Upload folder using huggingface_hub

README.md

@@ -0,0 +1,62 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+model_name: mistral7b_labels2codes_lora
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for mistral7b_labels2codes_lora
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.3](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.3).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.17.0
+- TRL: 0.21.0
+- Transformers: 4.55.2
+- Pytorch: 2.7.1
+- Datasets: 3.6.0
+- Tokenizers: 0.21.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": 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 sha256:1790b7928f19c11eea9b3ae25f2fe1a066a98224c55c01b0bee9e895ec7a9e48
+size 54560368

chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-1383/README.md

@@ -0,0 +1,209 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- 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 0.17.0

checkpoint-1383/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1383/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1790b7928f19c11eea9b3ae25f2fe1a066a98224c55c01b0bee9e895ec7a9e48
+size 54560368

checkpoint-1383/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-1383/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bf8d723239a9f8765ea2c9af5351cd7324f0b96a218f4a6ebba596375afa9aa
+size 1593

checkpoint-1383/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0bc6cb51ab7ae63fbe677bc72e378a12642b92ac6970fa9ba77833061d06c09b
+size 14645

checkpoint-1383/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9915a1d438f134c1517f1be983ddad5176ebd284be94defdc54893cbdfb31dd6
+size 1465

checkpoint-1383/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-1383/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-1383/trainer_state.json

