Upload folder using huggingface_hub

README.md

@@ -0,0 +1,207 @@
+---
+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
+- transformers
+---
+
+# 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 0.17.1

adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "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",
+    "q_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 sha256:02e3b8172a56ce4c92a61a6ee49e572c2e100bb1bced833c487cdc427d8cce20
+size 27280152

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-1614/README.md

@@ -0,0 +1,207 @@
+---
+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
+- transformers
+---
+
+# 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 0.17.1

checkpoint-1614/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "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",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-1614/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:138bc4a53345f66bbe9dccfeb764693d683d74f325bff087469b821689714e14
+size 27280152

checkpoint-1614/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0509d41125bc3f40db1342bb896becf5ff467cfb1d9d137b1e7922644297578d
+size 54636235

checkpoint-1614/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ff31d94a59a6800c19956b59e113de14dff0ed2c8b60ba63a119bfa9ddbce42
+size 14645

checkpoint-1614/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7347ad12e6e15aa1ca55f9964eb23b0a99161fe4d54b9b40659277f87dce33e3
+size 1383

checkpoint-1614/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef8631dd3c4ba7a3b65d5660a164f683f3ab8aee8c1b69d0593430f4c2690f41
+size 1465

checkpoint-1614/trainer_state.json

@@ -0,0 +1,1177 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 1614,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012397334573066791,
+      "grad_norm": 0.6915941834449768,
+      "learning_rate": 0.00018,
+      "loss": 2.3006,
+      "step": 10
+    },
+    {
+      "epoch": 0.024794669146133583,
+      "grad_norm": 0.6273291707038879,
+      "learning_rate": 0.0001992534218166736,
+      "loss": 2.1317,
+      "step": 20
+    },
+    {
+      "epoch": 0.037192003719200374,
+      "grad_norm": 0.45228877663612366,
+      "learning_rate": 0.00019842389050186645,
+      "loss": 1.9808,
+      "step": 30
+    },
+    {
+      "epoch": 0.049589338292267165,
+      "grad_norm": 0.3886250853538513,
+      "learning_rate": 0.00019759435918705932,
+      "loss": 1.8968,
+      "step": 40
+    },
+    {
+      "epoch": 0.06198667286533395,
+      "grad_norm": 0.3263673484325409,
+      "learning_rate": 0.00019676482787225219,
+      "loss": 1.9159,
+      "step": 50
+    },
+    {
+      "epoch": 0.07438400743840075,
+      "grad_norm": 0.3357856273651123,
+      "learning_rate": 0.00019593529655744505,
+      "loss": 1.9052,
+      "step": 60
+    },
+    {
+      "epoch": 0.08678134201146753,
+      "grad_norm": 0.3885687291622162,
+      "learning_rate": 0.00019510576524263792,
+      "loss": 1.8788,
+      "step": 70
+    },
+    {
+      "epoch": 0.09917867658453433,
+      "grad_norm": 0.33165615797042847,
+      "learning_rate": 0.00019427623392783078,
+      "loss": 1.876,
+      "step": 80
+    },
+    {
+      "epoch": 0.11157601115760112,
+      "grad_norm": 0.3510221242904663,
+      "learning_rate": 0.00019344670261302365,
+      "loss": 1.7992,
+      "step": 90
+    },
+    {
+      "epoch": 0.1239733457306679,
+      "grad_norm": 0.35817059874534607,
+      "learning_rate": 0.0001926171712982165,
+      "loss": 1.7386,
+      "step": 100
+    },
+    {
+      "epoch": 0.1363706803037347,
+      "grad_norm": 0.3222461938858032,
+      "learning_rate": 0.00019178763998340938,
+      "loss": 1.8766,
+      "step": 110
+    },
+    {
+      "epoch": 0.1487680148768015,
+      "grad_norm": 0.302379310131073,
+      "learning_rate": 0.00019095810866860224,
+      "loss": 1.833,
+      "step": 120
+    },
+    {
+      "epoch": 0.16116534944986827,
+      "grad_norm": 0.3621092736721039,
+      "learning_rate": 0.00019012857735379514,
+      "loss": 1.7433,
+      "step": 130
+    },
+    {
+      "epoch": 0.17356268402293507,
+      "grad_norm": 0.35103851556777954,
+      "learning_rate": 0.00018929904603898798,
+      "loss": 1.8552,
+      "step": 140
+    },
+    {
+      "epoch": 0.18596001859600186,
+      "grad_norm": 0.3761669993400574,
+      "learning_rate": 0.00018846951472418084,
+      "loss": 1.8072,
+      "step": 150
+    },
+    {
+      "epoch": 0.19835735316906866,
+      "grad_norm": 0.2791743576526642,
+      "learning_rate": 0.00018763998340937373,
+      "loss": 1.882,
+      "step": 160
+    },
+    {
+      "epoch": 0.21075468774213543,
+      "grad_norm": 0.28887104988098145,
+      "learning_rate": 0.00018681045209456657,
+      "loss": 1.945,
+      "step": 170
+    },
+    {
+      "epoch": 0.22315202231520223,
+      "grad_norm": 0.3621903955936432,
+      "learning_rate": 0.00018598092077975944,
+      "loss": 1.7506,
+      "step": 180
+    },
+    {
+      "epoch": 0.23554935688826903,
+      "grad_norm": 0.36899787187576294,
+      "learning_rate": 0.00018515138946495233,
+      "loss": 1.8959,
+      "step": 190
+    },
+    {
+      "epoch": 0.2479466914613358,
+      "grad_norm": 0.3354776203632355,
+      "learning_rate": 0.00018432185815014517,
+      "loss": 1.9282,
+      "step": 200
+    },
+    {
+      "epoch": 0.2603440260344026,
+      "grad_norm": 0.3030059337615967,
+      "learning_rate": 0.00018349232683533803,
+      "loss": 1.9876,
+      "step": 210
+    },
+    {
+      "epoch": 0.2727413606074694,
+      "grad_norm": 0.380134254693985,
+      "learning_rate": 0.00018266279552053093,
+      "loss": 1.795,
+      "step": 220
+    },
+    {
+      "epoch": 0.2851386951805362,
+      "grad_norm": 0.3484257161617279,
+      "learning_rate": 0.00018183326420572376,
+      "loss": 1.9131,
+      "step": 230
+    },
+    {
+      "epoch": 0.297536029753603,
+      "grad_norm": 0.3204387426376343,
+      "learning_rate": 0.00018100373289091663,
+      "loss": 1.9829,
+      "step": 240
+    },
+    {
+      "epoch": 0.3099333643266698,
+      "grad_norm": 0.3759450912475586,
+      "learning_rate": 0.00018017420157610952,
+      "loss": 1.9002,
+      "step": 250
+    },
+    {
+      "epoch": 0.32233069889973653,
+      "grad_norm": 0.3721698820590973,
+      "learning_rate": 0.00017934467026130236,
+      "loss": 1.8657,
+      "step": 260
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.35085615515708923,
+      "learning_rate": 0.00017851513894649523,
+      "loss": 1.8623,
+      "step": 270
+    },
+    {
+      "epoch": 0.34712536804587013,
+      "grad_norm": 0.35750696063041687,
+      "learning_rate": 0.00017768560763168812,
+      "loss": 1.8743,
+      "step": 280
+    },
+    {
+      "epoch": 0.35952270261893693,
+      "grad_norm": 0.3072109520435333,
+      "learning_rate": 0.00017685607631688096,
+      "loss": 1.9626,
+      "step": 290
+    },
+    {
+      "epoch": 0.3719200371920037,
+      "grad_norm": 0.40647512674331665,
+      "learning_rate": 0.00017602654500207382,
+      "loss": 1.8034,
+      "step": 300
+    },
+    {
+      "epoch": 0.3843173717650705,
+      "grad_norm": 0.3000311851501465,
+      "learning_rate": 0.00017519701368726672,
+      "loss": 1.8995,
+      "step": 310
+    },
+    {
+      "epoch": 0.3967147063381373,
+      "grad_norm": 0.36904624104499817,
+      "learning_rate": 0.00017436748237245955,
+      "loss": 1.82,
+      "step": 320
+    },
+    {
+      "epoch": 0.40911204091120407,
+      "grad_norm": 0.337799072265625,
+      "learning_rate": 0.00017353795105765242,
+      "loss": 1.8706,
+      "step": 330
+    },
+    {
+      "epoch": 0.42150937548427087,
+      "grad_norm": 0.4223800003528595,
+      "learning_rate": 0.0001727084197428453,
+      "loss": 1.8584,
+      "step": 340
+    },
+    {
+      "epoch": 0.43390671005733766,
+      "grad_norm": 0.34497585892677307,
+      "learning_rate": 0.00017187888842803818,
+      "loss": 1.8417,
+      "step": 350
+    },
+    {
+      "epoch": 0.44630404463040446,
+      "grad_norm": 0.34032031893730164,
+      "learning_rate": 0.00017104935711323102,
+      "loss": 1.7917,
+      "step": 360
+    },
+    {
+      "epoch": 0.45870137920347126,
+      "grad_norm": 0.4158859848976135,
+      "learning_rate": 0.0001702198257984239,
+      "loss": 1.8749,
+      "step": 370
+    },
+    {
+      "epoch": 0.47109871377653806,
+      "grad_norm": 0.36545196175575256,
+      "learning_rate": 0.00016939029448361678,
+      "loss": 1.8337,
+      "step": 380
+    },
+    {
+      "epoch": 0.48349604834960486,
+      "grad_norm": 0.32123473286628723,
+      "learning_rate": 0.00016856076316880961,
+      "loss": 1.9321,
+      "step": 390
+    },
+    {
+      "epoch": 0.4958933829226716,
+      "grad_norm": 0.45476439595222473,
+      "learning_rate": 0.0001677312318540025,
+      "loss": 1.8185,
+      "step": 400
+    },
+    {
+      "epoch": 0.5082907174957384,
+      "grad_norm": 0.3410905599594116,
+      "learning_rate": 0.00016690170053919537,
+      "loss": 1.9082,
+      "step": 410
+    },
+    {
+      "epoch": 0.5206880520688052,
+      "grad_norm": 0.3436656892299652,
+      "learning_rate": 0.0001660721692243882,
+      "loss": 1.7821,
+      "step": 420
+    },
+    {
+      "epoch": 0.533085386641872,
+      "grad_norm": 0.34343594312667847,
+      "learning_rate": 0.0001652426379095811,
+      "loss": 1.8184,
+      "step": 430
+    },
+    {
+      "epoch": 0.5454827212149388,
+      "grad_norm": 0.4309318959712982,
+      "learning_rate": 0.00016441310659477397,
+      "loss": 1.9124,
+      "step": 440
+    },
+    {
+      "epoch": 0.5578800557880056,
+      "grad_norm": 0.4032953679561615,
+      "learning_rate": 0.0001635835752799668,
+      "loss": 1.7962,
+      "step": 450
+    },
+    {
+      "epoch": 0.5702773903610724,
+      "grad_norm": 0.3726664185523987,
+      "learning_rate": 0.0001627540439651597,
+      "loss": 1.8158,
+      "step": 460
+    },
+    {
+      "epoch": 0.5826747249341392,
+      "grad_norm": 0.36948224902153015,
+      "learning_rate": 0.00016192451265035257,
+      "loss": 1.7539,
+      "step": 470
+    },
+    {
+      "epoch": 0.595072059507206,
+      "grad_norm": 0.33594000339508057,
+      "learning_rate": 0.0001610949813355454,
+      "loss": 1.9287,
+      "step": 480
+    },
+    {
+      "epoch": 0.6074693940802728,
+      "grad_norm": 0.3209264576435089,
