Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ 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
+checkpoint-2800/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,15 +1,64 @@
 ---
-license: cc-by-nc-4.0
+library_name: peft
+license: other
+base_model: Qwen/Qwen3-4B-Base
 tags:
-- mhm
-- text-generation
-library_name: transformers
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- llama-factory
+- lora
+- transformers
+pipeline_tag: text-generation
+model-index:
+- name: qwen3-4b-base-lingcoder-shortcot-4k-lora
+  results: []
 ---
 
-# qwen3_4b_base_lingcoder_shortcot_4k_lora
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
-Auto-uploaded by watcher (MergeBench excluded).
+# qwen3-4b-base-lingcoder-shortcot-4k-lora
 
-- Source path: `LlamaFactory/saves/restart/qwen3-4b-base-lingcoder-shortcot-4k-lora`
-- Uploaded at: `2026-05-22T09:21:03.997218`
-- Visibility: `public`
+This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the restart_lingcoder_shortcot_fixed200k_4k dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0001
+- train_batch_size: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 64
+- total_eval_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 0.05
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- PEFT 0.18.1
+- Transformers 5.2.0
+- Pytorch 2.11.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2

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/Qwen3-4B-Base",
+  "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": 64,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.3887930550675046e+18,
+    "train_loss": 0.4842414558126453,
+    "train_runtime": 8903.7116,
+    "train_samples_per_second": 22.238,
+    "train_steps_per_second": 0.347
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-2600/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- llama-factory
+- 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

checkpoint-2600/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/Qwen3-4B-Base",
+  "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": 64,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2600/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-2600/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2ca72af68ddcff4fb2a7a7fed3614813e8ed42bca8d8cdd17aa1d40ea18d2e2b
+size 528915403

checkpoint-2600/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6985d25a564d320d3f3a94656a8228ba8059694dd249ee6c2827a00e604289db
+size 15429

checkpoint-2600/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:448e60531f3436fa4cbfcfb944732ced2b1f531a0191ebe216986da1e6b08400
+size 15429

checkpoint-2600/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9421084ad4f505094979da922b4873721d2ef438bfaccf73f8a06ff77f315c53
+size 15429

checkpoint-2600/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3d1c40be223a9b3afc8cfae2a846ba09048725fc7ae780ba525ceaea45ee66a
+size 15429

checkpoint-2600/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:616fff79ddb34a58210a03175260c74366a4c27cf26656fd828d305098d08d79
+size 1465

checkpoint-2600/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2600/trainer_state.json

@@ -0,0 +1,1854 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.8404040404040404,
+  "eval_steps": 200,
+  "global_step": 2600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032323232323232323,
+      "grad_norm": 0.032284051179885864,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.6013355255126953,
+      "step": 10
+    },
+    {
+      "epoch": 0.006464646464646465,
+      "grad_norm": 0.01937970519065857,
+      "learning_rate": 1.2258064516129032e-05,
+      "loss": 0.5758121490478516,
+      "step": 20
+    },
+    {
+      "epoch": 0.009696969696969697,
+      "grad_norm": 0.014327733777463436,
+      "learning_rate": 1.870967741935484e-05,
+      "loss": 0.5787662506103516,
+      "step": 30
+    },
+    {
+      "epoch": 0.01292929292929293,
+      "grad_norm": 0.012254982255399227,
+      "learning_rate": 2.5161290322580645e-05,
+      "loss": 0.5327143669128418,
+      "step": 40
+    },
+    {
+      "epoch": 0.01616161616161616,
+      "grad_norm": 0.014536243863403797,
+      "learning_rate": 3.161290322580645e-05,
+      "loss": 0.5393171310424805,
+      "step": 50
+    },
+    {
+      "epoch": 0.019393939393939394,
+      "grad_norm": 0.011900736019015312,
+      "learning_rate": 3.8064516129032254e-05,
+      "loss": 0.5058945178985595,
+      "step": 60
+    },
+    {
+      "epoch": 0.022626262626262626,
+      "grad_norm": 0.01210293360054493,
+      "learning_rate": 4.451612903225807e-05,
+      "loss": 0.517607593536377,
+      "step": 70
+    },
+    {
+      "epoch": 0.02585858585858586,
+      "grad_norm": 0.017207792028784752,
+      "learning_rate": 5.096774193548387e-05,
+      "loss": 0.5269095420837402,
+      "step": 80
+    },
+    {
+      "epoch": 0.02909090909090909,
+      "grad_norm": 0.013736969791352749,
+      "learning_rate": 5.7419354838709685e-05,
+      "loss": 0.5040688514709473,
+      "step": 90
+    },
+    {
+      "epoch": 0.03232323232323232,
+      "grad_norm": 0.011664404533803463,
+      "learning_rate": 6.387096774193548e-05,
+      "loss": 0.5147775173187256,
+      "step": 100
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 0.014052552171051502,
+      "learning_rate": 7.03225806451613e-05,
+      "loss": 0.5230005741119385,
+      "step": 110
+    },
+    {
+      "epoch": 0.03878787878787879,
+      "grad_norm": 0.011644740588963032,
+      "learning_rate": 7.67741935483871e-05,
+      "loss": 0.5105222702026367,
+      "step": 120
+    },
+    {
+      "epoch": 0.04202020202020202,
+      "grad_norm": 0.011730308644473553,
+      "learning_rate": 8.32258064516129e-05,
+      "loss": 0.4989170074462891,
+      "step": 130
+    },
+    {
+      "epoch": 0.04525252525252525,
+      "grad_norm": 0.012009115889668465,
+      "learning_rate": 8.967741935483871e-05,
+      "loss": 0.5003124713897705,
+      "step": 140
+    },
+    {
+      "epoch": 0.048484848484848485,
+      "grad_norm": 0.012424134649336338,
+      "learning_rate": 9.612903225806452e-05,
+      "loss": 0.5077538013458252,
+      "step": 150
+    },
+    {
+      "epoch": 0.05171717171717172,
+      "grad_norm": 0.011461800895631313,
+      "learning_rate": 9.999954295400999e-05,
+      "loss": 0.5061477661132813,
+      "step": 160
+    },
+    {
+      "epoch": 0.05494949494949495,
+      "grad_norm": 0.011583201587200165,
+      "learning_rate": 9.999440128258112e-05,
+      "loss": 0.5013481140136719,
+      "step": 170
+    },
+    {
+      "epoch": 0.05818181818181818,
+      "grad_norm": 0.011583367362618446,
+      "learning_rate": 9.998354722168459e-05,
+      "loss": 0.48343815803527834,
+      "step": 180
+    },
+    {
+      "epoch": 0.061414141414141414,
+      "grad_norm": 0.011094105429947376,
+      "learning_rate": 9.996698201151175e-05,
+      "loss": 0.507840633392334,
+      "step": 190
+    },
+    {
+      "epoch": 0.06464646464646465,
+      "grad_norm": 0.011715452186763287,
+      "learning_rate": 9.994470754481315e-05,
+      "loss": 0.49884777069091796,
+      "step": 200
+    },
+    {
+      "epoch": 0.06787878787878789,
+      "grad_norm": 0.010746965184807777,
+      "learning_rate": 9.991672636668239e-05,
+      "loss": 0.5068713188171386,
+      "step": 210
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.012883410789072514,
+      "learning_rate": 9.988304167426519e-05,
+      "loss": 0.4920186519622803,
+      "step": 220
+    },
+    {
+      "epoch": 0.07434343434343435,
+      "grad_norm": 0.011187366209924221,
+      "learning_rate": 9.984365731639419e-05,
+      "loss": 0.5021648406982422,
+      "step": 230
+    },
+    {
+      "epoch": 0.07757575757575758,
+      "grad_norm": 0.010671757161617279,
+      "learning_rate": 9.979857779314906e-05,
+      "loss": 0.5038897514343261,
+      "step": 240
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.01044373121112585,
+      "learning_rate": 9.974780825534246e-05,
+      "loss": 0.4965065956115723,
+      "step": 250
+    },
+    {
+      "epoch": 0.08404040404040404,
+      "grad_norm": 0.010565251111984253,
+      "learning_rate": 9.969135450393141e-05,
+      "loss": 0.5145994186401367,
+      "step": 260
+    },
+    {
+      "epoch": 0.08727272727272728,
+      "grad_norm": 0.010024026967585087,
+      "learning_rate": 9.96292229893545e-05,
+      "loss": 0.505019235610962,
+      "step": 270
+    },
+    {
+      "epoch": 0.0905050505050505,
+      "grad_norm": 0.010430407710373402,
+      "learning_rate": 9.956142081079484e-05,
+      "loss": 0.5115808010101318,
+      "step": 280
+    },
+    {
+      "epoch": 0.09373737373737374,
+      "grad_norm": 0.010048807598650455,
+      "learning_rate": 9.948795571536891e-05,
+      "loss": 0.48525152206420896,
+      "step": 290
+    },
+    {
+      "epoch": 0.09696969696969697,
+      "grad_norm": 0.010108387097716331,
+      "learning_rate": 9.94088360972414e-05,
+      "loss": 0.5002010822296142,
+      "step": 300
+    },
+    {
+      "epoch": 0.10020202020202021,
+      "grad_norm": 0.010273640975356102,
+      "learning_rate": 9.932407099666608e-05,
+      "loss": 0.49662046432495116,
+      "step": 310
+    },
+    {
+      "epoch": 0.10343434343434343,
+      "grad_norm": 0.00995971355587244,
+      "learning_rate": 9.923367009895274e-05,
+      "loss": 0.48578290939331054,
+      "step": 320
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.010459775105118752,
+      "learning_rate": 9.913764373336079e-05,
+      "loss": 0.48862767219543457,
+      "step": 330
+    },
+    {
+      "epoch": 0.1098989898989899,
+      "grad_norm": 0.009838269092142582,
+      "learning_rate": 9.903600287191875e-05,
+      "loss": 0.5034208774566651,
+      "step": 340
+    },
+    {
+      "epoch": 0.11313131313131314,
+      "grad_norm": 0.00978950597345829,
+      "learning_rate": 9.892875912817079e-05,
+      "loss": 0.4870161533355713,
+      "step": 350
+    },
+    {
+      "epoch": 0.11636363636363636,
+      "grad_norm": 0.01030043140053749,
+      "learning_rate": 9.881592475584964e-05,
+      "loss": 0.5026071548461915,
+      "step": 360
+    },
+    {
+      "epoch": 0.1195959595959596,
+      "grad_norm": 0.010531975887715816,
+      "learning_rate": 9.869751264747656e-05,
+      "loss": 0.4883917808532715,
+      "step": 370
+    },
+    {
+      "epoch": 0.12282828282828283,
+      "grad_norm": 0.00986825954169035,
+      "learning_rate": 9.857353633288814e-05,
+      "loss": 0.4927018165588379,
+      "step": 380
+    },
+    {
+      "epoch": 0.12606060606060607,
+      "grad_norm": 0.009432349354028702,
+      "learning_rate": 9.844400997769043e-05,
+      "loss": 0.4908174514770508,
+      "step": 390
+    },
+    {
+      "epoch": 0.1292929292929293,
+      "grad_norm": 0.01057665515691042,
+      "learning_rate": 9.83089483816404e-05,
+      "loss": 0.5069625854492188,
+      "step": 400
+    },
+    {
+      "epoch": 0.13252525252525252,
+      "grad_norm": 0.010007908567786217,
+      "learning_rate": 9.816836697695482e-05,
+      "loss": 0.4988056182861328,
+      "step": 410
+    },
+    {
+      "epoch": 0.13575757575757577,
+      "grad_norm": 0.010027808137238026,
+      "learning_rate": 9.802228182654702e-05,
+      "loss": 0.5007385730743408,
+      "step": 420
+    },
+    {
+      "epoch": 0.138989898989899,
+      "grad_norm": 0.009953738190233707,
+      "learning_rate": 9.787070962219156e-05,
+      "loss": 0.5130783081054687,
+      "step": 430
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.010204462334513664,
+      "learning_rate": 9.771366768261696e-05,
+      "loss": 0.4947535514831543,
+      "step": 440
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 0.009612451307475567,
+      "learning_rate": 9.755117395152689e-05,
+      "loss": 0.4917112350463867,
+      "step": 450
+    },
+    {
+      "epoch": 0.1486868686868687,
+      "grad_norm": 0.00995573028922081,
+      "learning_rate": 9.73832469955499e-05,
+      "loss": 0.4882859230041504,
+      "step": 460
+    },
+    {
+      "epoch": 0.15191919191919193,
+      "grad_norm": 0.009584570303559303,
+      "learning_rate": 9.720990600211797e-05,
+      "loss": 0.500526762008667,
+      "step": 470
+    },
+    {
+      "epoch": 0.15515151515151515,
+      "grad_norm": 0.010585076175630093,
+      "learning_rate": 9.703117077727419e-05,
+      "loss": 0.496882963180542,
+      "step": 480
+    },
+    {
+      "epoch": 0.15838383838383838,
+      "grad_norm": 0.009859723038971424,
+      "learning_rate": 9.684706174340965e-05,
+      "loss": 0.48728485107421876,
+      "step": 490
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.010212041437625885,
+      "learning_rate": 9.665759993693e-05,
+      "loss": 0.49378366470336915,
+      "step": 500
+    },
+    {
+      "epoch": 0.16484848484848486,
+      "grad_norm": 0.009744231589138508,
+      "learning_rate": 9.646280700585185e-05,
+      "loss": 0.4663555145263672,
+      "step": 510
+    },
+    {
+      "epoch": 0.16808080808080808,
+      "grad_norm": 0.009789686650037766,
+      "learning_rate": 9.626270520732916e-05,
+      "loss": 0.4879913330078125,
+      "step": 520
+    },
+    {
+      "epoch": 0.1713131313131313,
+      "grad_norm": 0.009891769848763943,
+      "learning_rate": 9.605731740511022e-05,
+      "loss": 0.48809428215026857,
+      "step": 530
+    },
+    {
+      "epoch": 0.17454545454545456,
+      "grad_norm": 0.01002143882215023,
+      "learning_rate": 9.584666706692517e-05,
+      "loss": 0.4959606170654297,
+      "step": 540
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.009208496659994125,
+      "learning_rate": 9.56307782618046e-05,
+      "loss": 0.4878594398498535,
+      "step": 550
+    },
+    {
+      "epoch": 0.181010101010101,
+      "grad_norm": 0.009645081125199795,
+      "learning_rate": 9.540967565732937e-05,
+      "loss": 0.4769869804382324,
+      "step": 560
+    },
+    {
+      "epoch": 0.18424242424242424,
+      "grad_norm": 0.010497638955712318,
+      "learning_rate": 9.51833845168121e-05,
+      "loss": 0.4970097064971924,
+      "step": 570
+    },
+    {
+      "epoch": 0.1874747474747475,
+      "grad_norm": 0.010612033307552338,
+      "learning_rate": 9.495193069641057e-05,
+      "loss": 0.4945381164550781,
+      "step": 580
+    },
+    {
+      "epoch": 0.1907070707070707,
+      "grad_norm": 0.009433986619114876,
+      "learning_rate": 9.47153406421734e-05,
+      "loss": 0.4860210418701172,
+      "step": 590
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 0.009995914995670319,
+      "learning_rate": 9.447364138701823e-05,
+      "loss": 0.4904911994934082,
+      "step": 600
+    },
+    {
+      "epoch": 0.19717171717171716,
+      "grad_norm": 0.009814019314944744,
+      "learning_rate": 9.422686054764302e-05,
+      "loss": 0.4915336608886719,
+      "step": 610
+    },
+    {
+      "epoch": 0.20040404040404042,
+      "grad_norm": 0.010199982672929764,
+      "learning_rate": 9.397502632137055e-05,
+      "loss": 0.4805011749267578,
+      "step": 620
+    },
+    {
+      "epoch": 0.20363636363636364,
+      "grad_norm": 0.010121874511241913,
+      "learning_rate": 9.371816748292641e-05,
+      "loss": 0.47633209228515627,
+      "step": 630
+    },
+    {
+      "epoch": 0.20686868686868687,
+      "grad_norm": 0.009638865478336811,
+      "learning_rate": 9.345631338115141e-05,
+      "loss": 0.48993511199951173,
+      "step": 640
+    },
+    {
+      "epoch": 0.2101010101010101,
+      "grad_norm": 0.010041174478828907,
+      "learning_rate": 9.318949393564807e-05,
+      "loss": 0.4798978328704834,
+      "step": 650
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.010145517997443676,
+      "learning_rate": 9.291773963336193e-05,
+      "loss": 0.4696659564971924,
+      "step": 660
+    },
+    {
+      "epoch": 0.21656565656565657,
+      "grad_norm": 0.01043335534632206,
+      "learning_rate": 9.264108152509816e-05,
+      "loss": 0.4955574035644531,
+      "step": 670
+    },
+    {
+      "epoch": 0.2197979797979798,
+      "grad_norm": 0.010406569577753544,
+      "learning_rate": 9.235955122197368e-05,
+      "loss": 0.48659563064575195,
+      "step": 680
+    },
+    {
+      "epoch": 0.22303030303030302,
+      "grad_norm": 0.009870355017483234,
+      "learning_rate": 9.207318089180524e-05,
+      "loss": 0.4766091823577881,
+      "step": 690
+    },
+    {
+      "epoch": 0.22626262626262628,
+      "grad_norm": 0.009980005212128162,
+      "learning_rate": 9.178200325543384e-05,
+      "loss": 0.5022068023681641,
+      "step": 700
+    },
+    {
+      "epoch": 0.2294949494949495,
+      "grad_norm": 0.009765878319740295,
+      "learning_rate": 9.148605158298621e-05,
+      "loss": 0.48309478759765623,
+      "step": 710
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.009879437275230885,
+      "learning_rate": 9.118535969007314e-05,
+      "loss": 0.4793684959411621,
+      "step": 720
+    },
+    {
+      "epoch": 0.23595959595959595,
+      "grad_norm": 0.009907045401632786,
+      "learning_rate": 9.087996193392578e-05,
+      "loss": 0.49844112396240237,
+      "step": 730
+    },
+    {
+      "epoch": 0.2391919191919192,
+      "grad_norm": 0.009958872571587563,
+      "learning_rate": 9.056989320947e-05,
+      "loss": 0.48113102912902833,
+      "step": 740
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.010206855833530426,
+      "learning_rate": 9.025518894533921e-05,
+      "loss": 0.5048784255981446,
+      "step": 750
+    },
+    {
+      "epoch": 0.24565656565656566,
+      "grad_norm": 0.009286429733037949,
+      "learning_rate": 8.99358850998263e-05,
+      "loss": 0.4862624168395996,
+      "step": 760
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.009919015690684319,
+      "learning_rate": 8.9612018156775e-05,
+      "loss": 0.48739056587219237,
+      "step": 770
+    },
+    {
+      "epoch": 0.25212121212121213,
+      "grad_norm": 0.010435211472213268,
+      "learning_rate": 8.928362512141124e-05,
+      "loss": 0.48689990043640136,
+      "step": 780
+    },
+    {
+      "epoch": 0.25535353535353533,
+      "grad_norm": 0.009992080740630627,
+      "learning_rate": 8.895074351611488e-05,
+      "loss": 0.4848791599273682,
+      "step": 790
+    },
+    {
+      "epoch": 0.2585858585858586,
+      "grad_norm": 0.010449117980897427,
+      "learning_rate": 8.861341137613242e-05,
+      "loss": 0.49130568504333494,
+      "step": 800
+    },
+    {
+      "epoch": 0.26181818181818184,
+      "grad_norm": 0.010061345063149929,
+      "learning_rate": 8.827166724523105e-05,
+      "loss": 0.49056081771850585,
+      "step": 810
+    },
+    {
+      "epoch": 0.26505050505050504,
+      "grad_norm": 0.009908635169267654,
+      "learning_rate": 8.792555017129461e-05,
+      "loss": 0.4706866264343262,
+      "step": 820
+    },
+    {
+      "epoch": 0.2682828282828283,
+      "grad_norm": 0.010003669187426567,
+      "learning_rate": 8.757509970186196e-05,
+      "loss": 0.48719348907470705,
+      "step": 830
+    },
+    {
+      "epoch": 0.27151515151515154,
+      "grad_norm": 0.009513127617537975,
+      "learning_rate": 8.722035587960826e-05,
+      "loss": 0.48200483322143556,
+      "step": 840
+    },
+    {
+      "epoch": 0.27474747474747474,
+      "grad_norm": 0.009142451919615269,
+      "learning_rate": 8.686135923776969e-05,
+      "loss": 0.48613176345825193,
+      "step": 850
+    },
+    {
+      "epoch": 0.277979797979798,
+      "grad_norm": 0.00980432890355587,
+      "learning_rate": 8.649815079551205e-05,
+      "loss": 0.4976047515869141,
+      "step": 860
+    },
+    {
+      "epoch": 0.2812121212121212,
+      "grad_norm": 0.010442109778523445,
+      "learning_rate": 8.613077205324389e-05,
+      "loss": 0.48451838493347166,
+      "step": 870
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.009309548884630203,
+      "learning_rate": 8.575926498787476e-05,
+      "loss": 0.5115366458892823,
+      "step": 880
+    },
+    {
+      "epoch": 0.2876767676767677,
+      "grad_norm": 0.009093924425542355,
+      "learning_rate": 8.538367204801872e-05,
+      "loss": 0.48187432289123533,
+      "step": 890
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.009757987223565578,
+      "learning_rate": 8.500403614914432e-05,
+      "loss": 0.4882505416870117,
+      "step": 900
+    },
+    {
+      "epoch": 0.29414141414141415,
+      "grad_norm": 0.010261048562824726,
+      "learning_rate": 8.462040066867089e-05,
+      "loss": 0.49068965911865237,
+      "step": 910
+    },
+    {
+      "epoch": 0.2973737373737374,
+      "grad_norm": 0.009317740797996521,
+      "learning_rate": 8.423280944101233e-05,
+      "loss": 0.4966132164001465,
+      "step": 920
+    },
+    {
+      "epoch": 0.3006060606060606,
+      "grad_norm": 0.009787693619728088,
+      "learning_rate": 8.384130675256852e-05,
+      "loss": 0.4754981994628906,
+      "step": 930
+    },
+    {
+      "epoch": 0.30383838383838385,
+      "grad_norm": 0.010005015879869461,
+      "learning_rate": 8.34459373366651e-05,
+      "loss": 0.4735103130340576,
+      "step": 940
+    },
+    {
+      "epoch": 0.30707070707070705,
+      "grad_norm": 0.009837017394602299,
+      "learning_rate": 8.304674636844231e-05,
+      "loss": 0.4809592247009277,
+      "step": 950
+    },
+    {
+      "epoch": 0.3103030303030303,
+      "grad_norm": 0.009590484201908112,
+      "learning_rate": 8.264377945969312e-05,
+      "loss": 0.48206100463867185,
+      "step": 960
+    },
+    {
+      "epoch": 0.31353535353535356,
+      "grad_norm": 0.009699508547782898,
+      "learning_rate": 8.223708265365174e-05,
+      "loss": 0.48718748092651365,
+      "step": 970
+    },
+    {
+      "epoch": 0.31676767676767675,
+      "grad_norm": 0.010278215631842613,
+      "learning_rate": 8.182670241973253e-05,
+      "loss": 0.4952278137207031,
+      "step": 980
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.010104077868163586,
+      "learning_rate": 8.141268564822053e-05,
+      "loss": 0.47769975662231445,
+      "step": 990
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.009301737882196903,
+      "learning_rate": 8.099507964491369e-05,
+      "loss": 0.4862718105316162,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32646464646464646,
+      "grad_norm": 0.009307135827839375,
+      "learning_rate": 8.057393212571767e-05,
+      "loss": 0.49833106994628906,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3296969696969697,
+      "grad_norm": 0.009420682676136494,
+      "learning_rate": 8.014929121119378e-05,
+      "loss": 0.48829941749572753,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3329292929292929,
+      "grad_norm": 0.010058379732072353,
+      "learning_rate": 7.972120542106077e-05,
+      "loss": 0.46506147384643554,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33616161616161616,
+      "grad_norm": 0.009461579844355583,
+      "learning_rate": 7.92897236686508e-05,
+      "loss": 0.47866268157958985,
+      "step": 1040
+    },
+    {
+      "epoch": 0.3393939393939394,
+      "grad_norm": 0.010341835208237171,
+      "learning_rate": 7.885489525532075e-05,
+      "loss": 0.4966601371765137,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3426262626262626,
+      "grad_norm": 0.01042103860527277,
+      "learning_rate": 7.84167698648189e-05,
+      "loss": 0.49251084327697753,
+      "step": 1060
+    },
+    {
+      "epoch": 0.34585858585858587,
+      "grad_norm": 0.010442749597132206,
+      "learning_rate": 7.797539755760805e-05,
+      "loss": 0.4816086769104004,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3490909090909091,
+      "grad_norm": 0.010256553068757057,
+      "learning_rate": 7.753082876514562e-05,
+      "loss": 0.47102947235107423,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3523232323232323,
+      "grad_norm": 0.009399017319083214,
+      "learning_rate": 7.708311428412129e-05,
+      "loss": 0.4810478210449219,
+      "step": 1090
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.009499317966401577,
+      "learning_rate": 7.663230527065293e-05,
+      "loss": 0.47051143646240234,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35878787878787877,
+      "grad_norm": 0.009759469889104366,
+      "learning_rate": 7.617845323444156e-05,
+      "loss": 0.4780744552612305,
+      "step": 1110
+    },
+    {
+      "epoch": 0.362020202020202,
+      "grad_norm": 0.00987281370908022,
+      "learning_rate": 7.572161003288565e-05,
+      "loss": 0.4804032325744629,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3652525252525253,
+      "grad_norm": 0.00963522493839264,
+      "learning_rate": 7.526182786515609e-05,
+      "loss": 0.48206367492675783,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36848484848484847,
+      "grad_norm": 0.009587026201188564,
+      "learning_rate": 7.479915926623165e-05,
+      "loss": 0.49240264892578123,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3717171717171717,
+      "grad_norm": 0.009810036048293114,
+      "learning_rate": 7.433365710089646e-05,
+      "loss": 0.48599681854248045,
+      "step": 1150
+    },
+    {
+      "epoch": 0.374949494949495,
+      "grad_norm": 0.00978278461843729,
+      "learning_rate": 7.386537455769963e-05,
+      "loss": 0.4688436031341553,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3781818181818182,
+      "grad_norm": 0.00925996620208025,
+      "learning_rate": 7.339436514287783e-05,
+      "loss": 0.47986507415771484,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3814141414141414,
+      "grad_norm": 0.010006657801568508,
+      "learning_rate": 7.292068267424165e-05,
+      "loss": 0.4771553993225098,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3846464646464646,
+      "grad_norm": 0.010299976915121078,
+      "learning_rate": 7.244438127502647e-05,
+      "loss": 0.4854436874389648,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3878787878787879,
+      "grad_norm": 0.009807374328374863,
+      "learning_rate": 7.196551536770807e-05,
+      "loss": 0.4763533592224121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.010062369517982006,
+      "learning_rate": 7.148413966778451e-05,
+      "loss": 0.47457141876220704,
+      "step": 1210
+    },
+    {
+      "epoch": 0.39434343434343433,
+      "grad_norm": 0.009904388338327408,
+      "learning_rate": 7.100030917752423e-05,
+      "loss": 0.4732469081878662,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3975757575757576,
+      "grad_norm": 0.009578046388924122,
+      "learning_rate": 7.051407917968138e-05,
+      "loss": 0.47551660537719725,
+      "step": 1230
+    },
+    {
+      "epoch": 0.40080808080808084,
+      "grad_norm": 0.010024272836744785,
+      "learning_rate": 7.002550523117926e-05,
+      "loss": 0.4835049629211426,
+      "step": 1240
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.010056886821985245,
+      "learning_rate": 6.953464315676241e-05,
+      "loss": 0.4909071922302246,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4072727272727273,
+      "grad_norm": 0.009707778692245483,
+      "learning_rate": 6.904154904261792e-05,
+      "loss": 0.4842695236206055,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4105050505050505,
+      "grad_norm": 0.00976107269525528,
+      "learning_rate": 6.8546279229967e-05,
+      "loss": 0.48967390060424804,
+      "step": 1270
+    },
+    {
+      "epoch": 0.41373737373737374,
+      "grad_norm": 0.010392800904810429,
+      "learning_rate": 6.804889030862753e-05,
+      "loss": 0.48658218383789065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.416969696969697,
+      "grad_norm": 0.009267269633710384,
+      "learning_rate": 6.754943911054793e-05,
+      "loss": 0.48893008232116697,
+      "step": 1290
+    },
+    {
+      "epoch": 0.4202020202020202,
+      "grad_norm": 0.009753459133207798,
+      "learning_rate": 6.704798270331358e-05,
+      "loss": 0.49384117126464844,
+      "step": 1300
+    },
+    {
+      "epoch": 0.42343434343434344,
+      "grad_norm": 0.011121846735477448,
+      "learning_rate": 6.654457838362621e-05,
+      "loss": 0.47458324432373045,
+      "step": 1310
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.009406324476003647,
+      "learning_rate": 6.603928367075718e-05,
+      "loss": 0.4703402519226074,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4298989898989899,
+      "grad_norm": 0.010009719990193844,
+      "learning_rate": 6.553215629997529e-05,
+      "loss": 0.4851715087890625,
+      "step": 1330
+    },
+    {
+      "epoch": 0.43313131313131314,
+      "grad_norm": 0.009798573330044746,
+      "learning_rate": 6.502325421594988e-05,
+      "loss": 0.4779622554779053,
+      "step": 1340
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.0098969591781497,
+      "learning_rate": 6.451263556613007e-05,
+      "loss": 0.4708548545837402,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4395959595959596,
+      "grad_norm": 0.009853474795818329,
+      "learning_rate": 6.40003586941008e-05,
+      "loss": 0.4721970558166504,
+      "step": 1360
+    },
+    {
+      "epoch": 0.44282828282828285,
+      "grad_norm": 0.009663710370659828,
+      "learning_rate": 6.348648213291642e-05,
+      "loss": 0.4798272132873535,
+      "step": 1370
+    },
+    {
+      "epoch": 0.44606060606060605,
+      "grad_norm": 0.009419051930308342,
+      "learning_rate": 6.297106459841272e-05,
+      "loss": 0.471483039855957,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4492929292929293,
+      "grad_norm": 0.009978282265365124,
+      "learning_rate": 6.245416498249801e-05,
+      "loss": 0.4772329330444336,
+      "step": 1390
+    },
+    {
+      "epoch": 0.45252525252525255,
+      "grad_norm": 0.009491856209933758,
+      "learning_rate": 6.193584234642403e-05,
+      "loss": 0.48812179565429686,
+      "step": 1400
+    },
+    {
+      "epoch": 0.45575757575757575,
+      "grad_norm": 0.010496517643332481,
+      "learning_rate": 6.141615591403771e-05,
+      "loss": 0.48897976875305177,
+      "step": 1410
+    },
+    {
+      "epoch": 0.458989898989899,
+      "grad_norm": 0.01015474647283554,
+      "learning_rate": 6.0895165065014106e-05,
+      "loss": 0.4850447654724121,
+      "step": 1420
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.009763741865754128,
+      "learning_rate": 6.037292932807167e-05,
+      "loss": 0.4857158660888672,
+      "step": 1430
+    },
+    {
+      "epoch": 0.46545454545454545,
+      "grad_norm": 0.009874231182038784,
+      "learning_rate": 5.984950837417048e-05,
+      "loss": 0.4844364166259766,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4686868686868687,
+      "grad_norm": 0.010104037821292877,
+      "learning_rate": 5.932496200969422e-05,
+      "loss": 0.47542514801025393,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4719191919191919,
+      "grad_norm": 0.009445435367524624,
+      "learning_rate": 5.879935016961661e-05,
+      "loss": 0.48579182624816897,
+      "step": 1460
+    },
+    {
+      "epoch": 0.47515151515151516,
+      "grad_norm": 0.010507128201425076,
+      "learning_rate": 5.827273291065326e-05,
+      "loss": 0.48273677825927735,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4783838383838384,
+      "grad_norm": 0.009411566890776157,
+      "learning_rate": 5.7745170404399484e-05,
+      "loss": 0.46429009437561036,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4816161616161616,
+      "grad_norm": 0.010377817787230015,
+      "learning_rate": 5.721672293045518e-05,
+      "loss": 0.49172677993774416,
+      "step": 1490
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.009920118376612663,
+      "learning_rate": 5.668745086953712e-05,
+      "loss": 0.4934688568115234,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48808080808080806,
+      "grad_norm": 0.012272641994059086,
+      "learning_rate": 5.615741469657985e-05,
+      "loss": 0.4826413631439209,
+      "step": 1510
+    },
+    {
+      "epoch": 0.4913131313131313,
+      "grad_norm": 0.00981989037245512,
+      "learning_rate": 5.562667497382582e-05,
+      "loss": 0.48468503952026365,
+      "step": 1520
+    },
+    {
+      "epoch": 0.49454545454545457,
+      "grad_norm": 0.010148138739168644,
+      "learning_rate": 5.509529234390553e-05,
+      "loss": 0.47773942947387693,
+      "step": 1530
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.010528397746384144,
+      "learning_rate": 5.456332752290837e-05,
+      "loss": 0.47507562637329104,
+      "step": 1540
+    },
+    {
+      "epoch": 0.501010101010101,
+      "grad_norm": 0.01076479908078909,
+      "learning_rate": 5.4030841293445244e-05,
+      "loss": 0.486495304107666,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5042424242424243,
+      "grad_norm": 0.009976644068956375,
+      "learning_rate": 5.349789449770351e-05,
+      "loss": 0.48320484161376953,
+      "step": 1560
+    },
+    {
+      "epoch": 0.5074747474747475,
+      "grad_norm": 0.010504718869924545,
+      "learning_rate": 5.2964548030495065e-05,
+      "loss": 0.48847188949584963,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5107070707070707,
+      "grad_norm": 0.010325642302632332,
+      "learning_rate": 5.243086283229852e-05,
+      "loss": 0.47591514587402345,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5139393939393939,
+      "grad_norm": 0.010260741226375103,
+      "learning_rate": 5.18968998822961e-05,
+      "loss": 0.48136124610900877,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5171717171717172,
+      "grad_norm": 0.010797196067869663,
+      "learning_rate": 5.1362720191406065e-05,
+      "loss": 0.48076438903808594,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5204040404040404,
+      "grad_norm": 0.010010522790253162,
+      "learning_rate": 5.082838479531169e-05,
+      "loss": 0.5004307270050049,
+      "step": 1610
+    },
+    {
+      "epoch": 0.5236363636363637,
+      "grad_norm": 0.010120037943124771,
+      "learning_rate": 5.029395474748714e-05,
+      "loss": 0.4812767028808594,
+      "step": 1620
+    },
+    {
+      "epoch": 0.5268686868686868,
+      "grad_norm": 0.009431752376258373,
+      "learning_rate": 4.975949111222158e-05,
+      "loss": 0.4887521743774414,
+      "step": 1630
+    },
+    {
+      "epoch": 0.5301010101010101,
+      "grad_norm": 0.010080527514219284,
+      "learning_rate": 4.9225054957641916e-05,
+      "loss": 0.48248910903930664,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.009522376582026482,
+      "learning_rate": 4.8690707348735035e-05,
+      "loss": 0.4855649948120117,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5365656565656566,
+      "grad_norm": 0.009686745703220367,
+      "learning_rate": 4.8156509340370605e-05,
+      "loss": 0.47187280654907227,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5397979797979798,
+      "grad_norm": 0.011875285767018795,
+      "learning_rate": 4.762252197032482e-05,
+      "loss": 0.46579513549804685,
+      "step": 1670
+    },
+    {
+      "epoch": 0.5430303030303031,
+      "grad_norm": 0.009932303801178932,
+      "learning_rate": 4.7088806252306224e-05,
+      "loss": 0.47946829795837403,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5462626262626262,
+      "grad_norm": 0.017099183052778244,
+      "learning_rate": 4.655542316898423e-05,
+      "loss": 0.4593667030334473,
+      "step": 1690
+    },
+    {
+      "epoch": 0.5494949494949495,
+      "grad_norm": 0.010512005537748337,
+      "learning_rate": 4.6022433665021246e-05,
+      "loss": 0.48582897186279295,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5527272727272727,
+      "grad_norm": 0.00989206787198782,
+      "learning_rate": 4.548989864010902e-05,
+      "loss": 0.4849580764770508,
+      "step": 1710
+    },
+    {
+      "epoch": 0.555959595959596,
+      "grad_norm": 0.010284029878675938,
+      "learning_rate": 4.495787894201031e-05,
+      "loss": 0.49089298248291013,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5591919191919192,
+      "grad_norm": 0.00992760993540287,
+      "learning_rate": 4.442643535960631e-05,
+      "loss": 0.48010549545288084,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5624242424242424,
+      "grad_norm": 0.00978371873497963,
+      "learning_rate": 4.3895628615950864e-05,
+      "loss": 0.47594566345214845,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.00981004349887371,
+      "learning_rate": 4.3365519361332345e-05,
+      "loss": 0.48056421279907224,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.010216868482530117,
+      "learning_rate": 4.283616816634353e-05,
+      "loss": 0.47501134872436523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5721212121212121,
+      "grad_norm": 0.010267022997140884,
+      "learning_rate": 4.230763551496089e-05,
+      "loss": 0.478366756439209,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5753535353535354,
+      "grad_norm": 0.009910739958286285,
+      "learning_rate": 4.1779981797633645e-05,
+      "loss": 0.478058385848999,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5785858585858585,
+      "grad_norm": 0.011339185759425163,
+      "learning_rate": 4.1253267304383455e-05,
+      "loss": 0.48466057777404786,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 0.009522072039544582,
+      "learning_rate": 4.072755221791572e-05,
+      "loss": 0.4769908905029297,
+      "step": 1800
+    },
+    {
+      "epoch": 0.585050505050505,
+      "grad_norm": 0.009808518923819065,
+      "learning_rate": 4.020289660674306e-05,
+      "loss": 0.47162666320800783,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5882828282828283,
+      "grad_norm": 0.009962448850274086,
+      "learning_rate": 3.967936041832173e-05,
+      "loss": 0.46282405853271485,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5915151515151515,
+      "grad_norm": 0.009498678147792816,
+      "learning_rate": 3.9157003472202246e-05,
+      "loss": 0.4794480323791504,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5947474747474748,
+      "grad_norm": 0.009407177567481995,
+      "learning_rate": 3.863588545319407e-05,
+      "loss": 0.4729412078857422,
+      "step": 1840
+    },
+    {
+      "epoch": 0.597979797979798,
+      "grad_norm": 0.009899895638227463,
+      "learning_rate": 3.8116065904546196e-05,
+      "loss": 0.47380704879760743,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6012121212121212,
+      "grad_norm": 0.009560837410390377,
+      "learning_rate": 3.759760422114362e-05,
+      "loss": 0.47751388549804685,
+      "step": 1860
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.010970192961394787,
+      "learning_rate": 3.708055964272088e-05,
+      "loss": 0.47801823616027833,
+      "step": 1870
+    },
+    {
+      "epoch": 0.6076767676767677,
+      "grad_norm": 0.00964390765875578,
+      "learning_rate": 3.6564991247093234e-05,
+      "loss": 0.4800426483154297,
+      "step": 1880
+    },
+    {
+      "epoch": 0.610909090909091,
+      "grad_norm": 0.009764602407813072,
+      "learning_rate": 3.6050957943406465e-05,
+      "loss": 0.4812753677368164,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6141414141414141,
+      "grad_norm": 0.009959314949810505,
+      "learning_rate": 3.553851846540584e-05,
+      "loss": 0.47804956436157225,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6173737373737374,
+      "grad_norm": 0.010666392743587494,
+      "learning_rate": 3.50277313647252e-05,
+      "loss": 0.4772273063659668,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6206060606060606,
+      "grad_norm": 0.009173358790576458,
+      "learning_rate": 3.451865500419676e-05,
+      "loss": 0.4892144203186035,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6238383838383839,
+      "grad_norm": 0.010000358335673809,
+      "learning_rate": 3.401134755118256e-05,
+      "loss": 0.48959059715270997,
+      "step": 1930
+    },
+    {
+      "epoch": 0.6270707070707071,
+      "grad_norm": 0.010190536268055439,
+      "learning_rate": 3.350586697092826e-05,
+      "loss": 0.46478729248046874,
+      "step": 1940
+    },
+    {
+      "epoch": 0.6303030303030303,
+      "grad_norm": 0.010812178254127502,
+      "learning_rate": 3.300227101993998e-05,
+      "loss": 0.5046152114868164,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6335353535353535,
+      "grad_norm": 0.01017849799245596,
+      "learning_rate": 3.2500617239384947e-05,
+      "loss": 0.4698008060455322,
+      "step": 1960
+    },
+    {
+      "epoch": 0.6367676767676768,
+      "grad_norm": 0.011103908531367779,
+      "learning_rate": 3.200096294851691e-05,
+      "loss": 0.4716217041015625,
+      "step": 1970
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.009982883930206299,
+      "learning_rate": 3.150336523812674e-05,
+      "loss": 0.47135162353515625,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6432323232323233,
+      "grad_norm": 0.01043197326362133,
+      "learning_rate": 3.100788096401925e-05,
+      "loss": 0.4799614906311035,
+      "step": 1990
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.010667623952031136,
+      "learning_rate": 3.051456674051677e-05,
+      "loss": 0.4682164192199707,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6496969696969697,
+      "grad_norm": 0.010620036162436008,
+      "learning_rate": 3.0023478933990347e-05,
+      "loss": 0.4750208854675293,
+      "step": 2010
+    },
+    {
+      "epoch": 0.6529292929292929,
+      "grad_norm": 0.010374991223216057,
+      "learning_rate": 2.9534673656419377e-05,
+      "loss": 0.48034076690673827,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6561616161616162,
+      "grad_norm": 0.011932817287743092,
+      "learning_rate": 2.9048206758980136e-05,
+      "loss": 0.46314101219177245,
+      "step": 2030
+    },
+    {
+      "epoch": 0.6593939393939394,
+      "grad_norm": 0.01039852574467659,
+      "learning_rate": 2.856413382566425e-05,
+      "loss": 0.4783937454223633,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6626262626262627,
+      "grad_norm": 0.010200604796409607,
+      "learning_rate": 2.8082510166927583e-05,
+      "loss": 0.4792025089263916,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6658585858585858,
+      "grad_norm": 0.009561127051711082,
+      "learning_rate": 2.760339081337041e-05,
+      "loss": 0.4722686767578125,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6690909090909091,
+      "grad_norm": 0.00924921128898859,
+      "learning_rate": 2.7126830509449773e-05,
+      "loss": 0.4884464263916016,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6723232323232323,
+      "grad_norm": 0.00991444569081068,
+      "learning_rate": 2.6652883707224075e-05,
+      "loss": 0.4804549217224121,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.009902069345116615,
+      "learning_rate": 2.618160456013153e-05,
+      "loss": 0.4781071186065674,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 0.010504493489861488,
+      "learning_rate": 2.571304691680255e-05,
+      "loss": 0.48059587478637694,
+      "step": 2100
+    },
+    {
+      "epoch": 0.682020202020202,
+      "grad_norm": 0.009641965851187706,
+      "learning_rate": 2.5247264314906917e-05,
+      "loss": 0.4706240177154541,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6852525252525252,
+      "grad_norm": 0.010276644490659237,
+      "learning_rate": 2.4784309975036513e-05,
+      "loss": 0.4885101318359375,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6884848484848485,
+      "grad_norm": 0.010960405692458153,
+      "learning_rate": 2.4324236794624456e-05,
+      "loss": 0.4882383346557617,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6917171717171717,
+      "grad_norm": 0.010282796807587147,
+      "learning_rate": 2.386709734190079e-05,
+      "loss": 0.4768857479095459,
+      "step": 2140
+    },
+    {
+      "epoch": 0.694949494949495,
+      "grad_norm": 0.010104385204613209,
+      "learning_rate": 2.34129438498862e-05,
+      "loss": 0.4802837371826172,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6981818181818182,
+      "grad_norm": 0.010027035139501095,
+      "learning_rate": 2.296182821042374e-05,
+      "loss": 0.4874839782714844,
+      "step": 2160
+    },
+    {
+      "epoch": 0.7014141414141414,
+      "grad_norm": 0.010018851608037949,
+      "learning_rate": 2.2513801968249644e-05,
+      "loss": 0.4758561134338379,
+      "step": 2170
+    },
+    {
+      "epoch": 0.7046464646464646,
+      "grad_norm": 0.009862969629466534,
+      "learning_rate": 2.2068916315103783e-05,
+      "loss": 0.4686488151550293,
+      "step": 2180
+    },
+    {
+      "epoch": 0.7078787878787879,
+      "grad_norm": 0.00952910166233778,
+      "learning_rate": 2.162722208388057e-05,
+      "loss": 0.4782154083251953,
+      "step": 2190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.010213647037744522,
+      "learning_rate": 2.1188769742820625e-05,
+      "loss": 0.4773773193359375,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7143434343434344,
+      "grad_norm": 0.010498392395675182,
+      "learning_rate": 2.075360938974429e-05,
+      "loss": 0.4733907222747803,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7175757575757575,
+      "grad_norm": 0.009394815191626549,
+      "learning_rate": 2.03217907463275e-05,
+      "loss": 0.47564210891723635,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7208080808080808,
+      "grad_norm": 0.010383618995547295,
+      "learning_rate": 1.989336315242048e-05,
+      "loss": 0.4784512519836426,
+      "step": 2230
+    },
+    {
+      "epoch": 0.724040404040404,
+      "grad_norm": 0.01043599285185337,
+      "learning_rate": 1.9468375560410117e-05,
+      "loss": 0.4808964729309082,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.009953988716006279,
+      "learning_rate": 1.90468765296267e-05,
+      "loss": 0.49031834602355956,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7305050505050505,
+      "grad_norm": 0.010356656275689602,
+      "learning_rate": 1.8628914220795494e-05,
+      "loss": 0.48055601119995117,
+      "step": 2260
+    },
+    {
+      "epoch": 0.7337373737373737,
+      "grad_norm": 0.009841440245509148,
+      "learning_rate": 1.8214536390533822e-05,
+      "loss": 0.47170586585998536,
+      "step": 2270
+    },
+    {
+      "epoch": 0.7369696969696969,
+      "grad_norm": 0.010102550499141216,
+      "learning_rate": 1.7803790385894387e-05,
+      "loss": 0.4660043716430664,
+      "step": 2280
+    },
+    {
+      "epoch": 0.7402020202020202,
+      "grad_norm": 0.010421738028526306,
+      "learning_rate": 1.7396723138955428e-05,
+      "loss": 0.4599196434020996,
+      "step": 2290
+    },
+    {
+      "epoch": 0.7434343434343434,
+      "grad_norm": 0.009896540082991123,
+      "learning_rate": 1.699338116145811e-05,
+      "loss": 0.46491589546203616,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.010468855500221252,
+      "learning_rate": 1.6593810539492195e-05,
+      "loss": 0.47761125564575196,
+      "step": 2310
+    },
+    {
+      "epoch": 0.74989898989899,
+      "grad_norm": 0.010416937991976738,
+      "learning_rate": 1.619805692823016e-05,
+      "loss": 0.49956817626953126,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7531313131313131,
+      "grad_norm": 0.010007611475884914,
+      "learning_rate": 1.580616554671057e-05,
+      "loss": 0.4716916084289551,
+      "step": 2330
+    },
+    {
+      "epoch": 0.7563636363636363,
+      "grad_norm": 0.010231648571789265,
+      "learning_rate": 1.5418181172671382e-05,
+      "loss": 0.4909040451049805,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7595959595959596,
+      "grad_norm": 0.010324012488126755,
+      "learning_rate": 1.5034148137433623e-05,
+      "loss": 0.47939190864562986,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7628282828282829,
+      "grad_norm": 0.011009547859430313,
+      "learning_rate": 1.4654110320836017e-05,
+      "loss": 0.48291826248168945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7660606060606061,
+      "grad_norm": 0.010392943397164345,
+      "learning_rate": 1.4278111146221263e-05,
+      "loss": 0.49179973602294924,
+      "step": 2370
+    },
+    {
+      "epoch": 0.7692929292929293,
+      "grad_norm": 0.010355197824537754,
+      "learning_rate": 1.3906193575474508e-05,
+      "loss": 0.4716278076171875,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7725252525252525,
+      "grad_norm": 0.009932084940373898,
+      "learning_rate": 1.3538400104114446e-05,
+      "loss": 0.47190055847167967,
+      "step": 2390
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 0.010710643604397774,
+      "learning_rate": 1.3174772756437742e-05,
+      "loss": 0.4703176498413086,
+      "step": 2400
+    },
+    {
+      "epoch": 0.778989898989899,
+      "grad_norm": 0.010614068247377872,
+      "learning_rate": 1.2815353080717379e-05,
+      "loss": 0.47541141510009766,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.011346950195729733,
+      "learning_rate": 1.246018214445525e-05,
+      "loss": 0.4860015869140625,
+      "step": 2420
+    },
+    {
+      "epoch": 0.7854545454545454,
+      "grad_norm": 0.009824907407164574,
+      "learning_rate": 1.210930052968981e-05,
+      "loss": 0.49062480926513674,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7886868686868687,
+      "grad_norm": 0.010624224320054054,
+      "learning_rate": 1.1762748328359152e-05,
+      "loss": 0.4694485664367676,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7919191919191919,
+      "grad_norm": 0.01044746395200491,
+      "learning_rate": 1.1420565137720045e-05,
+      "loss": 0.47275629043579104,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7951515151515152,
+      "grad_norm": 0.010226710699498653,
+      "learning_rate": 1.1082790055823533e-05,
+      "loss": 0.4670067310333252,
+      "step": 2460
+    },
+    {
+      "epoch": 0.7983838383838384,
+      "grad_norm": 0.010427460074424744,
+      "learning_rate": 1.0749461677047624e-05,
+      "loss": 0.4700475692749023,
+      "step": 2470
+    },
+    {
+      "epoch": 0.8016161616161617,
+      "grad_norm": 0.010494428686797619,
+      "learning_rate": 1.0420618087687418e-05,
+      "loss": 0.46589016914367676,
+      "step": 2480
+    },
+    {
+      "epoch": 0.8048484848484848,
+      "grad_norm": 0.010100893676280975,
+      "learning_rate": 1.0096296861603321e-05,
+      "loss": 0.4704419136047363,
+      "step": 2490
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.010682797059416771,
+      "learning_rate": 9.776535055927931e-06,
+      "loss": 0.47326183319091797,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8113131313131313,
+      "grad_norm": 0.00972407590597868,
+      "learning_rate": 9.461369206831772e-06,
+      "loss": 0.48441619873046876,
+      "step": 2510
+    },
+    {
+      "epoch": 0.8145454545454546,
+      "grad_norm": 0.010327558033168316,
+      "learning_rate": 9.150835325348678e-06,
+      "loss": 0.45856351852416993,
+      "step": 2520
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.010118944570422173,
+      "learning_rate": 8.844968893261197e-06,
+      "loss": 0.48114948272705077,
+      "step": 2530
+    },
+    {
+      "epoch": 0.821010101010101,
+      "grad_norm": 0.010876161977648735,
+      "learning_rate": 8.543804859046345e-06,
+      "loss": 0.4930680274963379,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8242424242424242,
+      "grad_norm": 0.010722608305513859,
+      "learning_rate": 8.247377633882463e-06,
+      "loss": 0.46875743865966796,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8274747474747475,
+      "grad_norm": 0.01088438369333744,
+      "learning_rate": 7.95572108771726e-06,
+      "loss": 0.4768000602722168,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8307070707070707,
+      "grad_norm": 0.01026720181107521,
+      "learning_rate": 7.66886854539795e-06,
+      "loss": 0.479974365234375,
+      "step": 2570
+    },
+    {
+      "epoch": 0.833939393939394,
+      "grad_norm": 0.009710075333714485,
+      "learning_rate": 7.386852782863407e-06,
+      "loss": 0.4684715270996094,
+      "step": 2580
+    },
+    {
+      "epoch": 0.8371717171717171,
+      "grad_norm": 0.009966167621314526,
+      "learning_rate": 7.109706023399232e-06,
+      "loss": 0.47191972732543946,
+      "step": 2590
+    },
+    {
+      "epoch": 0.8404040404040404,
+      "grad_norm": 0.010125650092959404,
+      "learning_rate": 6.837459933955936e-06,
+      "loss": 0.4766803741455078,
+      "step": 2600
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.689461319477494e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2600/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f7c9df64c3878a6af022f87735f5d8a7b4ae14de05ab3af73dcc955b795285
+size 5585

