Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,207 @@
+---
+base_model: Qwen/Qwen3-1.7B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-1.7B
+- 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 0.18.1

adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-1.7B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 512,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 256,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_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 sha256:58e5fc90e87afbb5452a9efb707b2fcc1071ad5a36402ffef8935e719acec875
+size 2358210936

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3090196a901be5e02aee2de5659ce645ebfa8c463cd28e7b021f1d5213ec262f
+size 2231707643

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adf94c80baddaafc86f920b787da40159b16e118343eb6184b4f4f0895239ccc
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:711d2413056d845e789a2817c52b417be337d7b4a5a6303350e9063dd499a12c
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
+size 11422650

tokenizer_config.json

@@ -0,0 +1,29 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2541 @@
+{
+  "best_global_step": 3578,
+  "best_metric": 0.9194258451461792,
+  "best_model_checkpoint": "./qwen3-1.7b-text2json-v2/checkpoint-3578",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 3578,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0027950527566207813,
+      "grad_norm": 5.643767356872559,
+      "learning_rate": 3.016759776536313e-07,
+      "loss": 1.649482536315918,
+      "step": 10
+    },
+    {
+      "epoch": 0.005590105513241563,
+      "grad_norm": 4.668584823608398,
+      "learning_rate": 6.368715083798882e-07,
+      "loss": 1.6637184143066406,
+      "step": 20
+    },
+    {
+      "epoch": 0.008385158269862344,
+      "grad_norm": 3.2273833751678467,
+      "learning_rate": 9.720670391061452e-07,
+      "loss": 1.620625114440918,
+      "step": 30
+    },
+    {
+      "epoch": 0.011180211026483125,
+      "grad_norm": 2.4648287296295166,
+      "learning_rate": 1.3072625698324024e-06,
+      "loss": 1.4959917068481445,
+      "step": 40
+    },
+    {
+      "epoch": 0.013975263783103906,
+      "grad_norm": 1.6723942756652832,
+      "learning_rate": 1.642458100558659e-06,
+      "loss": 1.4724949836730956,
+      "step": 50
+    },
+    {
+      "epoch": 0.01677031653972469,
+      "grad_norm": 0.998455286026001,
+      "learning_rate": 1.9776536312849162e-06,
+      "loss": 1.4036648750305176,
+      "step": 60
+    },
+    {
+      "epoch": 0.019565369296345468,
+      "grad_norm": 0.5846454501152039,
+      "learning_rate": 2.312849162011173e-06,
+      "loss": 1.2452651977539062,
+      "step": 70
+    },
+    {
+      "epoch": 0.02236042205296625,
+      "grad_norm": 0.5780718922615051,
+      "learning_rate": 2.6480446927374305e-06,
+      "loss": 1.300985050201416,
+      "step": 80
+    },
+    {
+      "epoch": 0.02515547480958703,
+      "grad_norm": 0.49602633714675903,
+      "learning_rate": 2.9832402234636874e-06,
+      "loss": 1.2021345138549804,
+      "step": 90
+    },
+    {
+      "epoch": 0.027950527566207813,
+      "grad_norm": 0.5135180354118347,
+      "learning_rate": 3.318435754189944e-06,
+      "loss": 1.194033718109131,
+      "step": 100
+    },
+    {
+      "epoch": 0.030745580322828592,
+      "grad_norm": 0.39543935656547546,
+      "learning_rate": 3.6536312849162013e-06,
+      "loss": 1.1850563049316407,
+      "step": 110
+    },
+    {
+      "epoch": 0.03354063307944938,
+      "grad_norm": 0.4353114664554596,
+      "learning_rate": 3.988826815642458e-06,
+      "loss": 1.1643589973449706,
+      "step": 120
+    },
+    {
+      "epoch": 0.03633568583607016,
+      "grad_norm": 0.35825908184051514,
+      "learning_rate": 4.324022346368715e-06,
+      "loss": 1.1326589584350586,
+      "step": 130
+    },
+    {
+      "epoch": 0.039130738592690936,
+      "grad_norm": 0.4327046573162079,
+      "learning_rate": 4.6592178770949725e-06,
+      "loss": 1.1646012306213378,
+      "step": 140
+    },
+    {
+      "epoch": 0.041925791349311715,
+      "grad_norm": 0.40660929679870605,
+      "learning_rate": 4.994413407821229e-06,
+      "loss": 1.0970611572265625,
+      "step": 150
+    },
+    {
+      "epoch": 0.0447208441059325,
+      "grad_norm": 0.37189826369285583,
+      "learning_rate": 5.329608938547486e-06,
+      "loss": 1.052849006652832,
+      "step": 160
+    },
+    {
+      "epoch": 0.04751589686255328,
+      "grad_norm": 0.4213009774684906,
+      "learning_rate": 5.664804469273743e-06,
+      "loss": 1.184032917022705,
+      "step": 170
+    },
+    {
+      "epoch": 0.05031094961917406,
+      "grad_norm": 0.37389159202575684,
+      "learning_rate": 6e-06,
+      "loss": 1.0986117362976073,
+      "step": 180
+    },
+    {
+      "epoch": 0.053106002375794846,
+      "grad_norm": 0.35978958010673523,
+      "learning_rate": 6.3351955307262575e-06,
+      "loss": 1.1341217041015625,
+      "step": 190
+    },
+    {
+      "epoch": 0.055901055132415625,
+      "grad_norm": 0.36538344621658325,
+      "learning_rate": 6.670391061452514e-06,
+      "loss": 1.1568432807922364,
+      "step": 200
+    },
+    {
+      "epoch": 0.058696107889036404,
+      "grad_norm": 0.3577878177165985,
+      "learning_rate": 7.005586592178771e-06,
+      "loss": 1.1413363456726073,
+      "step": 210
+    },
+    {
+      "epoch": 0.061491160645657184,
+      "grad_norm": 0.37476423382759094,
+      "learning_rate": 7.340782122905028e-06,
+      "loss": 1.0659676551818849,
+      "step": 220
+    },
+    {
+      "epoch": 0.06428621340227797,
+      "grad_norm": 0.40813082456588745,
+      "learning_rate": 7.675977653631286e-06,
+      "loss": 1.0974410057067872,
+      "step": 230
+    },
+    {
+      "epoch": 0.06708126615889876,
+      "grad_norm": 0.33985811471939087,
+      "learning_rate": 8.011173184357543e-06,
+      "loss": 1.1290700912475586,
+      "step": 240
+    },
+    {
+      "epoch": 0.06987631891551953,
+      "grad_norm": 0.34717175364494324,
+      "learning_rate": 8.346368715083799e-06,
+      "loss": 1.0772873878479003,
+      "step": 250
+    },
+    {
+      "epoch": 0.07267137167214031,
+      "grad_norm": 0.3674837052822113,
+      "learning_rate": 8.681564245810056e-06,
+      "loss": 1.0954713821411133,
+      "step": 260
+    },
+    {
+      "epoch": 0.07546642442876109,
+      "grad_norm": 0.3208862543106079,
+      "learning_rate": 9.016759776536314e-06,
+      "loss": 1.1133221626281737,
+      "step": 270
+    },
+    {
+      "epoch": 0.07826147718538187,
+      "grad_norm": 0.3443635404109955,
+      "learning_rate": 9.35195530726257e-06,
+      "loss": 1.0993770599365233,
+      "step": 280
+    },
+    {
+      "epoch": 0.08105652994200266,
+      "grad_norm": 0.4215189814567566,
+      "learning_rate": 9.687150837988827e-06,
+      "loss": 1.0730499267578124,
+      "step": 290
+    },
+    {
+      "epoch": 0.08385158269862343,
+      "grad_norm": 0.37784650921821594,
+      "learning_rate": 1.0022346368715083e-05,
+      "loss": 1.0912086486816406,
+      "step": 300
+    },
+    {
+      "epoch": 0.08664663545524422,
+      "grad_norm": 0.38466012477874756,
+      "learning_rate": 1.0357541899441341e-05,
+      "loss": 1.1172038078308106,
+      "step": 310
+    },
+    {
+      "epoch": 0.089441688211865,
+      "grad_norm": 0.4363117516040802,
+      "learning_rate": 1.0692737430167598e-05,
+      "loss": 1.1165932655334472,
+      "step": 320
+    },
+    {
+      "epoch": 0.09223674096848578,
+      "grad_norm": 0.38784098625183105,
+      "learning_rate": 1.1027932960893854e-05,
+      "loss": 1.1101572036743164,
+      "step": 330
+    },
+    {
+      "epoch": 0.09503179372510656,
+      "grad_norm": 0.4113931953907013,
+      "learning_rate": 1.1363128491620111e-05,
+      "loss": 1.1031377792358399,
+      "step": 340
+    },
+    {
+      "epoch": 0.09782684648172735,
+      "grad_norm": 0.3761017918586731,
+      "learning_rate": 1.1698324022346369e-05,
+      "loss": 1.0470043182373048,
+      "step": 350
+    },
+    {
+      "epoch": 0.10062189923834812,
+      "grad_norm": 0.3837948739528656,
+      "learning_rate": 1.2033519553072627e-05,
+      "loss": 1.0470937728881835,
+      "step": 360
+    },
+    {
+      "epoch": 0.1034169519949689,
+      "grad_norm": 0.33570754528045654,
+      "learning_rate": 1.2368715083798884e-05,
+      "loss": 1.1301692008972168,
+      "step": 370
+    },
+    {
+      "epoch": 0.10621200475158969,
+      "grad_norm": 0.3694814443588257,
+      "learning_rate": 1.270391061452514e-05,
+      "loss": 1.0451414108276367,
+      "step": 380
+    },
+    {
+      "epoch": 0.10900705750821046,
+      "grad_norm": 0.38872382044792175,
+      "learning_rate": 1.3039106145251397e-05,
+      "loss": 1.1033297538757325,
