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": [
+    "k_proj",
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "up_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:d7954ff1d461348452ec12e1682fc6c556c73e2c97aad2a49bfd1dff7b8477ea
+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": 1.3651542961597443,
+      "epoch": 0.012944983818770227,
+      "grad_norm": 1.3304885625839233,
+      "learning_rate": 0.0,
+      "loss": 2.1373414993286133,
+      "mean_token_accuracy": 0.5150357112288475,
+      "num_tokens": 129715.0,
+      "step": 1
+    },
+    {
+      "entropy": 1.3770242929458618,
+      "epoch": 0.025889967637540454,
+      "grad_norm": 1.3239294290542603,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 2.154482841491699,
+      "mean_token_accuracy": 0.5157716199755669,
+      "num_tokens": 259772.0,
+      "step": 2
+    },
+    {
+      "entropy": 1.4346312582492828,
+      "epoch": 0.038834951456310676,
+      "grad_norm": 1.1268572807312012,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.0695247650146484,
+      "mean_token_accuracy": 0.5210058130323887,
+      "num_tokens": 389849.0,
+      "step": 3
+    },
+    {
+      "entropy": 1.5402012169361115,
+      "epoch": 0.05177993527508091,
+      "grad_norm": 0.9283472299575806,
+      "learning_rate": 1.25e-05,
+      "loss": 2.032970905303955,
+      "mean_token_accuracy": 0.5240041315555573,
+      "num_tokens": 518576.0,
+      "step": 4
+    },
+    {
+      "entropy": 1.6357156783342361,
+      "epoch": 0.06472491909385113,
+      "grad_norm": 0.5993914604187012,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 1.8982824087142944,
+      "mean_token_accuracy": 0.5411873385310173,
+      "num_tokens": 648530.0,
+      "step": 5
+    },
+    {
+      "entropy": 1.834080547094345,
+      "epoch": 0.07766990291262135,
+      "grad_norm": 0.41406694054603577,
+      "learning_rate": 2.0833333333333336e-05,
+      "loss": 1.8447895050048828,
+      "mean_token_accuracy": 0.5445547252893448,
+      "num_tokens": 778260.0,
+      "step": 6
+    },
+    {
+      "entropy": 1.9631124883890152,
+      "epoch": 0.09061488673139159,
+      "grad_norm": 0.5057855844497681,
+      "learning_rate": 2.5e-05,
+      "loss": 1.791555404663086,
+      "mean_token_accuracy": 0.5538995414972305,
+      "num_tokens": 908287.0,
+      "step": 7
+    },
+    {
+      "entropy": 2.0287728756666183,
+      "epoch": 0.10355987055016182,
+      "grad_norm": 0.5796622633934021,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 1.7787578105926514,
+      "mean_token_accuracy": 0.5525580644607544,
+      "num_tokens": 1038626.0,
+      "step": 8
+    },
+    {
+      "entropy": 1.8969777673482895,
+      "epoch": 0.11650485436893204,
+      "grad_norm": 0.49578264355659485,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 1.6710119247436523,
+      "mean_token_accuracy": 0.5709376186132431,
+      "num_tokens": 1168231.0,
+      "step": 9
+    },
+    {
+      "entropy": 1.7819280922412872,
+      "epoch": 0.12944983818770225,
+      "grad_norm": 0.39638879895210266,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.6355412006378174,
+      "mean_token_accuracy": 0.5758759081363678,
+      "num_tokens": 1298953.0,
+      "step": 10
+    },
+    {
+      "entropy": 1.6452170461416245,
+      "epoch": 0.1423948220064725,
+      "grad_norm": 0.31017157435417175,
+      "learning_rate": 4.166666666666667e-05,
+      "loss": 1.605017066001892,
+      "mean_token_accuracy": 0.5790466815233231,
+      "num_tokens": 1429030.0,
+      "step": 11
+    },
+    {
+      "entropy": 1.5164579153060913,
+      "epoch": 0.1553398058252427,
+      "grad_norm": 0.29436805844306946,
+      "learning_rate": 4.5833333333333334e-05,
+      "loss": 1.5629851818084717,
+      "mean_token_accuracy": 0.5837943032383919,
+      "num_tokens": 1556810.0,
+      "step": 12
+    },
+    {
+      "entropy": 1.4386323243379593,
+      "epoch": 0.16828478964401294,
+      "grad_norm": 0.2829895317554474,
+      "learning_rate": 5e-05,
+      "loss": 1.5202760696411133,
+      "mean_token_accuracy": 0.5939656496047974,
+      "num_tokens": 1687660.0,
+      "step": 13
+    },
+    {
+      "entropy": 1.3815916031599045,
+      "epoch": 0.18122977346278318,
+      "grad_norm": 0.25666117668151855,
+      "learning_rate": 4.9997496794168726e-05,
+      "loss": 1.4685187339782715,
+      "mean_token_accuracy": 0.6037300601601601,
+      "num_tokens": 1818622.0,
+      "step": 14
+    },
+    {
+      "entropy": 1.4070003181695938,
+      "epoch": 0.1941747572815534,
+      "grad_norm": 0.2441503256559372,
+      "learning_rate": 4.998998767795805e-05,
+      "loss": 1.447906732559204,
+      "mean_token_accuracy": 0.6062909737229347,
+      "num_tokens": 1948742.0,
+      "step": 15
+    },
+    {
+      "entropy": 1.4435111433267593,
+      "epoch": 0.20711974110032363,
+      "grad_norm": 0.26153597235679626,
+      "learning_rate": 4.9977474155117045e-05,
+      "loss": 1.4333127737045288,
+      "mean_token_accuracy": 0.607229471206665,
+      "num_tokens": 2078651.0,
+      "step": 16
+    },
+    {
+      "entropy": 1.427567034959793,
+      "epoch": 0.22006472491909385,
+      "grad_norm": 0.23656481504440308,
+      "learning_rate": 4.995995873155958e-05,
+      "loss": 1.396224021911621,
+      "mean_token_accuracy": 0.6134042665362358,
+      "num_tokens": 2205557.0,
+      "step": 17
+    },
+    {
+      "entropy": 1.433149129152298,
+      "epoch": 0.23300970873786409,
+      "grad_norm": 0.20005719363689423,
+      "learning_rate": 4.99374449148625e-05,
+      "loss": 1.392409324645996,
+      "mean_token_accuracy": 0.6163519993424416,
+      "num_tokens": 2332593.0,
+      "step": 18
+    },
+    {
+      "entropy": 1.4219946712255478,
+      "epoch": 0.2459546925566343,
+      "grad_norm": 0.19785650074481964,
+      "learning_rate": 4.9909937213563165e-05,
+      "loss": 1.3844692707061768,
+      "mean_token_accuracy": 0.6169420257210732,
+      "num_tokens": 2461816.0,
+      "step": 19
+    },
+    {
+      "entropy": 1.3724359720945358,