checkpoint-2800/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- llama-factory
+- 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

checkpoint-2800/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/Qwen3-4B-Base",
+  "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": 64,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-2800/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-2800/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024f1a82e53317ef477d8f6641ff28440490d074b1a208439dd1a41c4f003142
+size 528915403

checkpoint-2800/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dff92e737a96ed8e55fbb17dff25cf3c476aa30f177c1856764da007af68a5
+size 15429

checkpoint-2800/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c616ff04ed57f83b34bed7eb797bd8138608692f1b0bdd6c424bb2dbc936bc6a
+size 15429

checkpoint-2800/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cfe3fd382b286e47d9016978fb5527adb2134450523cd09af0a35698b39741e
+size 15429

checkpoint-2800/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2c79cb6e901e1a926fd96d91c3168c047f44ec5bfaef396189f60e74c841aa
+size 15429

checkpoint-2800/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5f9fccceef8f5147596ea909fed9ec198bc9df137155bc2bcc41e82a70dcb63
+size 1465

checkpoint-2800/tokenizer.json

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

checkpoint-2800/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-2800/trainer_state.json

@@ -0,0 +1,1994 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9050505050505051,
+  "eval_steps": 200,
+  "global_step": 2800,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032323232323232323,
+      "grad_norm": 0.032284051179885864,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.6013355255126953,
+      "step": 10
+    },
+    {
+      "epoch": 0.006464646464646465,
+      "grad_norm": 0.01937970519065857,
+      "learning_rate": 1.2258064516129032e-05,
+      "loss": 0.5758121490478516,
+      "step": 20
+    },
+    {
+      "epoch": 0.009696969696969697,
+      "grad_norm": 0.014327733777463436,
+      "learning_rate": 1.870967741935484e-05,
+      "loss": 0.5787662506103516,
+      "step": 30
+    },
+    {
+      "epoch": 0.01292929292929293,
+      "grad_norm": 0.012254982255399227,
+      "learning_rate": 2.5161290322580645e-05,
+      "loss": 0.5327143669128418,
+      "step": 40
+    },
+    {
+      "epoch": 0.01616161616161616,
+      "grad_norm": 0.014536243863403797,
+      "learning_rate": 3.161290322580645e-05,
+      "loss": 0.5393171310424805,
+      "step": 50
+    },
+    {
+      "epoch": 0.019393939393939394,
+      "grad_norm": 0.011900736019015312,
+      "learning_rate": 3.8064516129032254e-05,
+      "loss": 0.5058945178985595,
+      "step": 60
+    },
+    {
+      "epoch": 0.022626262626262626,
+      "grad_norm": 0.01210293360054493,
+      "learning_rate": 4.451612903225807e-05,
+      "loss": 0.517607593536377,
+      "step": 70
+    },
+    {
+      "epoch": 0.02585858585858586,
+      "grad_norm": 0.017207792028784752,
+      "learning_rate": 5.096774193548387e-05,
+      "loss": 0.5269095420837402,
+      "step": 80
+    },
+    {
+      "epoch": 0.02909090909090909,
+      "grad_norm": 0.013736969791352749,
+      "learning_rate": 5.7419354838709685e-05,
+      "loss": 0.5040688514709473,
+      "step": 90
+    },
+    {
+      "epoch": 0.03232323232323232,
+      "grad_norm": 0.011664404533803463,
+      "learning_rate": 6.387096774193548e-05,
+      "loss": 0.5147775173187256,
+      "step": 100
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 0.014052552171051502,
+      "learning_rate": 7.03225806451613e-05,
+      "loss": 0.5230005741119385,
+      "step": 110
+    },
+    {
+      "epoch": 0.03878787878787879,
+      "grad_norm": 0.011644740588963032,
+      "learning_rate": 7.67741935483871e-05,
+      "loss": 0.5105222702026367,
+      "step": 120
+    },
+    {
+      "epoch": 0.04202020202020202,
+      "grad_norm": 0.011730308644473553,
+      "learning_rate": 8.32258064516129e-05,
+      "loss": 0.4989170074462891,
+      "step": 130
+    },
+    {
+      "epoch": 0.04525252525252525,
+      "grad_norm": 0.012009115889668465,
+      "learning_rate": 8.967741935483871e-05,
+      "loss": 0.5003124713897705,
+      "step": 140
+    },
+    {
+      "epoch": 0.048484848484848485,
+      "grad_norm": 0.012424134649336338,
+      "learning_rate": 9.612903225806452e-05,
+      "loss": 0.5077538013458252,
+      "step": 150
+    },
+    {
+      "epoch": 0.05171717171717172,
+      "grad_norm": 0.011461800895631313,
+      "learning_rate": 9.999954295400999e-05,
+      "loss": 0.5061477661132813,
+      "step": 160
+    },
+    {
+      "epoch": 0.05494949494949495,
+      "grad_norm": 0.011583201587200165,
+      "learning_rate": 9.999440128258112e-05,
+      "loss": 0.5013481140136719,
+      "step": 170
+    },
+    {
+      "epoch": 0.05818181818181818,
+      "grad_norm": 0.011583367362618446,
+      "learning_rate": 9.998354722168459e-05,
+      "loss": 0.48343815803527834,
+      "step": 180
+    },
+    {
+      "epoch": 0.061414141414141414,
+      "grad_norm": 0.011094105429947376,
+      "learning_rate": 9.996698201151175e-05,
+      "loss": 0.507840633392334,
+      "step": 190
+    },
+    {
+      "epoch": 0.06464646464646465,
+      "grad_norm": 0.011715452186763287,
+      "learning_rate": 9.994470754481315e-05,
+      "loss": 0.49884777069091796,
+      "step": 200
+    },
+    {
+      "epoch": 0.06787878787878789,
+      "grad_norm": 0.010746965184807777,
+      "learning_rate": 9.991672636668239e-05,
+      "loss": 0.5068713188171386,
+      "step": 210
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.012883410789072514,
+      "learning_rate": 9.988304167426519e-05,
+      "loss": 0.4920186519622803,
+      "step": 220
+    },
+    {
+      "epoch": 0.07434343434343435,
+      "grad_norm": 0.011187366209924221,
+      "learning_rate": 9.984365731639419e-05,
+      "loss": 0.5021648406982422,
+      "step": 230
+    },
+    {
+      "epoch": 0.07757575757575758,
+      "grad_norm": 0.010671757161617279,
+      "learning_rate": 9.979857779314906e-05,
+      "loss": 0.5038897514343261,
+      "step": 240
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.01044373121112585,
+      "learning_rate": 9.974780825534246e-05,
+      "loss": 0.4965065956115723,
+      "step": 250
+    },
+    {
+      "epoch": 0.08404040404040404,
+      "grad_norm": 0.010565251111984253,
+      "learning_rate": 9.969135450393141e-05,
+      "loss": 0.5145994186401367,
+      "step": 260
+    },
+    {
+      "epoch": 0.08727272727272728,
+      "grad_norm": 0.010024026967585087,
+      "learning_rate": 9.96292229893545e-05,
+      "loss": 0.505019235610962,
+      "step": 270
+    },
+    {
+      "epoch": 0.0905050505050505,
+      "grad_norm": 0.010430407710373402,
+      "learning_rate": 9.956142081079484e-05,
+      "loss": 0.5115808010101318,
+      "step": 280
+    },
+    {
+      "epoch": 0.09373737373737374,
+      "grad_norm": 0.010048807598650455,
+      "learning_rate": 9.948795571536891e-05,
+      "loss": 0.48525152206420896,
+      "step": 290
+    },
+    {
+      "epoch": 0.09696969696969697,
+      "grad_norm": 0.010108387097716331,
+      "learning_rate": 9.94088360972414e-05,
+      "loss": 0.5002010822296142,
+      "step": 300
+    },
+    {
+      "epoch": 0.10020202020202021,
+      "grad_norm": 0.010273640975356102,
+      "learning_rate": 9.932407099666608e-05,
+      "loss": 0.49662046432495116,
+      "step": 310
+    },
+    {
+      "epoch": 0.10343434343434343,
+      "grad_norm": 0.00995971355587244,
+      "learning_rate": 9.923367009895274e-05,
+      "loss": 0.48578290939331054,
+      "step": 320
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.010459775105118752,
+      "learning_rate": 9.913764373336079e-05,
+      "loss": 0.48862767219543457,
+      "step": 330
+    },
+    {
+      "epoch": 0.1098989898989899,
+      "grad_norm": 0.009838269092142582,
+      "learning_rate": 9.903600287191875e-05,
+      "loss": 0.5034208774566651,
+      "step": 340
+    },
+    {
+      "epoch": 0.11313131313131314,
+      "grad_norm": 0.00978950597345829,
+      "learning_rate": 9.892875912817079e-05,
+      "loss": 0.4870161533355713,
+      "step": 350
+    },
+    {
+      "epoch": 0.11636363636363636,
+      "grad_norm": 0.01030043140053749,
+      "learning_rate": 9.881592475584964e-05,
+      "loss": 0.5026071548461915,
+      "step": 360
+    },
+    {
+      "epoch": 0.1195959595959596,
+      "grad_norm": 0.010531975887715816,
+      "learning_rate": 9.869751264747656e-05,
+      "loss": 0.4883917808532715,
+      "step": 370
+    },
+    {
+      "epoch": 0.12282828282828283,
+      "grad_norm": 0.00986825954169035,
+      "learning_rate": 9.857353633288814e-05,
+      "loss": 0.4927018165588379,
+      "step": 380
+    },
+    {
+      "epoch": 0.12606060606060607,
+      "grad_norm": 0.009432349354028702,
+      "learning_rate": 9.844400997769043e-05,
+      "loss": 0.4908174514770508,
+      "step": 390
+    },
+    {
+      "epoch": 0.1292929292929293,
+      "grad_norm": 0.01057665515691042,
+      "learning_rate": 9.83089483816404e-05,
+      "loss": 0.5069625854492188,
+      "step": 400
+    },
+    {
+      "epoch": 0.13252525252525252,
+      "grad_norm": 0.010007908567786217,
+      "learning_rate": 9.816836697695482e-05,
+      "loss": 0.4988056182861328,
+      "step": 410
+    },
+    {
+      "epoch": 0.13575757575757577,
+      "grad_norm": 0.010027808137238026,
+      "learning_rate": 9.802228182654702e-05,
+      "loss": 0.5007385730743408,
+      "step": 420
+    },
+    {
+      "epoch": 0.138989898989899,
+      "grad_norm": 0.009953738190233707,
+      "learning_rate": 9.787070962219156e-05,
+      "loss": 0.5130783081054687,
+      "step": 430
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.010204462334513664,
+      "learning_rate": 9.771366768261696e-05,
+      "loss": 0.4947535514831543,
+      "step": 440
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 0.009612451307475567,
+      "learning_rate": 9.755117395152689e-05,
+      "loss": 0.4917112350463867,
+      "step": 450
+    },
+    {
+      "epoch": 0.1486868686868687,
+      "grad_norm": 0.00995573028922081,
+      "learning_rate": 9.73832469955499e-05,
+      "loss": 0.4882859230041504,
+      "step": 460
+    },
+    {
+      "epoch": 0.15191919191919193,
+      "grad_norm": 0.009584570303559303,
+      "learning_rate": 9.720990600211797e-05,
+      "loss": 0.500526762008667,
+      "step": 470
+    },
+    {
+      "epoch": 0.15515151515151515,
+      "grad_norm": 0.010585076175630093,
+      "learning_rate": 9.703117077727419e-05,
+      "loss": 0.496882963180542,
+      "step": 480
+    },
+    {
+      "epoch": 0.15838383838383838,
+      "grad_norm": 0.009859723038971424,
+      "learning_rate": 9.684706174340965e-05,
+      "loss": 0.48728485107421876,
+      "step": 490
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.010212041437625885,
+      "learning_rate": 9.665759993693e-05,
+      "loss": 0.49378366470336915,
+      "step": 500
+    },
+    {
+      "epoch": 0.16484848484848486,
+      "grad_norm": 0.009744231589138508,
+      "learning_rate": 9.646280700585185e-05,
+      "loss": 0.4663555145263672,
+      "step": 510
+    },
+    {
+      "epoch": 0.16808080808080808,
+      "grad_norm": 0.009789686650037766,
+      "learning_rate": 9.626270520732916e-05,
+      "loss": 0.4879913330078125,
+      "step": 520
+    },
+    {
+      "epoch": 0.1713131313131313,
+      "grad_norm": 0.009891769848763943,
+      "learning_rate": 9.605731740511022e-05,
+      "loss": 0.48809428215026857,
+      "step": 530
+    },
+    {
+      "epoch": 0.17454545454545456,
+      "grad_norm": 0.01002143882215023,
+      "learning_rate": 9.584666706692517e-05,
+      "loss": 0.4959606170654297,
+      "step": 540
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.009208496659994125,
+      "learning_rate": 9.56307782618046e-05,
+      "loss": 0.4878594398498535,
+      "step": 550
+    },
+    {
+      "epoch": 0.181010101010101,
+      "grad_norm": 0.009645081125199795,
+      "learning_rate": 9.540967565732937e-05,
+      "loss": 0.4769869804382324,
+      "step": 560
+    },
+    {
+      "epoch": 0.18424242424242424,
+      "grad_norm": 0.010497638955712318,
+      "learning_rate": 9.51833845168121e-05,
+      "loss": 0.4970097064971924,
+      "step": 570
+    },
+    {
+      "epoch": 0.1874747474747475,
+      "grad_norm": 0.010612033307552338,
+      "learning_rate": 9.495193069641057e-05,
+      "loss": 0.4945381164550781,
+      "step": 580
+    },
+    {
+      "epoch": 0.1907070707070707,
+      "grad_norm": 0.009433986619114876,
+      "learning_rate": 9.47153406421734e-05,
+      "loss": 0.4860210418701172,
+      "step": 590
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 0.009995914995670319,
+      "learning_rate": 9.447364138701823e-05,
+      "loss": 0.4904911994934082,
+      "step": 600
+    },
+    {
+      "epoch": 0.19717171717171716,
+      "grad_norm": 0.009814019314944744,
+      "learning_rate": 9.422686054764302e-05,
+      "loss": 0.4915336608886719,
+      "step": 610
+    },
+    {
+      "epoch": 0.20040404040404042,
+      "grad_norm": 0.010199982672929764,
+      "learning_rate": 9.397502632137055e-05,
+      "loss": 0.4805011749267578,
+      "step": 620
+    },
+    {
+      "epoch": 0.20363636363636364,
+      "grad_norm": 0.010121874511241913,
+      "learning_rate": 9.371816748292641e-05,
+      "loss": 0.47633209228515627,
+      "step": 630
+    },
+    {
+      "epoch": 0.20686868686868687,
+      "grad_norm": 0.009638865478336811,
+      "learning_rate": 9.345631338115141e-05,
+      "loss": 0.48993511199951173,
+      "step": 640
+    },
+    {
+      "epoch": 0.2101010101010101,
+      "grad_norm": 0.010041174478828907,
+      "learning_rate": 9.318949393564807e-05,
+      "loss": 0.4798978328704834,
+      "step": 650
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.010145517997443676,
+      "learning_rate": 9.291773963336193e-05,
+      "loss": 0.4696659564971924,
+      "step": 660
+    },
+    {
+      "epoch": 0.21656565656565657,
+      "grad_norm": 0.01043335534632206,
+      "learning_rate": 9.264108152509816e-05,
+      "loss": 0.4955574035644531,
+      "step": 670
+    },
+    {
+      "epoch": 0.2197979797979798,
+      "grad_norm": 0.010406569577753544,
+      "learning_rate": 9.235955122197368e-05,
+      "loss": 0.48659563064575195,
+      "step": 680
+    },
+    {
+      "epoch": 0.22303030303030302,
+      "grad_norm": 0.009870355017483234,
+      "learning_rate": 9.207318089180524e-05,
+      "loss": 0.4766091823577881,
+      "step": 690
+    },
+    {
+      "epoch": 0.22626262626262628,
+      "grad_norm": 0.009980005212128162,
+      "learning_rate": 9.178200325543384e-05,
+      "loss": 0.5022068023681641,
+      "step": 700
+    },
+    {
+      "epoch": 0.2294949494949495,
+      "grad_norm": 0.009765878319740295,
+      "learning_rate": 9.148605158298621e-05,
+      "loss": 0.48309478759765623,
+      "step": 710
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.009879437275230885,
+      "learning_rate": 9.118535969007314e-05,
+      "loss": 0.4793684959411621,
+      "step": 720
+    },
+    {
+      "epoch": 0.23595959595959595,
+      "grad_norm": 0.009907045401632786,
+      "learning_rate": 9.087996193392578e-05,
+      "loss": 0.49844112396240237,
+      "step": 730
+    },
+    {
+      "epoch": 0.2391919191919192,
+      "grad_norm": 0.009958872571587563,
+      "learning_rate": 9.056989320947e-05,
+      "loss": 0.48113102912902833,
+      "step": 740
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.010206855833530426,
+      "learning_rate": 9.025518894533921e-05,
+      "loss": 0.5048784255981446,
+      "step": 750
+    },
+    {
+      "epoch": 0.24565656565656566,
+      "grad_norm": 0.009286429733037949,
+      "learning_rate": 8.99358850998263e-05,
+      "loss": 0.4862624168395996,
+      "step": 760
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.009919015690684319,
+      "learning_rate": 8.9612018156775e-05,
+      "loss": 0.48739056587219237,
+      "step": 770
+    },
+    {
+      "epoch": 0.25212121212121213,
+      "grad_norm": 0.010435211472213268,
+      "learning_rate": 8.928362512141124e-05,
+      "loss": 0.48689990043640136,
+      "step": 780
+    },
+    {
+      "epoch": 0.25535353535353533,
+      "grad_norm": 0.009992080740630627,
+      "learning_rate": 8.895074351611488e-05,
+      "loss": 0.4848791599273682,
+      "step": 790
+    },
+    {
+      "epoch": 0.2585858585858586,
+      "grad_norm": 0.010449117980897427,
+      "learning_rate": 8.861341137613242e-05,
+      "loss": 0.49130568504333494,
+      "step": 800
+    },
+    {
+      "epoch": 0.26181818181818184,
+      "grad_norm": 0.010061345063149929,
+      "learning_rate": 8.827166724523105e-05,
+      "loss": 0.49056081771850585,
+      "step": 810
+    },
+    {
+      "epoch": 0.26505050505050504,
+      "grad_norm": 0.009908635169267654,
+      "learning_rate": 8.792555017129461e-05,
+      "loss": 0.4706866264343262,
+      "step": 820
+    },
+    {
+      "epoch": 0.2682828282828283,
+      "grad_norm": 0.010003669187426567,
+      "learning_rate": 8.757509970186196e-05,
+      "loss": 0.48719348907470705,
+      "step": 830
+    },
+    {
+      "epoch": 0.27151515151515154,
+      "grad_norm": 0.009513127617537975,
+      "learning_rate": 8.722035587960826e-05,
+      "loss": 0.48200483322143556,
+      "step": 840
+    },
+    {
+      "epoch": 0.27474747474747474,
+      "grad_norm": 0.009142451919615269,
+      "learning_rate": 8.686135923776969e-05,
+      "loss": 0.48613176345825193,
+      "step": 850
+    },
+    {
+      "epoch": 0.277979797979798,
+      "grad_norm": 0.00980432890355587,
+      "learning_rate": 8.649815079551205e-05,
+      "loss": 0.4976047515869141,
+      "step": 860
+    },
+    {
+      "epoch": 0.2812121212121212,
+      "grad_norm": 0.010442109778523445,
+      "learning_rate": 8.613077205324389e-05,
+      "loss": 0.48451838493347166,
+      "step": 870
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.009309548884630203,
+      "learning_rate": 8.575926498787476e-05,
+      "loss": 0.5115366458892823,
+      "step": 880
+    },
+    {
+      "epoch": 0.2876767676767677,
+      "grad_norm": 0.009093924425542355,
+      "learning_rate": 8.538367204801872e-05,
+      "loss": 0.48187432289123533,
+      "step": 890
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.009757987223565578,
+      "learning_rate": 8.500403614914432e-05,
+      "loss": 0.4882505416870117,
+      "step": 900
+    },
+    {
+      "epoch": 0.29414141414141415,
+      "grad_norm": 0.010261048562824726,
+      "learning_rate": 8.462040066867089e-05,
+      "loss": 0.49068965911865237,
+      "step": 910
+    },
+    {
+      "epoch": 0.2973737373737374,
+      "grad_norm": 0.009317740797996521,
+      "learning_rate": 8.423280944101233e-05,
+      "loss": 0.4966132164001465,
+      "step": 920
+    },
+    {
+      "epoch": 0.3006060606060606,
+      "grad_norm": 0.009787693619728088,
+      "learning_rate": 8.384130675256852e-05,
+      "loss": 0.4754981994628906,
+      "step": 930
+    },
+    {
+      "epoch": 0.30383838383838385,
+      "grad_norm": 0.010005015879869461,
+      "learning_rate": 8.34459373366651e-05,
+      "loss": 0.4735103130340576,
+      "step": 940
+    },
+    {
+      "epoch": 0.30707070707070705,
+      "grad_norm": 0.009837017394602299,
+      "learning_rate": 8.304674636844231e-05,
+      "loss": 0.4809592247009277,
+      "step": 950
+    },
+    {
+      "epoch": 0.3103030303030303,
+      "grad_norm": 0.009590484201908112,
+      "learning_rate": 8.264377945969312e-05,
+      "loss": 0.48206100463867185,
+      "step": 960
+    },
+    {
+      "epoch": 0.31353535353535356,
+      "grad_norm": 0.009699508547782898,
+      "learning_rate": 8.223708265365174e-05,
+      "loss": 0.48718748092651365,
+      "step": 970
+    },
+    {
+      "epoch": 0.31676767676767675,
+      "grad_norm": 0.010278215631842613,
+      "learning_rate": 8.182670241973253e-05,
+      "loss": 0.4952278137207031,
+      "step": 980
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.010104077868163586,
+      "learning_rate": 8.141268564822053e-05,
+      "loss": 0.47769975662231445,
+      "step": 990
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.009301737882196903,
+      "learning_rate": 8.099507964491369e-05,
+      "loss": 0.4862718105316162,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32646464646464646,
+      "grad_norm": 0.009307135827839375,
+      "learning_rate": 8.057393212571767e-05,
+      "loss": 0.49833106994628906,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3296969696969697,
+      "grad_norm": 0.009420682676136494,
+      "learning_rate": 8.014929121119378e-05,
+      "loss": 0.48829941749572753,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3329292929292929,
+      "grad_norm": 0.010058379732072353,
+      "learning_rate": 7.972120542106077e-05,
+      "loss": 0.46506147384643554,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33616161616161616,
+      "grad_norm": 0.009461579844355583,
+      "learning_rate": 7.92897236686508e-05,
+      "loss": 0.47866268157958985,
+      "step": 1040
+    },
+    {
+      "epoch": 0.3393939393939394,
+      "grad_norm": 0.010341835208237171,
+      "learning_rate": 7.885489525532075e-05,
+      "loss": 0.4966601371765137,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3426262626262626,
+      "grad_norm": 0.01042103860527277,
+      "learning_rate": 7.84167698648189e-05,
+      "loss": 0.49251084327697753,
+      "step": 1060
+    },
+    {
+      "epoch": 0.34585858585858587,
+      "grad_norm": 0.010442749597132206,
+      "learning_rate": 7.797539755760805e-05,
+      "loss": 0.4816086769104004,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3490909090909091,
+      "grad_norm": 0.010256553068757057,
+      "learning_rate": 7.753082876514562e-05,
+      "loss": 0.47102947235107423,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3523232323232323,
+      "grad_norm": 0.009399017319083214,
+      "learning_rate": 7.708311428412129e-05,
+      "loss": 0.4810478210449219,
+      "step": 1090
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.009499317966401577,
+      "learning_rate": 7.663230527065293e-05,
+      "loss": 0.47051143646240234,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35878787878787877,
+      "grad_norm": 0.009759469889104366,
+      "learning_rate": 7.617845323444156e-05,
+      "loss": 0.4780744552612305,
+      "step": 1110
+    },
+    {
+      "epoch": 0.362020202020202,
+      "grad_norm": 0.00987281370908022,
+      "learning_rate": 7.572161003288565e-05,
+      "loss": 0.4804032325744629,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3652525252525253,
+      "grad_norm": 0.00963522493839264,
+      "learning_rate": 7.526182786515609e-05,
+      "loss": 0.48206367492675783,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36848484848484847,
+      "grad_norm": 0.009587026201188564,
+      "learning_rate": 7.479915926623165e-05,
+      "loss": 0.49240264892578123,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3717171717171717,
+      "grad_norm": 0.009810036048293114,
+      "learning_rate": 7.433365710089646e-05,
+      "loss": 0.48599681854248045,
+      "step": 1150
+    },
+    {
+      "epoch": 0.374949494949495,
+      "grad_norm": 0.00978278461843729,
+      "learning_rate": 7.386537455769963e-05,
+      "loss": 0.4688436031341553,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3781818181818182,
+      "grad_norm": 0.00925996620208025,
+      "learning_rate": 7.339436514287783e-05,
+      "loss": 0.47986507415771484,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3814141414141414,
+      "grad_norm": 0.010006657801568508,
+      "learning_rate": 7.292068267424165e-05,
+      "loss": 0.4771553993225098,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3846464646464646,
+      "grad_norm": 0.010299976915121078,
+      "learning_rate": 7.244438127502647e-05,
+      "loss": 0.4854436874389648,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3878787878787879,
+      "grad_norm": 0.009807374328374863,
+      "learning_rate": 7.196551536770807e-05,
+      "loss": 0.4763533592224121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.010062369517982006,
+      "learning_rate": 7.148413966778451e-05,
+      "loss": 0.47457141876220704,
+      "step": 1210
+    },
+    {
+      "epoch": 0.39434343434343433,
+      "grad_norm": 0.009904388338327408,
+      "learning_rate": 7.100030917752423e-05,
+      "loss": 0.4732469081878662,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3975757575757576,
+      "grad_norm": 0.009578046388924122,
+      "learning_rate": 7.051407917968138e-05,
+      "loss": 0.47551660537719725,
+      "step": 1230
+    },
+    {
+      "epoch": 0.40080808080808084,
+      "grad_norm": 0.010024272836744785,
+      "learning_rate": 7.002550523117926e-05,
+      "loss": 0.4835049629211426,
+      "step": 1240
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.010056886821985245,
+      "learning_rate": 6.953464315676241e-05,
+      "loss": 0.4909071922302246,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4072727272727273,
+      "grad_norm": 0.009707778692245483,
+      "learning_rate": 6.904154904261792e-05,
+      "loss": 0.4842695236206055,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4105050505050505,
+      "grad_norm": 0.00976107269525528,
+      "learning_rate": 6.8546279229967e-05,
+      "loss": 0.48967390060424804,
+      "step": 1270
+    },
+    {
+      "epoch": 0.41373737373737374,
+      "grad_norm": 0.010392800904810429,
+      "learning_rate": 6.804889030862753e-05,
+      "loss": 0.48658218383789065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.416969696969697,
+      "grad_norm": 0.009267269633710384,
+      "learning_rate": 6.754943911054793e-05,
+      "loss": 0.48893008232116697,
+      "step": 1290
+    },
+    {
+      "epoch": 0.4202020202020202,
+      "grad_norm": 0.009753459133207798,
+      "learning_rate": 6.704798270331358e-05,
+      "loss": 0.49384117126464844,
+      "step": 1300
+    },
+    {
+      "epoch": 0.42343434343434344,
+      "grad_norm": 0.011121846735477448,
+      "learning_rate": 6.654457838362621e-05,
+      "loss": 0.47458324432373045,
+      "step": 1310
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.009406324476003647,
+      "learning_rate": 6.603928367075718e-05,
+      "loss": 0.4703402519226074,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4298989898989899,
+      "grad_norm": 0.010009719990193844,
+      "learning_rate": 6.553215629997529e-05,
+      "loss": 0.4851715087890625,
+      "step": 1330
+    },
+    {
+      "epoch": 0.43313131313131314,
+      "grad_norm": 0.009798573330044746,
+      "learning_rate": 6.502325421594988e-05,
+      "loss": 0.4779622554779053,
+      "step": 1340
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.0098969591781497,
+      "learning_rate": 6.451263556613007e-05,
+      "loss": 0.4708548545837402,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4395959595959596,
+      "grad_norm": 0.009853474795818329,
+      "learning_rate": 6.40003586941008e-05,
+      "loss": 0.4721970558166504,
+      "step": 1360
+    },
+    {
+      "epoch": 0.44282828282828285,