@@ -0,0 +1,1276 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1383,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021719948415122516,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019869848156182213,
+      "loss": 6.0531,
+      "mean_token_accuracy": 0.37881034857127815,
+      "num_tokens": 78573.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.04343989683024503,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019725234996384672,
+      "loss": 5.9903,
+      "mean_token_accuracy": 0.3887314551044255,
+      "num_tokens": 157496.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.06515984524536754,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019580621836587129,
+      "loss": 5.9929,
+      "mean_token_accuracy": 0.3850487937917933,
+      "num_tokens": 236512.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08687979366049006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019436008676789588,
+      "loss": 5.986,
+      "mean_token_accuracy": 0.3865805763518438,
+      "num_tokens": 315608.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.10859974207561257,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019291395516992047,
+      "loss": 6.0318,
+      "mean_token_accuracy": 0.38490854618139564,
+      "num_tokens": 394791.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.13031969049073508,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019146782357194506,
+      "loss": 5.9875,
+      "mean_token_accuracy": 0.38546840590424836,
+      "num_tokens": 473456.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.1520396389058576,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019002169197396965,
+      "loss": 5.9773,
+      "mean_token_accuracy": 0.3837947838823311,
+      "num_tokens": 552247.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.17375958732098012,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001885755603759942,
+      "loss": 6.0197,
+      "mean_token_accuracy": 0.38375892234034836,
+      "num_tokens": 631096.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19547953573610263,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001871294287780188,
+      "loss": 6.0014,
+      "mean_token_accuracy": 0.38519658900331705,
+      "num_tokens": 710275.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.21719948415122514,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001856832971800434,
+      "loss": 6.0217,
+      "mean_token_accuracy": 0.3826989881345071,
+      "num_tokens": 789174.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.23891943256634765,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018423716558206799,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.3842650496866554,
+      "num_tokens": 867922.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.26063938098147016,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018279103398409255,
+      "loss": 5.9548,
+      "mean_token_accuracy": 0.3875111517496407,
+      "num_tokens": 947073.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2823593293965927,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018134490238611714,
+      "loss": 6.0071,
+      "mean_token_accuracy": 0.38376112943515184,
+      "num_tokens": 1026211.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.3040792778117152,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017989877078814173,
+      "loss": 6.0105,
+      "mean_token_accuracy": 0.38463024909142407,
+      "num_tokens": 1105147.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.3257992262268377,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001784526391901663,
+      "loss": 6.0449,
+      "mean_token_accuracy": 0.38241248747799544,
+      "num_tokens": 1183837.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.34751917464196025,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017700650759219091,
+      "loss": 5.9946,
+      "mean_token_accuracy": 0.3821917780907825,
+      "num_tokens": 1262676.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.36923912305708273,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017556037599421548,
+      "loss": 6.0049,
+      "mean_token_accuracy": 0.3842250820598565,
+      "num_tokens": 1341759.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.39095907147220527,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017411424439624007,
+      "loss": 5.9736,
+      "mean_token_accuracy": 0.3861917880363762,
+      "num_tokens": 1420987.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.41267901988732775,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017266811279826466,
+      "loss": 6.0431,
+      "mean_token_accuracy": 0.38146835477091373,
+      "num_tokens": 1499903.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.4343989683024503,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017122198120028922,
+      "loss": 6.0069,
+      "mean_token_accuracy": 0.3861038032686338,
+      "num_tokens": 1578880.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.4561189167175728,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016977584960231381,
+      "loss": 6.0091,
+      "mean_token_accuracy": 0.3845075036631897,
+      "num_tokens": 1657709.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.4778388651326953,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001683297180043384,
+      "loss": 6.0029,
+      "mean_token_accuracy": 0.38288453239947556,
+      "num_tokens": 1736620.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.49955881354781784,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000166883586406363,
+      "loss": 5.9933,
+      "mean_token_accuracy": 0.38531269936356694,
+      "num_tokens": 1815478.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.5212787619629403,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016543745480838756,
+      "loss": 6.0334,
+      "mean_token_accuracy": 0.3833939728909172,
+      "num_tokens": 1894256.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.5429987103780628,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016399132321041215,
+      "loss": 6.0484,
+      "mean_token_accuracy": 0.3841994108865038,
+      "num_tokens": 1972997.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.5647186587931854,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016254519161243674,
+      "loss": 6.0285,
+      "mean_token_accuracy": 0.38443261398933826,
+      "num_tokens": 2051890.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.5864386072083079,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016109906001446133,
+      "loss": 5.983,
+      "mean_token_accuracy": 0.385862308065407,
+      "num_tokens": 2130746.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.6081585556234304,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015965292841648592,
+      "loss": 6.0046,
+      "mean_token_accuracy": 0.3859730801777914,
+      "num_tokens": 2209603.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.6298785040385529,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001582067968185105,
+      "loss": 5.9887,
+      "mean_token_accuracy": 0.38499277490191164,
+      "num_tokens": 2288743.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.6515984524536754,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015676066522053508,
+      "loss": 5.9788,
+      "mean_token_accuracy": 0.3864025830756873,
+      "num_tokens": 2367648.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.6733184008687979,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015531453362255964,
+      "loss": 6.0162,
+      "mean_token_accuracy": 0.38221894631860776,
+      "num_tokens": 2446256.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.6950383492839205,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015386840202458423,
+      "loss": 6.0017,
+      "mean_token_accuracy": 0.38538019855041056,
+      "num_tokens": 2525065.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.716758297699043,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015242227042660883,
+      "loss": 5.9569,
+      "mean_token_accuracy": 0.3852926092222333,
+      "num_tokens": 2604183.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.7384782461141655,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015097613882863342,
+      "loss": 6.0072,
+      "mean_token_accuracy": 0.38616998645011336,
+      "num_tokens": 2683084.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.7601981945292879,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000149530007230658,
+      "loss": 6.0428,
+      "mean_token_accuracy": 0.3831095602363348,
+      "num_tokens": 2761824.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.7819181429444105,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014808387563268257,
+      "loss": 5.9781,
+      "mean_token_accuracy": 0.3861894382047467,
+      "num_tokens": 2840709.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.803638091359533,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014663774403470716,
+      "loss": 5.9898,
+      "mean_token_accuracy": 0.3846066597965546,
+      "num_tokens": 2919385.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.8253580397746555,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014519161243673173,
+      "loss": 6.0098,
+      "mean_token_accuracy": 0.38357423364650456,
+      "num_tokens": 2998308.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.8470779881897781,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014374548083875634,
+      "loss": 6.0349,
+      "mean_token_accuracy": 0.3809299209038727,
+      "num_tokens": 3076962.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.8687979366049006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001422993492407809,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.38217092433478683,
+      "num_tokens": 3155983.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.890517885020023,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001408532176428055,
+      "loss": 5.9728,
+      "mean_token_accuracy": 0.3870704318396747,
+      "num_tokens": 3234960.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.9122378334351456,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001394070860448301,
+      "loss": 6.0541,
+      "mean_token_accuracy": 0.38209462116938087,
+      "num_tokens": 3313797.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.9339577818502681,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013796095444685465,
+      "loss": 5.9871,
+      "mean_token_accuracy": 0.38401242352556436,
+      "num_tokens": 3392880.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.9556777302653906,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013651482284887927,
+      "loss": 5.9901,
+      "mean_token_accuracy": 0.38375150066567587,
+      "num_tokens": 3471597.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.9773976786805131,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013506869125090384,
+      "loss": 5.9797,
+      "mean_token_accuracy": 0.38728573790285736,
+      "num_tokens": 3550697.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.9991176270956357,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013362255965292843,
+      "loss": 5.9971,
+      "mean_token_accuracy": 0.38420643559657036,
+      "num_tokens": 3629481.0,
+      "step": 460
+    },
+    {
+      "epoch": 1.0195479535736103,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013217642805495302,
