Upload folder using huggingface_hub

README.md

@@ -0,0 +1,202 @@
+---
+base_model: ai21labs/AI21-Jamba-1.5-Mini
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.12.0

adapter_config.json

@@ -0,0 +1,38 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "ai21labs/AI21-Jamba-1.5-Mini",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 8,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "down_proj",
+    "up_proj",
+    "out_proj",
+    "x_proj",
+    "in_proj",
+    "v_proj",
+    "q_proj",
+    "gate_proj",
+    "embed_tokens",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41692ffa65157911fb7618fa6b6bc6f4b8ef104e257b5fc7c103dad2fab1d2c
+size 1061034800

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55a703896316aeb91d9ca5265a2cef996013942fd564bf833211c82059b0c69c
+size 1049332688

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c741ff062b9e5fa41a2e2c74153f537ac32edc52afb3552de422680a3bf8bad9
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f690b5a12c96bc867701ba82bb78243d7b91bcd6c93c5ddc786ea740de3b6076
+size 1064

special_tokens_map.json

@@ -0,0 +1,48 @@
+{
+  "additional_special_tokens": [
+    "<|eom|>",
+    "<|bom|>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|tool|>",
+    "<documents>",
+    "</documents>",
+    "<tool_definitions>",
+    "</tool_definitions>",
+    "<active_output_modes>",
+    "</active_output_modes>",
+    "<citations>",
+    "</citations>",
+    "<tool_calls>",
+    "</tool_calls>"
+  ],
+  "bos_token": {
+    "content": "<|startoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|unk|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,196 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|startoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<|unk|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "518": {
+      "content": "<|eom|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "519": {
+      "content": "<|bom|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "520": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "521": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "522": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "523": {
+      "content": "<|tool|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "524": {
+      "content": "<documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "525": {
+      "content": "</documents>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "526": {
+      "content": "<tool_definitions>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "527": {
+      "content": "</tool_definitions>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "528": {
+      "content": "<active_output_modes>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "529": {
+      "content": "</active_output_modes>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "530": {
+      "content": "<citations>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "531": {
+      "content": "</citations>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "532": {
+      "content": "<tool_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "533": {
+      "content": "</tool_calls>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|eom|>",
+    "<|bom|>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|tool|>",
+    "<documents>",
+    "</documents>",
+    "<tool_definitions>",
+    "</tool_definitions>",
+    "<active_output_modes>",
+    "</active_output_modes>",
+    "<citations>",
+    "</citations>",
+    "<tool_calls>",
+    "</tool_calls>"
+  ],
+  "bos_token": "<|startoftext|>",
+  "chat_template": "{# Variables #}\n{% set ns = namespace(message_count=0, is_last_checked_defined=False) %}\n{##}\n{% set bom_str = bom_str or \"<|bom|>\" %}\n{% set eom_str = eom_str or \"<|eom|>\" %}\n{% set default_system_message = \"\" %}\n{##}\n{% set documents_prefix = \"<documents>\" %}\n{% set documents_suffix = \"</documents>\" %}\n{% set tool_definitions_prefix = \"<tool_definitions>\" %}\n{% set tool_definitions_suffix = \"</tool_definitions>\" %}\n{% set active_modes_prefix = \"<active_output_modes>\" %}\n{% set active_modes_suffix = \"</active_output_modes>\" %}\n{##}\n{% set tool_calls_prefix = \"<tool_calls>\" %}\n{% set tool_calls_suffix = \"</tool_calls>\" %}\n{% set citations_prefix = \"<citations>\" %}\n{% set citations_suffix = \"</citations>\" %}\n{##}\n{% if add_generation_prompt is not defined %}\n  {% set add_generation_prompt = True %}\n{% endif %}\n{% set role_to_predict = role_to_predict or \"assistant\" %}\n{% if messages|length > 0 and messages[0].role == \"system\" %}\n  {% set system_message = messages[0].content %}\n  {% set loop_messages = messages[1:] %}\n{% else %}\n  {% set system_message = default_system_message %}\n  {% set loop_messages = messages %}\n{% endif %}\n{##}\n{##}\n{# Macros #}\n{% macro handle_tool_definitions(tools) %}\n  {{- tool_definitions_prefix -}}\n  {{- \"\\n# Tools\" -}}\n  {{- \"\\n\\n## Functions\" -}}\n  {% for tool in tools %}\n    {% set _ = is_param_set(tool, field=\"type\") %}\n    {% set is_tool_type_set = ns.is_last_checked_defined %}\n    {% if is_tool_type_set %}\n      {% if tool.type == \"function\" %}\n        {% set tool = tool.function %}\n      {% else %}\n        {{ raise_exception(\"Currently, the only supported tool type is `function`\") }}\n      {% endif %}\n    {% endif %}\n    {{- \"\\n\\n\" + (tool|tojson(indent=2)) -}}\n  {% endfor %}\n  {{- \"\\n\" + tool_definitions_suffix -}}\n{% endmacro %}\n{##}\n{% macro handle_first_system_message(system_message, tools) %}\n  {{- bom_str + handle_role(\"system\") -}}\n  {% set _ = is_param_set(system_message) %}\n  {% set is_system_message_set = ns.is_last_checked_defined %}\n  {% if is_system_message_set %}\n    {{- system_message -}}\n  {% endif %}\n  {% set _ = is_param_set(tools, is_list=True) %}\n  {% set is_tools_set = ns.is_last_checked_defined %}\n  {% if is_tools_set %}\n    {% if system_message %}\n      {{- \"\\n\\n\" -}}\n    {% endif %}\n    {{- handle_tool_definitions(tools) -}}\n  {% endif %}\n  {% set ns.message_count = ns.message_count + 1 %}\n{% endmacro %}\n{##}\n{% macro handle_tool_calls(tool_calls) %}\n  {{- tool_calls_prefix + \"[\\n\" -}}\n  {% for tool_call in tool_calls %}\n    {% set _ = is_param_set(tool_call, field=\"function\") %}\n    {% set is_tool_call_function_set = ns.is_last_checked_defined %}\n    {% if is_tool_call_function_set %}\n      {%- set tool_call = tool_call.function %}\n    {%- endif %}\n    {% set arguments = tool_call.arguments %}\n    {% if arguments is not string %}\n      {%- set arguments = arguments|tojson -%}\n    {%- endif %}\n    {{ \"{\\\"name\\\": \\\"\" + tool_call.name + \"\\\", \\\"arguments\\\": \" + arguments + \"}\" -}}\n    {% if not loop.last %}\n      {{- \",\" }}\n    {% endif %}\n  {% endfor %}\n  {{- \"\\n]\" + tool_calls_suffix -}}\n{% endmacro %}\n{##}\n{% macro handle_documents(documents) %}\n  {{- documents_prefix -}}\n  {{- \"\\n# Documents\" -}}\n  {{- \"\\n\\nYou can use the following documents for reference:\" -}}\n  {% for doc in documents %}\n    {{- \"\\n\\n## Document ID: \" + loop.index0|string -}}\n    {% set _ = is_param_set(doc, field=\"title\") %}\n    {% set is_doc_title_set = ns.is_last_checked_defined %}\n    {% if is_doc_title_set %}\n      {{- \"\\nTitle: \" + doc.title -}}\n    {% endif %}\n    {% for key, value in doc.items() %}\n      {% if key not in [\"title\", \"text\"] %}\n        {{- \"\\n\" + key|title + \": \" + value|string -}}\n      {% endif %}\n    {% endfor %}\n    {{- \"\\nText: \" + doc.text -}}\n  {% endfor %}\n  {{- \"\\n\" + documents_suffix -}}\n{% endmacro %}\n{##}\n{% macro handle_knobs(knobs) %}\n  {{- active_modes_prefix -}}\n  {{- \"\\n# Active Modes\" -}}\n  {{ \"\\n\\nThe following modes configure the format or style of your responses. You should adhere to all currently\" -}}\n  {{ \" active modes simultaneously.\" -}}\n  {% if knobs.citation_mode == \"fast\" %}\n    {{- \"\\n\\n## Citation Mode\" -}}\n    {{- \"\\n\\nProvide a list of references only for the documents you base your response on. Format your response\" -}}\n    {{ \" with the original answer followed by a citation section. Use this template:\" -}}\n    {{ \" `{answer}\" + citations_prefix + \"DOCUMENT_IDS\" + citations_suffix + \"`, where DOCUMENT_IDS are the relevant document numbers\" -}}\n    {{ \" (e.g. [2, 5, 9]), or [] if the answer cannot be supported by the provided documents.\" -}}\n  {% endif %}\n  {% if knobs.response_format == \"json_object\" %}\n    {{- \"\\n\\n## JSON Mode\" -}}\n    {{ \"\\n\\nProvide your response in JSON format. Adhere strictly to any schema given by the user.\" -}}\n    {{ \" If an appropriate JSON format exists, use it without modification.\" -}}\n  {% endif %}\n  {{- \"\\n\" + active_modes_suffix -}}\n{% endmacro %}\n{##}\n{% macro get_last_user_index(messages) %}\n  {% set ns.last_user_index = 0 %}\n  {% for message in messages %}\n    {% if message.role == 'user' %}\n      {% set ns.last_user_index = loop.index0 %}\n    {% endif %}\n  {% endfor %}\n  {{- ns.last_user_index -}}\n{% endmacro %}\n{##}\n{% macro handle_last_system_message(documents, knobs, use_documents, use_knobs) %}\n  {{- bom_str + handle_role(\"system\") -}}\n  {% set macros_to_call = [] %}\n  {% set params_for_macros = [] %}\n  {% if use_documents %}\n    {% set macros_to_call = macros_to_call + [handle_documents] %}\n    {% set params_for_macros = params_for_macros + [[documents]] %}\n  {% endif %}\n  {% if use_knobs %}\n    {% set macros_to_call = macros_to_call + [handle_knobs] %}\n    {% set params_for_macros = params_for_macros + [[knobs]] %}\n  {% endif %}\n  {% for i in range(macros_to_call|length) %}\n    {% if i > 0 %}\n      {{- \"\\n\\n\" -}}\n    {% endif %}\n    {{- macros_to_call[i](*params_for_macros[i]) -}}\n  {% endfor %}\n  {% set ns.message_count = ns.message_count + 1 %}\n{% endmacro %}\n{##}\n{% macro handle_role(role, add_space=True) %}\n  {{- \"<|\" + role + \"|>\" -}}\n  {% if add_space %}\n    {{- \" \" -}}\n  {% endif %}\n{% endmacro %}\n{##}\n{% macro is_param_set(param, field=none, is_list=False) %}\n  {% if field is not none %}\n    {% if field in param %}\n      {% set param = param[field] %}\n    {% else %}\n      {% set param = none %}\n    {% endif %}\n  {% endif %}\n  {% set is_defined = param is defined and param is not none %}\n  {% if is_list %}\n    {% set ns.is_last_checked_defined = is_defined and param|length > 0 %}\n  {% else %}\n    {% set ns.is_last_checked_defined = is_defined %}\n  {% endif %}\n{% endmacro %}\n{##}\n{##}\n{# Template #}\n{{- \"<|startoftext|>\" -}}\n{% set _ = is_param_set(system_message) %}\n{% set is_system_message_set = ns.is_last_checked_defined %}\n{% set _ = is_param_set(tools, is_list=True) %}\n{% set is_tools_set = ns.is_last_checked_defined %}\n{% set has_system_message = (is_system_message_set or is_tools_set) %}\n{% if has_system_message %}\n  {{- handle_first_system_message(system_message, tools) -}}\n{% endif %}\n{% set last_user_index = get_last_user_index(loop_messages)|int %}\n{% for message in loop_messages %}\n  {% if loop.index0 == last_user_index %}\n    {% set _ = is_param_set(documents, is_list=True) %}\n    {% set use_documents = ns.is_last_checked_defined %}\n    {% set _ = is_param_set(knobs) %}\n    {% set use_knobs = ns.is_last_checked_defined and knobs.is_set %}\n    {% set add_last_system_message = use_documents or use_knobs %}\n    {% if add_last_system_message %}\n      {% if ns.message_count > 0 %}\n        {{- eom_str -}}\n      {% endif %}\n      {{- handle_last_system_message(documents, knobs, use_documents, use_knobs) -}}\n    {% endif %}\n  {% endif %}\n  {% set role = message.role %}\n  {% set _ = is_param_set(message, field=\"name\") %}\n  {% set is_message_name_set = ns.is_last_checked_defined %}\n  {% if is_message_name_set %}\n    {% set message_prefix = handle_role(role) + \"(\" + message.name + \")\" %}\n  {% else %}\n    {% set message_prefix = handle_role(role) %}\n  {% endif %}\n  {% set content = (message.content or \"\") %}\n  {% if content is not string %}\n    {% set content = content|tojson %}\n  {% endif %}\n  {% if ns.message_count > 0 %}\n    {{- eom_str -}}\n  {% endif %}\n  {{- bom_str + message_prefix + content -}}\n  {% set _ = is_param_set(message, field=\"tool_calls\", is_list=True) %}\n  {% set is_tool_calls_set = ns.is_last_checked_defined %}\n  {% if role == \"assistant\" and is_tool_calls_set %}\n    {{- handle_tool_calls(message.tool_calls) -}}\n  {% endif %}\n  {% set _ = is_param_set(message, field=\"citations\", is_list=True) %}\n  {% set is_citations_set = ns.is_last_checked_defined %}\n  {% if role == \"assistant\" and is_citations_set %}\n    {{- citations_prefix + message.citations|map(attribute=\"document_id\")|list|string + citations_suffix -}}\n  {% endif %}\n  {% set ns.message_count = ns.message_count + 1 %}\n{% endfor %}\n{% if add_generation_prompt %}\n  {% if ns.message_count > 0 %}\n    {{- eom_str -}}\n  {% endif %}\n  {{- bom_str + handle_role(role_to_predict, add_space=False) -}}\n  {% set _ = is_param_set(generation_preamble) %}\n  {% set is_generation_preamble_set = ns.is_last_checked_defined %}\n  {% if is_generation_preamble_set and generation_preamble.strip() != \"\" %}\n    {{- \" \" + generation_preamble -}}\n  {% endif %}\n  {% set ns.message_count = ns.message_count + 1 %}\n{% else %}\n  {% if ns.message_count > 0 %}\n    {{- eom_str -}}\n  {% endif %}\n{% endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<|unk|>",
+  "use_default_system_prompt": false
+}

trainer_state.json

@@ -0,0 +1,969 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.11943863839952225,
+  "eval_steps": 100,
+  "global_step": 1200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0009953219866626853,
+      "grad_norm": 1.912980556488037,
+      "learning_rate": 9.995023390066686e-06,
+      "loss": 1.8703,
+      "step": 10
+    },
+    {
+      "epoch": 0.0019906439733253707,
+      "grad_norm": 1.866821050643921,
+      "learning_rate": 9.990046780133374e-06,
+      "loss": 1.8723,
+      "step": 20
+    },
+    {
+      "epoch": 0.002985965959988056,
+      "grad_norm": 2.058809280395508,
+      "learning_rate": 9.985070170200061e-06,
+      "loss": 1.8097,
+      "step": 30
+    },
+    {
+      "epoch": 0.003981287946650741,