+      "learning_rate": 0.0001602654500207383,
+      "loss": 1.8375,
+      "step": 490
+    },
+    {
+      "epoch": 0.6198667286533396,
+      "grad_norm": 0.38256484270095825,
+      "learning_rate": 0.00015943591870593116,
+      "loss": 1.817,
+      "step": 500
+    },
+    {
+      "epoch": 0.6322640632264063,
+      "grad_norm": 0.38966864347457886,
+      "learning_rate": 0.000158606387391124,
+      "loss": 1.7397,
+      "step": 510
+    },
+    {
+      "epoch": 0.6446613977994731,
+      "grad_norm": 0.45601052045822144,
+      "learning_rate": 0.0001577768560763169,
+      "loss": 1.7448,
+      "step": 520
+    },
+    {
+      "epoch": 0.6570587323725399,
+      "grad_norm": 0.39306697249412537,
+      "learning_rate": 0.00015694732476150976,
+      "loss": 1.8505,
+      "step": 530
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.4036141633987427,
+      "learning_rate": 0.00015611779344670262,
+      "loss": 1.9946,
+      "step": 540
+    },
+    {
+      "epoch": 0.6818534015186735,
+      "grad_norm": 0.34463125467300415,
+      "learning_rate": 0.0001552882621318955,
+      "loss": 2.0461,
+      "step": 550
+    },
+    {
+      "epoch": 0.6942507360917403,
+      "grad_norm": 0.3309987485408783,
+      "learning_rate": 0.00015445873081708835,
+      "loss": 1.8714,
+      "step": 560
+    },
+    {
+      "epoch": 0.7066480706648071,
+      "grad_norm": 0.40711745619773865,
+      "learning_rate": 0.00015362919950228122,
+      "loss": 1.9515,
+      "step": 570
+    },
+    {
+      "epoch": 0.7190454052378739,
+      "grad_norm": 0.4855351150035858,
+      "learning_rate": 0.00015279966818747409,
+      "loss": 1.928,
+      "step": 580
+    },
+    {
+      "epoch": 0.7314427398109407,
+      "grad_norm": 0.3159841299057007,
+      "learning_rate": 0.00015197013687266695,
+      "loss": 1.8648,
+      "step": 590
+    },
+    {
+      "epoch": 0.7438400743840075,
+      "grad_norm": 0.34454017877578735,
+      "learning_rate": 0.00015114060555785982,
+      "loss": 1.7614,
+      "step": 600
+    },
+    {
+      "epoch": 0.7562374089570743,
+      "grad_norm": 0.42112237215042114,
+      "learning_rate": 0.00015031107424305268,
+      "loss": 1.7943,
+      "step": 610
+    },
+    {
+      "epoch": 0.768634743530141,
+      "grad_norm": 0.4868924617767334,
+      "learning_rate": 0.00014948154292824555,
+      "loss": 1.8236,
+      "step": 620
+    },
+    {
+      "epoch": 0.7810320781032078,
+      "grad_norm": 0.27235159277915955,
+      "learning_rate": 0.00014865201161343841,
+      "loss": 1.8792,
+      "step": 630
+    },
+    {
+      "epoch": 0.7934294126762746,
+      "grad_norm": 0.36492735147476196,
+      "learning_rate": 0.00014782248029863128,
+      "loss": 1.8139,
+      "step": 640
+    },
+    {
+      "epoch": 0.8058267472493414,
+      "grad_norm": 0.3278910517692566,
+      "learning_rate": 0.00014699294898382414,
+      "loss": 1.9303,
+      "step": 650
+    },
+    {
+      "epoch": 0.8182240818224081,
+      "grad_norm": 0.4410141110420227,
+      "learning_rate": 0.000146163417669017,
+      "loss": 1.7458,
+      "step": 660
+    },
+    {
+      "epoch": 0.8306214163954749,
+      "grad_norm": 0.44660821557044983,
+      "learning_rate": 0.00014533388635420988,
+      "loss": 1.6484,
+      "step": 670
+    },
+    {
+      "epoch": 0.8430187509685417,
+      "grad_norm": 0.36396560072898865,
+      "learning_rate": 0.00014450435503940274,
+      "loss": 1.7457,
+      "step": 680
+    },
+    {
+      "epoch": 0.8554160855416085,
+      "grad_norm": 0.4536712169647217,
+      "learning_rate": 0.0001436748237245956,
+      "loss": 1.7763,
+      "step": 690
+    },
+    {
+      "epoch": 0.8678134201146753,
+      "grad_norm": 0.45438772439956665,
+      "learning_rate": 0.00014284529240978847,
+      "loss": 1.8736,
+      "step": 700
+    },
+    {
+      "epoch": 0.8802107546877421,
+      "grad_norm": 0.331462562084198,
+      "learning_rate": 0.00014201576109498134,
+      "loss": 1.9909,
+      "step": 710
+    },
+    {
+      "epoch": 0.8926080892608089,
+      "grad_norm": 0.29686763882637024,
+      "learning_rate": 0.00014118622978017423,
+      "loss": 1.9242,
+      "step": 720
+    },
+    {
+      "epoch": 0.9050054238338757,
+      "grad_norm": 0.4546560049057007,
+      "learning_rate": 0.00014035669846536707,
+      "loss": 1.8032,
+      "step": 730
+    },
+    {
+      "epoch": 0.9174027584069425,
+      "grad_norm": 0.3135245442390442,
+      "learning_rate": 0.00013952716715055993,
+      "loss": 1.835,
+      "step": 740
+    },
+    {
+      "epoch": 0.9298000929800093,
+      "grad_norm": 0.6448049545288086,
+      "learning_rate": 0.00013869763583575283,
+      "loss": 1.9127,
+      "step": 750
+    },
+    {
+      "epoch": 0.9421974275530761,
+      "grad_norm": 0.39725756645202637,
+      "learning_rate": 0.00013786810452094567,
+      "loss": 1.8041,
+      "step": 760
+    },
+    {
+      "epoch": 0.9545947621261429,
+      "grad_norm": 0.3762451708316803,
+      "learning_rate": 0.00013703857320613853,
+      "loss": 1.8003,
+      "step": 770
+    },
+    {
+      "epoch": 0.9669920966992097,
+      "grad_norm": 0.35813263058662415,
+      "learning_rate": 0.00013620904189133142,
+      "loss": 1.8474,
+      "step": 780
+    },
+    {
+      "epoch": 0.9793894312722765,
+      "grad_norm": 0.29999616742134094,
+      "learning_rate": 0.00013537951057652426,
+      "loss": 1.8705,
+      "step": 790
+    },
+    {
+      "epoch": 0.9917867658453432,
+      "grad_norm": 0.3202720880508423,
+      "learning_rate": 0.00013454997926171713,
+      "loss": 1.7752,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8193774223327637,
+      "eval_runtime": 78.8064,
+      "eval_samples_per_second": 9.098,
+      "eval_steps_per_second": 1.142,
+      "step": 807
+    },
+    {
+      "epoch": 1.00371920037192,
+      "grad_norm": 0.30241405963897705,
+      "learning_rate": 0.00013372044794691002,
+      "loss": 1.8318,
+      "step": 810
+    },
+    {
+      "epoch": 1.0161165349449868,
+      "grad_norm": 0.3700416386127472,
+      "learning_rate": 0.00013289091663210286,
+      "loss": 1.8938,
+      "step": 820
+    },
+    {
+      "epoch": 1.0285138695180536,
+      "grad_norm": 0.4154430329799652,
+      "learning_rate": 0.00013206138531729572,
+      "loss": 1.8733,
+      "step": 830
+    },
+    {
+      "epoch": 1.0409112040911204,
+      "grad_norm": 0.38313189148902893,
+      "learning_rate": 0.00013123185400248862,
+      "loss": 1.8571,
+      "step": 840
+    },
+    {
+      "epoch": 1.0533085386641872,
+      "grad_norm": 0.23230139911174774,
+      "learning_rate": 0.00013040232268768146,
+      "loss": 1.798,
+      "step": 850
+    },
+    {
+      "epoch": 1.065705873237254,
+      "grad_norm": 0.3701108992099762,
+      "learning_rate": 0.00012957279137287432,
+      "loss": 1.8533,
+      "step": 860
+    },
+    {
+      "epoch": 1.0781032078103208,
+      "grad_norm": 0.29064834117889404,
+      "learning_rate": 0.00012874326005806721,
+      "loss": 1.7453,
+      "step": 870
+    },
+    {
+      "epoch": 1.0905005423833876,
+      "grad_norm": 0.3150763213634491,
+      "learning_rate": 0.00012791372874326005,
+      "loss": 1.8977,
+      "step": 880
+    },
+    {
+      "epoch": 1.1028978769564544,
+      "grad_norm": 0.428843230009079,
+      "learning_rate": 0.00012708419742845292,
+      "loss": 1.8688,
+      "step": 890
+    },
+    {
+      "epoch": 1.1152952115295212,
+      "grad_norm": 0.2608051896095276,
+      "learning_rate": 0.0001262546661136458,
+      "loss": 1.7242,
+      "step": 900
+    },
+    {
+      "epoch": 1.127692546102588,
+      "grad_norm": 0.3821583688259125,
+      "learning_rate": 0.00012542513479883865,
+      "loss": 1.9037,
+      "step": 910
+    },
+    {
+      "epoch": 1.1400898806756548,
+      "grad_norm": 0.28013911843299866,
+      "learning_rate": 0.00012459560348403151,
+      "loss": 1.8215,
+      "step": 920
+    },
+    {
+      "epoch": 1.1524872152487216,
+      "grad_norm": 0.30506208539009094,
+      "learning_rate": 0.0001237660721692244,
+      "loss": 1.8197,
+      "step": 930
+    },
+    {
+      "epoch": 1.1648845498217884,
+      "grad_norm": 0.29327717423439026,
+      "learning_rate": 0.00012293654085441727,
+      "loss": 1.7784,
+      "step": 940
+    },
+    {
+      "epoch": 1.1772818843948551,
+      "grad_norm": 0.23550163209438324,
+      "learning_rate": 0.0001221070095396101,
+      "loss": 1.9318,
+      "step": 950
+    },
+    {
+      "epoch": 1.189679218967922,
+      "grad_norm": 0.21349768340587616,
+      "learning_rate": 0.000121277478224803,
+      "loss": 1.8084,
+      "step": 960
+    },
+    {
+      "epoch": 1.2020765535409887,
+      "grad_norm": 0.34790855646133423,
+      "learning_rate": 0.00012044794690999586,
+      "loss": 1.7587,
+      "step": 970
+    },
+    {
+      "epoch": 1.2144738881140555,
+      "grad_norm": 0.2519979774951935,
+      "learning_rate": 0.00011961841559518872,
+      "loss": 1.8055,
+      "step": 980
+    },
+    {
+      "epoch": 1.2268712226871223,
+      "grad_norm": 0.3781174123287201,
+      "learning_rate": 0.0001187888842803816,
+      "loss": 1.8436,
+      "step": 990
+    },
+    {
+      "epoch": 1.2392685572601891,
+      "grad_norm": 0.26533016562461853,
+      "learning_rate": 0.00011795935296557445,
+      "loss": 1.6512,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2516658918332557,
+      "grad_norm": 0.2862655818462372,
+      "learning_rate": 0.00011712982165076732,
+      "loss": 2.0418,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2640632264063227,
+      "grad_norm": 0.27094656229019165,
+      "learning_rate": 0.0001163002903359602,
+      "loss": 1.7278,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2764605609793893,
+      "grad_norm": 0.29184144735336304,
+      "learning_rate": 0.00011547075902115305,
+      "loss": 1.6938,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2888578955524563,
+      "grad_norm": 0.30606576800346375,
+      "learning_rate": 0.00011464122770634591,
+      "loss": 1.6627,
+      "step": 1040
+    },
+    {
+      "epoch": 1.301255230125523,
+      "grad_norm": 0.23827411234378815,
+      "learning_rate": 0.0001138116963915388,
+      "loss": 1.7671,
+      "step": 1050
+    },
+    {
+      "epoch": 1.31365256469859,
+      "grad_norm": 0.3038440942764282,
+      "learning_rate": 0.00011298216507673165,
