad_norm": 0.5083441138267517, + "learning_rate": 8.073430714567706e-07, + "loss": 0.4864, + "step": 2125 + }, + { + "epoch": 0.8393209632846427, + "grad_norm": 0.6642429828643799, + "learning_rate": 8.053691275167786e-07, + "loss": 0.588, + "step": 2126 + }, + { + "epoch": 0.8397157520726412, + "grad_norm": 0.604867160320282, + "learning_rate": 8.033951835767865e-07, + "loss": 0.524, + "step": 2127 + }, + { + "epoch": 0.8401105408606395, + "grad_norm": 0.6647956371307373, + "learning_rate": 8.014212396367944e-07, + "loss": 0.4872, + "step": 2128 + }, + { + "epoch": 0.840505329648638, + "grad_norm": 0.9653178453445435, + "learning_rate": 7.994472956968023e-07, + "loss": 0.6147, + "step": 2129 + }, + { + "epoch": 0.8409001184366364, + "grad_norm": 1.8651771545410156, + "learning_rate": 7.974733517568102e-07, + "loss": 0.5001, + "step": 2130 + }, + { + "epoch": 0.8412949072246348, + "grad_norm": 0.633307158946991, + "learning_rate": 7.954994078168181e-07, + "loss": 0.5058, + "step": 2131 + }, + { + "epoch": 0.8416896960126332, + "grad_norm": 0.6428931355476379, + "learning_rate": 7.93525463876826e-07, + "loss": 0.5866, + "step": 2132 + }, + { + "epoch": 0.8420844848006317, + "grad_norm": 0.6566193699836731, + "learning_rate": 7.915515199368339e-07, + "loss": 0.5198, + "step": 2133 + }, + { + "epoch": 0.8424792735886301, + "grad_norm": 0.5739274621009827, + "learning_rate": 7.895775759968417e-07, + "loss": 0.4833, + "step": 2134 + }, + { + "epoch": 0.8428740623766285, + "grad_norm": 0.6107453107833862, + "learning_rate": 7.876036320568496e-07, + "loss": 0.5474, + "step": 2135 + }, + { + "epoch": 0.8432688511646269, + "grad_norm": 0.708837628364563, + "learning_rate": 7.856296881168575e-07, + "loss": 0.6225, + "step": 2136 + }, + { + "epoch": 0.8436636399526254, + "grad_norm": 0.6807684898376465, + "learning_rate": 7.836557441768653e-07, + "loss": 0.5643, + "step": 2137 + }, + { + "epoch": 0.8440584287406238, + "grad_norm": 0.8731135725975037, + "learning_rate": 7.816818002368734e-07, + "loss": 0.5727, + "step": 2138 + }, + { + "epoch": 0.8444532175286222, + "grad_norm": 0.647262454032898, + "learning_rate": 7.797078562968813e-07, + "loss": 0.5145, + "step": 2139 + }, + { + "epoch": 0.8448480063166206, + "grad_norm": 0.6383690237998962, + "learning_rate": 7.777339123568891e-07, + "loss": 0.5247, + "step": 2140 + }, + { + "epoch": 0.8452427951046191, + "grad_norm": 0.7108294367790222, + "learning_rate": 7.75759968416897e-07, + "loss": 0.5281, + "step": 2141 + }, + { + "epoch": 0.8456375838926175, + "grad_norm": 0.9221882224082947, + "learning_rate": 7.737860244769049e-07, + "loss": 0.576, + "step": 2142 + }, + { + "epoch": 0.8460323726806158, + "grad_norm": 0.6099421381950378, + "learning_rate": 7.718120805369129e-07, + "loss": 0.4731, + "step": 2143 + }, + { + "epoch": 0.8464271614686143, + "grad_norm": 0.6871507167816162, + "learning_rate": 7.698381365969207e-07, + "loss": 0.5784, + "step": 2144 + }, + { + "epoch": 0.8468219502566127, + "grad_norm": 0.6788380742073059, + "learning_rate": 7.678641926569286e-07, + "loss": 0.55, + "step": 2145 + }, + { + "epoch": 0.8472167390446111, + "grad_norm": 0.7680887579917908, + "learning_rate": 7.658902487169365e-07, + "loss": 0.5779, + "step": 2146 + }, + { + "epoch": 0.8476115278326095, + "grad_norm": 0.883102536201477, + "learning_rate": 7.639163047769443e-07, + "loss": 0.55, + "step": 2147 + }, + { + "epoch": 0.848006316620608, + "grad_norm": 0.5846719145774841, + "learning_rate": 7.619423608369524e-07, + "loss": 0.5063, + "step": 2148 + }, + { + "epoch": 0.8484011054086064, + "grad_norm": 0.739219605922699, + "learning_rate": 7.599684168969603e-07, + "loss": 0.5572, + "step": 2149 + }, + { + "epoch": 0.8487958941966048, + "grad_norm": 0.804060697555542, + "learning_rate": 7.579944729569681e-07, + "loss": 0.5729, + "step": 2150 + }, + { + "epoch": 0.8491906829846032, + "grad_norm": 0.7735392451286316, + "learning_rate": 7.56020529016976e-07, + "loss": 0.5414, + "step": 2151 + }, + { + "epoch": 0.8495854717726017, + "grad_norm": 0.6378229260444641, + "learning_rate": 7.540465850769839e-07, + "loss": 0.4781, + "step": 2152 + }, + { + "epoch": 0.8499802605606, + "grad_norm": 0.7861314415931702, + "learning_rate": 7.520726411369917e-07, + "loss": 0.5636, + "step": 2153 + }, + { + "epoch": 0.8503750493485985, + "grad_norm": 1.125550627708435, + "learning_rate": 7.500986971969997e-07, + "loss": 0.5451, + "step": 2154 + }, + { + "epoch": 0.8507698381365969, + "grad_norm": 0.6138797998428345, + "learning_rate": 7.481247532570076e-07, + "loss": 0.5278, + "step": 2155 + }, + { + "epoch": 0.8511646269245954, + "grad_norm": 0.6873497366905212, + "learning_rate": 7.461508093170154e-07, + "loss": 0.5405, + "step": 2156 + }, + { + "epoch": 0.8515594157125937, + "grad_norm": 0.5955731272697449, + "learning_rate": 7.441768653770233e-07, + "loss": 0.4655, + "step": 2157 + }, + { + "epoch": 0.8519542045005922, + "grad_norm": 0.7723181843757629, + "learning_rate": 7.422029214370312e-07, + "loss": 0.5685, + "step": 2158 + }, + { + "epoch": 0.8523489932885906, + "grad_norm": 0.74553382396698, + "learning_rate": 7.402289774970393e-07, + "loss": 0.5221, + "step": 2159 + }, + { + "epoch": 0.8527437820765891, + "grad_norm": 0.6727122664451599, + "learning_rate": 7.382550335570471e-07, + "loss": 0.6093, + "step": 2160 + }, + { + "epoch": 0.8531385708645874, + "grad_norm": 0.7410052418708801, + "learning_rate": 7.36281089617055e-07, + "loss": 0.5354, + "step": 2161 + }, + { + "epoch": 0.8535333596525859, + "grad_norm": 0.684329092502594, + "learning_rate": 7.343071456770629e-07, + "loss": 0.5469, + "step": 2162 + }, + { + "epoch": 0.8539281484405843, + "grad_norm": 0.6406484246253967, + "learning_rate": 7.323332017370707e-07, + "loss": 0.5698, + "step": 2163 + }, + { + "epoch": 0.8543229372285827, + "grad_norm": 0.6341660022735596, + "learning_rate": 7.303592577970786e-07, + "loss": 0.426, + "step": 2164 + }, + { + "epoch": 0.8547177260165811, + "grad_norm": 0.560681164264679, + "learning_rate": 7.283853138570865e-07, + "loss": 0.5262, + "step": 2165 + }, + { + "epoch": 0.8551125148045795, + "grad_norm": 0.5923150181770325, + "learning_rate": 7.264113699170944e-07, + "loss": 0.4765, + "step": 2166 + }, + { + "epoch": 0.855507303592578, + "grad_norm": 0.7510805726051331, + "learning_rate": 7.244374259771023e-07, + "loss": 0.6087, + "step": 2167 + }, + { + "epoch": 0.8559020923805764, + "grad_norm": 0.6852939128875732, + "learning_rate": 7.224634820371102e-07, + "loss": 0.5259, + "step": 2168 + }, + { + "epoch": 0.8562968811685748, + "grad_norm": 0.6657065153121948, + "learning_rate": 7.204895380971181e-07, + "loss": 0.5649, + "step": 2169 + }, + { + "epoch": 0.8566916699565732, + "grad_norm": 0.7868438959121704, + "learning_rate": 7.18515594157126e-07, + "loss": 0.5067, + "step": 2170 + }, + { + "epoch": 0.8570864587445717, + "grad_norm": 0.6441265344619751, + "learning_rate": 7.16541650217134e-07, + "loss": 0.549, + "step": 2171 + }, + { + "epoch": 0.85748124753257, + "grad_norm": 0.7391132116317749, + "learning_rate": 7.145677062771418e-07, + "loss": 0.5778, + "step": 2172 + }, + { + "epoch": 0.8578760363205685, + "grad_norm": 0.6269891262054443, + "learning_rate": 7.125937623371497e-07, + "loss": 0.5084, + "step": 2173 + }, + { + "epoch": 0.8582708251085669, + "grad_norm": 0.7008499503135681, + "learning_rate": 7.106198183971576e-07, + "loss": 0.5703, + "step": 2174 + }, + { + "epoch": 0.8586656138965654, + "grad_norm": 0.7107571363449097, + "learning_rate": 7.086458744571654e-07, + "loss": 0.5746, + "step": 2175 + }, + { + "epoch": 0.8590604026845637, + "grad_norm": 0.5667499303817749, + "learning_rate": 7.066719305171733e-07, + "loss": 0.4791, + "step": 