Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,209 @@
+---
+base_model: meta-llama/Llama-3.1-70B-Instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:meta-llama/Llama-3.1-70B-Instruct
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.19.1

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "meta-llama/Llama-3.1-70B-Instruct",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "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": 128,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "down_proj",
+    "v_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70dfc47e0b8942e01f09fd2390c2d676ed906dfdc431051a20dc6b14838aaf08
+size 3313653480

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 %}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "is_local": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "tokenizer_class": "TokenizersBackend"
+}

trainer_state.json

@@ -0,0 +1,1594 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 156,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 1.3164514303207397,
+      "epoch": 0.012861736334405145,
+      "grad_norm": 1.3205718994140625,
+      "learning_rate": 0.0,
+      "loss": 2.108562469482422,
+      "mean_token_accuracy": 0.5302465185523033,
+      "num_tokens": 125343.0,
+      "step": 1
+    },
+    {
+      "entropy": 1.3486243188381195,
+      "epoch": 0.02572347266881029,
+      "grad_norm": 1.291916847229004,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 2.126715898513794,
+      "mean_token_accuracy": 0.5257277637720108,
+      "num_tokens": 254461.0,
+      "step": 2
+    },
+    {
+      "entropy": 1.3619738817214966,
+      "epoch": 0.03858520900321544,
+      "grad_norm": 1.2188917398452759,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.027977705001831,
+      "mean_token_accuracy": 0.53680220246315,
+      "num_tokens": 384058.0,
+      "step": 3
+    },
+    {
+      "entropy": 1.4663979560136795,
+      "epoch": 0.05144694533762058,
+      "grad_norm": 0.9349287152290344,
+      "learning_rate": 1.25e-05,
+      "loss": 1.9901375770568848,
+      "mean_token_accuracy": 0.5396364852786064,
+      "num_tokens": 512679.0,
+      "step": 4
+    },
+    {
+      "entropy": 1.6146472543478012,
+      "epoch": 0.06430868167202572,
+      "grad_norm": 0.6370308995246887,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.9074194431304932,
+      "mean_token_accuracy": 0.5429708510637283,
+      "num_tokens": 642851.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.7623443454504013,
+      "epoch": 0.07717041800643087,
+      "grad_norm": 0.41252008080482483,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 1.815047264099121,
+      "mean_token_accuracy": 0.557150200009346,
+      "num_tokens": 771427.0,
+      "step": 6
+    },
+    {
+      "entropy": 1.9809899777173996,
+      "epoch": 0.09003215434083602,
+      "grad_norm": 0.5013964772224426,
+      "learning_rate": 2.5e-05,
+      "loss": 1.824620246887207,
+      "mean_token_accuracy": 0.5521566867828369,
+      "num_tokens": 900229.0,
+      "step": 7
+    },
+    {
+      "entropy": 2.035237669944763,
+      "epoch": 0.10289389067524116,
+      "grad_norm": 0.5846648812294006,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.767448902130127,
+      "mean_token_accuracy": 0.5620294511318207,
+      "num_tokens": 1028916.0,
+      "step": 8
+    },
+    {
+      "entropy": 1.9594171047210693,
+      "epoch": 0.1157556270096463,
+      "grad_norm": 0.5288171172142029,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.7006888389587402,
+      "mean_token_accuracy": 0.5697884187102318,
+      "num_tokens": 1157441.0,
+      "step": 9
+    },
+    {
+      "entropy": 1.7999890595674515,
+      "epoch": 0.12861736334405144,
+      "grad_norm": 0.4071674346923828,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.625780701637268,
+      "mean_token_accuracy": 0.5814985409379005,
+      "num_tokens": 1285378.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.658578023314476,
+      "epoch": 0.1414790996784566,
+      "grad_norm": 0.3109852075576782,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.5975825786590576,
+      "mean_token_accuracy": 0.5808091089129448,
+      "num_tokens": 1413453.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.4805417656898499,
+      "epoch": 0.15434083601286175,
+      "grad_norm": 0.2870834469795227,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.518122673034668,
+      "mean_token_accuracy": 0.5996171087026596,
+      "num_tokens": 1542982.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.3833045214414597,
+      "epoch": 0.16720257234726688,
+      "grad_norm": 0.27810704708099365,
+      "learning_rate": 5e-05,
+      "loss": 1.4639174938201904,
+      "mean_token_accuracy": 0.6109028086066246,
+      "num_tokens": 1672219.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.3444313406944275,
+      "epoch": 0.18006430868167203,
+      "grad_norm": 0.2850067615509033,
+      "learning_rate": 4.9997496794168726e-05,
+      "loss": 1.4495856761932373,
+      "mean_token_accuracy": 0.6085417345166206,
+      "num_tokens": 1801169.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.3875805139541626,
+      "epoch": 0.19292604501607716,
+      "grad_norm": 0.22854836285114288,
+      "learning_rate": 4.998998767795805e-05,
+      "loss": 1.4494396448135376,
+      "mean_token_accuracy": 0.6096145436167717,
+      "num_tokens": 1929597.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.4042701870203018,
+      "epoch": 0.2057877813504823,
+      "grad_norm": 0.25544342398643494,
+      "learning_rate": 4.9977474155117045e-05,
+      "loss": 1.4276520013809204,
+      "mean_token_accuracy": 0.6092700362205505,
+      "num_tokens": 2058901.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.3920131623744965,
+      "epoch": 0.21864951768488747,
+      "grad_norm": 0.2532227039337158,
+      "learning_rate": 4.995995873155958e-05,
+      "loss": 1.372622013092041,
+      "mean_token_accuracy": 0.6218594387173653,
+      "num_tokens": 2188340.0,
+      "step": 17
+    },
+    {
+      "entropy": 1.4117262363433838,
+      "epoch": 0.2315112540192926,