+      "loss": 1.9029,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3260498992716565,
+      "grad_norm": 0.22325201332569122,
+      "learning_rate": 0.00011215263376192451,
+      "loss": 1.7413,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3384472338447233,
+      "grad_norm": 0.30867546796798706,
+      "learning_rate": 0.00011132310244711739,
+      "loss": 1.8252,
+      "step": 1080
+    },
+    {
+      "epoch": 1.35084456841779,
+      "grad_norm": 0.3236595392227173,
+      "learning_rate": 0.00011049357113231024,
+      "loss": 1.8856,
+      "step": 1090
+    },
+    {
+      "epoch": 1.363241902990857,
+      "grad_norm": 0.32089242339134216,
+      "learning_rate": 0.00010966403981750311,
+      "loss": 1.8437,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3756392375639237,
+      "grad_norm": 0.28864434361457825,
+      "learning_rate": 0.00010883450850269599,
+      "loss": 1.7875,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3880365721369905,
+      "grad_norm": 0.3817216455936432,
+      "learning_rate": 0.00010800497718788884,
+      "loss": 1.8455,
+      "step": 1120
+    },
+    {
+      "epoch": 1.4004339067100573,
+      "grad_norm": 0.22240202128887177,
+      "learning_rate": 0.0001071754458730817,
+      "loss": 1.7744,
+      "step": 1130
+    },
+    {
+      "epoch": 1.412831241283124,
+      "grad_norm": 0.28633448481559753,
+      "learning_rate": 0.00010634591455827458,
+      "loss": 1.765,
+      "step": 1140
+    },
+    {
+      "epoch": 1.425228575856191,
+      "grad_norm": 0.19945985078811646,
+      "learning_rate": 0.00010551638324346745,
+      "loss": 1.9739,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4376259104292577,
+      "grad_norm": 0.2815242111682892,
+      "learning_rate": 0.0001046868519286603,
+      "loss": 1.8369,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4500232450023245,
+      "grad_norm": 0.20174123346805573,
+      "learning_rate": 0.00010385732061385318,
+      "loss": 1.9351,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4624205795753913,
+      "grad_norm": 0.27899351716041565,
+      "learning_rate": 0.00010302778929904605,
+      "loss": 1.9544,
+      "step": 1180
+    },
+    {
+      "epoch": 1.474817914148458,
+      "grad_norm": 0.22028954327106476,
+      "learning_rate": 0.00010219825798423892,
+      "loss": 1.852,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4872152487215249,
+      "grad_norm": 0.2520454525947571,
+      "learning_rate": 0.00010136872666943178,
+      "loss": 1.6232,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4996125832945917,
+      "grad_norm": 0.34104567766189575,
+      "learning_rate": 0.00010053919535462464,
+      "loss": 1.9285,
+      "step": 1210
+    },
+    {
+      "epoch": 1.5120099178676585,
+      "grad_norm": 0.3216676414012909,
+      "learning_rate": 9.970966403981751e-05,
+      "loss": 1.6644,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5244072524407253,
+      "grad_norm": 0.22132286429405212,
+      "learning_rate": 9.888013272501037e-05,
+      "loss": 1.796,
+      "step": 1230
+    },
+    {
+      "epoch": 1.536804587013792,
+      "grad_norm": 0.35185569524765015,
+      "learning_rate": 9.805060141020324e-05,
+      "loss": 1.7821,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5492019215868589,
+      "grad_norm": 0.16420242190361023,
+      "learning_rate": 9.72210700953961e-05,
+      "loss": 1.8054,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5615992561599255,
+      "grad_norm": 0.32100507616996765,
+      "learning_rate": 9.639153878058897e-05,
+      "loss": 1.8707,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5739965907329925,
+      "grad_norm": 0.2014254331588745,
+      "learning_rate": 9.556200746578184e-05,
+      "loss": 1.8087,
+      "step": 1270
+    },
+    {
+      "epoch": 1.586393925306059,
+      "grad_norm": 0.23392640054225922,
+      "learning_rate": 9.47324761509747e-05,
+      "loss": 1.7327,
+      "step": 1280
+    },
+    {
+      "epoch": 1.598791259879126,
+      "grad_norm": 0.19987891614437103,
+      "learning_rate": 9.390294483616757e-05,
+      "loss": 1.8399,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6111885944521926,
+      "grad_norm": 0.13928192853927612,
+      "learning_rate": 9.307341352136043e-05,
+      "loss": 1.9271,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6235859290252597,
+      "grad_norm": 0.3423463702201843,
+      "learning_rate": 9.22438822065533e-05,
+      "loss": 1.81,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6359832635983262,
+      "grad_norm": 0.31117212772369385,
+      "learning_rate": 9.141435089174618e-05,
+      "loss": 1.8919,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6483805981713933,
+      "grad_norm": 0.1769014447927475,
+      "learning_rate": 9.058481957693903e-05,
+      "loss": 1.692,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6607779327444598,
+      "grad_norm": 0.1725306212902069,
+      "learning_rate": 8.97552882621319e-05,
+      "loss": 1.7833,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6731752673175269,
+      "grad_norm": 0.15333665907382965,
+      "learning_rate": 8.892575694732477e-05,
+      "loss": 1.7129,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6855726018905934,
+      "grad_norm": 0.225737065076828,
+      "learning_rate": 8.809622563251764e-05,
+      "loss": 2.0034,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6979699364636605,
+      "grad_norm": 0.27135154604911804,
+      "learning_rate": 8.726669431771049e-05,
+      "loss": 1.7641,
+      "step": 1370
+    },
+    {
+      "epoch": 1.710367271036727,
+      "grad_norm": 0.19318152964115143,
+      "learning_rate": 8.643716300290337e-05,
+      "loss": 1.9714,
+      "step": 1380
+    },
+    {
+      "epoch": 1.722764605609794,
+      "grad_norm": 0.09128980338573456,
+      "learning_rate": 8.560763168809624e-05,
+      "loss": 1.6477,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7351619401828606,
+      "grad_norm": 0.20176462829113007,
+      "learning_rate": 8.477810037328909e-05,
+      "loss": 1.8707,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7475592747559274,
+      "grad_norm": 0.1746564656496048,
+      "learning_rate": 8.394856905848197e-05,
+      "loss": 1.8979,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7599566093289942,
+      "grad_norm": 0.8505027294158936,
+      "learning_rate": 8.311903774367483e-05,
+      "loss": 1.71,
+      "step": 1420
+    },
+    {
+      "epoch": 1.772353943902061,
+      "grad_norm": 0.18071773648262024,
+      "learning_rate": 8.22895064288677e-05,
+      "loss": 1.9505,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7847512784751278,
+      "grad_norm": 0.29732322692871094,
+      "learning_rate": 8.145997511406056e-05,
+      "loss": 1.8041,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7971486130481946,
+      "grad_norm": 0.21795178949832916,
+      "learning_rate": 8.063044379925343e-05,
+      "loss": 1.7381,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8095459476212614,
+      "grad_norm": 0.23459061980247498,
+      "learning_rate": 7.98009124844463e-05,
+      "loss": 1.6636,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8219432821943282,
+      "grad_norm": 0.20895689725875854,
+      "learning_rate": 7.897138116963916e-05,
+      "loss": 1.8257,
+      "step": 1470
+    },
+    {
+      "epoch": 1.834340616767395,
+      "grad_norm": 0.18129809200763702,
+      "learning_rate": 7.814184985483203e-05,
+      "loss": 1.9791,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8467379513404618,
+      "grad_norm": 0.1758158951997757,
+      "learning_rate": 7.731231854002489e-05,
+      "loss": 1.7657,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8591352859135286,
+      "grad_norm": 0.14756101369857788,
+      "learning_rate": 7.648278722521776e-05,
+      "loss": 1.7483,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8715326204865954,
+      "grad_norm": 0.14168867468833923,
+      "learning_rate": 7.565325591041062e-05,
+      "loss": 1.8844,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8839299550596622,
+      "grad_norm": 0.1295221447944641,
+      "learning_rate": 7.482372459560349e-05,
+      "loss": 1.8121,
+      "step": 1520
+    },
+    {
+      "epoch": 1.896327289632729,
+      "grad_norm": 0.19356060028076172,
+      "learning_rate": 7.399419328079635e-05,
+      "loss": 1.5851,
+      "step": 1530
+    },
+    {
+      "epoch": 1.9087246242057958,
+      "grad_norm": 0.20035363733768463,
+      "learning_rate": 7.316466196598922e-05,
+      "loss": 1.7063,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9211219587788624,
+      "grad_norm": 0.12139635533094406,
+      "learning_rate": 7.233513065118208e-05,
+      "loss": 1.7962,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9335192933519294,
+      "grad_norm": 0.10587511211633682,
+      "learning_rate": 7.150559933637495e-05,
+      "loss": 1.7143,
+      "step": 1560
+    },
+    {
+      "epoch": 1.945916627924996,
+      "grad_norm": 0.18997065722942352,
+      "learning_rate": 7.067606802156782e-05,
+      "loss": 1.7636,
+      "step": 1570
+    },
+    {
+      "epoch": 1.958313962498063,
+      "grad_norm": 0.15760765969753265,
+      "learning_rate": 6.984653670676068e-05,
+      "loss": 1.7672,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9707112970711296,
+      "grad_norm": 0.1490117609500885,
+      "learning_rate": 6.901700539195355e-05,
+      "loss": 1.6405,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9831086316441966,
+      "grad_norm": 0.09482846409082413,
+      "learning_rate": 6.818747407714641e-05,
+      "loss": 1.8141,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9955059662172632,
+      "grad_norm": 0.182535782456398,
+      "learning_rate": 6.735794276233928e-05,
+      "loss": 1.7745,
+      "step": 1610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8065738677978516,
+      "eval_runtime": 78.829,
+      "eval_samples_per_second": 9.096,
+      "eval_steps_per_second": 1.142,
+      "step": 1614
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2421,
+  "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": 5.6462587058139955e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-1614/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ed81f35b71a674f101f42b5d39caf5a7c94955958bbf088fb20abcabaa812f
+size 5905

