diff --git a/.gitattributes b/.gitattributes index 398340c9277847901adb073cabc13870e3bd8e02..ed3cbd39ebeb0a3714ea3e98883006b8272f95f4 100644 --- a/.gitattributes +++ b/.gitattributes @@ -37,3 +37,6 @@ cycle_6/full_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text prev_8b_6skip/tokenizer.json filter=lfs diff=lfs merge=lfs -text prev_8b_11skip/tokenizer.json filter=lfs diff=lfs merge=lfs -text 8b_11skip/full_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text +llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/tokenizer.json filter=lfs diff=lfs merge=lfs -text +llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/tokenizer.json filter=lfs diff=lfs merge=lfs -text +llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/chat_template.jinja b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/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/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/config.json new file mode 100644 index 0000000000000000000000000000000000000000..d46f228af4f86807f6c43132edb66bfcbfb26c49 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 20, + "num_key_value_heads": 8, + "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": "4.57.6", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/generation_config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a7c15d9f6deeb875b0a7a8484198f87fd890722 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "transformers_version": "4.57.6" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_10/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_10/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..413ce3542cf7ede283086cf644e99414aea5de63 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_10/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b0737ed982459e8f52813f04df9bd8a25cea22557d61ba2892c81fc59585df5 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_12/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_12/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..240662d9a91fe3e1f1129288e52e39b502dd0ede --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_12/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78b583beb40946ec893deb83c58cae2a30aacb809de7018039a3f1ae3a407e1 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_14/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_14/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..223b021425d2b1edcb00a946c8dc30b2efca62ac --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_14/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b72fce950b96da8f6fa181e696bc8d084dc34bc0fde2bc628f632f5d6839bc74 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_16/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_16/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..7db5a6a84ab305cabe3f5d1aed437930b82bda24 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_16/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11b2d8839af4c4f61730b37785534d81a078626704f6f2701dc0ae51004b9e65 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_18/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_18/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..2a62e2995b252e291c76c4b3481edecea3aafbbb --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_18/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8849ccad5c723df674918a2a3af83c976cbe6d02617f6e343c858be33787ab04 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_2/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_2/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..c347e3e671ef22fc6d1d7f690f9f522fcd6d44d2 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_2/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13ecee13ad78cc4dd1562f716f448ae0273c55668bd869631cc69643ee8a5f9b +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_20/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_20/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dd0b805d6ff15fed68cd2ccba733bb4dfafae44 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_20/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8467191e7913f336c8abba68a3406493b068083ddfc7b2bd09cd17b12b43ed9c +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_4/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_4/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..9c96af4b581ad1fde41e42d2588dd1a277496874 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_4/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1d72349b06b4a64843e15207be9587e19602e2c363b1526356d5588e28765c6 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_6/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_6/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..f5820aaffe3f9f208c154fc1f7846cad4ccbd26f --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_6/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29413784411a89a90e046a7a1fbcc99288575bd648df9db8d6295f0a2bd8e770 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_8/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_8/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..5dbc5d84875e42392335e7e920a6466d8cc8741d --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_epoch_8/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a4da9011792e08d85f0ef331d1e2978c35d4955bc9ff781a93d40484430c473 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_final/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_final/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..3dd0b805d6ff15fed68cd2ccba733bb4dfafae44 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/lightweight_checkpoint_final/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8467191e7913f336c8abba68a3406493b068083ddfc7b2bd09cd17b12b43ed9c +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00001-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a59dca28867995c0d05384251ac5f4d62461a226 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1879f356aed350030bb40eb45ad362c89d9891096f79a3ab323d3ba5607668 +size 4976698672 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00002-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cf3e6fd52a7f93eaa0b3ab47d4787dac85f47aaa --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b54d927603514739b167436b8bb8fa2578f0be22bb037ec76c8d5a09386b3fd7 +size 4798483816 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00003-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..0b557876ba2c72b4f59a9bf87186a21bd1366695 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5321ca97dd0968a3e2b676b3a42728e9f5327d516bcf0addd4e9cd61c068a1ad +size 1050673280 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model.safetensors.index.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..8dd4db268dd812c7f0ce875d51db11797cc6c3fe --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/model.safetensors.index.json @@ -0,0 +1,191 @@ +{ + "metadata": { + "total_parameters": 5412917248, + "total_size": 10825834496 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.norm.weight": "model-00002-of-00003.safetensors" + } +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/run_args.txt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/run_args.txt new file mode 100644 index 0000000000000000000000000000000000000000..972c994252d92ee49ed24dbcc36e4bb20ec375b0 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/run_args.txt @@ -0,0 +1,9 @@ +git_commit=unknown +dataset=Open-Orca/SlimOrca +dataset_split=train +collect_batch_size=8 +train_batch_size=32 +gradient_accumulation_step=8 +target_effective_batch=256 +command: +python /workspace/here/abprune_update/compare_model/LLM-Streamline/mseloss_entry.py --model_name meta-llama/Llama-3.1-8B-Instruct --output_dir /workspace/here/abprune_update/results/llama31_8b_inst_streamline_slimorca_prune12_start18 --dataset Open-Orca/SlimOrca --dataset_split train --layer_intervals 12 --best_layer 18 --cosine_num_data 300 --train_num_data 30000 --epoches 20 --batch_size 8 --collect_batch_size 8 --train_batch_size 32 --dtype bfloat16 --gradient_accumulation_step 8 --lr 1e-5 --min_lr 5e-5 --wd 1e-3 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/special_tokens_map.