+      "grad_norm": 0.009663710370659828,
+      "learning_rate": 6.348648213291642e-05,
+      "loss": 0.4798272132873535,
+      "step": 1370
+    },
+    {
+      "epoch": 0.44606060606060605,
+      "grad_norm": 0.009419051930308342,
+      "learning_rate": 6.297106459841272e-05,
+      "loss": 0.471483039855957,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4492929292929293,
+      "grad_norm": 0.009978282265365124,
+      "learning_rate": 6.245416498249801e-05,
+      "loss": 0.4772329330444336,
+      "step": 1390
+    },
+    {
+      "epoch": 0.45252525252525255,
+      "grad_norm": 0.009491856209933758,
+      "learning_rate": 6.193584234642403e-05,
+      "loss": 0.48812179565429686,
+      "step": 1400
+    },
+    {
+      "epoch": 0.45575757575757575,
+      "grad_norm": 0.010496517643332481,
+      "learning_rate": 6.141615591403771e-05,
+      "loss": 0.48897976875305177,
+      "step": 1410
+    },
+    {
+      "epoch": 0.458989898989899,
+      "grad_norm": 0.01015474647283554,
+      "learning_rate": 6.0895165065014106e-05,
+      "loss": 0.4850447654724121,
+      "step": 1420
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.009763741865754128,
+      "learning_rate": 6.037292932807167e-05,
+      "loss": 0.4857158660888672,
+      "step": 1430
+    },
+    {
+      "epoch": 0.46545454545454545,
+      "grad_norm": 0.009874231182038784,
+      "learning_rate": 5.984950837417048e-05,
+      "loss": 0.4844364166259766,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4686868686868687,
+      "grad_norm": 0.010104037821292877,
+      "learning_rate": 5.932496200969422e-05,
+      "loss": 0.47542514801025393,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4719191919191919,
+      "grad_norm": 0.009445435367524624,
+      "learning_rate": 5.879935016961661e-05,
+      "loss": 0.48579182624816897,
+      "step": 1460
+    },
+    {
+      "epoch": 0.47515151515151516,
+      "grad_norm": 0.010507128201425076,
+      "learning_rate": 5.827273291065326e-05,
+      "loss": 0.48273677825927735,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4783838383838384,
+      "grad_norm": 0.009411566890776157,
+      "learning_rate": 5.7745170404399484e-05,
+      "loss": 0.46429009437561036,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4816161616161616,
+      "grad_norm": 0.010377817787230015,
+      "learning_rate": 5.721672293045518e-05,
+      "loss": 0.49172677993774416,
+      "step": 1490
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.009920118376612663,
+      "learning_rate": 5.668745086953712e-05,
+      "loss": 0.4934688568115234,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48808080808080806,
+      "grad_norm": 0.012272641994059086,
+      "learning_rate": 5.615741469657985e-05,
+      "loss": 0.4826413631439209,
+      "step": 1510
+    },
+    {
+      "epoch": 0.4913131313131313,
+      "grad_norm": 0.00981989037245512,
+      "learning_rate": 5.562667497382582e-05,
+      "loss": 0.48468503952026365,
+      "step": 1520
+    },
+    {
+      "epoch": 0.49454545454545457,
+      "grad_norm": 0.010148138739168644,
+      "learning_rate": 5.509529234390553e-05,
+      "loss": 0.47773942947387693,
+      "step": 1530
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.010528397746384144,
+      "learning_rate": 5.456332752290837e-05,
+      "loss": 0.47507562637329104,
+      "step": 1540
+    },
+    {
+      "epoch": 0.501010101010101,
+      "grad_norm": 0.01076479908078909,
+      "learning_rate": 5.4030841293445244e-05,
+      "loss": 0.486495304107666,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5042424242424243,
+      "grad_norm": 0.009976644068956375,
+      "learning_rate": 5.349789449770351e-05,
+      "loss": 0.48320484161376953,
+      "step": 1560
+    },
+    {
+      "epoch": 0.5074747474747475,
+      "grad_norm": 0.010504718869924545,
+      "learning_rate": 5.2964548030495065e-05,
+      "loss": 0.48847188949584963,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5107070707070707,
+      "grad_norm": 0.010325642302632332,
+      "learning_rate": 5.243086283229852e-05,
+      "loss": 0.47591514587402345,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5139393939393939,
+      "grad_norm": 0.010260741226375103,
+      "learning_rate": 5.18968998822961e-05,
+      "loss": 0.48136124610900877,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5171717171717172,
+      "grad_norm": 0.010797196067869663,
+      "learning_rate": 5.1362720191406065e-05,
+      "loss": 0.48076438903808594,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5204040404040404,
+      "grad_norm": 0.010010522790253162,
+      "learning_rate": 5.082838479531169e-05,
+      "loss": 0.5004307270050049,
+      "step": 1610
+    },
+    {
+      "epoch": 0.5236363636363637,
+      "grad_norm": 0.010120037943124771,
+      "learning_rate": 5.029395474748714e-05,
+      "loss": 0.4812767028808594,
+      "step": 1620
+    },
+    {
+      "epoch": 0.5268686868686868,
+      "grad_norm": 0.009431752376258373,
+      "learning_rate": 4.975949111222158e-05,
+      "loss": 0.4887521743774414,
+      "step": 1630
+    },
+    {
+      "epoch": 0.5301010101010101,
+      "grad_norm": 0.010080527514219284,
+      "learning_rate": 4.9225054957641916e-05,
+      "loss": 0.48248910903930664,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.009522376582026482,
+      "learning_rate": 4.8690707348735035e-05,
+      "loss": 0.4855649948120117,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5365656565656566,
+      "grad_norm": 0.009686745703220367,
+      "learning_rate": 4.8156509340370605e-05,
+      "loss": 0.47187280654907227,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5397979797979798,
+      "grad_norm": 0.011875285767018795,
+      "learning_rate": 4.762252197032482e-05,
+      "loss": 0.46579513549804685,
+      "step": 1670
+    },
+    {
+      "epoch": 0.5430303030303031,
+      "grad_norm": 0.009932303801178932,
+      "learning_rate": 4.7088806252306224e-05,
+      "loss": 0.47946829795837403,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5462626262626262,
+      "grad_norm": 0.017099183052778244,
+      "learning_rate": 4.655542316898423e-05,
+      "loss": 0.4593667030334473,
+      "step": 1690
+    },
+    {
+      "epoch": 0.5494949494949495,
+      "grad_norm": 0.010512005537748337,
+      "learning_rate": 4.6022433665021246e-05,
+      "loss": 0.48582897186279295,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5527272727272727,
+      "grad_norm": 0.00989206787198782,
+      "learning_rate": 4.548989864010902e-05,
+      "loss": 0.4849580764770508,
+      "step": 1710
+    },
+    {
+      "epoch": 0.555959595959596,
+      "grad_norm": 0.010284029878675938,
+      "learning_rate": 4.495787894201031e-05,
+      "loss": 0.49089298248291013,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5591919191919192,
+      "grad_norm": 0.00992760993540287,
+      "learning_rate": 4.442643535960631e-05,
+      "loss": 0.48010549545288084,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5624242424242424,
+      "grad_norm": 0.00978371873497963,
+      "learning_rate": 4.3895628615950864e-05,
+      "loss": 0.47594566345214845,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.00981004349887371,
+      "learning_rate": 4.3365519361332345e-05,
+      "loss": 0.48056421279907224,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.010216868482530117,
+      "learning_rate": 4.283616816634353e-05,
+      "loss": 0.47501134872436523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5721212121212121,
+      "grad_norm": 0.010267022997140884,
+      "learning_rate": 4.230763551496089e-05,
+      "loss": 0.478366756439209,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5753535353535354,
+      "grad_norm": 0.009910739958286285,
+      "learning_rate": 4.1779981797633645e-05,
+      "loss": 0.478058385848999,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5785858585858585,
+      "grad_norm": 0.011339185759425163,
+      "learning_rate": 4.1253267304383455e-05,
+      "loss": 0.48466057777404786,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 0.009522072039544582,
+      "learning_rate": 4.072755221791572e-05,
+      "loss": 0.4769908905029297,
+      "step": 1800
+    },
+    {
+      "epoch": 0.585050505050505,
+      "grad_norm": 0.009808518923819065,
+      "learning_rate": 4.020289660674306e-05,
+      "loss": 0.47162666320800783,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5882828282828283,
+      "grad_norm": 0.009962448850274086,
+      "learning_rate": 3.967936041832173e-05,
+      "loss": 0.46282405853271485,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5915151515151515,
+      "grad_norm": 0.009498678147792816,
+      "learning_rate": 3.9157003472202246e-05,
+      "loss": 0.4794480323791504,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5947474747474748,
+      "grad_norm": 0.009407177567481995,
+      "learning_rate": 3.863588545319407e-05,
+      "loss": 0.4729412078857422,
+      "step": 1840
+    },
+    {
+      "epoch": 0.597979797979798,
+      "grad_norm": 0.009899895638227463,
+      "learning_rate": 3.8116065904546196e-05,
+      "loss": 0.47380704879760743,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6012121212121212,
+      "grad_norm": 0.009560837410390377,
+      "learning_rate": 3.759760422114362e-05,
+      "loss": 0.47751388549804685,
+      "step": 1860
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.010970192961394787,
+      "learning_rate": 3.708055964272088e-05,
+      "loss": 0.47801823616027833,
+      "step": 1870
+    },
+    {
+      "epoch": 0.6076767676767677,
+      "grad_norm": 0.00964390765875578,
+      "learning_rate": 3.6564991247093234e-05,
+      "loss": 0.4800426483154297,
+      "step": 1880
+    },
+    {
+      "epoch": 0.610909090909091,
+      "grad_norm": 0.009764602407813072,
+      "learning_rate": 3.6050957943406465e-05,
+      "loss": 0.4812753677368164,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6141414141414141,
+      "grad_norm": 0.009959314949810505,
+      "learning_rate": 3.553851846540584e-05,
+      "loss": 0.47804956436157225,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6173737373737374,
+      "grad_norm": 0.010666392743587494,
+      "learning_rate": 3.50277313647252e-05,
+      "loss": 0.4772273063659668,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6206060606060606,
+      "grad_norm": 0.009173358790576458,
+      "learning_rate": 3.451865500419676e-05,
+      "loss": 0.4892144203186035,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6238383838383839,
+      "grad_norm": 0.010000358335673809,
+      "learning_rate": 3.401134755118256e-05,
+      "loss": 0.48959059715270997,
+      "step": 1930
+    },
+    {
+      "epoch": 0.6270707070707071,
+      "grad_norm": 0.010190536268055439,
+      "learning_rate": 3.350586697092826e-05,
+      "loss": 0.46478729248046874,
+      "step": 1940
+    },
+    {
+      "epoch": 0.6303030303030303,
+      "grad_norm": 0.010812178254127502,
+      "learning_rate": 3.300227101993998e-05,
+      "loss": 0.5046152114868164,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6335353535353535,
+      "grad_norm": 0.01017849799245596,
+      "learning_rate": 3.2500617239384947e-05,
+      "loss": 0.4698008060455322,
+      "step": 1960
+    },
+    {
+      "epoch": 0.6367676767676768,
+      "grad_norm": 0.011103908531367779,
+      "learning_rate": 3.200096294851691e-05,
+      "loss": 0.4716217041015625,
+      "step": 1970
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.009982883930206299,
+      "learning_rate": 3.150336523812674e-05,
+      "loss": 0.47135162353515625,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6432323232323233,
+      "grad_norm": 0.01043197326362133,
+      "learning_rate": 3.100788096401925e-05,
+      "loss": 0.4799614906311035,
+      "step": 1990
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.010667623952031136,
+      "learning_rate": 3.051456674051677e-05,
+      "loss": 0.4682164192199707,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6496969696969697,
+      "grad_norm": 0.010620036162436008,
+      "learning_rate": 3.0023478933990347e-05,
+      "loss": 0.4750208854675293,
+      "step": 2010
+    },
+    {
+      "epoch": 0.6529292929292929,
+      "grad_norm": 0.010374991223216057,
+      "learning_rate": 2.9534673656419377e-05,
+      "loss": 0.48034076690673827,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6561616161616162,
+      "grad_norm": 0.011932817287743092,
+      "learning_rate": 2.9048206758980136e-05,
+      "loss": 0.46314101219177245,
+      "step": 2030
+    },
+    {
+      "epoch": 0.6593939393939394,
+      "grad_norm": 0.01039852574467659,
+      "learning_rate": 2.856413382566425e-05,
+      "loss": 0.4783937454223633,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6626262626262627,
+      "grad_norm": 0.010200604796409607,
+      "learning_rate": 2.8082510166927583e-05,
+      "loss": 0.4792025089263916,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6658585858585858,
+      "grad_norm": 0.009561127051711082,
+      "learning_rate": 2.760339081337041e-05,
+      "loss": 0.4722686767578125,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6690909090909091,
+      "grad_norm": 0.00924921128898859,
+      "learning_rate": 2.7126830509449773e-05,
+      "loss": 0.4884464263916016,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6723232323232323,
+      "grad_norm": 0.00991444569081068,
+      "learning_rate": 2.6652883707224075e-05,
+      "loss": 0.4804549217224121,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.009902069345116615,
+      "learning_rate": 2.618160456013153e-05,
+      "loss": 0.4781071186065674,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 0.010504493489861488,
+      "learning_rate": 2.571304691680255e-05,
+      "loss": 0.48059587478637694,
+      "step": 2100
+    },
+    {
+      "epoch": 0.682020202020202,
+      "grad_norm": 0.009641965851187706,
+      "learning_rate": 2.5247264314906917e-05,
+      "loss": 0.4706240177154541,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6852525252525252,
+      "grad_norm": 0.010276644490659237,
+      "learning_rate": 2.4784309975036513e-05,
+      "loss": 0.4885101318359375,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6884848484848485,
+      "grad_norm": 0.010960405692458153,
+      "learning_rate": 2.4324236794624456e-05,
+      "loss": 0.4882383346557617,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6917171717171717,
+      "grad_norm": 0.010282796807587147,
+      "learning_rate": 2.386709734190079e-05,
+      "loss": 0.4768857479095459,
+      "step": 2140
+    },
+    {
+      "epoch": 0.694949494949495,
+      "grad_norm": 0.010104385204613209,
+      "learning_rate": 2.34129438498862e-05,
+      "loss": 0.4802837371826172,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6981818181818182,
+      "grad_norm": 0.010027035139501095,
+      "learning_rate": 2.296182821042374e-05,
+      "loss": 0.4874839782714844,
+      "step": 2160
+    },
+    {
+      "epoch": 0.7014141414141414,
+      "grad_norm": 0.010018851608037949,
+      "learning_rate": 2.2513801968249644e-05,
+      "loss": 0.4758561134338379,
+      "step": 2170
+    },
+    {
+      "epoch": 0.7046464646464646,
+      "grad_norm": 0.009862969629466534,
+      "learning_rate": 2.2068916315103783e-05,
+      "loss": 0.4686488151550293,
+      "step": 2180
+    },
+    {
+      "epoch": 0.7078787878787879,
+      "grad_norm": 0.00952910166233778,
+      "learning_rate": 2.162722208388057e-05,
+      "loss": 0.4782154083251953,
+      "step": 2190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.010213647037744522,
+      "learning_rate": 2.1188769742820625e-05,
+      "loss": 0.4773773193359375,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7143434343434344,
+      "grad_norm": 0.010498392395675182,
+      "learning_rate": 2.075360938974429e-05,
+      "loss": 0.4733907222747803,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7175757575757575,
+      "grad_norm": 0.009394815191626549,
+      "learning_rate": 2.03217907463275e-05,
+      "loss": 0.47564210891723635,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7208080808080808,
+      "grad_norm": 0.010383618995547295,
+      "learning_rate": 1.989336315242048e-05,
+      "loss": 0.4784512519836426,
+      "step": 2230
+    },
+    {
+      "epoch": 0.724040404040404,
+      "grad_norm": 0.01043599285185337,
+      "learning_rate": 1.9468375560410117e-05,
+      "loss": 0.4808964729309082,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.009953988716006279,
+      "learning_rate": 1.90468765296267e-05,
+      "loss": 0.49031834602355956,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7305050505050505,
+      "grad_norm": 0.010356656275689602,
+      "learning_rate": 1.8628914220795494e-05,
+      "loss": 0.48055601119995117,
+      "step": 2260
+    },
+    {
+      "epoch": 0.7337373737373737,
+      "grad_norm": 0.009841440245509148,
+      "learning_rate": 1.8214536390533822e-05,
+      "loss": 0.47170586585998536,
+      "step": 2270
+    },
+    {
+      "epoch": 0.7369696969696969,
+      "grad_norm": 0.010102550499141216,
+      "learning_rate": 1.7803790385894387e-05,
+      "loss": 0.4660043716430664,
+      "step": 2280
+    },
+    {
+      "epoch": 0.7402020202020202,
+      "grad_norm": 0.010421738028526306,
+      "learning_rate": 1.7396723138955428e-05,
+      "loss": 0.4599196434020996,
+      "step": 2290
+    },
+    {
+      "epoch": 0.7434343434343434,
+      "grad_norm": 0.009896540082991123,
+      "learning_rate": 1.699338116145811e-05,
+      "loss": 0.46491589546203616,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.010468855500221252,
+      "learning_rate": 1.6593810539492195e-05,
+      "loss": 0.47761125564575196,
+      "step": 2310
+    },
+    {
+      "epoch": 0.74989898989899,
+      "grad_norm": 0.010416937991976738,
+      "learning_rate": 1.619805692823016e-05,
+      "loss": 0.49956817626953126,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7531313131313131,
+      "grad_norm": 0.010007611475884914,
+      "learning_rate": 1.580616554671057e-05,
+      "loss": 0.4716916084289551,
+      "step": 2330
+    },
+    {
+      "epoch": 0.7563636363636363,
+      "grad_norm": 0.010231648571789265,
+      "learning_rate": 1.5418181172671382e-05,
+      "loss": 0.4909040451049805,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7595959595959596,
+      "grad_norm": 0.010324012488126755,
+      "learning_rate": 1.5034148137433623e-05,
+      "loss": 0.47939190864562986,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7628282828282829,
+      "grad_norm": 0.011009547859430313,
+      "learning_rate": 1.4654110320836017e-05,
+      "loss": 0.48291826248168945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7660606060606061,
+      "grad_norm": 0.010392943397164345,
+      "learning_rate": 1.4278111146221263e-05,
+      "loss": 0.49179973602294924,
+      "step": 2370
+    },
+    {
+      "epoch": 0.7692929292929293,
+      "grad_norm": 0.010355197824537754,
+      "learning_rate": 1.3906193575474508e-05,
+      "loss": 0.4716278076171875,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7725252525252525,
+      "grad_norm": 0.009932084940373898,
+      "learning_rate": 1.3538400104114446e-05,
+      "loss": 0.47190055847167967,
+      "step": 2390
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 0.010710643604397774,
+      "learning_rate": 1.3174772756437742e-05,
+      "loss": 0.4703176498413086,
+      "step": 2400
+    },
+    {
+      "epoch": 0.778989898989899,
+      "grad_norm": 0.010614068247377872,
+      "learning_rate": 1.2815353080717379e-05,
+      "loss": 0.47541141510009766,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.011346950195729733,
+      "learning_rate": 1.246018214445525e-05,
+      "loss": 0.4860015869140625,
+      "step": 2420
+    },
+    {
+      "epoch": 0.7854545454545454,
+      "grad_norm": 0.009824907407164574,
+      "learning_rate": 1.210930052968981e-05,
+      "loss": 0.49062480926513674,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7886868686868687,
+      "grad_norm": 0.010624224320054054,
+      "learning_rate": 1.1762748328359152e-05,
+      "loss": 0.4694485664367676,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7919191919191919,
+      "grad_norm": 0.01044746395200491,
+      "learning_rate": 1.1420565137720045e-05,
+      "loss": 0.47275629043579104,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7951515151515152,
+      "grad_norm": 0.010226710699498653,
+      "learning_rate": 1.1082790055823533e-05,
+      "loss": 0.4670067310333252,
+      "step": 2460
+    },
+    {
+      "epoch": 0.7983838383838384,
+      "grad_norm": 0.010427460074424744,
+      "learning_rate": 1.0749461677047624e-05,
+      "loss": 0.4700475692749023,
+      "step": 2470
+    },
+    {
+      "epoch": 0.8016161616161617,
+      "grad_norm": 0.010494428686797619,
+      "learning_rate": 1.0420618087687418e-05,
+      "loss": 0.46589016914367676,
+      "step": 2480
+    },
+    {
+      "epoch": 0.8048484848484848,
+      "grad_norm": 0.010100893676280975,
+      "learning_rate": 1.0096296861603321e-05,
+      "loss": 0.4704419136047363,
+      "step": 2490
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.010682797059416771,
+      "learning_rate": 9.776535055927931e-06,
+      "loss": 0.47326183319091797,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8113131313131313,
+      "grad_norm": 0.00972407590597868,
+      "learning_rate": 9.461369206831772e-06,
+      "loss": 0.48441619873046876,
+      "step": 2510
+    },
+    {
+      "epoch": 0.8145454545454546,
+      "grad_norm": 0.010327558033168316,
+      "learning_rate": 9.150835325348678e-06,
+      "loss": 0.45856351852416993,
+      "step": 2520
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.010118944570422173,
+      "learning_rate": 8.844968893261197e-06,
+      "loss": 0.48114948272705077,
+      "step": 2530
+    },
+    {
+      "epoch": 0.821010101010101,
+      "grad_norm": 0.010876161977648735,
+      "learning_rate": 8.543804859046345e-06,
+      "loss": 0.4930680274963379,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8242424242424242,
+      "grad_norm": 0.010722608305513859,
+      "learning_rate": 8.247377633882463e-06,
+      "loss": 0.46875743865966796,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8274747474747475,
+      "grad_norm": 0.01088438369333744,
+      "learning_rate": 7.95572108771726e-06,
+      "loss": 0.4768000602722168,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8307070707070707,
+      "grad_norm": 0.01026720181107521,
+      "learning_rate": 7.66886854539795e-06,
+      "loss": 0.479974365234375,
+      "step": 2570
+    },
+    {
+      "epoch": 0.833939393939394,
+      "grad_norm": 0.009710075333714485,
+      "learning_rate": 7.386852782863407e-06,
+      "loss": 0.4684715270996094,
+      "step": 2580
+    },
+    {
+      "epoch": 0.8371717171717171,
+      "grad_norm": 0.009966167621314526,
+      "learning_rate": 7.109706023399232e-06,
+      "loss": 0.47191972732543946,
+      "step": 2590
+    },
+    {
+      "epoch": 0.8404040404040404,
+      "grad_norm": 0.010125650092959404,
+      "learning_rate": 6.837459933955936e-06,
+      "loss": 0.4766803741455078,
+      "step": 2600
+    },
+    {
+      "epoch": 0.8436363636363636,
+      "grad_norm": 0.009984518401324749,
+      "learning_rate": 6.5701456215305656e-06,
+      "loss": 0.4592133045196533,
+      "step": 2610
+    },
+    {
+      "epoch": 0.8468686868686869,
+      "grad_norm": 0.010836348868906498,
+      "learning_rate": 6.307793629612452e-06,
+      "loss": 0.4658504009246826,
+      "step": 2620
+    },
+    {
+      "epoch": 0.8501010101010101,
+      "grad_norm": 0.010431919246912003,
+      "learning_rate": 6.050433934693339e-06,
+      "loss": 0.4936856269836426,
+      "step": 2630
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.01049034669995308,
+      "learning_rate": 5.798095942842141e-06,
+      "loss": 0.4765117645263672,
+      "step": 2640
+    },
+    {
+      "epoch": 0.8565656565656565,
+      "grad_norm": 0.009596607647836208,
+      "learning_rate": 5.550808486345072e-06,
+      "loss": 0.47063379287719725,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8597979797979798,
+      "grad_norm": 0.01032214518636465,
+      "learning_rate": 5.308599820411247e-06,
+      "loss": 0.4614537715911865,
+      "step": 2660
+    },
+    {
+      "epoch": 0.863030303030303,
+      "grad_norm": 0.009960100054740906,
+      "learning_rate": 5.071497619944171e-06,
+      "loss": 0.48136143684387206,
+      "step": 2670
+    },
+    {
+      "epoch": 0.8662626262626263,
+      "grad_norm": 0.010326167568564415,
+      "learning_rate": 4.839528976379648e-06,
+      "loss": 0.47299985885620116,
+      "step": 2680
+    },
+    {
+      "epoch": 0.8694949494949495,
+      "grad_norm": 0.010867294855415821,
+      "learning_rate": 4.612720394590286e-06,
+      "loss": 0.4829209327697754,
+      "step": 2690
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.01050047017633915,
+      "learning_rate": 4.391097789856985e-06,
+      "loss": 0.4762550354003906,
+      "step": 2700
+    },
+    {
+      "epoch": 0.8759595959595959,
+      "grad_norm": 0.010378929786384106,
+      "learning_rate": 4.174686484907908e-06,
+      "loss": 0.4898251533508301,
+      "step": 2710
+    },
+    {
+      "epoch": 0.8791919191919192,
+      "grad_norm": 0.01060938648879528,
+      "learning_rate": 3.963511207025078e-06,
+      "loss": 0.47261548042297363,
+      "step": 2720
+    },
+    {
+      "epoch": 0.8824242424242424,
+      "grad_norm": 0.01075353566557169,
+      "learning_rate": 3.7575960852189728e-06,
+      "loss": 0.4839645862579346,
+      "step": 2730
+    },
+    {
+      "epoch": 0.8856565656565657,
+      "grad_norm": 0.010416378267109394,
+      "learning_rate": 3.5569646474715722e-06,
+      "loss": 0.46989760398864744,
+      "step": 2740
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.010806340724229813,
+      "learning_rate": 3.361639818048068e-06,
+      "loss": 0.47272281646728515,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8921212121212121,
+      "grad_norm": 0.009753530845046043,
+      "learning_rate": 3.1716439148774534e-06,
+      "loss": 0.47122917175292967,
+      "step": 2760
+    },
+    {
+      "epoch": 0.8953535353535353,
+      "grad_norm": 0.01022200658917427,
+      "learning_rate": 2.986998647002498e-06,
+      "loss": 0.4727674961090088,
+      "step": 2770
+    },
+    {
+      "epoch": 0.8985858585858586,
+      "grad_norm": 0.010225590318441391,
+      "learning_rate": 2.8077251120992742e-06,
+      "loss": 0.46461896896362304,
+      "step": 2780
+    },
+    {
+      "epoch": 0.9018181818181819,
+      "grad_norm": 0.010752941481769085,
+      "learning_rate": 2.633843794066515e-06,
+      "loss": 0.46602635383605956,
+      "step": 2790
+    },
+    {
+      "epoch": 0.9050505050505051,
+      "grad_norm": 0.011064955033361912,
+      "learning_rate": 2.465374560685091e-06,
+      "loss": 0.4705932140350342,
+      "step": 2800
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.972749581988397e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-2800/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35f7c9df64c3878a6af022f87735f5d8a7b4ae14de05ab3af73dcc955b795285
+size 5585