checkpoint-2421/README.md

@@ -0,0 +1,207 @@
+---
+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
+- transformers
+---
+
+# 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 0.17.1

checkpoint-2421/adapter_config.json

@@ -0,0 +1,37 @@
+{
+  "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",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2421/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e3b8172a56ce4c92a61a6ee49e572c2e100bb1bced833c487cdc427d8cce20
+size 27280152

checkpoint-2421/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0f2a03fdaec93cd8b1bbbb4ae4ae2138788f5a4dfcc94be4cd3edf2df96724
+size 54636235

checkpoint-2421/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b821cc82cb3337448207066c689df8aec7433b98d3f9262e3045f36daf7c17f
+size 14645

checkpoint-2421/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6b2ab93d9c86cf9164261edee3306a3c8daeb04d79e7e4c3654c207511443a7
+size 1383

checkpoint-2421/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cfafc6475c9407a62a66770a84fe63099f25c87eacd07edc3d21fce1ea0b35a
+size 1465

checkpoint-2421/trainer_state.json

@@ -0,0 +1,1752 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2421,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.012397334573066791,
+      "grad_norm": 0.6915941834449768,
+      "learning_rate": 0.00018,
+      "loss": 2.3006,
+      "step": 10
+    },
+    {
+      "epoch": 0.024794669146133583,
+      "grad_norm": 0.6273291707038879,
+      "learning_rate": 0.0001992534218166736,
+      "loss": 2.1317,
+      "step": 20
+    },
+    {
+      "epoch": 0.037192003719200374,
+      "grad_norm": 0.45228877663612366,
+      "learning_rate": 0.00019842389050186645,
+      "loss": 1.9808,
+      "step": 30
+    },
+    {
+      "epoch": 0.049589338292267165,
+      "grad_norm": 0.3886250853538513,
+      "learning_rate": 0.00019759435918705932,
+      "loss": 1.8968,
+      "step": 40
+    },
+    {
+      "epoch": 0.06198667286533395,
+      "grad_norm": 0.3263673484325409,
+      "learning_rate": 0.00019676482787225219,
+      "loss": 1.9159,
+      "step": 50
+    },
+    {
+      "epoch": 0.07438400743840075,
+      "grad_norm": 0.3357856273651123,
+      "learning_rate": 0.00019593529655744505,
+      "loss": 1.9052,
+      "step": 60
+    },
+    {
+      "epoch": 0.08678134201146753,
+      "grad_norm": 0.3885687291622162,
+      "learning_rate": 0.00019510576524263792,
+      "loss": 1.8788,
+      "step": 70
+    },
+    {
+      "epoch": 0.09917867658453433,
+      "grad_norm": 0.33165615797042847,
+      "learning_rate": 0.00019427623392783078,
+      "loss": 1.876,
+      "step": 80
+    },
+    {
+      "epoch": 0.11157601115760112,
+      "grad_norm": 0.3510221242904663,
+      "learning_rate": 0.00019344670261302365,
+      "loss": 1.7992,
+      "step": 90
+    },
+    {
+      "epoch": 0.1239733457306679,
+      "grad_norm": 0.35817059874534607,
+      "learning_rate": 0.0001926171712982165,
+      "loss": 1.7386,
+      "step": 100
+    },
+    {
+      "epoch": 0.1363706803037347,
+      "grad_norm": 0.3222461938858032,
+      "learning_rate": 0.00019178763998340938,
+      "loss": 1.8766,
+      "step": 110
+    },
+    {
+      "epoch": 0.1487680148768015,
+      "grad_norm": 0.302379310131073,
+      "learning_rate": 0.00019095810866860224,
+      "loss": 1.833,
+      "step": 120
+    },
+    {
+      "epoch": 0.16116534944986827,
+      "grad_norm": 0.3621092736721039,
+      "learning_rate": 0.00019012857735379514,
+      "loss": 1.7433,
+      "step": 130
+    },
+    {
+      "epoch": 0.17356268402293507,
+      "grad_norm": 0.35103851556777954,
+      "learning_rate": 0.00018929904603898798,
+      "loss": 1.8552,
+      "step": 140
+    },
+    {
+      "epoch": 0.18596001859600186,
+      "grad_norm": 0.3761669993400574,
+      "learning_rate": 0.00018846951472418084,
+      "loss": 1.8072,
+      "step": 150
+    },
+    {
+      "epoch": 0.19835735316906866,
+      "grad_norm": 0.2791743576526642,
+      "learning_rate": 0.00018763998340937373,
+      "loss": 1.882,
+      "step": 160
+    },
+    {
+      "epoch": 0.21075468774213543,
+      "grad_norm": 0.28887104988098145,
+      "learning_rate": 0.00018681045209456657,
+      "loss": 1.945,
+      "step": 170
+    },
+    {
+      "epoch": 0.22315202231520223,
+      "grad_norm": 0.3621903955936432,
+      "learning_rate": 0.00018598092077975944,
+      "loss": 1.7506,
+      "step": 180
+    },
+    {
+      "epoch": 0.23554935688826903,
+      "grad_norm": 0.36899787187576294,
+      "learning_rate": 0.00018515138946495233,
+      "loss": 1.8959,
+      "step": 190
+    },
+    {
+      "epoch": 0.2479466914613358,
+      "grad_norm": 0.3354776203632355,
+      "learning_rate": 0.00018432185815014517,
+      "loss": 1.9282,
+      "step": 200
+    },
+    {
+      "epoch": 0.2603440260344026,
+      "grad_norm": 0.3030059337615967,
+      "learning_rate": 0.00018349232683533803,
+      "loss": 1.9876,
+      "step": 210
+    },
+    {
+      "epoch": 0.2727413606074694,
+      "grad_norm": 0.380134254693985,
+      "learning_rate": 0.00018266279552053093,
+      "loss": 1.795,
+      "step": 220
+    },
+    {
+      "epoch": 0.2851386951805362,
+      "grad_norm": 0.3484257161617279,
+      "learning_rate": 0.00018183326420572376,
+      "loss": 1.9131,
+      "step": 230
+    },
+    {
+      "epoch": 0.297536029753603,
+      "grad_norm": 0.3204387426376343,
+      "learning_rate": 0.00018100373289091663,
+      "loss": 1.9829,
+      "step": 240
+    },
+    {
+      "epoch": 0.3099333643266698,
+      "grad_norm": 0.3759450912475586,
+      "learning_rate": 0.00018017420157610952,
+      "loss": 1.9002,
+      "step": 250
+    },
+    {
+      "epoch": 0.32233069889973653,
+      "grad_norm": 0.3721698820590973,
+      "learning_rate": 0.00017934467026130236,
+      "loss": 1.8657,
+      "step": 260
+    },
+    {
+      "epoch": 0.33472803347280333,
+      "grad_norm": 0.35085615515708923,
+      "learning_rate": 0.00017851513894649523,
+      "loss": 1.8623,
+      "step": 270
+    },
+    {
+      "epoch": 0.34712536804587013,
+      "grad_norm": 0.35750696063041687,
+      "learning_rate": 0.00017768560763168812,
+      "loss": 1.8743,
+      "step": 280
+    },
+    {
+      "epoch": 0.35952270261893693,
+      "grad_norm": 0.3072109520435333,
+      "learning_rate": 0.00017685607631688096,
+      "loss": 1.9626,
+      "step": 290
+    },
+    {
+      "epoch": 0.3719200371920037,
+      "grad_norm": 0.40647512674331665,
+      "learning_rate": 0.00017602654500207382,
+      "loss": 1.8034,
+      "step": 300
+    },
+    {
+      "epoch": 0.3843173717650705,
+      "grad_norm": 0.3000311851501465,
+      "learning_rate": 0.00017519701368726672,
+      "loss": 1.8995,
+      "step": 310
+    },
+    {
+      "epoch": 0.3967147063381373,
+      "grad_norm": 0.36904624104499817,
+      "learning_rate": 0.00017436748237245955,
+      "loss": 1.82,
+      "step": 320
+    },
+    {
+      "epoch": 0.40911204091120407,
+      "grad_norm": 0.337799072265625,
+      "learning_rate": 0.00017353795105765242,
+      "loss": 1.8706,
+      "step": 330
+    },
+    {
+      "epoch": 0.42150937548427087,
+      "grad_norm": 0.4223800003528595,
+      "learning_rate": 0.0001727084197428453,
+      "loss": 1.8584,
+      "step": 340
+    },
+    {
+      "epoch": 0.43390671005733766,
+      "grad_norm": 0.34497585892677307,
+      "learning_rate": 0.00017187888842803818,
+      "loss": 1.8417,
+      "step": 350
+    },
+    {
+      "epoch": 0.44630404463040446,
+      "grad_norm": 0.34032031893730164,
+      "learning_rate": 0.00017104935711323102,
+      "loss": 1.7917,
+      "step": 360
+    },
+    {
+      "epoch": 0.45870137920347126,
+      "grad_norm": 0.4158859848976135,
+      "learning_rate": 0.0001702198257984239,
+      "loss": 1.8749,
+      "step": 370
+    },
+    {
+      "epoch": 0.47109871377653806,
+      "grad_norm": 0.36545196175575256,
+      "learning_rate": 0.00016939029448361678,
+      "loss": 1.8337,
+      "step": 380
+    },
+    {
+      "epoch": 0.48349604834960486,
+      "grad_norm": 0.32123473286628723,
+      "learning_rate": 0.00016856076316880961,
+      "loss": 1.9321,
+      "step": 390
+    },
+    {
+      "epoch": 0.4958933829226716,
+      "grad_norm": 0.45476439595222473,
+      "learning_rate": 0.0001677312318540025,
+      "loss": 1.8185,
+      "step": 400
+    },
+    {
+      "epoch": 0.5082907174957384,
+      "grad_norm": 0.3410905599594116,
+      "learning_rate": 0.00016690170053919537,
+      "loss": 1.9082,
+      "step": 410
+    },
+    {
+      "epoch": 0.5206880520688052,
+      "grad_norm": 0.3436656892299652,
+      "learning_rate": 0.0001660721692243882,
+      "loss": 1.7821,
+      "step": 420
+    },
+    {
+      "epoch": 0.533085386641872,
+      "grad_norm": 0.34343594312667847,
+      "learning_rate": 0.0001652426379095811,
+      "loss": 1.8184,
+      "step": 430
+    },
+    {
+      "epoch": 0.5454827212149388,
+      "grad_norm": 0.4309318959712982,
+      "learning_rate": 0.00016441310659477397,
+      "loss": 1.9124,
+      "step": 440
+    },
+    {
+      "epoch": 0.5578800557880056,
+      "grad_norm": 0.4032953679561615,