+      "grad_norm": 0.23465679585933685,
+      "learning_rate": 4.99374449148625e-05,
+      "loss": 1.3505568504333496,
+      "mean_token_accuracy": 0.6291927620768547,
+      "num_tokens": 2317737.0,
+      "step": 18
+    },
+    {
+      "entropy": 1.39142644405365,
+      "epoch": 0.24437299035369775,
+      "grad_norm": 0.1970938742160797,
+      "learning_rate": 4.9909937213563165e-05,
+      "loss": 1.3315509557724,
+      "mean_token_accuracy": 0.6313857734203339,
+      "num_tokens": 2447871.0,
+      "step": 19
+    },
+    {
+      "entropy": 1.396314412355423,
+      "epoch": 0.2572347266881029,
+      "grad_norm": 0.19241943955421448,
+      "learning_rate": 4.987744113625665e-05,
+      "loss": 1.3494808673858643,
+      "mean_token_accuracy": 0.6292985901236534,
+      "num_tokens": 2575540.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.332438975572586,
+      "epoch": 0.27009646302250806,
+      "grad_norm": 0.19267837703227997,
+      "learning_rate": 4.9839963190492576e-05,
+      "loss": 1.293985366821289,
+      "mean_token_accuracy": 0.640266053378582,
+      "num_tokens": 2701365.0,
+      "step": 21
+    },
+    {
+      "entropy": 1.3236675560474396,
+      "epoch": 0.2829581993569132,
+      "grad_norm": 0.18189704418182373,
+      "learning_rate": 4.979751088147192e-05,
+      "loss": 1.2964701652526855,
+      "mean_token_accuracy": 0.6390737816691399,
+      "num_tokens": 2830897.0,
+      "step": 22
+    },
+    {
+      "entropy": 1.3403686434030533,
+      "epoch": 0.2958199356913183,
+      "grad_norm": 0.16925957798957825,
+      "learning_rate": 4.975009271054409e-05,
+      "loss": 1.313760757446289,
+      "mean_token_accuracy": 0.6331784650683403,
+      "num_tokens": 2960144.0,
+      "step": 23
+    },
+    {
+      "entropy": 1.3093593418598175,
+      "epoch": 0.3086816720257235,
+      "grad_norm": 0.17534375190734863,
+      "learning_rate": 4.969771817350445e-05,
+      "loss": 1.2865062952041626,
+      "mean_token_accuracy": 0.6429941952228546,
+      "num_tokens": 3089440.0,
+      "step": 24
+    },
+    {
+      "entropy": 1.2958146631717682,
+      "epoch": 0.3215434083601286,
+      "grad_norm": 0.18624980747699738,
+      "learning_rate": 4.9640397758692715e-05,
+      "loss": 1.2817679643630981,
+      "mean_token_accuracy": 0.6394432112574577,
+      "num_tokens": 3217927.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.252070963382721,
+      "epoch": 0.33440514469453375,
+      "grad_norm": 0.16373585164546967,
+      "learning_rate": 4.957814294489261e-05,
+      "loss": 1.2472319602966309,
+      "mean_token_accuracy": 0.6489637866616249,
+      "num_tokens": 3347968.0,
+      "step": 26
+    },
+    {
+      "entropy": 1.239806517958641,
+      "epoch": 0.34726688102893893,
+      "grad_norm": 0.15866123139858246,
+      "learning_rate": 4.9510966199033174e-05,
+      "loss": 1.2464823722839355,
+      "mean_token_accuracy": 0.6469453647732735,
+      "num_tokens": 3476400.0,
+      "step": 27
+    },
+    {
+      "entropy": 1.2075979709625244,
+      "epoch": 0.36012861736334406,
+      "grad_norm": 0.15684208273887634,
+      "learning_rate": 4.943888097369216e-05,
+      "loss": 1.2147959470748901,
+      "mean_token_accuracy": 0.6535271480679512,
+      "num_tokens": 3606524.0,
+      "step": 28
+    },
+    {
+      "entropy": 1.2250622063875198,
+      "epoch": 0.3729903536977492,
+      "grad_norm": 0.16190986335277557,
+      "learning_rate": 4.936190170440208e-05,
+      "loss": 1.2240623235702515,
+      "mean_token_accuracy": 0.652711808681488,
+      "num_tokens": 3735020.0,
+      "step": 29
+    },
+    {
+      "entropy": 1.2123340517282486,
+      "epoch": 0.3858520900321543,
+      "grad_norm": 0.16800783574581146,
+      "learning_rate": 4.928004380675941e-05,
+      "loss": 1.204244613647461,
+      "mean_token_accuracy": 0.6567093506455421,
+      "num_tokens": 3865295.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.2247880101203918,
+      "epoch": 0.3987138263665595,
+      "grad_norm": 0.14405229687690735,
+      "learning_rate": 4.9193323673337476e-05,
+      "loss": 1.1991829872131348,
+      "mean_token_accuracy": 0.6602997556328773,
+      "num_tokens": 3994821.0,
+      "step": 31
+    },
+    {
+      "entropy": 1.2614206820726395,
+      "epoch": 0.4115755627009646,
+      "grad_norm": 0.15460604429244995,
+      "learning_rate": 4.910175867040377e-05,
+      "loss": 1.216886043548584,
+      "mean_token_accuracy": 0.6516416072845459,
+      "num_tokens": 4124589.0,
+      "step": 32
+    },
+    {
+      "entropy": 1.227910652756691,
+      "epoch": 0.42443729903536975,
+      "grad_norm": 0.16159985959529877,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 1.2033252716064453,
+      "mean_token_accuracy": 0.6573327481746674,
+      "num_tokens": 4251091.0,
+      "step": 33
+    },
+    {
+      "entropy": 1.2353373318910599,
+      "epoch": 0.43729903536977494,
+      "grad_norm": 0.14645665884017944,
+      "learning_rate": 4.890416836848127e-05,
+      "loss": 1.2113966941833496,
+      "mean_token_accuracy": 0.6547944620251656,
+      "num_tokens": 4381459.0,
+      "step": 34
+    },
+    {
+      "entropy": 1.224476620554924,
+      "epoch": 0.45016077170418006,
+      "grad_norm": 0.14515644311904907,
+      "learning_rate": 4.8798182638228166e-05,
+      "loss": 1.2142887115478516,
+      "mean_token_accuracy": 0.6527992635965347,
+      "num_tokens": 4510718.0,
+      "step": 35
+    },
+    {
+      "entropy": 1.1847395598888397,
+      "epoch": 0.4630225080385852,
+      "grad_norm": 0.14294442534446716,
+      "learning_rate": 4.868743116801074e-05,
+      "loss": 1.1840288639068604,
+      "mean_token_accuracy": 0.661017507314682,
+      "num_tokens": 4638887.0,
+      "step": 36
+    },
+    {
+      "entropy": 1.1811462491750717,
+      "epoch": 0.4758842443729904,
+      "grad_norm": 0.14014433324337006,
+      "learning_rate": 4.857193613652711e-05,
+      "loss": 1.1855542659759521,
+      "mean_token_accuracy": 0.6628495678305626,
+      "num_tokens": 4768654.0,
+      "step": 37
+    },
+    {
+      "entropy": 1.1724539399147034,