checkpoint-3000/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- llama-factory
+- 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

checkpoint-3000/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/Qwen3-4B-Base",
+  "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": 64,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-3000/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e5ecc88c9b9c9b63bdad801960258ec6decb7390998869300265a0ee95f732c
+size 264308896

checkpoint-3000/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-3000/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11cd612086011598c1bbf27c4887aeb5598128201aea858f07655e53a3c5905a
+size 528915403

checkpoint-3000/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98fd9945bfc43ed108f8f7803e6afce00be1e9025dc0bbbfff0e9c9079794dd1
+size 15429

checkpoint-3000/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96dd1485cd43047026c704147bc49b16458bfaee355e83bb825c89a0b1b25da7
+size 1465

checkpoint-3000/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-3000/trainer_state.json

@@ -0,0 +1,2134 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9696969696969697,
+  "eval_steps": 200,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032323232323232323,
+      "grad_norm": 0.032284051179885864,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.6013355255126953,
+      "step": 10
+    },
+    {
+      "epoch": 0.006464646464646465,
+      "grad_norm": 0.01937970519065857,
+      "learning_rate": 1.2258064516129032e-05,
+      "loss": 0.5758121490478516,
+      "step": 20
+    },
+    {
+      "epoch": 0.009696969696969697,
+      "grad_norm": 0.014327733777463436,
+      "learning_rate": 1.870967741935484e-05,
+      "loss": 0.5787662506103516,
+      "step": 30
+    },
+    {
+      "epoch": 0.01292929292929293,
+      "grad_norm": 0.012254982255399227,
+      "learning_rate": 2.5161290322580645e-05,
+      "loss": 0.5327143669128418,
+      "step": 40
+    },
+    {
+      "epoch": 0.01616161616161616,
+      "grad_norm": 0.014536243863403797,
+      "learning_rate": 3.161290322580645e-05,
+      "loss": 0.5393171310424805,
+      "step": 50
+    },
+    {
+      "epoch": 0.019393939393939394,
+      "grad_norm": 0.011900736019015312,
+      "learning_rate": 3.8064516129032254e-05,
+      "loss": 0.5058945178985595,
+      "step": 60
+    },
+    {
+      "epoch": 0.022626262626262626,
+      "grad_norm": 0.01210293360054493,
+      "learning_rate": 4.451612903225807e-05,
+      "loss": 0.517607593536377,
+      "step": 70
+    },
+    {
+      "epoch": 0.02585858585858586,
+      "grad_norm": 0.017207792028784752,
+      "learning_rate": 5.096774193548387e-05,
+      "loss": 0.5269095420837402,
+      "step": 80
+    },
+    {
+      "epoch": 0.02909090909090909,
+      "grad_norm": 0.013736969791352749,
+      "learning_rate": 5.7419354838709685e-05,
+      "loss": 0.5040688514709473,
+      "step": 90
+    },
+    {
+      "epoch": 0.03232323232323232,
+      "grad_norm": 0.011664404533803463,
+      "learning_rate": 6.387096774193548e-05,
+      "loss": 0.5147775173187256,
+      "step": 100
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 0.014052552171051502,
+      "learning_rate": 7.03225806451613e-05,
+      "loss": 0.5230005741119385,
+      "step": 110
+    },
+    {
+      "epoch": 0.03878787878787879,
+      "grad_norm": 0.011644740588963032,
+      "learning_rate": 7.67741935483871e-05,
+      "loss": 0.5105222702026367,
+      "step": 120
+    },
+    {
+      "epoch": 0.04202020202020202,
+      "grad_norm": 0.011730308644473553,
+      "learning_rate": 8.32258064516129e-05,
+      "loss": 0.4989170074462891,
+      "step": 130
+    },
+    {
+      "epoch": 0.04525252525252525,
+      "grad_norm": 0.012009115889668465,
+      "learning_rate": 8.967741935483871e-05,
+      "loss": 0.5003124713897705,
+      "step": 140
+    },
+    {
+      "epoch": 0.048484848484848485,
+      "grad_norm": 0.012424134649336338,
+      "learning_rate": 9.612903225806452e-05,
+      "loss": 0.5077538013458252,
+      "step": 150
+    },
+    {
+      "epoch": 0.05171717171717172,
+      "grad_norm": 0.011461800895631313,
+      "learning_rate": 9.999954295400999e-05,
+      "loss": 0.5061477661132813,
+      "step": 160
+    },
+    {
+      "epoch": 0.05494949494949495,
+      "grad_norm": 0.011583201587200165,
+      "learning_rate": 9.999440128258112e-05,
+      "loss": 0.5013481140136719,
+      "step": 170
+    },
+    {
+      "epoch": 0.05818181818181818,
+      "grad_norm": 0.011583367362618446,
+      "learning_rate": 9.998354722168459e-05,
+      "loss": 0.48343815803527834,
+      "step": 180
+    },
+    {
+      "epoch": 0.061414141414141414,
+      "grad_norm": 0.011094105429947376,
+      "learning_rate": 9.996698201151175e-05,
+      "loss": 0.507840633392334,
+      "step": 190
+    },
+    {
+      "epoch": 0.06464646464646465,
+      "grad_norm": 0.011715452186763287,
+      "learning_rate": 9.994470754481315e-05,
+      "loss": 0.49884777069091796,
+      "step": 200
+    },
+    {
+      "epoch": 0.06787878787878789,
+      "grad_norm": 0.010746965184807777,
+      "learning_rate": 9.991672636668239e-05,
+      "loss": 0.5068713188171386,
+      "step": 210
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.012883410789072514,
+      "learning_rate": 9.988304167426519e-05,
+      "loss": 0.4920186519622803,
+      "step": 220
+    },
+    {
+      "epoch": 0.07434343434343435,
+      "grad_norm": 0.011187366209924221,
+      "learning_rate": 9.984365731639419e-05,
+      "loss": 0.5021648406982422,
+      "step": 230
+    },
+    {
+      "epoch": 0.07757575757575758,
+      "grad_norm": 0.010671757161617279,
+      "learning_rate": 9.979857779314906e-05,
+      "loss": 0.5038897514343261,
+      "step": 240
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.01044373121112585,
+      "learning_rate": 9.974780825534246e-05,
+      "loss": 0.4965065956115723,
+      "step": 250
+    },
+    {
+      "epoch": 0.08404040404040404,
+      "grad_norm": 0.010565251111984253,
+      "learning_rate": 9.969135450393141e-05,
+      "loss": 0.5145994186401367,
+      "step": 260
+    },
+    {
+      "epoch": 0.08727272727272728,
+      "grad_norm": 0.010024026967585087,
+      "learning_rate": 9.96292229893545e-05,
+      "loss": 0.505019235610962,
+      "step": 270
+    },
+    {
+      "epoch": 0.0905050505050505,
+      "grad_norm": 0.010430407710373402,
+      "learning_rate": 9.956142081079484e-05,
+      "loss": 0.5115808010101318,
+      "step": 280
+    },
+    {
+      "epoch": 0.09373737373737374,
+      "grad_norm": 0.010048807598650455,
+      "learning_rate": 9.948795571536891e-05,
+      "loss": 0.48525152206420896,
+      "step": 290
+    },
+    {
+      "epoch": 0.09696969696969697,
+      "grad_norm": 0.010108387097716331,
+      "learning_rate": 9.94088360972414e-05,
+      "loss": 0.5002010822296142,
+      "step": 300
+    },
+    {
+      "epoch": 0.10020202020202021,
+      "grad_norm": 0.010273640975356102,
+      "learning_rate": 9.932407099666608e-05,
+      "loss": 0.49662046432495116,
+      "step": 310
+    },
+    {
+      "epoch": 0.10343434343434343,
+      "grad_norm": 0.00995971355587244,
+      "learning_rate": 9.923367009895274e-05,
+      "loss": 0.48578290939331054,
+      "step": 320
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.010459775105118752,
+      "learning_rate": 9.913764373336079e-05,
+      "loss": 0.48862767219543457,
+      "step": 330
+    },
+    {
+      "epoch": 0.1098989898989899,
+      "grad_norm": 0.009838269092142582,
+      "learning_rate": 9.903600287191875e-05,
+      "loss": 0.5034208774566651,
+      "step": 340
+    },
+    {
+      "epoch": 0.11313131313131314,
+      "grad_norm": 0.00978950597345829,
+      "learning_rate": 9.892875912817079e-05,
+      "loss": 0.4870161533355713,
+      "step": 350
+    },
+    {
+      "epoch": 0.11636363636363636,
+      "grad_norm": 0.01030043140053749,
+      "learning_rate": 9.881592475584964e-05,
+      "loss": 0.5026071548461915,
+      "step": 360
+    },
+    {
+      "epoch": 0.1195959595959596,
+      "grad_norm": 0.010531975887715816,
+      "learning_rate": 9.869751264747656e-05,
+      "loss": 0.4883917808532715,
+      "step": 370
+    },
+    {
+      "epoch": 0.12282828282828283,
+      "grad_norm": 0.00986825954169035,
+      "learning_rate": 9.857353633288814e-05,
+      "loss": 0.4927018165588379,
+      "step": 380
+    },
+    {
+      "epoch": 0.12606060606060607,
+      "grad_norm": 0.009432349354028702,
+      "learning_rate": 9.844400997769043e-05,
+      "loss": 0.4908174514770508,
+      "step": 390
+    },
+    {
+      "epoch": 0.1292929292929293,
+      "grad_norm": 0.01057665515691042,
+      "learning_rate": 9.83089483816404e-05,
+      "loss": 0.5069625854492188,
+      "step": 400
+    },
+    {
+      "epoch": 0.13252525252525252,
+      "grad_norm": 0.010007908567786217,
+      "learning_rate": 9.816836697695482e-05,
+      "loss": 0.4988056182861328,
+      "step": 410
+    },
+    {
+      "epoch": 0.13575757575757577,
+      "grad_norm": 0.010027808137238026,
+      "learning_rate": 9.802228182654702e-05,
+      "loss": 0.5007385730743408,
+      "step": 420
+    },
+    {
+      "epoch": 0.138989898989899,
+      "grad_norm": 0.009953738190233707,
+      "learning_rate": 9.787070962219156e-05,
+      "loss": 0.5130783081054687,
+      "step": 430
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.010204462334513664,
+      "learning_rate": 9.771366768261696e-05,
+      "loss": 0.4947535514831543,
+      "step": 440
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 0.009612451307475567,
+      "learning_rate": 9.755117395152689e-05,
+      "loss": 0.4917112350463867,
+      "step": 450
+    },
+    {
+      "epoch": 0.1486868686868687,
+      "grad_norm": 0.00995573028922081,
+      "learning_rate": 9.73832469955499e-05,
+      "loss": 0.4882859230041504,
+      "step": 460
+    },
+    {
+      "epoch": 0.15191919191919193,
+      "grad_norm": 0.009584570303559303,
+      "learning_rate": 9.720990600211797e-05,
+      "loss": 0.500526762008667,
+      "step": 470
+    },
+    {
+      "epoch": 0.15515151515151515,
+      "grad_norm": 0.010585076175630093,
+      "learning_rate": 9.703117077727419e-05,
+      "loss": 0.496882963180542,
+      "step": 480
+    },
+    {
+      "epoch": 0.15838383838383838,
+      "grad_norm": 0.009859723038971424,
+      "learning_rate": 9.684706174340965e-05,
+      "loss": 0.48728485107421876,
+      "step": 490
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.010212041437625885,
+      "learning_rate": 9.665759993693e-05,
+      "loss": 0.49378366470336915,
+      "step": 500
+    },
+    {
+      "epoch": 0.16484848484848486,
+      "grad_norm": 0.009744231589138508,
+      "learning_rate": 9.646280700585185e-05,
+      "loss": 0.4663555145263672,
+      "step": 510
+    },
+    {
+      "epoch": 0.16808080808080808,
+      "grad_norm": 0.009789686650037766,
+      "learning_rate": 9.626270520732916e-05,
+      "loss": 0.4879913330078125,
+      "step": 520
+    },
+    {
+      "epoch": 0.1713131313131313,
+      "grad_norm": 0.009891769848763943,
+      "learning_rate": 9.605731740511022e-05,
+      "loss": 0.48809428215026857,
+      "step": 530
+    },
+    {
+      "epoch": 0.17454545454545456,
+      "grad_norm": 0.01002143882215023,
+      "learning_rate": 9.584666706692517e-05,
+      "loss": 0.4959606170654297,
+      "step": 540
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.009208496659994125,
+      "learning_rate": 9.56307782618046e-05,
+      "loss": 0.4878594398498535,
+      "step": 550
+    },
+    {
+      "epoch": 0.181010101010101,
+      "grad_norm": 0.009645081125199795,
+      "learning_rate": 9.540967565732937e-05,
+      "loss": 0.4769869804382324,
+      "step": 560
+    },
+    {
+      "epoch": 0.18424242424242424,
+      "grad_norm": 0.010497638955712318,
+      "learning_rate": 9.51833845168121e-05,
+      "loss": 0.4970097064971924,
+      "step": 570
+    },
+    {
+      "epoch": 0.1874747474747475,
+      "grad_norm": 0.010612033307552338,
+      "learning_rate": 9.495193069641057e-05,
+      "loss": 0.4945381164550781,
+      "step": 580
+    },
+    {
+      "epoch": 0.1907070707070707,
+      "grad_norm": 0.009433986619114876,
+      "learning_rate": 9.47153406421734e-05,
+      "loss": 0.4860210418701172,
+      "step": 590
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 0.009995914995670319,
+      "learning_rate": 9.447364138701823e-05,
+      "loss": 0.4904911994934082,
+      "step": 600
+    },
+    {
+      "epoch": 0.19717171717171716,
+      "grad_norm": 0.009814019314944744,
+      "learning_rate": 9.422686054764302e-05,
+      "loss": 0.4915336608886719,
+      "step": 610
+    },
+    {
+      "epoch": 0.20040404040404042,
+      "grad_norm": 0.010199982672929764,
+      "learning_rate": 9.397502632137055e-05,
+      "loss": 0.4805011749267578,
+      "step": 620
+    },
+    {
+      "epoch": 0.20363636363636364,
+      "grad_norm": 0.010121874511241913,
+      "learning_rate": 9.371816748292641e-05,
+      "loss": 0.47633209228515627,
+      "step": 630
+    },
+    {
+      "epoch": 0.20686868686868687,
+      "grad_norm": 0.009638865478336811,
+      "learning_rate": 9.345631338115141e-05,
+      "loss": 0.48993511199951173,
+      "step": 640
+    },
+    {
+      "epoch": 0.2101010101010101,
+      "grad_norm": 0.010041174478828907,
+      "learning_rate": 9.318949393564807e-05,
+      "loss": 0.4798978328704834,
+      "step": 650
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.010145517997443676,
+      "learning_rate": 9.291773963336193e-05,
+      "loss": 0.4696659564971924,
+      "step": 660
+    },
+    {
+      "epoch": 0.21656565656565657,
+      "grad_norm": 0.01043335534632206,
+      "learning_rate": 9.264108152509816e-05,
+      "loss": 0.4955574035644531,
+      "step": 670
+    },
+    {
+      "epoch": 0.2197979797979798,
+      "grad_norm": 0.010406569577753544,
+      "learning_rate": 9.235955122197368e-05,
+      "loss": 0.48659563064575195,
+      "step": 680
+    },
+    {
+      "epoch": 0.22303030303030302,
+      "grad_norm": 0.009870355017483234,
+      "learning_rate": 9.207318089180524e-05,
+      "loss": 0.4766091823577881,
+      "step": 690
+    },
+    {
+      "epoch": 0.22626262626262628,
+      "grad_norm": 0.009980005212128162,
+      "learning_rate": 9.178200325543384e-05,
+      "loss": 0.5022068023681641,
+      "step": 700
+    },
+    {
+      "epoch": 0.2294949494949495,
+      "grad_norm": 0.009765878319740295,
+      "learning_rate": 9.148605158298621e-05,
+      "loss": 0.48309478759765623,
+      "step": 710
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.009879437275230885,
+      "learning_rate": 9.118535969007314e-05,
+      "loss": 0.4793684959411621,
+      "step": 720
+    },
+    {
+      "epoch": 0.23595959595959595,
+      "grad_norm": 0.009907045401632786,
+      "learning_rate": 9.087996193392578e-05,
+      "loss": 0.49844112396240237,
+      "step": 730
+    },
+    {
+      "epoch": 0.2391919191919192,
+      "grad_norm": 0.009958872571587563,
+      "learning_rate": 9.056989320947e-05,
+      "loss": 0.48113102912902833,
+      "step": 740
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.010206855833530426,
+      "learning_rate": 9.025518894533921e-05,
+      "loss": 0.5048784255981446,
+      "step": 750
+    },
+    {
+      "epoch": 0.24565656565656566,
+      "grad_norm": 0.009286429733037949,
+      "learning_rate": 8.99358850998263e-05,
+      "loss": 0.4862624168395996,
+      "step": 760
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.009919015690684319,
+      "learning_rate": 8.9612018156775e-05,
+      "loss": 0.48739056587219237,
+      "step": 770
+    },
+    {
+      "epoch": 0.25212121212121213,
+      "grad_norm": 0.010435211472213268,
+      "learning_rate": 8.928362512141124e-05,
+      "loss": 0.48689990043640136,
+      "step": 780
+    },
+    {
+      "epoch": 0.25535353535353533,
+      "grad_norm": 0.009992080740630627,
+      "learning_rate": 8.895074351611488e-05,
+      "loss": 0.4848791599273682,
+      "step": 790
+    },
+    {
+      "epoch": 0.2585858585858586,
+      "grad_norm": 0.010449117980897427,
+      "learning_rate": 8.861341137613242e-05,
+      "loss": 0.49130568504333494,
+      "step": 800
+    },
+    {
+      "epoch": 0.26181818181818184,
+      "grad_norm": 0.010061345063149929,
+      "learning_rate": 8.827166724523105e-05,
+      "loss": 0.49056081771850585,
+      "step": 810
+    },
+    {
+      "epoch": 0.26505050505050504,
+      "grad_norm": 0.009908635169267654,
+      "learning_rate": 8.792555017129461e-05,
+      "loss": 0.4706866264343262,
+      "step": 820
+    },
+    {
+      "epoch": 0.2682828282828283,
+      "grad_norm": 0.010003669187426567,
+      "learning_rate": 8.757509970186196e-05,
+      "loss": 0.48719348907470705,
+      "step": 830
+    },
+    {
+      "epoch": 0.27151515151515154,
+      "grad_norm": 0.009513127617537975,
+      "learning_rate": 8.722035587960826e-05,
+      "loss": 0.48200483322143556,
+      "step": 840
+    },
+    {
+      "epoch": 0.27474747474747474,
+      "grad_norm": 0.009142451919615269,
+      "learning_rate": 8.686135923776969e-05,
+      "loss": 0.48613176345825193,
+      "step": 850
+    },
+    {
+      "epoch": 0.277979797979798,
+      "grad_norm": 0.00980432890355587,
+      "learning_rate": 8.649815079551205e-05,
+      "loss": 0.4976047515869141,
+      "step": 860
+    },
+    {
+      "epoch": 0.2812121212121212,
+      "grad_norm": 0.010442109778523445,
+      "learning_rate": 8.613077205324389e-05,
+      "loss": 0.48451838493347166,
+      "step": 870
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.009309548884630203,
+      "learning_rate": 8.575926498787476e-05,
+      "loss": 0.5115366458892823,
+      "step": 880
+    },
+    {
+      "epoch": 0.2876767676767677,
+      "grad_norm": 0.009093924425542355,
+      "learning_rate": 8.538367204801872e-05,
+      "loss": 0.48187432289123533,
+      "step": 890
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.009757987223565578,
+      "learning_rate": 8.500403614914432e-05,
+      "loss": 0.4882505416870117,
+      "step": 900
+    },
+    {
+      "epoch": 0.29414141414141415,
+      "grad_norm": 0.010261048562824726,
+      "learning_rate": 8.462040066867089e-05,
+      "loss": 0.49068965911865237,
+      "step": 910
+    },
+    {
+      "epoch": 0.2973737373737374,
+      "grad_norm": 0.009317740797996521,
+      "learning_rate": 8.423280944101233e-05,
+      "loss": 0.4966132164001465,
+      "step": 920
+    },
+    {
+      "epoch": 0.3006060606060606,
+      "grad_norm": 0.009787693619728088,
+      "learning_rate": 8.384130675256852e-05,
+      "loss": 0.4754981994628906,
+      "step": 930
+    },
+    {
+      "epoch": 0.30383838383838385,
+      "grad_norm": 0.010005015879869461,
+      "learning_rate": 8.34459373366651e-05,
+      "loss": 0.4735103130340576,
+      "step": 940
+    },
+    {
+      "epoch": 0.30707070707070705,
+      "grad_norm": 0.009837017394602299,
+      "learning_rate": 8.304674636844231e-05,
+      "loss": 0.4809592247009277,
+      "step": 950
+    },
+    {
+      "epoch": 0.3103030303030303,
+      "grad_norm": 0.009590484201908112,
+      "learning_rate": 8.264377945969312e-05,
+      "loss": 0.48206100463867185,
+      "step": 960
+    },
+    {
+      "epoch": 0.31353535353535356,
+      "grad_norm": 0.009699508547782898,
+      "learning_rate": 8.223708265365174e-05,
+      "loss": 0.48718748092651365,
+      "step": 970
+    },
+    {
+      "epoch": 0.31676767676767675,
+      "grad_norm": 0.010278215631842613,
+      "learning_rate": 8.182670241973253e-05,
+      "loss": 0.4952278137207031,
+      "step": 980
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.010104077868163586,
+      "learning_rate": 8.141268564822053e-05,
+      "loss": 0.47769975662231445,
+      "step": 990
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.009301737882196903,
+      "learning_rate": 8.099507964491369e-05,
+      "loss": 0.4862718105316162,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32646464646464646,
+      "grad_norm": 0.009307135827839375,
+      "learning_rate": 8.057393212571767e-05,
+      "loss": 0.49833106994628906,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3296969696969697,
+      "grad_norm": 0.009420682676136494,
+      "learning_rate": 8.014929121119378e-05,
+      "loss": 0.48829941749572753,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3329292929292929,
+      "grad_norm": 0.010058379732072353,
+      "learning_rate": 7.972120542106077e-05,
+      "loss": 0.46506147384643554,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33616161616161616,
+      "grad_norm": 0.009461579844355583,
+      "learning_rate": 7.92897236686508e-05,
+      "loss": 0.47866268157958985,
+      "step": 1040
+    },
+    {
+      "epoch": 0.3393939393939394,
+      "grad_norm": 0.010341835208237171,
+      "learning_rate": 7.885489525532075e-05,
+      "loss": 0.4966601371765137,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3426262626262626,
+      "grad_norm": 0.01042103860527277,
+      "learning_rate": 7.84167698648189e-05,
+      "loss": 0.49251084327697753,
+      "step": 1060
+    },
+    {
+      "epoch": 0.34585858585858587,
+      "grad_norm": 0.010442749597132206,
+      "learning_rate": 7.797539755760805e-05,
+      "loss": 0.4816086769104004,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3490909090909091,
+      "grad_norm": 0.010256553068757057,
+      "learning_rate": 7.753082876514562e-05,
+      "loss": 0.47102947235107423,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3523232323232323,
+      "grad_norm": 0.009399017319083214,
+      "learning_rate": 7.708311428412129e-05,
+      "loss": 0.4810478210449219,
+      "step": 1090
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.009499317966401577,
+      "learning_rate": 7.663230527065293e-05,
+      "loss": 0.47051143646240234,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35878787878787877,
+      "grad_norm": 0.009759469889104366,
+      "learning_rate": 7.617845323444156e-05,
+      "loss": 0.4780744552612305,
+      "step": 1110
+    },
+    {
+      "epoch": 0.362020202020202,
+      "grad_norm": 0.00987281370908022,
+      "learning_rate": 7.572161003288565e-05,
+      "loss": 0.4804032325744629,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3652525252525253,
+      "grad_norm": 0.00963522493839264,
+      "learning_rate": 7.526182786515609e-05,
+      "loss": 0.48206367492675783,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36848484848484847,
+      "grad_norm": 0.009587026201188564,
+      "learning_rate": 7.479915926623165e-05,
+      "loss": 0.49240264892578123,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3717171717171717,
+      "grad_norm": 0.009810036048293114,
+      "learning_rate": 7.433365710089646e-05,
+      "loss": 0.48599681854248045,
+      "step": 1150
+    },
+    {
+      "epoch": 0.374949494949495,
+      "grad_norm": 0.00978278461843729,
+      "learning_rate": 7.386537455769963e-05,
+      "loss": 0.4688436031341553,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3781818181818182,
+      "grad_norm": 0.00925996620208025,
+      "learning_rate": 7.339436514287783e-05,
+      "loss": 0.47986507415771484,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3814141414141414,
+      "grad_norm": 0.010006657801568508,
+      "learning_rate": 7.292068267424165e-05,
+      "loss": 0.4771553993225098,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3846464646464646,
+      "grad_norm": 0.010299976915121078,
+      "learning_rate": 7.244438127502647e-05,
+      "loss": 0.4854436874389648,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3878787878787879,
+      "grad_norm": 0.009807374328374863,
+      "learning_rate": 7.196551536770807e-05,
+      "loss": 0.4763533592224121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.010062369517982006,
+      "learning_rate": 7.148413966778451e-05,
+      "loss": 0.47457141876220704,
+      "step": 1210
+    },
+    {
+      "epoch": 0.39434343434343433,
+      "grad_norm": 0.009904388338327408,
+      "learning_rate": 7.100030917752423e-05,
+      "loss": 0.4732469081878662,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3975757575757576,
+      "grad_norm": 0.009578046388924122,
+      "learning_rate": 7.051407917968138e-05,
+      "loss": 0.47551660537719725,
+      "step": 1230
+    },
+    {
+      "epoch": 0.40080808080808084,
+      "grad_norm": 0.010024272836744785,
+      "learning_rate": 7.002550523117926e-05,
+      "loss": 0.4835049629211426,
+      "step": 1240
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.010056886821985245,
+      "learning_rate": 6.953464315676241e-05,
+      "loss": 0.4909071922302246,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4072727272727273,
+      "grad_norm": 0.009707778692245483,
+      "learning_rate": 6.904154904261792e-05,
+      "loss": 0.4842695236206055,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4105050505050505,
+      "grad_norm": 0.00976107269525528,
+      "learning_rate": 6.8546279229967e-05,
+      "loss": 0.48967390060424804,
+      "step": 1270
+    },
+    {
+      "epoch": 0.41373737373737374,
+      "grad_norm": 0.010392800904810429,
+      "learning_rate": 6.804889030862753e-05,
+      "loss": 0.48658218383789065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.416969696969697,
+      "grad_norm": 0.009267269633710384,
+      "learning_rate": 6.754943911054793e-05,
+      "loss": 0.48893008232116697,
+      "step": 1290
+    },
+    {
+      "epoch": 0.4202020202020202,
+      "grad_norm": 0.009753459133207798,
+      "learning_rate": 6.704798270331358e-05,
+      "loss": 0.49384117126464844,
+      "step": 1300
+    },
+    {
+      "epoch": 0.42343434343434344,
+      "grad_norm": 0.011121846735477448,
+      "learning_rate": 6.654457838362621e-05,
+      "loss": 0.47458324432373045,
+      "step": 1310
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.009406324476003647,
+      "learning_rate": 6.603928367075718e-05,
+      "loss": 0.4703402519226074,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4298989898989899,
+      "grad_norm": 0.010009719990193844,
+      "learning_rate": 6.553215629997529e-05,
+      "loss": 0.4851715087890625,
+      "step": 1330
+    },
+    {
+      "epoch": 0.43313131313131314,
+      "grad_norm": 0.009798573330044746,
+      "learning_rate": 6.502325421594988e-05,
+      "loss": 0.4779622554779053,
+      "step": 1340
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.0098969591781497,
+      "learning_rate": 6.451263556613007e-05,
+      "loss": 0.4708548545837402,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4395959595959596,
+      "grad_norm": 0.009853474795818329,
+      "learning_rate": 6.40003586941008e-05,
+      "loss": 0.4721970558166504,
+      "step": 1360
+    },
+    {
+      "epoch": 0.44282828282828285,
+      "grad_norm": 0.009663710370659828,
+      "learning_rate": 6.348648213291642e-05,
+      "loss": 0.4798272132873535,
+      "step": 1370
+    },
+    {
+      "epoch": 0.44606060606060605,
+      "grad_norm": 0.009419051930308342,
+      "learning_rate": 6.297106459841272e-05,
+      "loss": 0.471483039855957,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4492929292929293,
+      "grad_norm": 0.009978282265365124,
+      "learning_rate": 6.245416498249801e-05,
+      "loss": 0.4772329330444336,
+      "step": 1390
+    },
+    {
+      "epoch": 0.45252525252525255,
+      "grad_norm": 0.009491856209933758,
+      "learning_rate": 6.193584234642403e-05,
+      "loss": 0.48812179565429686,
+      "step": 1400
+    },
+    {
+      "epoch": 0.45575757575757575,
+      "grad_norm": 0.010496517643332481,
+      "learning_rate": 6.141615591403771e-05,
+      "loss": 0.48897976875305177,
+      "step": 1410
+    },
+    {
+      "epoch": 0.458989898989899,
+      "grad_norm": 0.01015474647283554,
+      "learning_rate": 6.0895165065014106e-05,
+      "loss": 0.4850447654724121,
+      "step": 1420
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.009763741865754128,
+      "learning_rate": 6.037292932807167e-05,
+      "loss": 0.4857158660888672,
+      "step": 1430
+    },
+    {
+      "epoch": 0.46545454545454545,
+      "grad_norm": 0.009874231182038784,
+      "learning_rate": 5.984950837417048e-05,
+      "loss": 0.4844364166259766,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4686868686868687,
+      "grad_norm": 0.010104037821292877,
+      "learning_rate": 5.932496200969422e-05,
+      "loss": 0.47542514801025393,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4719191919191919,
+      "grad_norm": 0.009445435367524624,
+      "learning_rate": 5.879935016961661e-05,
+      "loss": 0.48579182624816897,
+      "step": 1460
+    },
+    {
+      "epoch": 0.47515151515151516,
+      "grad_norm": 0.010507128201425076,
+      "learning_rate": 5.827273291065326e-05,