+      "grad_norm": 1.459013819694519,
+      "learning_rate": 9.980093560266747e-06,
+      "loss": 1.7456,
+      "step": 40
+    },
+    {
+      "epoch": 0.004976609933313427,
+      "grad_norm": 0.9095586538314819,
+      "learning_rate": 9.975116950333434e-06,
+      "loss": 1.7195,
+      "step": 50
+    },
+    {
+      "epoch": 0.005971931919976112,
+      "grad_norm": 1.1065226793289185,
+      "learning_rate": 9.970140340400121e-06,
+      "loss": 1.6502,
+      "step": 60
+    },
+    {
+      "epoch": 0.0069672539066387975,
+      "grad_norm": 0.8301252126693726,
+      "learning_rate": 9.965163730466807e-06,
+      "loss": 1.5699,
+      "step": 70
+    },
+    {
+      "epoch": 0.007962575893301483,
+      "grad_norm": 1.0762828588485718,
+      "learning_rate": 9.960187120533493e-06,
+      "loss": 1.5072,
+      "step": 80
+    },
+    {
+      "epoch": 0.008957897879964169,
+      "grad_norm": 1.0814900398254395,
+      "learning_rate": 9.95521051060018e-06,
+      "loss": 1.4369,
+      "step": 90
+    },
+    {
+      "epoch": 0.009953219866626855,
+      "grad_norm": 1.3561326265335083,
+      "learning_rate": 9.950233900666867e-06,
+      "loss": 1.3467,
+      "step": 100
+    },
+    {
+      "epoch": 0.009953219866626855,
+      "eval_loss": 1.2846794128417969,
+      "eval_runtime": 147.6242,
+      "eval_samples_per_second": 1.375,
+      "eval_steps_per_second": 0.691,
+      "step": 100
+    },
+    {
+      "epoch": 0.010948541853289539,
+      "grad_norm": 1.438547968864441,
+      "learning_rate": 9.945257290733553e-06,
+      "loss": 1.2222,
+      "step": 110
+    },
+    {
+      "epoch": 0.011943863839952225,
+      "grad_norm": 1.402588963508606,
+      "learning_rate": 9.94028068080024e-06,
+      "loss": 1.1001,
+      "step": 120
+    },
+    {
+      "epoch": 0.012939185826614909,
+      "grad_norm": 1.4357985258102417,
+      "learning_rate": 9.935304070866926e-06,
+      "loss": 0.9657,
+      "step": 130
+    },
+    {
+      "epoch": 0.013934507813277595,
+      "grad_norm": 2.137953042984009,
+      "learning_rate": 9.930327460933613e-06,
+      "loss": 0.8211,
+      "step": 140
+    },
+    {
+      "epoch": 0.014929829799940281,
+      "grad_norm": 1.374299168586731,
+      "learning_rate": 9.925350851000299e-06,
+      "loss": 0.7142,
+      "step": 150
+    },
+    {
+      "epoch": 0.015925151786602965,
+      "grad_norm": 1.1510456800460815,
+      "learning_rate": 9.920374241066986e-06,
+      "loss": 0.656,
+      "step": 160
+    },
+    {
+      "epoch": 0.01692047377326565,
+      "grad_norm": 1.0226788520812988,
+      "learning_rate": 9.915397631133673e-06,
+      "loss": 0.6212,
+      "step": 170
+    },
+    {
+      "epoch": 0.017915795759928337,
+      "grad_norm": 0.9365411400794983,
+      "learning_rate": 9.910421021200359e-06,
+      "loss": 0.6069,
+      "step": 180
+    },
+    {
+      "epoch": 0.018911117746591023,
+      "grad_norm": 0.6880003213882446,
+      "learning_rate": 9.905444411267046e-06,
+      "loss": 0.6128,
+      "step": 190
+    },
+    {
+      "epoch": 0.01990643973325371,
+      "grad_norm": 1.1190361976623535,
+      "learning_rate": 9.900467801333732e-06,
+      "loss": 0.5426,
+      "step": 200
+    },
+    {
+      "epoch": 0.01990643973325371,
+      "eval_loss": 0.5788590908050537,
+      "eval_runtime": 147.511,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.691,
+      "step": 200
+    },
+    {
+      "epoch": 0.02090176171991639,
+      "grad_norm": 1.184279441833496,
+      "learning_rate": 9.895491191400419e-06,
+      "loss": 0.5887,
+      "step": 210
+    },
+    {
+      "epoch": 0.021897083706579078,
+      "grad_norm": 0.7627615928649902,
+      "learning_rate": 9.890514581467106e-06,
+      "loss": 0.5433,
+      "step": 220
+    },
+    {
+      "epoch": 0.022892405693241764,
+      "grad_norm": 0.7858164310455322,
+      "learning_rate": 9.885537971533792e-06,
+      "loss": 0.5843,
+      "step": 230
+    },
+    {
+      "epoch": 0.02388772767990445,
+      "grad_norm": 0.695697009563446,
+      "learning_rate": 9.880561361600478e-06,
+      "loss": 0.5365,
+      "step": 240
+    },
+    {
+      "epoch": 0.024883049666567136,
+      "grad_norm": 0.8994197845458984,
+      "learning_rate": 9.875584751667165e-06,
+      "loss": 0.5662,
+      "step": 250
+    },
+    {
+      "epoch": 0.025878371653229818,
+      "grad_norm": 0.8016309142112732,
+      "learning_rate": 9.870608141733852e-06,
+      "loss": 0.5592,
+      "step": 260
+    },
+    {
+      "epoch": 0.026873693639892504,
+      "grad_norm": 0.8534384369850159,
+      "learning_rate": 9.865631531800538e-06,
+      "loss": 0.5248,
+      "step": 270
+    },
+    {
+      "epoch": 0.02786901562655519,