+      "epoch": 0.2588996763754045,
+      "grad_norm": 0.1962433159351349,
+      "learning_rate": 4.987744113625665e-05,
+      "loss": 1.3383996486663818,
+      "mean_token_accuracy": 0.6265854984521866,
+      "num_tokens": 2592376.0,
+      "step": 20
+    },
+    {
+      "entropy": 1.35466168820858,
+      "epoch": 0.27184466019417475,
+      "grad_norm": 0.19052749872207642,
+      "learning_rate": 4.9839963190492576e-05,
+      "loss": 1.326986312866211,
+      "mean_token_accuracy": 0.6285954564809799,
+      "num_tokens": 2722180.0,
+      "step": 21
+    },
+    {
+      "entropy": 1.324196070432663,
+      "epoch": 0.284789644012945,
+      "grad_norm": 0.1686500757932663,
+      "learning_rate": 4.979751088147192e-05,
+      "loss": 1.307222604751587,
+      "mean_token_accuracy": 0.6329604238271713,
+      "num_tokens": 2852915.0,
+      "step": 22
+    },
+    {
+      "entropy": 1.3377470970153809,
+      "epoch": 0.2977346278317152,
+      "grad_norm": 0.16810794174671173,
+      "learning_rate": 4.975009271054409e-05,
+      "loss": 1.3078091144561768,
+      "mean_token_accuracy": 0.6321637183427811,
+      "num_tokens": 2983811.0,
+      "step": 23
+    },
+    {
+      "entropy": 1.3341724425554276,
+      "epoch": 0.3106796116504854,
+      "grad_norm": 0.18940500915050507,
+      "learning_rate": 4.969771817350445e-05,
+      "loss": 1.312269926071167,
+      "mean_token_accuracy": 0.6310013681650162,
+      "num_tokens": 3114232.0,
+      "step": 24
+    },
+    {
+      "entropy": 1.310901552438736,
+      "epoch": 0.32362459546925565,
+      "grad_norm": 0.1773822158575058,
+      "learning_rate": 4.9640397758692715e-05,
+      "loss": 1.2985689640045166,
+      "mean_token_accuracy": 0.6327972114086151,
+      "num_tokens": 3239638.0,
+      "step": 25
+    },
+    {
+      "entropy": 1.2651723623275757,
+      "epoch": 0.3365695792880259,
+      "grad_norm": 0.17164088785648346,
+      "learning_rate": 4.957814294489261e-05,
+      "loss": 1.2655669450759888,
+      "mean_token_accuracy": 0.6391567513346672,
+      "num_tokens": 3369129.0,
+      "step": 26
+    },
+    {
+      "entropy": 1.2860137075185776,
+      "epoch": 0.34951456310679613,
+      "grad_norm": 0.16309353709220886,
+      "learning_rate": 4.9510966199033174e-05,
+      "loss": 1.2871453762054443,
+      "mean_token_accuracy": 0.6366170793771744,
+      "num_tokens": 3498592.0,
+      "step": 27
+    },
+    {
+      "entropy": 1.2693277299404144,
+      "epoch": 0.36245954692556637,
+      "grad_norm": 0.15370261669158936,
+      "learning_rate": 4.943888097369216e-05,
+      "loss": 1.264456033706665,
+      "mean_token_accuracy": 0.6402129605412483,
+      "num_tokens": 3628933.0,
+      "step": 28
+    },
+    {
+      "entropy": 1.250020757317543,
+      "epoch": 0.37540453074433655,
+      "grad_norm": 0.15371794998645782,
+      "learning_rate": 4.936190170440208e-05,
+      "loss": 1.2349557876586914,
+      "mean_token_accuracy": 0.6465005129575729,
+      "num_tokens": 3759250.0,
+      "step": 29
+    },
+    {
+      "entropy": 1.2473177313804626,
+      "epoch": 0.3883495145631068,
+      "grad_norm": 0.156179279088974,
+      "learning_rate": 4.928004380675941e-05,
+      "loss": 1.2247097492218018,
+      "mean_token_accuracy": 0.6490338742733002,
+      "num_tokens": 3888347.0,
+      "step": 30
+    },
+    {
+      "entropy": 1.2503016591072083,
+      "epoch": 0.40129449838187703,
+      "grad_norm": 0.16324147582054138,
+      "learning_rate": 4.9193323673337476e-05,
+      "loss": 1.2284612655639648,
+      "mean_token_accuracy": 0.6461184471845627,
+      "num_tokens": 4018991.0,
+      "step": 31
+    },
+    {
+      "entropy": 1.2558909952640533,
+      "epoch": 0.41423948220064727,
+      "grad_norm": 0.14576396346092224,
+      "learning_rate": 4.910175867040377e-05,
+      "loss": 1.2321372032165527,
+      "mean_token_accuracy": 0.645910307765007,
+      "num_tokens": 4149100.0,
+      "step": 32
+    },
+    {
+      "entropy": 1.2409392595291138,
+      "epoch": 0.42718446601941745,
+      "grad_norm": 0.14837919175624847,
+      "learning_rate": 4.9005367134442235e-05,
+      "loss": 1.2166019678115845,
+      "mean_token_accuracy": 0.6500448063015938,
+      "num_tokens": 4279686.0,
+      "step": 33
+    },
+    {
+      "entropy": 1.2073234170675278,
+      "epoch": 0.4401294498381877,
+      "grad_norm": 0.1407850831747055,
+      "learning_rate": 4.890416836848127e-05,
+      "loss": 1.191582441329956,
+      "mean_token_accuracy": 0.654162771999836,
+      "num_tokens": 4409879.0,
+      "step": 34
+    },
+    {
+      "entropy": 1.224804401397705,
+      "epoch": 0.45307443365695793,
+      "grad_norm": 0.14388902485370636,
+      "learning_rate": 4.8798182638228166e-05,
+      "loss": 1.2188255786895752,
+      "mean_token_accuracy": 0.649294339120388,
+      "num_tokens": 4539958.0,
+      "step": 35
+    },
+    {
+      "entropy": 1.1996213346719742,
+      "epoch": 0.46601941747572817,
+      "grad_norm": 0.13835251331329346,
+      "learning_rate": 4.868743116801074e-05,
+      "loss": 1.1903774738311768,
+      "mean_token_accuracy": 0.6544475257396698,
+      "num_tokens": 4668863.0,
+      "step": 36
+    },
+    {
+      "entropy": 1.166234239935875,
+      "epoch": 0.47896440129449835,
+      "grad_norm": 0.13608549535274506,
+      "learning_rate": 4.857193613652711e-05,
+      "loss": 1.1813488006591797,
+      "mean_token_accuracy": 0.6577481329441071,
+      "num_tokens": 4799874.0,
+      "step": 37
+    },
+    {
+      "entropy": 1.197123497724533,
+      "epoch": 0.4919093851132686,
+      "grad_norm": 0.13925297558307648,
+      "learning_rate": 4.845172067240415e-05,
+      "loss": 1.2087821960449219,
+      "mean_token_accuracy": 0.6513781398534775,
+      "num_tokens": 4929372.0,
+      "step": 38
+    },
+    {
+      "entropy": 1.1750382333993912,
+      "epoch": 0.5048543689320388,
+      "grad_norm": 0.13949091732501984,
+      "learning_rate": 4.8326808849565936e-05,
+      "loss": 1.177015781402588,
+      "mean_token_accuracy": 0.6557950600981712,