+      "loss": 6.0223,
+      "mean_token_accuracy": 0.3833757105509308,
+      "num_tokens": 3703746.0,
+      "step": 470
+    },
+    {
+      "epoch": 1.0412679019887328,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013073029645697758,
+      "loss": 6.0146,
+      "mean_token_accuracy": 0.38417146790307016,
+      "num_tokens": 3782783.0,
+      "step": 480
+    },
+    {
+      "epoch": 1.0629878504038552,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012928416485900217,
+      "loss": 5.9713,
+      "mean_token_accuracy": 0.3863212176831439,
+      "num_tokens": 3862048.0,
+      "step": 490
+    },
+    {
+      "epoch": 1.0847077988189777,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012783803326102676,
+      "loss": 5.9944,
+      "mean_token_accuracy": 0.38522618702845646,
+      "num_tokens": 3941220.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.1064277472341004,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012639190166305135,
+      "loss": 5.9895,
+      "mean_token_accuracy": 0.38548907284857703,
+      "num_tokens": 4020089.0,
+      "step": 510
+    },
+    {
+      "epoch": 1.128147695649223,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012494577006507592,
+      "loss": 5.9901,
+      "mean_token_accuracy": 0.3841517207212746,
+      "num_tokens": 4098981.0,
+      "step": 520
+    },
+    {
+      "epoch": 1.1498676440643454,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001234996384671005,
+      "loss": 6.0125,
+      "mean_token_accuracy": 0.38393973018974065,
+      "num_tokens": 4177983.0,
+      "step": 530
+    },
+    {
+      "epoch": 1.1715875924794679,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012205350686912509,
+      "loss": 5.9999,
+      "mean_token_accuracy": 0.3848019931232557,
+      "num_tokens": 4256818.0,
+      "step": 540
+    },
+    {
+      "epoch": 1.1933075408945903,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012060737527114966,
+      "loss": 6.0146,
+      "mean_token_accuracy": 0.3834400905063376,
+      "num_tokens": 4335754.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.2150274893097128,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011916124367317427,
+      "loss": 5.9832,
+      "mean_token_accuracy": 0.38411646473687144,
+      "num_tokens": 4414480.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.2367474377248353,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011771511207519885,
+      "loss": 6.0393,
+      "mean_token_accuracy": 0.3809544609161094,
+      "num_tokens": 4493321.0,
+      "step": 570
+    },
+    {
+      "epoch": 1.2584673861399578,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011626898047722344,
+      "loss": 5.9989,
+      "mean_token_accuracy": 0.38565440035890786,
+      "num_tokens": 4572297.0,
+      "step": 580
+    },
+    {
+      "epoch": 1.2801873345550805,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011482284887924801,
+      "loss": 5.9983,
+      "mean_token_accuracy": 0.3863610655302182,
+      "num_tokens": 4651247.0,
+      "step": 590
+    },
+    {
+      "epoch": 1.301907282970203,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011337671728127259,
+      "loss": 6.0116,
+      "mean_token_accuracy": 0.3831069741398096,
+      "num_tokens": 4730012.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.3236272313853255,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001119305856832972,
+      "loss": 6.0195,
+      "mean_token_accuracy": 0.3857766560278833,
+      "num_tokens": 4809013.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.345347179800448,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011048445408532177,
+      "loss": 6.0108,
+      "mean_token_accuracy": 0.3835394912166521,
+      "num_tokens": 4888027.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.3670671282155704,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010903832248734635,
+      "loss": 5.9558,
+      "mean_token_accuracy": 0.3883327366434969,
+      "num_tokens": 4966859.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.3887870766306931,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010759219088937094,
+      "loss": 6.0088,
+      "mean_token_accuracy": 0.385754154715687,
+      "num_tokens": 5045905.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.4105070250458156,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010614605929139552,
+      "loss": 6.0236,
+      "mean_token_accuracy": 0.3829167880234309,
+      "num_tokens": 5124413.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.432226973460938,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001046999276934201,
+      "loss": 6.0154,
+      "mean_token_accuracy": 0.3834054367849603,
+      "num_tokens": 5203273.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.4539469218760606,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001032537960954447,
+      "loss": 6.005,
+      "mean_token_accuracy": 0.3848568681394681,
+      "num_tokens": 5281984.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.475666870291183,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010180766449746928,
+      "loss": 5.9805,
+      "mean_token_accuracy": 0.3862292483681813,
+      "num_tokens": 5360846.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.4973868187063055,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010036153289949386,
+      "loss": 5.9871,
+      "mean_token_accuracy": 0.3851381171494722,
+      "num_tokens": 5439758.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.519106767121428,
+      "grad_norm": 0.0,
+      "learning_rate": 9.891540130151843e-05,
+      "loss": 6.0254,
+      "mean_token_accuracy": 0.3831110308994539,
+      "num_tokens": 5518768.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.5408267155365505,
+      "grad_norm": 0.0,
+      "learning_rate": 9.746926970354303e-05,
+      "loss": 6.0339,
+      "mean_token_accuracy": 0.3808896674308926,
+      "num_tokens": 5597672.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.562546663951673,
+      "grad_norm": 0.0,
+      "learning_rate": 9.602313810556762e-05,
+      "loss": 5.994,
+      "mean_token_accuracy": 0.3865658549708314,
+      "num_tokens": 5676393.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.5842666123667957,
+      "grad_norm": 0.0,
+      "learning_rate": 9.45770065075922e-05,
+      "loss": 6.0026,
+      "mean_token_accuracy": 0.38676879862323404,
+      "num_tokens": 5755416.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.6059865607819181,
+      "grad_norm": 0.0,
+      "learning_rate": 9.313087490961678e-05,
+      "loss": 6.0175,
+      "mean_token_accuracy": 0.38389978763880206,
+      "num_tokens": 5834322.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.6277065091970406,
+      "grad_norm": 0.0,
+      "learning_rate": 9.168474331164136e-05,
+      "loss": 6.0224,
+      "mean_token_accuracy": 0.3840769061935134,
+      "num_tokens": 5912925.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.6494264576121633,
+      "grad_norm": 0.0,
+      "learning_rate": 9.023861171366594e-05,
+      "loss": 5.9683,
+      "mean_token_accuracy": 0.38740592543035746,
+      "num_tokens": 5991913.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.6711464060272858,
+      "grad_norm": 0.0,
+      "learning_rate": 8.879248011569053e-05,
+      "loss": 6.0136,
+      "mean_token_accuracy": 0.3827170055825263,
+      "num_tokens": 6070546.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.6928663544424083,
+      "grad_norm": 0.0,
+      "learning_rate": 8.734634851771512e-05,
+      "loss": 5.9688,
+      "mean_token_accuracy": 0.3871995336958207,
+      "num_tokens": 6149623.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.7145863028575308,
+      "grad_norm": 0.0,
+      "learning_rate": 8.59002169197397e-05,
+      "loss": 6.0639,
+      "mean_token_accuracy": 0.3800558194401674,
+      "num_tokens": 6228396.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.7363062512726533,
+      "grad_norm": 0.0,
+      "learning_rate": 8.445408532176429e-05,
+      "loss": 5.9778,
+      "mean_token_accuracy": 0.3854194077430293,
+      "num_tokens": 6307375.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.7580261996877757,
+      "grad_norm": 0.0,
+      "learning_rate": 8.300795372378887e-05,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.38350161886774004,
+      "num_tokens": 6386536.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.7797461481028982,
+      "grad_norm": 0.0,
+      "learning_rate": 8.156182212581345e-05,
+      "loss": 5.9736,
+      "mean_token_accuracy": 0.38414000715129076,
+      "num_tokens": 6465708.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.8014660965180207,
+      "grad_norm": 0.0,
+      "learning_rate": 8.011569052783804e-05,
+      "loss": 5.9847,
+      "mean_token_accuracy": 0.3877883184002712,
+      "num_tokens": 6544782.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.8231860449331432,
+      "grad_norm": 0.0,
+      "learning_rate": 7.866955892986261e-05,
+      "loss": 6.043,
+      "mean_token_accuracy": 0.38251175949117167,
+      "num_tokens": 6623497.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.8449059933482657,
+      "grad_norm": 0.0,
+      "learning_rate": 7.72234273318872e-05,
+      "loss": 6.0297,
+      "mean_token_accuracy": 0.38357739897910503,
+      "num_tokens": 6702159.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.8666259417633884,
+      "grad_norm": 0.0,
+      "learning_rate": 7.57772957339118e-05,
+      "loss": 6.0335,
+      "mean_token_accuracy": 0.38290644709486515,
+      "num_tokens": 6780886.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.8883458901785108,
+      "grad_norm": 0.0,
+      "learning_rate": 7.433116413593637e-05,
+      "loss": 6.0273,
+      "mean_token_accuracy": 0.38307004772359504,
+      "num_tokens": 6859533.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.9100658385936333,
+      "grad_norm": 0.0,
+      "learning_rate": 7.288503253796096e-05,
+      "loss": 5.9827,
+      "mean_token_accuracy": 0.385389854805544,
+      "num_tokens": 6938490.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.9317857870087558,
+      "grad_norm": 0.0,
+      "learning_rate": 7.143890093998554e-05,
+      "loss": 6.0212,
+      "mean_token_accuracy": 0.382453205762431,
+      "num_tokens": 7017297.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.9535057354238785,
+      "grad_norm": 0.0,
+      "learning_rate": 6.999276934201012e-05,
+      "loss": 6.0043,
+      "mean_token_accuracy": 0.38360455771908164,
+      "num_tokens": 7096419.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.975225683839001,
+      "grad_norm": 0.0,
+      "learning_rate": 6.854663774403471e-05,
+      "loss": 5.985,
+      "mean_token_accuracy": 0.38632277538999915,
+      "num_tokens": 7175650.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.9969456322541235,
+      "grad_norm": 0.0,
+      "learning_rate": 6.71005061460593e-05,
+      "loss": 6.009,
+      "mean_token_accuracy": 0.38311313565354793,
+      "num_tokens": 7254378.0,
+      "step": 920
+    },
+    {
+      "epoch": 2.017375958732098,
+      "grad_norm": 0.0,
+      "learning_rate": 6.565437454808388e-05,
+      "loss": 5.968,
+      "mean_token_accuracy": 0.38770305797259674,
+      "num_tokens": 7328545.0,
+      "step": 930
+    },
+    {
+      "epoch": 2.0390959071472206,