+      "grad_norm": 0.9857029914855957,
+      "learning_rate": 9.860654921867225e-06,
+      "loss": 0.5294,
+      "step": 280
+    },
+    {
+      "epoch": 0.028864337613217876,
+      "grad_norm": 0.7766090631484985,
+      "learning_rate": 9.855678311933912e-06,
+      "loss": 0.5198,
+      "step": 290
+    },
+    {
+      "epoch": 0.029859659599880562,
+      "grad_norm": 0.6832401752471924,
+      "learning_rate": 9.850701702000598e-06,
+      "loss": 0.5844,
+      "step": 300
+    },
+    {
+      "epoch": 0.029859659599880562,
+      "eval_loss": 0.536589503288269,
+      "eval_runtime": 147.4968,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.692,
+      "step": 300
+    },
+    {
+      "epoch": 0.030854981586543248,
+      "grad_norm": 0.7720848917961121,
+      "learning_rate": 9.845725092067284e-06,
+      "loss": 0.5365,
+      "step": 310
+    },
+    {
+      "epoch": 0.03185030357320593,
+      "grad_norm": 0.7022100687026978,
+      "learning_rate": 9.840748482133971e-06,
+      "loss": 0.4841,
+      "step": 320
+    },
+    {
+      "epoch": 0.03284562555986862,
+      "grad_norm": 1.0030310153961182,
+      "learning_rate": 9.835771872200658e-06,
+      "loss": 0.4635,
+      "step": 330
+    },
+    {
+      "epoch": 0.0338409475465313,
+      "grad_norm": 0.8628882765769958,
+      "learning_rate": 9.830795262267344e-06,
+      "loss": 0.4932,
+      "step": 340
+    },
+    {
+      "epoch": 0.034836269533193985,
+      "grad_norm": 0.7178316712379456,
+      "learning_rate": 9.825818652334031e-06,
+      "loss": 0.6057,
+      "step": 350
+    },
+    {
+      "epoch": 0.035831591519856675,
+      "grad_norm": 0.9564626216888428,
+      "learning_rate": 9.820842042400718e-06,
+      "loss": 0.5371,
+      "step": 360
+    },
+    {
+      "epoch": 0.03682691350651936,
+      "grad_norm": 0.7041760683059692,
+      "learning_rate": 9.815865432467404e-06,
+      "loss": 0.513,
+      "step": 370
+    },
+    {
+      "epoch": 0.037822235493182046,
+      "grad_norm": 1.0203750133514404,
+      "learning_rate": 9.81088882253409e-06,
+      "loss": 0.5118,
+      "step": 380
+    },
+    {
+      "epoch": 0.03881755747984473,
+      "grad_norm": 0.8765382170677185,
+      "learning_rate": 9.805912212600777e-06,
+      "loss": 0.4529,
+      "step": 390
+    },
+    {
+      "epoch": 0.03981287946650742,
+      "grad_norm": 0.9951983690261841,
+      "learning_rate": 9.800935602667464e-06,
+      "loss": 0.5336,
+      "step": 400
+    },
+    {
+      "epoch": 0.03981287946650742,
+      "eval_loss": 0.5151349306106567,
+      "eval_runtime": 147.6615,
+      "eval_samples_per_second": 1.375,
+      "eval_steps_per_second": 0.691,
+      "step": 400
+    },
+    {
+      "epoch": 0.0408082014531701,
+      "grad_norm": 0.7691435813903809,
+      "learning_rate": 9.79595899273415e-06,
+      "loss": 0.506,
+      "step": 410
+    },
+    {
+      "epoch": 0.04180352343983278,
+      "grad_norm": 1.1955533027648926,
+      "learning_rate": 9.790982382800837e-06,
+      "loss": 0.4692,
+      "step": 420
+    },
+    {
+      "epoch": 0.04279884542649547,
+      "grad_norm": 1.128085732460022,
+      "learning_rate": 9.786005772867525e-06,
+      "loss": 0.4608,
+      "step": 430
+    },
+    {
+      "epoch": 0.043794167413158155,
+      "grad_norm": 0.5518949627876282,
+      "learning_rate": 9.78102916293421e-06,
+      "loss": 0.5006,
+      "step": 440
+    },
+    {
+      "epoch": 0.044789489399820845,
+      "grad_norm": 0.7164484858512878,
+      "learning_rate": 9.776052553000896e-06,
+      "loss": 0.4996,
+      "step": 450
+    },
+    {
+      "epoch": 0.04578481138648353,
+      "grad_norm": 0.5959630012512207,
+      "learning_rate": 9.771075943067583e-06,
+      "loss": 0.4843,
+      "step": 460
+    },
+    {
+      "epoch": 0.04678013337314621,
+      "grad_norm": 0.743648111820221,
+      "learning_rate": 9.76609933313427e-06,
+      "loss": 0.4363,
+      "step": 470
+    },
+    {
+      "epoch": 0.0477754553598089,
+      "grad_norm": 0.8757079243659973,
+      "learning_rate": 9.761122723200956e-06,
+      "loss": 0.4665,
+      "step": 480
+    },
+    {
+      "epoch": 0.04877077734647158,
+      "grad_norm": 1.0122153759002686,
+      "learning_rate": 9.756146113267643e-06,
+      "loss": 0.492,
+      "step": 490
+    },
+    {
+      "epoch": 0.04976609933313427,
+      "grad_norm": 0.6179729700088501,
+      "learning_rate": 9.751169503334329e-06,
+      "loss": 0.5022,
+      "step": 500
+    },
+    {
+      "epoch": 0.04976609933313427,
+      "eval_loss": 0.4993921220302582,
+      "eval_runtime": 147.7401,
+      "eval_samples_per_second": 1.374,
+      "eval_steps_per_second": 0.69,
+      "step": 500
+    },
+    {
+      "epoch": 0.050761421319796954,