+      "num_tokens": 5059840.0,
+      "step": 39
+    },
+    {
+      "entropy": 1.1692189127206802,
+      "epoch": 0.517799352750809,
+      "grad_norm": 0.14397211372852325,
+      "learning_rate": 4.819722568241274e-05,
+      "loss": 1.1632399559020996,
+      "mean_token_accuracy": 0.6591483578085899,
+      "num_tokens": 5189026.0,
+      "step": 40
+    },
+    {
+      "entropy": 1.1593063026666641,
+      "epoch": 0.5307443365695793,
+      "grad_norm": 0.13899798691272736,
+      "learning_rate": 4.806299712081172e-05,
+      "loss": 1.1517739295959473,
+      "mean_token_accuracy": 0.6616862490773201,
+      "num_tokens": 5319304.0,
+      "step": 41
+    },
+    {
+      "entropy": 1.1965416818857193,
+      "epoch": 0.5436893203883495,
+      "grad_norm": 0.13963711261749268,
+      "learning_rate": 4.792415004490034e-05,
+      "loss": 1.1859239339828491,
+      "mean_token_accuracy": 0.6556195169687271,
+      "num_tokens": 5449076.0,
+      "step": 42
+    },
+    {
+      "entropy": 1.1787460893392563,
+      "epoch": 0.5566343042071198,
+      "grad_norm": 0.13826416432857513,
+      "learning_rate": 4.77807122597034e-05,
+      "loss": 1.154212236404419,
+      "mean_token_accuracy": 0.6633580550551414,
+      "num_tokens": 5578972.0,
+      "step": 43
+    },
+    {
+      "entropy": 1.1719040125608444,
+      "epoch": 0.56957928802589,
+      "grad_norm": 0.13135474920272827,
+      "learning_rate": 4.7632712489564926e-05,
+      "loss": 1.152864694595337,
+      "mean_token_accuracy": 0.6626269146800041,
+      "num_tokens": 5709351.0,
+      "step": 44
+    },
+    {
+      "entropy": 1.1761715561151505,
+      "epoch": 0.5825242718446602,
+      "grad_norm": 0.1382664293050766,
+      "learning_rate": 4.748018037239592e-05,
+      "loss": 1.1596863269805908,
+      "mean_token_accuracy": 0.66019656509161,
+      "num_tokens": 5839241.0,
+      "step": 45
+    },
+    {
+      "entropy": 1.1685755103826523,
+      "epoch": 0.5954692556634305,
+      "grad_norm": 0.1334962695837021,
+      "learning_rate": 4.732314645373921e-05,
+      "loss": 1.1554309129714966,
+      "mean_token_accuracy": 0.6611259058117867,
+      "num_tokens": 5969064.0,
+      "step": 46
+    },
+    {
+      "entropy": 1.143287107348442,
+      "epoch": 0.6084142394822006,
+      "grad_norm": 0.13915717601776123,
+      "learning_rate": 4.7161642180652464e-05,
+      "loss": 1.13901948928833,
+      "mean_token_accuracy": 0.6638868674635887,
+      "num_tokens": 6099092.0,
+      "step": 47
+    },
+    {
+      "entropy": 1.1229832172393799,
+      "epoch": 0.6213592233009708,
+      "grad_norm": 0.16735908389091492,
+      "learning_rate": 4.699569989541074e-05,
+      "loss": 1.1253852844238281,
+      "mean_token_accuracy": 0.6694925650954247,
+      "num_tokens": 6229169.0,
+      "step": 48
+    },
+    {
+      "entropy": 1.142636001110077,
+      "epoch": 0.6343042071197411,
+      "grad_norm": 0.1340433806180954,
+      "learning_rate": 4.6825352829029705e-05,
+      "loss": 1.1438826322555542,
+      "mean_token_accuracy": 0.6639438346028328,
+      "num_tokens": 6359167.0,
+      "step": 49
+    },
+    {
+      "entropy": 1.1389989107847214,
+      "epoch": 0.6472491909385113,
+      "grad_norm": 0.1330229490995407,
+      "learning_rate": 4.665063509461097e-05,
+      "loss": 1.1328400373458862,
+      "mean_token_accuracy": 0.668202169239521,
+      "num_tokens": 6489483.0,
+      "step": 50
+    },
+    {
+      "entropy": 1.1350421458482742,
+      "epoch": 0.6601941747572816,
+      "grad_norm": 0.13832047581672668,
+      "learning_rate": 4.647158168051066e-05,
+      "loss": 1.134395956993103,
+      "mean_token_accuracy": 0.6662710979580879,
+      "num_tokens": 6618304.0,
+      "step": 51
+    },
+    {
+      "entropy": 1.1280719488859177,
+      "epoch": 0.6731391585760518,
+      "grad_norm": 0.13961584866046906,
+      "learning_rate": 4.628822844333278e-05,
+      "loss": 1.1157816648483276,
+      "mean_token_accuracy": 0.6674881353974342,
+      "num_tokens": 6748534.0,
+      "step": 52
+    },
+    {
+      "entropy": 1.1400533020496368,
+      "epoch": 0.686084142394822,
+      "grad_norm": 0.13416820764541626,
+      "learning_rate": 4.6100612100748765e-05,
+      "loss": 1.1322004795074463,
+      "mean_token_accuracy": 0.664855606853962,
+      "num_tokens": 6878351.0,
+      "step": 53
+    },
+    {
+      "entropy": 1.117271676659584,
+      "epoch": 0.6990291262135923,
+      "grad_norm": 0.13155770301818848,
+      "learning_rate": 4.59087702241444e-05,
+      "loss": 1.1148383617401123,
+      "mean_token_accuracy": 0.6699468269944191,
+      "num_tokens": 7008842.0,
+      "step": 54
+    },
+    {
+      "entropy": 1.1524481028318405,
+      "epoch": 0.7119741100323624,
+      "grad_norm": 0.13490092754364014,
+      "learning_rate": 4.571274123109606e-05,
+      "loss": 1.1433762311935425,
+      "mean_token_accuracy": 0.6656594127416611,
+      "num_tokens": 7139302.0,
+      "step": 55
+    },
+    {
+      "entropy": 1.128203958272934,
+      "epoch": 0.7249190938511327,
+      "grad_norm": 0.13910333812236786,
+      "learning_rate": 4.551256437767719e-05,
+      "loss": 1.1198092699050903,
+      "mean_token_accuracy": 0.6694299727678299,
+      "num_tokens": 7268920.0,
+      "step": 56
+    },
+    {
+      "entropy": 1.1252606362104416,
+      "epoch": 0.7378640776699029,
+      "grad_norm": 0.13880470395088196,
+      "learning_rate": 4.530827975059715e-05,
+      "loss": 1.1268362998962402,
+      "mean_token_accuracy": 0.6689485609531403,
+      "num_tokens": 7399537.0,
+      "step": 57
+    },
+    {
+      "entropy": 1.1418287009000778,
+      "epoch": 0.7508090614886731,
+      "grad_norm": 0.1401115506887436,
+      "learning_rate": 4.5099928259173516e-05,
+      "loss": 1.1322367191314697,
+      "mean_token_accuracy": 0.6656085550785065,
+      "num_tokens": 7525788.0,
+      "step": 58
+    },
+    {
+      "entropy": 1.1480491310358047,
+      "epoch": 0.7637540453074434,
+      "grad_norm": 0.14310455322265625,