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "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": "<|eot_id|>" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/tokenizer.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/tokenizer_config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3beeacc86a6ca3cae14ad3004263ab74a4bac07a --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/train_loss.txt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/train_loss.txt new file mode 100644 index 0000000000000000000000000000000000000000..0dc8bf2df0850ce3c27531c0b3b72d5fb0a8190b --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune12_start18/train_loss.txt @@ -0,0 +1,188 @@ +# Train loss logged every 100 global steps +epoch=0 global_step=100 optimizer_step=12 loss=0.3281250000 +epoch=0 global_step=200 optimizer_step=24 loss=0.3261718750 +epoch=0 global_step=300 optimizer_step=37 loss=0.3144531250 +epoch=0 global_step=400 optimizer_step=49 loss=0.3222656250 +epoch=0 global_step=500 optimizer_step=62 loss=0.3066406250 +epoch=0 global_step=600 optimizer_step=74 loss=0.2636718750 +epoch=0 global_step=700 optimizer_step=87 loss=0.2402343750 +epoch=0 global_step=800 optimizer_step=99 loss=0.1748046875 +epoch=0 global_step=900 optimizer_step=112 loss=0.1875000000 +epoch=1 global_step=1000 optimizer_step=124 loss=0.1650390625 +epoch=1 global_step=1100 optimizer_step=137 loss=0.1718750000 +epoch=1 global_step=1200 optimizer_step=149 loss=0.1494140625 +epoch=1 global_step=1300 optimizer_step=162 loss=0.1347656250 +epoch=1 global_step=1400 optimizer_step=174 loss=0.1347656250 +epoch=1 global_step=1500 optimizer_step=187 loss=0.1484375000 +epoch=1 global_step=1600 optimizer_step=199 loss=0.1308593750 +epoch=1 global_step=1700 optimizer_step=212 loss=0.1308593750 +epoch=1 global_step=1800 optimizer_step=224 loss=0.1298828125 +epoch=2 global_step=1900 optimizer_step=236 loss=0.1259765625 +epoch=2 global_step=2000 optimizer_step=249 loss=0.1210937500 +epoch=2 global_step=2100 optimizer_step=261 loss=0.1298828125 +epoch=2 global_step=2200 optimizer_step=274 loss=0.1542968750 +epoch=2 global_step=2300 optimizer_step=286 loss=0.1435546875 +epoch=2 global_step=2400 optimizer_step=299 loss=0.1572265625 +epoch=2 global_step=2500 optimizer_step=311 loss=0.1298828125 +epoch=2 global_step=2600 optimizer_step=324 loss=0.1533203125 +epoch=2 global_step=2700 optimizer_step=336 loss=0.1259765625 +epoch=2 global_step=2800 optimizer_step=349 loss=0.1386718750 +epoch=3 global_step=2900 optimizer_step=361 loss=0.1484375000 +epoch=3 global_step=3000 optimizer_step=374 loss=0.1513671875 +epoch=3 global_step=3100 optimizer_step=386 loss=0.1376953125 +epoch=3 global_step=3200 optimizer_step=399 loss=0.1240234375 +epoch=3 global_step=3300 optimizer_step=411 loss=0.1186523438 +epoch=3 global_step=3400 optimizer_step=424 loss=0.1298828125 +epoch=3 global_step=3500 optimizer_step=436 loss=0.1259765625 +epoch=3 global_step=3600 optimizer_step=449 loss=0.1108398438 +epoch=3 global_step=3700 optimizer_step=461 loss=0.1147460938 +epoch=4 global_step=3800 optimizer_step=473 loss=0.1406250000 +epoch=4 global_step=3900 optimizer_step=486 loss=0.1020507812 +epoch=4 global_step=4000 optimizer_step=498 loss=0.1181640625 +epoch=4 global_step=4100 optimizer_step=511 loss=0.1328125000 +epoch=4 global_step=4200 optimizer_step=523 loss=0.1245117188 +epoch=4 global_step=4300 optimizer_step=536 loss=0.1220703125 +epoch=4 global_step=4400 optimizer_step=548 loss=0.1147460938 +epoch=4 global_step=4500 optimizer_step=561 loss=0.1337890625 +epoch=4 global_step=4600 optimizer_step=573 loss=0.1044921875 +epoch=5 global_step=4700 optimizer_step=586 loss=0.1064453125 +epoch=5 global_step=4800 optimizer_step=598 loss=0.1259765625 +epoch=5 global_step=4900 optimizer_step=611 loss=0.1337890625 +epoch=5 global_step=5000 optimizer_step=623 loss=0.1337890625 +epoch=5 global_step=5100 optimizer_step=636 loss=0.1337890625 +epoch=5 global_step=5200 optimizer_step=648 loss=0.1171875000 +epoch=5 global_step=5300 optimizer_step=661 loss=0.1166992188 +epoch=5 global_step=5400 optimizer_step=673 loss=0.0991210938 +epoch=5 global_step=5500 optimizer_step=686 loss=0.1206054688 +epoch=5 global_step=5600 optimizer_step=698 loss=0.1357421875 +epoch=6 global_step=5700 optimizer_step=710 loss=0.1142578125 +epoch=6 global_step=5800 optimizer_step=723 loss=0.1513671875 +epoch=6 global_step=5900 optimizer_step=735 loss=0.0932617188 +epoch=6 global_step=6000 optimizer_step=748 loss=0.1542968750 +epoch=6 global_step=6100 optimizer_step=760 loss=0.1308593750 +epoch=6 global_step=6200 optimizer_step=773 loss=0.1079101562 +epoch=6 global_step=6300 optimizer_step=785 loss=0.1142578125 +epoch=6 global_step=6400 optimizer_step=798 loss=0.1132812500 +epoch=6 global_step=6500 optimizer_step=810 loss=0.1162109375 +epoch=7 global_step=6600 optimizer_step=823 loss=0.1464843750 +epoch=7 global_step=6700 optimizer_step=835 loss=0.1108398438 +epoch=7 global_step=6800 optimizer_step=848 loss=0.1113281250 +epoch=7 global_step=6900 optimizer_step=860 loss=0.0991210938 +epoch=7 global_step=7000 optimizer_step=873 loss=0.1347656250 +epoch=7 global_step=7100 optimizer_step=885 loss=0.1196289062 +epoch=7 global_step=7200 optimizer_step=898 loss=0.1225585938 +epoch=7 global_step=7300 optimizer_step=910 loss=0.1259765625 +epoch=7 global_step=7400 optimizer_step=923 loss=0.1206054688 +epoch=7 global_step=7500 optimizer_step=935 loss=0.1250000000 +epoch=8 global_step=7600 optimizer_step=947 loss=0.1088867188 +epoch=8 global_step=7700 optimizer_step=960 loss=0.1171875000 +epoch=8 global_step=7800 optimizer_step=972 loss=0.1279296875 +epoch=8 global_step=7900 optimizer_step=985 loss=0.1347656250 +epoch=8 global_step=8000 optimizer_step=997 loss=0.0898437500 +epoch=8 global_step=8100 optimizer_step=1010 loss=0.1318359375 +epoch=8 global_step=8200 optimizer_step=1022 loss=0.1416015625 +epoch=8 global_step=8300 optimizer_step=1035 loss=0.1064453125 +epoch=8 global_step=8400 optimizer_step=1047 loss=0.1279296875 +epoch=9 global_step=8500 optimizer_step=1060 loss=0.0908203125 +epoch=9 global_step=8600 optimizer_step=1072 loss=0.1108398438 +epoch=9 global_step=8700 optimizer_step=1085 loss=0.1098632812 +epoch=9 global_step=8800 optimizer_step=1097 loss=0.1147460938 +epoch=9 global_step=8900 optimizer_step=1110 loss=0.1289062500 +epoch=9 global_step=9000 optimizer_step=1122 loss=0.1098632812 +epoch=9 global_step=9100 optimizer_step=1135 loss=0.1000976562 +epoch=9 global_step=9200 optimizer_step=1147 loss=0.1176757812 +epoch=9 global_step=9300 optimizer_step=1160 loss=0.1040039062 +epoch=10 global_step=9400 optimizer_step=1172 loss=0.1049804688 +epoch=10 global_step=9500 optimizer_step=1184 loss=0.1088867188 +epoch=10 global_step=9600 optimizer_step=1197 loss=0.0957031250 +epoch=10 global_step=9700 optimizer_step=1209 loss=0.1279296875 +epoch=10 global_step=9800 optimizer_step=1222 loss=0.1074218750 +epoch=10 global_step=9900 optimizer_step=1234 loss=0.1108398438 +epoch=10 global_step=10000 optimizer_step=1247 loss=0.0917968750 +epoch=10 global_step=10100 optimizer_step=1259 loss=0.1083984375 +epoch=10 global_step=10200 optimizer_step=1272 loss=0.1245117188 +epoch=10 global_step=10300 optimizer_step=1284 loss=0.1064453125 +epoch=11 global_step=10400 optimizer_step=1297 loss=0.0991210938 +epoch=11 global_step=10500 optimizer_step=1309 loss=0.1230468750 +epoch=11 global_step=10600 optimizer_step=1322 loss=0.1328125000 +epoch=11 global_step=10700 optimizer_step=1334 loss=0.1196289062 +epoch=11 global_step=10800 