+      "learning_rate": 0.0001635835752799668,
+      "loss": 1.7962,
+      "step": 450
+    },
+    {
+      "epoch": 0.5702773903610724,
+      "grad_norm": 0.3726664185523987,
+      "learning_rate": 0.0001627540439651597,
+      "loss": 1.8158,
+      "step": 460
+    },
+    {
+      "epoch": 0.5826747249341392,
+      "grad_norm": 0.36948224902153015,
+      "learning_rate": 0.00016192451265035257,
+      "loss": 1.7539,
+      "step": 470
+    },
+    {
+      "epoch": 0.595072059507206,
+      "grad_norm": 0.33594000339508057,
+      "learning_rate": 0.0001610949813355454,
+      "loss": 1.9287,
+      "step": 480
+    },
+    {
+      "epoch": 0.6074693940802728,
+      "grad_norm": 0.3209264576435089,
+      "learning_rate": 0.0001602654500207383,
+      "loss": 1.8375,
+      "step": 490
+    },
+    {
+      "epoch": 0.6198667286533396,
+      "grad_norm": 0.38256484270095825,
+      "learning_rate": 0.00015943591870593116,
+      "loss": 1.817,
+      "step": 500
+    },
+    {
+      "epoch": 0.6322640632264063,
+      "grad_norm": 0.38966864347457886,
+      "learning_rate": 0.000158606387391124,
+      "loss": 1.7397,
+      "step": 510
+    },
+    {
+      "epoch": 0.6446613977994731,
+      "grad_norm": 0.45601052045822144,
+      "learning_rate": 0.0001577768560763169,
+      "loss": 1.7448,
+      "step": 520
+    },
+    {
+      "epoch": 0.6570587323725399,
+      "grad_norm": 0.39306697249412537,
+      "learning_rate": 0.00015694732476150976,
+      "loss": 1.8505,
+      "step": 530
+    },
+    {
+      "epoch": 0.6694560669456067,
+      "grad_norm": 0.4036141633987427,
+      "learning_rate": 0.00015611779344670262,
+      "loss": 1.9946,
+      "step": 540
+    },
+    {
+      "epoch": 0.6818534015186735,
+      "grad_norm": 0.34463125467300415,
+      "learning_rate": 0.0001552882621318955,
+      "loss": 2.0461,
+      "step": 550
+    },
+    {
+      "epoch": 0.6942507360917403,
+      "grad_norm": 0.3309987485408783,
+      "learning_rate": 0.00015445873081708835,
+      "loss": 1.8714,
+      "step": 560
+    },
+    {
+      "epoch": 0.7066480706648071,
+      "grad_norm": 0.40711745619773865,
+      "learning_rate": 0.00015362919950228122,
+      "loss": 1.9515,
+      "step": 570
+    },
+    {
+      "epoch": 0.7190454052378739,
+      "grad_norm": 0.4855351150035858,
+      "learning_rate": 0.00015279966818747409,
+      "loss": 1.928,
+      "step": 580
+    },
+    {
+      "epoch": 0.7314427398109407,
+      "grad_norm": 0.3159841299057007,
+      "learning_rate": 0.00015197013687266695,
+      "loss": 1.8648,
+      "step": 590
+    },
+    {
+      "epoch": 0.7438400743840075,
+      "grad_norm": 0.34454017877578735,
+      "learning_rate": 0.00015114060555785982,
+      "loss": 1.7614,
+      "step": 600
+    },
+    {
+      "epoch": 0.7562374089570743,
+      "grad_norm": 0.42112237215042114,
+      "learning_rate": 0.00015031107424305268,
+      "loss": 1.7943,
+      "step": 610
+    },
+    {
+      "epoch": 0.768634743530141,
+      "grad_norm": 0.4868924617767334,
+      "learning_rate": 0.00014948154292824555,
+      "loss": 1.8236,
+      "step": 620
+    },
+    {
+      "epoch": 0.7810320781032078,
+      "grad_norm": 0.27235159277915955,
+      "learning_rate": 0.00014865201161343841,
+      "loss": 1.8792,
+      "step": 630
+    },
+    {
+      "epoch": 0.7934294126762746,
+      "grad_norm": 0.36492735147476196,
+      "learning_rate": 0.00014782248029863128,
+      "loss": 1.8139,
+      "step": 640
+    },
+    {
+      "epoch": 0.8058267472493414,
+      "grad_norm": 0.3278910517692566,
+      "learning_rate": 0.00014699294898382414,
+      "loss": 1.9303,
+      "step": 650
+    },
+    {
+      "epoch": 0.8182240818224081,
+      "grad_norm": 0.4410141110420227,
+      "learning_rate": 0.000146163417669017,
+      "loss": 1.7458,
+      "step": 660
+    },
+    {
+      "epoch": 0.8306214163954749,
+      "grad_norm": 0.44660821557044983,
+      "learning_rate": 0.00014533388635420988,
+      "loss": 1.6484,
+      "step": 670
+    },
+    {
+      "epoch": 0.8430187509685417,
+      "grad_norm": 0.36396560072898865,
+      "learning_rate": 0.00014450435503940274,
+      "loss": 1.7457,
+      "step": 680
+    },
+    {
+      "epoch": 0.8554160855416085,
+      "grad_norm": 0.4536712169647217,
+      "learning_rate": 0.0001436748237245956,
+      "loss": 1.7763,
+      "step": 690
+    },
+    {
+      "epoch": 0.8678134201146753,
+      "grad_norm": 0.45438772439956665,
+      "learning_rate": 0.00014284529240978847,
+      "loss": 1.8736,
+      "step": 700
+    },
+    {
+      "epoch": 0.8802107546877421,
+      "grad_norm": 0.331462562084198,
+      "learning_rate": 0.00014201576109498134,
+      "loss": 1.9909,
+      "step": 710
+    },
+    {
+      "epoch": 0.8926080892608089,
+      "grad_norm": 0.29686763882637024,
+      "learning_rate": 0.00014118622978017423,
+      "loss": 1.9242,
+      "step": 720
+    },
+    {
+      "epoch": 0.9050054238338757,
+      "grad_norm": 0.4546560049057007,
+      "learning_rate": 0.00014035669846536707,
+      "loss": 1.8032,
+      "step": 730
+    },
+    {
+      "epoch": 0.9174027584069425,
+      "grad_norm": 0.3135245442390442,
+      "learning_rate": 0.00013952716715055993,
+      "loss": 1.835,
+      "step": 740
+    },
+    {
+      "epoch": 0.9298000929800093,
+      "grad_norm": 0.6448049545288086,
+      "learning_rate": 0.00013869763583575283,
+      "loss": 1.9127,
+      "step": 750
+    },
+    {
+      "epoch": 0.9421974275530761,
+      "grad_norm": 0.39725756645202637,
+      "learning_rate": 0.00013786810452094567,
+      "loss": 1.8041,
+      "step": 760
+    },
+    {
+      "epoch": 0.9545947621261429,
+      "grad_norm": 0.3762451708316803,
+      "learning_rate": 0.00013703857320613853,
+      "loss": 1.8003,
+      "step": 770
+    },
+    {
+      "epoch": 0.9669920966992097,
+      "grad_norm": 0.35813263058662415,
+      "learning_rate": 0.00013620904189133142,
+      "loss": 1.8474,
+      "step": 780
+    },
+    {
+      "epoch": 0.9793894312722765,
+      "grad_norm": 0.29999616742134094,
+      "learning_rate": 0.00013537951057652426,
+      "loss": 1.8705,
+      "step": 790
+    },
+    {
+      "epoch": 0.9917867658453432,
+      "grad_norm": 0.3202720880508423,
+      "learning_rate": 0.00013454997926171713,
+      "loss": 1.7752,
+      "step": 800
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.8193774223327637,
+      "eval_runtime": 78.8064,
+      "eval_samples_per_second": 9.098,
+      "eval_steps_per_second": 1.142,
+      "step": 807
+    },
+    {
+      "epoch": 1.00371920037192,
+      "grad_norm": 0.30241405963897705,
+      "learning_rate": 0.00013372044794691002,
+      "loss": 1.8318,
+      "step": 810
+    },
+    {
+      "epoch": 1.0161165349449868,
+      "grad_norm": 0.3700416386127472,
+      "learning_rate": 0.00013289091663210286,
+      "loss": 1.8938,
+      "step": 820
+    },
+    {
+      "epoch": 1.0285138695180536,
+      "grad_norm": 0.4154430329799652,
+      "learning_rate": 0.00013206138531729572,
+      "loss": 1.8733,
+      "step": 830
+    },
+    {
+      "epoch": 1.0409112040911204,
+      "grad_norm": 0.38313189148902893,
+      "learning_rate": 0.00013123185400248862,
+      "loss": 1.8571,
+      "step": 840
+    },
+    {
+      "epoch": 1.0533085386641872,
+      "grad_norm": 0.23230139911174774,
+      "learning_rate": 0.00013040232268768146,
+      "loss": 1.798,
+      "step": 850
+    },
+    {
+      "epoch": 1.065705873237254,
+      "grad_norm": 0.3701108992099762,
+      "learning_rate": 0.00012957279137287432,
+      "loss": 1.8533,
+      "step": 860
+    },
+    {
+      "epoch": 1.0781032078103208,
+      "grad_norm": 0.29064834117889404,
+      "learning_rate": 0.00012874326005806721,
+      "loss": 1.7453,
+      "step": 870
+    },
+    {
+      "epoch": 1.0905005423833876,
+      "grad_norm": 0.3150763213634491,
+      "learning_rate": 0.00012791372874326005,
+      "loss": 1.8977,
+      "step": 880
+    },
+    {
+      "epoch": 1.1028978769564544,
+      "grad_norm": 0.428843230009079,
+      "learning_rate": 0.00012708419742845292,
+      "loss": 1.8688,
+      "step": 890
+    },
+    {
+      "epoch": 1.1152952115295212,
+      "grad_norm": 0.2608051896095276,
+      "learning_rate": 0.0001262546661136458,
+      "loss": 1.7242,
+      "step": 900
+    },
+    {
+      "epoch": 1.127692546102588,
+      "grad_norm": 0.3821583688259125,
+      "learning_rate": 0.00012542513479883865,
+      "loss": 1.9037,
+      "step": 910
+    },
+    {
+      "epoch": 1.1400898806756548,
+      "grad_norm": 0.28013911843299866,
+      "learning_rate": 0.00012459560348403151,
+      "loss": 1.8215,
+      "step": 920
+    },
+    {
+      "epoch": 1.1524872152487216,
+      "grad_norm": 0.30506208539009094,
+      "learning_rate": 0.0001237660721692244,
+      "loss": 1.8197,
+      "step": 930
+    },
+    {
+      "epoch": 1.1648845498217884,
+      "grad_norm": 0.29327717423439026,
+      "learning_rate": 0.00012293654085441727,
+      "loss": 1.7784,
+      "step": 940
+    },
+    {
+      "epoch": 1.1772818843948551,
+      "grad_norm": 0.23550163209438324,