+      "grad_norm": 0.0,
+      "learning_rate": 6.420824295010847e-05,
+      "loss": 5.9938,
+      "mean_token_accuracy": 0.38461664781207217,
+      "num_tokens": 7407672.0,
+      "step": 940
+    },
+    {
+      "epoch": 2.060815855562343,
+      "grad_norm": 0.0,
+      "learning_rate": 6.276211135213305e-05,
+      "loss": 6.0073,
+      "mean_token_accuracy": 0.3848728087265044,
+      "num_tokens": 7486852.0,
+      "step": 950
+    },
+    {
+      "epoch": 2.0825358039774655,
+      "grad_norm": 0.0,
+      "learning_rate": 6.131597975415762e-05,
+      "loss": 5.9564,
+      "mean_token_accuracy": 0.3856648310320452,
+      "num_tokens": 7565680.0,
+      "step": 960
+    },
+    {
+      "epoch": 2.104255752392588,
+      "grad_norm": 0.0,
+      "learning_rate": 5.9869848156182215e-05,
+      "loss": 6.0092,
+      "mean_token_accuracy": 0.38208459480665624,
+      "num_tokens": 7644328.0,
+      "step": 970
+    },
+    {
+      "epoch": 2.1259757008077105,
+      "grad_norm": 0.0,
+      "learning_rate": 5.84237165582068e-05,
+      "loss": 6.0331,
+      "mean_token_accuracy": 0.38403523166198283,
+      "num_tokens": 7723297.0,
+      "step": 980
+    },
+    {
+      "epoch": 2.147695649222833,
+      "grad_norm": 0.0,
+      "learning_rate": 5.697758496023138e-05,
+      "loss": 6.0003,
+      "mean_token_accuracy": 0.38371361922472713,
+      "num_tokens": 7802228.0,
+      "step": 990
+    },
+    {
+      "epoch": 2.1694155976379554,
+      "grad_norm": 0.0,
+      "learning_rate": 5.553145336225597e-05,
+      "loss": 5.9941,
+      "mean_token_accuracy": 0.386648180836346,
+      "num_tokens": 7881292.0,
+      "step": 1000
+    },
+    {
+      "epoch": 2.191135546053078,
+      "grad_norm": 0.0,
+      "learning_rate": 5.408532176428055e-05,
+      "loss": 5.9629,
+      "mean_token_accuracy": 0.3859988093841821,
+      "num_tokens": 7960306.0,
+      "step": 1010
+    },
+    {
+      "epoch": 2.212855494468201,
+      "grad_norm": 0.0,
+      "learning_rate": 5.263919016630514e-05,
+      "loss": 5.9615,
+      "mean_token_accuracy": 0.3859686201903969,
+      "num_tokens": 8039403.0,
+      "step": 1020
+    },
+    {
+      "epoch": 2.2345754428833233,
+      "grad_norm": 0.0,
+      "learning_rate": 5.119305856832972e-05,
+      "loss": 5.9744,
+      "mean_token_accuracy": 0.3849541787989438,
+      "num_tokens": 8118810.0,
+      "step": 1030
+    },
+    {
+      "epoch": 2.256295391298446,
+      "grad_norm": 0.0,
+      "learning_rate": 4.9746926970354304e-05,
+      "loss": 6.0192,
+      "mean_token_accuracy": 0.3843318622326478,
+      "num_tokens": 8197744.0,
+      "step": 1040
+    },
+    {
+      "epoch": 2.2780153397135683,
+      "grad_norm": 0.0,
+      "learning_rate": 4.830079537237889e-05,
+      "loss": 6.0364,
+      "mean_token_accuracy": 0.38417832332197577,
+      "num_tokens": 8276673.0,
+      "step": 1050
+    },
+    {
+      "epoch": 2.2997352881286908,
+      "grad_norm": 0.0,
+      "learning_rate": 4.685466377440347e-05,
+      "loss": 6.0178,
+      "mean_token_accuracy": 0.38303852297831326,
+      "num_tokens": 8355486.0,
+      "step": 1060
+    },
+    {
+      "epoch": 2.3214552365438132,
+      "grad_norm": 0.0,
+      "learning_rate": 4.540853217642806e-05,
+      "loss": 5.9567,
+      "mean_token_accuracy": 0.38857606865931305,
+      "num_tokens": 8434638.0,
+      "step": 1070
+    },
+    {
+      "epoch": 2.3431751849589357,
+      "grad_norm": 0.0,
+      "learning_rate": 4.396240057845264e-05,
+      "loss": 5.9893,
+      "mean_token_accuracy": 0.38565383905079215,
+      "num_tokens": 8513720.0,
+      "step": 1080
+    },
+    {
+      "epoch": 2.364895133374058,
+      "grad_norm": 0.0,
+      "learning_rate": 4.2516268980477226e-05,
+      "loss": 5.9812,
+      "mean_token_accuracy": 0.38872407528106123,
+      "num_tokens": 8592514.0,
+      "step": 1090
+    },
+    {
+      "epoch": 2.3866150817891807,
+      "grad_norm": 0.0,
+      "learning_rate": 4.107013738250181e-05,
+      "loss": 6.0234,
+      "mean_token_accuracy": 0.3825469396775588,
+      "num_tokens": 8671231.0,
+      "step": 1100
+    },
+    {
+      "epoch": 2.408335030204303,
+      "grad_norm": 0.0,
+      "learning_rate": 3.9624005784526394e-05,
+      "loss": 6.0149,
+      "mean_token_accuracy": 0.3845805463381112,
+      "num_tokens": 8750288.0,
+      "step": 1110
+    },
+    {
+      "epoch": 2.4300549786194257,
+      "grad_norm": 0.0,
+      "learning_rate": 3.817787418655098e-05,
+      "loss": 6.0056,
+      "mean_token_accuracy": 0.38355012007523326,
+      "num_tokens": 8829159.0,
+      "step": 1120
+    },
+    {
+      "epoch": 2.451774927034548,
+      "grad_norm": 0.0,
+      "learning_rate": 3.673174258857556e-05,
+      "loss": 5.9945,
+      "mean_token_accuracy": 0.38476743231294674,
+      "num_tokens": 8907706.0,
+      "step": 1130
+    },
+    {
+      "epoch": 2.4734948754496706,
+      "grad_norm": 0.0,
+      "learning_rate": 3.5285610990600147e-05,
+      "loss": 5.9712,
+      "mean_token_accuracy": 0.3861268714419566,
+      "num_tokens": 8986526.0,
+      "step": 1140
+    },
+    {
+      "epoch": 2.495214823864793,
+      "grad_norm": 0.0,
+      "learning_rate": 3.383947939262473e-05,
+      "loss": 6.0243,
+      "mean_token_accuracy": 0.3839300020830706,
+      "num_tokens": 9065399.0,
+      "step": 1150
+    },
+    {
+      "epoch": 2.5169347722799156,
+      "grad_norm": 0.0,
+      "learning_rate": 3.2393347794649315e-05,
+      "loss": 6.0197,
+      "mean_token_accuracy": 0.3838517373194918,
+      "num_tokens": 9144182.0,
+      "step": 1160
+    },
+    {
+      "epoch": 2.5386547206950385,
+      "grad_norm": 0.0,
+      "learning_rate": 3.09472161966739e-05,
+      "loss": 6.0336,
+      "mean_token_accuracy": 0.38345675652381034,
+      "num_tokens": 9222743.0,
+      "step": 1170
+    },
+    {
+      "epoch": 2.560374669110161,
+      "grad_norm": 0.0,
+      "learning_rate": 2.950108459869848e-05,
+      "loss": 6.0275,
+      "mean_token_accuracy": 0.38377260488923637,
+      "num_tokens": 9301686.0,
+      "step": 1180
+    },
+    {
+      "epoch": 2.5820946175252835,
+      "grad_norm": 0.0,
+      "learning_rate": 2.8054953000723068e-05,
+      "loss": 6.0401,
+      "mean_token_accuracy": 0.38272831091890114,
+      "num_tokens": 9380398.0,
+      "step": 1190
+    },
+    {
+      "epoch": 2.603814565940406,
+      "grad_norm": 0.0,
+      "learning_rate": 2.6608821402747652e-05,
+      "loss": 6.003,
+      "mean_token_accuracy": 0.38574083771090956,
+      "num_tokens": 9459228.0,
+      "step": 1200
+    },
+    {
+      "epoch": 2.6255345143555284,
+      "grad_norm": 0.0,
+      "learning_rate": 2.516268980477224e-05,
+      "loss": 6.0233,
+      "mean_token_accuracy": 0.3827782694483176,
+      "num_tokens": 9538141.0,
+      "step": 1210
+    },
+    {
+      "epoch": 2.647254462770651,
+      "grad_norm": 0.0,
+      "learning_rate": 2.3716558206796817e-05,
+      "loss": 6.0003,
+      "mean_token_accuracy": 0.3853726448956877,
+      "num_tokens": 9617091.0,
+      "step": 1220
+    },
+    {
+      "epoch": 2.6689744111857734,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2270426608821404e-05,
+      "loss": 6.0271,
+      "mean_token_accuracy": 0.38530398234725,
+      "num_tokens": 9696158.0,
+      "step": 1230
+    },
+    {
+      "epoch": 2.690694359600896,
+      "grad_norm": 0.0,
+      "learning_rate": 2.082429501084599e-05,
+      "loss": 5.9816,
+      "mean_token_accuracy": 0.38289073556661607,
+      "num_tokens": 9775025.0,
+      "step": 1240
+    },
+    {
+      "epoch": 2.7124143080160183,
+      "grad_norm": 0.0,
+      "learning_rate": 1.9378163412870573e-05,
+      "loss": 6.003,
+      "mean_token_accuracy": 0.3852554757846519,
+      "num_tokens": 9853991.0,
+      "step": 1250
+    },
+    {
+      "epoch": 2.734134256431141,
+      "grad_norm": 0.0,
+      "learning_rate": 1.7932031814895157e-05,
+      "loss": 6.0387,
+      "mean_token_accuracy": 0.38218798900488765,
+      "num_tokens": 9932459.0,
+      "step": 1260
+    },
+    {
+      "epoch": 2.7558542048462638,
+      "grad_norm": 0.0,
+      "learning_rate": 1.648590021691974e-05,
+      "loss": 6.0218,
+      "mean_token_accuracy": 0.38361733745550736,
+      "num_tokens": 10011147.0,
+      "step": 1270
+    },
+    {
+      "epoch": 2.7775741532613862,
+      "grad_norm": 0.0,
+      "learning_rate": 1.5039768618944326e-05,
+      "loss": 6.0164,
+      "mean_token_accuracy": 0.3833353664376773,
+      "num_tokens": 10089867.0,
+      "step": 1280
+    },
+    {
+      "epoch": 2.7992941016765087,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3593637020968908e-05,
+      "loss": 6.0203,
+      "mean_token_accuracy": 0.3844827389344573,
+      "num_tokens": 10168558.0,
+      "step": 1290
+    },
+    {
+      "epoch": 2.821014050091631,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2147505422993492e-05,
+      "loss": 6.0223,
+      "mean_token_accuracy": 0.38475555207114664,
+      "num_tokens": 10247626.0,
+      "step": 1300
+    },
+    {
+      "epoch": 2.8427339985067537,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0701373825018076e-05,
+      "loss": 5.997,
+      "mean_token_accuracy": 0.3833994207670912,
+      "num_tokens": 10326786.0,
+      "step": 1310
+    },
+    {
+      "epoch": 2.864453946921876,
+      "grad_norm": 0.0,
+      "learning_rate": 9.25524222704266e-06,
+      "loss": 6.0283,
+      "mean_token_accuracy": 0.3812030048458837,
+      "num_tokens": 10405619.0,
+      "step": 1320
+    },
+    {
+      "epoch": 2.8861738953369986,
+      "grad_norm": 0.0,
+      "learning_rate": 7.809110629067245e-06,
+      "loss": 6.0422,
+      "mean_token_accuracy": 0.381096905877348,
+      "num_tokens": 10484466.0,
+      "step": 1330
+    },
+    {
+      "epoch": 2.907893843752121,
+      "grad_norm": 0.0,
+      "learning_rate": 6.36297903109183e-06,
+      "loss": 5.9859,
+      "mean_token_accuracy": 0.38405414449516684,
+      "num_tokens": 10563350.0,
+      "step": 1340
+    },
+    {
+      "epoch": 2.9296137921672436,
+      "grad_norm": 0.0,
+      "learning_rate": 4.916847433116413e-06,
+      "loss": 6.0283,
+      "mean_token_accuracy": 0.38398846148047594,
+      "num_tokens": 10642421.0,
+      "step": 1350
+    },
+    {
+      "epoch": 2.951333740582366,
+      "grad_norm": 0.0,
+      "learning_rate": 3.470715835140998e-06,
+      "loss": 6.0132,
+      "mean_token_accuracy": 0.3835720970411785,
+      "num_tokens": 10721272.0,
+      "step": 1360
+    },
+    {
+      "epoch": 2.9730536889974886,
+      "grad_norm": 0.0,
+      "learning_rate": 2.024584237165582e-06,
+      "loss": 6.0098,
+      "mean_token_accuracy": 0.3844847684260458,
+      "num_tokens": 10800144.0,
+      "step": 1370
+    },
+    {
+      "epoch": 2.994773637412611,
+      "grad_norm": 0.0,
+      "learning_rate": 5.784526391901663e-07,
+      "loss": 5.962,
+      "mean_token_accuracy": 0.3870904964976944,
+      "num_tokens": 10879173.0,
+      "step": 1380
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1383,
+  "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": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.6605276253782835e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1383/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131a0a21414525756ac7e71774e33b16bf1fd48bed5fd2484806044f425159ba
+size 6161