2176 + }, + { + "epoch": 0.8594551914725622, + "grad_norm": 0.5719448328018188, + "learning_rate": 7.046979865771812e-07, + "loss": 0.5134, + "step": 2177 + }, + { + "epoch": 0.8598499802605606, + "grad_norm": 0.665658175945282, + "learning_rate": 7.027240426371891e-07, + "loss": 0.5486, + "step": 2178 + }, + { + "epoch": 0.8602447690485591, + "grad_norm": 0.7255663871765137, + "learning_rate": 7.007500986971971e-07, + "loss": 0.5514, + "step": 2179 + }, + { + "epoch": 0.8606395578365574, + "grad_norm": 0.7340226769447327, + "learning_rate": 6.98776154757205e-07, + "loss": 0.5797, + "step": 2180 + }, + { + "epoch": 0.8610343466245559, + "grad_norm": 0.6052846312522888, + "learning_rate": 6.968022108172129e-07, + "loss": 0.4707, + "step": 2181 + }, + { + "epoch": 0.8614291354125543, + "grad_norm": 0.5885152220726013, + "learning_rate": 6.948282668772207e-07, + "loss": 0.4708, + "step": 2182 + }, + { + "epoch": 0.8618239242005526, + "grad_norm": 0.6804608702659607, + "learning_rate": 6.928543229372287e-07, + "loss": 0.5391, + "step": 2183 + }, + { + "epoch": 0.8622187129885511, + "grad_norm": 0.6031436324119568, + "learning_rate": 6.908803789972366e-07, + "loss": 0.4649, + "step": 2184 + }, + { + "epoch": 0.8626135017765495, + "grad_norm": 0.9794080257415771, + "learning_rate": 6.889064350572444e-07, + "loss": 0.5243, + "step": 2185 + }, + { + "epoch": 0.863008290564548, + "grad_norm": 0.6992178559303284, + "learning_rate": 6.869324911172523e-07, + "loss": 0.5343, + "step": 2186 + }, + { + "epoch": 0.8634030793525463, + "grad_norm": 0.7219116687774658, + "learning_rate": 6.849585471772602e-07, + "loss": 0.5662, + "step": 2187 + }, + { + "epoch": 0.8637978681405448, + "grad_norm": 0.626034677028656, + "learning_rate": 6.82984603237268e-07, + "loss": 0.5247, + "step": 2188 + }, + { + "epoch": 0.8641926569285432, + "grad_norm": 0.8633387684822083, + "learning_rate": 6.81010659297276e-07, + "loss": 0.5347, + "step": 2189 + }, + { + "epoch": 0.8645874457165417, + "grad_norm": 0.6020026206970215, + "learning_rate": 6.79036715357284e-07, + "loss": 0.541, + "step": 2190 + }, + { + "epoch": 0.86498223450454, + "grad_norm": 0.7661065459251404, + "learning_rate": 6.770627714172918e-07, + "loss": 0.5555, + "step": 2191 + }, + { + "epoch": 0.8653770232925385, + "grad_norm": 0.7369532585144043, + "learning_rate": 6.750888274772997e-07, + "loss": 0.5971, + "step": 2192 + }, + { + "epoch": 0.8657718120805369, + "grad_norm": 0.7046823501586914, + "learning_rate": 6.731148835373076e-07, + "loss": 0.5334, + "step": 2193 + }, + { + "epoch": 0.8661666008685354, + "grad_norm": 0.6199171543121338, + "learning_rate": 6.711409395973155e-07, + "loss": 0.4892, + "step": 2194 + }, + { + "epoch": 0.8665613896565337, + "grad_norm": 0.685124933719635, + "learning_rate": 6.691669956573234e-07, + "loss": 0.5683, + "step": 2195 + }, + { + "epoch": 0.8669561784445322, + "grad_norm": 0.6335270404815674, + "learning_rate": 6.671930517173313e-07, + "loss": 0.5377, + "step": 2196 + }, + { + "epoch": 0.8673509672325306, + "grad_norm": 0.723034679889679, + "learning_rate": 6.652191077773391e-07, + "loss": 0.6001, + "step": 2197 + }, + { + "epoch": 0.8677457560205291, + "grad_norm": 0.785228967666626, + "learning_rate": 6.63245163837347e-07, + "loss": 0.5714, + "step": 2198 + }, + { + "epoch": 0.8681405448085274, + "grad_norm": 0.6501197218894958, + "learning_rate": 6.612712198973549e-07, + "loss": 0.5124, + "step": 2199 + }, + { + "epoch": 0.8685353335965259, + "grad_norm": 0.6219085454940796, + "learning_rate": 6.59297275957363e-07, + "loss": 0.5686, + "step": 2200 + }, + { + "epoch": 0.8689301223845243, + "grad_norm": 0.594508171081543, + "learning_rate": 6.573233320173708e-07, + "loss": 0.5335, + "step": 2201 + }, + { + "epoch": 0.8693249111725228, + "grad_norm": 0.762143611907959, + "learning_rate": 6.553493880773787e-07, + "loss": 0.5482, + "step": 2202 + }, + { + "epoch": 0.8697196999605211, + "grad_norm": 0.69218510389328, + "learning_rate": 6.533754441373866e-07, + "loss": 0.5334, + "step": 2203 + }, + { + "epoch": 0.8701144887485195, + "grad_norm": 0.7078151106834412, + "learning_rate": 6.514015001973944e-07, + "loss": 0.5845, + "step": 2204 + }, + { + "epoch": 0.870509277536518, + "grad_norm": 0.5517215728759766, + "learning_rate": 6.494275562574023e-07, + "loss": 0.5087, + "step": 2205 + }, + { + "epoch": 0.8709040663245163, + "grad_norm": 0.7107746005058289, + "learning_rate": 6.474536123174103e-07, + "loss": 0.5517, + "step": 2206 + }, + { + "epoch": 0.8712988551125148, + "grad_norm": 0.6753160953521729, + "learning_rate": 6.454796683774181e-07, + "loss": 0.574, + "step": 2207 + }, + { + "epoch": 0.8716936439005132, + "grad_norm": 0.8064541816711426, + "learning_rate": 6.43505724437426e-07, + "loss": 0.5771, + "step": 2208 + }, + { + "epoch": 0.8720884326885117, + "grad_norm": 0.5903174877166748, + "learning_rate": 6.415317804974339e-07, + "loss": 0.5109, + "step": 2209 + }, + { + "epoch": 0.87248322147651, + "grad_norm": 0.5891028046607971, + "learning_rate": 6.395578365574418e-07, + "loss": 0.5573, + "step": 2210 + }, + { + "epoch": 0.8728780102645085, + "grad_norm": 0.7679726481437683, + "learning_rate": 6.375838926174498e-07, + "loss": 0.6235, + "step": 2211 + }, + { + "epoch": 0.8732727990525069, + "grad_norm": 0.6323354840278625, + "learning_rate": 6.356099486774577e-07, + "loss": 0.5016, + "step": 2212 + }, + { + "epoch": 0.8736675878405054, + "grad_norm": 0.8518285155296326, + "learning_rate": 6.336360047374655e-07, + "loss": 0.5926, + "step": 2213 + }, + { + "epoch": 0.8740623766285037, + "grad_norm": 0.5726081728935242, + "learning_rate": 6.316620607974734e-07, + "loss": 0.562, + "step": 2214 + }, + { + "epoch": 0.8744571654165022, + "grad_norm": 0.5563525557518005, + "learning_rate": 6.296881168574813e-07, + "loss": 0.4861, + "step": 2215 + }, + { + "epoch": 0.8748519542045006, + "grad_norm": 0.7756510972976685, + "learning_rate": 6.277141729174891e-07, + "loss": 0.5891, + "step": 2216 + }, + { + "epoch": 0.875246742992499, + "grad_norm": 0.680072009563446, + "learning_rate": 6.25740228977497e-07, + "loss": 0.5145, + "step": 2217 + }, + { + "epoch": 0.8756415317804974, + "grad_norm": 0.6772300601005554, + "learning_rate": 6.23766285037505e-07, + "loss": 0.4665, + "step": 2218 + }, + { + "epoch": 0.8760363205684959, + "grad_norm": 0.7799654603004456, + "learning_rate": 6.217923410975128e-07, + "loss": 0.5258, + "step": 2219 + }, + { + "epoch": 0.8764311093564943, + "grad_norm": 0.6349869966506958, + "learning_rate": 6.198183971575208e-07, + "loss": 0.5257, + "step": 2220 + }, + { + "epoch": 0.8768258981444927, + "grad_norm": 0.9970679879188538, + "learning_rate": 6.178444532175287e-07, + "loss": 0.569, + "step": 2221 + }, + { + "epoch": 0.8772206869324911, + "grad_norm": 0.6859429478645325, + "learning_rate": 6.158705092775366e-07, + "loss": 0.5103, + "step": 2222 + }, + { + "epoch": 0.8776154757204896, + "grad_norm": 0.7322346568107605, + "learning_rate": 6.138965653375445e-07, + "loss": 0.5946, + "step": 2223 + }, + { + "epoch": 0.878010264508488, + "grad_norm": 0.6161044239997864, + "learning_rate": 6.119226213975524e-07, + "loss": 0.5751, + "step": 2224 + }, + { + "epoch": 0.8784050532964863, + "grad_norm": 0.5629905462265015, + "learning_rate": 6.099486774575603e-07, + "loss": 0.4628, + "step": 2225 + }, + { + "epoch": 0.8787998420844848, + "grad_norm": 0.6612836718559265, + "learning_rate": 6.079747335175681e-07, + "loss": 0.5737, + "step": 2226 + }, + { + "epoch": 0.8791946308724832, + "grad_norm": 0.5811361074447632, + "learning_rate": 6.06000789577576e-07, + "loss": 0.5115, + "step": 2227 + }, + { + "epoch": 0.8795894196604817, + "grad_norm": 0.6818163990974426, + "learning_rate": 