+      "grad_norm": 0.952812671661377,
+      "learning_rate": 9.746192893401016e-06,
+      "loss": 0.4901,
+      "step": 510
+    },
+    {
+      "epoch": 0.051756743306459636,
+      "grad_norm": 0.6715916991233826,
+      "learning_rate": 9.741216283467702e-06,
+      "loss": 0.5055,
+      "step": 520
+    },
+    {
+      "epoch": 0.052752065293122326,
+      "grad_norm": 0.674640953540802,
+      "learning_rate": 9.736239673534389e-06,
+      "loss": 0.4874,
+      "step": 530
+    },
+    {
+      "epoch": 0.05374738727978501,
+      "grad_norm": 0.7867962718009949,
+      "learning_rate": 9.731263063601075e-06,
+      "loss": 0.4956,
+      "step": 540
+    },
+    {
+      "epoch": 0.0547427092664477,
+      "grad_norm": 0.9035332202911377,
+      "learning_rate": 9.726286453667762e-06,
+      "loss": 0.499,
+      "step": 550
+    },
+    {
+      "epoch": 0.05573803125311038,
+      "grad_norm": 0.7009295225143433,
+      "learning_rate": 9.72130984373445e-06,
+      "loss": 0.5034,
+      "step": 560
+    },
+    {
+      "epoch": 0.05673335323977307,
+      "grad_norm": 0.7018862366676331,
+      "learning_rate": 9.716333233801135e-06,
+      "loss": 0.5137,
+      "step": 570
+    },
+    {
+      "epoch": 0.05772867522643575,
+      "grad_norm": 0.7812825441360474,
+      "learning_rate": 9.711356623867822e-06,
+      "loss": 0.4724,
+      "step": 580
+    },
+    {
+      "epoch": 0.058723997213098435,
+      "grad_norm": 0.6245225071907043,
+      "learning_rate": 9.70638001393451e-06,
+      "loss": 0.4446,
+      "step": 590
+    },
+    {
+      "epoch": 0.059719319199761124,
+      "grad_norm": 0.9083976149559021,
+      "learning_rate": 9.701403404001195e-06,
+      "loss": 0.4884,
+      "step": 600
+    },
+    {
+      "epoch": 0.059719319199761124,
+      "eval_loss": 0.4891846477985382,
+      "eval_runtime": 147.5284,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.691,
+      "step": 600
+    },
+    {
+      "epoch": 0.06071464118642381,
+      "grad_norm": 0.6195352673530579,
+      "learning_rate": 9.69642679406788e-06,
+      "loss": 0.5121,
+      "step": 610
+    },
+    {
+      "epoch": 0.061709963173086496,
+      "grad_norm": 0.8068727254867554,
+      "learning_rate": 9.691450184134568e-06,
+      "loss": 0.4689,
+      "step": 620
+    },
+    {
+      "epoch": 0.06270528515974919,
+      "grad_norm": 1.0427749156951904,
+      "learning_rate": 9.686473574201255e-06,
+      "loss": 0.4968,
+      "step": 630
+    },
+    {
+      "epoch": 0.06370060714641186,
+      "grad_norm": 0.698349118232727,
+      "learning_rate": 9.681496964267941e-06,
+      "loss": 0.4691,
+      "step": 640
+    },
+    {
+      "epoch": 0.06469592913307455,
+      "grad_norm": 0.9104384183883667,
+      "learning_rate": 9.676520354334628e-06,
+      "loss": 0.4775,
+      "step": 650
+    },
+    {
+      "epoch": 0.06569125111973724,
+      "grad_norm": 0.8729726076126099,
+      "learning_rate": 9.671543744401316e-06,
+      "loss": 0.5201,
+      "step": 660
+    },
+    {
+      "epoch": 0.06668657310639992,
+      "grad_norm": 0.9858236908912659,
+      "learning_rate": 9.666567134468001e-06,
+      "loss": 0.4268,
+      "step": 670
+    },
+    {
+      "epoch": 0.0676818950930626,
+      "grad_norm": 2.322754383087158,
+      "learning_rate": 9.661590524534687e-06,
+      "loss": 0.4744,
+      "step": 680
+    },
+    {
+      "epoch": 0.0686772170797253,
+      "grad_norm": 0.9327623248100281,
+      "learning_rate": 9.656613914601374e-06,
+      "loss": 0.4355,
+      "step": 690
+    },
+    {
+      "epoch": 0.06967253906638797,
+      "grad_norm": 0.6949413418769836,
+      "learning_rate": 9.651637304668062e-06,
+      "loss": 0.465,
+      "step": 700
+    },
+    {
+      "epoch": 0.06967253906638797,
+      "eval_loss": 0.4817120432853699,
+      "eval_runtime": 147.5643,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.691,
+      "step": 700
+    },
+    {
+      "epoch": 0.07066786105305066,
+      "grad_norm": 0.5208165049552917,
+      "learning_rate": 9.646660694734747e-06,
+      "loss": 0.4973,
+      "step": 710
+    },
+    {
+      "epoch": 0.07166318303971335,
+      "grad_norm": 0.8434884548187256,
+      "learning_rate": 9.641684084801434e-06,
+      "loss": 0.4721,
+      "step": 720
+    },
+    {
+      "epoch": 0.07265850502637604,
+      "grad_norm": 0.7161769866943359,
+      "learning_rate": 9.636707474868122e-06,
+      "loss": 0.498,
+      "step": 730
+    },
+    {
+      "epoch": 0.07365382701303871,
+      "grad_norm": 0.7036088705062866,
+      "learning_rate": 9.631730864934807e-06,
+      "loss": 0.4672,
+      "step": 740
+    },
+    {
+      "epoch": 0.0746491489997014,
+      "grad_norm": 0.9175013899803162,