optimizer_step=1347 loss=0.1186523438 +epoch=11 global_step=10900 optimizer_step=1359 loss=0.1025390625 +epoch=11 global_step=11000 optimizer_step=1372 loss=0.1181640625 +epoch=11 global_step=11100 optimizer_step=1384 loss=0.1240234375 +epoch=11 global_step=11200 optimizer_step=1397 loss=0.1098632812 +epoch=12 global_step=11300 optimizer_step=1409 loss=0.1088867188 +epoch=12 global_step=11400 optimizer_step=1421 loss=0.1206054688 +epoch=12 global_step=11500 optimizer_step=1434 loss=0.1245117188 +epoch=12 global_step=11600 optimizer_step=1446 loss=0.1127929688 +epoch=12 global_step=11700 optimizer_step=1459 loss=0.1176757812 +epoch=12 global_step=11800 optimizer_step=1471 loss=0.1201171875 +epoch=12 global_step=11900 optimizer_step=1484 loss=0.0903320312 +epoch=12 global_step=12000 optimizer_step=1496 loss=0.1010742188 +epoch=12 global_step=12100 optimizer_step=1509 loss=0.1069335938 +epoch=13 global_step=12200 optimizer_step=1521 loss=0.1093750000 +epoch=13 global_step=12300 optimizer_step=1534 loss=0.1181640625 +epoch=13 global_step=12400 optimizer_step=1546 loss=0.1040039062 +epoch=13 global_step=12500 optimizer_step=1559 loss=0.1269531250 +epoch=13 global_step=12600 optimizer_step=1571 loss=0.1215820312 +epoch=13 global_step=12700 optimizer_step=1584 loss=0.0957031250 +epoch=13 global_step=12800 optimizer_step=1596 loss=0.1308593750 +epoch=13 global_step=12900 optimizer_step=1609 loss=0.1000976562 +epoch=13 global_step=13000 optimizer_step=1621 loss=0.1201171875 +epoch=13 global_step=13100 optimizer_step=1634 loss=0.1074218750 +epoch=14 global_step=13200 optimizer_step=1646 loss=0.0903320312 +epoch=14 global_step=13300 optimizer_step=1658 loss=0.1083984375 +epoch=14 global_step=13400 optimizer_step=1671 loss=0.1162109375 +epoch=14 global_step=13500 optimizer_step=1683 loss=0.1059570312 +epoch=14 global_step=13600 optimizer_step=1696 loss=0.1035156250 +epoch=14 global_step=13700 optimizer_step=1708 loss=0.0917968750 +epoch=14 global_step=13800 optimizer_step=1721 loss=0.1088867188 +epoch=14 global_step=13900 optimizer_step=1733 loss=0.1113281250 +epoch=14 global_step=14000 optimizer_step=1746 loss=0.1093750000 +epoch=15 global_step=14100 optimizer_step=1758 loss=0.0996093750 +epoch=15 global_step=14200 optimizer_step=1771 loss=0.1103515625 +epoch=15 global_step=14300 optimizer_step=1783 loss=0.1044921875 +epoch=15 global_step=14400 optimizer_step=1796 loss=0.1206054688 +epoch=15 global_step=14500 optimizer_step=1808 loss=0.1030273438 +epoch=15 global_step=14600 optimizer_step=1821 loss=0.0947265625 +epoch=15 global_step=14700 optimizer_step=1833 loss=0.1025390625 +epoch=15 global_step=14800 optimizer_step=1846 loss=0.1020507812 +epoch=15 global_step=14900 optimizer_step=1858 loss=0.0815429688 +epoch=15 global_step=15000 optimizer_step=1871 loss=0.0996093750 +epoch=16 global_step=15100 optimizer_step=1883 loss=0.1049804688 +epoch=16 global_step=15200 optimizer_step=1895 loss=0.1030273438 +epoch=16 global_step=15300 optimizer_step=1908 loss=0.0952148438 +epoch=16 global_step=15400 optimizer_step=1920 loss=0.0996093750 +epoch=16 global_step=15500 optimizer_step=1933 loss=0.1220703125 +epoch=16 global_step=15600 optimizer_step=1945 loss=0.1176757812 +epoch=16 global_step=15700 optimizer_step=1958 loss=0.1059570312 +epoch=16 global_step=15800 optimizer_step=1970 loss=0.1367187500 +epoch=16 global_step=15900 optimizer_step=1983 loss=0.0991210938 +epoch=17 global_step=16000 optimizer_step=1995 loss=0.0903320312 +epoch=17 global_step=16100 optimizer_step=2008 loss=0.1015625000 +epoch=17 global_step=16200 optimizer_step=2020 loss=0.1088867188 +epoch=17 global_step=16300 optimizer_step=2033 loss=0.1098632812 +epoch=17 global_step=16400 optimizer_step=2045 loss=0.1176757812 +epoch=17 global_step=16500 optimizer_step=2058 loss=0.1035156250 +epoch=17 global_step=16600 optimizer_step=2070 loss=0.0966796875 +epoch=17 global_step=16700 optimizer_step=2083 loss=0.1171875000 +epoch=17 global_step=16800 optimizer_step=2095 loss=0.1113281250 +epoch=18 global_step=16900 optimizer_step=2107 loss=0.1181640625 +epoch=18 global_step=17000 optimizer_step=2120 loss=0.1289062500 +epoch=18 global_step=17100 optimizer_step=2132 loss=0.1093750000 +epoch=18 global_step=17200 optimizer_step=2145 loss=0.0961914062 +epoch=18 global_step=17300 optimizer_step=2157 loss=0.0961914062 +epoch=18 global_step=17400 optimizer_step=2170 loss=0.0991210938 +epoch=18 global_step=17500 optimizer_step=2182 loss=0.1127929688 +epoch=18 global_step=17600 optimizer_step=2195 loss=0.1123046875 +epoch=18 global_step=17700 optimizer_step=2207 loss=0.1020507812 +epoch=18 global_step=17800 optimizer_step=2220 loss=0.0952148438 +epoch=19 global_step=17900 optimizer_step=2232 loss=0.1049804688 +epoch=19 global_step=18000 optimizer_step=2245 loss=0.0864257812 +epoch=19 global_step=18100 optimizer_step=2257 loss=0.0932617188 +epoch=19 global_step=18200 optimizer_step=2270 loss=0.1005859375 +epoch=19 global_step=18300 optimizer_step=2282 loss=0.1074218750 +epoch=19 global_step=18400 optimizer_step=2295 loss=0.1250000000 +epoch=19 global_step=18500 optimizer_step=2307 loss=0.1181640625 +epoch=19 global_step=18600 optimizer_step=2320 loss=0.0922851562 +epoch=19 global_step=18700 optimizer_step=2332 loss=0.0981445312 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/chat_template.jinja b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/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/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/config.json new file mode 100644 index 0000000000000000000000000000000000000000..8de6410f363cbe0b83c33e5137c641f139580cd8 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 28, + "num_key_value_heads": 8, + "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": "4.57.6", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/generation_config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a7c15d9f6deeb875b0a7a8484198f87fd890722 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "transformers_version": "4.57.6" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_10/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_10/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..82e236426f4fb69a0e9322c76ad57a68579fc16f --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_10/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a941a1b49686783c4a534c47974a1382c6ba43ee3e8415b6e642a11b37ea70db +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_12/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_12/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..4737a13bb9028bc8e428323dbab5eab8d0f2ac28 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_12/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad68e4fbe924f6cd5f30497b50831af48cc3f72e0a0020756e5f39421775bcc8 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_14/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_14/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e7990f0d9f77c4d237d62bb766f8f31fd4033dd --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_14/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dd8d2b17364f6444f1a7285ac34b2e8351751f9c07da6d08e63b6d5630bb2b1 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_16/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_16/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..ee0bde3797ba5d2ec57cc86128c4bf71cdb1ea09 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_16/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83e414c2a188127fe88465e80d0a3c32ae0ed780b69e80086acbfabe31bd58ee +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_18/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_18/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..7989a744616a2d4349135e45a3c37a9bfc6ead5d --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_18/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ba90a91dc97bc09162b917365efd49e7b87f2c81e270ad594b0dc4700ce83e +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_2/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_2/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..1fd71ce4d5e2448c935aac8ca4eae5df9afb8ef8 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_2/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88f150b6801167a5c99c820f039d906486d4bcd23b3918c7bf7ca27c1042729f +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_20/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_20/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a1a1bc283aca4a3597836d73e43bd4c5d242273 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_20/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0e41764471fa7664ffc1d97707f3478bb3140c5001eee3cb2162c109d0d337 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_4/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_4/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..d84e48a89d8f1646c5b2c35f315db5ee1c14b8e9 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_4/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a13f5f87cced1fce1abe16c6c650f886fcd016b61a71c59785be6a3b867b35cf +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_6/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_6/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..eef87b6d1419bcd6d8f0ee2b1e6f7ba47f5a1229 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_6/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:872407e54e2e80c1c9c1b204182665b5ac1484c85d3bf1ed2331a2fe3aafe457 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_8/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_8/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..c4638894252f06681b43c21133cfd9d1addfd2b8 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_epoch_8/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98a66eba03a19c33393ac334c332dad6c9d824fc58e2ea82823cea8dbbbd6307 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_final/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_final/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..8a1a1bc283aca4a3597836d73e43bd4c5d242273 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/lightweight_checkpoint_final/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d0e41764471fa7664ffc1d97707f3478bb3140c5001eee3cb2162c109d0d337 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00001-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a59dca28867995c0d05384251ac5f4d62461a226 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1879f356aed350030bb40eb45ad362c89d9891096f79a3ab323d3ba5607668 +size 4976698672 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00002-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ab0726caf5e75dd1e5700c7e7899ac8c0798428 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d433f650646834a83c580877bd60c6d1f88f7755305c12576b5c7058f9af15 +size 4999802720 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00003-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..997c041e081c12dea28993e88793508e84625581 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:373f9ba784fc6508bf118373fb98fc8d6e43e606178f1c4fb132efdaa0c16e91 +size 4339154792 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model.safetensors.index.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..2f4e99f3e7b90133b5828f4815b7834aa4245238 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/model.safetensors.index.json @@ -0,0 +1,263 @@ +{ + "metadata": { + "total_parameters": 7157813248, + "total_size": 14315626496 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/run_args.txt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/run_args.txt new file mode 100644 index 0000000000000000000000000000000000000000..3cad39bd4ed57eec0b7949273bbae57bcaee3f47 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/run_args.txt @@ -0,0 +1,9 @@ +git_commit=unknown +dataset=Open-Orca/SlimOrca +dataset_split=train +collect_batch_size=8 +train_batch_size=32 +gradient_accumulation_step=8 +target_effective_batch=256 +command: +python /workspace/here/abprune_update/compare_model/LLM-Streamline/mseloss_entry.py --model_name meta-llama/Llama-3.1-8B-Instruct --output_dir /workspace/here/abprune_update/results/llama31_8b_inst_streamline_slimorca_prune4_start23 --dataset Open-Orca/SlimOrca --dataset_split train --layer_intervals 4 --best_layer 23 --cosine_num_data 300 --train_num_data 30000 --epoches 20 --batch_size 8 --collect_batch_size 8 --train_batch_size 32 --dtype bfloat16 --gradient_accumulation_step 8 --lr 1e-5 --min_lr 5e-5 --wd 1e-3 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/special_tokens_map.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "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": "<|eot_id|>" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/tokenizer.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/tokenizer_config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3beeacc86a6ca3cae14ad3004263ab74a4bac07a --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/train_loss.txt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/train_loss.txt new file mode 100644 index 0000000000000000000000000000000000000000..8b4d401be528803710bb2ecc9a0d88039e799b35 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune4_start23/train_loss.txt @@ -0,0 +1,188 @@ +# Train loss logged every 100 global steps +epoch=0 global_step=100 optimizer_step=12 loss=0.0942382812 +epoch=0 global_step=200 optimizer_step=24 loss=0.0908203125 +epoch=0 global_step=300 optimizer_step=37 loss=0.0874023438 +epoch=0 global_step=400 optimizer_step=49 loss=0.0800781250 +epoch=0 global_step=500 optimizer_step=62 loss=0.0703125000 +epoch=0 global_step=600 optimizer_step=74 loss=0.0649414062 +epoch=0 global_step=700 optimizer_step=87 loss=0.0549316406 +epoch=0 global_step=800 optimizer_step=99 loss=0.0424804688 +epoch=0 global_step=900 optimizer_step=112 loss=0.0354003906 +epoch=1 global_step=1000 optimizer_step=124 loss=0.0322265625 +epoch=1 global_step=1100 optimizer_step=137 loss=0.0361328125 +epoch=1 global_step=1200 optimizer_step=149 loss=0.0317382812 +epoch=1 global_step=1300 optimizer_step=162 loss=0.0332031250 +epoch=1 global_step=1400 optimizer_step=174 loss=0.0336914062 +epoch=1 global_step=1500 optimizer_step=187 loss=0.0329589844 +epoch=1 global_step=1600 optimizer_step=199 loss=0.0356445312 +epoch=1 global_step=1700 optimizer_step=212 loss=0.0314941406 +epoch=1 global_step=1800 optimizer_step=224 loss=0.0312500000 +epoch=2 global_step=1900 optimizer_step=236 loss=0.0288085938 +epoch=2 global_step=2000 optimizer_step=249 loss=0.0273437500 +epoch=2 global_step=2100 optimizer_step=261 loss=0.0262451172 +epoch=2 global_step=2200 optimizer_step=274 loss=0.0300292969 +epoch=2 global_step=2300 optimizer_step=286 loss=0.0290527344 +epoch=2 global_step=2400 optimizer_step=299 loss=0.0299072266 +epoch=2 global_step=2500 optimizer_step=311 loss=0.0307617188 +epoch=2 global_step=2600 optimizer_step=324 loss=0.0346679688 +epoch=2 global_step=2700 optimizer_step=336 loss=0.0301513672 +epoch=2 global_step=2800 optimizer_step=349 loss=0.0261230469 +epoch=3 global_step=2900 optimizer_step=361 loss=0.0292968750 +epoch=3 global_step=3000 optimizer_step=374 loss=0.0306396484 +epoch=3 global_step=3100 optimizer_step=386 loss=0.0314941406 +epoch=3 global_step=3200 optimizer_step=399 loss=0.0295410156 +epoch=3 global_step=3300 optimizer_step=411 loss=0.0263671875 +epoch=3 global_step=3400 optimizer_step=424 loss=0.0269775391 +epoch=3 global_step=3500 optimizer_step=436 loss=0.0285644531 +epoch=3 global_step=3600 optimizer_step=449 loss=0.0279541016 +epoch=3 global_step=3700 optimizer_step=461 loss=0.0249023438 +epoch=4 global_step=3800 optimizer_step=473 loss=0.0308837891 +epoch=4 global_step=3900 optimizer_step=486 loss=0.0280761719 +epoch=4 global_step=4000 optimizer_step=498 loss=0.0294189453 +epoch=4 global_step=4100 optimizer_step=511 loss=0.0278320312 +epoch=4 global_step=4200 optimizer_step=523 loss=0.0268554688 +epoch=4 global_step=4300 optimizer_step=536 loss=0.0251464844 +epoch=4 global_step=4400 optimizer_step=548 loss=0.0250244141 +epoch=4 global_step=4500 optimizer_step=561 loss=0.0255126953 +epoch=4 global_step=4600 optimizer_step=573 loss=0.0252685547 +epoch=5 global_step=4700 optimizer_step=586 loss=0.0217285156 +epoch=5 global_step=4800 optimizer_step=598 loss=0.0262451172 +epoch=5 global_step=4900 optimizer_step=611 loss=0.0257568359 +epoch=5 global_step=5000 optimizer_step=623 loss=0.0255126953 +epoch=5 global_step=5100 optimizer_step=636 loss=0.0261230469 +epoch=5 global_step=5200 optimizer_step=648 loss=0.0242919922 +epoch=5 global_step=5300 optimizer_step=661 loss=0.0297851562 +epoch=5 global_step=5400 optimizer_step=673 loss=0.0275878906 +epoch=5 global_step=5500 optimizer_step=686 loss=0.0240478516 +epoch=5 global_step=5600 optimizer_step=698 loss=0.0227050781 +epoch=6 global_step=5700 optimizer_step=710 loss=0.0253906250 +epoch=6 global_step=5800 optimizer_step=723 loss=0.0253906250 +epoch=6 global_step=5900 optimizer_step=735 loss=0.0306396484 +epoch=6 global_step=6000 optimizer_step=748 loss=0.0233154297 +epoch=6 global_step=6100 optimizer_step=760 loss=0.0249023438 +epoch=6 global_step=6200 optimizer_step=773 loss=0.0260009766 +epoch=6 global_step=6300 optimizer_step=785 loss=0.0275878906 +epoch=6 global_step=6400 optimizer_step=798 loss=0.0234375000 +epoch=6 global_step=6500 optimizer_step=810 loss=0.0234375000 +epoch=7 global_step=6600 optimizer_step=823 loss=0.0263671875 +epoch=7 global_step=6700 optimizer_step=835 loss=0.0239257812 +epoch=7 global_step=6800 optimizer_step=848 loss=0.0258789062 +epoch=7 global_step=6900 optimizer_step=860 loss=0.0249023438 +epoch=7 global_step=7000 optimizer_step=873 loss=0.0264892578 +epoch=7 global_step=7100 optimizer_step=885 loss=0.0255126953 +epoch=7 global_step=7200 optimizer_step=898 loss=0.0238037109 +epoch=7 global_step=7300 optimizer_step=910 loss=0.0281982422 +epoch=7 global_step=7400 optimizer_step=923 loss=0.0235595703 +epoch=7 global_step=7500 optimizer_step=935 loss=0.0296630859 +epoch=8 global_step=7600 optimizer_step=947 loss=0.0250244141 +epoch=8 global_step=7700 optimizer_step=960 loss=0.0263671875 +epoch=8 global_step=7800 optimizer_step=972 loss=0.0234375000 +epoch=8 global_step=7900 optimizer_step=985 loss=0.0195312500 +epoch=8 global_step=8000 optimizer_step=997 loss=0.0255126953 +epoch=8 global_step=8100 optimizer_step=1010 loss=0.0256347656 +epoch=8 global_step=8200 optimizer_step=1022 loss=0.0230712891 +epoch=8 global_step=8300 optimizer_step=1035 loss=0.0225830078 +epoch=8 global_step=8400 optimizer_step=1047 loss=0.0253906250 +epoch=9 global_step=8500 optimizer_step=1060 loss=0.0236816406 +epoch=9 global_step=8600 optimizer_step=1072 loss=0.0246582031 +epoch=9 global_step=8700 optimizer_step=1085 loss=0.0240478516 +epoch=9 global_step=8800 optimizer_step=1097 loss=0.0269775391 +epoch=9 global_step=8900 optimizer_step=1110 loss=0.0241699219 +epoch=9 global_step=9000 optimizer_step=1122 loss=0.0219726562 +epoch=9 global_step=9100 optimizer_step=1135 loss=0.0252685547 +epoch=9 global_step=9200 optimizer_step=1147 loss=0.0278320312 +epoch=9 global_step=9300 optimizer_step=1160 loss=0.0266113281 +epoch=10 global_step=9400 optimizer_step=1172 loss=0.0270996094 +epoch=10 global_step=9500 optimizer_step=1184 loss=0.0246582031 +epoch=10 global_step=9600 optimizer_step=1197 loss=0.0296630859 +epoch=10 global_step=9700 optimizer_step=1209 loss=0.0236816406 +epoch=10 global_step=9800 optimizer_step=1222 loss=0.0279541016 +epoch=10 global_step=9900 optimizer_step=1234 loss=0.0273437500 +epoch=10 global_step=10000 optimizer_step=1247 loss=0.0218505859 +epoch=10 global_step=10100 optimizer_step=1259 loss=0.0242919922 +epoch=10 global_step=10200 optimizer_step=1272 loss=0.0240478516 +epoch=10 global_step=10300 optimizer_step=1284 loss=0.0242919922 +epoch=11 global_step=10400 optimizer_step=1297 loss=0.0274658203 +epoch=11 global_step=10500 optimizer_step=1309 loss=0.0214843750 +epoch=11 global_step=10600 optimizer_step=1322 loss=0.0263671875 +epoch=11 global_step=10700 optimizer_step=1334 loss=0.0260009766 +epoch=11 global_step=10800 optimizer_step=1347 loss=0.0211181641 +epoch=11 global_step=10900 optimizer_step=1359 loss=0.0247802734 +epoch=11 global_step=11000 optimizer_step=1372 loss=0.0201416016 +epoch=11 global_step=11100 optimizer_step=1384 loss=0.0272216797 +epoch=11 global_step=11200 optimizer_step=1397 loss=0.0225830078 +epoch=12 global_step=11300 optimizer_step=1409 loss=0.0246582031 +epoch=12 global_step=11400 optimizer_step=1421 loss=0.0240478516 +epoch=12 global_step=11500 optimizer_step=1434 loss=0.0240478516 +epoch=12 global_step=11600 optimizer_step=1446 loss=0.0268554688 +epoch=12 global_step=11700 optimizer_step=1459 loss=0.0189208984 +epoch=12 global_step=11800 optimizer_step=1471 loss=0.0234375000 +epoch=12 global_step=11900 optimizer_step=1484 loss=0.0274658203 +epoch=12 global_step=12000 optimizer_step=1496 loss=0.0255126953 +epoch=12 global_step=12100 optimizer_step=1509 loss=0.0238037109 +epoch=13 global_step=12200 optimizer_step=1521 loss=0.0225830078 +epoch=13 global_step=12300 optimizer_step=1534 loss=0.0236816406 +epoch=13 global_step=12400 optimizer_step=1546 loss=0.0234375000 +epoch=13 global_step=12500 optimizer_step=1559 loss=0.0253906250 +epoch=13 global_step=12600 optimizer_step=1571 loss=0.0225830078 +epoch=13 global_step=12700 optimizer_step=1584 loss=0.0240478516 +epoch=13 global_step=12800 optimizer_step=1596 loss=0.0234375000 +epoch=13 global_step=12900 optimizer_step=1609 loss=0.0235595703 +epoch=13 global_step=13000 optimizer_step=1621 loss=0.0229492188 +epoch=13 global_step=13100 optimizer_step=1634 loss=0.0256347656 +epoch=14 global_step=13200 optimizer_step=1646 loss=0.0224609375 +epoch=14 global_step=13300 optimizer_step=1658 loss=0.0233154297 +epoch=14 global_step=13400 optimizer_step=1671 loss=0.0223388672 +epoch=14 global_step=13500 optimizer_step=1683 loss=0.0256347656 +epoch=14 global_step=13600 optimizer_step=1696 loss=0.0283203125 +epoch=14 global_step=13700 optimizer_step=1708 loss=0.0264892578 +epoch=14 global_step=13800 optimizer_step=1721 loss=0.0231933594 +epoch=14 global_step=13900 optimizer_step=1733 loss=0.0229492188 +epoch=14 global_step=14000 optimizer_step=1746 loss=0.0267333984 +epoch=15 global_step=14100 optimizer_step=1758 loss=0.0239257812 +epoch=15 global_step=14200 optimizer_step=1771 loss=0.0209960938 +epoch=15 global_step=14300 optimizer_step=1783 loss=0.0217285156 +epoch=15 global_step=14400 optimizer_step=1796 loss=0.0223388672 +epoch=15 global_step=14500 optimizer_step=1808 loss=0.0229492188 +epoch=15 global_step=14600 optimizer_step=1821 loss=0.0206298828 +epoch=15 global_step=14700 optimizer_step=1833 loss=0.0245361328 +epoch=15 global_step=14800 optimizer_step=1846 loss=0.0208740234 +epoch=15 global_step=14900 optimizer_step=1858 loss=0.0242919922 +epoch=15 global_step=15000 optimizer_step=1871 loss=0.0255126953 +epoch=16 global_step=15100 optimizer_step=1883 loss=0.0246582031 +epoch=16 global_step=15200 optimizer_step=1895 loss=0.0207519531 +epoch=16 global_step=15300 optimizer_step=1908 loss=0.0233154297 +epoch=16 global_step=15400 optimizer_step=1920 loss=0.0261230469 +epoch=16 global_step=15500 optimizer_step=1933 loss=0.0209960938 +epoch=16 global_step=15600 optimizer_step=1945 loss=0.0253906250 +epoch=16 global_step=15700 optimizer_step=1958 loss=0.0251464844 +epoch=16 global_step=15800 optimizer_step=1970 loss=0.0262451172 +epoch=16 global_step=15900 optimizer_step=1983 loss=0.0173339844 +epoch=17 global_step=16000 