checkpoint-461/README.md

@@ -0,0 +1,209 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- 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 0.17.0

checkpoint-461/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-461/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1790b7928f19c11eea9b3ae25f2fe1a066a98224c55c01b0bee9e895ec7a9e48
+size 54560368

checkpoint-461/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-461/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05d4690c9f75679e3413c951426acd91577e23ee13a26df1957e90b9e5a8893f
+size 1593

checkpoint-461/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fea141dda0bb9d06867529f5f3e0869ed584743a0c64dab3e70fc8a6c34be4ad
+size 14645

checkpoint-461/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ce7281ad70bf1f6664bc4ba855e401060fe9cb5ebab1f99f4310600a12d6c33
+size 1465

checkpoint-461/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-461/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-461/trainer_state.json

@@ -0,0 +1,448 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 461,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021719948415122516,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019869848156182213,
+      "loss": 6.0531,
+      "mean_token_accuracy": 0.37881034857127815,
+      "num_tokens": 78573.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.04343989683024503,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019725234996384672,
+      "loss": 5.9903,
+      "mean_token_accuracy": 0.3887314551044255,
+      "num_tokens": 157496.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.06515984524536754,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019580621836587129,
+      "loss": 5.9929,
+      "mean_token_accuracy": 0.3850487937917933,
+      "num_tokens": 236512.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08687979366049006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019436008676789588,
+      "loss": 5.986,
+      "mean_token_accuracy": 0.3865805763518438,
+      "num_tokens": 315608.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.10859974207561257,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019291395516992047,
+      "loss": 6.0318,
+      "mean_token_accuracy": 0.38490854618139564,
+      "num_tokens": 394791.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.13031969049073508,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019146782357194506,
+      "loss": 5.9875,
+      "mean_token_accuracy": 0.38546840590424836,
+      "num_tokens": 473456.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.1520396389058576,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019002169197396965,
+      "loss": 5.9773,
+      "mean_token_accuracy": 0.3837947838823311,
+      "num_tokens": 552247.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.17375958732098012,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001885755603759942,
+      "loss": 6.0197,
+      "mean_token_accuracy": 0.38375892234034836,
+      "num_tokens": 631096.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19547953573610263,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001871294287780188,
+      "loss": 6.0014,
+      "mean_token_accuracy": 0.38519658900331705,
+      "num_tokens": 710275.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.21719948415122514,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001856832971800434,
+      "loss": 6.0217,
+      "mean_token_accuracy": 0.3826989881345071,
+      "num_tokens": 789174.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.23891943256634765,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018423716558206799,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.3842650496866554,
+      "num_tokens": 867922.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.26063938098147016,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018279103398409255,
+      "loss": 5.9548,
+      "mean_token_accuracy": 0.3875111517496407,
+      "num_tokens": 947073.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2823593293965927,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018134490238611714,
+      "loss": 6.0071,
+      "mean_token_accuracy": 0.38376112943515184,
+      "num_tokens": 1026211.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.3040792778117152,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017989877078814173,
+      "loss": 6.0105,
+      "mean_token_accuracy": 0.38463024909142407,
+      "num_tokens": 1105147.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.3257992262268377,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001784526391901663,
+      "loss": 6.0449,
+      "mean_token_accuracy": 0.38241248747799544,
+      "num_tokens": 1183837.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.34751917464196025,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017700650759219091,
+      "loss": 5.9946,
+      "mean_token_accuracy": 0.3821917780907825,
+      "num_tokens": 1262676.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.36923912305708273,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017556037599421548,
+      "loss": 6.0049,
+      "mean_token_accuracy": 0.3842250820598565,
+      "num_tokens": 1341759.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.39095907147220527,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017411424439624007,
+      "loss": 5.9736,
+      "mean_token_accuracy": 0.3861917880363762,
+      "num_tokens": 1420987.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.41267901988732775,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017266811279826466,
+      "loss": 6.0431,
+      "mean_token_accuracy": 0.38146835477091373,
+      "num_tokens": 1499903.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.4343989683024503,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017122198120028922,
+      "loss": 6.0069,
+      "mean_token_accuracy": 0.3861038032686338,
+      "num_tokens": 1578880.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.4561189167175728,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016977584960231381,
+      "loss": 6.0091,
+      "mean_token_accuracy": 0.3845075036631897,
+      "num_tokens": 1657709.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.4778388651326953,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001683297180043384,
+      "loss": 6.0029,
+      "mean_token_accuracy": 0.38288453239947556,
+      "num_tokens": 1736620.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.49955881354781784,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000166883586406363,
+      "loss": 5.9933,
+      "mean_token_accuracy": 0.38531269936356694,
+      "num_tokens": 1815478.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.5212787619629403,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016543745480838756,
+      "loss": 6.0334,
+      "mean_token_accuracy": 0.3833939728909172,
+      "num_tokens": 1894256.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.5429987103780628,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016399132321041215,
+      "loss": 6.0484,
+      "mean_token_accuracy": 0.3841994108865038,
+      "num_tokens": 1972997.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.5647186587931854,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016254519161243674,
+      "loss": 6.0285,
+      "mean_token_accuracy": 0.38443261398933826,
+      "num_tokens": 2051890.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.5864386072083079,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016109906001446133,
+      "loss": 5.983,
+      "mean_token_accuracy": 0.385862308065407,
+      "num_tokens": 2130746.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.6081585556234304,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015965292841648592,
+      "loss": 6.0046,
+      "mean_token_accuracy": 0.3859730801777914,
+      "num_tokens": 2209603.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.6298785040385529,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001582067968185105,
+      "loss": 5.9887,
+      "mean_token_accuracy": 0.38499277490191164,
+      "num_tokens": 2288743.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.6515984524536754,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015676066522053508,
+      "loss": 5.9788,
+      "mean_token_accuracy": 0.3864025830756873,
+      "num_tokens": 2367648.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.6733184008687979,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015531453362255964,
+      "loss": 6.0162,
+      "mean_token_accuracy": 0.38221894631860776,
+      "num_tokens": 2446256.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.6950383492839205,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015386840202458423,
+      "loss": 6.0017,
+      "mean_token_accuracy": 0.38538019855041056,
+      "num_tokens": 2525065.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.716758297699043,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015242227042660883,
+      "loss": 5.9569,
+      "mean_token_accuracy": 0.3852926092222333,
+      "num_tokens": 2604183.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.7384782461141655,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015097613882863342,
+      "loss": 6.0072,
+      "mean_token_accuracy": 0.38616998645011336,
+      "num_tokens": 2683084.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.7601981945292879,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000149530007230658,
+      "loss": 6.0428,
+      "mean_token_accuracy": 0.3831095602363348,
+      "num_tokens": 2761824.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.7819181429444105,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014808387563268257,
+      "loss": 5.9781,
+      "mean_token_accuracy": 0.3861894382047467,
+      "num_tokens": 2840709.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.803638091359533,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014663774403470716,
+      "loss": 5.9898,
+      "mean_token_accuracy": 0.3846066597965546,
+      "num_tokens": 2919385.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.8253580397746555,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014519161243673173,
+      "loss": 6.0098,
+      "mean_token_accuracy": 0.38357423364650456,
+      "num_tokens": 2998308.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.8470779881897781,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014374548083875634,
+      "loss": 6.0349,
+      "mean_token_accuracy": 0.3809299209038727,
+      "num_tokens": 3076962.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.8687979366049006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001422993492407809,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.38217092433478683,
+      "num_tokens": 3155983.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.890517885020023,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001408532176428055,
+      "loss": 5.9728,
+      "mean_token_accuracy": 0.3870704318396747,
+      "num_tokens": 3234960.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.9122378334351456,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001394070860448301,
+      "loss": 6.0541,
+      "mean_token_accuracy": 0.38209462116938087,
+      "num_tokens": 3313797.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.9339577818502681,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013796095444685465,
+      "loss": 5.9871,
+      "mean_token_accuracy": 0.38401242352556436,
+      "num_tokens": 3392880.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.9556777302653906,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013651482284887927,
+      "loss": 5.9901,
+      "mean_token_accuracy": 0.38375150066567587,
+      "num_tokens": 3471597.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.9773976786805131,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013506869125090384,
+      "loss": 5.9797,
+      "mean_token_accuracy": 0.38728573790285736,
+      "num_tokens": 3550697.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.9991176270956357,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013362255965292843,
+      "loss": 5.9971,
+      "mean_token_accuracy": 0.38420643559657036,
+      "num_tokens": 3629481.0,
+      "step": 460
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1383,
+  "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": 1.553509208459428e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-461/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131a0a21414525756ac7e71774e33b16bf1fd48bed5fd2484806044f425159ba
+size 6161

checkpoint-922/README.md

@@ -0,0 +1,209 @@
+---
+base_model: mistralai/Mistral-7B-Instruct-v0.3
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:mistralai/Mistral-7B-Instruct-v0.3
+- 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 0.17.0

checkpoint-922/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "mistralai/Mistral-7B-Instruct-v0.3",
+  "bias": "none",
+  "corda_config": null,
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-922/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1790b7928f19c11eea9b3ae25f2fe1a066a98224c55c01b0bee9e895ec7a9e48
+size 54560368