+      "step": 390
+    },
+    {
+      "epoch": 0.11180211026483125,
+      "grad_norm": 0.3904806077480316,
+      "learning_rate": 1.3374301675977653e-05,
+      "loss": 1.1097043991088866,
+      "step": 400
+    },
+    {
+      "epoch": 0.11459716302145204,
+      "grad_norm": 0.2938089370727539,
+      "learning_rate": 1.3709497206703912e-05,
+      "loss": 1.0522205352783203,
+      "step": 410
+    },
+    {
+      "epoch": 0.11739221577807281,
+      "grad_norm": 0.3930291533470154,
+      "learning_rate": 1.4044692737430168e-05,
+      "loss": 1.068246078491211,
+      "step": 420
+    },
+    {
+      "epoch": 0.1201872685346936,
+      "grad_norm": 0.4230504631996155,
+      "learning_rate": 1.4379888268156425e-05,
+      "loss": 1.0642436027526856,
+      "step": 430
+    },
+    {
+      "epoch": 0.12298232129131437,
+      "grad_norm": 0.3574168384075165,
+      "learning_rate": 1.4715083798882681e-05,
+      "loss": 1.0741335868835449,
+      "step": 440
+    },
+    {
+      "epoch": 0.12577737404793515,
+      "grad_norm": 0.3820915222167969,
+      "learning_rate": 1.5050279329608937e-05,
+      "loss": 1.1127784729003907,
+      "step": 450
+    },
+    {
+      "epoch": 0.12857242680455594,
+      "grad_norm": 0.3761838674545288,
+      "learning_rate": 1.5385474860335196e-05,
+      "loss": 1.0927792549133302,
+      "step": 460
+    },
+    {
+      "epoch": 0.13136747956117673,
+      "grad_norm": 0.4056966006755829,
+      "learning_rate": 1.5720670391061452e-05,
+      "loss": 1.0605798721313477,
+      "step": 470
+    },
+    {
+      "epoch": 0.1341625323177975,
+      "grad_norm": 0.46689334511756897,
+      "learning_rate": 1.6055865921787712e-05,
+      "loss": 1.038266086578369,
+      "step": 480
+    },
+    {
+      "epoch": 0.13695758507441827,
+      "grad_norm": 0.4448232054710388,
+      "learning_rate": 1.639106145251397e-05,
+      "loss": 1.0706561088562012,
+      "step": 490
+    },
+    {
+      "epoch": 0.13975263783103906,
+      "grad_norm": 0.36253008246421814,
+      "learning_rate": 1.6726256983240225e-05,
+      "loss": 1.0975689888000488,
+      "step": 500
+    },
+    {
+      "epoch": 0.14254769058765984,
+      "grad_norm": 0.3154246211051941,
+      "learning_rate": 1.706145251396648e-05,
+      "loss": 1.082898998260498,
+      "step": 510
+    },
+    {
+      "epoch": 0.14534274334428063,
+      "grad_norm": 0.3553566336631775,
+      "learning_rate": 1.7396648044692738e-05,
+      "loss": 1.0855050086975098,
+      "step": 520
+    },
+    {
+      "epoch": 0.14813779610090141,
+      "grad_norm": 0.2990500330924988,
+      "learning_rate": 1.7731843575418995e-05,
+      "loss": 1.0738759994506837,
+      "step": 530
+    },
+    {
+      "epoch": 0.15093284885752217,
+      "grad_norm": 0.3952273428440094,
+      "learning_rate": 1.806703910614525e-05,
+      "loss": 1.0667924880981445,
+      "step": 540
+    },
+    {
+      "epoch": 0.15372790161414296,
+      "grad_norm": 0.42053553462028503,
+      "learning_rate": 1.8402234636871508e-05,
+      "loss": 1.032864475250244,
+      "step": 550
+    },
+    {
+      "epoch": 0.15652295437076374,
+      "grad_norm": 0.4121285080909729,
+      "learning_rate": 1.8737430167597764e-05,
+      "loss": 1.0744197845458985,
+      "step": 560
+    },
+    {
+      "epoch": 0.15931800712738453,
+      "grad_norm": 0.42475244402885437,
+      "learning_rate": 1.9072625698324024e-05,
+      "loss": 1.0168725967407226,
+      "step": 570
+    },
+    {
+      "epoch": 0.16211305988400532,
+      "grad_norm": 0.3706689476966858,
+      "learning_rate": 1.940782122905028e-05,
+      "loss": 1.0727126121520996,
+      "step": 580
+    },
+    {
+      "epoch": 0.1649081126406261,
+      "grad_norm": 0.30601057410240173,
+      "learning_rate": 1.9743016759776537e-05,
+      "loss": 1.034100341796875,
+      "step": 590
+    },
+    {
+      "epoch": 0.16770316539724686,
+      "grad_norm": 0.35653752088546753,
+      "learning_rate": 2.0078212290502793e-05,
+      "loss": 1.0130882263183594,
+      "step": 600
+    },
+    {
+      "epoch": 0.17049821815386765,
+      "grad_norm": 0.38125112652778625,
+      "learning_rate": 2.041340782122905e-05,
+      "loss": 1.0439627647399903,
+      "step": 610
+    },
+    {
+      "epoch": 0.17329327091048843,
+      "grad_norm": 0.31715694069862366,
+      "learning_rate": 2.0748603351955306e-05,
+      "loss": 1.0409150123596191,
+      "step": 620
+    },
+    {
+      "epoch": 0.17608832366710922,
+      "grad_norm": 0.3510577082633972,
+      "learning_rate": 2.1083798882681563e-05,
+      "loss": 1.0283869743347167,
+      "step": 630
+    },
+    {
+      "epoch": 0.17888337642373,
+      "grad_norm": 0.338158518075943,
+      "learning_rate": 2.141899441340782e-05,
+      "loss": 1.0281116485595703,
+      "step": 640
+    },
+    {
+      "epoch": 0.1816784291803508,
+      "grad_norm": 0.4553789794445038,
+      "learning_rate": 2.1754189944134076e-05,
+      "loss": 1.0968013763427735,
+      "step": 650
+    },
+    {
+      "epoch": 0.18447348193697155,
+      "grad_norm": 0.37961041927337646,
+      "learning_rate": 2.2089385474860332e-05,
+      "loss": 1.0369602203369142,
+      "step": 660
+    },
+    {
+      "epoch": 0.18726853469359234,
+      "grad_norm": 0.30950912833213806,
+      "learning_rate": 2.2424581005586596e-05,
+      "loss": 1.0765933036804198,
+      "step": 670
+    },
+    {
+      "epoch": 0.19006358745021312,
+      "grad_norm": 0.3528067171573639,
+      "learning_rate": 2.2759776536312852e-05,
+      "loss": 1.0690201759338378,
+      "step": 680
+    },
+    {
+      "epoch": 0.1928586402068339,
+      "grad_norm": 0.40091198682785034,
+      "learning_rate": 2.309497206703911e-05,
+      "loss": 1.0370705604553223,
+      "step": 690
+    },
+    {
+      "epoch": 0.1956536929634547,
+      "grad_norm": 0.3499792814254761,
+      "learning_rate": 2.3430167597765365e-05,
+      "loss": 1.0379643440246582,
+      "step": 700
+    },
+    {
+      "epoch": 0.19844874572007545,
+      "grad_norm": 0.32263559103012085,
+      "learning_rate": 2.3765363128491622e-05,
+      "loss": 0.9880000114440918,
+      "step": 710
+    },
+    {
+      "epoch": 0.20124379847669624,
+      "grad_norm": 0.40820619463920593,
+      "learning_rate": 2.4100558659217878e-05,
+      "loss": 1.0606675148010254,
+      "step": 720
+    },
+    {
+      "epoch": 0.20403885123331703,
+      "grad_norm": 0.33786195516586304,
+      "learning_rate": 2.4435754189944135e-05,
+      "loss": 1.054260540008545,
+      "step": 730
+    },
+    {
+      "epoch": 0.2068339039899378,
+      "grad_norm": 0.33243510127067566,
+      "learning_rate": 2.477094972067039e-05,
+      "loss": 1.0376768112182617,
+      "step": 740
+    },
+    {
+      "epoch": 0.2096289567465586,
+      "grad_norm": 0.346973180770874,
+      "learning_rate": 2.5106145251396648e-05,
+      "loss": 1.12500057220459,
+      "step": 750
+    },
+    {
+      "epoch": 0.21242400950317938,
+      "grad_norm": 0.29655370116233826,
+      "learning_rate": 2.5441340782122908e-05,
+      "loss": 1.0486486434936524,
+      "step": 760
+    },
+    {
+      "epoch": 0.21521906225980014,
+      "grad_norm": 0.31937628984451294,
+      "learning_rate": 2.5776536312849164e-05,
+      "loss": 1.0881372451782227,
+      "step": 770
+    },
+    {
+      "epoch": 0.21801411501642093,
+      "grad_norm": 0.3570577800273895,
+      "learning_rate": 2.611173184357542e-05,
+      "loss": 1.0278472900390625,
+      "step": 780
+    },
+    {
+      "epoch": 0.22080916777304171,
+      "grad_norm": 0.3659631311893463,
+      "learning_rate": 2.6446927374301677e-05,
+      "loss": 1.0619357109069825,
+      "step": 790
+    },
+    {
+      "epoch": 0.2236042205296625,
+      "grad_norm": 0.3441682755947113,
+      "learning_rate": 2.6782122905027934e-05,
+      "loss": 1.0706026077270507,
+      "step": 800
+    },
+    {
+      "epoch": 0.2263992732862833,
+      "grad_norm": 0.35944634675979614,
+      "learning_rate": 2.711731843575419e-05,
+      "loss": 1.0401902198791504,
+      "step": 810
+    },
+    {
+      "epoch": 0.22919432604290407,
+      "grad_norm": 0.3168131709098816,
+      "learning_rate": 2.7452513966480447e-05,
+      "loss": 1.0667524337768555,
+      "step": 820
+    },
+    {
+      "epoch": 0.23198937879952483,
+      "grad_norm": 0.36638668179512024,
+      "learning_rate": 2.7787709497206703e-05,
+      "loss": 1.052546215057373,
+      "step": 830
+    },
+    {
+      "epoch": 0.23478443155614562,
+      "grad_norm": 0.39376768469810486,
+      "learning_rate": 2.812290502793296e-05,
+      "loss": 1.0390704154968262,
+      "step": 840
+    },
+    {
+      "epoch": 0.2375794843127664,
+      "grad_norm": 0.2895391285419464,
+      "learning_rate": 2.845810055865922e-05,