6.04026845637584e-07, + "loss": 0.5274, + "step": 2228 + }, + { + "epoch": 0.87998420844848, + "grad_norm": 0.7553676962852478, + "learning_rate": 6.020529016975918e-07, + "loss": 0.6167, + "step": 2229 + }, + { + "epoch": 0.8803789972364785, + "grad_norm": 0.6787428259849548, + "learning_rate": 6.000789577575997e-07, + "loss": 0.5601, + "step": 2230 + }, + { + "epoch": 0.8807737860244769, + "grad_norm": 0.753305971622467, + "learning_rate": 5.981050138176076e-07, + "loss": 0.5487, + "step": 2231 + }, + { + "epoch": 0.8811685748124753, + "grad_norm": 0.8021446466445923, + "learning_rate": 5.961310698776155e-07, + "loss": 0.6082, + "step": 2232 + }, + { + "epoch": 0.8815633636004737, + "grad_norm": 0.7666680812835693, + "learning_rate": 5.941571259376234e-07, + "loss": 0.5776, + "step": 2233 + }, + { + "epoch": 0.8819581523884722, + "grad_norm": 0.5984578728675842, + "learning_rate": 5.921831819976314e-07, + "loss": 0.517, + "step": 2234 + }, + { + "epoch": 0.8823529411764706, + "grad_norm": 0.6500260233879089, + "learning_rate": 5.902092380576392e-07, + "loss": 0.4936, + "step": 2235 + }, + { + "epoch": 0.882747729964469, + "grad_norm": 0.8108259439468384, + "learning_rate": 5.882352941176471e-07, + "loss": 0.5527, + "step": 2236 + }, + { + "epoch": 0.8831425187524674, + "grad_norm": 0.7309831380844116, + "learning_rate": 5.86261350177655e-07, + "loss": 0.5345, + "step": 2237 + }, + { + "epoch": 0.8835373075404659, + "grad_norm": 0.7081683874130249, + "learning_rate": 5.84287406237663e-07, + "loss": 0.5114, + "step": 2238 + }, + { + "epoch": 0.8839320963284643, + "grad_norm": 0.6836078763008118, + "learning_rate": 5.823134622976708e-07, + "loss": 0.5521, + "step": 2239 + }, + { + "epoch": 0.8843268851164627, + "grad_norm": 0.7124300599098206, + "learning_rate": 5.803395183576787e-07, + "loss": 0.6335, + "step": 2240 + }, + { + "epoch": 0.8847216739044611, + "grad_norm": 0.666441798210144, + "learning_rate": 5.783655744176866e-07, + "loss": 0.6254, + "step": 2241 + }, + { + "epoch": 0.8851164626924596, + "grad_norm": 0.6535055637359619, + "learning_rate": 5.763916304776944e-07, + "loss": 0.5079, + "step": 2242 + }, + { + "epoch": 0.885511251480458, + "grad_norm": 0.6872673630714417, + "learning_rate": 5.744176865377024e-07, + "loss": 0.5475, + "step": 2243 + }, + { + "epoch": 0.8859060402684564, + "grad_norm": 0.6362855434417725, + "learning_rate": 5.724437425977103e-07, + "loss": 0.5292, + "step": 2244 + }, + { + "epoch": 0.8863008290564548, + "grad_norm": 0.6271122097969055, + "learning_rate": 5.704697986577181e-07, + "loss": 0.5183, + "step": 2245 + }, + { + "epoch": 0.8866956178444532, + "grad_norm": 0.6928723454475403, + "learning_rate": 5.684958547177261e-07, + "loss": 0.6198, + "step": 2246 + }, + { + "epoch": 0.8870904066324516, + "grad_norm": 0.7407101392745972, + "learning_rate": 5.66521910777734e-07, + "loss": 0.5992, + "step": 2247 + }, + { + "epoch": 0.88748519542045, + "grad_norm": 0.9071176052093506, + "learning_rate": 5.645479668377418e-07, + "loss": 0.6332, + "step": 2248 + }, + { + "epoch": 0.8878799842084485, + "grad_norm": 0.711224377155304, + "learning_rate": 5.625740228977498e-07, + "loss": 0.5202, + "step": 2249 + }, + { + "epoch": 0.8882747729964469, + "grad_norm": 0.6280567049980164, + "learning_rate": 5.606000789577577e-07, + "loss": 0.5193, + "step": 2250 + }, + { + "epoch": 0.8886695617844453, + "grad_norm": 0.6756207346916199, + "learning_rate": 5.586261350177655e-07, + "loss": 0.5755, + "step": 2251 + }, + { + "epoch": 0.8890643505724437, + "grad_norm": 0.7000789642333984, + "learning_rate": 5.566521910777734e-07, + "loss": 0.5073, + "step": 2252 + }, + { + "epoch": 0.8894591393604422, + "grad_norm": 0.635033369064331, + "learning_rate": 5.546782471377813e-07, + "loss": 0.5114, + "step": 2253 + }, + { + "epoch": 0.8898539281484406, + "grad_norm": 0.6982858180999756, + "learning_rate": 5.527043031977892e-07, + "loss": 0.5212, + "step": 2254 + }, + { + "epoch": 0.890248716936439, + "grad_norm": 0.6472845077514648, + "learning_rate": 5.507303592577971e-07, + "loss": 0.5686, + "step": 2255 + }, + { + "epoch": 0.8906435057244374, + "grad_norm": 0.6490532159805298, + "learning_rate": 5.48756415317805e-07, + "loss": 0.5088, + "step": 2256 + }, + { + "epoch": 0.8910382945124359, + "grad_norm": 0.721055805683136, + "learning_rate": 5.46782471377813e-07, + "loss": 0.5385, + "step": 2257 + }, + { + "epoch": 0.8914330833004342, + "grad_norm": 0.6125562191009521, + "learning_rate": 5.448085274378208e-07, + "loss": 0.5497, + "step": 2258 + }, + { + "epoch": 0.8918278720884327, + "grad_norm": 0.7567596435546875, + "learning_rate": 5.428345834978287e-07, + "loss": 0.5836, + "step": 2259 + }, + { + "epoch": 0.8922226608764311, + "grad_norm": 0.7670243978500366, + "learning_rate": 5.408606395578367e-07, + "loss": 0.5405, + "step": 2260 + }, + { + "epoch": 0.8926174496644296, + "grad_norm": 0.6801192760467529, + "learning_rate": 5.388866956178445e-07, + "loss": 0.5544, + "step": 2261 + }, + { + "epoch": 0.8930122384524279, + "grad_norm": 0.7059129476547241, + "learning_rate": 5.369127516778524e-07, + "loss": 0.5744, + "step": 2262 + }, + { + "epoch": 0.8934070272404264, + "grad_norm": 0.6809226870536804, + "learning_rate": 5.349388077378603e-07, + "loss": 0.5886, + "step": 2263 + }, + { + "epoch": 0.8938018160284248, + "grad_norm": 0.8368067145347595, + "learning_rate": 5.329648637978682e-07, + "loss": 0.593, + "step": 2264 + }, + { + "epoch": 0.8941966048164233, + "grad_norm": 0.6611719131469727, + "learning_rate": 5.309909198578761e-07, + "loss": 0.5468, + "step": 2265 + }, + { + "epoch": 0.8945913936044216, + "grad_norm": 0.8046811819076538, + "learning_rate": 5.29016975917884e-07, + "loss": 0.6064, + "step": 2266 + }, + { + "epoch": 0.89498618239242, + "grad_norm": 0.6952224373817444, + "learning_rate": 5.270430319778918e-07, + "loss": 0.5965, + "step": 2267 + }, + { + "epoch": 0.8953809711804185, + "grad_norm": 0.6325015425682068, + "learning_rate": 5.250690880378997e-07, + "loss": 0.5647, + "step": 2268 + }, + { + "epoch": 0.8957757599684169, + "grad_norm": 0.6502445340156555, + "learning_rate": 5.230951440979077e-07, + "loss": 0.5213, + "step": 2269 + }, + { + "epoch": 0.8961705487564153, + "grad_norm": 0.67838054895401, + "learning_rate": 5.211212001579155e-07, + "loss": 0.5371, + "step": 2270 + }, + { + "epoch": 0.8965653375444137, + "grad_norm": 0.6395519375801086, + "learning_rate": 5.191472562179235e-07, + "loss": 0.5311, + "step": 2271 + }, + { + "epoch": 0.8969601263324122, + "grad_norm": 0.73374342918396, + "learning_rate": 5.171733122779314e-07, + "loss": 0.5792, + "step": 2272 + }, + { + "epoch": 0.8973549151204105, + "grad_norm": 0.6038732528686523, + "learning_rate": 5.151993683379392e-07, + "loss": 0.5298, + "step": 2273 + }, + { + "epoch": 0.897749703908409, + "grad_norm": 0.6702163815498352, + "learning_rate": 5.132254243979471e-07, + "loss": 0.5874, + "step": 2274 + }, + { + "epoch": 0.8981444926964074, + "grad_norm": 0.6853083968162537, + "learning_rate": 5.112514804579551e-07, + "loss": 0.5676, + "step": 2275 + }, + { + "epoch": 0.8985392814844059, + "grad_norm": 0.6188691854476929, + "learning_rate": 5.09277536517963e-07, + "loss": 0.5581, + "step": 2276 + }, + { + "epoch": 0.8989340702724042, + "grad_norm": 0.7021827697753906, + "learning_rate": 5.073035925779708e-07, + "loss": 0.5201, + "step": 2277 + }, + { + "epoch": 0.8993288590604027, + "grad_norm": 0.5914571285247803, + "learning_rate": 5.053296486379787e-07, + "loss": 0.4875, + "step": 2278 + }, + { + "epoch": 0.8997236478484011, + "grad_norm": 0.7975223660469055, + "learning_rate": 5.033557046979866e-07, + "loss": 0.5666, + "step": 2279 + }, + { + "epoch": 