optimizer_step=1995 loss=0.0219726562 +epoch=17 global_step=16100 optimizer_step=2008 loss=0.0224609375 +epoch=17 global_step=16200 optimizer_step=2020 loss=0.0192871094 +epoch=17 global_step=16300 optimizer_step=2033 loss=0.0231933594 +epoch=17 global_step=16400 optimizer_step=2045 loss=0.0247802734 +epoch=17 global_step=16500 optimizer_step=2058 loss=0.0218505859 +epoch=17 global_step=16600 optimizer_step=2070 loss=0.0207519531 +epoch=17 global_step=16700 optimizer_step=2083 loss=0.0235595703 +epoch=17 global_step=16800 optimizer_step=2095 loss=0.0251464844 +epoch=18 global_step=16900 optimizer_step=2107 loss=0.0236816406 +epoch=18 global_step=17000 optimizer_step=2120 loss=0.0205078125 +epoch=18 global_step=17100 optimizer_step=2132 loss=0.0244140625 +epoch=18 global_step=17200 optimizer_step=2145 loss=0.0187988281 +epoch=18 global_step=17300 optimizer_step=2157 loss=0.0200195312 +epoch=18 global_step=17400 optimizer_step=2170 loss=0.0219726562 +epoch=18 global_step=17500 optimizer_step=2182 loss=0.0218505859 +epoch=18 global_step=17600 optimizer_step=2195 loss=0.0249023438 +epoch=18 global_step=17700 optimizer_step=2207 loss=0.0227050781 +epoch=18 global_step=17800 optimizer_step=2220 loss=0.0212402344 +epoch=19 global_step=17900 optimizer_step=2232 loss=0.0283203125 +epoch=19 global_step=18000 optimizer_step=2245 loss=0.0251464844 +epoch=19 global_step=18100 optimizer_step=2257 loss=0.0224609375 +epoch=19 global_step=18200 optimizer_step=2270 loss=0.0208740234 +epoch=19 global_step=18300 optimizer_step=2282 loss=0.0245361328 +epoch=19 global_step=18400 optimizer_step=2295 loss=0.0209960938 +epoch=19 global_step=18500 optimizer_step=2307 loss=0.0191650391 +epoch=19 global_step=18600 optimizer_step=2320 loss=0.0257568359 +epoch=19 global_step=18700 optimizer_step=2332 loss=0.0203857422 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/chat_template.jinja b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..33089ace1be88f22a10fe861ad49718d5d886090 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/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/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/config.json new file mode 100644 index 0000000000000000000000000000000000000000..cb95d5e3e1a4a93a73599653969c562b89b4cb8d --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/config.json @@ -0,0 +1,39 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 24, + "num_key_value_heads": 8, + "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": "4.57.6", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/generation_config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..9a7c15d9f6deeb875b0a7a8484198f87fd890722 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "bos_token_id": 128000, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "transformers_version": "4.57.6" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_10/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_10/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..61bbea293dae1fa57a85069ea75797472b50b799 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_10/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e987c2ea1798beb414ead868213e39c6e2181c8b06ac079fe4ffc68f0f997c68 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_12/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_12/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..929b3a5cb90eccece79d240b2267ab7721bc5345 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_12/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb30c09fad89fc81199674f4b9bcac3790d8088130a56c44ca9260e9591f436 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_14/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_14/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..d11b6fd53a17e71a21282170cab8f278278b9a36 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_14/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bb4cd91a1d407c0cbdfcd2a909f3d053286203df7bd2fc4caae6da963c5fe463 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_16/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_16/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..10871d82503a38856267a3ca533c5685176edc43 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_16/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a314ddd4d5754baa142981e16d9445ed9806e4ce26420831ebfde939c791426 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_18/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_18/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..8ba667b1e555fed8f030c8caa4c0d52a7a10706c --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_18/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7c8913a626fe0fe1101d651b03ee198879e257fe1e09c71474b0b772d993ce6 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_2/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_2/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..764c0cea065a9db4700190f3924c6035b4146b0a --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_2/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6599ca6e6e25a5199a0c72afd9871cc0688a1f76171bbd92de290e87942921e +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_20/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_20/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d893c8f60fd24c34b036e533142bb0367cd728b --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_20/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355222ccafe1cd0c70645187e7fe80ecb89365d9dd75e955b74d3a995c30ee1e +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_4/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_4/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..2e59ed893244dd89eafeaf682847c89c22506df9 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_4/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd66a747cab16842ea4a11b61decbe893f9c53a48cd7fd6c43844f77af16a8a9 +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_6/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_6/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..a1f501b4e4324f499c86c384188f0cd803bd8922 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_6/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:968bcdbd90affe69331dfac9908686e705b9195e938e85335d08d59c9f87a54d +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_8/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_8/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..d7ced7207bf27922066c92360b49094ff9b2ba07 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_epoch_8/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56c7cd43b96774e568964dafc94e86921592335ae1e872d2e5746b35eed9362a +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_final/checkpoint.pt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_final/checkpoint.pt new file mode 100644 index 0000000000000000000000000000000000000000..8d893c8f60fd24c34b036e533142bb0367cd728b --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/lightweight_checkpoint_final/checkpoint.pt @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:355222ccafe1cd0c70645187e7fe80ecb89365d9dd75e955b74d3a995c30ee1e +size 436228790 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00001-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00001-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a59dca28867995c0d05384251ac5f4d62461a226 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00001-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b1879f356aed350030bb40eb45ad362c89d9891096f79a3ab323d3ba5607668 +size 4976698672 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00002-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00002-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..4ab0726caf5e75dd1e5700c7e7899ac8c0798428 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00002-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d433f650646834a83c580877bd60c6d1f88f7755305c12576b5c7058f9af15 +size 4999802720 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00003-of-00003.safetensors b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..555bf0e5d1ba1ecbd8230273b096475bcbb755b9 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b3cc37b9aa92ba6f3e35b0cc1ff891146ba26e826a65d23f2a8b83274554743 +size 2594254592 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model.safetensors.index.