checkpoint-922/chat_template.jinja

@@ -0,0 +1,87 @@
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+{%- if not tools is defined %}
+    {%- set tools = none %}
+{%- endif %}
+{%- set user_messages = loop_messages | selectattr("role", "equalto", "user") | list %}
+
+{#- This block checks for alternating user/assistant messages, skipping tool calling messages #}
+{%- set ns = namespace() %}
+{%- set ns.index = 0 %}
+{%- for message in loop_messages %}
+    {%- if not (message.role == "tool" or message.role == "tool_results" or (message.tool_calls is defined and message.tool_calls is not none)) %}
+        {%- if (message["role"] == "user") != (ns.index % 2 == 0) %}
+            {{- raise_exception("After the optional system message, conversation roles must alternate user/assistant/user/assistant/...") }}
+        {%- endif %}
+        {%- set ns.index = ns.index + 1 %}
+    {%- endif %}
+{%- endfor %}
+
+{{- bos_token }}
+{%- for message in loop_messages %}
+    {%- if message["role"] == "user" %}
+        {%- if tools is not none and (message == user_messages[-1]) %}
+            {{- "[AVAILABLE_TOOLS] [" }}
+            {%- for tool in tools %}
+                {%- set tool = tool.function %}
+                {{- '{"type": "function", "function": {' }}
+                {%- for key, val in tool.items() if key != "return" %}
+                    {%- if val is string %}
+                        {{- '"' + key + '": "' + val + '"' }}
+                    {%- else %}
+                        {{- '"' + key + '": ' + val|tojson }}
+                    {%- endif %}
+                    {%- if not loop.last %}
+                        {{- ", " }}
+                    {%- endif %}
+                {%- endfor %}
+                {{- "}}" }}
+                {%- if not loop.last %}
+                    {{- ", " }}
+                {%- else %}
+                    {{- "]" }}
+                {%- endif %}
+            {%- endfor %}
+            {{- "[/AVAILABLE_TOOLS]" }}
+            {%- endif %}
+        {%- if loop.last and system_message is defined %}
+            {{- "[INST] " + system_message + "\n\n" + message["content"] + "[/INST]" }}
+        {%- else %}
+            {{- "[INST] " + message["content"] + "[/INST]" }}
+        {%- endif %}
+    {%- elif message.tool_calls is defined and message.tool_calls is not none %}
+        {{- "[TOOL_CALLS] [" }}
+        {%- for tool_call in message.tool_calls %}
+            {%- set out = tool_call.function|tojson %}
+            {{- out[:-1] }}
+            {%- if not tool_call.id is defined or tool_call.id|length != 9 %}
+                {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+            {%- endif %}
+            {{- ', "id": "' + tool_call.id + '"}' }}
+            {%- if not loop.last %}
+                {{- ", " }}
+            {%- else %}
+                {{- "]" + eos_token }}
+            {%- endif %}
+        {%- endfor %}
+    {%- elif message["role"] == "assistant" %}
+        {{- " " + message["content"]|trim + eos_token}}
+    {%- elif message["role"] == "tool_results" or message["role"] == "tool" %}
+        {%- if message.content is defined and message.content.content is defined %}
+            {%- set content = message.content.content %}
+        {%- else %}
+            {%- set content = message.content %}
+        {%- endif %}
+        {{- '[TOOL_RESULTS] {"content": ' + content|string + ", " }}
+        {%- if not message.tool_call_id is defined or message.tool_call_id|length != 9 %}
+            {{- raise_exception("Tool call IDs should be alphanumeric strings with length 9!") }}
+        {%- endif %}
+        {{- '"call_id": "' + message.tool_call_id + '"}[/TOOL_RESULTS]' }}
+    {%- else %}
+        {{- raise_exception("Only user and assistant roles are supported, with the exception of an initial optional system message!") }}
+    {%- endif %}
+{%- endfor %}

checkpoint-922/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d25237402eecb22fcce8a7b527f350a3dea69b08a73fb37359db364a0e2692a8
+size 1593

checkpoint-922/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7a8c296296f6fbd072906c578880fb09f4a8720fc9aef9a7ee1b60d9ab6bb9f
+size 14645

checkpoint-922/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c56a513ca46c68f1d30f1c250981246cbe3ec666f9a8922ea6f553f4e3931ea
+size 1465

checkpoint-922/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-922/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