+      "learning_rate": 4.488755162713975e-05,
+      "loss": 1.1316089630126953,
+      "mean_token_accuracy": 0.6664536520838737,
+      "num_tokens": 7656150.0,
+      "step": 59
+    },
+    {
+      "entropy": 1.1366282999515533,
+      "epoch": 0.7766990291262136,
+      "grad_norm": 0.12998667359352112,
+      "learning_rate": 4.467119238428975e-05,
+      "loss": 1.1231651306152344,
+      "mean_token_accuracy": 0.6681933254003525,
+      "num_tokens": 7786291.0,
+      "step": 60
+    },
+    {
+      "entropy": 1.105496659874916,
+      "epoch": 0.7896440129449838,
+      "grad_norm": 0.1398758739233017,
+      "learning_rate": 4.445089385796099e-05,
+      "loss": 1.0939688682556152,
+      "mean_token_accuracy": 0.6759221702814102,
+      "num_tokens": 7916189.0,
+      "step": 61
+    },
+    {
+      "entropy": 1.1114656925201416,
+      "epoch": 0.8025889967637541,
+      "grad_norm": 0.13194960355758667,
+      "learning_rate": 4.422670016435792e-05,
+      "loss": 1.1039596796035767,
+      "mean_token_accuracy": 0.6731015890836716,
+      "num_tokens": 8046519.0,
+      "step": 62
+    },
+    {
+      "entropy": 1.0888657569885254,
+      "epoch": 0.8155339805825242,
+      "grad_norm": 0.1397247463464737,
+      "learning_rate": 4.3998656199717435e-05,
+      "loss": 1.0911369323730469,
+      "mean_token_accuracy": 0.6746554225683212,
+      "num_tokens": 8176740.0,
+      "step": 63
+    },
+    {
+      "entropy": 1.1219657808542252,
+      "epoch": 0.8284789644012945,
+      "grad_norm": 0.13516487181186676,
+      "learning_rate": 4.3766807631318106e-05,
+      "loss": 1.1249346733093262,
+      "mean_token_accuracy": 0.668804943561554,
+      "num_tokens": 8306981.0,
+      "step": 64
+    },
+    {
+      "entropy": 1.096419408917427,
+      "epoch": 0.8414239482200647,
+      "grad_norm": 0.13442112505435944,
+      "learning_rate": 4.353120088833501e-05,
+      "loss": 1.0880069732666016,
+      "mean_token_accuracy": 0.675564743578434,
+      "num_tokens": 8437012.0,
+      "step": 65
+    },
+    {
+      "entropy": 1.0983364135026932,
+      "epoch": 0.8543689320388349,
+      "grad_norm": 0.1384594589471817,
+      "learning_rate": 4.329188315254196e-05,
+      "loss": 1.0896861553192139,
+      "mean_token_accuracy": 0.6748483330011368,
+      "num_tokens": 8567432.0,
+      "step": 66
+    },
+    {
+      "entropy": 1.1061086654663086,
+      "epoch": 0.8673139158576052,
+      "grad_norm": 0.12975235283374786,
+      "learning_rate": 4.3048902348863116e-05,
+      "loss": 1.092883825302124,
+      "mean_token_accuracy": 0.6738436594605446,
+      "num_tokens": 8697482.0,
+      "step": 67
+    },
+    {
+      "entropy": 1.1013841927051544,
+      "epoch": 0.8802588996763754,
+      "grad_norm": 0.13858407735824585,
+      "learning_rate": 4.280230713577564e-05,
+      "loss": 1.0877230167388916,
+      "mean_token_accuracy": 0.6764405071735382,
+      "num_tokens": 8826353.0,
+      "step": 68
+    },
+    {
+      "entropy": 1.1029959172010422,
+      "epoch": 0.8932038834951457,
+      "grad_norm": 0.13860292732715607,
+      "learning_rate": 4.255214689556557e-05,
+      "loss": 1.1019368171691895,
+      "mean_token_accuracy": 0.6718069836497307,
+      "num_tokens": 8955338.0,
+      "step": 69
+    },
+    {
+      "entropy": 1.1007527112960815,
+      "epoch": 0.9061488673139159,
+      "grad_norm": 0.13615350425243378,
+      "learning_rate": 4.229847172443866e-05,
+      "loss": 1.1066391468048096,
+      "mean_token_accuracy": 0.6710008159279823,
+      "num_tokens": 9085706.0,
+      "step": 70
+    },
+    {
+      "entropy": 1.0915730148553848,
+      "epoch": 0.919093851132686,
+      "grad_norm": 0.1343710720539093,
+      "learning_rate": 4.204133242248832e-05,
+      "loss": 1.0948892831802368,
+      "mean_token_accuracy": 0.6748337969183922,
+      "num_tokens": 9216028.0,
+      "step": 71
+    },
+    {
+      "entropy": 1.1037265211343765,
+      "epoch": 0.9320388349514563,
+      "grad_norm": 0.13998186588287354,
+      "learning_rate": 4.1780780483522575e-05,
+      "loss": 1.097463607788086,
+      "mean_token_accuracy": 0.6743032932281494,
+      "num_tokens": 9346732.0,
+      "step": 72
+    },
+    {
+      "entropy": 1.081187054514885,
+      "epoch": 0.9449838187702265,
+      "grad_norm": 0.13939902186393738,
+      "learning_rate": 4.151686808475204e-05,
+      "loss": 1.0713167190551758,
+      "mean_token_accuracy": 0.6809784397482872,
+      "num_tokens": 9477265.0,
+      "step": 73
+    },
+    {
+      "entropy": 1.092852994799614,
+      "epoch": 0.9579288025889967,
+      "grad_norm": 0.13595172762870789,
+      "learning_rate": 4.1249648076341165e-05,
+      "loss": 1.085597038269043,
+      "mean_token_accuracy": 0.6780063956975937,
+      "num_tokens": 9606420.0,
+      "step": 74
+    },
+    {
+      "entropy": 1.09284046292305,
+      "epoch": 0.970873786407767,
+      "grad_norm": 0.12815804779529572,
+      "learning_rate": 4.0979173970824626e-05,
+      "loss": 1.0821534395217896,
+      "mean_token_accuracy": 0.6755026131868362,
+      "num_tokens": 9737245.0,
+      "step": 75
+    },
+    {
+      "entropy": 1.0906607061624527,
+      "epoch": 0.9838187702265372,
+      "grad_norm": 0.14664161205291748,
+      "learning_rate": 4.070549993239106e-05,
+      "loss": 1.0785982608795166,
+      "mean_token_accuracy": 0.6788846999406815,
+      "num_tokens": 9867367.0,
+      "step": 76
+    },
+    {
+      "entropy": 1.0882694870233536,
+      "epoch": 0.9967637540453075,
+      "grad_norm": 0.13629893958568573,
+      "learning_rate": 4.0428680766036384e-05,
+      "loss": 1.0791587829589844,
+      "mean_token_accuracy": 0.6776749864220619,
+      "num_tokens": 9998012.0,
+      "step": 77
+    },
+    {
+      "entropy": 1.1047788858413696,
+      "epoch": 1.0,
+      "grad_norm": 0.24593353271484375,
+      "learning_rate": 4.0148771906588706e-05,
+      "loss": 1.063537359237671,
+      "mean_token_accuracy": 0.6715989708900452,
+      "num_tokens": 10006202.0,
+      "step": 78
+    },
+    {
+      "entropy": 1.0793865472078323,