+      "loss": 1.0275959014892577,
+      "step": 850
+    },
+    {
+      "epoch": 0.2403745370693872,
+      "grad_norm": 0.3222823441028595,
+      "learning_rate": 2.8793296089385476e-05,
+      "loss": 1.0830079078674317,
+      "step": 860
+    },
+    {
+      "epoch": 0.24316958982600798,
+      "grad_norm": 0.3823617100715637,
+      "learning_rate": 2.9128491620111733e-05,
+      "loss": 1.0468826293945312,
+      "step": 870
+    },
+    {
+      "epoch": 0.24596464258262873,
+      "grad_norm": 0.3948187828063965,
+      "learning_rate": 2.946368715083799e-05,
+      "loss": 1.0295352935791016,
+      "step": 880
+    },
+    {
+      "epoch": 0.24875969533924952,
+      "grad_norm": 0.3245835602283478,
+      "learning_rate": 2.9798882681564246e-05,
+      "loss": 1.0973793029785157,
+      "step": 890
+    },
+    {
+      "epoch": 0.2515547480958703,
+      "grad_norm": 0.32093924283981323,
+      "learning_rate": 2.9992939099735218e-05,
+      "loss": 1.0175031661987304,
+      "step": 900
+    },
+    {
+      "epoch": 0.2543498008524911,
+      "grad_norm": 0.3369489908218384,
+      "learning_rate": 2.997528684907326e-05,
+      "loss": 1.0713120460510255,
+      "step": 910
+    },
+    {
+      "epoch": 0.2571448536091119,
+      "grad_norm": 0.3308013081550598,
+      "learning_rate": 2.99576345984113e-05,
+      "loss": 0.9863748550415039,
+      "step": 920
+    },
+    {
+      "epoch": 0.25993990636573266,
+      "grad_norm": 0.2931237518787384,
+      "learning_rate": 2.9939982347749338e-05,
+      "loss": 0.9957609176635742,
+      "step": 930
+    },
+    {
+      "epoch": 0.26273495912235345,
+      "grad_norm": 0.3004375100135803,
+      "learning_rate": 2.992233009708738e-05,
+      "loss": 1.0490875244140625,
+      "step": 940
+    },
+    {
+      "epoch": 0.26553001187897424,
+      "grad_norm": 0.30455997586250305,
+      "learning_rate": 2.990467784642542e-05,
+      "loss": 0.969981575012207,
+      "step": 950
+    },
+    {
+      "epoch": 0.268325064635595,
+      "grad_norm": 0.30235281586647034,
+      "learning_rate": 2.988702559576346e-05,
+      "loss": 1.0383959770202638,
+      "step": 960
+    },
+    {
+      "epoch": 0.27112011739221575,
+      "grad_norm": 0.33622094988822937,
+      "learning_rate": 2.9869373345101503e-05,
+      "loss": 1.096113395690918,
+      "step": 970
+    },
+    {
+      "epoch": 0.27391517014883654,
+      "grad_norm": 0.3102216124534607,
+      "learning_rate": 2.985172109443954e-05,
+      "loss": 1.0069896697998046,
+      "step": 980
+    },
+    {
+      "epoch": 0.2767102229054573,
+      "grad_norm": 0.31250712275505066,
+      "learning_rate": 2.983406884377758e-05,
+      "loss": 1.0165568351745606,
+      "step": 990
+    },
+    {
+      "epoch": 0.2795052756620781,
+      "grad_norm": 0.2913067638874054,
+      "learning_rate": 2.9816416593115623e-05,
+      "loss": 1.1328548431396483,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2823003284186989,
+      "grad_norm": 0.2881060540676117,
+      "learning_rate": 2.9798764342453664e-05,
+      "loss": 1.0683287620544433,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2850953811753197,
+      "grad_norm": 0.25279340147972107,
+      "learning_rate": 2.9781112091791705e-05,
+      "loss": 1.0043587684631348,
+      "step": 1020
+    },
+    {
+      "epoch": 0.28789043393194047,
+      "grad_norm": 0.29510220885276794,
+      "learning_rate": 2.9763459841129743e-05,
+      "loss": 0.9762296676635742,
+      "step": 1030
+    },
+    {
+      "epoch": 0.29068548668856126,
+      "grad_norm": 0.2661595344543457,
+      "learning_rate": 2.9745807590467784e-05,
+      "loss": 1.0301525115966796,
+      "step": 1040
+    },
+    {
+      "epoch": 0.29348053944518204,
+      "grad_norm": 0.32319095730781555,
+      "learning_rate": 2.9728155339805825e-05,
+      "loss": 0.9689548492431641,
+      "step": 1050
+    },
+    {
+      "epoch": 0.29627559220180283,
+      "grad_norm": 0.29703575372695923,
+      "learning_rate": 2.9710503089143866e-05,
+      "loss": 1.0159470558166503,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2990706449584236,
+      "grad_norm": 0.34380561113357544,
+      "learning_rate": 2.9692850838481907e-05,
+      "loss": 1.009904670715332,
+      "step": 1070
+    },
+    {
+      "epoch": 0.30186569771504435,
+      "grad_norm": 0.3270290195941925,
+      "learning_rate": 2.967519858781995e-05,
+      "loss": 1.000676441192627,
+      "step": 1080
+    },
+    {
+      "epoch": 0.30466075047166513,
+      "grad_norm": 0.28638219833374023,
+      "learning_rate": 2.965754633715799e-05,
+      "loss": 0.9915603637695313,
+      "step": 1090
+    },
+    {
+      "epoch": 0.3074558032282859,
+      "grad_norm": 0.3670640289783478,
+      "learning_rate": 2.963989408649603e-05,
+      "loss": 0.9769265174865722,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3102508559849067,
+      "grad_norm": 0.251179039478302,
+      "learning_rate": 2.9622241835834072e-05,
+      "loss": 1.002616786956787,
+      "step": 1110
+    },
+    {
+      "epoch": 0.3130459087415275,
+      "grad_norm": 0.3262287974357605,
+      "learning_rate": 2.9604589585172113e-05,
+      "loss": 1.0142257690429688,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3158409614981483,
+      "grad_norm": 0.2572724521160126,
+      "learning_rate": 2.958693733451015e-05,
+      "loss": 0.9764951705932617,
+      "step": 1130
+    },
+    {
+      "epoch": 0.31863601425476906,
+      "grad_norm": 0.26741188764572144,
+      "learning_rate": 2.956928508384819e-05,
+      "loss": 1.0414302825927735,
+      "step": 1140
+    },
+    {
+      "epoch": 0.32143106701138985,
+      "grad_norm": 0.30550289154052734,
+      "learning_rate": 2.955163283318623e-05,
+      "loss": 1.0412059783935548,
+      "step": 1150
+    },
+    {
+      "epoch": 0.32422611976801063,
+      "grad_norm": 0.27935805916786194,
+      "learning_rate": 2.953398058252427e-05,
+      "loss": 1.0061474800109864,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3270211725246314,
+      "grad_norm": 0.32680583000183105,
+      "learning_rate": 2.9516328331862312e-05,
+      "loss": 1.0311594009399414,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3298162252812522,
+      "grad_norm": 0.30033761262893677,
+      "learning_rate": 2.9498676081200353e-05,
+      "loss": 1.007315731048584,
+      "step": 1180
+    },
+    {
+      "epoch": 0.33261127803787294,
+      "grad_norm": 0.31935498118400574,
+      "learning_rate": 2.9481023830538394e-05,
+      "loss": 1.0023454666137694,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3354063307944937,
+      "grad_norm": 0.24859681725502014,
+      "learning_rate": 2.9463371579876435e-05,
+      "loss": 1.0599953651428222,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3382013835511145,
+      "grad_norm": 0.28637224435806274,
+      "learning_rate": 2.9445719329214476e-05,
+      "loss": 0.9715568542480468,
+      "step": 1210
+    },
+    {
+      "epoch": 0.3409964363077353,
+      "grad_norm": 0.3125148415565491,
+      "learning_rate": 2.9428067078552518e-05,
+      "loss": 1.0343916893005372,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3437914890643561,
+      "grad_norm": 0.31528884172439575,
+      "learning_rate": 2.941041482789056e-05,
+      "loss": 0.9525131225585938,
+      "step": 1230
+    },
+    {
+      "epoch": 0.34658654182097687,
+      "grad_norm": 0.24459350109100342,
+      "learning_rate": 2.9392762577228597e-05,
+      "loss": 1.0504046440124513,
+      "step": 1240
+    },
+    {
+      "epoch": 0.34938159457759765,
+      "grad_norm": 0.2881556749343872,
+      "learning_rate": 2.9375110326566638e-05,
+      "loss": 1.0129762649536134,
+      "step": 1250
+    },
+    {
+      "epoch": 0.35217664733421844,
+      "grad_norm": 0.25519442558288574,
+      "learning_rate": 2.935745807590468e-05,
+      "loss": 1.0512026786804198,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3549717000908392,
+      "grad_norm": 0.25984570384025574,
+      "learning_rate": 2.933980582524272e-05,
+      "loss": 0.9846024513244629,
+      "step": 1270
+    },
+    {
+      "epoch": 0.35776675284746,
+      "grad_norm": 0.28499749302864075,
+      "learning_rate": 2.932215357458076e-05,
+      "loss": 1.0733858108520509,
+      "step": 1280
+    },
+    {
+      "epoch": 0.3605618056040808,
+      "grad_norm": 0.29380694031715393,
+      "learning_rate": 2.9304501323918802e-05,
+      "loss": 0.9989897727966308,
+      "step": 1290
+    },
+    {
+      "epoch": 0.3633568583607016,
+      "grad_norm": 0.30164292454719543,
+      "learning_rate": 2.928684907325684e-05,
+      "loss": 1.0077524185180664,
+      "step": 1300
+    },
+    {
+      "epoch": 0.3661519111173223,
+      "grad_norm": 0.23782745003700256,