0.9001184366363996, + "grad_norm": 0.7353789806365967, + "learning_rate": 5.013817607579945e-07, + "loss": 0.5685, + "step": 2280 + }, + { + "epoch": 0.9005132254243979, + "grad_norm": 0.5935133695602417, + "learning_rate": 4.994078168180024e-07, + "loss": 0.4592, + "step": 2281 + }, + { + "epoch": 0.9009080142123964, + "grad_norm": 0.7251344919204712, + "learning_rate": 4.974338728780103e-07, + "loss": 0.5249, + "step": 2282 + }, + { + "epoch": 0.9013028030003948, + "grad_norm": 0.6595778465270996, + "learning_rate": 4.954599289380182e-07, + "loss": 0.606, + "step": 2283 + }, + { + "epoch": 0.9016975917883933, + "grad_norm": 0.6252221465110779, + "learning_rate": 4.934859849980261e-07, + "loss": 0.5605, + "step": 2284 + }, + { + "epoch": 0.9020923805763916, + "grad_norm": 0.7759472727775574, + "learning_rate": 4.915120410580341e-07, + "loss": 0.5345, + "step": 2285 + }, + { + "epoch": 0.90248716936439, + "grad_norm": 0.8137644529342651, + "learning_rate": 4.895380971180419e-07, + "loss": 0.5797, + "step": 2286 + }, + { + "epoch": 0.9028819581523885, + "grad_norm": 0.7750760316848755, + "learning_rate": 4.875641531780498e-07, + "loss": 0.5586, + "step": 2287 + }, + { + "epoch": 0.9032767469403868, + "grad_norm": 0.6644168496131897, + "learning_rate": 4.855902092380577e-07, + "loss": 0.5758, + "step": 2288 + }, + { + "epoch": 0.9036715357283853, + "grad_norm": 0.8084530830383301, + "learning_rate": 4.836162652980655e-07, + "loss": 0.5383, + "step": 2289 + }, + { + "epoch": 0.9040663245163837, + "grad_norm": 0.5593348741531372, + "learning_rate": 4.816423213580735e-07, + "loss": 0.55, + "step": 2290 + }, + { + "epoch": 0.9044611133043822, + "grad_norm": 0.601047694683075, + "learning_rate": 4.796683774180814e-07, + "loss": 0.5101, + "step": 2291 + }, + { + "epoch": 0.9048559020923805, + "grad_norm": 0.6981596946716309, + "learning_rate": 4.776944334780892e-07, + "loss": 0.5794, + "step": 2292 + }, + { + "epoch": 0.905250690880379, + "grad_norm": 0.5361005067825317, + "learning_rate": 4.7572048953809716e-07, + "loss": 0.4956, + "step": 2293 + }, + { + "epoch": 0.9056454796683774, + "grad_norm": 0.9282245635986328, + "learning_rate": 4.7374654559810503e-07, + "loss": 0.5432, + "step": 2294 + }, + { + "epoch": 0.9060402684563759, + "grad_norm": 0.6658674478530884, + "learning_rate": 4.71772601658113e-07, + "loss": 0.5703, + "step": 2295 + }, + { + "epoch": 0.9064350572443742, + "grad_norm": 0.6192303895950317, + "learning_rate": 4.6979865771812087e-07, + "loss": 0.5075, + "step": 2296 + }, + { + "epoch": 0.9068298460323727, + "grad_norm": 0.7384130954742432, + "learning_rate": 4.6782471377812874e-07, + "loss": 0.5532, + "step": 2297 + }, + { + "epoch": 0.9072246348203711, + "grad_norm": 0.7708972096443176, + "learning_rate": 4.658507698381366e-07, + "loss": 0.6097, + "step": 2298 + }, + { + "epoch": 0.9076194236083696, + "grad_norm": 0.9724142551422119, + "learning_rate": 4.638768258981445e-07, + "loss": 0.5589, + "step": 2299 + }, + { + "epoch": 0.9080142123963679, + "grad_norm": 0.8201656341552734, + "learning_rate": 4.6190288195815244e-07, + "loss": 0.5988, + "step": 2300 + }, + { + "epoch": 0.9084090011843664, + "grad_norm": 0.5238615870475769, + "learning_rate": 4.5992893801816036e-07, + "loss": 0.4822, + "step": 2301 + }, + { + "epoch": 0.9088037899723648, + "grad_norm": 0.6995232701301575, + "learning_rate": 4.5795499407816823e-07, + "loss": 0.522, + "step": 2302 + }, + { + "epoch": 0.9091985787603633, + "grad_norm": 0.6782302856445312, + "learning_rate": 4.559810501381761e-07, + "loss": 0.5455, + "step": 2303 + }, + { + "epoch": 0.9095933675483616, + "grad_norm": 0.5869399905204773, + "learning_rate": 4.5400710619818396e-07, + "loss": 0.5053, + "step": 2304 + }, + { + "epoch": 0.9099881563363601, + "grad_norm": 0.733551561832428, + "learning_rate": 4.5203316225819194e-07, + "loss": 0.5308, + "step": 2305 + }, + { + "epoch": 0.9103829451243585, + "grad_norm": 0.7993149161338806, + "learning_rate": 4.500592183181998e-07, + "loss": 0.5732, + "step": 2306 + }, + { + "epoch": 0.9107777339123568, + "grad_norm": 0.718228280544281, + "learning_rate": 4.480852743782077e-07, + "loss": 0.4867, + "step": 2307 + }, + { + "epoch": 0.9111725227003553, + "grad_norm": 0.7124208211898804, + "learning_rate": 4.461113304382156e-07, + "loss": 0.5302, + "step": 2308 + }, + { + "epoch": 0.9115673114883537, + "grad_norm": 0.7246851325035095, + "learning_rate": 4.4413738649822346e-07, + "loss": 0.5259, + "step": 2309 + }, + { + "epoch": 0.9119621002763522, + "grad_norm": 0.6590450406074524, + "learning_rate": 4.421634425582313e-07, + "loss": 0.5842, + "step": 2310 + }, + { + "epoch": 0.9123568890643505, + "grad_norm": 0.6214744448661804, + "learning_rate": 4.401894986182393e-07, + "loss": 0.5383, + "step": 2311 + }, + { + "epoch": 0.912751677852349, + "grad_norm": 0.6390805840492249, + "learning_rate": 4.3821555467824716e-07, + "loss": 0.5477, + "step": 2312 + }, + { + "epoch": 0.9131464666403474, + "grad_norm": 0.6669002771377563, + "learning_rate": 4.362416107382551e-07, + "loss": 0.5924, + "step": 2313 + }, + { + "epoch": 0.9135412554283459, + "grad_norm": 0.6265949010848999, + "learning_rate": 4.3426766679826295e-07, + "loss": 0.5525, + "step": 2314 + }, + { + "epoch": 0.9139360442163442, + "grad_norm": 0.6126975417137146, + "learning_rate": 4.322937228582708e-07, + "loss": 0.4631, + "step": 2315 + }, + { + "epoch": 0.9143308330043427, + "grad_norm": 0.6640539765357971, + "learning_rate": 4.303197789182788e-07, + "loss": 0.5548, + "step": 2316 + }, + { + "epoch": 0.9147256217923411, + "grad_norm": 0.8621968626976013, + "learning_rate": 4.2834583497828665e-07, + "loss": 0.6333, + "step": 2317 + }, + { + "epoch": 0.9151204105803395, + "grad_norm": 0.7150605320930481, + "learning_rate": 4.263718910382945e-07, + "loss": 0.5912, + "step": 2318 + }, + { + "epoch": 0.9155151993683379, + "grad_norm": 0.8427056670188904, + "learning_rate": 4.2439794709830244e-07, + "loss": 0.6161, + "step": 2319 + }, + { + "epoch": 0.9159099881563364, + "grad_norm": 0.6395319104194641, + "learning_rate": 4.224240031583103e-07, + "loss": 0.5154, + "step": 2320 + }, + { + "epoch": 0.9163047769443348, + "grad_norm": 0.6437375545501709, + "learning_rate": 4.204500592183183e-07, + "loss": 0.5031, + "step": 2321 + }, + { + "epoch": 0.9166995657323332, + "grad_norm": 0.8011043071746826, + "learning_rate": 4.1847611527832615e-07, + "loss": 0.589, + "step": 2322 + }, + { + "epoch": 0.9170943545203316, + "grad_norm": 0.8008151650428772, + "learning_rate": 4.16502171338334e-07, + "loss": 0.6283, + "step": 2323 + }, + { + "epoch": 0.9174891433083301, + "grad_norm": 0.8507754802703857, + "learning_rate": 4.145282273983419e-07, + "loss": 0.5731, + "step": 2324 + }, + { + "epoch": 0.9178839320963285, + "grad_norm": 1.1530799865722656, + "learning_rate": 4.125542834583498e-07, + "loss": 0.5883, + "step": 2325 + }, + { + "epoch": 0.9182787208843269, + "grad_norm": 0.6311620473861694, + "learning_rate": 4.105803395183577e-07, + "loss": 0.4961, + "step": 2326 + }, + { + "epoch": 0.9186735096723253, + "grad_norm": 0.8379600048065186, + "learning_rate": 4.0860639557836564e-07, + "loss": 0.6198, + "step": 2327 + }, + { + "epoch": 0.9190682984603237, + "grad_norm": 0.7047327756881714, + "learning_rate": 4.066324516383735e-07, + "loss": 0.5826, + "step": 2328 + }, + { + "epoch": 0.9194630872483222, + "grad_norm": 0.6738960146903992, + "learning_rate": 4.046585076983814e-07, + "loss": 0.5754, + "step": 2329 + }, + { + "epoch": 0.9198578760363205, + "grad_norm": 0.602218747138977, + "learning_rate": 4.026845637583893e-07, + "loss": 0.5142, + "step": 2330 + }, + { + "epoch": 0.920252664824319, + "grad_norm": 0.7076849937438965, + "learning_rate": 