+      "epoch": 0.4887459807073955,
+      "grad_norm": 0.13748519122600555,
+      "learning_rate": 4.845172067240415e-05,
+      "loss": 1.1737499237060547,
+      "mean_token_accuracy": 0.6616369336843491,
+      "num_tokens": 4897218.0,
+      "step": 38
+    },
+    {
+      "entropy": 1.1392606794834137,
+      "epoch": 0.5016077170418006,
+      "grad_norm": 0.13618677854537964,
+      "learning_rate": 4.8326808849565936e-05,
+      "loss": 1.1376512050628662,
+      "mean_token_accuracy": 0.6733426377177238,
+      "num_tokens": 5025378.0,
+      "step": 39
+    },
+    {
+      "entropy": 1.1519914269447327,
+      "epoch": 0.5144694533762058,
+      "grad_norm": 0.3906066119670868,
+      "learning_rate": 4.819722568241274e-05,
+      "loss": 1.143772840499878,
+      "mean_token_accuracy": 0.6695929691195488,
+      "num_tokens": 5155612.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.1371284574270248,
+      "epoch": 0.5273311897106109,
+      "grad_norm": 0.13867925107479095,
+      "learning_rate": 4.806299712081172e-05,
+      "loss": 1.1251044273376465,
+      "mean_token_accuracy": 0.6758962124586105,
+      "num_tokens": 5284700.0,
+      "step": 41
+    },
+    {
+      "entropy": 1.137900173664093,
+      "epoch": 0.5401929260450161,
+      "grad_norm": 0.1261901706457138,
+      "learning_rate": 4.792415004490034e-05,
+      "loss": 1.1260221004486084,
+      "mean_token_accuracy": 0.6749331429600716,
+      "num_tokens": 5414507.0,
+      "step": 42
+    },
+    {
+      "entropy": 1.1564348489046097,
+      "epoch": 0.5530546623794212,
+      "grad_norm": 0.13415029644966125,
+      "learning_rate": 4.77807122597034e-05,
+      "loss": 1.1496460437774658,
+      "mean_token_accuracy": 0.6670970395207405,
+      "num_tokens": 5542542.0,
+      "step": 43
+    },
+    {
+      "entropy": 1.1538237184286118,
+      "epoch": 0.5659163987138264,
+      "grad_norm": 0.13376805186271667,
+      "learning_rate": 4.7632712489564926e-05,
+      "loss": 1.142371416091919,
+      "mean_token_accuracy": 0.6690651848912239,
+      "num_tokens": 5672067.0,
+      "step": 44
+    },
+    {
+      "entropy": 1.1469541490077972,
+      "epoch": 0.5787781350482315,
+      "grad_norm": 0.1293802261352539,
+      "learning_rate": 4.748018037239592e-05,
+      "loss": 1.1333601474761963,
+      "mean_token_accuracy": 0.6723547354340553,
+      "num_tokens": 5800609.0,
+      "step": 45
+    },
+    {
+      "entropy": 1.1472823396325111,
+      "epoch": 0.5916398713826366,
+      "grad_norm": 0.13228115439414978,
+      "learning_rate": 4.732314645373921e-05,
+      "loss": 1.1329843997955322,
+      "mean_token_accuracy": 0.6703030541539192,
+      "num_tokens": 5930479.0,
+      "step": 46
+    },
+    {
+      "entropy": 1.1718984246253967,
+      "epoch": 0.6045016077170418,
+      "grad_norm": 0.13948604464530945,
+      "learning_rate": 4.7161642180652464e-05,
+      "loss": 1.1499552726745605,
+      "mean_token_accuracy": 0.6675512716174126,
+      "num_tokens": 6059629.0,
+      "step": 47
+    },
+    {
+      "entropy": 1.1396477073431015,
+      "epoch": 0.617363344051447,
+      "grad_norm": 0.1955496221780777,
+      "learning_rate": 4.699569989541074e-05,
+      "loss": 1.1260184049606323,
+      "mean_token_accuracy": 0.6692441701889038,
+      "num_tokens": 6188823.0,
+      "step": 48
+    },
+    {
+      "entropy": 1.1151351928710938,
+      "epoch": 0.6302250803858521,
+      "grad_norm": 0.12929458916187286,
+      "learning_rate": 4.6825352829029705e-05,
+      "loss": 1.113462209701538,
+      "mean_token_accuracy": 0.6757279857993126,
+      "num_tokens": 6318206.0,
+      "step": 49
+    },
+    {
+      "entropy": 1.1347133666276932,
+      "epoch": 0.6430868167202572,
+      "grad_norm": 0.13723939657211304,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 1.1344139575958252,
+      "mean_token_accuracy": 0.6683605685830116,
+      "num_tokens": 6447361.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.1195298731327057,
+      "epoch": 0.6559485530546624,
+      "grad_norm": 0.13720719516277313,
+      "learning_rate": 4.647158168051066e-05,
+      "loss": 1.1230884790420532,
+      "mean_token_accuracy": 0.6711617782711983,
+      "num_tokens": 6575145.0,
+      "step": 51
+    },
+    {
+      "entropy": 1.1320514380931854,
+      "epoch": 0.6688102893890675,
+      "grad_norm": 0.13503903150558472,
+      "learning_rate": 4.628822844333278e-05,
+      "loss": 1.1332721710205078,
+      "mean_token_accuracy": 0.6704861670732498,
+      "num_tokens": 6704707.0,
+      "step": 52
+    },
+    {
+      "entropy": 1.089632272720337,
+      "epoch": 0.6816720257234726,
+      "grad_norm": 0.13158641755580902,
+      "learning_rate": 4.6100612100748765e-05,
+      "loss": 1.0860098600387573,
+      "mean_token_accuracy": 0.6809655949473381,
+      "num_tokens": 6833251.0,
+      "step": 53
+    },
+    {
+      "entropy": 1.0989741384983063,
+      "epoch": 0.6945337620578779,
+      "grad_norm": 0.1341676563024521,
+      "learning_rate": 4.59087702241444e-05,
+      "loss": 1.0967470407485962,
+      "mean_token_accuracy": 0.6795956119894981,
+      "num_tokens": 6962347.0,
+      "step": 54
+    },
+    {
+      "entropy": 1.1306142508983612,
+      "epoch": 0.707395498392283,
+      "grad_norm": 0.13467787206172943,
+      "learning_rate": 4.571274123109606e-05,
+      "loss": 1.1218006610870361,
+      "mean_token_accuracy": 0.671770267188549,
+      "num_tokens": 7092228.0,
+      "step": 55
+    },
+    {
+      "entropy": 1.1027807146310806,
+      "epoch": 0.7202572347266881,
+      "grad_norm": 0.13593968749046326,
+      "learning_rate": 4.551256437767719e-05,
+      "loss": 1.095794439315796,
+      "mean_token_accuracy": 0.6783477663993835,
+      "num_tokens": 7221530.0,
+      "step": 56
+    },
+    {
+      "entropy": 1.107944592833519,
+      "epoch": 0.7331189710610932,
+      "grad_norm": 0.1346762329339981,
+      "learning_rate": 4.530827975059715e-05,
+      "loss": 1.1026043891906738,
+      "mean_token_accuracy": 0.678081251680851,
+      "num_tokens": 7351093.0,
+      "step": 57
+    },
+    {
+      "entropy": 1.0734399557113647,