+      "learning_rate": 9.626754255001493e-06,
+      "loss": 0.4781,
+      "step": 750
+    },
+    {
+      "epoch": 0.07564447098636409,
+      "grad_norm": 0.678519606590271,
+      "learning_rate": 9.62177764506818e-06,
+      "loss": 0.4048,
+      "step": 760
+    },
+    {
+      "epoch": 0.07663979297302677,
+      "grad_norm": 0.6295528411865234,
+      "learning_rate": 9.616801035134868e-06,
+      "loss": 0.449,
+      "step": 770
+    },
+    {
+      "epoch": 0.07763511495968946,
+      "grad_norm": 0.5424385666847229,
+      "learning_rate": 9.611824425201553e-06,
+      "loss": 0.4394,
+      "step": 780
+    },
+    {
+      "epoch": 0.07863043694635215,
+      "grad_norm": 0.508836030960083,
+      "learning_rate": 9.60684781526824e-06,
+      "loss": 0.4317,
+      "step": 790
+    },
+    {
+      "epoch": 0.07962575893301484,
+      "grad_norm": 0.6004147529602051,
+      "learning_rate": 9.601871205334926e-06,
+      "loss": 0.4308,
+      "step": 800
+    },
+    {
+      "epoch": 0.07962575893301484,
+      "eval_loss": 0.47557342052459717,
+      "eval_runtime": 147.5812,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.691,
+      "step": 800
+    },
+    {
+      "epoch": 0.08062108091967751,
+      "grad_norm": 0.5553786754608154,
+      "learning_rate": 9.596894595401613e-06,
+      "loss": 0.4376,
+      "step": 810
+    },
+    {
+      "epoch": 0.0816164029063402,
+      "grad_norm": 0.7254445552825928,
+      "learning_rate": 9.591917985468299e-06,
+      "loss": 0.4884,
+      "step": 820
+    },
+    {
+      "epoch": 0.08261172489300289,
+      "grad_norm": 0.7175013422966003,
+      "learning_rate": 9.586941375534986e-06,
+      "loss": 0.4167,
+      "step": 830
+    },
+    {
+      "epoch": 0.08360704687966557,
+      "grad_norm": 0.6464620232582092,
+      "learning_rate": 9.581964765601674e-06,
+      "loss": 0.4622,
+      "step": 840
+    },
+    {
+      "epoch": 0.08460236886632826,
+      "grad_norm": 0.6999176144599915,
+      "learning_rate": 9.57698815566836e-06,
+      "loss": 0.4708,
+      "step": 850
+    },
+    {
+      "epoch": 0.08559769085299095,
+      "grad_norm": 0.7939727306365967,
+      "learning_rate": 9.572011545735047e-06,
+      "loss": 0.4633,
+      "step": 860
+    },
+    {
+      "epoch": 0.08659301283965362,
+      "grad_norm": 0.473017156124115,
+      "learning_rate": 9.567034935801732e-06,
+      "loss": 0.4585,
+      "step": 870
+    },
+    {
+      "epoch": 0.08758833482631631,
+      "grad_norm": 0.7265183329582214,
+      "learning_rate": 9.56205832586842e-06,
+      "loss": 0.4485,
+      "step": 880
+    },
+    {
+      "epoch": 0.088583656812979,
+      "grad_norm": 0.539735734462738,
+      "learning_rate": 9.557081715935105e-06,
+      "loss": 0.475,
+      "step": 890
+    },
+    {
+      "epoch": 0.08957897879964169,
+      "grad_norm": 0.7587076425552368,
+      "learning_rate": 9.552105106001792e-06,
+      "loss": 0.4347,
+      "step": 900
+    },
+    {
+      "epoch": 0.08957897879964169,
+      "eval_loss": 0.4690374732017517,
+      "eval_runtime": 147.5672,
+      "eval_samples_per_second": 1.376,
+      "eval_steps_per_second": 0.691,
+      "step": 900
+    },
+    {
+      "epoch": 0.09057430078630437,
+      "grad_norm": 0.7549741864204407,
+      "learning_rate": 9.547128496068478e-06,
+      "loss": 0.4434,
+      "step": 910
+    },
+    {
+      "epoch": 0.09156962277296705,
+      "grad_norm": 0.686689555644989,
+      "learning_rate": 9.542151886135165e-06,
+      "loss": 0.4052,
+      "step": 920
+    },
+    {
+      "epoch": 0.09256494475962974,
+      "grad_norm": 1.02870512008667,
+      "learning_rate": 9.537175276201853e-06,
+      "loss": 0.4806,
+      "step": 930
+    },
+    {
+      "epoch": 0.09356026674629242,
+      "grad_norm": 0.7680675983428955,
+      "learning_rate": 9.532198666268538e-06,
+      "loss": 0.4609,
+      "step": 940
+    },
+    {
+      "epoch": 0.09455558873295511,
+      "grad_norm": 0.5478435754776001,
+      "learning_rate": 9.527222056335224e-06,
+      "loss": 0.4171,
+      "step": 950
+    },
+    {
+      "epoch": 0.0955509107196178,
+      "grad_norm": 0.5974985361099243,
+      "learning_rate": 9.522245446401913e-06,
+      "loss": 0.4686,
+      "step": 960
+    },
+    {
+      "epoch": 0.09654623270628049,
+      "grad_norm": 0.997151792049408,
+      "learning_rate": 9.517268836468598e-06,
+      "loss": 0.4676,
+      "step": 970
+    },
+    {
+      "epoch": 0.09754155469294316,
+      "grad_norm": 0.6366075277328491,
+      "learning_rate": 9.512292226535284e-06,
+      "loss": 0.4467,
+      "step": 980
+    },
+    {
+      "epoch": 0.09853687667960585,
+      "grad_norm": 0.5682553052902222,
+      "learning_rate": 9.507315616601971e-06,