+      "learning_rate": 2.926919682259488e-05,
+      "loss": 1.0419427871704101,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3689469638739431,
+      "grad_norm": 0.22514177858829498,
+      "learning_rate": 2.9251544571932922e-05,
+      "loss": 1.0001588821411134,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3717420166305639,
+      "grad_norm": 0.2654188573360443,
+      "learning_rate": 2.9233892321270963e-05,
+      "loss": 0.9365455627441406,
+      "step": 1330
+    },
+    {
+      "epoch": 0.3745370693871847,
+      "grad_norm": 0.28745606541633606,
+      "learning_rate": 2.9216240070609e-05,
+      "loss": 1.0396409988403321,
+      "step": 1340
+    },
+    {
+      "epoch": 0.37733212214380546,
+      "grad_norm": 0.29193657636642456,
+      "learning_rate": 2.9198587819947042e-05,
+      "loss": 0.9870634078979492,
+      "step": 1350
+    },
+    {
+      "epoch": 0.38012717490042625,
+      "grad_norm": 0.3073195815086365,
+      "learning_rate": 2.9180935569285084e-05,
+      "loss": 0.9565372467041016,
+      "step": 1360
+    },
+    {
+      "epoch": 0.38292222765704703,
+      "grad_norm": 0.2933987081050873,
+      "learning_rate": 2.9163283318623125e-05,
+      "loss": 1.0597519874572754,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3857172804136678,
+      "grad_norm": 0.23969174921512604,
+      "learning_rate": 2.9145631067961166e-05,
+      "loss": 1.0359637260437011,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3885123331702886,
+      "grad_norm": 0.32519665360450745,
+      "learning_rate": 2.9127978817299207e-05,
+      "loss": 1.0731128692626952,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3913073859269094,
+      "grad_norm": 0.3296833634376526,
+      "learning_rate": 2.9110326566637248e-05,
+      "loss": 1.001913070678711,
+      "step": 1400
+    },
+    {
+      "epoch": 0.3941024386835302,
+      "grad_norm": 0.25598061084747314,
+      "learning_rate": 2.909267431597529e-05,
+      "loss": 1.0088472366333008,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3968974914401509,
+      "grad_norm": 0.2599712908267975,
+      "learning_rate": 2.907502206531333e-05,
+      "loss": 1.017747402191162,
+      "step": 1420
+    },
+    {
+      "epoch": 0.3996925441967717,
+      "grad_norm": 0.23938290774822235,
+      "learning_rate": 2.905736981465137e-05,
+      "loss": 1.041401481628418,
+      "step": 1430
+    },
+    {
+      "epoch": 0.4024875969533925,
+      "grad_norm": 0.273282527923584,
+      "learning_rate": 2.903971756398941e-05,
+      "loss": 1.0373397827148438,
+      "step": 1440
+    },
+    {
+      "epoch": 0.40528264971001327,
+      "grad_norm": 0.27002406120300293,
+      "learning_rate": 2.902206531332745e-05,
+      "loss": 1.0188671112060548,
+      "step": 1450
+    },
+    {
+      "epoch": 0.40807770246663405,
+      "grad_norm": 0.26821863651275635,
+      "learning_rate": 2.9004413062665488e-05,
+      "loss": 1.0574458122253418,
+      "step": 1460
+    },
+    {
+      "epoch": 0.41087275522325484,
+      "grad_norm": 0.2928693890571594,
+      "learning_rate": 2.898676081200353e-05,
+      "loss": 1.0109037399291991,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4136678079798756,
+      "grad_norm": 0.24917741119861603,
+      "learning_rate": 2.896910856134157e-05,
+      "loss": 0.9672279357910156,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4164628607364964,
+      "grad_norm": 0.30354684591293335,
+      "learning_rate": 2.895145631067961e-05,
+      "loss": 0.9972775459289551,
+      "step": 1490
+    },
+    {
+      "epoch": 0.4192579134931172,
+      "grad_norm": 0.28315505385398865,
+      "learning_rate": 2.8933804060017653e-05,
+      "loss": 1.052345085144043,
+      "step": 1500
+    },
+    {
+      "epoch": 0.422052966249738,
+      "grad_norm": 0.2571980953216553,
+      "learning_rate": 2.8916151809355694e-05,
+      "loss": 0.9936285972595215,
+      "step": 1510
+    },
+    {
+      "epoch": 0.42484801900635877,
+      "grad_norm": 0.26506495475769043,
+      "learning_rate": 2.8898499558693735e-05,
+      "loss": 1.0691999435424804,
+      "step": 1520
+    },
+    {
+      "epoch": 0.4276430717629795,
+      "grad_norm": 0.2906590402126312,
+      "learning_rate": 2.8880847308031776e-05,
+      "loss": 1.029029083251953,
+      "step": 1530
+    },
+    {
+      "epoch": 0.4304381245196003,
+      "grad_norm": 0.2804986536502838,
+      "learning_rate": 2.8863195057369814e-05,
+      "loss": 0.9693903923034668,
+      "step": 1540
+    },
+    {
+      "epoch": 0.43323317727622107,
+      "grad_norm": 0.3137750029563904,
+      "learning_rate": 2.8845542806707855e-05,
+      "loss": 0.9986073493957519,
+      "step": 1550
+    },
+    {
+      "epoch": 0.43602823003284186,
+      "grad_norm": 0.27715569734573364,
+      "learning_rate": 2.8827890556045896e-05,
+      "loss": 1.0288854598999024,
+      "step": 1560
+    },
+    {
+      "epoch": 0.43882328278946264,
+      "grad_norm": 0.3083079159259796,
+      "learning_rate": 2.8810238305383937e-05,
+      "loss": 1.0549062728881835,
+      "step": 1570
+    },
+    {
+      "epoch": 0.44161833554608343,
+      "grad_norm": 0.25902026891708374,
+      "learning_rate": 2.879258605472198e-05,
+      "loss": 1.0527615547180176,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4444133883027042,
+      "grad_norm": 0.28043800592422485,
+      "learning_rate": 2.877493380406002e-05,
+      "loss": 0.9656842231750489,
+      "step": 1590
+    },
+    {
+      "epoch": 0.447208441059325,
+      "grad_norm": 0.2748812735080719,
+      "learning_rate": 2.875728155339806e-05,
+      "loss": 0.9797506332397461,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4500034938159458,
+      "grad_norm": 0.24105726182460785,
+      "learning_rate": 2.8739629302736102e-05,
+      "loss": 1.0202052116394043,
+      "step": 1610
+    },
+    {
+      "epoch": 0.4527985465725666,
+      "grad_norm": 0.2766578495502472,
+      "learning_rate": 2.872197705207414e-05,
+      "loss": 1.0396312713623046,
+      "step": 1620
+    },
+    {
+      "epoch": 0.45559359932918736,
+      "grad_norm": 0.27033212780952454,
+      "learning_rate": 2.870432480141218e-05,
+      "loss": 1.015242862701416,
+      "step": 1630
+    },
+    {
+      "epoch": 0.45838865208580815,
+      "grad_norm": 0.2830497622489929,
+      "learning_rate": 2.868667255075022e-05,
+      "loss": 1.0283113479614259,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4611837048424289,
+      "grad_norm": 0.2722684442996979,
+      "learning_rate": 2.866902030008826e-05,
+      "loss": 0.960938549041748,
+      "step": 1650
+    },
+    {
+      "epoch": 0.46397875759904966,
+      "grad_norm": 0.2851269543170929,
+      "learning_rate": 2.86513680494263e-05,
+      "loss": 1.0592517852783203,
+      "step": 1660
+    },
+    {
+      "epoch": 0.46677381035567045,
+      "grad_norm": 0.3040626049041748,
+      "learning_rate": 2.8633715798764342e-05,
+      "loss": 1.027792263031006,
+      "step": 1670
+    },
+    {
+      "epoch": 0.46956886311229123,
+      "grad_norm": 0.27696627378463745,
+      "learning_rate": 2.8616063548102383e-05,
+      "loss": 1.0521678924560547,
+      "step": 1680
+    },
+    {
+      "epoch": 0.472363915868912,
+      "grad_norm": 0.2812741994857788,
+      "learning_rate": 2.8598411297440424e-05,
+      "loss": 1.0757858276367187,
+      "step": 1690
+    },
+    {
+      "epoch": 0.4751589686255328,
+      "grad_norm": 0.28111204504966736,
+      "learning_rate": 2.8580759046778466e-05,
+      "loss": 1.012517547607422,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4779540213821536,
+      "grad_norm": 0.23783713579177856,
+      "learning_rate": 2.8563106796116507e-05,
+      "loss": 1.0381376266479492,
+      "step": 1710
+    },
+    {
+      "epoch": 0.4807490741387744,
+      "grad_norm": 0.2889651954174042,
+      "learning_rate": 2.8545454545454548e-05,
+      "loss": 0.8898016929626464,
+      "step": 1720
+    },
+    {
+      "epoch": 0.48354412689539517,
+      "grad_norm": 0.29550856351852417,
+      "learning_rate": 2.852780229479259e-05,
+      "loss": 1.0425692558288575,
+      "step": 1730
+    },
+    {
+      "epoch": 0.48633917965201595,
+      "grad_norm": 0.21420054137706757,
+      "learning_rate": 2.851015004413063e-05,
+      "loss": 0.9967288970947266,
+      "step": 1740
+    },
+    {
+      "epoch": 0.48913423240863674,
+      "grad_norm": 0.2627513110637665,
+      "learning_rate": 2.8492497793468668e-05,
+      "loss": 0.9291762351989746,
+      "step": 1750
+    },
+    {
+      "epoch": 0.49192928516525747,
+      "grad_norm": 0.2861141264438629,
+      "learning_rate": 2.847484554280671e-05,
+      "loss": 1.0772159576416016,
+      "step": 1760
+    },
+    {