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..f152f2d21865fb8f730a69b0a19256f3500d5bd8 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/model.safetensors.index.json @@ -0,0 +1,227 @@ +{ + "metadata": { + "total_parameters": 6285365248, + "total_size": 12570730496 + }, + "weight_map": { + "lm_head.weight": "model-00003-of-00003.safetensors", + "model.embed_tokens.weight": "model-00001-of-00003.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.20.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.20.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.21.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.21.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", + "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", + "model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", + "model.norm.weight": "model-00003-of-00003.safetensors" + } +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/run_args.txt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/run_args.txt new file mode 100644 index 0000000000000000000000000000000000000000..08142bedde1386bc9e21bf4605e57e041bf53eb7 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/run_args.txt @@ -0,0 +1,9 @@ +git_commit=unknown +dataset=Open-Orca/SlimOrca +dataset_split=train +collect_batch_size=8 +train_batch_size=32 +gradient_accumulation_step=8 +target_effective_batch=256 +command: +python /workspace/here/abprune_update/compare_model/LLM-Streamline/mseloss_entry.py --model_name meta-llama/Llama-3.1-8B-Instruct --output_dir /workspace/here/abprune_update/results/llama31_8b_inst_streamline_slimorca_prune8_start21 --dataset Open-Orca/SlimOrca --dataset_split train --layer_intervals 8 --best_layer 21 --cosine_num_data 300 --train_num_data 30000 --epoches 20 --batch_size 8 --collect_batch_size 8 --train_batch_size 32 --dtype bfloat16 --gradient_accumulation_step 8 --lr 1e-5 --min_lr 5e-5 --wd 1e-3 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/special_tokens_map.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..b43be96621d147110fb8a18b5776ec6e38516127 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/special_tokens_map.json @@ -0,0 +1,17 @@ +{ + "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": "<|eot_id|>" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/tokenizer.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/tokenizer_config.json b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..3beeacc86a6ca3cae14ad3004263ab74a4bac07a --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/tokenizer_config.json @@ -0,0 +1,2063 @@ +{ + "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|>", + "tokenizer_class": "PreTrainedTokenizerFast" +} diff --git a/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/train_loss.txt b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/train_loss.txt new file mode 100644 index 0000000000000000000000000000000000000000..86e1b24358f78e74b758345b756755119fc142e1 --- /dev/null +++ b/llmstream_results/llama31_8b_inst_streamline_slimorca_prune8_start21/train_loss.txt @@ -0,0 +1,188 @@ +# Train loss logged every 100 global steps +epoch=0 global_step=100 optimizer_step=12 loss=0.2011718750 +epoch=0 global_step=200 optimizer_step=24 loss=0.2021484375 +epoch=0 global_step=300 optimizer_step=37 loss=0.1923828125 +epoch=0 global_step=400 optimizer_step=49 loss=0.1787109375 +epoch=0 global_step=500 optimizer_step=62 loss=0.1660156250 +epoch=0 global_step=600 optimizer_step=74 loss=0.1533203125 +epoch=0 global_step=700 optimizer_step=87 loss=0.1357421875 +epoch=0 global_step=800 optimizer_step=99 loss=0.1049804688 +epoch=0 global_step=900 optimizer_step=112 loss=0.0971679688 +epoch=1 global_step=1000 optimizer_step=124 loss=0.0937500000 +epoch=1 global_step=1100 optimizer_step=137 loss=0.0854492188 +epoch=1 global_step=1200 optimizer_step=149 loss=0.0893554688 +epoch=1 global_step=1300 optimizer_step=162 loss=0.0874023438 +epoch=1 global_step=1400 optimizer_step=174 loss=0.0844726562 +epoch=1 global_step=1500 optimizer_step=187 loss=0.0859375000 +epoch=1 global_step=1600 optimizer_step=199 loss=0.0869140625 +epoch=1 global_step=1700 optimizer_step=212 loss=0.0781250000 +epoch=1 global_step=1800 optimizer_step=224 loss=0.0815429688 +epoch=2 global_step=1900 optimizer_step=236 loss=0.0834960938 +epoch=2 global_step=2000 optimizer_step=249 loss=0.0869140625 +epoch=2 global_step=2100 optimizer_step=261 loss=0.0747070312 +epoch=2 global_step=2200 optimizer_step=274 loss=0.0849609375 +epoch=2 global_step=2300 optimizer_step=286 loss=0.0654296875 +epoch=2 global_step=2400 optimizer_step=299 loss=0.0644531250 +epoch=2 global_step=2500 optimizer_step=311 loss=0.0588378906 +epoch=2 global_step=2600 optimizer_step=324 loss=0.0698242188 +epoch=2 global_step=2700 optimizer_step=336 loss=0.0830078125 +epoch=2 global_step=2800 optimizer_step=349 loss=0.0805664062 +epoch=3 global_step=2900 optimizer_step=361 loss=0.0722656250 +epoch=3 global_step=3000 optimizer_step=374 loss=0.0688476562 +epoch=3 global_step=3100 optimizer_step=386 loss=0.0625000000 +epoch=3 global_step=3200 optimizer_step=399 loss=0.0625000000 +epoch=3 global_step=3300 optimizer_step=411 loss=0.0634765625 +epoch=3 global_step=3400 optimizer_step=424 loss=0.0678710938 +epoch=3 global_step=3500 optimizer_step=436 loss=0.0742187500 +epoch=3 global_step=3600 optimizer_step=449 loss=0.0620117188 +epoch=3 global_step=3700 optimizer_step=461 loss=0.0620117188 +epoch=4 global_step=3800 optimizer_step=473 loss=0.0654296875 +epoch=4 global_step=3900 optimizer_step=486 loss=0.0747070312 +epoch=4 global_step=4000 optimizer_step=498 loss=0.0791015625 +epoch=4 global_step=4100 optimizer_step=511 loss=0.0722656250 +epoch=4 global_step=4200 optimizer_step=523 loss=0.0722656250 +epoch=4 global_step=4300 optimizer_step=536 loss=0.0747070312 +epoch=4 global_step=4400 optimizer_step=548 loss=0.0751953125 +epoch=4 global_step=4500 optimizer_step=561 loss=0.0693359375 +epoch=4 global_step=4600 optimizer_step=573 loss=0.0612792969 +epoch=5 global_step=4700 optimizer_step=586 loss=0.0678710938 +epoch=5 global_step=4800 optimizer_step=598 loss=0.0532226562 +epoch=5 global_step=4900 optimizer_step=611 loss=0.0688476562 +epoch=5 global_step=5000 optimizer_step=623 loss=0.0639648438 +epoch=5 global_step=5100 optimizer_step=636 loss=0.0649414062 +epoch=5 global_step=5200 optimizer_step=648 loss=0.0649414062 +epoch=5 global_step=5300 optimizer_step=661 loss=0.0649414062 +epoch=5 global_step=5400 optimizer_step=673 loss=0.0634765625 +epoch=5 global_step=5500 optimizer_step=686 loss=0.0668945312 +epoch=5 global_step=5600 optimizer_step=698 loss=0.0605468750 +epoch=6 global_step=5700 optimizer_step=710 loss=0.0664062500 +epoch=6 global_step=5800 optimizer_step=723 loss=0.0571289062 +epoch=6 global_step=5900 optimizer_step=735 loss=0.0634765625 +epoch=6 global_step=6000 optimizer_step=748 loss=0.0693359375 +epoch=6 global_step=6100 optimizer_step=760 loss=0.0683593750 +epoch=6 global_step=6200 optimizer_step=773 loss=0.0590820312 +epoch=6 global_step=6300 optimizer_step=785 loss=0.0761718750 +epoch=6 global_step=6400 optimizer_step=798 loss=0.0578613281 +epoch=6 global_step=6500 optimizer_step=810 loss=0.0600585938 +epoch=7 global_step=6600 optimizer_step=823 loss=0.0581054688 +epoch=7 global_step=6700 optimizer_step=835 loss=0.0639648438 +epoch=7 global_step=6800 optimizer_step=848 loss=0.0654296875 +epoch=7 global_step=6900 optimizer_step=860 loss=0.0654296875 +epoch=7 global_step=7000 optimizer_step=873 loss=0.0649414062 +epoch=7 global_step=7100 optimizer_step=885 loss=0.0561523438 +epoch=7 global_step=7200 optimizer_step=898 loss=0.0576171875 +epoch=7 global_step=7300 optimizer_step=910 loss=0.0610351562 +epoch=7 global_step=7400 optimizer_step=923 loss=0.0688476562 +epoch=7 global_step=7500 optimizer_step=935 loss=0.0612792969 +epoch=8 global_step=7600 optimizer_step=947 loss=0.0673828125 +epoch=8 global_step=7700 optimizer_step=960 loss=0.0593261719 +epoch=8 global_step=7800 optimizer_step=972 loss=0.0571289062 +epoch=8 global_step=7900 optimizer_step=985 loss=0.0683593750 +epoch=8 global_step=8000 optimizer_step=997 loss=0.0603027344 +epoch=8 global_step=8100 optimizer_step=1010 loss=0.0634765625 +epoch=8 global_step=8200 optimizer_step=1022 loss=0.0673828125 +epoch=8 global_step=8300 optimizer_step=1035 loss=0.0742187500 +epoch=8 global_step=8400 optimizer_step=1047 loss=0.0581054688 +epoch=9 global_step=8500 optimizer_step=1060 loss=0.0585937500 +epoch=9 global_step=8600 optimizer_step=1072 loss=0.0563964844 +epoch=9 global_step=8700 optimizer_step=1085 loss=0.0563964844 +epoch=9 global_step=8800 optimizer_step=1097 loss=0.0693359375 +epoch=9 global_step=8900 optimizer_step=1110 loss=0.0688476562 +epoch=9 global_step=9000 optimizer_step=1122 loss=0.0537109375 +epoch=9 global_step=9100 optimizer_step=1135 loss=0.0556640625 +epoch=9 global_step=9200 optimizer_step=1147 loss=0.0766601562 +epoch=9 global_step=9300 optimizer_step=1160 loss=0.0668945312 +epoch=10 global_step=9400 optimizer_step=1172 loss=0.0639648438 +epoch=10 global_step=9500 optimizer_step=1184 loss=0.0649414062 +epoch=10 global_step=9600 optimizer_step=1197 loss=0.0568847656 +epoch=10 global_step=9700 optimizer_step=1209 loss=0.0561523438 +epoch=10 global_step=9800 optimizer_step=1222 loss=0.0644531250 +epoch=10 global_step=9900 optimizer_step=1234 loss=0.0578613281 +epoch=10 global_step=10000 optimizer_step=1247 loss=0.0583496094 +epoch=10 global_step=10100 optimizer_step=1259 loss=0.0751953125 +epoch=10 global_step=10200 optimizer_step=1272 loss=0.0588378906 +epoch=10 global_step=10300 optimizer_step=1284 loss=0.0578613281 +epoch=11 global_step=10400 optimizer_step=1297 loss=0.0742187500 +epoch=11 global_step=10500 optimizer_step=1309 loss=0.0571289062 +epoch=11 global_step=10600 optimizer_step=1322 loss=0.0639648438 +epoch=11 global_step=10700 optimizer_step=1334 loss=0.0678710938 +epoch=11 global_step=10800 optimizer_step=1347 loss=0.0561523438 +epoch=11 global_step=10900 optimizer_step=1359 loss=0.0607910156 +epoch=11 global_step=11000 optimizer_step=1372 loss=0.0524902344 +epoch=11 global_step=11100 optimizer_step=1384 loss=0.0751953125 +epoch=11 global_step=11200 optimizer_step=1397 loss=0.0668945312 +epoch=12 global_step=11300 optimizer_step=1409 loss=0.0654296875 +epoch=12 global_step=11400 optimizer_step=1421 loss=0.0534667969 +epoch=12 global_step=11500 optimizer_step=1434 loss=0.0612792969 +epoch=12 global_step=11600 optimizer_step=1446 loss=0.0622558594 +epoch=12 global_step=11700 optimizer_step=1459 loss=0.0598144531 +epoch=12 global_step=11800 optimizer_step=1471 loss=0.0683593750 +epoch=12 global_step=11900 optimizer_step=1484 loss=0.0522460938 +epoch=12 global_step=12000 optimizer_step=1496 loss=0.0532226562 +epoch=12 global_step=12100 optimizer_step=1509 loss=0.0649414062 +epoch=13 global_step=12200 optimizer_step=1521 loss=0.0581054688 +epoch=13 global_step=12300 optimizer_step=1534 loss=0.0625000000 +epoch=13 global_step=12400 optimizer_step=1546 loss=0.0639648438 +epoch=13 global_step=12500 optimizer_step=1559 loss=0.0639648438 +epoch=13 global_step=12600 optimizer_step=1571 loss=0.0639648438 +epoch=13 global_step=12700 optimizer_step=1584 loss=0.0688476562 +epoch=13 global_step=12800 optimizer_step=1596 loss=0.0664062500 +epoch=13 global_step=12900 optimizer_step=1609 loss=0.0673828125 +epoch=13 global_step=13000 optimizer_step=1621 loss=0.0476074219 +epoch=13 global_step=13100 optimizer_step=1634 loss=0.0578613281 +epoch=14 global_step=13200 optimizer_step=1646 loss=0.0566406250 +epoch=14 global_step=13300 optimizer_step=1658 loss=0.0585937500 +epoch=14 global_step=13400 optimizer_step=1671 loss=0.0546875000 +epoch=14 global_step=13500 optimizer_step=1683 loss=0.0568847656 +epoch=14 global_step=13600 optimizer_step=1696 loss=0.0546875000 +epoch=14 global_step=13700 optimizer_step=1708 loss=0.0622558594 +epoch=14 global_step=13800 optimizer_step=1721 loss=0.0634765625 +epoch=14 global_step=13900 optimizer_step=1733 loss=0.0761718750 +epoch=14 global_step=14000 optimizer_step=1746 loss=0.0625000000 +epoch=15 global_step=14100 optimizer_step=1758 loss=0.0551757812 +epoch=15 global_step=14200 optimizer_step=1771 loss=0.0727539062 +epoch=15 global_step=14300 optimizer_step=1783 loss=0.0659179688 +epoch=15 global_step=14400 optimizer_step=1796 loss=0.0585937500 +epoch=15 global_step=14500 optimizer_step=1808 loss=0.0598144531 +epoch=15 global_step=14600 optimizer_step=1821 loss=0.0644531250 +epoch=15 global_step=14700 optimizer_step=1833 loss=0.0732421875 +epoch=15 global_step=14800 optimizer_step=1846 loss=0.0737304688 +epoch=15 global_step=14900 optimizer_step=1858 loss=0.0588378906 +epoch=15 global_step=15000 optimizer_step=1871 loss=0.0578613281 +epoch=16 global_step=15100 optimizer_step=1883 loss=0.0510253906 +epoch=16 global_step=15200 optimizer_step=1895 loss=0.0698242188 +epoch=16 global_step=15300 optimizer_step=1908 loss=0.0498046875 +epoch=16 global_step=15400 optimizer_step=1920 loss=0.0629882812 +epoch=16 global_step=15500 optimizer_step=1933 loss=0.0522460938 +epoch=16 global_step=15600 optimizer_step=1945 loss=0.0598144531 +epoch=16 global_step=15700 optimizer_step=1958 loss=0.0539550781 +epoch=16 global_step=15800 optimizer_step=1970 loss=0.0541992188 +epoch=16 global_step=15900 optimizer_step=1983 loss=0.0549316406 +epoch=17 global_step=16000 optimizer_step=1995 loss=0.0612792969 +epoch=17 global_step=16100 optimizer_step=2008 loss=0.0561523438 +epoch=17 global_step=16200 optimizer_step=2020 loss=0.0678710938 +epoch=17 global_step=16300 optimizer_step=2033 loss=0.0712890625 +epoch=17 global_step=16400 optimizer_step=2045 loss=0.0607910156 +epoch=17 global_step=16500 optimizer_step=2058 loss=0.0529785156 +epoch=17 global_step=16600 optimizer_step=2070 loss=0.0678710938 +epoch=17 global_step=16700 optimizer_step=2083 loss=0.0539550781 +epoch=17 global_step=16800 optimizer_step=2095 loss=0.0703125000 +epoch=18 global_step=16900 optimizer_step=2107 loss=0.0593261719 +epoch=18 global_step=17000 optimizer_step=2120 loss=0.0683593750 +epoch=18 global_step=17100 optimizer_step=2132 loss=0.0588378906 +epoch=18 global_step=17200 optimizer_step=2145 loss=0.0505371094 +epoch=18 global_step=17300 optimizer_step=2157 loss=0.0493164062 +epoch=18 global_step=17400 optimizer_step=2170 loss=0.0737304688 +epoch=18 global_step=17500 optimizer_step=2182 loss=0.0590820312 +epoch=18 global_step=17600 optimizer_step=2195 loss=0.0583496094 +epoch=18 global_step=17700 optimizer_step=2207 loss=0.0659179688 +epoch=18 global_step=17800 optimizer_step=2220 loss=0.0727539062 +epoch=19 global_step=17900 optimizer_step=2232 loss=0.0539550781 +epoch=19 global_step=18000 optimizer_step=2245 loss=0.0537109375 +epoch=19 global_step=18100 optimizer_step=2257 loss=0.0559082031 +epoch=19 global_step=18200 optimizer_step=2270 loss=0.0573730469 +epoch=19 global_step=18300 optimizer_step=2282 loss=0.0551757812 +epoch=19 global_step=18400 optimizer_step=2295 loss=0.0517578125 +epoch=19 global_step=18500 optimizer_step=2307 loss=0.0576171875 +epoch=19 global_step=18600 optimizer_step=2320 loss=0.0534667969 +epoch=19 global_step=18700 optimizer_step=2332 loss=0.0559082031