+      "loss": 0.4772,
+      "step": 990
+    },
+    {
+      "epoch": 0.09953219866626854,
+      "grad_norm": 0.5869882106781006,
+      "learning_rate": 9.502339006668659e-06,
+      "loss": 0.3976,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09953219866626854,
+      "eval_loss": 0.46156319975852966,
+      "eval_runtime": 147.6656,
+      "eval_samples_per_second": 1.375,
+      "eval_steps_per_second": 0.691,
+      "step": 1000
+    },
+    {
+      "epoch": 0.10052752065293122,
+      "grad_norm": 0.5758237838745117,
+      "learning_rate": 9.497362396735344e-06,
+      "loss": 0.4528,
+      "step": 1010
+    },
+    {
+      "epoch": 0.10152284263959391,
+      "grad_norm": 0.700281023979187,
+      "learning_rate": 9.492385786802032e-06,
+      "loss": 0.4545,
+      "step": 1020
+    },
+    {
+      "epoch": 0.1025181646262566,
+      "grad_norm": 1.1320914030075073,
+      "learning_rate": 9.487409176868719e-06,
+      "loss": 0.4331,
+      "step": 1030
+    },
+    {
+      "epoch": 0.10351348661291927,
+      "grad_norm": 0.6469867825508118,
+      "learning_rate": 9.482432566935405e-06,
+      "loss": 0.3759,
+      "step": 1040
+    },
+    {
+      "epoch": 0.10450880859958196,
+      "grad_norm": 0.9471383094787598,
+      "learning_rate": 9.47745595700209e-06,
+      "loss": 0.4041,
+      "step": 1050
+    },
+    {
+      "epoch": 0.10550413058624465,
+      "grad_norm": 0.5729160904884338,
+      "learning_rate": 9.472479347068777e-06,
+      "loss": 0.4871,
+      "step": 1060
+    },
+    {
+      "epoch": 0.10649945257290734,
+      "grad_norm": 0.642436683177948,
+      "learning_rate": 9.467502737135465e-06,
+      "loss": 0.3893,
+      "step": 1070
+    },
+    {
+      "epoch": 0.10749477455957002,
+      "grad_norm": 0.95659339427948,
+      "learning_rate": 9.46252612720215e-06,
+      "loss": 0.4486,
+      "step": 1080
+    },
+    {
+      "epoch": 0.1084900965462327,
+      "grad_norm": 0.6642667055130005,
+      "learning_rate": 9.457549517268838e-06,
+      "loss": 0.5168,
+      "step": 1090
+    },
+    {
+      "epoch": 0.1094854185328954,
+      "grad_norm": 0.5805796980857849,
+      "learning_rate": 9.452572907335525e-06,
+      "loss": 0.4019,
+      "step": 1100
+    },
+    {
+      "epoch": 0.1094854185328954,
+      "eval_loss": 0.4559178054332733,
+      "eval_runtime": 147.5891,
+      "eval_samples_per_second": 1.375,
+      "eval_steps_per_second": 0.691,
+      "step": 1100
+    },
+    {
+      "epoch": 0.11048074051955807,
+      "grad_norm": 0.7006909251213074,
+      "learning_rate": 9.44759629740221e-06,
+      "loss": 0.457,
+      "step": 1110
+    },
+    {
+      "epoch": 0.11147606250622076,
+      "grad_norm": 1.1821540594100952,
+      "learning_rate": 9.442619687468896e-06,
+      "loss": 0.3484,
+      "step": 1120
+    },
+    {
+      "epoch": 0.11247138449288345,
+      "grad_norm": 0.7232743501663208,
+      "learning_rate": 9.437643077535584e-06,
+      "loss": 0.417,
+      "step": 1130
+    },
+    {
+      "epoch": 0.11346670647954614,
+      "grad_norm": 0.6104183197021484,
+      "learning_rate": 9.43266646760227e-06,
+      "loss": 0.4821,
+      "step": 1140
+    },
+    {
+      "epoch": 0.11446202846620881,
+      "grad_norm": 0.5961386561393738,
+      "learning_rate": 9.427689857668956e-06,
+      "loss": 0.4834,
+      "step": 1150
+    },
+    {
+      "epoch": 0.1154573504528715,
+      "grad_norm": 0.5530894994735718,
+      "learning_rate": 9.422713247735644e-06,
+      "loss": 0.443,
+      "step": 1160
+    },
+    {
+      "epoch": 0.1164526724395342,
+      "grad_norm": 0.5148622393608093,
+      "learning_rate": 9.41773663780233e-06,
+      "loss": 0.4029,
+      "step": 1170
+    },
+    {
+      "epoch": 0.11744799442619687,
+      "grad_norm": 0.6148583292961121,
+      "learning_rate": 9.412760027869017e-06,
+      "loss": 0.4308,
+      "step": 1180
+    },
+    {
+      "epoch": 0.11844331641285956,
+      "grad_norm": 0.7840449213981628,
+      "learning_rate": 9.407783417935702e-06,
+      "loss": 0.499,
+      "step": 1190
+    },
+    {
+      "epoch": 0.11943863839952225,
+      "grad_norm": 0.6757422089576721,
+      "learning_rate": 9.40280680800239e-06,
+      "loss": 0.4263,
+      "step": 1200
+    },
+    {
+      "epoch": 0.11943863839952225,
+      "eval_loss": 0.4505193829536438,
+      "eval_runtime": 147.6664,
+      "eval_samples_per_second": 1.375,
+      "eval_steps_per_second": 0.691,
+      "step": 1200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 20094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.756627798568276e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c7aafcd6219383d43af3afb872b499570b7bc3857059e6738e1f455694febb5
+size 5432