4.007106198183972e-07, + "loss": 0.5587, + "step": 2331 + }, + { + "epoch": 0.9206474536123174, + "grad_norm": 0.6024356484413147, + "learning_rate": 3.987366758784051e-07, + "loss": 0.5499, + "step": 2332 + }, + { + "epoch": 0.9210422424003158, + "grad_norm": 0.5799064636230469, + "learning_rate": 3.96762731938413e-07, + "loss": 0.4935, + "step": 2333 + }, + { + "epoch": 0.9214370311883142, + "grad_norm": 0.634414553642273, + "learning_rate": 3.9478878799842087e-07, + "loss": 0.5759, + "step": 2334 + }, + { + "epoch": 0.9218318199763127, + "grad_norm": 0.8074020147323608, + "learning_rate": 3.9281484405842873e-07, + "loss": 0.6306, + "step": 2335 + }, + { + "epoch": 0.9222266087643111, + "grad_norm": 0.7681320309638977, + "learning_rate": 3.908409001184367e-07, + "loss": 0.5391, + "step": 2336 + }, + { + "epoch": 0.9226213975523095, + "grad_norm": 0.690470278263092, + "learning_rate": 3.8886695617844457e-07, + "loss": 0.5608, + "step": 2337 + }, + { + "epoch": 0.9230161863403079, + "grad_norm": 0.9998036026954651, + "learning_rate": 3.8689301223845244e-07, + "loss": 0.5396, + "step": 2338 + }, + { + "epoch": 0.9234109751283064, + "grad_norm": 0.7204393148422241, + "learning_rate": 3.8491906829846036e-07, + "loss": 0.6364, + "step": 2339 + }, + { + "epoch": 0.9238057639163048, + "grad_norm": 0.6767198443412781, + "learning_rate": 3.829451243584682e-07, + "loss": 0.5633, + "step": 2340 + }, + { + "epoch": 0.9242005527043032, + "grad_norm": 0.6745386123657227, + "learning_rate": 3.809711804184762e-07, + "loss": 0.6348, + "step": 2341 + }, + { + "epoch": 0.9245953414923016, + "grad_norm": 0.7909767627716064, + "learning_rate": 3.7899723647848407e-07, + "loss": 0.5171, + "step": 2342 + }, + { + "epoch": 0.9249901302803001, + "grad_norm": 0.7122387886047363, + "learning_rate": 3.7702329253849193e-07, + "loss": 0.6192, + "step": 2343 + }, + { + "epoch": 0.9253849190682985, + "grad_norm": 0.674788236618042, + "learning_rate": 3.7504934859849985e-07, + "loss": 0.583, + "step": 2344 + }, + { + "epoch": 0.9257797078562969, + "grad_norm": 0.7317351698875427, + "learning_rate": 3.730754046585077e-07, + "loss": 0.5703, + "step": 2345 + }, + { + "epoch": 0.9261744966442953, + "grad_norm": 0.7465486526489258, + "learning_rate": 3.711014607185156e-07, + "loss": 0.6087, + "step": 2346 + }, + { + "epoch": 0.9265692854322938, + "grad_norm": 0.5640500783920288, + "learning_rate": 3.6912751677852356e-07, + "loss": 0.4929, + "step": 2347 + }, + { + "epoch": 0.9269640742202921, + "grad_norm": 0.8494970202445984, + "learning_rate": 3.671535728385314e-07, + "loss": 0.6243, + "step": 2348 + }, + { + "epoch": 0.9273588630082905, + "grad_norm": 0.9254979491233826, + "learning_rate": 3.651796288985393e-07, + "loss": 0.6071, + "step": 2349 + }, + { + "epoch": 0.927753651796289, + "grad_norm": 0.5747636556625366, + "learning_rate": 3.632056849585472e-07, + "loss": 0.544, + "step": 2350 + }, + { + "epoch": 0.9281484405842874, + "grad_norm": 0.7010864019393921, + "learning_rate": 3.612317410185551e-07, + "loss": 0.5715, + "step": 2351 + }, + { + "epoch": 0.9285432293722858, + "grad_norm": 0.7205281853675842, + "learning_rate": 3.59257797078563e-07, + "loss": 0.5193, + "step": 2352 + }, + { + "epoch": 0.9289380181602842, + "grad_norm": 0.923243522644043, + "learning_rate": 3.572838531385709e-07, + "loss": 0.5926, + "step": 2353 + }, + { + "epoch": 0.9293328069482827, + "grad_norm": 0.7773244976997375, + "learning_rate": 3.553099091985788e-07, + "loss": 0.6072, + "step": 2354 + }, + { + "epoch": 0.929727595736281, + "grad_norm": 0.6552662253379822, + "learning_rate": 3.5333596525858665e-07, + "loss": 0.4712, + "step": 2355 + }, + { + "epoch": 0.9301223845242795, + "grad_norm": 0.7168061137199402, + "learning_rate": 3.5136202131859457e-07, + "loss": 0.6043, + "step": 2356 + }, + { + "epoch": 0.9305171733122779, + "grad_norm": 0.8168758749961853, + "learning_rate": 3.493880773786025e-07, + "loss": 0.5996, + "step": 2357 + }, + { + "epoch": 0.9309119621002764, + "grad_norm": 0.7800599932670593, + "learning_rate": 3.4741413343861036e-07, + "loss": 0.5567, + "step": 2358 + }, + { + "epoch": 0.9313067508882747, + "grad_norm": 0.6038302779197693, + "learning_rate": 3.454401894986183e-07, + "loss": 0.5302, + "step": 2359 + }, + { + "epoch": 0.9317015396762732, + "grad_norm": 0.717754065990448, + "learning_rate": 3.4346624555862615e-07, + "loss": 0.7018, + "step": 2360 + }, + { + "epoch": 0.9320963284642716, + "grad_norm": 0.759384274482727, + "learning_rate": 3.41492301618634e-07, + "loss": 0.6158, + "step": 2361 + }, + { + "epoch": 0.9324911172522701, + "grad_norm": 0.7007467150688171, + "learning_rate": 3.39518357678642e-07, + "loss": 0.5888, + "step": 2362 + }, + { + "epoch": 0.9328859060402684, + "grad_norm": 0.6448672413825989, + "learning_rate": 3.3754441373864985e-07, + "loss": 0.5788, + "step": 2363 + }, + { + "epoch": 0.9332806948282669, + "grad_norm": 0.6561088562011719, + "learning_rate": 3.3557046979865777e-07, + "loss": 0.5831, + "step": 2364 + }, + { + "epoch": 0.9336754836162653, + "grad_norm": 0.6319699883460999, + "learning_rate": 3.3359652585866564e-07, + "loss": 0.6065, + "step": 2365 + }, + { + "epoch": 0.9340702724042638, + "grad_norm": 0.8462998270988464, + "learning_rate": 3.316225819186735e-07, + "loss": 0.6206, + "step": 2366 + }, + { + "epoch": 0.9344650611922621, + "grad_norm": 0.6736757159233093, + "learning_rate": 3.296486379786815e-07, + "loss": 0.5601, + "step": 2367 + }, + { + "epoch": 0.9348598499802606, + "grad_norm": 0.5784498453140259, + "learning_rate": 3.2767469403868934e-07, + "loss": 0.4705, + "step": 2368 + }, + { + "epoch": 0.935254638768259, + "grad_norm": 0.6324255466461182, + "learning_rate": 3.257007500986972e-07, + "loss": 0.5496, + "step": 2369 + }, + { + "epoch": 0.9356494275562574, + "grad_norm": 0.615319013595581, + "learning_rate": 3.2372680615870513e-07, + "loss": 0.5403, + "step": 2370 + }, + { + "epoch": 0.9360442163442558, + "grad_norm": 0.5836330056190491, + "learning_rate": 3.21752862218713e-07, + "loss": 0.5542, + "step": 2371 + }, + { + "epoch": 0.9364390051322542, + "grad_norm": 0.7345790266990662, + "learning_rate": 3.197789182787209e-07, + "loss": 0.5646, + "step": 2372 + }, + { + "epoch": 0.9368337939202527, + "grad_norm": 0.588121235370636, + "learning_rate": 3.1780497433872884e-07, + "loss": 0.5216, + "step": 2373 + }, + { + "epoch": 0.937228582708251, + "grad_norm": 0.6957311630249023, + "learning_rate": 3.158310303987367e-07, + "loss": 0.5818, + "step": 2374 + }, + { + "epoch": 0.9376233714962495, + "grad_norm": 0.7051143646240234, + "learning_rate": 3.1385708645874457e-07, + "loss": 0.4932, + "step": 2375 + }, + { + "epoch": 0.9380181602842479, + "grad_norm": 0.7232518196105957, + "learning_rate": 3.118831425187525e-07, + "loss": 0.5783, + "step": 2376 + }, + { + "epoch": 0.9384129490722464, + "grad_norm": 0.8059953451156616, + "learning_rate": 3.099091985787604e-07, + "loss": 0.576, + "step": 2377 + }, + { + "epoch": 0.9388077378602447, + "grad_norm": 0.7519161701202393, + "learning_rate": 3.079352546387683e-07, + "loss": 0.6254, + "step": 2378 + }, + { + "epoch": 0.9392025266482432, + "grad_norm": 0.6647464632987976, + "learning_rate": 3.059613106987762e-07, + "loss": 0.5528, + "step": 2379 + }, + { + "epoch": 0.9395973154362416, + "grad_norm": 0.6570882201194763, + "learning_rate": 3.0398736675878406e-07, + "loss": 0.4981, + "step": 2380 + }, + { + "epoch": 0.9399921042242401, + "grad_norm": 0.6404784917831421, + "learning_rate": 3.02013422818792e-07, + "loss": 0.5867, + "step": 2381 + }, + { + "epoch": 0.9403868930122384, + "grad_norm": 0.7689688205718994, + "learning_rate": 3.0003947887879985e-07, + "loss": 0.6175, + "step": 