+      "loss": 0.48273677825927735,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4783838383838384,
+      "grad_norm": 0.009411566890776157,
+      "learning_rate": 5.7745170404399484e-05,
+      "loss": 0.46429009437561036,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4816161616161616,
+      "grad_norm": 0.010377817787230015,
+      "learning_rate": 5.721672293045518e-05,
+      "loss": 0.49172677993774416,
+      "step": 1490
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.009920118376612663,
+      "learning_rate": 5.668745086953712e-05,
+      "loss": 0.4934688568115234,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48808080808080806,
+      "grad_norm": 0.012272641994059086,
+      "learning_rate": 5.615741469657985e-05,
+      "loss": 0.4826413631439209,
+      "step": 1510
+    },
+    {
+      "epoch": 0.4913131313131313,
+      "grad_norm": 0.00981989037245512,
+      "learning_rate": 5.562667497382582e-05,
+      "loss": 0.48468503952026365,
+      "step": 1520
+    },
+    {
+      "epoch": 0.49454545454545457,
+      "grad_norm": 0.010148138739168644,
+      "learning_rate": 5.509529234390553e-05,
+      "loss": 0.47773942947387693,
+      "step": 1530
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.010528397746384144,
+      "learning_rate": 5.456332752290837e-05,
+      "loss": 0.47507562637329104,
+      "step": 1540
+    },
+    {
+      "epoch": 0.501010101010101,
+      "grad_norm": 0.01076479908078909,
+      "learning_rate": 5.4030841293445244e-05,
+      "loss": 0.486495304107666,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5042424242424243,
+      "grad_norm": 0.009976644068956375,
+      "learning_rate": 5.349789449770351e-05,
+      "loss": 0.48320484161376953,
+      "step": 1560
+    },
+    {
+      "epoch": 0.5074747474747475,
+      "grad_norm": 0.010504718869924545,
+      "learning_rate": 5.2964548030495065e-05,
+      "loss": 0.48847188949584963,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5107070707070707,
+      "grad_norm": 0.010325642302632332,
+      "learning_rate": 5.243086283229852e-05,
+      "loss": 0.47591514587402345,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5139393939393939,
+      "grad_norm": 0.010260741226375103,
+      "learning_rate": 5.18968998822961e-05,
+      "loss": 0.48136124610900877,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5171717171717172,
+      "grad_norm": 0.010797196067869663,
+      "learning_rate": 5.1362720191406065e-05,
+      "loss": 0.48076438903808594,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5204040404040404,
+      "grad_norm": 0.010010522790253162,
+      "learning_rate": 5.082838479531169e-05,
+      "loss": 0.5004307270050049,
+      "step": 1610
+    },
+    {
+      "epoch": 0.5236363636363637,
+      "grad_norm": 0.010120037943124771,
+      "learning_rate": 5.029395474748714e-05,
+      "loss": 0.4812767028808594,
+      "step": 1620
+    },
+    {
+      "epoch": 0.5268686868686868,
+      "grad_norm": 0.009431752376258373,
+      "learning_rate": 4.975949111222158e-05,
+      "loss": 0.4887521743774414,
+      "step": 1630
+    },
+    {
+      "epoch": 0.5301010101010101,
+      "grad_norm": 0.010080527514219284,
+      "learning_rate": 4.9225054957641916e-05,
+      "loss": 0.48248910903930664,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.009522376582026482,
+      "learning_rate": 4.8690707348735035e-05,
+      "loss": 0.4855649948120117,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5365656565656566,
+      "grad_norm": 0.009686745703220367,
+      "learning_rate": 4.8156509340370605e-05,
+      "loss": 0.47187280654907227,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5397979797979798,
+      "grad_norm": 0.011875285767018795,
+      "learning_rate": 4.762252197032482e-05,
+      "loss": 0.46579513549804685,
+      "step": 1670
+    },
+    {
+      "epoch": 0.5430303030303031,
+      "grad_norm": 0.009932303801178932,
+      "learning_rate": 4.7088806252306224e-05,
+      "loss": 0.47946829795837403,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5462626262626262,
+      "grad_norm": 0.017099183052778244,
+      "learning_rate": 4.655542316898423e-05,
+      "loss": 0.4593667030334473,
+      "step": 1690
+    },
+    {
+      "epoch": 0.5494949494949495,
+      "grad_norm": 0.010512005537748337,
+      "learning_rate": 4.6022433665021246e-05,
+      "loss": 0.48582897186279295,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5527272727272727,
+      "grad_norm": 0.00989206787198782,
+      "learning_rate": 4.548989864010902e-05,
+      "loss": 0.4849580764770508,
+      "step": 1710
+    },
+    {
+      "epoch": 0.555959595959596,
+      "grad_norm": 0.010284029878675938,
+      "learning_rate": 4.495787894201031e-05,
+      "loss": 0.49089298248291013,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5591919191919192,
+      "grad_norm": 0.00992760993540287,
+      "learning_rate": 4.442643535960631e-05,
+      "loss": 0.48010549545288084,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5624242424242424,
+      "grad_norm": 0.00978371873497963,
+      "learning_rate": 4.3895628615950864e-05,
+      "loss": 0.47594566345214845,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.00981004349887371,
+      "learning_rate": 4.3365519361332345e-05,
+      "loss": 0.48056421279907224,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.010216868482530117,
+      "learning_rate": 4.283616816634353e-05,
+      "loss": 0.47501134872436523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5721212121212121,
+      "grad_norm": 0.010267022997140884,
+      "learning_rate": 4.230763551496089e-05,
+      "loss": 0.478366756439209,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5753535353535354,
+      "grad_norm": 0.009910739958286285,
+      "learning_rate": 4.1779981797633645e-05,
+      "loss": 0.478058385848999,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5785858585858585,
+      "grad_norm": 0.011339185759425163,
+      "learning_rate": 4.1253267304383455e-05,
+      "loss": 0.48466057777404786,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 0.009522072039544582,
+      "learning_rate": 4.072755221791572e-05,
+      "loss": 0.4769908905029297,
+      "step": 1800
+    },
+    {
+      "epoch": 0.585050505050505,
+      "grad_norm": 0.009808518923819065,
+      "learning_rate": 4.020289660674306e-05,
+      "loss": 0.47162666320800783,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5882828282828283,
+      "grad_norm": 0.009962448850274086,
+      "learning_rate": 3.967936041832173e-05,
+      "loss": 0.46282405853271485,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5915151515151515,
+      "grad_norm": 0.009498678147792816,
+      "learning_rate": 3.9157003472202246e-05,
+      "loss": 0.4794480323791504,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5947474747474748,
+      "grad_norm": 0.009407177567481995,
+      "learning_rate": 3.863588545319407e-05,
+      "loss": 0.4729412078857422,
+      "step": 1840
+    },
+    {
+      "epoch": 0.597979797979798,
+      "grad_norm": 0.009899895638227463,
+      "learning_rate": 3.8116065904546196e-05,
+      "loss": 0.47380704879760743,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6012121212121212,
+      "grad_norm": 0.009560837410390377,
+      "learning_rate": 3.759760422114362e-05,
+      "loss": 0.47751388549804685,
+      "step": 1860
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.010970192961394787,
+      "learning_rate": 3.708055964272088e-05,
+      "loss": 0.47801823616027833,
+      "step": 1870
+    },
+    {
+      "epoch": 0.6076767676767677,
+      "grad_norm": 0.00964390765875578,
+      "learning_rate": 3.6564991247093234e-05,
+      "loss": 0.4800426483154297,
+      "step": 1880
+    },
+    {
+      "epoch": 0.610909090909091,
+      "grad_norm": 0.009764602407813072,
+      "learning_rate": 3.6050957943406465e-05,
+      "loss": 0.4812753677368164,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6141414141414141,
+      "grad_norm": 0.009959314949810505,
+      "learning_rate": 3.553851846540584e-05,
+      "loss": 0.47804956436157225,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6173737373737374,
+      "grad_norm": 0.010666392743587494,
+      "learning_rate": 3.50277313647252e-05,
+      "loss": 0.4772273063659668,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6206060606060606,
+      "grad_norm": 0.009173358790576458,
+      "learning_rate": 3.451865500419676e-05,
+      "loss": 0.4892144203186035,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6238383838383839,
+      "grad_norm": 0.010000358335673809,
+      "learning_rate": 3.401134755118256e-05,
+      "loss": 0.48959059715270997,
+      "step": 1930
+    },
+    {
+      "epoch": 0.6270707070707071,
+      "grad_norm": 0.010190536268055439,
+      "learning_rate": 3.350586697092826e-05,
+      "loss": 0.46478729248046874,
+      "step": 1940
+    },
+    {
+      "epoch": 0.6303030303030303,
+      "grad_norm": 0.010812178254127502,
+      "learning_rate": 3.300227101993998e-05,
+      "loss": 0.5046152114868164,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6335353535353535,
+      "grad_norm": 0.01017849799245596,
+      "learning_rate": 3.2500617239384947e-05,
+      "loss": 0.4698008060455322,
+      "step": 1960
+    },
+    {
+      "epoch": 0.6367676767676768,
+      "grad_norm": 0.011103908531367779,
+      "learning_rate": 3.200096294851691e-05,
+      "loss": 0.4716217041015625,
+      "step": 1970
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.009982883930206299,
+      "learning_rate": 3.150336523812674e-05,
+      "loss": 0.47135162353515625,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6432323232323233,
+      "grad_norm": 0.01043197326362133,
+      "learning_rate": 3.100788096401925e-05,
+      "loss": 0.4799614906311035,
+      "step": 1990
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.010667623952031136,
+      "learning_rate": 3.051456674051677e-05,
+      "loss": 0.4682164192199707,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6496969696969697,
+      "grad_norm": 0.010620036162436008,
+      "learning_rate": 3.0023478933990347e-05,
+      "loss": 0.4750208854675293,
+      "step": 2010
+    },
+    {
+      "epoch": 0.6529292929292929,
+      "grad_norm": 0.010374991223216057,
+      "learning_rate": 2.9534673656419377e-05,
+      "loss": 0.48034076690673827,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6561616161616162,
+      "grad_norm": 0.011932817287743092,
+      "learning_rate": 2.9048206758980136e-05,
+      "loss": 0.46314101219177245,
+      "step": 2030
+    },
+    {
+      "epoch": 0.6593939393939394,
+      "grad_norm": 0.01039852574467659,
+      "learning_rate": 2.856413382566425e-05,
+      "loss": 0.4783937454223633,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6626262626262627,
+      "grad_norm": 0.010200604796409607,
+      "learning_rate": 2.8082510166927583e-05,
+      "loss": 0.4792025089263916,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6658585858585858,
+      "grad_norm": 0.009561127051711082,
+      "learning_rate": 2.760339081337041e-05,
+      "loss": 0.4722686767578125,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6690909090909091,
+      "grad_norm": 0.00924921128898859,
+      "learning_rate": 2.7126830509449773e-05,
+      "loss": 0.4884464263916016,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6723232323232323,
+      "grad_norm": 0.00991444569081068,
+      "learning_rate": 2.6652883707224075e-05,
+      "loss": 0.4804549217224121,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.009902069345116615,
+      "learning_rate": 2.618160456013153e-05,
+      "loss": 0.4781071186065674,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 0.010504493489861488,
+      "learning_rate": 2.571304691680255e-05,
+      "loss": 0.48059587478637694,
+      "step": 2100
+    },
+    {
+      "epoch": 0.682020202020202,
+      "grad_norm": 0.009641965851187706,
+      "learning_rate": 2.5247264314906917e-05,
+      "loss": 0.4706240177154541,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6852525252525252,
+      "grad_norm": 0.010276644490659237,
+      "learning_rate": 2.4784309975036513e-05,
+      "loss": 0.4885101318359375,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6884848484848485,
+      "grad_norm": 0.010960405692458153,
+      "learning_rate": 2.4324236794624456e-05,
+      "loss": 0.4882383346557617,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6917171717171717,
+      "grad_norm": 0.010282796807587147,
+      "learning_rate": 2.386709734190079e-05,
+      "loss": 0.4768857479095459,
+      "step": 2140
+    },
+    {
+      "epoch": 0.694949494949495,
+      "grad_norm": 0.010104385204613209,
+      "learning_rate": 2.34129438498862e-05,
+      "loss": 0.4802837371826172,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6981818181818182,
+      "grad_norm": 0.010027035139501095,
+      "learning_rate": 2.296182821042374e-05,
+      "loss": 0.4874839782714844,
+      "step": 2160
+    },
+    {
+      "epoch": 0.7014141414141414,
+      "grad_norm": 0.010018851608037949,
+      "learning_rate": 2.2513801968249644e-05,
+      "loss": 0.4758561134338379,
+      "step": 2170
+    },
+    {
+      "epoch": 0.7046464646464646,
+      "grad_norm": 0.009862969629466534,
+      "learning_rate": 2.2068916315103783e-05,
+      "loss": 0.4686488151550293,
+      "step": 2180
+    },
+    {
+      "epoch": 0.7078787878787879,
+      "grad_norm": 0.00952910166233778,
+      "learning_rate": 2.162722208388057e-05,
+      "loss": 0.4782154083251953,
+      "step": 2190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.010213647037744522,
+      "learning_rate": 2.1188769742820625e-05,
+      "loss": 0.4773773193359375,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7143434343434344,
+      "grad_norm": 0.010498392395675182,
+      "learning_rate": 2.075360938974429e-05,
+      "loss": 0.4733907222747803,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7175757575757575,
+      "grad_norm": 0.009394815191626549,
+      "learning_rate": 2.03217907463275e-05,
+      "loss": 0.47564210891723635,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7208080808080808,
+      "grad_norm": 0.010383618995547295,
+      "learning_rate": 1.989336315242048e-05,
+      "loss": 0.4784512519836426,
+      "step": 2230
+    },
+    {
+      "epoch": 0.724040404040404,
+      "grad_norm": 0.01043599285185337,
+      "learning_rate": 1.9468375560410117e-05,
+      "loss": 0.4808964729309082,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.009953988716006279,
+      "learning_rate": 1.90468765296267e-05,
+      "loss": 0.49031834602355956,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7305050505050505,
+      "grad_norm": 0.010356656275689602,
+      "learning_rate": 1.8628914220795494e-05,
+      "loss": 0.48055601119995117,
+      "step": 2260
+    },
+    {
+      "epoch": 0.7337373737373737,
+      "grad_norm": 0.009841440245509148,
+      "learning_rate": 1.8214536390533822e-05,
+      "loss": 0.47170586585998536,
+      "step": 2270
+    },
+    {
+      "epoch": 0.7369696969696969,
+      "grad_norm": 0.010102550499141216,
+      "learning_rate": 1.7803790385894387e-05,
+      "loss": 0.4660043716430664,
+      "step": 2280
+    },
+    {
+      "epoch": 0.7402020202020202,
+      "grad_norm": 0.010421738028526306,
+      "learning_rate": 1.7396723138955428e-05,
+      "loss": 0.4599196434020996,
+      "step": 2290
+    },
+    {
+      "epoch": 0.7434343434343434,
+      "grad_norm": 0.009896540082991123,
+      "learning_rate": 1.699338116145811e-05,
+      "loss": 0.46491589546203616,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.010468855500221252,
+      "learning_rate": 1.6593810539492195e-05,
+      "loss": 0.47761125564575196,
+      "step": 2310
+    },
+    {
+      "epoch": 0.74989898989899,
+      "grad_norm": 0.010416937991976738,
+      "learning_rate": 1.619805692823016e-05,
+      "loss": 0.49956817626953126,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7531313131313131,
+      "grad_norm": 0.010007611475884914,
+      "learning_rate": 1.580616554671057e-05,
+      "loss": 0.4716916084289551,
+      "step": 2330
+    },
+    {
+      "epoch": 0.7563636363636363,
+      "grad_norm": 0.010231648571789265,
+      "learning_rate": 1.5418181172671382e-05,
+      "loss": 0.4909040451049805,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7595959595959596,
+      "grad_norm": 0.010324012488126755,
+      "learning_rate": 1.5034148137433623e-05,
+      "loss": 0.47939190864562986,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7628282828282829,
+      "grad_norm": 0.011009547859430313,
+      "learning_rate": 1.4654110320836017e-05,
+      "loss": 0.48291826248168945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7660606060606061,
+      "grad_norm": 0.010392943397164345,
+      "learning_rate": 1.4278111146221263e-05,
+      "loss": 0.49179973602294924,
+      "step": 2370
+    },
+    {
+      "epoch": 0.7692929292929293,
+      "grad_norm": 0.010355197824537754,
+      "learning_rate": 1.3906193575474508e-05,
+      "loss": 0.4716278076171875,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7725252525252525,
+      "grad_norm": 0.009932084940373898,
+      "learning_rate": 1.3538400104114446e-05,
+      "loss": 0.47190055847167967,
+      "step": 2390
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 0.010710643604397774,
+      "learning_rate": 1.3174772756437742e-05,
+      "loss": 0.4703176498413086,
+      "step": 2400
+    },
+    {
+      "epoch": 0.778989898989899,
+      "grad_norm": 0.010614068247377872,
+      "learning_rate": 1.2815353080717379e-05,
+      "loss": 0.47541141510009766,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.011346950195729733,
+      "learning_rate": 1.246018214445525e-05,
+      "loss": 0.4860015869140625,
+      "step": 2420
+    },
+    {
+      "epoch": 0.7854545454545454,
+      "grad_norm": 0.009824907407164574,
+      "learning_rate": 1.210930052968981e-05,
+      "loss": 0.49062480926513674,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7886868686868687,
+      "grad_norm": 0.010624224320054054,
+      "learning_rate": 1.1762748328359152e-05,
+      "loss": 0.4694485664367676,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7919191919191919,
+      "grad_norm": 0.01044746395200491,
+      "learning_rate": 1.1420565137720045e-05,
+      "loss": 0.47275629043579104,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7951515151515152,
+      "grad_norm": 0.010226710699498653,
+      "learning_rate": 1.1082790055823533e-05,
+      "loss": 0.4670067310333252,
+      "step": 2460
+    },
+    {
+      "epoch": 0.7983838383838384,
+      "grad_norm": 0.010427460074424744,
+      "learning_rate": 1.0749461677047624e-05,
+      "loss": 0.4700475692749023,
+      "step": 2470
+    },
+    {
+      "epoch": 0.8016161616161617,
+      "grad_norm": 0.010494428686797619,
+      "learning_rate": 1.0420618087687418e-05,
+      "loss": 0.46589016914367676,
+      "step": 2480
+    },
+    {
+      "epoch": 0.8048484848484848,
+      "grad_norm": 0.010100893676280975,
+      "learning_rate": 1.0096296861603321e-05,
+      "loss": 0.4704419136047363,
+      "step": 2490
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.010682797059416771,
+      "learning_rate": 9.776535055927931e-06,
+      "loss": 0.47326183319091797,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8113131313131313,
+      "grad_norm": 0.00972407590597868,
+      "learning_rate": 9.461369206831772e-06,
+      "loss": 0.48441619873046876,
+      "step": 2510
+    },
+    {
+      "epoch": 0.8145454545454546,
+      "grad_norm": 0.010327558033168316,
+      "learning_rate": 9.150835325348678e-06,
+      "loss": 0.45856351852416993,
+      "step": 2520
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.010118944570422173,
+      "learning_rate": 8.844968893261197e-06,
+      "loss": 0.48114948272705077,
+      "step": 2530
+    },
+    {
+      "epoch": 0.821010101010101,
+      "grad_norm": 0.010876161977648735,
+      "learning_rate": 8.543804859046345e-06,
+      "loss": 0.4930680274963379,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8242424242424242,
+      "grad_norm": 0.010722608305513859,
+      "learning_rate": 8.247377633882463e-06,
+      "loss": 0.46875743865966796,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8274747474747475,
+      "grad_norm": 0.01088438369333744,
+      "learning_rate": 7.95572108771726e-06,
+      "loss": 0.4768000602722168,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8307070707070707,
+      "grad_norm": 0.01026720181107521,
+      "learning_rate": 7.66886854539795e-06,
+      "loss": 0.479974365234375,
+      "step": 2570
+    },
+    {
+      "epoch": 0.833939393939394,
+      "grad_norm": 0.009710075333714485,
+      "learning_rate": 7.386852782863407e-06,
+      "loss": 0.4684715270996094,
+      "step": 2580
+    },
+    {
+      "epoch": 0.8371717171717171,
+      "grad_norm": 0.009966167621314526,
+      "learning_rate": 7.109706023399232e-06,
+      "loss": 0.47191972732543946,
+      "step": 2590
+    },
+    {
+      "epoch": 0.8404040404040404,
+      "grad_norm": 0.010125650092959404,
+      "learning_rate": 6.837459933955936e-06,
+      "loss": 0.4766803741455078,
+      "step": 2600
+    },
+    {
+      "epoch": 0.8436363636363636,
+      "grad_norm": 0.009984518401324749,
+      "learning_rate": 6.5701456215305656e-06,
+      "loss": 0.4592133045196533,
+      "step": 2610
+    },
+    {
+      "epoch": 0.8468686868686869,
+      "grad_norm": 0.010836348868906498,
+      "learning_rate": 6.307793629612452e-06,
+      "loss": 0.4658504009246826,
+      "step": 2620
+    },
+    {
+      "epoch": 0.8501010101010101,
+      "grad_norm": 0.010431919246912003,
+      "learning_rate": 6.050433934693339e-06,
+      "loss": 0.4936856269836426,
+      "step": 2630
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.01049034669995308,
+      "learning_rate": 5.798095942842141e-06,
+      "loss": 0.4765117645263672,
+      "step": 2640
+    },
+    {
+      "epoch": 0.8565656565656565,
+      "grad_norm": 0.009596607647836208,
+      "learning_rate": 5.550808486345072e-06,
+      "loss": 0.47063379287719725,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8597979797979798,
+      "grad_norm": 0.01032214518636465,
+      "learning_rate": 5.308599820411247e-06,
+      "loss": 0.4614537715911865,
+      "step": 2660
+    },
+    {
+      "epoch": 0.863030303030303,
+      "grad_norm": 0.009960100054740906,
+      "learning_rate": 5.071497619944171e-06,
+      "loss": 0.48136143684387206,
+      "step": 2670
+    },
+    {
+      "epoch": 0.8662626262626263,
+      "grad_norm": 0.010326167568564415,
+      "learning_rate": 4.839528976379648e-06,
+      "loss": 0.47299985885620116,
+      "step": 2680
+    },
+    {
+      "epoch": 0.8694949494949495,
+      "grad_norm": 0.010867294855415821,
+      "learning_rate": 4.612720394590286e-06,
+      "loss": 0.4829209327697754,
+      "step": 2690
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.01050047017633915,
+      "learning_rate": 4.391097789856985e-06,
+      "loss": 0.4762550354003906,
+      "step": 2700
+    },
+    {
+      "epoch": 0.8759595959595959,
+      "grad_norm": 0.010378929786384106,
+      "learning_rate": 4.174686484907908e-06,
+      "loss": 0.4898251533508301,
+      "step": 2710
+    },
+    {
+      "epoch": 0.8791919191919192,
+      "grad_norm": 0.01060938648879528,
+      "learning_rate": 3.963511207025078e-06,
+      "loss": 0.47261548042297363,
+      "step": 2720
+    },
+    {
+      "epoch": 0.8824242424242424,
+      "grad_norm": 0.01075353566557169,
+      "learning_rate": 3.7575960852189728e-06,
+      "loss": 0.4839645862579346,
+      "step": 2730
+    },
+    {
+      "epoch": 0.8856565656565657,
+      "grad_norm": 0.010416378267109394,
+      "learning_rate": 3.5569646474715722e-06,
+      "loss": 0.46989760398864744,
+      "step": 2740
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.010806340724229813,
+      "learning_rate": 3.361639818048068e-06,
+      "loss": 0.47272281646728515,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8921212121212121,
+      "grad_norm": 0.009753530845046043,
+      "learning_rate": 3.1716439148774534e-06,
+      "loss": 0.47122917175292967,
+      "step": 2760
+    },
+    {
+      "epoch": 0.8953535353535353,
+      "grad_norm": 0.01022200658917427,
+      "learning_rate": 2.986998647002498e-06,
+      "loss": 0.4727674961090088,
+      "step": 2770
+    },
+    {
+      "epoch": 0.8985858585858586,
+      "grad_norm": 0.010225590318441391,
+      "learning_rate": 2.8077251120992742e-06,
+      "loss": 0.46461896896362304,
+      "step": 2780
+    },
+    {
+      "epoch": 0.9018181818181819,
+      "grad_norm": 0.010752941481769085,
+      "learning_rate": 2.633843794066515e-06,
+      "loss": 0.46602635383605956,
+      "step": 2790
+    },
+    {
+      "epoch": 0.9050505050505051,
+      "grad_norm": 0.011064955033361912,
+      "learning_rate": 2.465374560685091e-06,
+      "loss": 0.4705932140350342,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9082828282828282,
+      "grad_norm": 0.00982996542006731,
+      "learning_rate": 2.302336661347926e-06,
+      "loss": 0.4687389373779297,
+      "step": 2810
+    },
+    {
+      "epoch": 0.9115151515151515,
+      "grad_norm": 0.010190518572926521,
+      "learning_rate": 2.1447487248605513e-06,
+      "loss": 0.4906333923339844,
+      "step": 2820
+    },
+    {
+      "epoch": 0.9147474747474748,
+      "grad_norm": 0.01034579798579216,
+      "learning_rate": 1.9926287573125537e-06,
+      "loss": 0.47768077850341795,
+      "step": 2830
+    },
+    {
+      "epoch": 0.917979797979798,
+      "grad_norm": 0.010615529492497444,
+      "learning_rate": 1.845994140020213e-06,
+      "loss": 0.47643141746520995,
+      "step": 2840
+    },
+    {
+      "epoch": 0.9212121212121213,
+      "grad_norm": 0.010776858776807785,
+      "learning_rate": 1.7048616275404771e-06,
+      "loss": 0.4636590003967285,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.010271280072629452,
+      "learning_rate": 1.5692473457565748e-06,
+      "loss": 0.4707911014556885,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9276767676767677,
+      "grad_norm": 0.009596684016287327,
+      "learning_rate": 1.439166790035501e-06,
+      "loss": 0.45751228332519533,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9309090909090909,
+      "grad_norm": 0.009914812631905079,
+      "learning_rate": 1.3146348234574724e-06,
+      "loss": 0.4842953681945801,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9341414141414142,
+      "grad_norm": 0.01014726422727108,
+      "learning_rate": 1.1956656751176577e-06,
+      "loss": 0.482682991027832,
+      "step": 2890
+    },
+    {
+      "epoch": 0.9373737373737374,
+      "grad_norm": 0.010660757310688496,
+      "learning_rate": 1.0822729385003727e-06,
+      "loss": 0.48476057052612304,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9406060606060606,
+      "grad_norm": 0.010105855762958527,
+      "learning_rate": 9.744695699258955e-07,
+      "loss": 0.4767448425292969,
+      "step": 2910
+    },
+    {
+      "epoch": 0.9438383838383838,
+      "grad_norm": 0.010221844539046288,
+      "learning_rate": 8.722678870700274e-07,
+      "loss": 0.4663360118865967,
+      "step": 2920
+    },
+    {
+      "epoch": 0.9470707070707071,
+      "grad_norm": 0.011003104969859123,
+      "learning_rate": 7.756795675566919e-07,
+      "loss": 0.48151307106018065,
+      "step": 2930
+    },
+    {
+      "epoch": 0.9503030303030303,
+      "grad_norm": 0.01029619574546814,
+      "learning_rate": 6.847156476236516e-07,
+      "loss": 0.48086977005004883,
+      "step": 2940
+    },
+    {
+      "epoch": 0.9535353535353536,
+      "grad_norm": 0.010033480823040009,
+      "learning_rate": 5.993865208614835e-07,
+      "loss": 0.4648440361022949,
+      "step": 2950
+    },
+    {
+      "epoch": 0.9567676767676768,
+      "grad_norm": 0.010539564304053783,
+      "learning_rate": 5.197019370260125e-07,
+      "loss": 0.46828551292419435,
+      "step": 2960
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.009619071148335934,
+      "learning_rate": 4.4567100092429704e-07,
+      "loss": 0.48481130599975586,
+      "step": 2970
+    },
+    {
+      "epoch": 0.9632323232323232,
+      "grad_norm": 0.010197056457400322,
+      "learning_rate": 3.7730217137428857e-07,
+      "loss": 0.47917518615722654,
+      "step": 2980
+    },
+    {
+      "epoch": 0.9664646464646465,
+      "grad_norm": 0.01057458110153675,
+      "learning_rate": 3.1460326023836083e-07,
+      "loss": 0.48064794540405276,
+      "step": 2990
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.01009963545948267,
+      "learning_rate": 2.575814315306846e-07,
+      "loss": 0.4831876754760742,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.256389449849504e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3094/README.md