+      "epoch": 0.49472433792187825,
+      "grad_norm": 0.29838570952415466,
+      "learning_rate": 2.8457193292144747e-05,
+      "loss": 1.0173179626464843,
+      "step": 1770
+    },
+    {
+      "epoch": 0.49751939067849904,
+      "grad_norm": 0.24560388922691345,
+      "learning_rate": 2.8439541041482788e-05,
+      "loss": 1.045723819732666,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5003144434351199,
+      "grad_norm": 0.24704307317733765,
+      "learning_rate": 2.842188879082083e-05,
+      "loss": 0.9675786018371582,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5031094961917406,
+      "grad_norm": 0.2765197157859802,
+      "learning_rate": 2.840423654015887e-05,
+      "loss": 0.9299778938293457,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5059045489483615,
+      "grad_norm": 0.24500268697738647,
+      "learning_rate": 2.838658428949691e-05,
+      "loss": 0.9785917282104493,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5086996017049822,
+      "grad_norm": 0.29823580384254456,
+      "learning_rate": 2.8368932038834953e-05,
+      "loss": 0.9930375099182129,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5114946544616029,
+      "grad_norm": 0.26167577505111694,
+      "learning_rate": 2.8351279788172994e-05,
+      "loss": 0.9894954681396484,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5142897072182238,
+      "grad_norm": 0.29972001910209656,
+      "learning_rate": 2.8333627537511035e-05,
+      "loss": 0.9791035652160645,
+      "step": 1840
+    },
+    {
+      "epoch": 0.5170847599748445,
+      "grad_norm": 0.25320589542388916,
+      "learning_rate": 2.8315975286849073e-05,
+      "loss": 1.0297391891479493,
+      "step": 1850
+    },
+    {
+      "epoch": 0.5198798127314653,
+      "grad_norm": 0.2759966552257538,
+      "learning_rate": 2.8298323036187114e-05,
+      "loss": 1.0344117164611817,
+      "step": 1860
+    },
+    {
+      "epoch": 0.5226748654880861,
+      "grad_norm": 0.31191888451576233,
+      "learning_rate": 2.8280670785525155e-05,
+      "loss": 1.0009819984436035,
+      "step": 1870
+    },
+    {
+      "epoch": 0.5254699182447069,
+      "grad_norm": 0.28785309195518494,
+      "learning_rate": 2.8263018534863196e-05,
+      "loss": 1.0129854202270507,
+      "step": 1880
+    },
+    {
+      "epoch": 0.5282649710013276,
+      "grad_norm": 0.2400604784488678,
+      "learning_rate": 2.8245366284201237e-05,
+      "loss": 1.0410121917724608,
+      "step": 1890
+    },
+    {
+      "epoch": 0.5310600237579485,
+      "grad_norm": 0.24152550101280212,
+      "learning_rate": 2.8227714033539278e-05,
+      "loss": 0.9955686569213867,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5338550765145692,
+      "grad_norm": 0.2534623146057129,
+      "learning_rate": 2.821006178287732e-05,
+      "loss": 1.024580955505371,
+      "step": 1910
+    },
+    {
+      "epoch": 0.53665012927119,
+      "grad_norm": 0.23304277658462524,
+      "learning_rate": 2.819240953221536e-05,
+      "loss": 0.9629706382751465,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5394451820278108,
+      "grad_norm": 0.2977767288684845,
+      "learning_rate": 2.81747572815534e-05,
+      "loss": 1.0088661193847657,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5422402347844315,
+      "grad_norm": 0.23684540390968323,
+      "learning_rate": 2.815710503089144e-05,
+      "loss": 1.0221837043762207,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5450352875410523,
+      "grad_norm": 0.267940878868103,
+      "learning_rate": 2.8139452780229477e-05,
+      "loss": 1.0226426124572754,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5478303402976731,
+      "grad_norm": 0.28908538818359375,
+      "learning_rate": 2.812180052956752e-05,
+      "loss": 1.0010106086730957,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5506253930542939,
+      "grad_norm": 0.24775131046772003,
+      "learning_rate": 2.810414827890556e-05,
+      "loss": 1.0094176292419434,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5534204458109147,
+      "grad_norm": 0.22591879963874817,
+      "learning_rate": 2.80864960282436e-05,
+      "loss": 0.9766402244567871,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5562154985675355,
+      "grad_norm": 0.23937548696994781,
+      "learning_rate": 2.8068843777581642e-05,
+      "loss": 0.9925274848937988,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5590105513241562,
+      "grad_norm": 0.22813533246517181,
+      "learning_rate": 2.8051191526919683e-05,
+      "loss": 1.0093528747558593,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5618056040807771,
+      "grad_norm": 0.24084998667240143,
+      "learning_rate": 2.8033539276257724e-05,
+      "loss": 0.9568892478942871,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5646006568373978,
+      "grad_norm": 0.23621933162212372,
+      "learning_rate": 2.8015887025595765e-05,
+      "loss": 0.8862425804138183,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5673957095940186,
+      "grad_norm": 0.3026232123374939,
+      "learning_rate": 2.7998234774933806e-05,
+      "loss": 0.9181072235107421,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5701907623506394,
+      "grad_norm": 0.23941676318645477,
+      "learning_rate": 2.7980582524271848e-05,
+      "loss": 0.9964937210083008,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5729858151072601,
+      "grad_norm": 0.2133600264787674,
+      "learning_rate": 2.7962930273609885e-05,
+      "loss": 0.9572068214416504,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5757808678638809,
+      "grad_norm": 0.2363349348306656,
+      "learning_rate": 2.7945278022947926e-05,
+      "loss": 0.9120099067687988,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5785759206205017,
+      "grad_norm": 0.2861199975013733,
+      "learning_rate": 2.7927625772285968e-05,
+      "loss": 0.9934441566467285,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5813709733771225,
+      "grad_norm": 0.30457618832588196,
+      "learning_rate": 2.790997352162401e-05,
+      "loss": 1.0133195877075196,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5841660261337432,
+      "grad_norm": 0.29116353392601013,
+      "learning_rate": 2.7892321270962047e-05,
+      "loss": 1.0317489624023437,
+      "step": 2090
+    },
+    {
+      "epoch": 0.5869610788903641,
+      "grad_norm": 0.2552635669708252,
+      "learning_rate": 2.7874669020300088e-05,
+      "loss": 0.8719029426574707,
+      "step": 2100
+    },
+    {
+      "epoch": 0.5897561316469848,
+      "grad_norm": 0.24574051797389984,
+      "learning_rate": 2.785701676963813e-05,
+      "loss": 0.9595466613769531,
+      "step": 2110
+    },
+    {
+      "epoch": 0.5925511844036057,
+      "grad_norm": 0.2948808968067169,
+      "learning_rate": 2.783936451897617e-05,
+      "loss": 1.0388020515441894,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5953462371602264,
+      "grad_norm": 0.3055399954319,
+      "learning_rate": 2.782171226831421e-05,
+      "loss": 1.0131010055541991,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5981412899168472,
+      "grad_norm": 0.27569034695625305,
+      "learning_rate": 2.7804060017652252e-05,
+      "loss": 1.0485116958618164,
+      "step": 2140
+    },
+    {
+      "epoch": 0.600936342673468,
+      "grad_norm": 0.25929781794548035,
+      "learning_rate": 2.778640776699029e-05,
+      "loss": 0.9605886459350585,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6037313954300887,
+      "grad_norm": 0.2691594958305359,
+      "learning_rate": 2.776875551632833e-05,
+      "loss": 0.9345485687255859,
+      "step": 2160
+    },
+    {
+      "epoch": 0.6065264481867095,
+      "grad_norm": 0.266194224357605,
+      "learning_rate": 2.7751103265666372e-05,
+      "loss": 1.010661792755127,
+      "step": 2170
+    },
+    {
+      "epoch": 0.6093215009433303,
+      "grad_norm": 0.2730449438095093,
+      "learning_rate": 2.7733451015004413e-05,
+      "loss": 0.9402640342712403,
+      "step": 2180
+    },
+    {
+      "epoch": 0.6121165536999511,
+      "grad_norm": 0.24693098664283752,
+      "learning_rate": 2.7715798764342455e-05,
+      "loss": 0.9830196380615235,
+      "step": 2190
+    },
+    {
+      "epoch": 0.6149116064565718,
+      "grad_norm": 0.2656702697277069,
+      "learning_rate": 2.7698146513680496e-05,
+      "loss": 1.0225579261779785,
+      "step": 2200
+    },
+    {
+      "epoch": 0.6177066592131927,
+      "grad_norm": 0.23829874396324158,
+      "learning_rate": 2.7680494263018537e-05,
+      "loss": 0.943142032623291,
+      "step": 2210
+    },
+    {
+      "epoch": 0.6205017119698134,
+      "grad_norm": 0.2343863546848297,
+      "learning_rate": 2.7662842012356578e-05,
+      "loss": 0.9064154624938965,