2382 + }, + { + "epoch": 0.9407816818002369, + "grad_norm": 0.6754779815673828, + "learning_rate": 2.9806553493880777e-07, + "loss": 0.5252, + "step": 2383 + }, + { + "epoch": 0.9411764705882353, + "grad_norm": 0.5782623887062073, + "learning_rate": 2.960915909988157e-07, + "loss": 0.4944, + "step": 2384 + }, + { + "epoch": 0.9415712593762338, + "grad_norm": 0.618755042552948, + "learning_rate": 2.9411764705882356e-07, + "loss": 0.5548, + "step": 2385 + }, + { + "epoch": 0.9419660481642321, + "grad_norm": 0.7932008504867554, + "learning_rate": 2.921437031188315e-07, + "loss": 0.6182, + "step": 2386 + }, + { + "epoch": 0.9423608369522306, + "grad_norm": 0.6160772442817688, + "learning_rate": 2.9016975917883934e-07, + "loss": 0.568, + "step": 2387 + }, + { + "epoch": 0.942755625740229, + "grad_norm": 0.6796038746833801, + "learning_rate": 2.881958152388472e-07, + "loss": 0.6227, + "step": 2388 + }, + { + "epoch": 0.9431504145282273, + "grad_norm": 0.6690921783447266, + "learning_rate": 2.8622187129885513e-07, + "loss": 0.5939, + "step": 2389 + }, + { + "epoch": 0.9435452033162258, + "grad_norm": 0.9586527943611145, + "learning_rate": 2.8424792735886305e-07, + "loss": 0.5751, + "step": 2390 + }, + { + "epoch": 0.9439399921042242, + "grad_norm": 0.5985625386238098, + "learning_rate": 2.822739834188709e-07, + "loss": 0.5823, + "step": 2391 + }, + { + "epoch": 0.9443347808922227, + "grad_norm": 0.9316598773002625, + "learning_rate": 2.8030003947887884e-07, + "loss": 0.6671, + "step": 2392 + }, + { + "epoch": 0.944729569680221, + "grad_norm": 0.6819871068000793, + "learning_rate": 2.783260955388867e-07, + "loss": 0.5795, + "step": 2393 + }, + { + "epoch": 0.9451243584682195, + "grad_norm": 0.6833275556564331, + "learning_rate": 2.763521515988946e-07, + "loss": 0.5554, + "step": 2394 + }, + { + "epoch": 0.9455191472562179, + "grad_norm": 0.7527327537536621, + "learning_rate": 2.743782076589025e-07, + "loss": 0.5916, + "step": 2395 + }, + { + "epoch": 0.9459139360442164, + "grad_norm": 0.9592670202255249, + "learning_rate": 2.724042637189104e-07, + "loss": 0.6874, + "step": 2396 + }, + { + "epoch": 0.9463087248322147, + "grad_norm": 0.6970340609550476, + "learning_rate": 2.7043031977891833e-07, + "loss": 0.6032, + "step": 2397 + }, + { + "epoch": 0.9467035136202132, + "grad_norm": 0.6741743683815002, + "learning_rate": 2.684563758389262e-07, + "loss": 0.5304, + "step": 2398 + }, + { + "epoch": 0.9470983024082116, + "grad_norm": 0.8310311436653137, + "learning_rate": 2.664824318989341e-07, + "loss": 0.5994, + "step": 2399 + }, + { + "epoch": 0.9474930911962101, + "grad_norm": 0.6389337778091431, + "learning_rate": 2.64508487958942e-07, + "loss": 0.5892, + "step": 2400 + }, + { + "epoch": 0.9478878799842084, + "grad_norm": 0.7394595146179199, + "learning_rate": 2.6253454401894985e-07, + "loss": 0.5502, + "step": 2401 + }, + { + "epoch": 0.9482826687722069, + "grad_norm": 0.7215089797973633, + "learning_rate": 2.6056060007895777e-07, + "loss": 0.6119, + "step": 2402 + }, + { + "epoch": 0.9486774575602053, + "grad_norm": 0.6652763485908508, + "learning_rate": 2.585866561389657e-07, + "loss": 0.5503, + "step": 2403 + }, + { + "epoch": 0.9490722463482038, + "grad_norm": 0.6257871985435486, + "learning_rate": 2.5661271219897356e-07, + "loss": 0.5069, + "step": 2404 + }, + { + "epoch": 0.9494670351362021, + "grad_norm": 0.6563241481781006, + "learning_rate": 2.546387682589815e-07, + "loss": 0.5732, + "step": 2405 + }, + { + "epoch": 0.9498618239242006, + "grad_norm": 0.8282145261764526, + "learning_rate": 2.5266482431898934e-07, + "loss": 0.5823, + "step": 2406 + }, + { + "epoch": 0.950256612712199, + "grad_norm": 0.9526405930519104, + "learning_rate": 2.5069088037899726e-07, + "loss": 0.6216, + "step": 2407 + }, + { + "epoch": 0.9506514015001974, + "grad_norm": 0.6744877696037292, + "learning_rate": 2.4871693643900513e-07, + "loss": 0.5465, + "step": 2408 + }, + { + "epoch": 0.9510461902881958, + "grad_norm": 0.732859194278717, + "learning_rate": 2.4674299249901305e-07, + "loss": 0.5472, + "step": 2409 + }, + { + "epoch": 0.9514409790761942, + "grad_norm": 0.6557504534721375, + "learning_rate": 2.4476904855902097e-07, + "loss": 0.5599, + "step": 2410 + }, + { + "epoch": 0.9518357678641927, + "grad_norm": 0.7623392939567566, + "learning_rate": 2.4279510461902883e-07, + "loss": 0.5643, + "step": 2411 + }, + { + "epoch": 0.952230556652191, + "grad_norm": 0.6383155584335327, + "learning_rate": 2.4082116067903675e-07, + "loss": 0.5417, + "step": 2412 + }, + { + "epoch": 0.9526253454401895, + "grad_norm": 0.6369761824607849, + "learning_rate": 2.388472167390446e-07, + "loss": 0.4816, + "step": 2413 + }, + { + "epoch": 0.9530201342281879, + "grad_norm": 0.6844856142997742, + "learning_rate": 2.3687327279905251e-07, + "loss": 0.6048, + "step": 2414 + }, + { + "epoch": 0.9534149230161864, + "grad_norm": 0.8149580955505371, + "learning_rate": 2.3489932885906043e-07, + "loss": 0.5797, + "step": 2415 + }, + { + "epoch": 0.9538097118041847, + "grad_norm": 0.7205204963684082, + "learning_rate": 2.329253849190683e-07, + "loss": 0.6373, + "step": 2416 + }, + { + "epoch": 0.9542045005921832, + "grad_norm": 0.7323193550109863, + "learning_rate": 2.3095144097907622e-07, + "loss": 0.5671, + "step": 2417 + }, + { + "epoch": 0.9545992893801816, + "grad_norm": 0.6017329096794128, + "learning_rate": 2.2897749703908411e-07, + "loss": 0.517, + "step": 2418 + }, + { + "epoch": 0.95499407816818, + "grad_norm": 0.862851083278656, + "learning_rate": 2.2700355309909198e-07, + "loss": 0.66, + "step": 2419 + }, + { + "epoch": 0.9553888669561784, + "grad_norm": 0.5692169070243835, + "learning_rate": 2.250296091590999e-07, + "loss": 0.5526, + "step": 2420 + }, + { + "epoch": 0.9557836557441769, + "grad_norm": 0.7350135445594788, + "learning_rate": 2.230556652191078e-07, + "loss": 0.4983, + "step": 2421 + }, + { + "epoch": 0.9561784445321753, + "grad_norm": 0.6356835961341858, + "learning_rate": 2.2108172127911566e-07, + "loss": 0.539, + "step": 2422 + }, + { + "epoch": 0.9565732333201737, + "grad_norm": 1.0766633749008179, + "learning_rate": 2.1910777733912358e-07, + "loss": 0.5557, + "step": 2423 + }, + { + "epoch": 0.9569680221081721, + "grad_norm": 0.8792092204093933, + "learning_rate": 2.1713383339913147e-07, + "loss": 0.5752, + "step": 2424 + }, + { + "epoch": 0.9573628108961706, + "grad_norm": 0.9701594710350037, + "learning_rate": 2.151598894591394e-07, + "loss": 0.6643, + "step": 2425 + }, + { + "epoch": 0.957757599684169, + "grad_norm": 0.7607301473617554, + "learning_rate": 2.1318594551914726e-07, + "loss": 0.5963, + "step": 2426 + }, + { + "epoch": 0.9581523884721674, + "grad_norm": 0.6467885375022888, + "learning_rate": 2.1121200157915515e-07, + "loss": 0.5999, + "step": 2427 + }, + { + "epoch": 0.9585471772601658, + "grad_norm": 0.5686421394348145, + "learning_rate": 2.0923805763916307e-07, + "loss": 0.5524, + "step": 2428 + }, + { + "epoch": 0.9589419660481643, + "grad_norm": 0.6834062337875366, + "learning_rate": 2.0726411369917094e-07, + "loss": 0.5865, + "step": 2429 + }, + { + "epoch": 0.9593367548361627, + "grad_norm": 0.7666902542114258, + "learning_rate": 2.0529016975917886e-07, + "loss": 0.6458, + "step": 2430 + }, + { + "epoch": 0.959731543624161, + "grad_norm": 0.7442139387130737, + "learning_rate": 2.0331622581918675e-07, + "loss": 0.5902, + "step": 2431 + }, + { + "epoch": 0.9601263324121595, + "grad_norm": 0.6747311353683472, + "learning_rate": 2.0134228187919465e-07, + "loss": 0.5947, + "step": 2432 + }, + { + "epoch": 0.9605211212001579, + "grad_norm": 0.648018479347229, + "learning_rate": 1.9936833793920254e-07, + "loss": 0.5705, + "step": 2433 + }, + { + "epoch": 0.9609159099881563, + "grad_norm": 