checkpoint-922/trainer_state.json

@@ -0,0 +1,862 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 922,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.021719948415122516,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019869848156182213,
+      "loss": 6.0531,
+      "mean_token_accuracy": 0.37881034857127815,
+      "num_tokens": 78573.0,
+      "step": 10
+    },
+    {
+      "epoch": 0.04343989683024503,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019725234996384672,
+      "loss": 5.9903,
+      "mean_token_accuracy": 0.3887314551044255,
+      "num_tokens": 157496.0,
+      "step": 20
+    },
+    {
+      "epoch": 0.06515984524536754,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019580621836587129,
+      "loss": 5.9929,
+      "mean_token_accuracy": 0.3850487937917933,
+      "num_tokens": 236512.0,
+      "step": 30
+    },
+    {
+      "epoch": 0.08687979366049006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019436008676789588,
+      "loss": 5.986,
+      "mean_token_accuracy": 0.3865805763518438,
+      "num_tokens": 315608.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.10859974207561257,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019291395516992047,
+      "loss": 6.0318,
+      "mean_token_accuracy": 0.38490854618139564,
+      "num_tokens": 394791.0,
+      "step": 50
+    },
+    {
+      "epoch": 0.13031969049073508,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019146782357194506,
+      "loss": 5.9875,
+      "mean_token_accuracy": 0.38546840590424836,
+      "num_tokens": 473456.0,
+      "step": 60
+    },
+    {
+      "epoch": 0.1520396389058576,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00019002169197396965,
+      "loss": 5.9773,
+      "mean_token_accuracy": 0.3837947838823311,
+      "num_tokens": 552247.0,
+      "step": 70
+    },
+    {
+      "epoch": 0.17375958732098012,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001885755603759942,
+      "loss": 6.0197,
+      "mean_token_accuracy": 0.38375892234034836,
+      "num_tokens": 631096.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.19547953573610263,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001871294287780188,
+      "loss": 6.0014,
+      "mean_token_accuracy": 0.38519658900331705,
+      "num_tokens": 710275.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.21719948415122514,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001856832971800434,
+      "loss": 6.0217,
+      "mean_token_accuracy": 0.3826989881345071,
+      "num_tokens": 789174.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.23891943256634765,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018423716558206799,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.3842650496866554,
+      "num_tokens": 867922.0,
+      "step": 110
+    },
+    {
+      "epoch": 0.26063938098147016,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018279103398409255,
+      "loss": 5.9548,
+      "mean_token_accuracy": 0.3875111517496407,
+      "num_tokens": 947073.0,
+      "step": 120
+    },
+    {
+      "epoch": 0.2823593293965927,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00018134490238611714,
+      "loss": 6.0071,
+      "mean_token_accuracy": 0.38376112943515184,
+      "num_tokens": 1026211.0,
+      "step": 130
+    },
+    {
+      "epoch": 0.3040792778117152,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017989877078814173,
+      "loss": 6.0105,
+      "mean_token_accuracy": 0.38463024909142407,
+      "num_tokens": 1105147.0,
+      "step": 140
+    },
+    {
+      "epoch": 0.3257992262268377,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001784526391901663,
+      "loss": 6.0449,
+      "mean_token_accuracy": 0.38241248747799544,
+      "num_tokens": 1183837.0,
+      "step": 150
+    },
+    {
+      "epoch": 0.34751917464196025,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017700650759219091,
+      "loss": 5.9946,
+      "mean_token_accuracy": 0.3821917780907825,
+      "num_tokens": 1262676.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.36923912305708273,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017556037599421548,
+      "loss": 6.0049,
+      "mean_token_accuracy": 0.3842250820598565,
+      "num_tokens": 1341759.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.39095907147220527,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017411424439624007,
+      "loss": 5.9736,
+      "mean_token_accuracy": 0.3861917880363762,
+      "num_tokens": 1420987.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.41267901988732775,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017266811279826466,
+      "loss": 6.0431,
+      "mean_token_accuracy": 0.38146835477091373,
+      "num_tokens": 1499903.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.4343989683024503,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00017122198120028922,
+      "loss": 6.0069,
+      "mean_token_accuracy": 0.3861038032686338,
+      "num_tokens": 1578880.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.4561189167175728,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016977584960231381,
+      "loss": 6.0091,
+      "mean_token_accuracy": 0.3845075036631897,
+      "num_tokens": 1657709.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.4778388651326953,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001683297180043384,
+      "loss": 6.0029,
+      "mean_token_accuracy": 0.38288453239947556,
+      "num_tokens": 1736620.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.49955881354781784,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000166883586406363,
+      "loss": 5.9933,
+      "mean_token_accuracy": 0.38531269936356694,
+      "num_tokens": 1815478.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.5212787619629403,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016543745480838756,
+      "loss": 6.0334,
+      "mean_token_accuracy": 0.3833939728909172,
+      "num_tokens": 1894256.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.5429987103780628,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016399132321041215,
+      "loss": 6.0484,
+      "mean_token_accuracy": 0.3841994108865038,
+      "num_tokens": 1972997.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.5647186587931854,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016254519161243674,
+      "loss": 6.0285,
+      "mean_token_accuracy": 0.38443261398933826,
+      "num_tokens": 2051890.0,
+      "step": 260
+    },
+    {
+      "epoch": 0.5864386072083079,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00016109906001446133,
+      "loss": 5.983,
+      "mean_token_accuracy": 0.385862308065407,
+      "num_tokens": 2130746.0,
+      "step": 270
+    },
+    {
+      "epoch": 0.6081585556234304,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015965292841648592,
+      "loss": 6.0046,
+      "mean_token_accuracy": 0.3859730801777914,
+      "num_tokens": 2209603.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.6298785040385529,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001582067968185105,
+      "loss": 5.9887,
+      "mean_token_accuracy": 0.38499277490191164,
+      "num_tokens": 2288743.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.6515984524536754,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015676066522053508,
+      "loss": 5.9788,
+      "mean_token_accuracy": 0.3864025830756873,
+      "num_tokens": 2367648.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.6733184008687979,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015531453362255964,
+      "loss": 6.0162,
+      "mean_token_accuracy": 0.38221894631860776,
+      "num_tokens": 2446256.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.6950383492839205,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015386840202458423,
+      "loss": 6.0017,
+      "mean_token_accuracy": 0.38538019855041056,
+      "num_tokens": 2525065.0,
+      "step": 320
+    },
+    {
+      "epoch": 0.716758297699043,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015242227042660883,
+      "loss": 5.9569,
+      "mean_token_accuracy": 0.3852926092222333,
+      "num_tokens": 2604183.0,
+      "step": 330
+    },
+    {
+      "epoch": 0.7384782461141655,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00015097613882863342,
+      "loss": 6.0072,
+      "mean_token_accuracy": 0.38616998645011336,
+      "num_tokens": 2683084.0,
+      "step": 340
+    },
+    {
+      "epoch": 0.7601981945292879,
+      "grad_norm": 0.0,
+      "learning_rate": 0.000149530007230658,
+      "loss": 6.0428,
+      "mean_token_accuracy": 0.3831095602363348,
+      "num_tokens": 2761824.0,
+      "step": 350
+    },
+    {
+      "epoch": 0.7819181429444105,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014808387563268257,
+      "loss": 5.9781,
+      "mean_token_accuracy": 0.3861894382047467,
+      "num_tokens": 2840709.0,
+      "step": 360
+    },
+    {
+      "epoch": 0.803638091359533,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014663774403470716,
+      "loss": 5.9898,
+      "mean_token_accuracy": 0.3846066597965546,
+      "num_tokens": 2919385.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.8253580397746555,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014519161243673173,
+      "loss": 6.0098,
+      "mean_token_accuracy": 0.38357423364650456,
+      "num_tokens": 2998308.0,
+      "step": 380
+    },
+    {
+      "epoch": 0.8470779881897781,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00014374548083875634,
+      "loss": 6.0349,
+      "mean_token_accuracy": 0.3809299209038727,
+      "num_tokens": 3076962.0,
+      "step": 390
+    },
+    {
+      "epoch": 0.8687979366049006,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001422993492407809,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.38217092433478683,
+      "num_tokens": 3155983.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.890517885020023,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001408532176428055,
+      "loss": 5.9728,
+      "mean_token_accuracy": 0.3870704318396747,
+      "num_tokens": 3234960.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.9122378334351456,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001394070860448301,
+      "loss": 6.0541,
+      "mean_token_accuracy": 0.38209462116938087,
+      "num_tokens": 3313797.0,
+      "step": 420
+    },
+    {
+      "epoch": 0.9339577818502681,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013796095444685465,
+      "loss": 5.9871,
+      "mean_token_accuracy": 0.38401242352556436,
+      "num_tokens": 3392880.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.9556777302653906,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013651482284887927,
+      "loss": 5.9901,
+      "mean_token_accuracy": 0.38375150066567587,
+      "num_tokens": 3471597.0,
+      "step": 440
+    },
+    {
+      "epoch": 0.9773976786805131,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013506869125090384,
+      "loss": 5.9797,
+      "mean_token_accuracy": 0.38728573790285736,
+      "num_tokens": 3550697.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.9991176270956357,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013362255965292843,
+      "loss": 5.9971,
+      "mean_token_accuracy": 0.38420643559657036,
+      "num_tokens": 3629481.0,
+      "step": 460
+    },
+    {
+      "epoch": 1.0195479535736103,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013217642805495302,
+      "loss": 6.0223,