+      "learning_rate": 0.0001221070095396101,
+      "loss": 1.9318,
+      "step": 950
+    },
+    {
+      "epoch": 1.189679218967922,
+      "grad_norm": 0.21349768340587616,
+      "learning_rate": 0.000121277478224803,
+      "loss": 1.8084,
+      "step": 960
+    },
+    {
+      "epoch": 1.2020765535409887,
+      "grad_norm": 0.34790855646133423,
+      "learning_rate": 0.00012044794690999586,
+      "loss": 1.7587,
+      "step": 970
+    },
+    {
+      "epoch": 1.2144738881140555,
+      "grad_norm": 0.2519979774951935,
+      "learning_rate": 0.00011961841559518872,
+      "loss": 1.8055,
+      "step": 980
+    },
+    {
+      "epoch": 1.2268712226871223,
+      "grad_norm": 0.3781174123287201,
+      "learning_rate": 0.0001187888842803816,
+      "loss": 1.8436,
+      "step": 990
+    },
+    {
+      "epoch": 1.2392685572601891,
+      "grad_norm": 0.26533016562461853,
+      "learning_rate": 0.00011795935296557445,
+      "loss": 1.6512,
+      "step": 1000
+    },
+    {
+      "epoch": 1.2516658918332557,
+      "grad_norm": 0.2862655818462372,
+      "learning_rate": 0.00011712982165076732,
+      "loss": 2.0418,
+      "step": 1010
+    },
+    {
+      "epoch": 1.2640632264063227,
+      "grad_norm": 0.27094656229019165,
+      "learning_rate": 0.0001163002903359602,
+      "loss": 1.7278,
+      "step": 1020
+    },
+    {
+      "epoch": 1.2764605609793893,
+      "grad_norm": 0.29184144735336304,
+      "learning_rate": 0.00011547075902115305,
+      "loss": 1.6938,
+      "step": 1030
+    },
+    {
+      "epoch": 1.2888578955524563,
+      "grad_norm": 0.30606576800346375,
+      "learning_rate": 0.00011464122770634591,
+      "loss": 1.6627,
+      "step": 1040
+    },
+    {
+      "epoch": 1.301255230125523,
+      "grad_norm": 0.23827411234378815,
+      "learning_rate": 0.0001138116963915388,
+      "loss": 1.7671,
+      "step": 1050
+    },
+    {
+      "epoch": 1.31365256469859,
+      "grad_norm": 0.3038440942764282,
+      "learning_rate": 0.00011298216507673165,
+      "loss": 1.9029,
+      "step": 1060
+    },
+    {
+      "epoch": 1.3260498992716565,
+      "grad_norm": 0.22325201332569122,
+      "learning_rate": 0.00011215263376192451,
+      "loss": 1.7413,
+      "step": 1070
+    },
+    {
+      "epoch": 1.3384472338447233,
+      "grad_norm": 0.30867546796798706,
+      "learning_rate": 0.00011132310244711739,
+      "loss": 1.8252,
+      "step": 1080
+    },
+    {
+      "epoch": 1.35084456841779,
+      "grad_norm": 0.3236595392227173,
+      "learning_rate": 0.00011049357113231024,
+      "loss": 1.8856,
+      "step": 1090
+    },
+    {
+      "epoch": 1.363241902990857,
+      "grad_norm": 0.32089242339134216,
+      "learning_rate": 0.00010966403981750311,
+      "loss": 1.8437,
+      "step": 1100
+    },
+    {
+      "epoch": 1.3756392375639237,
+      "grad_norm": 0.28864434361457825,
+      "learning_rate": 0.00010883450850269599,
+      "loss": 1.7875,
+      "step": 1110
+    },
+    {
+      "epoch": 1.3880365721369905,
+      "grad_norm": 0.3817216455936432,
+      "learning_rate": 0.00010800497718788884,
+      "loss": 1.8455,
+      "step": 1120
+    },
+    {
+      "epoch": 1.4004339067100573,
+      "grad_norm": 0.22240202128887177,
+      "learning_rate": 0.0001071754458730817,
+      "loss": 1.7744,
+      "step": 1130
+    },
+    {
+      "epoch": 1.412831241283124,
+      "grad_norm": 0.28633448481559753,
+      "learning_rate": 0.00010634591455827458,
+      "loss": 1.765,
+      "step": 1140
+    },
+    {
+      "epoch": 1.425228575856191,
+      "grad_norm": 0.19945985078811646,
+      "learning_rate": 0.00010551638324346745,
+      "loss": 1.9739,
+      "step": 1150
+    },
+    {
+      "epoch": 1.4376259104292577,
+      "grad_norm": 0.2815242111682892,
+      "learning_rate": 0.0001046868519286603,
+      "loss": 1.8369,
+      "step": 1160
+    },
+    {
+      "epoch": 1.4500232450023245,
+      "grad_norm": 0.20174123346805573,
+      "learning_rate": 0.00010385732061385318,
+      "loss": 1.9351,
+      "step": 1170
+    },
+    {
+      "epoch": 1.4624205795753913,
+      "grad_norm": 0.27899351716041565,
+      "learning_rate": 0.00010302778929904605,
+      "loss": 1.9544,
+      "step": 1180
+    },
+    {
+      "epoch": 1.474817914148458,
+      "grad_norm": 0.22028954327106476,
+      "learning_rate": 0.00010219825798423892,
+      "loss": 1.852,
+      "step": 1190
+    },
+    {
+      "epoch": 1.4872152487215249,
+      "grad_norm": 0.2520454525947571,
+      "learning_rate": 0.00010136872666943178,
+      "loss": 1.6232,
+      "step": 1200
+    },
+    {
+      "epoch": 1.4996125832945917,
+      "grad_norm": 0.34104567766189575,
+      "learning_rate": 0.00010053919535462464,
+      "loss": 1.9285,
+      "step": 1210
+    },
+    {
+      "epoch": 1.5120099178676585,
+      "grad_norm": 0.3216676414012909,
+      "learning_rate": 9.970966403981751e-05,
+      "loss": 1.6644,
+      "step": 1220
+    },
+    {
+      "epoch": 1.5244072524407253,
+      "grad_norm": 0.22132286429405212,
+      "learning_rate": 9.888013272501037e-05,
+      "loss": 1.796,
+      "step": 1230
+    },
+    {
+      "epoch": 1.536804587013792,
+      "grad_norm": 0.35185569524765015,
+      "learning_rate": 9.805060141020324e-05,
+      "loss": 1.7821,
+      "step": 1240
+    },
+    {
+      "epoch": 1.5492019215868589,
+      "grad_norm": 0.16420242190361023,
+      "learning_rate": 9.72210700953961e-05,
+      "loss": 1.8054,
+      "step": 1250
+    },
+    {
+      "epoch": 1.5615992561599255,
+      "grad_norm": 0.32100507616996765,
+      "learning_rate": 9.639153878058897e-05,
+      "loss": 1.8707,
+      "step": 1260
+    },
+    {
+      "epoch": 1.5739965907329925,
+      "grad_norm": 0.2014254331588745,
+      "learning_rate": 9.556200746578184e-05,
+      "loss": 1.8087,
+      "step": 1270
+    },
+    {
+      "epoch": 1.586393925306059,
+      "grad_norm": 0.23392640054225922,
+      "learning_rate": 9.47324761509747e-05,
+      "loss": 1.7327,
+      "step": 1280
+    },
+    {
+      "epoch": 1.598791259879126,
+      "grad_norm": 0.19987891614437103,
+      "learning_rate": 9.390294483616757e-05,
+      "loss": 1.8399,
+      "step": 1290
+    },
+    {
+      "epoch": 1.6111885944521926,
+      "grad_norm": 0.13928192853927612,
+      "learning_rate": 9.307341352136043e-05,
+      "loss": 1.9271,
+      "step": 1300
+    },
+    {
+      "epoch": 1.6235859290252597,
+      "grad_norm": 0.3423463702201843,
+      "learning_rate": 9.22438822065533e-05,
+      "loss": 1.81,
+      "step": 1310
+    },
+    {
+      "epoch": 1.6359832635983262,
+      "grad_norm": 0.31117212772369385,
+      "learning_rate": 9.141435089174618e-05,
+      "loss": 1.8919,
+      "step": 1320
+    },
+    {
+      "epoch": 1.6483805981713933,
+      "grad_norm": 0.1769014447927475,
+      "learning_rate": 9.058481957693903e-05,
+      "loss": 1.692,
+      "step": 1330
+    },
+    {
+      "epoch": 1.6607779327444598,
+      "grad_norm": 0.1725306212902069,
+      "learning_rate": 8.97552882621319e-05,
+      "loss": 1.7833,
+      "step": 1340
+    },
+    {
+      "epoch": 1.6731752673175269,
+      "grad_norm": 0.15333665907382965,
+      "learning_rate": 8.892575694732477e-05,
+      "loss": 1.7129,
+      "step": 1350
+    },
+    {
+      "epoch": 1.6855726018905934,
+      "grad_norm": 0.225737065076828,
+      "learning_rate": 8.809622563251764e-05,
+      "loss": 2.0034,
+      "step": 1360
+    },
+    {
+      "epoch": 1.6979699364636605,
+      "grad_norm": 0.27135154604911804,
+      "learning_rate": 8.726669431771049e-05,
+      "loss": 1.7641,
+      "step": 1370
+    },
+    {
+      "epoch": 1.710367271036727,
+      "grad_norm": 0.19318152964115143,
+      "learning_rate": 8.643716300290337e-05,
+      "loss": 1.9714,
+      "step": 1380
+    },
+    {
+      "epoch": 1.722764605609794,
+      "grad_norm": 0.09128980338573456,
+      "learning_rate": 8.560763168809624e-05,
+      "loss": 1.6477,
+      "step": 1390
+    },
+    {
+      "epoch": 1.7351619401828606,
+      "grad_norm": 0.20176462829113007,
+      "learning_rate": 8.477810037328909e-05,
+      "loss": 1.8707,
+      "step": 1400
+    },
+    {
+      "epoch": 1.7475592747559274,
+      "grad_norm": 0.1746564656496048,
+      "learning_rate": 8.394856905848197e-05,
+      "loss": 1.8979,
+      "step": 1410
+    },
+    {
+      "epoch": 1.7599566093289942,
+      "grad_norm": 0.8505027294158936,
+      "learning_rate": 8.311903774367483e-05,
+      "loss": 1.71,
+      "step": 1420
+    },
+    {
+      "epoch": 1.772353943902061,
+      "grad_norm": 0.18071773648262024,
+      "learning_rate": 8.22895064288677e-05,
+      "loss": 1.9505,
+      "step": 1430
+    },
+    {
+      "epoch": 1.7847512784751278,
+      "grad_norm": 0.29732322692871094,
+      "learning_rate": 8.145997511406056e-05,
+      "loss": 1.8041,
+      "step": 1440
+    },
+    {
+      "epoch": 1.7971486130481946,
+      "grad_norm": 0.21795178949832916,
+      "learning_rate": 8.063044379925343e-05,
+      "loss": 1.7381,
+      "step": 1450
+    },
+    {
+      "epoch": 1.8095459476212614,
+      "grad_norm": 0.23459061980247498,