0.8742552399635315, + "learning_rate": 1.9739439399921043e-07, + "loss": 0.6682, + "step": 2434 + }, + { + "epoch": 0.9613106987761547, + "grad_norm": 0.7133161425590515, + "learning_rate": 1.9542045005921835e-07, + "loss": 0.5692, + "step": 2435 + }, + { + "epoch": 0.9617054875641532, + "grad_norm": 1.2091143131256104, + "learning_rate": 1.9344650611922622e-07, + "loss": 0.6154, + "step": 2436 + }, + { + "epoch": 0.9621002763521516, + "grad_norm": 0.5332632064819336, + "learning_rate": 1.914725621792341e-07, + "loss": 0.5319, + "step": 2437 + }, + { + "epoch": 0.96249506514015, + "grad_norm": 0.6913630366325378, + "learning_rate": 1.8949861823924203e-07, + "loss": 0.5775, + "step": 2438 + }, + { + "epoch": 0.9628898539281484, + "grad_norm": 0.8432965874671936, + "learning_rate": 1.8752467429924993e-07, + "loss": 0.5565, + "step": 2439 + }, + { + "epoch": 0.9632846427161469, + "grad_norm": 0.7513471841812134, + "learning_rate": 1.855507303592578e-07, + "loss": 0.5682, + "step": 2440 + }, + { + "epoch": 0.9636794315041453, + "grad_norm": 0.6753767728805542, + "learning_rate": 1.835767864192657e-07, + "loss": 0.6205, + "step": 2441 + }, + { + "epoch": 0.9640742202921437, + "grad_norm": 0.6421536207199097, + "learning_rate": 1.816028424792736e-07, + "loss": 0.6005, + "step": 2442 + }, + { + "epoch": 0.9644690090801421, + "grad_norm": 0.9739588499069214, + "learning_rate": 1.796288985392815e-07, + "loss": 0.6768, + "step": 2443 + }, + { + "epoch": 0.9648637978681406, + "grad_norm": 0.8456331491470337, + "learning_rate": 1.776549545992894e-07, + "loss": 0.614, + "step": 2444 + }, + { + "epoch": 0.965258586656139, + "grad_norm": 0.7423616051673889, + "learning_rate": 1.7568101065929729e-07, + "loss": 0.6344, + "step": 2445 + }, + { + "epoch": 0.9656533754441374, + "grad_norm": 0.6443474292755127, + "learning_rate": 1.7370706671930518e-07, + "loss": 0.5972, + "step": 2446 + }, + { + "epoch": 0.9660481642321358, + "grad_norm": 0.790887713432312, + "learning_rate": 1.7173312277931307e-07, + "loss": 0.5922, + "step": 2447 + }, + { + "epoch": 0.9664429530201343, + "grad_norm": 0.6178786158561707, + "learning_rate": 1.69759178839321e-07, + "loss": 0.5525, + "step": 2448 + }, + { + "epoch": 0.9668377418081326, + "grad_norm": 0.7417503595352173, + "learning_rate": 1.6778523489932889e-07, + "loss": 0.6169, + "step": 2449 + }, + { + "epoch": 0.9672325305961311, + "grad_norm": 0.7012566924095154, + "learning_rate": 1.6581129095933675e-07, + "loss": 0.593, + "step": 2450 + }, + { + "epoch": 0.9676273193841295, + "grad_norm": 0.6360821723937988, + "learning_rate": 1.6383734701934467e-07, + "loss": 0.5681, + "step": 2451 + }, + { + "epoch": 0.9680221081721279, + "grad_norm": 0.724746584892273, + "learning_rate": 1.6186340307935257e-07, + "loss": 0.5566, + "step": 2452 + }, + { + "epoch": 0.9684168969601263, + "grad_norm": 0.5262120962142944, + "learning_rate": 1.5988945913936046e-07, + "loss": 0.4949, + "step": 2453 + }, + { + "epoch": 0.9688116857481247, + "grad_norm": 0.6907106041908264, + "learning_rate": 1.5791551519936835e-07, + "loss": 0.6215, + "step": 2454 + }, + { + "epoch": 0.9692064745361232, + "grad_norm": 0.7569233775138855, + "learning_rate": 1.5594157125937625e-07, + "loss": 0.5672, + "step": 2455 + }, + { + "epoch": 0.9696012633241216, + "grad_norm": 0.814324676990509, + "learning_rate": 1.5396762731938414e-07, + "loss": 0.6322, + "step": 2456 + }, + { + "epoch": 0.96999605211212, + "grad_norm": 0.8839899897575378, + "learning_rate": 1.5199368337939203e-07, + "loss": 0.7318, + "step": 2457 + }, + { + "epoch": 0.9703908409001184, + "grad_norm": 0.6586651802062988, + "learning_rate": 1.5001973943939993e-07, + "loss": 0.5319, + "step": 2458 + }, + { + "epoch": 0.9707856296881169, + "grad_norm": 0.8331881761550903, + "learning_rate": 1.4804579549940784e-07, + "loss": 0.66, + "step": 2459 + }, + { + "epoch": 0.9711804184761152, + "grad_norm": 0.7551396489143372, + "learning_rate": 1.4607185155941574e-07, + "loss": 0.5304, + "step": 2460 + }, + { + "epoch": 0.9715752072641137, + "grad_norm": 0.7671434283256531, + "learning_rate": 1.440979076194236e-07, + "loss": 0.6322, + "step": 2461 + }, + { + "epoch": 0.9719699960521121, + "grad_norm": 0.7607762217521667, + "learning_rate": 1.4212396367943152e-07, + "loss": 0.62, + "step": 2462 + }, + { + "epoch": 0.9723647848401106, + "grad_norm": 0.8147897124290466, + "learning_rate": 1.4015001973943942e-07, + "loss": 0.6108, + "step": 2463 + }, + { + "epoch": 0.9727595736281089, + "grad_norm": 0.6383792757987976, + "learning_rate": 1.381760757994473e-07, + "loss": 0.5778, + "step": 2464 + }, + { + "epoch": 0.9731543624161074, + "grad_norm": 0.695807933807373, + "learning_rate": 1.362021318594552e-07, + "loss": 0.5689, + "step": 2465 + }, + { + "epoch": 0.9735491512041058, + "grad_norm": 0.7073339223861694, + "learning_rate": 1.342281879194631e-07, + "loss": 0.5633, + "step": 2466 + }, + { + "epoch": 0.9739439399921043, + "grad_norm": 0.6741154193878174, + "learning_rate": 1.32254243979471e-07, + "loss": 0.587, + "step": 2467 + }, + { + "epoch": 0.9743387287801026, + "grad_norm": 0.9638950228691101, + "learning_rate": 1.3028030003947888e-07, + "loss": 0.696, + "step": 2468 + }, + { + "epoch": 0.9747335175681011, + "grad_norm": 0.6639662384986877, + "learning_rate": 1.2830635609948678e-07, + "loss": 0.5779, + "step": 2469 + }, + { + "epoch": 0.9751283063560995, + "grad_norm": 0.7612658739089966, + "learning_rate": 1.2633241215949467e-07, + "loss": 0.6013, + "step": 2470 + }, + { + "epoch": 0.975523095144098, + "grad_norm": 0.6564285755157471, + "learning_rate": 1.2435846821950256e-07, + "loss": 0.604, + "step": 2471 + }, + { + "epoch": 0.9759178839320963, + "grad_norm": 0.7690833806991577, + "learning_rate": 1.2238452427951048e-07, + "loss": 0.5956, + "step": 2472 + }, + { + "epoch": 0.9763126727200947, + "grad_norm": 0.7600560188293457, + "learning_rate": 1.2041058033951838e-07, + "loss": 0.6288, + "step": 2473 + }, + { + "epoch": 0.9767074615080932, + "grad_norm": 0.6818309426307678, + "learning_rate": 1.1843663639952626e-07, + "loss": 0.5276, + "step": 2474 + }, + { + "epoch": 0.9771022502960915, + "grad_norm": 0.776541531085968, + "learning_rate": 1.1646269245953415e-07, + "loss": 0.5977, + "step": 2475 + }, + { + "epoch": 0.97749703908409, + "grad_norm": 0.7540000081062317, + "learning_rate": 1.1448874851954206e-07, + "loss": 0.5463, + "step": 2476 + }, + { + "epoch": 0.9778918278720884, + "grad_norm": 0.6592136025428772, + "learning_rate": 1.1251480457954995e-07, + "loss": 0.5548, + "step": 2477 + }, + { + "epoch": 0.9782866166600869, + "grad_norm": 0.6438143849372864, + "learning_rate": 1.1054086063955783e-07, + "loss": 0.6025, + "step": 2478 + }, + { + "epoch": 0.9786814054480852, + "grad_norm": 0.8597297072410583, + "learning_rate": 1.0856691669956574e-07, + "loss": 0.556, + "step": 2479 + }, + { + "epoch": 0.9790761942360837, + "grad_norm": 0.5596076846122742, + "learning_rate": 1.0659297275957363e-07, + "loss": 0.6187, + "step": 2480 + }, + { + "epoch": 0.9794709830240821, + "grad_norm": 0.6758546233177185, + "learning_rate": 1.0461902881958154e-07, + "loss": 0.5809, + "step": 2481 + }, + { + "epoch": 0.9798657718120806, + "grad_norm": 0.6783113479614258, + "learning_rate": 1.0264508487958943e-07, + "loss": 0.6142, + "step": 2482 + }, + { + "epoch": 0.9802605606000789, + "grad_norm": 0.7316352128982544, + "learning_rate": 1.0067114093959732e-07, + "loss": 0.5928, + "step": 2483 + }, + { + "epoch": 0.9806553493880774, + "grad_norm": 0.7312946915626526, + "learning_rate": 9.869719699960522e-08, + "loss": 0.5511, + "step": 2484 + }, + { + "epoch": 0.9810501381760758, + "grad_norm": 0.6953846216201782, + "learning_rate": 