+      "epoch": 0.7459807073954984,
+      "grad_norm": 0.13501109182834625,
+      "learning_rate": 4.5099928259173516e-05,
+      "loss": 1.0623465776443481,
+      "mean_token_accuracy": 0.6868591457605362,
+      "num_tokens": 7480072.0,
+      "step": 58
+    },
+    {
+      "entropy": 1.1313968002796173,
+      "epoch": 0.7588424437299035,
+      "grad_norm": 0.13890723884105682,
+      "learning_rate": 4.488755162713975e-05,
+      "loss": 1.1160048246383667,
+      "mean_token_accuracy": 0.6727871224284172,
+      "num_tokens": 7609332.0,
+      "step": 59
+    },
+    {
+      "entropy": 1.095849946141243,
+      "epoch": 0.7717041800643086,
+      "grad_norm": 0.13449780642986298,
+      "learning_rate": 4.467119238428975e-05,
+      "loss": 1.0761332511901855,
+      "mean_token_accuracy": 0.6832353696227074,
+      "num_tokens": 7738055.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.1199684739112854,
+      "epoch": 0.7845659163987139,
+      "grad_norm": 0.1393275260925293,
+      "learning_rate": 4.445089385796099e-05,
+      "loss": 1.103759527206421,
+      "mean_token_accuracy": 0.6751135662198067,
+      "num_tokens": 7866931.0,
+      "step": 61
+    },
+    {
+      "entropy": 1.1070469170808792,
+      "epoch": 0.797427652733119,
+      "grad_norm": 0.1381961554288864,
+      "learning_rate": 4.422670016435792e-05,
+      "loss": 1.0982931852340698,
+      "mean_token_accuracy": 0.6770086959004402,
+      "num_tokens": 7996176.0,
+      "step": 62
+    },
+    {
+      "entropy": 1.094884604215622,
+      "epoch": 0.8102893890675241,
+      "grad_norm": 0.13925445079803467,
+      "learning_rate": 4.3998656199717435e-05,
+      "loss": 1.0968135595321655,
+      "mean_token_accuracy": 0.6778521537780762,
+      "num_tokens": 8122564.0,
+      "step": 63
+    },
+    {
+      "entropy": 1.1247451156377792,
+      "epoch": 0.8231511254019293,
+      "grad_norm": 0.1368095874786377,
+      "learning_rate": 4.3766807631318106e-05,
+      "loss": 1.1230825185775757,
+      "mean_token_accuracy": 0.6699690893292427,
+      "num_tokens": 8248931.0,
+      "step": 64
+    },
+    {
+      "entropy": 1.1110749542713165,
+      "epoch": 0.8360128617363344,
+      "grad_norm": 0.1357615739107132,
+      "learning_rate": 4.353120088833501e-05,
+      "loss": 1.1095378398895264,
+      "mean_token_accuracy": 0.674089215695858,
+      "num_tokens": 8377505.0,
+      "step": 65
+    },
+    {
+      "entropy": 1.0629576370120049,
+      "epoch": 0.8488745980707395,
+      "grad_norm": 0.13470520079135895,
+      "learning_rate": 4.329188315254196e-05,
+      "loss": 1.0582916736602783,
+      "mean_token_accuracy": 0.6866432577371597,
+      "num_tokens": 8506057.0,
+      "step": 66
+    },
+    {
+      "entropy": 1.093516543507576,
+      "epoch": 0.8617363344051447,
+      "grad_norm": 0.13414740562438965,
+      "learning_rate": 4.3048902348863116e-05,
+      "loss": 1.0902202129364014,
+      "mean_token_accuracy": 0.6787593588232994,
+      "num_tokens": 8634840.0,
+      "step": 67
+    },
+    {
+      "entropy": 1.1101883202791214,
+      "epoch": 0.8745980707395499,
+      "grad_norm": 0.15326927602291107,
+      "learning_rate": 4.280230713577564e-05,
+      "loss": 1.1111077070236206,
+      "mean_token_accuracy": 0.6747671589255333,
+      "num_tokens": 8764641.0,
+      "step": 68
+    },
+    {
+      "entropy": 1.1037775576114655,
+      "epoch": 0.887459807073955,
+      "grad_norm": 0.13019205629825592,
+      "learning_rate": 4.255214689556557e-05,
+      "loss": 1.0991560220718384,
+      "mean_token_accuracy": 0.6750917881727219,
+      "num_tokens": 8894121.0,
+      "step": 69
+    },
+    {
+      "entropy": 1.0799639970064163,
+      "epoch": 0.9003215434083601,
+      "grad_norm": 0.13600145280361176,
+      "learning_rate": 4.229847172443866e-05,
+      "loss": 1.0659914016723633,
+      "mean_token_accuracy": 0.6862578168511391,
+      "num_tokens": 9021109.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.0842745453119278,
+      "epoch": 0.9131832797427653,
+      "grad_norm": 0.13035736978054047,
+      "learning_rate": 4.204133242248832e-05,
+      "loss": 1.0697667598724365,
+      "mean_token_accuracy": 0.6838485077023506,
+      "num_tokens": 9150645.0,
+      "step": 71
+    },
+    {
+      "entropy": 1.0927303433418274,
+      "epoch": 0.9260450160771704,
+      "grad_norm": 0.12931469082832336,
+      "learning_rate": 4.1780780483522575e-05,
+      "loss": 1.0853153467178345,
+      "mean_token_accuracy": 0.6794879287481308,
+      "num_tokens": 9279241.0,
+      "step": 72
+    },
+    {
+      "entropy": 1.0969749689102173,
+      "epoch": 0.9389067524115756,
+      "grad_norm": 0.14029595255851746,
+      "learning_rate": 4.151686808475204e-05,
+      "loss": 1.0877366065979004,
+      "mean_token_accuracy": 0.6796814650297165,
+      "num_tokens": 9409900.0,
+      "step": 73
+    },
+    {
+      "entropy": 1.0737035870552063,
+      "epoch": 0.9517684887459807,
+      "grad_norm": 0.13181892037391663,
+      "learning_rate": 4.1249648076341165e-05,
+      "loss": 1.0674468278884888,
+      "mean_token_accuracy": 0.6823575049638748,
+      "num_tokens": 9539355.0,
+      "step": 74
+    },
+    {
+      "entropy": 1.077784962952137,
+      "epoch": 0.9646302250803859,
+      "grad_norm": 0.13357527554035187,
+      "learning_rate": 4.0979173970824626e-05,
+      "loss": 1.0709781646728516,
+      "mean_token_accuracy": 0.6832851618528366,
+      "num_tokens": 9669661.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.0898889154195786,
+      "epoch": 0.977491961414791,
+      "grad_norm": 0.1380884051322937,
+      "learning_rate": 4.070549993239106e-05,
+      "loss": 1.079447627067566,
+      "mean_token_accuracy": 0.6803383082151413,
+      "num_tokens": 9799265.0,
+      "step": 76
+    },
+    {
+      "entropy": 1.1030114442110062,
+      "epoch": 0.9903536977491961,
+      "grad_norm": 0.14150051772594452,
+      "learning_rate": 4.0428680766036384e-05,
+      "loss": 1.0985944271087646,
+      "mean_token_accuracy": 0.6765774413943291,
+      "num_tokens": 9928475.0,
+      "step": 77
+    },