+      "epoch": 1.0129449838187703,
+      "grad_norm": 0.1301373392343521,
+      "learning_rate": 3.986582940760717e-05,
+      "loss": 1.0542354583740234,
+      "mean_token_accuracy": 0.6828000247478485,
+      "num_tokens": 10136364.0,
+      "step": 79
+    },
+    {
+      "entropy": 1.0615715086460114,
+      "epoch": 1.0258899676375404,
+      "grad_norm": 0.14376649260520935,
+      "learning_rate": 3.957990993015683e-05,
+      "loss": 1.042524814605713,
+      "mean_token_accuracy": 0.6859273239970207,
+      "num_tokens": 10267185.0,
+      "step": 80
+    },
+    {
+      "entropy": 1.0814688503742218,
+      "epoch": 1.0388349514563107,
+      "grad_norm": 0.1429099142551422,
+      "learning_rate": 3.929107073146197e-05,
+      "loss": 1.0707274675369263,
+      "mean_token_accuracy": 0.6797767356038094,
+      "num_tokens": 10397579.0,
+      "step": 81
+    },
+    {
+      "entropy": 1.0523302108049393,
+      "epoch": 1.051779935275081,
+      "grad_norm": 0.13949202001094818,
+      "learning_rate": 3.899936965343989e-05,
+      "loss": 1.0439385175704956,
+      "mean_token_accuracy": 0.6843096166849136,
+      "num_tokens": 10527592.0,
+      "step": 82
+    },
+    {
+      "entropy": 1.0631293207406998,
+      "epoch": 1.064724919093851,
+      "grad_norm": 0.139011412858963,
+      "learning_rate": 3.8704865111117746e-05,
+      "loss": 1.0628037452697754,
+      "mean_token_accuracy": 0.6787978634238243,
+      "num_tokens": 10654859.0,
+      "step": 83
+    },
+    {
+      "entropy": 1.0537770837545395,
+      "epoch": 1.0776699029126213,
+      "grad_norm": 0.2928038239479065,
+      "learning_rate": 3.840761608093456e-05,
+      "loss": 1.0620827674865723,
+      "mean_token_accuracy": 0.6819959208369255,
+      "num_tokens": 10784927.0,
+      "step": 84
+    },
+    {
+      "entropy": 1.037618413567543,
+      "epoch": 1.0906148867313916,
+      "grad_norm": 0.14370758831501007,
+      "learning_rate": 3.8107682088930794e-05,
+      "loss": 1.044572353363037,
+      "mean_token_accuracy": 0.683650940656662,
+      "num_tokens": 10914750.0,
+      "step": 85
+    },
+    {
+      "entropy": 1.0501893609762192,
+      "epoch": 1.103559870550162,
+      "grad_norm": 0.13791602849960327,
+      "learning_rate": 3.7805123198827857e-05,
+      "loss": 1.046133279800415,
+      "mean_token_accuracy": 0.6837264969944954,
+      "num_tokens": 11044842.0,
+      "step": 86
+    },
+    {
+      "entropy": 1.0563921481370926,
+      "epoch": 1.116504854368932,
+      "grad_norm": 0.13362936675548553,
+      "learning_rate": 3.7500000000000003e-05,
+      "loss": 1.0573209524154663,
+      "mean_token_accuracy": 0.6832020804286003,
+      "num_tokens": 11174518.0,
+      "step": 87
+    },
+    {
+      "entropy": 1.064748615026474,
+      "epoch": 1.1294498381877023,
+      "grad_norm": 0.1401379555463791,
+      "learning_rate": 3.719237359534087e-05,
+      "loss": 1.0473384857177734,
+      "mean_token_accuracy": 0.6870113164186478,
+      "num_tokens": 11304999.0,
+      "step": 88
+    },
+    {
+      "entropy": 1.0635596364736557,
+      "epoch": 1.1423948220064726,
+      "grad_norm": 0.15294352173805237,
+      "learning_rate": 3.688230558902725e-05,
+      "loss": 1.046224594116211,
+      "mean_token_accuracy": 0.6833971738815308,
+      "num_tokens": 11434763.0,
+      "step": 89
+    },
+    {
+      "entropy": 1.048565037548542,
+      "epoch": 1.1553398058252426,
+      "grad_norm": 0.14027105271816254,
+      "learning_rate": 3.656985807418248e-05,
+      "loss": 1.0255308151245117,
+      "mean_token_accuracy": 0.6887662187218666,
+      "num_tokens": 11564852.0,
+      "step": 90
+    },
+    {
+      "entropy": 1.049909919500351,
+      "epoch": 1.168284789644013,
+      "grad_norm": 0.1372356414794922,
+      "learning_rate": 3.6255093620441834e-05,
+      "loss": 1.0371609926223755,
+      "mean_token_accuracy": 0.6852358728647232,
+      "num_tokens": 11695587.0,
+      "step": 91
+    },
+    {
+      "entropy": 1.050833709537983,
+      "epoch": 1.1812297734627832,
+      "grad_norm": 0.1350698471069336,
+      "learning_rate": 3.593807526142261e-05,
+      "loss": 1.0426298379898071,
+      "mean_token_accuracy": 0.6834184303879738,
+      "num_tokens": 11825470.0,
+      "step": 92
+    },
+    {
+      "entropy": 1.047458566725254,
+      "epoch": 1.1941747572815533,
+      "grad_norm": 0.14042825996875763,
+      "learning_rate": 3.56188664821012e-05,
+      "loss": 1.0439410209655762,
+      "mean_token_accuracy": 0.6839079484343529,
+      "num_tokens": 11952094.0,
+      "step": 93
+    },
+    {
+      "entropy": 1.0416604727506638,
+      "epoch": 1.2071197411003236,
+      "grad_norm": 0.14407604932785034,
+      "learning_rate": 3.529753120609982e-05,
+      "loss": 1.0408530235290527,
+      "mean_token_accuracy": 0.6859614551067352,
+      "num_tokens": 12079148.0,
+      "step": 94
+    },
+    {
+      "entropy": 1.032593734562397,
+      "epoch": 1.220064724919094,
+      "grad_norm": 0.1412661373615265,
+      "learning_rate": 3.497413378288541e-05,
+      "loss": 1.0320262908935547,
+      "mean_token_accuracy": 0.6871174648404121,
+      "num_tokens": 12209523.0,
+      "step": 95
+    },
+    {
+      "entropy": 1.0136415883898735,
+      "epoch": 1.233009708737864,
+      "grad_norm": 0.14111459255218506,
+      "learning_rate": 3.464873897488322e-05,
+      "loss": 1.0045194625854492,
+      "mean_token_accuracy": 0.6947158724069595,
+      "num_tokens": 12340431.0,
+      "step": 96
+    },
+    {
+      "entropy": 1.051560029387474,
+      "epoch": 1.2459546925566343,
+      "grad_norm": 0.14038066565990448,
+      "learning_rate": 3.432141194450772e-05,
+      "loss": 1.0422347784042358,
+      "mean_token_accuracy": 0.6865646913647652,
+      "num_tokens": 12470212.0,
+      "step": 97
+    },
+    {
+      "entropy": 1.0481782108545303,
+      "epoch": 1.2588996763754046,
+      "grad_norm": 0.1397588700056076,
+      "learning_rate": 3.39922182411134e-05,
+      "loss": 1.0391991138458252,