@@ -0,0 +1,208 @@
+---
+base_model: Qwen/Qwen3-4B-Base
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:Qwen/Qwen3-4B-Base
+- llama-factory
+- 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

checkpoint-3094/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/Qwen3-4B-Base",
+  "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": 64,
+  "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": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-3094/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09a868524bc650caecf8a96c1b7a8c9806ed1f7de09f68a94990a38d5cc3720a
+size 264308896

checkpoint-3094/chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 %}

checkpoint-3094/tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-3094/trainer_state.json

@@ -0,0 +1,2197 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 3094,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032323232323232323,
+      "grad_norm": 0.032284051179885864,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.6013355255126953,
+      "step": 10
+    },
+    {
+      "epoch": 0.006464646464646465,
+      "grad_norm": 0.01937970519065857,
+      "learning_rate": 1.2258064516129032e-05,
+      "loss": 0.5758121490478516,
+      "step": 20
+    },
+    {
+      "epoch": 0.009696969696969697,
+      "grad_norm": 0.014327733777463436,
+      "learning_rate": 1.870967741935484e-05,
+      "loss": 0.5787662506103516,
+      "step": 30
+    },
+    {
+      "epoch": 0.01292929292929293,
+      "grad_norm": 0.012254982255399227,
+      "learning_rate": 2.5161290322580645e-05,
+      "loss": 0.5327143669128418,
+      "step": 40
+    },
+    {
+      "epoch": 0.01616161616161616,
+      "grad_norm": 0.014536243863403797,
+      "learning_rate": 3.161290322580645e-05,
+      "loss": 0.5393171310424805,
+      "step": 50
+    },
+    {
+      "epoch": 0.019393939393939394,
+      "grad_norm": 0.011900736019015312,
+      "learning_rate": 3.8064516129032254e-05,
+      "loss": 0.5058945178985595,
+      "step": 60
+    },
+    {
+      "epoch": 0.022626262626262626,
+      "grad_norm": 0.01210293360054493,
+      "learning_rate": 4.451612903225807e-05,
+      "loss": 0.517607593536377,
+      "step": 70
+    },
+    {
+      "epoch": 0.02585858585858586,
+      "grad_norm": 0.017207792028784752,
+      "learning_rate": 5.096774193548387e-05,
+      "loss": 0.5269095420837402,
+      "step": 80
+    },
+    {
+      "epoch": 0.02909090909090909,
+      "grad_norm": 0.013736969791352749,
+      "learning_rate": 5.7419354838709685e-05,
+      "loss": 0.5040688514709473,
+      "step": 90
+    },
+    {
+      "epoch": 0.03232323232323232,
+      "grad_norm": 0.011664404533803463,
+      "learning_rate": 6.387096774193548e-05,
+      "loss": 0.5147775173187256,
+      "step": 100
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 0.014052552171051502,
+      "learning_rate": 7.03225806451613e-05,
+      "loss": 0.5230005741119385,
+      "step": 110
+    },
+    {
+      "epoch": 0.03878787878787879,
+      "grad_norm": 0.011644740588963032,
+      "learning_rate": 7.67741935483871e-05,
+      "loss": 0.5105222702026367,
+      "step": 120
+    },
+    {
+      "epoch": 0.04202020202020202,
+      "grad_norm": 0.011730308644473553,
+      "learning_rate": 8.32258064516129e-05,
+      "loss": 0.4989170074462891,
+      "step": 130
+    },
+    {
+      "epoch": 0.04525252525252525,
+      "grad_norm": 0.012009115889668465,
+      "learning_rate": 8.967741935483871e-05,
+      "loss": 0.5003124713897705,
+      "step": 140
+    },
+    {
+      "epoch": 0.048484848484848485,
+      "grad_norm": 0.012424134649336338,
+      "learning_rate": 9.612903225806452e-05,
+      "loss": 0.5077538013458252,
+      "step": 150
+    },
+    {
+      "epoch": 0.05171717171717172,
+      "grad_norm": 0.011461800895631313,
+      "learning_rate": 9.999954295400999e-05,
+      "loss": 0.5061477661132813,
+      "step": 160
+    },
+    {
+      "epoch": 0.05494949494949495,
+      "grad_norm": 0.011583201587200165,
+      "learning_rate": 9.999440128258112e-05,
+      "loss": 0.5013481140136719,
+      "step": 170
+    },
+    {
+      "epoch": 0.05818181818181818,
+      "grad_norm": 0.011583367362618446,
+      "learning_rate": 9.998354722168459e-05,
+      "loss": 0.48343815803527834,
+      "step": 180
+    },
+    {
+      "epoch": 0.061414141414141414,
+      "grad_norm": 0.011094105429947376,
+      "learning_rate": 9.996698201151175e-05,
+      "loss": 0.507840633392334,
+      "step": 190
+    },
+    {
+      "epoch": 0.06464646464646465,
+      "grad_norm": 0.011715452186763287,
+      "learning_rate": 9.994470754481315e-05,
+      "loss": 0.49884777069091796,
+      "step": 200
+    },
+    {
+      "epoch": 0.06787878787878789,
+      "grad_norm": 0.010746965184807777,
+      "learning_rate": 9.991672636668239e-05,
+      "loss": 0.5068713188171386,
+      "step": 210
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.012883410789072514,
+      "learning_rate": 9.988304167426519e-05,
+      "loss": 0.4920186519622803,
+      "step": 220
+    },
+    {
+      "epoch": 0.07434343434343435,
+      "grad_norm": 0.011187366209924221,
+      "learning_rate": 9.984365731639419e-05,
+      "loss": 0.5021648406982422,
+      "step": 230
+    },
+    {
+      "epoch": 0.07757575757575758,
+      "grad_norm": 0.010671757161617279,
+      "learning_rate": 9.979857779314906e-05,
+      "loss": 0.5038897514343261,
+      "step": 240
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.01044373121112585,
+      "learning_rate": 9.974780825534246e-05,
+      "loss": 0.4965065956115723,
+      "step": 250
+    },
+    {
+      "epoch": 0.08404040404040404,
+      "grad_norm": 0.010565251111984253,
+      "learning_rate": 9.969135450393141e-05,
+      "loss": 0.5145994186401367,
+      "step": 260
+    },
+    {
+      "epoch": 0.08727272727272728,
+      "grad_norm": 0.010024026967585087,
+      "learning_rate": 9.96292229893545e-05,
+      "loss": 0.505019235610962,
+      "step": 270
+    },
+    {
+      "epoch": 0.0905050505050505,
+      "grad_norm": 0.010430407710373402,
+      "learning_rate": 9.956142081079484e-05,
+      "loss": 0.5115808010101318,
+      "step": 280
+    },
+    {
+      "epoch": 0.09373737373737374,
+      "grad_norm": 0.010048807598650455,
+      "learning_rate": 9.948795571536891e-05,
+      "loss": 0.48525152206420896,
+      "step": 290
+    },
+    {
+      "epoch": 0.09696969696969697,
+      "grad_norm": 0.010108387097716331,
+      "learning_rate": 9.94088360972414e-05,
+      "loss": 0.5002010822296142,
+      "step": 300
+    },
+    {
+      "epoch": 0.10020202020202021,
+      "grad_norm": 0.010273640975356102,
+      "learning_rate": 9.932407099666608e-05,
+      "loss": 0.49662046432495116,
+      "step": 310
+    },
+    {
+      "epoch": 0.10343434343434343,
+      "grad_norm": 0.00995971355587244,
+      "learning_rate": 9.923367009895274e-05,
+      "loss": 0.48578290939331054,
+      "step": 320
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.010459775105118752,
+      "learning_rate": 9.913764373336079e-05,
+      "loss": 0.48862767219543457,
+      "step": 330
+    },
+    {
+      "epoch": 0.1098989898989899,
+      "grad_norm": 0.009838269092142582,
+      "learning_rate": 9.903600287191875e-05,
+      "loss": 0.5034208774566651,
+      "step": 340
+    },
+    {
+      "epoch": 0.11313131313131314,
+      "grad_norm": 0.00978950597345829,
+      "learning_rate": 9.892875912817079e-05,
+      "loss": 0.4870161533355713,
+      "step": 350
+    },
+    {
+      "epoch": 0.11636363636363636,
+      "grad_norm": 0.01030043140053749,
+      "learning_rate": 9.881592475584964e-05,
+      "loss": 0.5026071548461915,
+      "step": 360
+    },
+    {
+      "epoch": 0.1195959595959596,
+      "grad_norm": 0.010531975887715816,
+      "learning_rate": 9.869751264747656e-05,
+      "loss": 0.4883917808532715,
+      "step": 370
+    },
+    {
+      "epoch": 0.12282828282828283,
+      "grad_norm": 0.00986825954169035,
+      "learning_rate": 9.857353633288814e-05,
+      "loss": 0.4927018165588379,
+      "step": 380
+    },
+    {
+      "epoch": 0.12606060606060607,
+      "grad_norm": 0.009432349354028702,
+      "learning_rate": 9.844400997769043e-05,
+      "loss": 0.4908174514770508,
+      "step": 390
+    },
+    {
+      "epoch": 0.1292929292929293,
+      "grad_norm": 0.01057665515691042,
+      "learning_rate": 9.83089483816404e-05,
+      "loss": 0.5069625854492188,
+      "step": 400
+    },
+    {
+      "epoch": 0.13252525252525252,
+      "grad_norm": 0.010007908567786217,
+      "learning_rate": 9.816836697695482e-05,
+      "loss": 0.4988056182861328,
+      "step": 410
+    },
+    {
+      "epoch": 0.13575757575757577,
+      "grad_norm": 0.010027808137238026,
+      "learning_rate": 9.802228182654702e-05,
+      "loss": 0.5007385730743408,
+      "step": 420
+    },
+    {
+      "epoch": 0.138989898989899,
+      "grad_norm": 0.009953738190233707,
+      "learning_rate": 9.787070962219156e-05,
+      "loss": 0.5130783081054687,
+      "step": 430
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.010204462334513664,
+      "learning_rate": 9.771366768261696e-05,
+      "loss": 0.4947535514831543,
+      "step": 440
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 0.009612451307475567,
+      "learning_rate": 9.755117395152689e-05,
+      "loss": 0.4917112350463867,
+      "step": 450
+    },
+    {
+      "epoch": 0.1486868686868687,
+      "grad_norm": 0.00995573028922081,
+      "learning_rate": 9.73832469955499e-05,
+      "loss": 0.4882859230041504,
+      "step": 460
+    },
+    {
+      "epoch": 0.15191919191919193,
+      "grad_norm": 0.009584570303559303,
+      "learning_rate": 9.720990600211797e-05,
+      "loss": 0.500526762008667,
+      "step": 470
+    },
+    {
+      "epoch": 0.15515151515151515,
+      "grad_norm": 0.010585076175630093,
+      "learning_rate": 9.703117077727419e-05,
+      "loss": 0.496882963180542,
+      "step": 480
+    },
+    {
+      "epoch": 0.15838383838383838,
+      "grad_norm": 0.009859723038971424,
+      "learning_rate": 9.684706174340965e-05,
+      "loss": 0.48728485107421876,
+      "step": 490
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.010212041437625885,
+      "learning_rate": 9.665759993693e-05,
+      "loss": 0.49378366470336915,
+      "step": 500
+    },
+    {
+      "epoch": 0.16484848484848486,
+      "grad_norm": 0.009744231589138508,
+      "learning_rate": 9.646280700585185e-05,
+      "loss": 0.4663555145263672,
+      "step": 510
+    },
+    {
+      "epoch": 0.16808080808080808,
+      "grad_norm": 0.009789686650037766,
+      "learning_rate": 9.626270520732916e-05,
+      "loss": 0.4879913330078125,
+      "step": 520
+    },
+    {
+      "epoch": 0.1713131313131313,
+      "grad_norm": 0.009891769848763943,
+      "learning_rate": 9.605731740511022e-05,
+      "loss": 0.48809428215026857,
+      "step": 530
+    },
+    {
+      "epoch": 0.17454545454545456,
+      "grad_norm": 0.01002143882215023,
+      "learning_rate": 9.584666706692517e-05,
+      "loss": 0.4959606170654297,
+      "step": 540
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.009208496659994125,
+      "learning_rate": 9.56307782618046e-05,
+      "loss": 0.4878594398498535,
+      "step": 550
+    },
+    {
+      "epoch": 0.181010101010101,
+      "grad_norm": 0.009645081125199795,
+      "learning_rate": 9.540967565732937e-05,
+      "loss": 0.4769869804382324,
+      "step": 560
+    },
+    {
+      "epoch": 0.18424242424242424,
+      "grad_norm": 0.010497638955712318,
+      "learning_rate": 9.51833845168121e-05,
+      "loss": 0.4970097064971924,
+      "step": 570
+    },
+    {
+      "epoch": 0.1874747474747475,
+      "grad_norm": 0.010612033307552338,
+      "learning_rate": 9.495193069641057e-05,
+      "loss": 0.4945381164550781,
+      "step": 580
+    },
+    {
+      "epoch": 0.1907070707070707,
+      "grad_norm": 0.009433986619114876,
+      "learning_rate": 9.47153406421734e-05,
+      "loss": 0.4860210418701172,
+      "step": 590
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 0.009995914995670319,
+      "learning_rate": 9.447364138701823e-05,
+      "loss": 0.4904911994934082,
+      "step": 600
+    },
+    {
+      "epoch": 0.19717171717171716,
+      "grad_norm": 0.009814019314944744,
+      "learning_rate": 9.422686054764302e-05,
+      "loss": 0.4915336608886719,
+      "step": 610
+    },
+    {
+      "epoch": 0.20040404040404042,
+      "grad_norm": 0.010199982672929764,
+      "learning_rate": 9.397502632137055e-05,
+      "loss": 0.4805011749267578,
+      "step": 620
+    },
+    {
+      "epoch": 0.20363636363636364,
+      "grad_norm": 0.010121874511241913,
+      "learning_rate": 9.371816748292641e-05,
+      "loss": 0.47633209228515627,
+      "step": 630
+    },
+    {
+      "epoch": 0.20686868686868687,
+      "grad_norm": 0.009638865478336811,
+      "learning_rate": 9.345631338115141e-05,
+      "loss": 0.48993511199951173,
+      "step": 640
+    },
+    {
+      "epoch": 0.2101010101010101,
+      "grad_norm": 0.010041174478828907,
+      "learning_rate": 9.318949393564807e-05,
+      "loss": 0.4798978328704834,
+      "step": 650
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.010145517997443676,
+      "learning_rate": 9.291773963336193e-05,
+      "loss": 0.4696659564971924,
+      "step": 660
+    },
+    {
+      "epoch": 0.21656565656565657,
+      "grad_norm": 0.01043335534632206,
+      "learning_rate": 9.264108152509816e-05,
+      "loss": 0.4955574035644531,
+      "step": 670
+    },
+    {
+      "epoch": 0.2197979797979798,
+      "grad_norm": 0.010406569577753544,
+      "learning_rate": 9.235955122197368e-05,
+      "loss": 0.48659563064575195,
+      "step": 680
+    },
+    {
+      "epoch": 0.22303030303030302,
+      "grad_norm": 0.009870355017483234,
+      "learning_rate": 9.207318089180524e-05,
+      "loss": 0.4766091823577881,
+      "step": 690
+    },
+    {
+      "epoch": 0.22626262626262628,
+      "grad_norm": 0.009980005212128162,
+      "learning_rate": 9.178200325543384e-05,
+      "loss": 0.5022068023681641,
+      "step": 700
+    },
+    {
+      "epoch": 0.2294949494949495,
+      "grad_norm": 0.009765878319740295,
+      "learning_rate": 9.148605158298621e-05,
+      "loss": 0.48309478759765623,
+      "step": 710
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.009879437275230885,
+      "learning_rate": 9.118535969007314e-05,
+      "loss": 0.4793684959411621,
+      "step": 720
+    },
+    {
+      "epoch": 0.23595959595959595,
+      "grad_norm": 0.009907045401632786,
+      "learning_rate": 9.087996193392578e-05,
+      "loss": 0.49844112396240237,
+      "step": 730
+    },
+    {
+      "epoch": 0.2391919191919192,
+      "grad_norm": 0.009958872571587563,
+      "learning_rate": 9.056989320947e-05,
+      "loss": 0.48113102912902833,
+      "step": 740
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.010206855833530426,
+      "learning_rate": 9.025518894533921e-05,
+      "loss": 0.5048784255981446,
+      "step": 750
+    },
+    {
+      "epoch": 0.24565656565656566,
+      "grad_norm": 0.009286429733037949,
+      "learning_rate": 8.99358850998263e-05,
+      "loss": 0.4862624168395996,
+      "step": 760
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.009919015690684319,
+      "learning_rate": 8.9612018156775e-05,
+      "loss": 0.48739056587219237,
+      "step": 770
+    },
+    {
+      "epoch": 0.25212121212121213,
+      "grad_norm": 0.010435211472213268,
+      "learning_rate": 8.928362512141124e-05,
+      "loss": 0.48689990043640136,
+      "step": 780
+    },
+    {
+      "epoch": 0.25535353535353533,
+      "grad_norm": 0.009992080740630627,
+      "learning_rate": 8.895074351611488e-05,
+      "loss": 0.4848791599273682,
+      "step": 790
+    },
+    {
+      "epoch": 0.2585858585858586,
+      "grad_norm": 0.010449117980897427,
+      "learning_rate": 8.861341137613242e-05,
+      "loss": 0.49130568504333494,
+      "step": 800
+    },
+    {
+      "epoch": 0.26181818181818184,
+      "grad_norm": 0.010061345063149929,
+      "learning_rate": 8.827166724523105e-05,
+      "loss": 0.49056081771850585,
+      "step": 810
+    },
+    {
+      "epoch": 0.26505050505050504,
+      "grad_norm": 0.009908635169267654,
+      "learning_rate": 8.792555017129461e-05,
+      "loss": 0.4706866264343262,
+      "step": 820
+    },
+    {
+      "epoch": 0.2682828282828283,
+      "grad_norm": 0.010003669187426567,
+      "learning_rate": 8.757509970186196e-05,
+      "loss": 0.48719348907470705,
+      "step": 830
+    },
+    {
+      "epoch": 0.27151515151515154,
+      "grad_norm": 0.009513127617537975,
+      "learning_rate": 8.722035587960826e-05,
+      "loss": 0.48200483322143556,
+      "step": 840
+    },
+    {
+      "epoch": 0.27474747474747474,
+      "grad_norm": 0.009142451919615269,
+      "learning_rate": 8.686135923776969e-05,
+      "loss": 0.48613176345825193,
+      "step": 850
+    },
+    {
+      "epoch": 0.277979797979798,
+      "grad_norm": 0.00980432890355587,
+      "learning_rate": 8.649815079551205e-05,
+      "loss": 0.4976047515869141,
+      "step": 860
+    },
+    {
+      "epoch": 0.2812121212121212,
+      "grad_norm": 0.010442109778523445,
+      "learning_rate": 8.613077205324389e-05,
+      "loss": 0.48451838493347166,
+      "step": 870
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.009309548884630203,
+      "learning_rate": 8.575926498787476e-05,
+      "loss": 0.5115366458892823,
+      "step": 880
+    },
+    {
+      "epoch": 0.2876767676767677,
+      "grad_norm": 0.009093924425542355,
+      "learning_rate": 8.538367204801872e-05,
+      "loss": 0.48187432289123533,
+      "step": 890
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.009757987223565578,
+      "learning_rate": 8.500403614914432e-05,
+      "loss": 0.4882505416870117,
+      "step": 900
+    },
+    {
+      "epoch": 0.29414141414141415,
+      "grad_norm": 0.010261048562824726,
+      "learning_rate": 8.462040066867089e-05,
+      "loss": 0.49068965911865237,
+      "step": 910
+    },
+    {
+      "epoch": 0.2973737373737374,
+      "grad_norm": 0.009317740797996521,
+      "learning_rate": 8.423280944101233e-05,
+      "loss": 0.4966132164001465,
+      "step": 920
+    },
+    {
+      "epoch": 0.3006060606060606,
+      "grad_norm": 0.009787693619728088,
+      "learning_rate": 8.384130675256852e-05,
+      "loss": 0.4754981994628906,
+      "step": 930
+    },
+    {
+      "epoch": 0.30383838383838385,
+      "grad_norm": 0.010005015879869461,
+      "learning_rate": 8.34459373366651e-05,
+      "loss": 0.4735103130340576,
+      "step": 940
+    },
+    {
+      "epoch": 0.30707070707070705,
+      "grad_norm": 0.009837017394602299,
+      "learning_rate": 8.304674636844231e-05,
+      "loss": 0.4809592247009277,
+      "step": 950
+    },
+    {
+      "epoch": 0.3103030303030303,
+      "grad_norm": 0.009590484201908112,
+      "learning_rate": 8.264377945969312e-05,
+      "loss": 0.48206100463867185,
+      "step": 960
+    },
+    {
+      "epoch": 0.31353535353535356,
+      "grad_norm": 0.009699508547782898,
+      "learning_rate": 8.223708265365174e-05,
+      "loss": 0.48718748092651365,
+      "step": 970
+    },
+    {
+      "epoch": 0.31676767676767675,
+      "grad_norm": 0.010278215631842613,
+      "learning_rate": 8.182670241973253e-05,
+      "loss": 0.4952278137207031,
+      "step": 980
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.010104077868163586,
+      "learning_rate": 8.141268564822053e-05,
+      "loss": 0.47769975662231445,
+      "step": 990
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.009301737882196903,
+      "learning_rate": 8.099507964491369e-05,
+      "loss": 0.4862718105316162,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32646464646464646,
+      "grad_norm": 0.009307135827839375,
+      "learning_rate": 8.057393212571767e-05,
+      "loss": 0.49833106994628906,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3296969696969697,
+      "grad_norm": 0.009420682676136494,
+      "learning_rate": 8.014929121119378e-05,
+      "loss": 0.48829941749572753,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3329292929292929,
+      "grad_norm": 0.010058379732072353,
+      "learning_rate": 7.972120542106077e-05,
+      "loss": 0.46506147384643554,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33616161616161616,
+      "grad_norm": 0.009461579844355583,
+      "learning_rate": 7.92897236686508e-05,
+      "loss": 0.47866268157958985,
+      "step": 1040
+    },
+    {
+      "epoch": 0.3393939393939394,
+      "grad_norm": 0.010341835208237171,
+      "learning_rate": 7.885489525532075e-05,
+      "loss": 0.4966601371765137,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3426262626262626,
+      "grad_norm": 0.01042103860527277,
+      "learning_rate": 7.84167698648189e-05,
+      "loss": 0.49251084327697753,
+      "step": 1060
+    },
+    {
+      "epoch": 0.34585858585858587,
+      "grad_norm": 0.010442749597132206,
+      "learning_rate": 7.797539755760805e-05,
+      "loss": 0.4816086769104004,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3490909090909091,
+      "grad_norm": 0.010256553068757057,
+      "learning_rate": 7.753082876514562e-05,
+      "loss": 0.47102947235107423,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3523232323232323,
+      "grad_norm": 0.009399017319083214,
+      "learning_rate": 7.708311428412129e-05,
+      "loss": 0.4810478210449219,
+      "step": 1090
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.009499317966401577,
+      "learning_rate": 7.663230527065293e-05,
+      "loss": 0.47051143646240234,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35878787878787877,
+      "grad_norm": 0.009759469889104366,
+      "learning_rate": 7.617845323444156e-05,
+      "loss": 0.4780744552612305,
+      "step": 1110
+    },
+    {
+      "epoch": 0.362020202020202,
+      "grad_norm": 0.00987281370908022,
+      "learning_rate": 7.572161003288565e-05,
+      "loss": 0.4804032325744629,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3652525252525253,
+      "grad_norm": 0.00963522493839264,
+      "learning_rate": 7.526182786515609e-05,
+      "loss": 0.48206367492675783,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36848484848484847,
+      "grad_norm": 0.009587026201188564,
+      "learning_rate": 7.479915926623165e-05,
+      "loss": 0.49240264892578123,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3717171717171717,
+      "grad_norm": 0.009810036048293114,
+      "learning_rate": 7.433365710089646e-05,
+      "loss": 0.48599681854248045,
+      "step": 1150
+    },
+    {
+      "epoch": 0.374949494949495,
+      "grad_norm": 0.00978278461843729,
+      "learning_rate": 7.386537455769963e-05,
+      "loss": 0.4688436031341553,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3781818181818182,
+      "grad_norm": 0.00925996620208025,
+      "learning_rate": 7.339436514287783e-05,
+      "loss": 0.47986507415771484,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3814141414141414,
+      "grad_norm": 0.010006657801568508,
+      "learning_rate": 7.292068267424165e-05,
+      "loss": 0.4771553993225098,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3846464646464646,
+      "grad_norm": 0.010299976915121078,
+      "learning_rate": 7.244438127502647e-05,
+      "loss": 0.4854436874389648,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3878787878787879,
+      "grad_norm": 0.009807374328374863,
+      "learning_rate": 7.196551536770807e-05,
+      "loss": 0.4763533592224121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.010062369517982006,
+      "learning_rate": 7.148413966778451e-05,
+      "loss": 0.47457141876220704,
+      "step": 1210
+    },
+    {
+      "epoch": 0.39434343434343433,
+      "grad_norm": 0.009904388338327408,
+      "learning_rate": 7.100030917752423e-05,
+      "loss": 0.4732469081878662,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3975757575757576,
+      "grad_norm": 0.009578046388924122,
+      "learning_rate": 7.051407917968138e-05,
+      "loss": 0.47551660537719725,
+      "step": 1230
+    },
+    {
+      "epoch": 0.40080808080808084,
+      "grad_norm": 0.010024272836744785,
+      "learning_rate": 7.002550523117926e-05,
+      "loss": 0.4835049629211426,
+      "step": 1240
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.010056886821985245,
+      "learning_rate": 6.953464315676241e-05,
+      "loss": 0.4909071922302246,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4072727272727273,
+      "grad_norm": 0.009707778692245483,
+      "learning_rate": 6.904154904261792e-05,
+      "loss": 0.4842695236206055,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4105050505050505,
+      "grad_norm": 0.00976107269525528,
+      "learning_rate": 6.8546279229967e-05,
+      "loss": 0.48967390060424804,
+      "step": 1270
+    },
+    {
+      "epoch": 0.41373737373737374,
+      "grad_norm": 0.010392800904810429,
+      "learning_rate": 6.804889030862753e-05,
+      "loss": 0.48658218383789065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.416969696969697,
+      "grad_norm": 0.009267269633710384,
+      "learning_rate": 6.754943911054793e-05,
+      "loss": 0.48893008232116697,
+      "step": 1290
+    },
+    {
+      "epoch": 0.4202020202020202,
+      "grad_norm": 0.009753459133207798,
+      "learning_rate": 6.704798270331358e-05,
+      "loss": 0.49384117126464844,
+      "step": 1300
+    },
+    {
+      "epoch": 0.42343434343434344,
+      "grad_norm": 0.011121846735477448,
+      "learning_rate": 6.654457838362621e-05,
+      "loss": 0.47458324432373045,
+      "step": 1310
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.009406324476003647,
+      "learning_rate": 6.603928367075718e-05,
+      "loss": 0.4703402519226074,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4298989898989899,
+      "grad_norm": 0.010009719990193844,
+      "learning_rate": 6.553215629997529e-05,
+      "loss": 0.4851715087890625,
+      "step": 1330
+    },
+    {
+      "epoch": 0.43313131313131314,
+      "grad_norm": 0.009798573330044746,
+      "learning_rate": 6.502325421594988e-05,
+      "loss": 0.4779622554779053,
+      "step": 1340
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.0098969591781497,
+      "learning_rate": 6.451263556613007e-05,
+      "loss": 0.4708548545837402,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4395959595959596,
+      "grad_norm": 0.009853474795818329,
+      "learning_rate": 6.40003586941008e-05,
+      "loss": 0.4721970558166504,
+      "step": 1360
+    },
+    {
+      "epoch": 0.44282828282828285,
+      "grad_norm": 0.009663710370659828,
+      "learning_rate": 6.348648213291642e-05,
+      "loss": 0.4798272132873535,
+      "step": 1370
+    },
+    {
+      "epoch": 0.44606060606060605,
+      "grad_norm": 0.009419051930308342,
+      "learning_rate": 6.297106459841272e-05,
+      "loss": 0.471483039855957,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4492929292929293,
+      "grad_norm": 0.009978282265365124,
+      "learning_rate": 6.245416498249801e-05,
+      "loss": 0.4772329330444336,
+      "step": 1390
+    },
+    {
+      "epoch": 0.45252525252525255,
+      "grad_norm": 0.009491856209933758,
+      "learning_rate": 6.193584234642403e-05,
+      "loss": 0.48812179565429686,
+      "step": 1400
+    },
+    {
+      "epoch": 0.45575757575757575,
+      "grad_norm": 0.010496517643332481,
+      "learning_rate": 6.141615591403771e-05,
+      "loss": 0.48897976875305177,
+      "step": 1410
+    },
+    {
+      "epoch": 0.458989898989899,
+      "grad_norm": 0.01015474647283554,
+      "learning_rate": 6.0895165065014106e-05,
+      "loss": 0.4850447654724121,
+      "step": 1420
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.009763741865754128,
+      "learning_rate": 6.037292932807167e-05,
+      "loss": 0.4857158660888672,
+      "step": 1430
+    },
+    {
+      "epoch": 0.46545454545454545,
+      "grad_norm": 0.009874231182038784,
+      "learning_rate": 5.984950837417048e-05,
+      "loss": 0.4844364166259766,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4686868686868687,
+      "grad_norm": 0.010104037821292877,
+      "learning_rate": 5.932496200969422e-05,
+      "loss": 0.47542514801025393,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4719191919191919,
+      "grad_norm": 0.009445435367524624,
+      "learning_rate": 5.879935016961661e-05,
+      "loss": 0.48579182624816897,
+      "step": 1460
+    },
+    {
+      "epoch": 0.47515151515151516,
+      "grad_norm": 0.010507128201425076,
+      "learning_rate": 5.827273291065326e-05,
+      "loss": 0.48273677825927735,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4783838383838384,
+      "grad_norm": 0.009411566890776157,
+      "learning_rate": 5.7745170404399484e-05,
+      "loss": 0.46429009437561036,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4816161616161616,
+      "grad_norm": 0.010377817787230015,
+      "learning_rate": 5.721672293045518e-05,
+      "loss": 0.49172677993774416,
+      "step": 1490
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.009920118376612663,
+      "learning_rate": 5.668745086953712e-05,
+      "loss": 0.4934688568115234,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48808080808080806,
+      "grad_norm": 0.012272641994059086,
+      "learning_rate": 5.615741469657985e-05,
+      "loss": 0.4826413631439209,
+      "step": 1510
+    },
+    {
+      "epoch": 0.4913131313131313,
+      "grad_norm": 0.00981989037245512,
+      "learning_rate": 5.562667497382582e-05,
+      "loss": 0.48468503952026365,
+      "step": 1520
+    },
+    {
+      "epoch": 0.49454545454545457,
+      "grad_norm": 0.010148138739168644,
+      "learning_rate": 5.509529234390553e-05,