+      "step": 2220
+    },
+    {
+      "epoch": 0.6232967647264342,
+      "grad_norm": 0.26842376589775085,
+      "learning_rate": 2.764518976169462e-05,
+      "loss": 0.9745256423950195,
+      "step": 2230
+    },
+    {
+      "epoch": 0.626091817483055,
+      "grad_norm": 0.2468368113040924,
+      "learning_rate": 2.762753751103266e-05,
+      "loss": 1.0400543212890625,
+      "step": 2240
+    },
+    {
+      "epoch": 0.6288868702396758,
+      "grad_norm": 0.2550053894519806,
+      "learning_rate": 2.7609885260370698e-05,
+      "loss": 1.0353093147277832,
+      "step": 2250
+    },
+    {
+      "epoch": 0.6316819229962966,
+      "grad_norm": 0.25663992762565613,
+      "learning_rate": 2.7592233009708736e-05,
+      "loss": 0.934177017211914,
+      "step": 2260
+    },
+    {
+      "epoch": 0.6344769757529173,
+      "grad_norm": 0.23147332668304443,
+      "learning_rate": 2.7574580759046777e-05,
+      "loss": 0.9813748359680176,
+      "step": 2270
+    },
+    {
+      "epoch": 0.6372720285095381,
+      "grad_norm": 0.2842564880847931,
+      "learning_rate": 2.7556928508384818e-05,
+      "loss": 0.9712874412536621,
+      "step": 2280
+    },
+    {
+      "epoch": 0.6400670812661589,
+      "grad_norm": 0.2781323492527008,
+      "learning_rate": 2.753927625772286e-05,
+      "loss": 0.9109337806701661,
+      "step": 2290
+    },
+    {
+      "epoch": 0.6428621340227797,
+      "grad_norm": 0.2820802927017212,
+      "learning_rate": 2.75216240070609e-05,
+      "loss": 0.9500028610229492,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6456571867794004,
+      "grad_norm": 0.22479397058486938,
+      "learning_rate": 2.750397175639894e-05,
+      "loss": 0.9440972328186035,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6484522395360213,
+      "grad_norm": 0.23917120695114136,
+      "learning_rate": 2.7486319505736983e-05,
+      "loss": 0.9791379928588867,
+      "step": 2320
+    },
+    {
+      "epoch": 0.651247292292642,
+      "grad_norm": 0.2782130837440491,
+      "learning_rate": 2.7468667255075024e-05,
+      "loss": 1.002306842803955,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6540423450492628,
+      "grad_norm": 0.2682194411754608,
+      "learning_rate": 2.7451015004413065e-05,
+      "loss": 1.0483274459838867,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6568373978058836,
+      "grad_norm": 0.25254103541374207,
+      "learning_rate": 2.7433362753751106e-05,
+      "loss": 0.9714167594909668,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6596324505625044,
+      "grad_norm": 0.2928752899169922,
+      "learning_rate": 2.7415710503089144e-05,
+      "loss": 1.0260162353515625,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6624275033191251,
+      "grad_norm": 0.26557931303977966,
+      "learning_rate": 2.7398058252427185e-05,
+      "loss": 1.0083256721496583,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6652225560757459,
+      "grad_norm": 0.2501239478588104,
+      "learning_rate": 2.7380406001765226e-05,
+      "loss": 0.8799171447753906,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6680176088323667,
+      "grad_norm": 0.2711493670940399,
+      "learning_rate": 2.7362753751103267e-05,
+      "loss": 0.9456501007080078,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6708126615889874,
+      "grad_norm": 0.26978161931037903,
+      "learning_rate": 2.734510150044131e-05,
+      "loss": 0.9659811973571777,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6736077143456083,
+      "grad_norm": 0.24001675844192505,
+      "learning_rate": 2.7327449249779346e-05,
+      "loss": 1.0193899154663086,
+      "step": 2410
+    },
+    {
+      "epoch": 0.676402767102229,
+      "grad_norm": 0.2932204008102417,
+      "learning_rate": 2.7309796999117387e-05,
+      "loss": 0.9731010437011719,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6791978198588499,
+      "grad_norm": 0.3117287755012512,
+      "learning_rate": 2.729214474845543e-05,
+      "loss": 0.9811773300170898,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6819928726154706,
+      "grad_norm": 0.2856774628162384,
+      "learning_rate": 2.727449249779347e-05,
+      "loss": 0.9740645408630371,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6847879253720914,
+      "grad_norm": 0.2622590959072113,
+      "learning_rate": 2.725684024713151e-05,
+      "loss": 1.0141623497009278,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6875829781287122,
+      "grad_norm": 0.25373291969299316,
+      "learning_rate": 2.723918799646955e-05,
+      "loss": 0.9394130706787109,
+      "step": 2460
+    },
+    {
+      "epoch": 0.690378030885333,
+      "grad_norm": 0.25906476378440857,
+      "learning_rate": 2.722153574580759e-05,
+      "loss": 1.022439670562744,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6931730836419537,
+      "grad_norm": 0.2625322639942169,
+      "learning_rate": 2.720388349514563e-05,
+      "loss": 1.0256818771362304,
+      "step": 2480
+    },
+    {
+      "epoch": 0.6959681363985746,
+      "grad_norm": 0.26505494117736816,
+      "learning_rate": 2.7186231244483672e-05,
+      "loss": 0.9361432075500489,
+      "step": 2490
+    },
+    {
+      "epoch": 0.6987631891551953,
+      "grad_norm": 0.2422180026769638,
+      "learning_rate": 2.7168578993821713e-05,
+      "loss": 0.9653936386108398,
+      "step": 2500
+    },
+    {
+      "epoch": 0.701558241911816,
+      "grad_norm": 0.2775800824165344,
+      "learning_rate": 2.7150926743159754e-05,
+      "loss": 0.9954863548278808,
+      "step": 2510
+    },
+    {
+      "epoch": 0.7043532946684369,
+      "grad_norm": 0.27944275736808777,
+      "learning_rate": 2.7133274492497795e-05,
+      "loss": 0.9623871803283691,
+      "step": 2520
+    },
+    {
+      "epoch": 0.7071483474250576,
+      "grad_norm": 0.28735777735710144,
+      "learning_rate": 2.7115622241835837e-05,
+      "loss": 0.9494200706481933,
+      "step": 2530
+    },
+    {
+      "epoch": 0.7099434001816785,
+      "grad_norm": 0.2936880886554718,
+      "learning_rate": 2.7097969991173878e-05,
+      "loss": 0.9977819442749023,
+      "step": 2540
+    },
+    {
+      "epoch": 0.7127384529382992,
+      "grad_norm": 0.24009165167808533,
+      "learning_rate": 2.708031774051192e-05,
+      "loss": 0.9474093437194824,
+      "step": 2550
+    },
+    {
+      "epoch": 0.71553350569492,
+      "grad_norm": 0.26245182752609253,
+      "learning_rate": 2.7062665489849957e-05,
+      "loss": 0.9796277046203613,
+      "step": 2560
+    },
+    {
+      "epoch": 0.7183285584515408,
+      "grad_norm": 0.2610528767108917,
+      "learning_rate": 2.7045013239187994e-05,
+      "loss": 1.0227899551391602,
+      "step": 2570
+    },
+    {
+      "epoch": 0.7211236112081616,
+      "grad_norm": 0.2596687376499176,
+      "learning_rate": 2.7027360988526036e-05,
+      "loss": 0.9537247657775879,
+      "step": 2580
+    },
+    {
+      "epoch": 0.7239186639647823,
+      "grad_norm": 0.2195677012205124,
+      "learning_rate": 2.7009708737864077e-05,
+      "loss": 0.9501275062561035,
+      "step": 2590
+    },
+    {
+      "epoch": 0.7267137167214032,
+      "grad_norm": 0.2544189691543579,
+      "learning_rate": 2.6992056487202118e-05,
+      "loss": 1.0224814414978027,
+      "step": 2600
+    },
+    {
+      "epoch": 0.7295087694780239,
+      "grad_norm": 0.2762031555175781,
+      "learning_rate": 2.697440423654016e-05,
+      "loss": 1.088548469543457,
+      "step": 2610
+    },
+    {
+      "epoch": 0.7323038222346446,
+      "grad_norm": 0.2782108783721924,
+      "learning_rate": 2.69567519858782e-05,
+      "loss": 0.974736213684082,
+      "step": 2620
+    },
+    {
+      "epoch": 0.7350988749912655,
+      "grad_norm": 0.30571404099464417,
+      "learning_rate": 2.693909973521624e-05,
+      "loss": 0.9846074104309082,
+      "step": 2630
+    },
+    {
+      "epoch": 0.7378939277478862,
+      "grad_norm": 0.2530606985092163,
+      "learning_rate": 2.6921447484554282e-05,
+      "loss": 1.0162484169006347,
+      "step": 2640
+    },
+    {
+      "epoch": 0.740688980504507,
+      "grad_norm": 0.2569025456905365,
+      "learning_rate": 2.6903795233892324e-05,
+      "loss": 0.9284350395202636,
+      "step": 2650
+    },
+    {
+      "epoch": 0.7434840332611278,
+      "grad_norm": 0.24733856320381165,
+      "learning_rate": 2.688614298323036e-05,
+      "loss": 0.9186759948730469,
+      "step": 2660
+    },
+    {
+      "epoch": 0.7462790860177486,
+      "grad_norm": 0.27425336837768555,
+      "learning_rate": 2.6868490732568402e-05,
+      "loss": 1.0373435974121095,
+      "step": 2670
+    },
+    {
+      "epoch": 0.7490741387743693,
+      "grad_norm": 0.25906410813331604,
+      "learning_rate": 2.6850838481906444e-05,