+      "mean_token_accuracy": 0.6847709640860558,
+      "num_tokens": 12600848.0,
+      "step": 98
+    },
+    {
+      "entropy": 1.0571434199810028,
+      "epoch": 1.2718446601941746,
+      "grad_norm": 0.1416858583688736,
+      "learning_rate": 3.3661223787868094e-05,
+      "loss": 1.0532944202423096,
+      "mean_token_accuracy": 0.682709351181984,
+      "num_tokens": 12730861.0,
+      "step": 99
+    },
+    {
+      "entropy": 1.033029980957508,
+      "epoch": 1.284789644012945,
+      "grad_norm": 0.1399715691804886,
+      "learning_rate": 3.332849486855144e-05,
+      "loss": 1.0335698127746582,
+      "mean_token_accuracy": 0.6876120045781136,
+      "num_tokens": 12856809.0,
+      "step": 100
+    },
+    {
+      "entropy": 1.04202900826931,
+      "epoch": 1.2977346278317152,
+      "grad_norm": 0.13759812712669373,
+      "learning_rate": 3.2994098114281134e-05,
+      "loss": 1.0285584926605225,
+      "mean_token_accuracy": 0.6880297958850861,
+      "num_tokens": 12986427.0,
+      "step": 101
+    },
+    {
+      "entropy": 1.0641857832670212,
+      "epoch": 1.3106796116504853,
+      "grad_norm": 0.14462466537952423,
+      "learning_rate": 3.265810049016959e-05,
+      "loss": 1.0581681728363037,
+      "mean_token_accuracy": 0.683790534734726,
+      "num_tokens": 13116966.0,
+      "step": 102
+    },
+    {
+      "entropy": 1.0504063814878464,
+      "epoch": 1.3236245954692556,
+      "grad_norm": 0.14422035217285156,
+      "learning_rate": 3.232056928191376e-05,
+      "loss": 1.0456278324127197,
+      "mean_token_accuracy": 0.6848116368055344,
+      "num_tokens": 13246681.0,
+      "step": 103
+    },
+    {
+      "entropy": 1.038411796092987,
+      "epoch": 1.3365695792880259,
+      "grad_norm": 0.14174729585647583,
+      "learning_rate": 3.1981572082320756e-05,
+      "loss": 1.0359523296356201,
+      "mean_token_accuracy": 0.6853675097227097,
+      "num_tokens": 13376920.0,
+      "step": 104
+    },
+    {
+      "entropy": 1.0447421371936798,
+      "epoch": 1.3495145631067962,
+      "grad_norm": 0.15686437487602234,
+      "learning_rate": 3.164117677777191e-05,
+      "loss": 1.0456362962722778,
+      "mean_token_accuracy": 0.685419425368309,
+      "num_tokens": 13507157.0,
+      "step": 105
+    },
+    {
+      "entropy": 1.042502984404564,
+      "epoch": 1.3624595469255665,
+      "grad_norm": 0.1450643539428711,
+      "learning_rate": 3.1299451534628135e-05,
+      "loss": 1.0352379083633423,
+      "mean_token_accuracy": 0.6877066269516945,
+      "num_tokens": 13635707.0,
+      "step": 106
+    },
+    {
+      "entropy": 1.0504102855920792,
+      "epoch": 1.3754045307443366,
+      "grad_norm": 0.14115434885025024,
+      "learning_rate": 3.0956464785579124e-05,
+      "loss": 1.0395991802215576,
+      "mean_token_accuracy": 0.6867645904421806,
+      "num_tokens": 13764408.0,
+      "step": 107
+    },
+    {
+      "entropy": 1.023859016597271,
+      "epoch": 1.3883495145631068,
+      "grad_norm": 0.1452028602361679,
+      "learning_rate": 3.061228521593931e-05,
+      "loss": 1.0140364170074463,
+      "mean_token_accuracy": 0.6895884871482849,
+      "num_tokens": 13894812.0,
+      "step": 108
+    },
+    {
+      "entropy": 1.0468136668205261,
+      "epoch": 1.4012944983818771,
+      "grad_norm": 0.14509586989879608,
+      "learning_rate": 3.0266981749893157e-05,
+      "loss": 1.0377655029296875,
+      "mean_token_accuracy": 0.685391828417778,
+      "num_tokens": 14025213.0,
+      "step": 109
+    },
+    {
+      "entropy": 1.0328698828816414,
+      "epoch": 1.4142394822006472,
+      "grad_norm": 0.1392725557088852,
+      "learning_rate": 2.9920623536692638e-05,
+      "loss": 1.0397965908050537,
+      "mean_token_accuracy": 0.6867645233869553,
+      "num_tokens": 14154525.0,
+      "step": 110
+    },
+    {
+      "entropy": 1.0457722693681717,
+      "epoch": 1.4271844660194175,
+      "grad_norm": 0.14031684398651123,
+      "learning_rate": 2.9573279936809667e-05,
+      "loss": 1.0414118766784668,
+      "mean_token_accuracy": 0.6839371249079704,
+      "num_tokens": 14284644.0,
+      "step": 111
+    },
+    {
+      "entropy": 1.028133824467659,
+      "epoch": 1.4401294498381878,
+      "grad_norm": 0.14316803216934204,
+      "learning_rate": 2.9225020508046232e-05,
+      "loss": 1.012750506401062,
+      "mean_token_accuracy": 0.6908283829689026,
+      "num_tokens": 14413882.0,
+      "step": 112
+    },
+    {
+      "entropy": 1.0364510789513588,
+      "epoch": 1.4530744336569579,
+      "grad_norm": 0.13855139911174774,
+      "learning_rate": 2.8875914991604948e-05,
+      "loss": 1.0293610095977783,
+      "mean_token_accuracy": 0.6889501288533211,
+      "num_tokens": 14543040.0,
+      "step": 113
+    },
+    {
+      "entropy": 1.0487663447856903,
+      "epoch": 1.4660194174757282,
+      "grad_norm": 0.15151230990886688,
+      "learning_rate": 2.8526033298122985e-05,
+      "loss": 1.0312678813934326,
+      "mean_token_accuracy": 0.6874943599104881,
+      "num_tokens": 14673458.0,
+      "step": 114
+    },
+    {
+      "entropy": 1.0504018738865852,
+      "epoch": 1.4789644012944985,
+      "grad_norm": 0.1419685184955597,
+      "learning_rate": 2.8175445493671972e-05,
+      "loss": 1.0388998985290527,
+      "mean_token_accuracy": 0.6856456473469734,
+      "num_tokens": 14804112.0,
+      "step": 115
+    },
+    {
+      "entropy": 1.0200290083885193,
+      "epoch": 1.4919093851132685,
+      "grad_norm": 0.1363752782344818,
+      "learning_rate": 2.782422178572682e-05,
+      "loss": 1.0119816064834595,
+      "mean_token_accuracy": 0.6932434141635895,
+      "num_tokens": 14934245.0,
+      "step": 116
+    },
+    {
+      "entropy": 1.0283359810709953,
+      "epoch": 1.5048543689320388,
+      "grad_norm": 0.14866895973682404,
+      "learning_rate": 2.7472432509106248e-05,
+      "loss": 1.0333629846572876,
+      "mean_token_accuracy": 0.6870463192462921,
+      "num_tokens": 15065111.0,
+      "step": 117
+    },
+    {
+      "entropy": 1.02705879509449,
+      "epoch": 1.5177993527508091,