+    {
+      "entropy": 1.1045236786206563,
+      "epoch": 1.0,
+      "grad_norm": 0.15571743249893188,
+      "learning_rate": 4.0148771906588706e-05,
+      "loss": 1.078245759010315,
+      "mean_token_accuracy": 0.6769482294718424,
+      "num_tokens": 9977189.0,
+      "step": 78
+    },
+    {
+      "entropy": 1.0683289542794228,
+      "epoch": 1.0128617363344052,
+      "grad_norm": 0.13981281220912933,
+      "learning_rate": 3.986582940760717e-05,
+      "loss": 1.0460418462753296,
+      "mean_token_accuracy": 0.6902914494276047,
+      "num_tokens": 10105339.0,
+      "step": 79
+    },
+    {
+      "entropy": 1.0724314153194427,
+      "epoch": 1.0257234726688103,
+      "grad_norm": 0.13858474791049957,
+      "learning_rate": 3.957990993015683e-05,
+      "loss": 1.058566689491272,
+      "mean_token_accuracy": 0.6862828806042671,
+      "num_tokens": 10233560.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.0439308360219002,
+      "epoch": 1.0385852090032155,
+      "grad_norm": 0.13067184388637543,
+      "learning_rate": 3.929107073146197e-05,
+      "loss": 1.0285696983337402,
+      "mean_token_accuracy": 0.6929319873452187,
+      "num_tokens": 10362651.0,
+      "step": 81
+    },
+    {
+      "entropy": 1.0342618599534035,
+      "epoch": 1.0514469453376205,
+      "grad_norm": 0.13264496624469757,
+      "learning_rate": 3.899936965343989e-05,
+      "loss": 1.020930290222168,
+      "mean_token_accuracy": 0.6948301270604134,
+      "num_tokens": 10491289.0,
+      "step": 82
+    },
+    {
+      "entropy": 1.0256158709526062,
+      "epoch": 1.0643086816720257,
+      "grad_norm": 0.1373288482427597,
+      "learning_rate": 3.8704865111117746e-05,
+      "loss": 1.0285718441009521,
+      "mean_token_accuracy": 0.6936678141355515,
+      "num_tokens": 10620832.0,
+      "step": 83
+    },
+    {
+      "entropy": 1.0326555371284485,
+      "epoch": 1.077170418006431,
+      "grad_norm": 0.1444251984357834,
+      "learning_rate": 3.840761608093456e-05,
+      "loss": 1.0367753505706787,
+      "mean_token_accuracy": 0.6911751106381416,
+      "num_tokens": 10750624.0,
+      "step": 84
+    },
+    {
+      "entropy": 1.0205135494470596,
+      "epoch": 1.090032154340836,
+      "grad_norm": 0.13858884572982788,
+      "learning_rate": 3.8107682088930794e-05,
+      "loss": 1.0239979028701782,
+      "mean_token_accuracy": 0.6956590712070465,
+      "num_tokens": 10879099.0,
+      "step": 85
+    },
+    {
+      "entropy": 1.0474818050861359,
+      "epoch": 1.1028938906752412,
+      "grad_norm": 0.14154711365699768,
+      "learning_rate": 3.7805123198827857e-05,
+      "loss": 1.042170524597168,
+      "mean_token_accuracy": 0.6909758225083351,
+      "num_tokens": 11009207.0,
+      "step": 86
+    },
+    {
+      "entropy": 1.0394180342555046,
+      "epoch": 1.1157556270096463,
+      "grad_norm": 0.14775335788726807,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.0259459018707275,
+      "mean_token_accuracy": 0.6935660615563393,
+      "num_tokens": 11139036.0,
+      "step": 87
+    },
+    {
+      "entropy": 1.0534177646040916,
+      "epoch": 1.1286173633440515,
+      "grad_norm": 0.14417701959609985,
+      "learning_rate": 3.719237359534087e-05,
+      "loss": 1.0396783351898193,
+      "mean_token_accuracy": 0.6897511631250381,
+      "num_tokens": 11266983.0,
+      "step": 88
+    },
+    {
+      "entropy": 1.0333143174648285,
+      "epoch": 1.1414790996784565,
+      "grad_norm": 0.15050315856933594,
+      "learning_rate": 3.688230558902725e-05,
+      "loss": 1.022615671157837,
+      "mean_token_accuracy": 0.6909365877509117,
+      "num_tokens": 11397059.0,
+      "step": 89
+    },
+    {
+      "entropy": 1.0427064970135689,
+      "epoch": 1.1543408360128617,
+      "grad_norm": 0.15112678706645966,
+      "learning_rate": 3.656985807418248e-05,
+      "loss": 1.0306596755981445,
+      "mean_token_accuracy": 0.6910304948687553,
+      "num_tokens": 11526998.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.0196963846683502,
+      "epoch": 1.167202572347267,
+      "grad_norm": 0.1419505625963211,
+      "learning_rate": 3.6255093620441834e-05,
+      "loss": 1.0061671733856201,
+      "mean_token_accuracy": 0.6976384967565536,
+      "num_tokens": 11655079.0,
+      "step": 91
+    },
+    {
+      "entropy": 1.024051696062088,
+      "epoch": 1.180064308681672,
+      "grad_norm": 0.14213676750659943,
+      "learning_rate": 3.593807526142261e-05,
+      "loss": 1.022234320640564,
+      "mean_token_accuracy": 0.6946855783462524,
+      "num_tokens": 11783991.0,
+      "step": 92
+    },
+    {
+      "entropy": 1.062528796494007,
+      "epoch": 1.1929260450160772,
+      "grad_norm": 0.14591965079307556,
+      "learning_rate": 3.56188664821012e-05,
+      "loss": 1.059708833694458,
+      "mean_token_accuracy": 0.6844379678368568,
+      "num_tokens": 11912889.0,
+      "step": 93
+    },
+    {
+      "entropy": 1.014865756034851,
+      "epoch": 1.2057877813504823,
+      "grad_norm": 0.14508739113807678,
+      "learning_rate": 3.529753120609982e-05,
+      "loss": 1.008953332901001,
+      "mean_token_accuracy": 0.6950033009052277,
+      "num_tokens": 12043098.0,
+      "step": 94
+    },
+    {
+      "entropy": 1.0338283330202103,
+      "epoch": 1.2186495176848875,
+      "grad_norm": 0.14221173524856567,
+      "learning_rate": 3.497413378288541e-05,
+      "loss": 1.0276838541030884,
+      "mean_token_accuracy": 0.6916381195187569,
+      "num_tokens": 12171981.0,
+      "step": 95
+    },
+    {
+      "entropy": 1.0400319248437881,
+      "epoch": 1.2315112540192925,
+      "grad_norm": 0.18457354605197906,
+      "learning_rate": 3.464873897488322e-05,
+      "loss": 1.0370912551879883,
+      "mean_token_accuracy": 0.6903758645057678,
+      "num_tokens": 12301609.0,
+      "step": 96
+    },
+    {
+      "entropy": 1.0322081372141838,
+      "epoch": 1.2443729903536977,
+      "grad_norm": 0.1326817274093628,
+      "learning_rate": 3.432141194450772e-05,
+      "loss": 1.025341510772705,
+      "mean_token_accuracy": 0.6925187185406685,
+      "num_tokens": 12430150.0,