+      "learning_rate": 7.98009124844463e-05,
+      "loss": 1.6636,
+      "step": 1460
+    },
+    {
+      "epoch": 1.8219432821943282,
+      "grad_norm": 0.20895689725875854,
+      "learning_rate": 7.897138116963916e-05,
+      "loss": 1.8257,
+      "step": 1470
+    },
+    {
+      "epoch": 1.834340616767395,
+      "grad_norm": 0.18129809200763702,
+      "learning_rate": 7.814184985483203e-05,
+      "loss": 1.9791,
+      "step": 1480
+    },
+    {
+      "epoch": 1.8467379513404618,
+      "grad_norm": 0.1758158951997757,
+      "learning_rate": 7.731231854002489e-05,
+      "loss": 1.7657,
+      "step": 1490
+    },
+    {
+      "epoch": 1.8591352859135286,
+      "grad_norm": 0.14756101369857788,
+      "learning_rate": 7.648278722521776e-05,
+      "loss": 1.7483,
+      "step": 1500
+    },
+    {
+      "epoch": 1.8715326204865954,
+      "grad_norm": 0.14168867468833923,
+      "learning_rate": 7.565325591041062e-05,
+      "loss": 1.8844,
+      "step": 1510
+    },
+    {
+      "epoch": 1.8839299550596622,
+      "grad_norm": 0.1295221447944641,
+      "learning_rate": 7.482372459560349e-05,
+      "loss": 1.8121,
+      "step": 1520
+    },
+    {
+      "epoch": 1.896327289632729,
+      "grad_norm": 0.19356060028076172,
+      "learning_rate": 7.399419328079635e-05,
+      "loss": 1.5851,
+      "step": 1530
+    },
+    {
+      "epoch": 1.9087246242057958,
+      "grad_norm": 0.20035363733768463,
+      "learning_rate": 7.316466196598922e-05,
+      "loss": 1.7063,
+      "step": 1540
+    },
+    {
+      "epoch": 1.9211219587788624,
+      "grad_norm": 0.12139635533094406,
+      "learning_rate": 7.233513065118208e-05,
+      "loss": 1.7962,
+      "step": 1550
+    },
+    {
+      "epoch": 1.9335192933519294,
+      "grad_norm": 0.10587511211633682,
+      "learning_rate": 7.150559933637495e-05,
+      "loss": 1.7143,
+      "step": 1560
+    },
+    {
+      "epoch": 1.945916627924996,
+      "grad_norm": 0.18997065722942352,
+      "learning_rate": 7.067606802156782e-05,
+      "loss": 1.7636,
+      "step": 1570
+    },
+    {
+      "epoch": 1.958313962498063,
+      "grad_norm": 0.15760765969753265,
+      "learning_rate": 6.984653670676068e-05,
+      "loss": 1.7672,
+      "step": 1580
+    },
+    {
+      "epoch": 1.9707112970711296,
+      "grad_norm": 0.1490117609500885,
+      "learning_rate": 6.901700539195355e-05,
+      "loss": 1.6405,
+      "step": 1590
+    },
+    {
+      "epoch": 1.9831086316441966,
+      "grad_norm": 0.09482846409082413,
+      "learning_rate": 6.818747407714641e-05,
+      "loss": 1.8141,
+      "step": 1600
+    },
+    {
+      "epoch": 1.9955059662172632,
+      "grad_norm": 0.182535782456398,
+      "learning_rate": 6.735794276233928e-05,
+      "loss": 1.7745,
+      "step": 1610
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.8065738677978516,
+      "eval_runtime": 78.829,
+      "eval_samples_per_second": 9.096,
+      "eval_steps_per_second": 1.142,
+      "step": 1614
+    },
+    {
+      "epoch": 2.00743840074384,
+      "grad_norm": 0.24950097501277924,
+      "learning_rate": 6.652841144753214e-05,
+      "loss": 1.7537,
+      "step": 1620
+    },
+    {
+      "epoch": 2.019835735316907,
+      "grad_norm": 0.12352726608514786,
+      "learning_rate": 6.569888013272502e-05,
+      "loss": 1.7048,
+      "step": 1630
+    },
+    {
+      "epoch": 2.0322330698899735,
+      "grad_norm": 0.23885582387447357,
+      "learning_rate": 6.486934881791787e-05,
+      "loss": 1.7903,
+      "step": 1640
+    },
+    {
+      "epoch": 2.0446304044630406,
+      "grad_norm": 0.08030597865581512,
+      "learning_rate": 6.403981750311074e-05,
+      "loss": 1.8085,
+      "step": 1650
+    },
+    {
+      "epoch": 2.057027739036107,
+      "grad_norm": 0.12623316049575806,
+      "learning_rate": 6.321028618830362e-05,
+      "loss": 1.7876,
+      "step": 1660
+    },
+    {
+      "epoch": 2.069425073609174,
+      "grad_norm": 0.08768967539072037,
+      "learning_rate": 6.238075487349647e-05,
+      "loss": 1.767,
+      "step": 1670
+    },
+    {
+      "epoch": 2.0818224081822407,
+      "grad_norm": 0.39565062522888184,
+      "learning_rate": 6.155122355868934e-05,
+      "loss": 1.7355,
+      "step": 1680
+    },
+    {
+      "epoch": 2.0942197427553078,
+      "grad_norm": 0.1476745903491974,
+      "learning_rate": 6.072169224388221e-05,
+      "loss": 1.8694,
+      "step": 1690
+    },
+    {
+      "epoch": 2.1066170773283743,
+      "grad_norm": 0.10529963672161102,
+      "learning_rate": 5.989216092907508e-05,
+      "loss": 1.8461,
+      "step": 1700
+    },
+    {
+      "epoch": 2.1190144119014414,
+      "grad_norm": 0.11380179971456528,
+      "learning_rate": 5.906262961426794e-05,
+      "loss": 1.7705,
+      "step": 1710
+    },
+    {
+      "epoch": 2.131411746474508,
+      "grad_norm": 0.16582056879997253,
+      "learning_rate": 5.823309829946081e-05,
+      "loss": 1.7271,
+      "step": 1720
+    },
+    {
+      "epoch": 2.143809081047575,
+      "grad_norm": 0.09009672701358795,
+      "learning_rate": 5.740356698465368e-05,
+      "loss": 1.9473,
+      "step": 1730
+    },
+    {
+      "epoch": 2.1562064156206415,
+      "grad_norm": 0.09548009186983109,
+      "learning_rate": 5.6574035669846536e-05,
+      "loss": 1.8999,
+      "step": 1740
+    },
+    {
+      "epoch": 2.1686037501937085,
+      "grad_norm": 0.08916931599378586,
+      "learning_rate": 5.574450435503941e-05,
+      "loss": 1.7541,
+      "step": 1750
+    },
+    {
+      "epoch": 2.181001084766775,
+      "grad_norm": 0.09346842020750046,
+      "learning_rate": 5.4914973040232274e-05,
+      "loss": 1.7848,
+      "step": 1760
+    },
+    {
+      "epoch": 2.193398419339842,
+      "grad_norm": 0.09803362190723419,
+      "learning_rate": 5.408544172542513e-05,
+      "loss": 1.8555,
+      "step": 1770
+    },
+    {
+      "epoch": 2.2057957539129087,
+      "grad_norm": 0.23660095036029816,
+      "learning_rate": 5.3255910410618005e-05,
+      "loss": 1.8483,
+      "step": 1780
+    },
+    {
+      "epoch": 2.2181930884859753,
+      "grad_norm": 0.0797749012708664,
+      "learning_rate": 5.242637909581087e-05,
+      "loss": 1.8747,
+      "step": 1790
+    },
+    {
+      "epoch": 2.2305904230590423,
+      "grad_norm": 0.13405947387218475,
+      "learning_rate": 5.159684778100373e-05,
+      "loss": 1.874,
+      "step": 1800
+    },
+    {
+      "epoch": 2.242987757632109,
+      "grad_norm": 0.0895572081208229,
+      "learning_rate": 5.07673164661966e-05,
+      "loss": 1.7637,
+      "step": 1810
+    },
+    {
+      "epoch": 2.255385092205176,
+      "grad_norm": 0.1163070872426033,
+      "learning_rate": 4.993778515138947e-05,
+      "loss": 1.9363,
+      "step": 1820
+    },
+    {
+      "epoch": 2.2677824267782425,
+      "grad_norm": 0.08817609399557114,
+      "learning_rate": 4.910825383658233e-05,
+      "loss": 1.8142,
+      "step": 1830
+    },
+    {
+      "epoch": 2.2801797613513095,
+      "grad_norm": 0.1023801639676094,
+      "learning_rate": 4.82787225217752e-05,
+      "loss": 1.9672,
+      "step": 1840
+    },
+    {
+      "epoch": 2.292577095924376,
+      "grad_norm": 0.12135002017021179,
+      "learning_rate": 4.7449191206968064e-05,
+      "loss": 1.9507,
+      "step": 1850
+    },
+    {
+      "epoch": 2.304974430497443,
+      "grad_norm": 0.11531046777963638,
+      "learning_rate": 4.6619659892160936e-05,
+      "loss": 1.6656,
+      "step": 1860
+    },
+    {
+      "epoch": 2.3173717650705097,
+      "grad_norm": 0.08688156306743622,
+      "learning_rate": 4.5790128577353795e-05,
+      "loss": 1.6901,
+      "step": 1870
+    },
+    {
+      "epoch": 2.3297690996435767,
+      "grad_norm": 0.12937931716442108,
+      "learning_rate": 4.496059726254666e-05,
+      "loss": 1.6826,
+      "step": 1880
+    },
+    {
+      "epoch": 2.3421664342166433,
+      "grad_norm": 0.08356551826000214,
+      "learning_rate": 4.413106594773953e-05,
+      "loss": 1.7614,
+      "step": 1890
+    },
+    {
+      "epoch": 2.3545637687897103,
+      "grad_norm": 0.08626966178417206,
+      "learning_rate": 4.330153463293239e-05,
+      "loss": 1.924,
+      "step": 1900
+    },
+    {
+      "epoch": 2.366961103362777,
+      "grad_norm": 0.12821203470230103,
+      "learning_rate": 4.247200331812526e-05,
+      "loss": 1.6473,
+      "step": 1910
+    },
+    {
+      "epoch": 2.379358437935844,
+      "grad_norm": 0.08293508738279343,
+      "learning_rate": 4.164247200331813e-05,
+      "loss": 1.8332,
+      "step": 1920
+    },
+    {
+      "epoch": 2.3917557725089105,
+      "grad_norm": 0.07418167591094971,
+      "learning_rate": 4.0812940688510995e-05,
+      "loss": 1.8255,
+      "step": 1930
+    },
+    {
+      "epoch": 2.4041531070819775,
+      "grad_norm": 0.10695914179086685,
+      "learning_rate": 3.998340937370386e-05,
+      "loss": 1.7543,
+      "step": 1940
+    },
+    {
+      "epoch": 2.416550441655044,
+      "grad_norm": 0.0908871591091156,
+      "learning_rate": 3.9153878058896726e-05,
+      "loss": 1.7794,
+      "step": 1950
+    },
+    {
+      "epoch": 2.428947776228111,
+      "grad_norm": 0.11525363475084305,