+      "grad_norm": 0.14171157777309418,
+      "learning_rate": 2.7120148111887732e-05,
+      "loss": 1.0255823135375977,
+      "mean_token_accuracy": 0.6886087208986282,
+      "num_tokens": 15195395.0,
+      "step": 118
+    },
+    {
+      "entropy": 1.0195337459445,
+      "epoch": 1.5307443365695792,
+      "grad_norm": 0.137300044298172,
+      "learning_rate": 2.6767439141299865e-05,
+      "loss": 1.0249097347259521,
+      "mean_token_accuracy": 0.6881711855530739,
+      "num_tokens": 15325873.0,
+      "step": 119
+    },
+    {
+      "entropy": 1.045641377568245,
+      "epoch": 1.5436893203883495,
+      "grad_norm": 0.1500910520553589,
+      "learning_rate": 2.6414376229594813e-05,
+      "loss": 1.042417287826538,
+      "mean_token_accuracy": 0.6856146231293678,
+      "num_tokens": 15456568.0,
+      "step": 120
+    },
+    {
+      "entropy": 1.025648020207882,
+      "epoch": 1.5566343042071198,
+      "grad_norm": 0.15413540601730347,
+      "learning_rate": 2.606103007990371e-05,
+      "loss": 1.0176175832748413,
+      "mean_token_accuracy": 0.6913169324398041,
+      "num_tokens": 15584558.0,
+      "step": 121
+    },
+    {
+      "entropy": 1.014452114701271,
+      "epoch": 1.5695792880258899,
+      "grad_norm": 0.1436716765165329,
+      "learning_rate": 2.570747145207796e-05,
+      "loss": 1.0058581829071045,
+      "mean_token_accuracy": 0.6949772462248802,
+      "num_tokens": 15714770.0,
+      "step": 122
+    },
+    {
+      "entropy": 1.0195590406656265,
+      "epoch": 1.5825242718446602,
+      "grad_norm": 0.1428489238023758,
+      "learning_rate": 2.5353771148519057e-05,
+      "loss": 1.0073108673095703,
+      "mean_token_accuracy": 0.6948005929589272,
+      "num_tokens": 15845667.0,
+      "step": 123
+    },
+    {
+      "entropy": 1.0366466492414474,
+      "epoch": 1.5954692556634305,
+      "grad_norm": 0.14365780353546143,
+      "learning_rate": 2.5e-05,
+      "loss": 1.0264899730682373,
+      "mean_token_accuracy": 0.6886240467429161,
+      "num_tokens": 15975988.0,
+      "step": 124
+    },
+    {
+      "entropy": 1.0400130897760391,
+      "epoch": 1.6084142394822005,
+      "grad_norm": 0.14898498356342316,
+      "learning_rate": 2.4646228851480956e-05,
+      "loss": 1.0336707830429077,
+      "mean_token_accuracy": 0.6866266429424286,
+      "num_tokens": 16105352.0,
+      "step": 125
+    },
+    {
+      "entropy": 1.0187797024846077,
+      "epoch": 1.6213592233009708,
+      "grad_norm": 0.1424783319234848,
+      "learning_rate": 2.429252854792205e-05,
+      "loss": 1.0120515823364258,
+      "mean_token_accuracy": 0.6910470202565193,
+      "num_tokens": 16235128.0,
+      "step": 126
+    },
+    {
+      "entropy": 1.0371646136045456,
+      "epoch": 1.6343042071197411,
+      "grad_norm": 0.14739543199539185,
+      "learning_rate": 2.39389699200963e-05,
+      "loss": 1.0284910202026367,
+      "mean_token_accuracy": 0.686544694006443,
+      "num_tokens": 16364820.0,
+      "step": 127
+    },
+    {
+      "entropy": 1.0144242346286774,
+      "epoch": 1.6472491909385112,
+      "grad_norm": 0.14023685455322266,
+      "learning_rate": 2.358562377040519e-05,
+      "loss": 1.011099934577942,
+      "mean_token_accuracy": 0.6919900849461555,
+      "num_tokens": 16495010.0,
+      "step": 128
+    },
+    {
+      "entropy": 1.0424084663391113,
+      "epoch": 1.6601941747572817,
+      "grad_norm": 0.14127855002880096,
+      "learning_rate": 2.3232560858700137e-05,
+      "loss": 1.0348625183105469,
+      "mean_token_accuracy": 0.6857902184128761,
+      "num_tokens": 16624053.0,
+      "step": 129
+    },
+    {
+      "entropy": 1.0389196053147316,
+      "epoch": 1.6731391585760518,
+      "grad_norm": 0.14043182134628296,
+      "learning_rate": 2.287985188811228e-05,
+      "loss": 1.0278400182724,
+      "mean_token_accuracy": 0.6889984756708145,
+      "num_tokens": 16754013.0,
+      "step": 130
+    },
+    {
+      "entropy": 1.0327453166246414,
+      "epoch": 1.6860841423948218,
+      "grad_norm": 0.13774602115154266,
+      "learning_rate": 2.2527567490893758e-05,
+      "loss": 1.0192316770553589,
+      "mean_token_accuracy": 0.6896380558609962,
+      "num_tokens": 16884900.0,
+      "step": 131
+    },
+    {
+      "entropy": 1.0411661118268967,
+      "epoch": 1.6990291262135924,
+      "grad_norm": 0.1432965099811554,
+      "learning_rate": 2.2175778214273185e-05,
+      "loss": 1.0254759788513184,
+      "mean_token_accuracy": 0.6884243860840797,
+      "num_tokens": 17015566.0,
+      "step": 132
+    },
+    {
+      "entropy": 1.0357749685645103,
+      "epoch": 1.7119741100323624,
+      "grad_norm": 0.14122679829597473,
+      "learning_rate": 2.182455450632803e-05,
+      "loss": 1.0263139009475708,
+      "mean_token_accuracy": 0.6886742264032364,
+      "num_tokens": 17145290.0,
+      "step": 133
+    },
+    {
+      "entropy": 1.0433481931686401,
+      "epoch": 1.7249190938511327,
+      "grad_norm": 0.1418823003768921,
+      "learning_rate": 2.1473966701877025e-05,
+      "loss": 1.0395673513412476,
+      "mean_token_accuracy": 0.6867275536060333,
+      "num_tokens": 17276182.0,
+      "step": 134
+    },
+    {
+      "entropy": 1.043164886534214,
+      "epoch": 1.737864077669903,
+      "grad_norm": 0.14382290840148926,
+      "learning_rate": 2.1124085008395054e-05,
+      "loss": 1.0374891757965088,
+      "mean_token_accuracy": 0.6853289008140564,
+      "num_tokens": 17406273.0,
+      "step": 135
+    },
+    {
+      "entropy": 1.0135142654180527,
+      "epoch": 1.750809061488673,
+      "grad_norm": 0.14157947897911072,
+      "learning_rate": 2.0774979491953777e-05,
+      "loss": 1.0156872272491455,
+      "mean_token_accuracy": 0.6926322430372238,
+      "num_tokens": 17536152.0,
+      "step": 136
+    },
+    {
+      "entropy": 1.0207490772008896,
+      "epoch": 1.7637540453074434,
+      "grad_norm": 0.1438336968421936,
+      "learning_rate": 2.0426720063190335e-05,
+      "loss": 1.0126570463180542,
+      "mean_token_accuracy": 0.6893723979592323,