+      "step": 97
+    },
+    {
+      "entropy": 1.0298928320407867,
+      "epoch": 1.257234726688103,
+      "grad_norm": 0.14167922735214233,
+      "learning_rate": 3.39922182411134e-05,
+      "loss": 1.014509916305542,
+      "mean_token_accuracy": 0.6953136399388313,
+      "num_tokens": 12559512.0,
+      "step": 98
+    },
+    {
+      "entropy": 1.0197517424821854,
+      "epoch": 1.270096463022508,
+      "grad_norm": 0.13899077475070953,
+      "learning_rate": 3.3661223787868094e-05,
+      "loss": 1.0131255388259888,
+      "mean_token_accuracy": 0.6959795951843262,
+      "num_tokens": 12687827.0,
+      "step": 99
+    },
+    {
+      "entropy": 1.0366832986474037,
+      "epoch": 1.2829581993569132,
+      "grad_norm": 0.13772615790367126,
+      "learning_rate": 3.332849486855144e-05,
+      "loss": 1.0223910808563232,
+      "mean_token_accuracy": 0.6944098025560379,
+      "num_tokens": 12817156.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.0325315073132515,
+      "epoch": 1.2958199356913183,
+      "grad_norm": 0.15611401200294495,
+      "learning_rate": 3.2994098114281134e-05,
+      "loss": 1.0330082178115845,
+      "mean_token_accuracy": 0.691231481730938,
+      "num_tokens": 12947173.0,
+      "step": 101
+    },
+    {
+      "entropy": 1.0560040026903152,
+      "epoch": 1.3086816720257235,
+      "grad_norm": 0.14017708599567413,
+      "learning_rate": 3.265810049016959e-05,
+      "loss": 1.0507452487945557,
+      "mean_token_accuracy": 0.685476116836071,
+      "num_tokens": 13075894.0,
+      "step": 102
+    },
+    {
+      "entropy": 1.042766660451889,
+      "epoch": 1.3215434083601285,
+      "grad_norm": 0.14003020524978638,
+      "learning_rate": 3.232056928191376e-05,
+      "loss": 1.0352094173431396,
+      "mean_token_accuracy": 0.6894162222743034,
+      "num_tokens": 13205219.0,
+      "step": 103
+    },
+    {
+      "entropy": 1.0263932943344116,
+      "epoch": 1.3344051446945338,
+      "grad_norm": 0.13725009560585022,
+      "learning_rate": 3.1981572082320756e-05,
+      "loss": 1.0180981159210205,
+      "mean_token_accuracy": 0.6936993226408958,
+      "num_tokens": 13335089.0,
+      "step": 104
+    },
+    {
+      "entropy": 1.0104412212967873,
+      "epoch": 1.347266881028939,
+      "grad_norm": 0.14933514595031738,
+      "learning_rate": 3.164117677777191e-05,
+      "loss": 0.9994776844978333,
+      "mean_token_accuracy": 0.6973492205142975,
+      "num_tokens": 13464440.0,
+      "step": 105
+    },
+    {
+      "entropy": 1.0537932738661766,
+      "epoch": 1.360128617363344,
+      "grad_norm": 0.1450837105512619,
+      "learning_rate": 3.1299451534628135e-05,
+      "loss": 1.051639199256897,
+      "mean_token_accuracy": 0.6868981495499611,
+      "num_tokens": 13593649.0,
+      "step": 106
+    },
+    {
+      "entropy": 1.017456293106079,
+      "epoch": 1.3729903536977492,
+      "grad_norm": 0.14285609126091003,
+      "learning_rate": 3.0956464785579124e-05,
+      "loss": 1.0186431407928467,
+      "mean_token_accuracy": 0.695085383951664,
+      "num_tokens": 13724124.0,
+      "step": 107
+    },
+    {
+      "entropy": 1.0262678861618042,
+      "epoch": 1.3858520900321543,
+      "grad_norm": 0.14491550624370575,
+      "learning_rate": 3.061228521593931e-05,
+      "loss": 1.0281405448913574,
+      "mean_token_accuracy": 0.6912555918097496,
+      "num_tokens": 13852550.0,
+      "step": 108
+    },
+    {
+      "entropy": 1.0199785828590393,
+      "epoch": 1.3987138263665595,
+      "grad_norm": 0.14578810334205627,
+      "learning_rate": 3.0266981749893157e-05,
+      "loss": 1.0094892978668213,
+      "mean_token_accuracy": 0.6954217851161957,
+      "num_tokens": 13982198.0,
+      "step": 109
+    },
+    {
+      "entropy": 1.0189271494746208,
+      "epoch": 1.4115755627009645,
+      "grad_norm": 0.14735683798789978,
+      "learning_rate": 2.9920623536692638e-05,
+      "loss": 1.0204169750213623,
+      "mean_token_accuracy": 0.6930175870656967,
+      "num_tokens": 14112179.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.0573503896594048,
+      "epoch": 1.4244372990353698,
+      "grad_norm": 0.14606919884681702,
+      "learning_rate": 2.9573279936809667e-05,
+      "loss": 1.0510833263397217,
+      "mean_token_accuracy": 0.6851395890116692,
+      "num_tokens": 14240203.0,
+      "step": 111
+    },
+    {
+      "entropy": 1.0205455496907234,
+      "epoch": 1.437299035369775,
+      "grad_norm": 0.14531320333480835,
+      "learning_rate": 2.9225020508046232e-05,
+      "loss": 1.0060853958129883,
+      "mean_token_accuracy": 0.6955965086817741,
+      "num_tokens": 14369975.0,
+      "step": 112
+    },
+    {
+      "entropy": 1.0478145331144333,
+      "epoch": 1.45016077170418,
+      "grad_norm": 0.1450543850660324,
+      "learning_rate": 2.8875914991604948e-05,
+      "loss": 1.0418668985366821,
+      "mean_token_accuracy": 0.6893027424812317,
+      "num_tokens": 14498762.0,
+      "step": 113
+    },
+    {
+      "entropy": 1.0268871635198593,
+      "epoch": 1.4630225080385852,
+      "grad_norm": 0.14605779945850372,
+      "learning_rate": 2.8526033298122985e-05,
+      "loss": 1.0171765089035034,
+      "mean_token_accuracy": 0.6931166872382164,
+      "num_tokens": 14626461.0,
+      "step": 114
+    },
+    {
+      "entropy": 1.013284906744957,
+      "epoch": 1.4758842443729905,
+      "grad_norm": 0.14352023601531982,
+      "learning_rate": 2.8175445493671972e-05,
+      "loss": 1.0023720264434814,
+      "mean_token_accuracy": 0.69627246260643,
+      "num_tokens": 14755502.0,
+      "step": 115
+    },
+    {
+      "entropy": 1.0020411610603333,
+      "epoch": 1.4887459807073955,
+      "grad_norm": 0.14316576719284058,
+      "learning_rate": 2.782422178572682e-05,
+      "loss": 0.989754319190979,
+      "mean_token_accuracy": 0.7029954716563225,
+      "num_tokens": 14884196.0,
+      "step": 116
+    },
+    {
+      "entropy": 1.0218420624732971,
+      "epoch": 1.5016077170418005,
+      "grad_norm": 0.14747917652130127,
+      "learning_rate": 2.7472432509106248e-05,
+      "loss": 1.0065988302230835,