+      "learning_rate": 3.832434674408959e-05,
+      "loss": 1.6607,
+      "step": 1960
+    },
+    {
+      "epoch": 2.4413451108011777,
+      "grad_norm": 0.07907426357269287,
+      "learning_rate": 3.749481542928246e-05,
+      "loss": 1.7764,
+      "step": 1970
+    },
+    {
+      "epoch": 2.4537424453742447,
+      "grad_norm": 0.0990724042057991,
+      "learning_rate": 3.666528411447532e-05,
+      "loss": 1.857,
+      "step": 1980
+    },
+    {
+      "epoch": 2.4661397799473113,
+      "grad_norm": 0.06209372356534004,
+      "learning_rate": 3.583575279966819e-05,
+      "loss": 1.9036,
+      "step": 1990
+    },
+    {
+      "epoch": 2.4785371145203783,
+      "grad_norm": 0.07287060469388962,
+      "learning_rate": 3.5006221484861054e-05,
+      "loss": 1.8647,
+      "step": 2000
+    },
+    {
+      "epoch": 2.490934449093445,
+      "grad_norm": 0.06776302307844162,
+      "learning_rate": 3.417669017005392e-05,
+      "loss": 1.8703,
+      "step": 2010
+    },
+    {
+      "epoch": 2.5033317836665114,
+      "grad_norm": 0.08577609807252884,
+      "learning_rate": 3.3347158855246785e-05,
+      "loss": 1.8978,
+      "step": 2020
+    },
+    {
+      "epoch": 2.5157291182395785,
+      "grad_norm": 0.087737075984478,
+      "learning_rate": 3.251762754043966e-05,
+      "loss": 1.7975,
+      "step": 2030
+    },
+    {
+      "epoch": 2.5281264528126455,
+      "grad_norm": 0.07157925516366959,
+      "learning_rate": 3.1688096225632516e-05,
+      "loss": 1.8695,
+      "step": 2040
+    },
+    {
+      "epoch": 2.540523787385712,
+      "grad_norm": 0.0907244011759758,
+      "learning_rate": 3.085856491082538e-05,
+      "loss": 1.8752,
+      "step": 2050
+    },
+    {
+      "epoch": 2.5529211219587786,
+      "grad_norm": 0.0730370432138443,
+      "learning_rate": 3.0029033596018254e-05,
+      "loss": 1.6779,
+      "step": 2060
+    },
+    {
+      "epoch": 2.5653184565318456,
+      "grad_norm": 0.09164728224277496,
+      "learning_rate": 2.9199502281211116e-05,
+      "loss": 1.7662,
+      "step": 2070
+    },
+    {
+      "epoch": 2.5777157911049127,
+      "grad_norm": 0.08118163049221039,
+      "learning_rate": 2.8369970966403985e-05,
+      "loss": 1.7423,
+      "step": 2080
+    },
+    {
+      "epoch": 2.5901131256779792,
+      "grad_norm": 0.07020942121744156,
+      "learning_rate": 2.754043965159685e-05,
+      "loss": 1.6809,
+      "step": 2090
+    },
+    {
+      "epoch": 2.602510460251046,
+      "grad_norm": 0.08827990293502808,
+      "learning_rate": 2.6710908336789713e-05,
+      "loss": 1.5771,
+      "step": 2100
+    },
+    {
+      "epoch": 2.614907794824113,
+      "grad_norm": 0.11959416419267654,
+      "learning_rate": 2.5881377021982585e-05,
+      "loss": 1.756,
+      "step": 2110
+    },
+    {
+      "epoch": 2.62730512939718,
+      "grad_norm": 0.18080498278141022,
+      "learning_rate": 2.5051845707175447e-05,
+      "loss": 1.7437,
+      "step": 2120
+    },
+    {
+      "epoch": 2.6397024639702464,
+      "grad_norm": 0.08301777392625809,
+      "learning_rate": 2.4222314392368316e-05,
+      "loss": 1.9331,
+      "step": 2130
+    },
+    {
+      "epoch": 2.652099798543313,
+      "grad_norm": 0.08320324867963791,
+      "learning_rate": 2.3392783077561178e-05,
+      "loss": 1.6681,
+      "step": 2140
+    },
+    {
+      "epoch": 2.66449713311638,
+      "grad_norm": 0.09895749390125275,
+      "learning_rate": 2.2563251762754044e-05,
+      "loss": 1.7887,
+      "step": 2150
+    },
+    {
+      "epoch": 2.6768944676894466,
+      "grad_norm": 0.08482034504413605,
+      "learning_rate": 2.1733720447946913e-05,
+      "loss": 1.8258,
+      "step": 2160
+    },
+    {
+      "epoch": 2.6892918022625136,
+      "grad_norm": 0.08512965589761734,
+      "learning_rate": 2.0904189133139775e-05,
+      "loss": 1.8644,
+      "step": 2170
+    },
+    {
+      "epoch": 2.70168913683558,
+      "grad_norm": 0.0718398168683052,
+      "learning_rate": 2.0074657818332644e-05,
+      "loss": 1.875,
+      "step": 2180
+    },
+    {
+      "epoch": 2.7140864714086472,
+      "grad_norm": 0.07293003052473068,
+      "learning_rate": 1.924512650352551e-05,
+      "loss": 1.905,
+      "step": 2190
+    },
+    {
+      "epoch": 2.726483805981714,
+      "grad_norm": 0.07507035881280899,
+      "learning_rate": 1.8415595188718375e-05,
+      "loss": 1.8567,
+      "step": 2200
+    },
+    {
+      "epoch": 2.738881140554781,
+      "grad_norm": 0.07978376746177673,
+      "learning_rate": 1.758606387391124e-05,
+      "loss": 1.763,
+      "step": 2210
+    },
+    {
+      "epoch": 2.7512784751278474,
+      "grad_norm": 0.06767022609710693,
+      "learning_rate": 1.6756532559104106e-05,
+      "loss": 1.7365,
+      "step": 2220
+    },
+    {
+      "epoch": 2.7636758097009144,
+      "grad_norm": 0.08018273115158081,
+      "learning_rate": 1.5927001244296975e-05,
+      "loss": 1.7595,
+      "step": 2230
+    },
+    {
+      "epoch": 2.776073144273981,
+      "grad_norm": 0.09407597035169601,
+      "learning_rate": 1.5097469929489839e-05,
+      "loss": 1.6947,
+      "step": 2240
+    },
+    {
+      "epoch": 2.788470478847048,
+      "grad_norm": 0.0730314627289772,
+      "learning_rate": 1.4267938614682704e-05,
+      "loss": 1.8826,
+      "step": 2250
+    },
+    {
+      "epoch": 2.8008678134201146,
+      "grad_norm": 0.06652677804231644,
+      "learning_rate": 1.3438407299875571e-05,
+      "loss": 1.8177,
+      "step": 2260
+    },
+    {
+      "epoch": 2.8132651479931816,
+      "grad_norm": 0.07838471233844757,
+      "learning_rate": 1.2608875985068435e-05,
+      "loss": 1.8317,
+      "step": 2270
+    },
+    {
+      "epoch": 2.825662482566248,
+      "grad_norm": 0.0950925275683403,
+      "learning_rate": 1.1779344670261303e-05,
+      "loss": 1.7767,
+      "step": 2280
+    },
+    {
+      "epoch": 2.838059817139315,
+      "grad_norm": 0.08422578871250153,
+      "learning_rate": 1.094981335545417e-05,
+      "loss": 1.8927,
+      "step": 2290
+    },
+    {
+      "epoch": 2.850457151712382,
+      "grad_norm": 0.08127064257860184,
+      "learning_rate": 1.0120282040647035e-05,
+      "loss": 1.8953,
+      "step": 2300
+    },
+    {
+      "epoch": 2.862854486285449,
+      "grad_norm": 0.0867166519165039,
+      "learning_rate": 9.290750725839901e-06,
+      "loss": 1.7904,
+      "step": 2310
+    },
+    {
+      "epoch": 2.8752518208585154,
+      "grad_norm": 0.09853280335664749,
+      "learning_rate": 8.461219411032766e-06,
+      "loss": 1.7074,
+      "step": 2320
+    },
+    {
+      "epoch": 2.887649155431582,
+      "grad_norm": 0.0887097492814064,
+      "learning_rate": 7.631688096225632e-06,
+      "loss": 1.7587,
+      "step": 2330
+    },
+    {
+      "epoch": 2.900046490004649,
+      "grad_norm": 0.0924605056643486,
+      "learning_rate": 6.802156781418499e-06,
+      "loss": 1.9213,
+      "step": 2340
+    },
+    {
+      "epoch": 2.912443824577716,
+      "grad_norm": 0.08043299615383148,
+      "learning_rate": 5.972625466611365e-06,
+      "loss": 1.8088,
+      "step": 2350
+    },
+    {
+      "epoch": 2.9248411591507826,
+      "grad_norm": 0.08430881798267365,
+      "learning_rate": 5.143094151804231e-06,
+      "loss": 1.8026,
+      "step": 2360
+    },
+    {
+      "epoch": 2.937238493723849,
+      "grad_norm": 0.07314042001962662,
+      "learning_rate": 4.313562836997097e-06,
+      "loss": 1.7945,
+      "step": 2370
+    },
+    {
+      "epoch": 2.949635828296916,
+      "grad_norm": 0.07442809641361237,
+      "learning_rate": 3.484031522189963e-06,
+      "loss": 1.6588,
+      "step": 2380
+    },
+    {
+      "epoch": 2.962033162869983,
+      "grad_norm": 0.08359961956739426,
+      "learning_rate": 2.6545002073828286e-06,
+      "loss": 1.7927,
+      "step": 2390
+    },
+    {
+      "epoch": 2.9744304974430498,
+      "grad_norm": 0.07364208996295929,
+      "learning_rate": 1.8249688925756948e-06,
+      "loss": 1.7357,
+      "step": 2400
+    },
+    {
+      "epoch": 2.9868278320161163,
+      "grad_norm": 0.07607521116733551,
+      "learning_rate": 9.95437577768561e-07,
+      "loss": 1.8463,
+      "step": 2410
+    },
+    {
+      "epoch": 2.9992251665891834,
+      "grad_norm": 0.08674101531505585,
+      "learning_rate": 1.6590626296142679e-07,
+      "loss": 1.9422,
+      "step": 2420
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 1.8053849935531616,
+      "eval_runtime": 78.8378,
+      "eval_samples_per_second": 9.095,
+      "eval_steps_per_second": 1.142,
+      "step": 2421
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 2421,
+  "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": 8.469388058720993e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2421/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15ed81f35b71a674f101f42b5d39caf5a7c94955958bbf088fb20abcabaa812f
+size 5905

runs/Oct31_19-53-38_66a1d7a2b568/events.out.tfevents.1761940446.66a1d7a2b568.942.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c565ed1e25f4e26b1a87b2a9ca699bb6587e0f3132f8d40f7927babad4c430a7
+size 57740

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