+      "loss": 0.47773942947387693,
+      "step": 1530
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.010528397746384144,
+      "learning_rate": 5.456332752290837e-05,
+      "loss": 0.47507562637329104,
+      "step": 1540
+    },
+    {
+      "epoch": 0.501010101010101,
+      "grad_norm": 0.01076479908078909,
+      "learning_rate": 5.4030841293445244e-05,
+      "loss": 0.486495304107666,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5042424242424243,
+      "grad_norm": 0.009976644068956375,
+      "learning_rate": 5.349789449770351e-05,
+      "loss": 0.48320484161376953,
+      "step": 1560
+    },
+    {
+      "epoch": 0.5074747474747475,
+      "grad_norm": 0.010504718869924545,
+      "learning_rate": 5.2964548030495065e-05,
+      "loss": 0.48847188949584963,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5107070707070707,
+      "grad_norm": 0.010325642302632332,
+      "learning_rate": 5.243086283229852e-05,
+      "loss": 0.47591514587402345,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5139393939393939,
+      "grad_norm": 0.010260741226375103,
+      "learning_rate": 5.18968998822961e-05,
+      "loss": 0.48136124610900877,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5171717171717172,
+      "grad_norm": 0.010797196067869663,
+      "learning_rate": 5.1362720191406065e-05,
+      "loss": 0.48076438903808594,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5204040404040404,
+      "grad_norm": 0.010010522790253162,
+      "learning_rate": 5.082838479531169e-05,
+      "loss": 0.5004307270050049,
+      "step": 1610
+    },
+    {
+      "epoch": 0.5236363636363637,
+      "grad_norm": 0.010120037943124771,
+      "learning_rate": 5.029395474748714e-05,
+      "loss": 0.4812767028808594,
+      "step": 1620
+    },
+    {
+      "epoch": 0.5268686868686868,
+      "grad_norm": 0.009431752376258373,
+      "learning_rate": 4.975949111222158e-05,
+      "loss": 0.4887521743774414,
+      "step": 1630
+    },
+    {
+      "epoch": 0.5301010101010101,
+      "grad_norm": 0.010080527514219284,
+      "learning_rate": 4.9225054957641916e-05,
+      "loss": 0.48248910903930664,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.009522376582026482,
+      "learning_rate": 4.8690707348735035e-05,
+      "loss": 0.4855649948120117,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5365656565656566,
+      "grad_norm": 0.009686745703220367,
+      "learning_rate": 4.8156509340370605e-05,
+      "loss": 0.47187280654907227,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5397979797979798,
+      "grad_norm": 0.011875285767018795,
+      "learning_rate": 4.762252197032482e-05,
+      "loss": 0.46579513549804685,
+      "step": 1670
+    },
+    {
+      "epoch": 0.5430303030303031,
+      "grad_norm": 0.009932303801178932,
+      "learning_rate": 4.7088806252306224e-05,
+      "loss": 0.47946829795837403,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5462626262626262,
+      "grad_norm": 0.017099183052778244,
+      "learning_rate": 4.655542316898423e-05,
+      "loss": 0.4593667030334473,
+      "step": 1690
+    },
+    {
+      "epoch": 0.5494949494949495,
+      "grad_norm": 0.010512005537748337,
+      "learning_rate": 4.6022433665021246e-05,
+      "loss": 0.48582897186279295,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5527272727272727,
+      "grad_norm": 0.00989206787198782,
+      "learning_rate": 4.548989864010902e-05,
+      "loss": 0.4849580764770508,
+      "step": 1710
+    },
+    {
+      "epoch": 0.555959595959596,
+      "grad_norm": 0.010284029878675938,
+      "learning_rate": 4.495787894201031e-05,
+      "loss": 0.49089298248291013,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5591919191919192,
+      "grad_norm": 0.00992760993540287,
+      "learning_rate": 4.442643535960631e-05,
+      "loss": 0.48010549545288084,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5624242424242424,
+      "grad_norm": 0.00978371873497963,
+      "learning_rate": 4.3895628615950864e-05,
+      "loss": 0.47594566345214845,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.00981004349887371,
+      "learning_rate": 4.3365519361332345e-05,
+      "loss": 0.48056421279907224,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.010216868482530117,
+      "learning_rate": 4.283616816634353e-05,
+      "loss": 0.47501134872436523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5721212121212121,
+      "grad_norm": 0.010267022997140884,
+      "learning_rate": 4.230763551496089e-05,
+      "loss": 0.478366756439209,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5753535353535354,
+      "grad_norm": 0.009910739958286285,
+      "learning_rate": 4.1779981797633645e-05,
+      "loss": 0.478058385848999,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5785858585858585,
+      "grad_norm": 0.011339185759425163,
+      "learning_rate": 4.1253267304383455e-05,
+      "loss": 0.48466057777404786,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 0.009522072039544582,
+      "learning_rate": 4.072755221791572e-05,
+      "loss": 0.4769908905029297,
+      "step": 1800
+    },
+    {
+      "epoch": 0.585050505050505,
+      "grad_norm": 0.009808518923819065,
+      "learning_rate": 4.020289660674306e-05,
+      "loss": 0.47162666320800783,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5882828282828283,
+      "grad_norm": 0.009962448850274086,
+      "learning_rate": 3.967936041832173e-05,
+      "loss": 0.46282405853271485,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5915151515151515,
+      "grad_norm": 0.009498678147792816,
+      "learning_rate": 3.9157003472202246e-05,
+      "loss": 0.4794480323791504,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5947474747474748,
+      "grad_norm": 0.009407177567481995,
+      "learning_rate": 3.863588545319407e-05,
+      "loss": 0.4729412078857422,
+      "step": 1840
+    },
+    {
+      "epoch": 0.597979797979798,
+      "grad_norm": 0.009899895638227463,
+      "learning_rate": 3.8116065904546196e-05,
+      "loss": 0.47380704879760743,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6012121212121212,
+      "grad_norm": 0.009560837410390377,
+      "learning_rate": 3.759760422114362e-05,
+      "loss": 0.47751388549804685,
+      "step": 1860
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.010970192961394787,
+      "learning_rate": 3.708055964272088e-05,
+      "loss": 0.47801823616027833,
+      "step": 1870
+    },
+    {
+      "epoch": 0.6076767676767677,
+      "grad_norm": 0.00964390765875578,
+      "learning_rate": 3.6564991247093234e-05,
+      "loss": 0.4800426483154297,
+      "step": 1880
+    },
+    {
+      "epoch": 0.610909090909091,
+      "grad_norm": 0.009764602407813072,
+      "learning_rate": 3.6050957943406465e-05,
+      "loss": 0.4812753677368164,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6141414141414141,
+      "grad_norm": 0.009959314949810505,
+      "learning_rate": 3.553851846540584e-05,
+      "loss": 0.47804956436157225,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6173737373737374,
+      "grad_norm": 0.010666392743587494,
+      "learning_rate": 3.50277313647252e-05,
+      "loss": 0.4772273063659668,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6206060606060606,
+      "grad_norm": 0.009173358790576458,
+      "learning_rate": 3.451865500419676e-05,
+      "loss": 0.4892144203186035,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6238383838383839,
+      "grad_norm": 0.010000358335673809,
+      "learning_rate": 3.401134755118256e-05,
+      "loss": 0.48959059715270997,
+      "step": 1930
+    },
+    {
+      "epoch": 0.6270707070707071,
+      "grad_norm": 0.010190536268055439,
+      "learning_rate": 3.350586697092826e-05,
+      "loss": 0.46478729248046874,
+      "step": 1940
+    },
+    {
+      "epoch": 0.6303030303030303,
+      "grad_norm": 0.010812178254127502,
+      "learning_rate": 3.300227101993998e-05,
+      "loss": 0.5046152114868164,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6335353535353535,
+      "grad_norm": 0.01017849799245596,
+      "learning_rate": 3.2500617239384947e-05,
+      "loss": 0.4698008060455322,
+      "step": 1960
+    },
+    {
+      "epoch": 0.6367676767676768,
+      "grad_norm": 0.011103908531367779,
+      "learning_rate": 3.200096294851691e-05,
+      "loss": 0.4716217041015625,
+      "step": 1970
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.009982883930206299,
+      "learning_rate": 3.150336523812674e-05,
+      "loss": 0.47135162353515625,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6432323232323233,
+      "grad_norm": 0.01043197326362133,
+      "learning_rate": 3.100788096401925e-05,
+      "loss": 0.4799614906311035,
+      "step": 1990
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.010667623952031136,
+      "learning_rate": 3.051456674051677e-05,
+      "loss": 0.4682164192199707,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6496969696969697,
+      "grad_norm": 0.010620036162436008,
+      "learning_rate": 3.0023478933990347e-05,
+      "loss": 0.4750208854675293,
+      "step": 2010
+    },
+    {
+      "epoch": 0.6529292929292929,
+      "grad_norm": 0.010374991223216057,
+      "learning_rate": 2.9534673656419377e-05,
+      "loss": 0.48034076690673827,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6561616161616162,
+      "grad_norm": 0.011932817287743092,
+      "learning_rate": 2.9048206758980136e-05,
+      "loss": 0.46314101219177245,
+      "step": 2030
+    },
+    {
+      "epoch": 0.6593939393939394,
+      "grad_norm": 0.01039852574467659,
+      "learning_rate": 2.856413382566425e-05,
+      "loss": 0.4783937454223633,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6626262626262627,
+      "grad_norm": 0.010200604796409607,
+      "learning_rate": 2.8082510166927583e-05,
+      "loss": 0.4792025089263916,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6658585858585858,
+      "grad_norm": 0.009561127051711082,
+      "learning_rate": 2.760339081337041e-05,
+      "loss": 0.4722686767578125,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6690909090909091,
+      "grad_norm": 0.00924921128898859,
+      "learning_rate": 2.7126830509449773e-05,
+      "loss": 0.4884464263916016,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6723232323232323,
+      "grad_norm": 0.00991444569081068,
+      "learning_rate": 2.6652883707224075e-05,
+      "loss": 0.4804549217224121,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.009902069345116615,
+      "learning_rate": 2.618160456013153e-05,
+      "loss": 0.4781071186065674,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 0.010504493489861488,
+      "learning_rate": 2.571304691680255e-05,
+      "loss": 0.48059587478637694,
+      "step": 2100
+    },
+    {
+      "epoch": 0.682020202020202,
+      "grad_norm": 0.009641965851187706,
+      "learning_rate": 2.5247264314906917e-05,
+      "loss": 0.4706240177154541,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6852525252525252,
+      "grad_norm": 0.010276644490659237,
+      "learning_rate": 2.4784309975036513e-05,
+      "loss": 0.4885101318359375,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6884848484848485,
+      "grad_norm": 0.010960405692458153,
+      "learning_rate": 2.4324236794624456e-05,
+      "loss": 0.4882383346557617,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6917171717171717,
+      "grad_norm": 0.010282796807587147,
+      "learning_rate": 2.386709734190079e-05,
+      "loss": 0.4768857479095459,
+      "step": 2140
+    },
+    {
+      "epoch": 0.694949494949495,
+      "grad_norm": 0.010104385204613209,
+      "learning_rate": 2.34129438498862e-05,
+      "loss": 0.4802837371826172,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6981818181818182,
+      "grad_norm": 0.010027035139501095,
+      "learning_rate": 2.296182821042374e-05,
+      "loss": 0.4874839782714844,
+      "step": 2160
+    },
+    {
+      "epoch": 0.7014141414141414,
+      "grad_norm": 0.010018851608037949,
+      "learning_rate": 2.2513801968249644e-05,
+      "loss": 0.4758561134338379,
+      "step": 2170
+    },
+    {
+      "epoch": 0.7046464646464646,
+      "grad_norm": 0.009862969629466534,
+      "learning_rate": 2.2068916315103783e-05,
+      "loss": 0.4686488151550293,
+      "step": 2180
+    },
+    {
+      "epoch": 0.7078787878787879,
+      "grad_norm": 0.00952910166233778,
+      "learning_rate": 2.162722208388057e-05,
+      "loss": 0.4782154083251953,
+      "step": 2190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.010213647037744522,
+      "learning_rate": 2.1188769742820625e-05,
+      "loss": 0.4773773193359375,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7143434343434344,
+      "grad_norm": 0.010498392395675182,
+      "learning_rate": 2.075360938974429e-05,
+      "loss": 0.4733907222747803,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7175757575757575,
+      "grad_norm": 0.009394815191626549,
+      "learning_rate": 2.03217907463275e-05,
+      "loss": 0.47564210891723635,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7208080808080808,
+      "grad_norm": 0.010383618995547295,
+      "learning_rate": 1.989336315242048e-05,
+      "loss": 0.4784512519836426,
+      "step": 2230
+    },
+    {
+      "epoch": 0.724040404040404,
+      "grad_norm": 0.01043599285185337,
+      "learning_rate": 1.9468375560410117e-05,
+      "loss": 0.4808964729309082,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.009953988716006279,
+      "learning_rate": 1.90468765296267e-05,
+      "loss": 0.49031834602355956,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7305050505050505,
+      "grad_norm": 0.010356656275689602,
+      "learning_rate": 1.8628914220795494e-05,
+      "loss": 0.48055601119995117,
+      "step": 2260
+    },
+    {
+      "epoch": 0.7337373737373737,
+      "grad_norm": 0.009841440245509148,
+      "learning_rate": 1.8214536390533822e-05,
+      "loss": 0.47170586585998536,
+      "step": 2270
+    },
+    {
+      "epoch": 0.7369696969696969,
+      "grad_norm": 0.010102550499141216,
+      "learning_rate": 1.7803790385894387e-05,
+      "loss": 0.4660043716430664,
+      "step": 2280
+    },
+    {
+      "epoch": 0.7402020202020202,
+      "grad_norm": 0.010421738028526306,
+      "learning_rate": 1.7396723138955428e-05,
+      "loss": 0.4599196434020996,
+      "step": 2290
+    },
+    {
+      "epoch": 0.7434343434343434,
+      "grad_norm": 0.009896540082991123,
+      "learning_rate": 1.699338116145811e-05,
+      "loss": 0.46491589546203616,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.010468855500221252,
+      "learning_rate": 1.6593810539492195e-05,
+      "loss": 0.47761125564575196,
+      "step": 2310
+    },
+    {
+      "epoch": 0.74989898989899,
+      "grad_norm": 0.010416937991976738,
+      "learning_rate": 1.619805692823016e-05,
+      "loss": 0.49956817626953126,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7531313131313131,
+      "grad_norm": 0.010007611475884914,
+      "learning_rate": 1.580616554671057e-05,
+      "loss": 0.4716916084289551,
+      "step": 2330
+    },
+    {
+      "epoch": 0.7563636363636363,
+      "grad_norm": 0.010231648571789265,
+      "learning_rate": 1.5418181172671382e-05,
+      "loss": 0.4909040451049805,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7595959595959596,
+      "grad_norm": 0.010324012488126755,
+      "learning_rate": 1.5034148137433623e-05,
+      "loss": 0.47939190864562986,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7628282828282829,
+      "grad_norm": 0.011009547859430313,
+      "learning_rate": 1.4654110320836017e-05,
+      "loss": 0.48291826248168945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7660606060606061,
+      "grad_norm": 0.010392943397164345,
+      "learning_rate": 1.4278111146221263e-05,
+      "loss": 0.49179973602294924,
+      "step": 2370
+    },
+    {
+      "epoch": 0.7692929292929293,
+      "grad_norm": 0.010355197824537754,
+      "learning_rate": 1.3906193575474508e-05,
+      "loss": 0.4716278076171875,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7725252525252525,
+      "grad_norm": 0.009932084940373898,
+      "learning_rate": 1.3538400104114446e-05,
+      "loss": 0.47190055847167967,
+      "step": 2390
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 0.010710643604397774,
+      "learning_rate": 1.3174772756437742e-05,
+      "loss": 0.4703176498413086,
+      "step": 2400
+    },
+    {
+      "epoch": 0.778989898989899,
+      "grad_norm": 0.010614068247377872,
+      "learning_rate": 1.2815353080717379e-05,
+      "loss": 0.47541141510009766,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.011346950195729733,
+      "learning_rate": 1.246018214445525e-05,
+      "loss": 0.4860015869140625,
+      "step": 2420
+    },
+    {
+      "epoch": 0.7854545454545454,
+      "grad_norm": 0.009824907407164574,
+      "learning_rate": 1.210930052968981e-05,
+      "loss": 0.49062480926513674,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7886868686868687,
+      "grad_norm": 0.010624224320054054,
+      "learning_rate": 1.1762748328359152e-05,
+      "loss": 0.4694485664367676,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7919191919191919,
+      "grad_norm": 0.01044746395200491,
+      "learning_rate": 1.1420565137720045e-05,
+      "loss": 0.47275629043579104,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7951515151515152,
+      "grad_norm": 0.010226710699498653,
+      "learning_rate": 1.1082790055823533e-05,
+      "loss": 0.4670067310333252,
+      "step": 2460
+    },
+    {
+      "epoch": 0.7983838383838384,
+      "grad_norm": 0.010427460074424744,
+      "learning_rate": 1.0749461677047624e-05,
+      "loss": 0.4700475692749023,
+      "step": 2470
+    },
+    {
+      "epoch": 0.8016161616161617,
+      "grad_norm": 0.010494428686797619,
+      "learning_rate": 1.0420618087687418e-05,
+      "loss": 0.46589016914367676,
+      "step": 2480
+    },
+    {
+      "epoch": 0.8048484848484848,
+      "grad_norm": 0.010100893676280975,
+      "learning_rate": 1.0096296861603321e-05,
+      "loss": 0.4704419136047363,
+      "step": 2490
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.010682797059416771,
+      "learning_rate": 9.776535055927931e-06,
+      "loss": 0.47326183319091797,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8113131313131313,
+      "grad_norm": 0.00972407590597868,
+      "learning_rate": 9.461369206831772e-06,
+      "loss": 0.48441619873046876,
+      "step": 2510
+    },
+    {
+      "epoch": 0.8145454545454546,
+      "grad_norm": 0.010327558033168316,
+      "learning_rate": 9.150835325348678e-06,
+      "loss": 0.45856351852416993,
+      "step": 2520
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.010118944570422173,
+      "learning_rate": 8.844968893261197e-06,
+      "loss": 0.48114948272705077,
+      "step": 2530
+    },
+    {
+      "epoch": 0.821010101010101,
+      "grad_norm": 0.010876161977648735,
+      "learning_rate": 8.543804859046345e-06,
+      "loss": 0.4930680274963379,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8242424242424242,
+      "grad_norm": 0.010722608305513859,
+      "learning_rate": 8.247377633882463e-06,
+      "loss": 0.46875743865966796,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8274747474747475,
+      "grad_norm": 0.01088438369333744,
+      "learning_rate": 7.95572108771726e-06,
+      "loss": 0.4768000602722168,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8307070707070707,
+      "grad_norm": 0.01026720181107521,
+      "learning_rate": 7.66886854539795e-06,
+      "loss": 0.479974365234375,
+      "step": 2570
+    },
+    {
+      "epoch": 0.833939393939394,
+      "grad_norm": 0.009710075333714485,
+      "learning_rate": 7.386852782863407e-06,
+      "loss": 0.4684715270996094,
+      "step": 2580
+    },
+    {
+      "epoch": 0.8371717171717171,
+      "grad_norm": 0.009966167621314526,
+      "learning_rate": 7.109706023399232e-06,
+      "loss": 0.47191972732543946,
+      "step": 2590
+    },
+    {
+      "epoch": 0.8404040404040404,
+      "grad_norm": 0.010125650092959404,
+      "learning_rate": 6.837459933955936e-06,
+      "loss": 0.4766803741455078,
+      "step": 2600
+    },
+    {
+      "epoch": 0.8436363636363636,
+      "grad_norm": 0.009984518401324749,
+      "learning_rate": 6.5701456215305656e-06,
+      "loss": 0.4592133045196533,
+      "step": 2610
+    },
+    {
+      "epoch": 0.8468686868686869,
+      "grad_norm": 0.010836348868906498,
+      "learning_rate": 6.307793629612452e-06,
+      "loss": 0.4658504009246826,
+      "step": 2620
+    },
+    {
+      "epoch": 0.8501010101010101,
+      "grad_norm": 0.010431919246912003,
+      "learning_rate": 6.050433934693339e-06,
+      "loss": 0.4936856269836426,
+      "step": 2630
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.01049034669995308,
+      "learning_rate": 5.798095942842141e-06,
+      "loss": 0.4765117645263672,
+      "step": 2640
+    },
+    {
+      "epoch": 0.8565656565656565,
+      "grad_norm": 0.009596607647836208,
+      "learning_rate": 5.550808486345072e-06,
+      "loss": 0.47063379287719725,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8597979797979798,
+      "grad_norm": 0.01032214518636465,
+      "learning_rate": 5.308599820411247e-06,
+      "loss": 0.4614537715911865,
+      "step": 2660
+    },
+    {
+      "epoch": 0.863030303030303,
+      "grad_norm": 0.009960100054740906,
+      "learning_rate": 5.071497619944171e-06,
+      "loss": 0.48136143684387206,
+      "step": 2670
+    },
+    {
+      "epoch": 0.8662626262626263,
+      "grad_norm": 0.010326167568564415,
+      "learning_rate": 4.839528976379648e-06,
+      "loss": 0.47299985885620116,
+      "step": 2680
+    },
+    {
+      "epoch": 0.8694949494949495,
+      "grad_norm": 0.010867294855415821,
+      "learning_rate": 4.612720394590286e-06,
+      "loss": 0.4829209327697754,
+      "step": 2690
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.01050047017633915,
+      "learning_rate": 4.391097789856985e-06,
+      "loss": 0.4762550354003906,
+      "step": 2700
+    },
+    {
+      "epoch": 0.8759595959595959,
+      "grad_norm": 0.010378929786384106,
+      "learning_rate": 4.174686484907908e-06,
+      "loss": 0.4898251533508301,
+      "step": 2710
+    },
+    {
+      "epoch": 0.8791919191919192,
+      "grad_norm": 0.01060938648879528,
+      "learning_rate": 3.963511207025078e-06,
+      "loss": 0.47261548042297363,
+      "step": 2720
+    },
+    {
+      "epoch": 0.8824242424242424,
+      "grad_norm": 0.01075353566557169,
+      "learning_rate": 3.7575960852189728e-06,
+      "loss": 0.4839645862579346,
+      "step": 2730
+    },
+    {
+      "epoch": 0.8856565656565657,
+      "grad_norm": 0.010416378267109394,
+      "learning_rate": 3.5569646474715722e-06,
+      "loss": 0.46989760398864744,
+      "step": 2740
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.010806340724229813,
+      "learning_rate": 3.361639818048068e-06,
+      "loss": 0.47272281646728515,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8921212121212121,
+      "grad_norm": 0.009753530845046043,
+      "learning_rate": 3.1716439148774534e-06,
+      "loss": 0.47122917175292967,
+      "step": 2760
+    },
+    {
+      "epoch": 0.8953535353535353,
+      "grad_norm": 0.01022200658917427,
+      "learning_rate": 2.986998647002498e-06,
+      "loss": 0.4727674961090088,
+      "step": 2770
+    },
+    {
+      "epoch": 0.8985858585858586,
+      "grad_norm": 0.010225590318441391,
+      "learning_rate": 2.8077251120992742e-06,
+      "loss": 0.46461896896362304,
+      "step": 2780
+    },
+    {
+      "epoch": 0.9018181818181819,
+      "grad_norm": 0.010752941481769085,
+      "learning_rate": 2.633843794066515e-06,
+      "loss": 0.46602635383605956,
+      "step": 2790
+    },
+    {
+      "epoch": 0.9050505050505051,
+      "grad_norm": 0.011064955033361912,
+      "learning_rate": 2.465374560685091e-06,
+      "loss": 0.4705932140350342,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9082828282828282,
+      "grad_norm": 0.00982996542006731,
+      "learning_rate": 2.302336661347926e-06,
+      "loss": 0.4687389373779297,
+      "step": 2810
+    },
+    {
+      "epoch": 0.9115151515151515,
+      "grad_norm": 0.010190518572926521,
+      "learning_rate": 2.1447487248605513e-06,
+      "loss": 0.4906333923339844,
+      "step": 2820
+    },
+    {
+      "epoch": 0.9147474747474748,
+      "grad_norm": 0.01034579798579216,
+      "learning_rate": 1.9926287573125537e-06,
+      "loss": 0.47768077850341795,
+      "step": 2830
+    },
+    {
+      "epoch": 0.917979797979798,
+      "grad_norm": 0.010615529492497444,
+      "learning_rate": 1.845994140020213e-06,
+      "loss": 0.47643141746520995,
+      "step": 2840
+    },
+    {
+      "epoch": 0.9212121212121213,
+      "grad_norm": 0.010776858776807785,
+      "learning_rate": 1.7048616275404771e-06,
+      "loss": 0.4636590003967285,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.010271280072629452,
+      "learning_rate": 1.5692473457565748e-06,
+      "loss": 0.4707911014556885,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9276767676767677,
+      "grad_norm": 0.009596684016287327,
+      "learning_rate": 1.439166790035501e-06,
+      "loss": 0.45751228332519533,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9309090909090909,
+      "grad_norm": 0.009914812631905079,
+      "learning_rate": 1.3146348234574724e-06,
+      "loss": 0.4842953681945801,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9341414141414142,
+      "grad_norm": 0.01014726422727108,
+      "learning_rate": 1.1956656751176577e-06,
+      "loss": 0.482682991027832,
+      "step": 2890
+    },
+    {
+      "epoch": 0.9373737373737374,
+      "grad_norm": 0.010660757310688496,
+      "learning_rate": 1.0822729385003727e-06,
+      "loss": 0.48476057052612304,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9406060606060606,
+      "grad_norm": 0.010105855762958527,
+      "learning_rate": 9.744695699258955e-07,
+      "loss": 0.4767448425292969,
+      "step": 2910
+    },
+    {
+      "epoch": 0.9438383838383838,
+      "grad_norm": 0.010221844539046288,
+      "learning_rate": 8.722678870700274e-07,
+      "loss": 0.4663360118865967,
+      "step": 2920
+    },
+    {
+      "epoch": 0.9470707070707071,
+      "grad_norm": 0.011003104969859123,
+      "learning_rate": 7.756795675566919e-07,
+      "loss": 0.48151307106018065,
+      "step": 2930
+    },
+    {
+      "epoch": 0.9503030303030303,
+      "grad_norm": 0.01029619574546814,
+      "learning_rate": 6.847156476236516e-07,
+      "loss": 0.48086977005004883,
+      "step": 2940
+    },
+    {
+      "epoch": 0.9535353535353536,
+      "grad_norm": 0.010033480823040009,
+      "learning_rate": 5.993865208614835e-07,
+      "loss": 0.4648440361022949,
+      "step": 2950
+    },
+    {
+      "epoch": 0.9567676767676768,
+      "grad_norm": 0.010539564304053783,
+      "learning_rate": 5.197019370260125e-07,
+      "loss": 0.46828551292419435,
+      "step": 2960
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.009619071148335934,
+      "learning_rate": 4.4567100092429704e-07,
+      "loss": 0.48481130599975586,
+      "step": 2970
+    },
+    {
+      "epoch": 0.9632323232323232,
+      "grad_norm": 0.010197056457400322,
+      "learning_rate": 3.7730217137428857e-07,
+      "loss": 0.47917518615722654,
+      "step": 2980
+    },
+    {
+      "epoch": 0.9664646464646465,
+      "grad_norm": 0.01057458110153675,
+      "learning_rate": 3.1460326023836083e-07,
+      "loss": 0.48064794540405276,
+      "step": 2990
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.01009963545948267,
+      "learning_rate": 2.575814315306846e-07,
+      "loss": 0.4831876754760742,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972929292929293,
+      "grad_norm": 0.010343736037611961,
+      "learning_rate": 2.0624320059869918e-07,
+      "loss": 0.4821047306060791,
+      "step": 3010
+    },
+    {
+      "epoch": 0.9761616161616161,
+      "grad_norm": 0.010384611785411835,
+      "learning_rate": 1.6059443337861912e-07,
+      "loss": 0.46325201988220216,
+      "step": 3020
+    },
+    {
+      "epoch": 0.9793939393939394,
+      "grad_norm": 0.010477159172296524,
+      "learning_rate": 1.2064034572523142e-07,
+      "loss": 0.4779689788818359,
+      "step": 3030
+    },
+    {
+      "epoch": 0.9826262626262626,
+      "grad_norm": 0.010612626560032368,
+      "learning_rate": 8.638550281591107e-08,
+      "loss": 0.4866930484771729,
+      "step": 3040
+    },
+    {
+      "epoch": 0.9858585858585859,
+      "grad_norm": 0.01027057133615017,
+      "learning_rate": 5.7833818629005054e-08,
+      "loss": 0.48350844383239744,
+      "step": 3050
+    },
+    {
+      "epoch": 0.9890909090909091,
+      "grad_norm": 0.010666116140782833,
+      "learning_rate": 3.498855549660118e-08,
+      "loss": 0.4722591400146484,
+      "step": 3060
+    },
+    {
+      "epoch": 0.9923232323232323,
+      "grad_norm": 0.009852438233792782,
+      "learning_rate": 1.785232373180401e-08,
+      "loss": 0.48914670944213867,
+      "step": 3070
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.010089240968227386,
+      "learning_rate": 6.427081330456774e-09,
+      "loss": 0.4730827331542969,
+      "step": 3080
+    },
+    {
+      "epoch": 0.9987878787878788,
+      "grad_norm": 0.010913597419857979,
+      "learning_rate": 7.141337474148025e-10,
+      "loss": 0.4666846752166748,
+      "step": 3090
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.3887930550675046e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 4.3887930550675046e+18,
+    "train_loss": 0.4842414558126453,
+    "train_runtime": 8903.7116,
+    "train_samples_per_second": 22.238,
+    "train_steps_per_second": 0.347
+}