+      "mean_token_accuracy": 0.6965539827942848,
+      "num_tokens": 15012865.0,
+      "step": 117
+    },
+    {
+      "entropy": 1.0173380076885223,
+      "epoch": 1.5144694533762058,
+      "grad_norm": 0.14551785588264465,
+      "learning_rate": 2.7120148111887732e-05,
+      "loss": 1.0089175701141357,
+      "mean_token_accuracy": 0.6974302604794502,
+      "num_tokens": 15141248.0,
+      "step": 118
+    },
+    {
+      "entropy": 1.0024594068527222,
+      "epoch": 1.527331189710611,
+      "grad_norm": 0.14043141901493073,
+      "learning_rate": 2.6767439141299865e-05,
+      "loss": 0.9960304498672485,
+      "mean_token_accuracy": 0.7003949508070946,
+      "num_tokens": 15270772.0,
+      "step": 119
+    },
+    {
+      "entropy": 1.055966004729271,
+      "epoch": 1.540192926045016,
+      "grad_norm": 0.14059734344482422,
+      "learning_rate": 2.6414376229594813e-05,
+      "loss": 1.0553550720214844,
+      "mean_token_accuracy": 0.6855349242687225,
+      "num_tokens": 15400804.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.0126784667372704,
+      "epoch": 1.5530546623794212,
+      "grad_norm": 0.14205649495124817,
+      "learning_rate": 2.606103007990371e-05,
+      "loss": 1.011533260345459,
+      "mean_token_accuracy": 0.694344624876976,
+      "num_tokens": 15530652.0,
+      "step": 121
+    },
+    {
+      "entropy": 0.999858908355236,
+      "epoch": 1.5659163987138265,
+      "grad_norm": 0.15500670671463013,
+      "learning_rate": 2.570747145207796e-05,
+      "loss": 1.004133701324463,
+      "mean_token_accuracy": 0.6966777518391609,
+      "num_tokens": 15658153.0,
+      "step": 122
+    },
+    {
+      "entropy": 1.0271989032626152,
+      "epoch": 1.5787781350482315,
+      "grad_norm": 0.14966429769992828,
+      "learning_rate": 2.5353771148519057e-05,
+      "loss": 1.0208675861358643,
+      "mean_token_accuracy": 0.693551167845726,
+      "num_tokens": 15787029.0,
+      "step": 123
+    },
+    {
+      "entropy": 1.0353132709860802,
+      "epoch": 1.5916398713826365,
+      "grad_norm": 0.1523454636335373,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0247621536254883,
+      "mean_token_accuracy": 0.6914970651268959,
+      "num_tokens": 15916192.0,
+      "step": 124
+    },
+    {
+      "entropy": 1.0225750729441643,
+      "epoch": 1.6045016077170418,
+      "grad_norm": 0.14648166298866272,
+      "learning_rate": 2.4646228851480956e-05,
+      "loss": 1.0078290700912476,
+      "mean_token_accuracy": 0.6966298222541809,
+      "num_tokens": 16043897.0,
+      "step": 125
+    },
+    {
+      "entropy": 0.9982719793915749,
+      "epoch": 1.617363344051447,
+      "grad_norm": 0.14288683235645294,
+      "learning_rate": 2.429252854792205e-05,
+      "loss": 0.9868754744529724,
+      "mean_token_accuracy": 0.7016725540161133,
+      "num_tokens": 16172507.0,
+      "step": 126
+    },
+    {
+      "entropy": 1.0020750612020493,
+      "epoch": 1.630225080385852,
+      "grad_norm": 0.1414753645658493,
+      "learning_rate": 2.39389699200963e-05,
+      "loss": 0.9897010326385498,
+      "mean_token_accuracy": 0.7008322700858116,
+      "num_tokens": 16301734.0,
+      "step": 127
+    },
+    {
+      "entropy": 1.0149573609232903,
+      "epoch": 1.6430868167202572,
+      "grad_norm": 0.14801090955734253,
+      "learning_rate": 2.358562377040519e-05,
+      "loss": 1.0131919384002686,
+      "mean_token_accuracy": 0.6938123106956482,
+      "num_tokens": 16431817.0,
+      "step": 128
+    },
+    {
+      "entropy": 0.9920919686555862,
+      "epoch": 1.6559485530546625,
+      "grad_norm": 0.14460355043411255,
+      "learning_rate": 2.3232560858700137e-05,
+      "loss": 0.9964196085929871,
+      "mean_token_accuracy": 0.698267288506031,
+      "num_tokens": 16561567.0,
+      "step": 129
+    },
+    {
+      "entropy": 0.9969829842448235,
+      "epoch": 1.6688102893890675,
+      "grad_norm": 0.15064753592014313,
+      "learning_rate": 2.287985188811228e-05,
+      "loss": 1.0022106170654297,
+      "mean_token_accuracy": 0.6973504200577736,
+      "num_tokens": 16690566.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.0201608687639236,
+      "epoch": 1.6816720257234725,
+      "grad_norm": 0.14219549298286438,
+      "learning_rate": 2.2527567490893758e-05,
+      "loss": 1.0155024528503418,
+      "mean_token_accuracy": 0.6942505687475204,
+      "num_tokens": 16818452.0,
+      "step": 131
+    },
+    {
+      "entropy": 1.014929585158825,
+      "epoch": 1.694533762057878,
+      "grad_norm": 0.1448146253824234,
+      "learning_rate": 2.2175778214273185e-05,
+      "loss": 1.0040041208267212,
+      "mean_token_accuracy": 0.6980330944061279,
+      "num_tokens": 16947349.0,
+      "step": 132
+    },
+    {
+      "entropy": 0.9866555854678154,
+      "epoch": 1.707395498392283,
+      "grad_norm": 0.14621956646442413,
+      "learning_rate": 2.182455450632803e-05,
+      "loss": 0.9739984273910522,
+      "mean_token_accuracy": 0.704859234392643,
+      "num_tokens": 17076397.0,
+      "step": 133
+    },
+    {
+      "entropy": 1.002526581287384,
+      "epoch": 1.720257234726688,
+      "grad_norm": 0.148386150598526,
+      "learning_rate": 2.1473966701877025e-05,
+      "loss": 0.9954771995544434,
+      "mean_token_accuracy": 0.6984783560037613,
+      "num_tokens": 17205973.0,
+      "step": 134
+    },
+    {
+      "entropy": 1.0385541915893555,
+      "epoch": 1.7331189710610932,
+      "grad_norm": 0.1525644212961197,
+      "learning_rate": 2.1124085008395054e-05,
+      "loss": 1.0283631086349487,
+      "mean_token_accuracy": 0.6918526068329811,
+      "num_tokens": 17335707.0,
+      "step": 135
+    },
+    {
+      "entropy": 1.0001368671655655,
+      "epoch": 1.7459807073954985,
+      "grad_norm": 0.14488427340984344,
+      "learning_rate": 2.0774979491953777e-05,
+      "loss": 0.996589183807373,
+      "mean_token_accuracy": 0.6981855407357216,
+      "num_tokens": 17465830.0,
+      "step": 136
+    },
+    {
+      "entropy": 1.0219169780611992,
+      "epoch": 1.7588424437299035,
+      "grad_norm": 0.14797741174697876,
+      "learning_rate": 2.0426720063190335e-05,