+      "mean_token_accuracy": 0.3833757105509308,
+      "num_tokens": 3703746.0,
+      "step": 470
+    },
+    {
+      "epoch": 1.0412679019887328,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00013073029645697758,
+      "loss": 6.0146,
+      "mean_token_accuracy": 0.38417146790307016,
+      "num_tokens": 3782783.0,
+      "step": 480
+    },
+    {
+      "epoch": 1.0629878504038552,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012928416485900217,
+      "loss": 5.9713,
+      "mean_token_accuracy": 0.3863212176831439,
+      "num_tokens": 3862048.0,
+      "step": 490
+    },
+    {
+      "epoch": 1.0847077988189777,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012783803326102676,
+      "loss": 5.9944,
+      "mean_token_accuracy": 0.38522618702845646,
+      "num_tokens": 3941220.0,
+      "step": 500
+    },
+    {
+      "epoch": 1.1064277472341004,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012639190166305135,
+      "loss": 5.9895,
+      "mean_token_accuracy": 0.38548907284857703,
+      "num_tokens": 4020089.0,
+      "step": 510
+    },
+    {
+      "epoch": 1.128147695649223,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012494577006507592,
+      "loss": 5.9901,
+      "mean_token_accuracy": 0.3841517207212746,
+      "num_tokens": 4098981.0,
+      "step": 520
+    },
+    {
+      "epoch": 1.1498676440643454,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001234996384671005,
+      "loss": 6.0125,
+      "mean_token_accuracy": 0.38393973018974065,
+      "num_tokens": 4177983.0,
+      "step": 530
+    },
+    {
+      "epoch": 1.1715875924794679,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012205350686912509,
+      "loss": 5.9999,
+      "mean_token_accuracy": 0.3848019931232557,
+      "num_tokens": 4256818.0,
+      "step": 540
+    },
+    {
+      "epoch": 1.1933075408945903,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00012060737527114966,
+      "loss": 6.0146,
+      "mean_token_accuracy": 0.3834400905063376,
+      "num_tokens": 4335754.0,
+      "step": 550
+    },
+    {
+      "epoch": 1.2150274893097128,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011916124367317427,
+      "loss": 5.9832,
+      "mean_token_accuracy": 0.38411646473687144,
+      "num_tokens": 4414480.0,
+      "step": 560
+    },
+    {
+      "epoch": 1.2367474377248353,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011771511207519885,
+      "loss": 6.0393,
+      "mean_token_accuracy": 0.3809544609161094,
+      "num_tokens": 4493321.0,
+      "step": 570
+    },
+    {
+      "epoch": 1.2584673861399578,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011626898047722344,
+      "loss": 5.9989,
+      "mean_token_accuracy": 0.38565440035890786,
+      "num_tokens": 4572297.0,
+      "step": 580
+    },
+    {
+      "epoch": 1.2801873345550805,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011482284887924801,
+      "loss": 5.9983,
+      "mean_token_accuracy": 0.3863610655302182,
+      "num_tokens": 4651247.0,
+      "step": 590
+    },
+    {
+      "epoch": 1.301907282970203,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011337671728127259,
+      "loss": 6.0116,
+      "mean_token_accuracy": 0.3831069741398096,
+      "num_tokens": 4730012.0,
+      "step": 600
+    },
+    {
+      "epoch": 1.3236272313853255,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001119305856832972,
+      "loss": 6.0195,
+      "mean_token_accuracy": 0.3857766560278833,
+      "num_tokens": 4809013.0,
+      "step": 610
+    },
+    {
+      "epoch": 1.345347179800448,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00011048445408532177,
+      "loss": 6.0108,
+      "mean_token_accuracy": 0.3835394912166521,
+      "num_tokens": 4888027.0,
+      "step": 620
+    },
+    {
+      "epoch": 1.3670671282155704,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010903832248734635,
+      "loss": 5.9558,
+      "mean_token_accuracy": 0.3883327366434969,
+      "num_tokens": 4966859.0,
+      "step": 630
+    },
+    {
+      "epoch": 1.3887870766306931,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010759219088937094,
+      "loss": 6.0088,
+      "mean_token_accuracy": 0.385754154715687,
+      "num_tokens": 5045905.0,
+      "step": 640
+    },
+    {
+      "epoch": 1.4105070250458156,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010614605929139552,
+      "loss": 6.0236,
+      "mean_token_accuracy": 0.3829167880234309,
+      "num_tokens": 5124413.0,
+      "step": 650
+    },
+    {
+      "epoch": 1.432226973460938,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001046999276934201,
+      "loss": 6.0154,
+      "mean_token_accuracy": 0.3834054367849603,
+      "num_tokens": 5203273.0,
+      "step": 660
+    },
+    {
+      "epoch": 1.4539469218760606,
+      "grad_norm": 0.0,
+      "learning_rate": 0.0001032537960954447,
+      "loss": 6.005,
+      "mean_token_accuracy": 0.3848568681394681,
+      "num_tokens": 5281984.0,
+      "step": 670
+    },
+    {
+      "epoch": 1.475666870291183,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010180766449746928,
+      "loss": 5.9805,
+      "mean_token_accuracy": 0.3862292483681813,
+      "num_tokens": 5360846.0,
+      "step": 680
+    },
+    {
+      "epoch": 1.4973868187063055,
+      "grad_norm": 0.0,
+      "learning_rate": 0.00010036153289949386,
+      "loss": 5.9871,
+      "mean_token_accuracy": 0.3851381171494722,
+      "num_tokens": 5439758.0,
+      "step": 690
+    },
+    {
+      "epoch": 1.519106767121428,
+      "grad_norm": 0.0,
+      "learning_rate": 9.891540130151843e-05,
+      "loss": 6.0254,
+      "mean_token_accuracy": 0.3831110308994539,
+      "num_tokens": 5518768.0,
+      "step": 700
+    },
+    {
+      "epoch": 1.5408267155365505,
+      "grad_norm": 0.0,
+      "learning_rate": 9.746926970354303e-05,
+      "loss": 6.0339,
+      "mean_token_accuracy": 0.3808896674308926,
+      "num_tokens": 5597672.0,
+      "step": 710
+    },
+    {
+      "epoch": 1.562546663951673,
+      "grad_norm": 0.0,
+      "learning_rate": 9.602313810556762e-05,
+      "loss": 5.994,
+      "mean_token_accuracy": 0.3865658549708314,
+      "num_tokens": 5676393.0,
+      "step": 720
+    },
+    {
+      "epoch": 1.5842666123667957,
+      "grad_norm": 0.0,
+      "learning_rate": 9.45770065075922e-05,
+      "loss": 6.0026,
+      "mean_token_accuracy": 0.38676879862323404,
+      "num_tokens": 5755416.0,
+      "step": 730
+    },
+    {
+      "epoch": 1.6059865607819181,
+      "grad_norm": 0.0,
+      "learning_rate": 9.313087490961678e-05,
+      "loss": 6.0175,
+      "mean_token_accuracy": 0.38389978763880206,
+      "num_tokens": 5834322.0,
+      "step": 740
+    },
+    {
+      "epoch": 1.6277065091970406,
+      "grad_norm": 0.0,
+      "learning_rate": 9.168474331164136e-05,
+      "loss": 6.0224,
+      "mean_token_accuracy": 0.3840769061935134,
+      "num_tokens": 5912925.0,
+      "step": 750
+    },
+    {
+      "epoch": 1.6494264576121633,
+      "grad_norm": 0.0,
+      "learning_rate": 9.023861171366594e-05,
+      "loss": 5.9683,
+      "mean_token_accuracy": 0.38740592543035746,
+      "num_tokens": 5991913.0,
+      "step": 760
+    },
+    {
+      "epoch": 1.6711464060272858,
+      "grad_norm": 0.0,
+      "learning_rate": 8.879248011569053e-05,
+      "loss": 6.0136,
+      "mean_token_accuracy": 0.3827170055825263,
+      "num_tokens": 6070546.0,
+      "step": 770
+    },
+    {
+      "epoch": 1.6928663544424083,
+      "grad_norm": 0.0,
+      "learning_rate": 8.734634851771512e-05,
+      "loss": 5.9688,
+      "mean_token_accuracy": 0.3871995336958207,
+      "num_tokens": 6149623.0,
+      "step": 780
+    },
+    {
+      "epoch": 1.7145863028575308,
+      "grad_norm": 0.0,
+      "learning_rate": 8.59002169197397e-05,
+      "loss": 6.0639,
+      "mean_token_accuracy": 0.3800558194401674,
+      "num_tokens": 6228396.0,
+      "step": 790
+    },
+    {
+      "epoch": 1.7363062512726533,
+      "grad_norm": 0.0,
+      "learning_rate": 8.445408532176429e-05,
+      "loss": 5.9778,
+      "mean_token_accuracy": 0.3854194077430293,
+      "num_tokens": 6307375.0,
+      "step": 800
+    },
+    {
+      "epoch": 1.7580261996877757,
+      "grad_norm": 0.0,
+      "learning_rate": 8.300795372378887e-05,
+      "loss": 6.0294,
+      "mean_token_accuracy": 0.38350161886774004,
+      "num_tokens": 6386536.0,
+      "step": 810
+    },
+    {
+      "epoch": 1.7797461481028982,
+      "grad_norm": 0.0,
+      "learning_rate": 8.156182212581345e-05,
+      "loss": 5.9736,
+      "mean_token_accuracy": 0.38414000715129076,
+      "num_tokens": 6465708.0,
+      "step": 820
+    },
+    {
+      "epoch": 1.8014660965180207,
+      "grad_norm": 0.0,
+      "learning_rate": 8.011569052783804e-05,
+      "loss": 5.9847,
+      "mean_token_accuracy": 0.3877883184002712,
+      "num_tokens": 6544782.0,
+      "step": 830
+    },
+    {
+      "epoch": 1.8231860449331432,
+      "grad_norm": 0.0,
+      "learning_rate": 7.866955892986261e-05,
+      "loss": 6.043,
+      "mean_token_accuracy": 0.38251175949117167,
+      "num_tokens": 6623497.0,
+      "step": 840
+    },
+    {
+      "epoch": 1.8449059933482657,
+      "grad_norm": 0.0,
+      "learning_rate": 7.72234273318872e-05,
+      "loss": 6.0297,
+      "mean_token_accuracy": 0.38357739897910503,
+      "num_tokens": 6702159.0,
+      "step": 850
+    },
+    {
+      "epoch": 1.8666259417633884,
+      "grad_norm": 0.0,
+      "learning_rate": 7.57772957339118e-05,
+      "loss": 6.0335,
+      "mean_token_accuracy": 0.38290644709486515,
+      "num_tokens": 6780886.0,
+      "step": 860
+    },
+    {
+      "epoch": 1.8883458901785108,
+      "grad_norm": 0.0,
+      "learning_rate": 7.433116413593637e-05,
+      "loss": 6.0273,
+      "mean_token_accuracy": 0.38307004772359504,
+      "num_tokens": 6859533.0,
+      "step": 870
+    },
+    {
+      "epoch": 1.9100658385936333,
+      "grad_norm": 0.0,
+      "learning_rate": 7.288503253796096e-05,
+      "loss": 5.9827,
+      "mean_token_accuracy": 0.385389854805544,
+      "num_tokens": 6938490.0,
+      "step": 880
+    },
+    {
+      "epoch": 1.9317857870087558,
+      "grad_norm": 0.0,
+      "learning_rate": 7.143890093998554e-05,
+      "loss": 6.0212,
+      "mean_token_accuracy": 0.382453205762431,
+      "num_tokens": 7017297.0,
+      "step": 890
+    },
+    {
+      "epoch": 1.9535057354238785,
+      "grad_norm": 0.0,
+      "learning_rate": 6.999276934201012e-05,
+      "loss": 6.0043,
+      "mean_token_accuracy": 0.38360455771908164,
+      "num_tokens": 7096419.0,
+      "step": 900
+    },
+    {
+      "epoch": 1.975225683839001,
+      "grad_norm": 0.0,
+      "learning_rate": 6.854663774403471e-05,
+      "loss": 5.985,
+      "mean_token_accuracy": 0.38632277538999915,
+      "num_tokens": 7175650.0,
+      "step": 910
+    },
+    {
+      "epoch": 1.9969456322541235,
+      "grad_norm": 0.0,
+      "learning_rate": 6.71005061460593e-05,
+      "loss": 6.009,
+      "mean_token_accuracy": 0.38311313565354793,
+      "num_tokens": 7254378.0,
+      "step": 920
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1383,
+  "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": 3.107018416918856e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-922/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131a0a21414525756ac7e71774e33b16bf1fd48bed5fd2484806044f425159ba
+size 6161

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:131a0a21414525756ac7e71774e33b16bf1fd48bed5fd2484806044f425159ba
+size 6161