+      "loss": 0.9976903915405273,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7518691915309902,
+      "grad_norm": 0.2727071940898895,
+      "learning_rate": 2.6833186231244485e-05,
+      "loss": 1.0046795845031737,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7546642442876109,
+      "grad_norm": 0.26839467883110046,
+      "learning_rate": 2.6815533980582526e-05,
+      "loss": 0.9550431251525879,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7574592970442318,
+      "grad_norm": 0.27869123220443726,
+      "learning_rate": 2.6797881729920567e-05,
+      "loss": 1.0735899925231933,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7602543498008525,
+      "grad_norm": 0.2724617123603821,
+      "learning_rate": 2.6780229479258608e-05,
+      "loss": 0.9853955268859863,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7630494025574732,
+      "grad_norm": 0.2852199673652649,
+      "learning_rate": 2.6762577228596646e-05,
+      "loss": 0.9493398666381836,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7658444553140941,
+      "grad_norm": 0.28923094272613525,
+      "learning_rate": 2.6744924977934687e-05,
+      "loss": 0.9663130760192871,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7686395080707148,
+      "grad_norm": 0.295719712972641,
+      "learning_rate": 2.6727272727272728e-05,
+      "loss": 0.9795102119445801,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7714345608273356,
+      "grad_norm": 0.2401362806558609,
+      "learning_rate": 2.6709620476610766e-05,
+      "loss": 0.9830924034118652,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7742296135839564,
+      "grad_norm": 0.21877291798591614,
+      "learning_rate": 2.6691968225948807e-05,
+      "loss": 0.9561982154846191,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7770246663405772,
+      "grad_norm": 0.24706599116325378,
+      "learning_rate": 2.667431597528685e-05,
+      "loss": 0.9468561172485351,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7798197190971979,
+      "grad_norm": 0.30815020203590393,
+      "learning_rate": 2.665666372462489e-05,
+      "loss": 0.9948485374450684,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7826147718538188,
+      "grad_norm": 0.2928260564804077,
+      "learning_rate": 2.663901147396293e-05,
+      "loss": 0.95052490234375,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7854098246104395,
+      "grad_norm": 0.2835254669189453,
+      "learning_rate": 2.6621359223300972e-05,
+      "loss": 1.0023465156555176,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7882048773670604,
+      "grad_norm": 0.2268739491701126,
+      "learning_rate": 2.6603706972639013e-05,
+      "loss": 0.9253812789916992,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7909999301236811,
+      "grad_norm": 0.24687357246875763,
+      "learning_rate": 2.6586054721977054e-05,
+      "loss": 0.8779177665710449,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7937949828803018,
+      "grad_norm": 0.29058724641799927,
+      "learning_rate": 2.6568402471315095e-05,
+      "loss": 1.0069132804870606,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7965900356369227,
+      "grad_norm": 0.22541478276252747,
+      "learning_rate": 2.6550750220653136e-05,
+      "loss": 0.9553056716918945,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7993850883935434,
+      "grad_norm": 0.29543501138687134,
+      "learning_rate": 2.6533097969991174e-05,
+      "loss": 1.027346420288086,
+      "step": 2860
+    },
+    {
+      "epoch": 0.8021801411501642,
+      "grad_norm": 0.27390241622924805,
+      "learning_rate": 2.6515445719329215e-05,
+      "loss": 0.9783252716064453,
+      "step": 2870
+    },
+    {
+      "epoch": 0.804975193906785,
+      "grad_norm": 0.24834339320659637,
+      "learning_rate": 2.6497793468667256e-05,
+      "loss": 1.0231882095336915,
+      "step": 2880
+    },
+    {
+      "epoch": 0.8077702466634058,
+      "grad_norm": 0.250249981880188,
+      "learning_rate": 2.6480141218005294e-05,
+      "loss": 0.9661766052246094,
+      "step": 2890
+    },
+    {
+      "epoch": 0.8105652994200265,
+      "grad_norm": 0.27758678793907166,
+      "learning_rate": 2.6462488967343335e-05,
+      "loss": 0.9762771606445313,
+      "step": 2900
+    },
+    {
+      "epoch": 0.8133603521766474,
+      "grad_norm": 0.2580934464931488,
+      "learning_rate": 2.6444836716681376e-05,
+      "loss": 0.9904850959777832,
+      "step": 2910
+    },
+    {
+      "epoch": 0.8161554049332681,
+      "grad_norm": 0.2620713412761688,
+      "learning_rate": 2.6427184466019418e-05,
+      "loss": 0.948126220703125,
+      "step": 2920
+    },
+    {
+      "epoch": 0.8189504576898889,
+      "grad_norm": 0.2510469853878021,
+      "learning_rate": 2.640953221535746e-05,
+      "loss": 0.9975191116333008,
+      "step": 2930
+    },
+    {
+      "epoch": 0.8217455104465097,
+      "grad_norm": 0.30051833391189575,
+      "learning_rate": 2.63918799646955e-05,
+      "loss": 0.9524502754211426,
+      "step": 2940
+    },
+    {
+      "epoch": 0.8245405632031304,
+      "grad_norm": 0.2563886046409607,
+      "learning_rate": 2.637422771403354e-05,
+      "loss": 0.9865316390991211,
+      "step": 2950
+    },
+    {
+      "epoch": 0.8273356159597512,
+      "grad_norm": 0.2876911461353302,
+      "learning_rate": 2.6356575463371582e-05,
+      "loss": 0.9719761848449707,
+      "step": 2960
+    },
+    {
+      "epoch": 0.830130668716372,
+      "grad_norm": 0.2837851941585541,
+      "learning_rate": 2.633892321270962e-05,
+      "loss": 0.9687664985656739,
+      "step": 2970
+    },
+    {
+      "epoch": 0.8329257214729928,
+      "grad_norm": 0.2448406219482422,
+      "learning_rate": 2.632127096204766e-05,
+      "loss": 1.0187525749206543,
+      "step": 2980
+    },
+    {
+      "epoch": 0.8357207742296135,
+      "grad_norm": 0.2598477005958557,
+      "learning_rate": 2.6303618711385702e-05,
+      "loss": 0.9314325332641602,
+      "step": 2990
+    },
+    {
+      "epoch": 0.8385158269862344,
+      "grad_norm": 0.289228230714798,
+      "learning_rate": 2.6285966460723743e-05,
+      "loss": 1.0144015312194825,
+      "step": 3000
+    },
+    {
+      "epoch": 0.8413108797428551,
+      "grad_norm": 0.2784416973590851,
+      "learning_rate": 2.6268314210061785e-05,
+      "loss": 0.9686221122741699,
+      "step": 3010
+    },
+    {
+      "epoch": 0.844105932499476,
+      "grad_norm": 0.2573226988315582,
+      "learning_rate": 2.6250661959399826e-05,
+      "loss": 1.0380694389343261,
+      "step": 3020
+    },
+    {
+      "epoch": 0.8469009852560967,
+      "grad_norm": 0.29329171776771545,
+      "learning_rate": 2.6233009708737867e-05,
+      "loss": 0.9407861709594727,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8496960380127175,
+      "grad_norm": 0.2668832540512085,
+      "learning_rate": 2.6215357458075908e-05,
+      "loss": 0.9378229141235351,
+      "step": 3040
+    },
+    {
+      "epoch": 0.8524910907693383,
+      "grad_norm": 0.25152280926704407,
+      "learning_rate": 2.6197705207413946e-05,
+      "loss": 0.9678263664245605,
+      "step": 3050
+    },
+    {
+      "epoch": 0.855286143525959,
+      "grad_norm": 0.2694884240627289,
+      "learning_rate": 2.6180052956751987e-05,
+      "loss": 0.9072006225585938,
+      "step": 3060
+    },
+    {
+      "epoch": 0.8580811962825798,
+      "grad_norm": 0.2215639352798462,
+      "learning_rate": 2.6162400706090025e-05,
+      "loss": 1.017903709411621,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8608762490392006,
+      "grad_norm": 0.27085110545158386,
+      "learning_rate": 2.6144748455428066e-05,
+      "loss": 0.9469708442687989,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8636713017958214,
+      "grad_norm": 0.2667694091796875,
+      "learning_rate": 2.6127096204766107e-05,
+      "loss": 0.9949071884155274,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8664663545524421,
+      "grad_norm": 0.3139512836933136,
+      "learning_rate": 2.6109443954104148e-05,
+      "loss": 0.9318760871887207,
+      "step": 3100
+    },
+    {
+      "epoch": 0.869261407309063,
+      "grad_norm": 0.2578687071800232,
+      "learning_rate": 2.609179170344219e-05,
+      "loss": 0.9587287902832031,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8720564600656837,
+      "grad_norm": 0.25773486495018005,
+      "learning_rate": 2.607413945278023e-05,
+      "loss": 0.922269630432129,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8748515128223046,
+      "grad_norm": 0.24266088008880615,
+      "learning_rate": 2.605648720211827e-05,
+      "loss": 0.9688119888305664,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8776465655789253,
+      "grad_norm": 0.26375895738601685,