+      "loss": 1.0206077098846436,
+      "mean_token_accuracy": 0.6923353374004364,
+      "num_tokens": 17594754.0,
+      "step": 137
+    },
+    {
+      "entropy": 0.9785831719636917,
+      "epoch": 1.7717041800643085,
+      "grad_norm": 0.1460637003183365,
+      "learning_rate": 2.0079376463307368e-05,
+      "loss": 0.9752854108810425,
+      "mean_token_accuracy": 0.7047566249966621,
+      "num_tokens": 17724659.0,
+      "step": 138
+    },
+    {
+      "entropy": 1.0215095803141594,
+      "epoch": 1.784565916398714,
+      "grad_norm": 0.15597465634346008,
+      "learning_rate": 1.973301825010685e-05,
+      "loss": 1.009293556213379,
+      "mean_token_accuracy": 0.696241021156311,
+      "num_tokens": 17854110.0,
+      "step": 139
+    },
+    {
+      "entropy": 1.0135700479149818,
+      "epoch": 1.797427652733119,
+      "grad_norm": 0.14796903729438782,
+      "learning_rate": 1.9387714784060685e-05,
+      "loss": 1.0113576650619507,
+      "mean_token_accuracy": 0.6949452012777328,
+      "num_tokens": 17984291.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.0059723034501076,
+      "epoch": 1.810289389067524,
+      "grad_norm": 0.14315755665302277,
+      "learning_rate": 1.904353521442088e-05,
+      "loss": 0.995486855506897,
+      "mean_token_accuracy": 0.6992441266775131,
+      "num_tokens": 18114833.0,
+      "step": 141
+    },
+    {
+      "entropy": 0.9882848560810089,
+      "epoch": 1.8231511254019293,
+      "grad_norm": 0.14123207330703735,
+      "learning_rate": 1.8700548465371874e-05,
+      "loss": 0.9792846441268921,
+      "mean_token_accuracy": 0.7027938365936279,
+      "num_tokens": 18243460.0,
+      "step": 142
+    },
+    {
+      "entropy": 0.997884638607502,
+      "epoch": 1.8360128617363345,
+      "grad_norm": 0.14799004793167114,
+      "learning_rate": 1.8358823222228097e-05,
+      "loss": 0.9837270975112915,
+      "mean_token_accuracy": 0.7027879133820534,
+      "num_tokens": 18372916.0,
+      "step": 143
+    },
+    {
+      "entropy": 0.9896392747759819,
+      "epoch": 1.8488745980707395,
+      "grad_norm": 0.1497086137533188,
+      "learning_rate": 1.801842791767925e-05,
+      "loss": 0.9768578410148621,
+      "mean_token_accuracy": 0.7023695260286331,
+      "num_tokens": 18500767.0,
+      "step": 144
+    },
+    {
+      "entropy": 1.016235202550888,
+      "epoch": 1.8617363344051447,
+      "grad_norm": 0.14535240828990936,
+      "learning_rate": 1.7679430718086243e-05,
+      "loss": 1.0091252326965332,
+      "mean_token_accuracy": 0.6962308958172798,
+      "num_tokens": 18630361.0,
+      "step": 145
+    },
+    {
+      "entropy": 1.02140112221241,
+      "epoch": 1.87459807073955,
+      "grad_norm": 0.14852745831012726,
+      "learning_rate": 1.7341899509830416e-05,
+      "loss": 1.014499545097351,
+      "mean_token_accuracy": 0.6943220645189285,
+      "num_tokens": 18758686.0,
+      "step": 146
+    },
+    {
+      "entropy": 1.0222366377711296,
+      "epoch": 1.887459807073955,
+      "grad_norm": 0.15775741636753082,
+      "learning_rate": 1.700590188571887e-05,
+      "loss": 1.0132200717926025,
+      "mean_token_accuracy": 0.6938814222812653,
+      "num_tokens": 18887531.0,
+      "step": 147
+    },
+    {
+      "entropy": 0.998849555850029,
+      "epoch": 1.90032154340836,
+      "grad_norm": 0.14149253070354462,
+      "learning_rate": 1.667150513144856e-05,
+      "loss": 0.988683819770813,
+      "mean_token_accuracy": 0.6997354626655579,
+      "num_tokens": 19016209.0,
+      "step": 148
+    },
+    {
+      "entropy": 0.9932566359639168,
+      "epoch": 1.9131832797427653,
+      "grad_norm": 0.14270193874835968,
+      "learning_rate": 1.633877621213192e-05,
+      "loss": 0.9862449169158936,
+      "mean_token_accuracy": 0.7042566016316414,
+      "num_tokens": 19146046.0,
+      "step": 149
+    },
+    {
+      "entropy": 0.9795461744070053,
+      "epoch": 1.9260450160771705,
+      "grad_norm": 0.14396356046199799,
+      "learning_rate": 1.6007781758886607e-05,
+      "loss": 0.9702467918395996,
+      "mean_token_accuracy": 0.7039490714669228,
+      "num_tokens": 19276179.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.9995869025588036,
+      "epoch": 1.9389067524115755,
+      "grad_norm": 0.1701769083738327,
+      "learning_rate": 1.567858805549229e-05,
+      "loss": 0.9991304278373718,
+      "mean_token_accuracy": 0.700151190161705,
+      "num_tokens": 19403041.0,
+      "step": 151
+    },
+    {
+      "entropy": 1.014798641204834,
+      "epoch": 1.9517684887459807,
+      "grad_norm": 0.14598311483860016,
+      "learning_rate": 1.535126102511678e-05,
+      "loss": 1.0107059478759766,
+      "mean_token_accuracy": 0.6958801373839378,
+      "num_tokens": 19530573.0,
+      "step": 152
+    },
+    {
+      "entropy": 0.9927611947059631,
+      "epoch": 1.964630225080386,
+      "grad_norm": 0.1453687846660614,
+      "learning_rate": 1.5025866217114592e-05,
+      "loss": 0.9930230379104614,
+      "mean_token_accuracy": 0.6993638649582863,
+      "num_tokens": 19657825.0,
+      "step": 153
+    },
+    {
+      "entropy": 1.00187648832798,
+      "epoch": 1.977491961414791,
+      "grad_norm": 0.14231781661510468,
+      "learning_rate": 1.4702468793900188e-05,
+      "loss": 0.9966546893119812,
+      "mean_token_accuracy": 0.6981053948402405,
+      "num_tokens": 19786273.0,
+      "step": 154
+    },
+    {
+      "entropy": 1.0072660073637962,
+      "epoch": 1.990353697749196,
+      "grad_norm": 0.14735294878482819,
+      "learning_rate": 1.4381133517898804e-05,
+      "loss": 0.9908390641212463,
+      "mean_token_accuracy": 0.6999674960970879,
+      "num_tokens": 19908864.0,
+      "step": 155
+    },
+    {
+      "entropy": 1.0254995822906494,
+      "epoch": 2.0,
+      "grad_norm": 0.16183844208717346,
+      "learning_rate": 1.4061924738577403e-05,
+      "loss": 1.0296363830566406,
+      "mean_token_accuracy": 0.6913449863592783,
+      "num_tokens": 19955748.0,
+      "step": 156
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.1154271674488586e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}