+      "num_tokens": 17665709.0,
+      "step": 137
+    },
+    {
+      "entropy": 1.031029760837555,
+      "epoch": 1.7766990291262137,
+      "grad_norm": 0.14654259383678436,
+      "learning_rate": 2.0079376463307368e-05,
+      "loss": 1.0254521369934082,
+      "mean_token_accuracy": 0.6898153051733971,
+      "num_tokens": 17795725.0,
+      "step": 138
+    },
+    {
+      "entropy": 1.0286231860518456,
+      "epoch": 1.7896440129449838,
+      "grad_norm": 0.14215368032455444,
+      "learning_rate": 1.973301825010685e-05,
+      "loss": 1.0211424827575684,
+      "mean_token_accuracy": 0.6894683688879013,
+      "num_tokens": 17925869.0,
+      "step": 139
+    },
+    {
+      "entropy": 1.0320534706115723,
+      "epoch": 1.802588996763754,
+      "grad_norm": 0.13870325684547424,
+      "learning_rate": 1.9387714784060685e-05,
+      "loss": 1.0351669788360596,
+      "mean_token_accuracy": 0.6847272291779518,
+      "num_tokens": 18056215.0,
+      "step": 140
+    },
+    {
+      "entropy": 1.0036064609885216,
+      "epoch": 1.8155339805825244,
+      "grad_norm": 0.1447254866361618,
+      "learning_rate": 1.904353521442088e-05,
+      "loss": 0.9998693466186523,
+      "mean_token_accuracy": 0.6936472877860069,
+      "num_tokens": 18185346.0,
+      "step": 141
+    },
+    {
+      "entropy": 1.0466959178447723,
+      "epoch": 1.8284789644012944,
+      "grad_norm": 0.14772695302963257,
+      "learning_rate": 1.8700548465371874e-05,
+      "loss": 1.045184850692749,
+      "mean_token_accuracy": 0.6844764202833176,
+      "num_tokens": 18315007.0,
+      "step": 142
+    },
+    {
+      "entropy": 1.02869962900877,
+      "epoch": 1.8414239482200647,
+      "grad_norm": 0.1422375589609146,
+      "learning_rate": 1.8358823222228097e-05,
+      "loss": 1.0235483646392822,
+      "mean_token_accuracy": 0.6905021890997887,
+      "num_tokens": 18444894.0,
+      "step": 143
+    },
+    {
+      "entropy": 1.0311558917164803,
+      "epoch": 1.854368932038835,
+      "grad_norm": 0.1477019041776657,
+      "learning_rate": 1.801842791767925e-05,
+      "loss": 1.0244710445404053,
+      "mean_token_accuracy": 0.6892124861478806,
+      "num_tokens": 18574694.0,
+      "step": 144
+    },
+    {
+      "entropy": 1.043830282986164,
+      "epoch": 1.867313915857605,
+      "grad_norm": 0.14222465455532074,
+      "learning_rate": 1.7679430718086243e-05,
+      "loss": 1.032785415649414,
+      "mean_token_accuracy": 0.6885510012507439,
+      "num_tokens": 18704772.0,
+      "step": 145
+    },
+    {
+      "entropy": 1.0300543755292892,
+      "epoch": 1.8802588996763754,
+      "grad_norm": 0.14112794399261475,
+      "learning_rate": 1.7341899509830416e-05,
+      "loss": 1.0181026458740234,
+      "mean_token_accuracy": 0.6906857863068581,
+      "num_tokens": 18834819.0,
+      "step": 146
+    },
+    {
+      "entropy": 1.0159508436918259,
+      "epoch": 1.8932038834951457,
+      "grad_norm": 0.141503244638443,
+      "learning_rate": 1.700590188571887e-05,
+      "loss": 1.0101823806762695,
+      "mean_token_accuracy": 0.6921093240380287,
+      "num_tokens": 18965463.0,
+      "step": 147
+    },
+    {
+      "entropy": 1.0109246894717216,
+      "epoch": 1.9061488673139158,
+      "grad_norm": 0.1380421668291092,
+      "learning_rate": 1.667150513144856e-05,
+      "loss": 1.002206802368164,
+      "mean_token_accuracy": 0.6948473379015923,
+      "num_tokens": 19095571.0,
+      "step": 148
+    },
+    {
+      "entropy": 1.0220000967383385,
+      "epoch": 1.919093851132686,
+      "grad_norm": 0.14566011726856232,
+      "learning_rate": 1.633877621213192e-05,
+      "loss": 1.0207855701446533,
+      "mean_token_accuracy": 0.6889239624142647,
+      "num_tokens": 19225355.0,
+      "step": 149
+    },
+    {
+      "entropy": 1.011439025402069,
+      "epoch": 1.9320388349514563,
+      "grad_norm": 0.1550174206495285,
+      "learning_rate": 1.6007781758886607e-05,
+      "loss": 1.0031033754348755,
+      "mean_token_accuracy": 0.6945909336209297,
+      "num_tokens": 19356027.0,
+      "step": 150
+    },
+    {
+      "entropy": 1.0311592370271683,
+      "epoch": 1.9449838187702264,
+      "grad_norm": 0.14708086848258972,
+      "learning_rate": 1.567858805549229e-05,
+      "loss": 1.026855230331421,
+      "mean_token_accuracy": 0.6892969906330109,
+      "num_tokens": 19485070.0,
+      "step": 151
+    },
+    {
+      "entropy": 1.0317912995815277,
+      "epoch": 1.9579288025889967,
+      "grad_norm": 0.3733585774898529,
+      "learning_rate": 1.535126102511678e-05,
+      "loss": 1.0244548320770264,
+      "mean_token_accuracy": 0.6887175664305687,
+      "num_tokens": 19614246.0,
+      "step": 152
+    },
+    {
+      "entropy": 0.9934456944465637,
+      "epoch": 1.970873786407767,
+      "grad_norm": 0.13808943331241608,
+      "learning_rate": 1.5025866217114592e-05,
+      "loss": 0.9845442771911621,
+      "mean_token_accuracy": 0.6991605833172798,
+      "num_tokens": 19744778.0,
+      "step": 153
+    },
+    {
+      "entropy": 1.0197140723466873,
+      "epoch": 1.983818770226537,
+      "grad_norm": 0.14794670045375824,
+      "learning_rate": 1.4702468793900188e-05,
+      "loss": 1.0132488012313843,
+      "mean_token_accuracy": 0.690579317510128,
+      "num_tokens": 19874524.0,
+      "step": 154
+    },
+    {
+      "entropy": 1.0350212305784225,
+      "epoch": 1.9967637540453076,
+      "grad_norm": 0.14313679933547974,
+      "learning_rate": 1.4381133517898804e-05,
+      "loss": 1.0308572053909302,
+      "mean_token_accuracy": 0.6873542219400406,
+      "num_tokens": 20004307.0,
+      "step": 155
+    },
+    {
+      "entropy": 1.0506715178489685,
+      "epoch": 2.0,
+      "grad_norm": 0.2900261878967285,
+      "learning_rate": 1.4061924738577403e-05,
+      "loss": 1.017795443534851,
+      "mean_token_accuracy": 0.6803950071334839,
+      "num_tokens": 20012405.0,
+      "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": 2.1164680117024195e+18,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}