9.672325305961311e-08, + "loss": 0.53, + "step": 2485 + }, + { + "epoch": 0.9814449269640743, + "grad_norm": 0.7741590738296509, + "learning_rate": 9.474930911962102e-08, + "loss": 0.6214, + "step": 2486 + }, + { + "epoch": 0.9818397157520726, + "grad_norm": 0.7430833578109741, + "learning_rate": 9.27753651796289e-08, + "loss": 0.5696, + "step": 2487 + }, + { + "epoch": 0.9822345045400711, + "grad_norm": 0.770401656627655, + "learning_rate": 9.08014212396368e-08, + "loss": 0.6604, + "step": 2488 + }, + { + "epoch": 0.9826292933280695, + "grad_norm": 0.5999031662940979, + "learning_rate": 8.88274772996447e-08, + "loss": 0.5886, + "step": 2489 + }, + { + "epoch": 0.983024082116068, + "grad_norm": 0.7066329121589661, + "learning_rate": 8.685353335965259e-08, + "loss": 0.5747, + "step": 2490 + }, + { + "epoch": 0.9834188709040663, + "grad_norm": 0.7701288461685181, + "learning_rate": 8.48795894196605e-08, + "loss": 0.6251, + "step": 2491 + }, + { + "epoch": 0.9838136596920647, + "grad_norm": 0.7709187269210815, + "learning_rate": 8.290564547966838e-08, + "loss": 0.6363, + "step": 2492 + }, + { + "epoch": 0.9842084484800632, + "grad_norm": 0.8057327270507812, + "learning_rate": 8.093170153967628e-08, + "loss": 0.5867, + "step": 2493 + }, + { + "epoch": 0.9846032372680615, + "grad_norm": 0.881464958190918, + "learning_rate": 7.895775759968418e-08, + "loss": 0.5742, + "step": 2494 + }, + { + "epoch": 0.98499802605606, + "grad_norm": 0.6676511168479919, + "learning_rate": 7.698381365969207e-08, + "loss": 0.6075, + "step": 2495 + }, + { + "epoch": 0.9853928148440584, + "grad_norm": 0.5603543519973755, + "learning_rate": 7.500986971969996e-08, + "loss": 0.4836, + "step": 2496 + }, + { + "epoch": 0.9857876036320569, + "grad_norm": 0.7495811581611633, + "learning_rate": 7.303592577970787e-08, + "loss": 0.6555, + "step": 2497 + }, + { + "epoch": 0.9861823924200552, + "grad_norm": 0.8105030655860901, + "learning_rate": 7.106198183971576e-08, + "loss": 0.712, + "step": 2498 + }, + { + "epoch": 0.9865771812080537, + "grad_norm": 0.6745395064353943, + "learning_rate": 6.908803789972366e-08, + "loss": 0.5967, + "step": 2499 + }, + { + "epoch": 0.9869719699960521, + "grad_norm": 0.7183120846748352, + "learning_rate": 6.711409395973155e-08, + "loss": 0.5682, + "step": 2500 + }, + { + "epoch": 0.9873667587840506, + "grad_norm": 0.9028608202934265, + "learning_rate": 6.514015001973944e-08, + "loss": 0.6772, + "step": 2501 + }, + { + "epoch": 0.9877615475720489, + "grad_norm": 0.6985450983047485, + "learning_rate": 6.316620607974734e-08, + "loss": 0.5974, + "step": 2502 + }, + { + "epoch": 0.9881563363600474, + "grad_norm": 0.6633962392807007, + "learning_rate": 6.119226213975524e-08, + "loss": 0.5207, + "step": 2503 + }, + { + "epoch": 0.9885511251480458, + "grad_norm": 0.8525327444076538, + "learning_rate": 5.921831819976313e-08, + "loss": 0.6935, + "step": 2504 + }, + { + "epoch": 0.9889459139360443, + "grad_norm": 0.8326323628425598, + "learning_rate": 5.724437425977103e-08, + "loss": 0.6095, + "step": 2505 + }, + { + "epoch": 0.9893407027240426, + "grad_norm": 0.8185986876487732, + "learning_rate": 5.5270430319778915e-08, + "loss": 0.5681, + "step": 2506 + }, + { + "epoch": 0.9897354915120411, + "grad_norm": 0.7278211116790771, + "learning_rate": 5.3296486379786815e-08, + "loss": 0.615, + "step": 2507 + }, + { + "epoch": 0.9901302803000395, + "grad_norm": 0.6226075887680054, + "learning_rate": 5.1322542439794715e-08, + "loss": 0.4741, + "step": 2508 + }, + { + "epoch": 0.990525069088038, + "grad_norm": 0.8247083425521851, + "learning_rate": 4.934859849980261e-08, + "loss": 0.6892, + "step": 2509 + }, + { + "epoch": 0.9909198578760363, + "grad_norm": 0.8937152028083801, + "learning_rate": 4.737465455981051e-08, + "loss": 0.5692, + "step": 2510 + }, + { + "epoch": 0.9913146466640348, + "grad_norm": 0.5769678950309753, + "learning_rate": 4.54007106198184e-08, + "loss": 0.5212, + "step": 2511 + }, + { + "epoch": 0.9917094354520332, + "grad_norm": 0.7112499475479126, + "learning_rate": 4.3426766679826295e-08, + "loss": 0.5568, + "step": 2512 + }, + { + "epoch": 0.9921042242400315, + "grad_norm": 0.6414216160774231, + "learning_rate": 4.145282273983419e-08, + "loss": 0.5077, + "step": 2513 + }, + { + "epoch": 0.99249901302803, + "grad_norm": 0.865508496761322, + "learning_rate": 3.947887879984209e-08, + "loss": 0.6406, + "step": 2514 + }, + { + "epoch": 0.9928938018160284, + "grad_norm": 0.6220317482948303, + "learning_rate": 3.750493485984998e-08, + "loss": 0.5634, + "step": 2515 + }, + { + "epoch": 0.9932885906040269, + "grad_norm": 0.8257157206535339, + "learning_rate": 3.553099091985788e-08, + "loss": 0.688, + "step": 2516 + }, + { + "epoch": 0.9936833793920252, + "grad_norm": 0.766491174697876, + "learning_rate": 3.3557046979865774e-08, + "loss": 0.6322, + "step": 2517 + }, + { + "epoch": 0.9940781681800237, + "grad_norm": 0.6419973969459534, + "learning_rate": 3.158310303987367e-08, + "loss": 0.5891, + "step": 2518 + }, + { + "epoch": 0.9944729569680221, + "grad_norm": 0.7309244275093079, + "learning_rate": 2.9609159099881564e-08, + "loss": 0.5782, + "step": 2519 + }, + { + "epoch": 0.9948677457560205, + "grad_norm": 0.9396386742591858, + "learning_rate": 2.7635215159889458e-08, + "loss": 0.6266, + "step": 2520 + }, + { + "epoch": 0.9952625345440189, + "grad_norm": 0.675393283367157, + "learning_rate": 2.5661271219897358e-08, + "loss": 0.5969, + "step": 2521 + }, + { + "epoch": 0.9956573233320174, + "grad_norm": 0.6904029846191406, + "learning_rate": 2.3687327279905254e-08, + "loss": 0.5781, + "step": 2522 + }, + { + "epoch": 0.9960521121200158, + "grad_norm": 0.7146249413490295, + "learning_rate": 2.1713383339913147e-08, + "loss": 0.6505, + "step": 2523 + }, + { + "epoch": 0.9964469009080142, + "grad_norm": 0.6696389317512512, + "learning_rate": 1.9739439399921044e-08, + "loss": 0.5596, + "step": 2524 + }, + { + "epoch": 0.9968416896960126, + "grad_norm": 0.710936427116394, + "learning_rate": 1.776549545992894e-08, + "loss": 0.6009, + "step": 2525 + }, + { + "epoch": 0.9972364784840111, + "grad_norm": 0.7200362086296082, + "learning_rate": 1.5791551519936834e-08, + "loss": 0.6352, + "step": 2526 + }, + { + "epoch": 0.9976312672720095, + "grad_norm": 0.702644944190979, + "learning_rate": 1.3817607579944729e-08, + "loss": 0.6136, + "step": 2527 + }, + { + "epoch": 0.9980260560600079, + "grad_norm": 0.7026209831237793, + "learning_rate": 1.1843663639952627e-08, + "loss": 0.5961, + "step": 2528 + }, + { + "epoch": 0.9984208448480063, + "grad_norm": 0.8817763328552246, + "learning_rate": 9.869719699960522e-09, + "loss": 0.619, + "step": 2529 + }, + { + "epoch": 0.9988156336360048, + "grad_norm": 0.7362896203994751, + "learning_rate": 7.895775759968417e-09, + "loss": 0.6327, + "step": 2530 + }, + { + "epoch": 0.9992104224240032, + "grad_norm": 0.6728416085243225, + "learning_rate": 5.9218318199763135e-09, + "loss": 0.6152, + "step": 2531 + }, + { + "epoch": 0.9996052112120016, + "grad_norm": 0.8583646416664124, + "learning_rate": 3.9478878799842085e-09, + "loss": 0.6266, + "step": 2532 + }, + { + "epoch": 1.0, + "grad_norm": 0.49964165687561035, + "learning_rate": 1.9739439399921042e-09, + "loss": 0.3747, + "step": 2533 + } + ], + "logging_steps": 1.0, + "max_steps": 2533, + "num_input_tokens_seen": 0, + "num_train_epochs": 1, + "save_steps": 0, + "stateful_callbacks": { + "TrainerControl": { + "args": { + "should_epoch_stop": false, + "should_evaluate": false, + "should_log": false, + "should_save": true, + "should_training_stop": true + }, + "attributes": {} + } + }, + "total_flos": 6.678162965359126e+19, + "train_batch_size": 1, + "trial_name": null, + "trial_params": null +}