+      "learning_rate": 2.6038834951456313e-05,
+      "loss": 0.9974651336669922,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8804416183355461,
+      "grad_norm": 0.26057514548301697,
+      "learning_rate": 2.6021182700794354e-05,
+      "loss": 0.9487582206726074,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8832366710921669,
+      "grad_norm": 0.26842471957206726,
+      "learning_rate": 2.6003530450132395e-05,
+      "loss": 0.9565431594848632,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8860317238487877,
+      "grad_norm": 0.2577967047691345,
+      "learning_rate": 2.5985878199470433e-05,
+      "loss": 0.990451717376709,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8888267766054084,
+      "grad_norm": 0.2923356294631958,
+      "learning_rate": 2.5968225948808474e-05,
+      "loss": 0.9503488540649414,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8916218293620292,
+      "grad_norm": 0.31514692306518555,
+      "learning_rate": 2.5950573698146515e-05,
+      "loss": 0.9986662864685059,
+      "step": 3190
+    },
+    {
+      "epoch": 0.89441688211865,
+      "grad_norm": 0.26433926820755005,
+      "learning_rate": 2.5932921447484553e-05,
+      "loss": 0.9942965507507324,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8972119348752707,
+      "grad_norm": 0.25231367349624634,
+      "learning_rate": 2.5915269196822594e-05,
+      "loss": 0.9757192611694336,
+      "step": 3210
+    },
+    {
+      "epoch": 0.9000069876318916,
+      "grad_norm": 0.28670942783355713,
+      "learning_rate": 2.5897616946160635e-05,
+      "loss": 1.010460662841797,
+      "step": 3220
+    },
+    {
+      "epoch": 0.9028020403885123,
+      "grad_norm": 0.22908306121826172,
+      "learning_rate": 2.5879964695498676e-05,
+      "loss": 0.9534653663635254,
+      "step": 3230
+    },
+    {
+      "epoch": 0.9055970931451331,
+      "grad_norm": 0.26819711923599243,
+      "learning_rate": 2.5862312444836717e-05,
+      "loss": 0.921439266204834,
+      "step": 3240
+    },
+    {
+      "epoch": 0.9083921459017539,
+      "grad_norm": 0.24798987805843353,
+      "learning_rate": 2.584466019417476e-05,
+      "loss": 0.9415060997009277,
+      "step": 3250
+    },
+    {
+      "epoch": 0.9111871986583747,
+      "grad_norm": 0.2548549771308899,
+      "learning_rate": 2.58270079435128e-05,
+      "loss": 1.1272334098815917,
+      "step": 3260
+    },
+    {
+      "epoch": 0.9139822514149955,
+      "grad_norm": 0.2839723825454712,
+      "learning_rate": 2.5809355692850837e-05,
+      "loss": 0.9753469467163086,
+      "step": 3270
+    },
+    {
+      "epoch": 0.9167773041716163,
+      "grad_norm": 0.27934613823890686,
+      "learning_rate": 2.579170344218888e-05,
+      "loss": 0.9586450576782226,
+      "step": 3280
+    },
+    {
+      "epoch": 0.919572356928237,
+      "grad_norm": 0.2402600646018982,
+      "learning_rate": 2.577405119152692e-05,
+      "loss": 1.019408893585205,
+      "step": 3290
+    },
+    {
+      "epoch": 0.9223674096848578,
+      "grad_norm": 0.28812214732170105,
+      "learning_rate": 2.575639894086496e-05,
+      "loss": 0.9838976860046387,
+      "step": 3300
+    },
+    {
+      "epoch": 0.9251624624414786,
+      "grad_norm": 0.21850886940956116,
+      "learning_rate": 2.5738746690203002e-05,
+      "loss": 0.9522347450256348,
+      "step": 3310
+    },
+    {
+      "epoch": 0.9279575151980993,
+      "grad_norm": 0.266902893781662,
+      "learning_rate": 2.5721094439541043e-05,
+      "loss": 0.9286007881164551,
+      "step": 3320
+    },
+    {
+      "epoch": 0.9307525679547202,
+      "grad_norm": 0.25756779313087463,
+      "learning_rate": 2.5703442188879084e-05,
+      "loss": 0.8901268005371094,
+      "step": 3330
+    },
+    {
+      "epoch": 0.9335476207113409,
+      "grad_norm": 0.24394448101520538,
+      "learning_rate": 2.5685789938217125e-05,
+      "loss": 0.9559040069580078,
+      "step": 3340
+    },
+    {
+      "epoch": 0.9363426734679617,
+      "grad_norm": 0.2422792613506317,
+      "learning_rate": 2.5668137687555167e-05,
+      "loss": 1.0175907135009765,
+      "step": 3350
+    },
+    {
+      "epoch": 0.9391377262245825,
+      "grad_norm": 0.2847517132759094,
+      "learning_rate": 2.5650485436893204e-05,
+      "loss": 0.9294634819030761,
+      "step": 3360
+    },
+    {
+      "epoch": 0.9419327789812033,
+      "grad_norm": 0.22152088582515717,
+      "learning_rate": 2.5632833186231242e-05,
+      "loss": 0.9412069320678711,
+      "step": 3370
+    },
+    {
+      "epoch": 0.944727831737824,
+      "grad_norm": 0.2812557518482208,
+      "learning_rate": 2.5615180935569283e-05,
+      "loss": 0.9728023529052734,
+      "step": 3380
+    },
+    {
+      "epoch": 0.9475228844944449,
+      "grad_norm": 0.22737649083137512,
+      "learning_rate": 2.5597528684907324e-05,
+      "loss": 1.0076075553894044,
+      "step": 3390
+    },
+    {
+      "epoch": 0.9503179372510656,
+      "grad_norm": 0.2991273105144501,
+      "learning_rate": 2.5579876434245365e-05,
+      "loss": 0.9727883338928223,
+      "step": 3400
+    },
+    {
+      "epoch": 0.9531129900076863,
+      "grad_norm": 0.2813841700553894,
+      "learning_rate": 2.5562224183583407e-05,
+      "loss": 1.0197256088256836,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9559080427643072,
+      "grad_norm": 0.2415975034236908,
+      "learning_rate": 2.5544571932921448e-05,
+      "loss": 0.984050178527832,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9587030955209279,
+      "grad_norm": 0.2696859836578369,
+      "learning_rate": 2.552691968225949e-05,
+      "loss": 0.9838951110839844,
+      "step": 3430
+    },
+    {
+      "epoch": 0.9614981482775488,
+      "grad_norm": 0.2510502338409424,
+      "learning_rate": 2.550926743159753e-05,
+      "loss": 0.9829157829284668,
+      "step": 3440
+    },
+    {
+      "epoch": 0.9642932010341695,
+      "grad_norm": 0.2660929560661316,
+      "learning_rate": 2.549161518093557e-05,
+      "loss": 1.0031258583068847,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9670882537907903,
+      "grad_norm": 0.24025480449199677,
+      "learning_rate": 2.5473962930273612e-05,
+      "loss": 1.0306617736816406,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9698833065474111,
+      "grad_norm": 0.2683681547641754,
+      "learning_rate": 2.5456310679611653e-05,
+      "loss": 0.9578551292419434,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9726783593040319,
+      "grad_norm": 0.2383909821510315,
+      "learning_rate": 2.543865842894969e-05,
+      "loss": 1.0200163841247558,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9754734120606526,
+      "grad_norm": 0.26530158519744873,
+      "learning_rate": 2.5421006178287732e-05,
+      "loss": 0.895325756072998,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9782684648172735,
+      "grad_norm": 0.2723603844642639,
+      "learning_rate": 2.5403353927625774e-05,
+      "loss": 0.9434194564819336,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9810635175738942,
+      "grad_norm": 0.258129358291626,
+      "learning_rate": 2.5385701676963815e-05,
+      "loss": 0.9840938568115234,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9838585703305149,
+      "grad_norm": 0.2922714650630951,
+      "learning_rate": 2.5368049426301852e-05,
+      "loss": 0.972865104675293,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9866536230871358,
+      "grad_norm": 0.2598571181297302,
+      "learning_rate": 2.5350397175639894e-05,
+      "loss": 0.9674478530883789,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9894486758437565,
+      "grad_norm": 0.2545435428619385,
+      "learning_rate": 2.5332744924977935e-05,
+      "loss": 1.0111292839050292,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9922437286003774,
+      "grad_norm": 0.27518677711486816,
+      "learning_rate": 2.5315092674315976e-05,
+      "loss": 0.9681413650512696,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9950387813569981,
+      "grad_norm": 0.25355812907218933,
+      "learning_rate": 2.5297440423654017e-05,
+      "loss": 0.9298019409179688,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9978338341136189,
+      "grad_norm": 0.25585663318634033,
+      "learning_rate": 2.5279788172992058e-05,
+      "loss": 1.0329684257507323,
+      "step": 3570
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.9194258451461792,
+      "eval_runtime": 125.1354,
+      "eval_samples_per_second": 18.668,
+      "eval_steps_per_second": 9.334,
+      "step": 3578
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 17890,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8733868226500198e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35d7b3fceb17e8d6b83421fc3bb116fe7af1b40606cb202590601db90e9e11cd
+size 5201