trainer_log.jsonl

@@ -0,0 +1,310 @@
+{"current_steps": 10, "total_steps": 3094, "loss": 0.6013355255126953, "lr": 5.806451612903226e-06, "epoch": 0.0032323232323232323, "percentage": 0.32, "elapsed_time": "0:00:40", "remaining_time": "3:26:56"}
+{"current_steps": 20, "total_steps": 3094, "loss": 0.5758121490478516, "lr": 1.2258064516129032e-05, "epoch": 0.006464646464646465, "percentage": 0.65, "elapsed_time": "0:01:13", "remaining_time": "3:09:04"}
+{"current_steps": 30, "total_steps": 3094, "loss": 0.5787662506103516, "lr": 1.870967741935484e-05, "epoch": 0.009696969696969697, "percentage": 0.97, "elapsed_time": "0:01:44", "remaining_time": "2:57:10"}
+{"current_steps": 40, "total_steps": 3094, "loss": 0.5327143669128418, "lr": 2.5161290322580645e-05, "epoch": 0.01292929292929293, "percentage": 1.29, "elapsed_time": "0:02:15", "remaining_time": "2:51:53"}
+{"current_steps": 50, "total_steps": 3094, "loss": 0.5393171310424805, "lr": 3.161290322580645e-05, "epoch": 0.01616161616161616, "percentage": 1.62, "elapsed_time": "0:02:45", "remaining_time": "2:48:01"}
+{"current_steps": 60, "total_steps": 3094, "loss": 0.5058945178985595, "lr": 3.8064516129032254e-05, "epoch": 0.019393939393939394, "percentage": 1.94, "elapsed_time": "0:03:16", "remaining_time": "2:45:28"}
+{"current_steps": 70, "total_steps": 3094, "loss": 0.517607593536377, "lr": 4.451612903225807e-05, "epoch": 0.022626262626262626, "percentage": 2.26, "elapsed_time": "0:03:46", "remaining_time": "2:42:45"}
+{"current_steps": 80, "total_steps": 3094, "loss": 0.5269095420837402, "lr": 5.096774193548387e-05, "epoch": 0.02585858585858586, "percentage": 2.59, "elapsed_time": "0:04:14", "remaining_time": "2:40:03"}
+{"current_steps": 90, "total_steps": 3094, "loss": 0.5040688514709473, "lr": 5.7419354838709685e-05, "epoch": 0.02909090909090909, "percentage": 2.91, "elapsed_time": "0:04:44", "remaining_time": "2:38:15"}
+{"current_steps": 100, "total_steps": 3094, "loss": 0.5147775173187256, "lr": 6.387096774193548e-05, "epoch": 0.03232323232323232, "percentage": 3.23, "elapsed_time": "0:05:12", "remaining_time": "2:36:09"}
+{"current_steps": 110, "total_steps": 3094, "loss": 0.5230005741119385, "lr": 7.03225806451613e-05, "epoch": 0.035555555555555556, "percentage": 3.56, "elapsed_time": "0:05:41", "remaining_time": "2:34:18"}
+{"current_steps": 120, "total_steps": 3094, "loss": 0.5105222702026367, "lr": 7.67741935483871e-05, "epoch": 0.03878787878787879, "percentage": 3.88, "elapsed_time": "0:06:09", "remaining_time": "2:32:46"}
+{"current_steps": 130, "total_steps": 3094, "loss": 0.4989170074462891, "lr": 8.32258064516129e-05, "epoch": 0.04202020202020202, "percentage": 4.2, "elapsed_time": "0:06:38", "remaining_time": "2:31:30"}
+{"current_steps": 140, "total_steps": 3094, "loss": 0.5003124713897705, "lr": 8.967741935483871e-05, "epoch": 0.04525252525252525, "percentage": 4.52, "elapsed_time": "0:07:07", "remaining_time": "2:30:27"}
+{"current_steps": 150, "total_steps": 3094, "loss": 0.5077538013458252, "lr": 9.612903225806452e-05, "epoch": 0.048484848484848485, "percentage": 4.85, "elapsed_time": "0:07:36", "remaining_time": "2:29:17"}
+{"current_steps": 160, "total_steps": 3094, "loss": 0.5061477661132813, "lr": 9.999954295400999e-05, "epoch": 0.05171717171717172, "percentage": 5.17, "elapsed_time": "0:08:04", "remaining_time": "2:28:10"}
+{"current_steps": 170, "total_steps": 3094, "loss": 0.5013481140136719, "lr": 9.999440128258112e-05, "epoch": 0.05494949494949495, "percentage": 5.49, "elapsed_time": "0:08:33", "remaining_time": "2:27:13"}
+{"current_steps": 180, "total_steps": 3094, "loss": 0.48343815803527834, "lr": 9.998354722168459e-05, "epoch": 0.05818181818181818, "percentage": 5.82, "elapsed_time": "0:09:02", "remaining_time": "2:26:28"}
+{"current_steps": 190, "total_steps": 3094, "loss": 0.507840633392334, "lr": 9.996698201151175e-05, "epoch": 0.061414141414141414, "percentage": 6.14, "elapsed_time": "0:09:31", "remaining_time": "2:25:30"}
+{"current_steps": 200, "total_steps": 3094, "loss": 0.49884777069091796, "lr": 9.994470754481315e-05, "epoch": 0.06464646464646465, "percentage": 6.46, "elapsed_time": "0:09:58", "remaining_time": "2:24:27"}
+{"current_steps": 210, "total_steps": 3094, "loss": 0.5068713188171386, "lr": 9.991672636668239e-05, "epoch": 0.06787878787878789, "percentage": 6.79, "elapsed_time": "0:10:39", "remaining_time": "2:26:19"}
+{"current_steps": 220, "total_steps": 3094, "loss": 0.4920186519622803, "lr": 9.988304167426519e-05, "epoch": 0.07111111111111111, "percentage": 7.11, "elapsed_time": "0:11:07", "remaining_time": "2:25:18"}
+{"current_steps": 230, "total_steps": 3094, "loss": 0.5021648406982422, "lr": 9.984365731639419e-05, "epoch": 0.07434343434343435, "percentage": 7.43, "elapsed_time": "0:11:36", "remaining_time": "2:24:27"}
+{"current_steps": 240, "total_steps": 3094, "loss": 0.5038897514343261, "lr": 9.979857779314906e-05, "epoch": 0.07757575757575758, "percentage": 7.76, "elapsed_time": "0:12:05", "remaining_time": "2:23:41"}
+{"current_steps": 250, "total_steps": 3094, "loss": 0.4965065956115723, "lr": 9.974780825534246e-05, "epoch": 0.08080808080808081, "percentage": 8.08, "elapsed_time": "0:12:32", "remaining_time": "2:22:37"}
+{"current_steps": 260, "total_steps": 3094, "loss": 0.5145994186401367, "lr": 9.969135450393141e-05, "epoch": 0.08404040404040404, "percentage": 8.4, "elapsed_time": "0:13:00", "remaining_time": "2:21:49"}
+{"current_steps": 270, "total_steps": 3094, "loss": 0.505019235610962, "lr": 9.96292229893545e-05, "epoch": 0.08727272727272728, "percentage": 8.73, "elapsed_time": "0:13:29", "remaining_time": "2:21:02"}
+{"current_steps": 280, "total_steps": 3094, "loss": 0.5115808010101318, "lr": 9.956142081079484e-05, "epoch": 0.0905050505050505, "percentage": 9.05, "elapsed_time": "0:13:56", "remaining_time": "2:20:10"}
+{"current_steps": 290, "total_steps": 3094, "loss": 0.48525152206420896, "lr": 9.948795571536891e-05, "epoch": 0.09373737373737374, "percentage": 9.37, "elapsed_time": "0:14:25", "remaining_time": "2:19:31"}
+{"current_steps": 300, "total_steps": 3094, "loss": 0.5002010822296142, "lr": 9.94088360972414e-05, "epoch": 0.09696969696969697, "percentage": 9.7, "elapsed_time": "0:14:53", "remaining_time": "2:18:45"}
+{"current_steps": 310, "total_steps": 3094, "loss": 0.49662046432495116, "lr": 9.932407099666608e-05, "epoch": 0.10020202020202021, "percentage": 10.02, "elapsed_time": "0:15:21", "remaining_time": "2:17:57"}
+{"current_steps": 320, "total_steps": 3094, "loss": 0.48578290939331054, "lr": 9.923367009895274e-05, "epoch": 0.10343434343434343, "percentage": 10.34, "elapsed_time": "0:15:50", "remaining_time": "2:17:19"}
+{"current_steps": 330, "total_steps": 3094, "loss": 0.48862767219543457, "lr": 9.913764373336079e-05, "epoch": 0.10666666666666667, "percentage": 10.67, "elapsed_time": "0:16:19", "remaining_time": "2:16:45"}
+{"current_steps": 340, "total_steps": 3094, "loss": 0.5034208774566651, "lr": 9.903600287191875e-05, "epoch": 0.1098989898989899, "percentage": 10.99, "elapsed_time": "0:16:48", "remaining_time": "2:16:05"}
+{"current_steps": 350, "total_steps": 3094, "loss": 0.4870161533355713, "lr": 9.892875912817079e-05, "epoch": 0.11313131313131314, "percentage": 11.31, "elapsed_time": "0:17:16", "remaining_time": "2:15:25"}
+{"current_steps": 360, "total_steps": 3094, "loss": 0.5026071548461915, "lr": 9.881592475584964e-05, "epoch": 0.11636363636363636, "percentage": 11.64, "elapsed_time": "0:17:44", "remaining_time": "2:14:41"}
+{"current_steps": 370, "total_steps": 3094, "loss": 0.4883917808532715, "lr": 9.869751264747656e-05, "epoch": 0.1195959595959596, "percentage": 11.96, "elapsed_time": "0:18:12", "remaining_time": "2:14:01"}
+{"current_steps": 380, "total_steps": 3094, "loss": 0.4927018165588379, "lr": 9.857353633288814e-05, "epoch": 0.12282828282828283, "percentage": 12.28, "elapsed_time": "0:18:40", "remaining_time": "2:13:25"}
+{"current_steps": 390, "total_steps": 3094, "loss": 0.4908174514770508, "lr": 9.844400997769043e-05, "epoch": 0.12606060606060607, "percentage": 12.61, "elapsed_time": "0:19:09", "remaining_time": "2:12:51"}
+{"current_steps": 400, "total_steps": 3094, "loss": 0.5069625854492188, "lr": 9.83089483816404e-05, "epoch": 0.1292929292929293, "percentage": 12.93, "elapsed_time": "0:19:38", "remaining_time": "2:12:17"}
+{"current_steps": 410, "total_steps": 3094, "loss": 0.4988056182861328, "lr": 9.816836697695482e-05, "epoch": 0.13252525252525252, "percentage": 13.25, "elapsed_time": "0:20:14", "remaining_time": "2:12:28"}
+{"current_steps": 420, "total_steps": 3094, "loss": 0.5007385730743408, "lr": 9.802228182654702e-05, "epoch": 0.13575757575757577, "percentage": 13.57, "elapsed_time": "0:20:42", "remaining_time": "2:11:53"}
+{"current_steps": 430, "total_steps": 3094, "loss": 0.5130783081054687, "lr": 9.787070962219156e-05, "epoch": 0.138989898989899, "percentage": 13.9, "elapsed_time": "0:21:10", "remaining_time": "2:11:13"}
+{"current_steps": 440, "total_steps": 3094, "loss": 0.4947535514831543, "lr": 9.771366768261696e-05, "epoch": 0.14222222222222222, "percentage": 14.22, "elapsed_time": "0:21:38", "remaining_time": "2:10:32"}
+{"current_steps": 450, "total_steps": 3094, "loss": 0.4917112350463867, "lr": 9.755117395152689e-05, "epoch": 0.14545454545454545, "percentage": 14.54, "elapsed_time": "0:22:05", "remaining_time": "2:09:49"}
+{"current_steps": 460, "total_steps": 3094, "loss": 0.4882859230041504, "lr": 9.73832469955499e-05, "epoch": 0.1486868686868687, "percentage": 14.87, "elapsed_time": "0:22:35", "remaining_time": "2:09:18"}
+{"current_steps": 470, "total_steps": 3094, "loss": 0.500526762008667, "lr": 9.720990600211797e-05, "epoch": 0.15191919191919193, "percentage": 15.19, "elapsed_time": "0:23:03", "remaining_time": "2:08:42"}
+{"current_steps": 480, "total_steps": 3094, "loss": 0.496882963180542, "lr": 9.703117077727419e-05, "epoch": 0.15515151515151515, "percentage": 15.51, "elapsed_time": "0:23:31", "remaining_time": "2:08:05"}
+{"current_steps": 490, "total_steps": 3094, "loss": 0.48728485107421876, "lr": 9.684706174340965e-05, "epoch": 0.15838383838383838, "percentage": 15.84, "elapsed_time": "0:23:58", "remaining_time": "2:07:24"}
+{"current_steps": 500, "total_steps": 3094, "loss": 0.49378366470336915, "lr": 9.665759993693e-05, "epoch": 0.16161616161616163, "percentage": 16.16, "elapsed_time": "0:24:26", "remaining_time": "2:06:48"}
+{"current_steps": 510, "total_steps": 3094, "loss": 0.4663555145263672, "lr": 9.646280700585185e-05, "epoch": 0.16484848484848486, "percentage": 16.48, "elapsed_time": "0:24:54", "remaining_time": "2:06:13"}
+{"current_steps": 520, "total_steps": 3094, "loss": 0.4879913330078125, "lr": 9.626270520732916e-05, "epoch": 0.16808080808080808, "percentage": 16.81, "elapsed_time": "0:25:22", "remaining_time": "2:05:36"}
+{"current_steps": 530, "total_steps": 3094, "loss": 0.48809428215026857, "lr": 9.605731740511022e-05, "epoch": 0.1713131313131313, "percentage": 17.13, "elapsed_time": "0:25:51", "remaining_time": "2:05:05"}
+{"current_steps": 540, "total_steps": 3094, "loss": 0.4959606170654297, "lr": 9.584666706692517e-05, "epoch": 0.17454545454545456, "percentage": 17.45, "elapsed_time": "0:26:20", "remaining_time": "2:04:33"}
+{"current_steps": 550, "total_steps": 3094, "loss": 0.4878594398498535, "lr": 9.56307782618046e-05, "epoch": 0.17777777777777778, "percentage": 17.78, "elapsed_time": "0:26:48", "remaining_time": "2:03:59"}
+{"current_steps": 560, "total_steps": 3094, "loss": 0.4769869804382324, "lr": 9.540967565732937e-05, "epoch": 0.181010101010101, "percentage": 18.1, "elapsed_time": "0:27:17", "remaining_time": "2:03:30"}
+{"current_steps": 570, "total_steps": 3094, "loss": 0.4970097064971924, "lr": 9.51833845168121e-05, "epoch": 0.18424242424242424, "percentage": 18.42, "elapsed_time": "0:27:45", "remaining_time": "2:02:53"}
+{"current_steps": 580, "total_steps": 3094, "loss": 0.4945381164550781, "lr": 9.495193069641057e-05, "epoch": 0.1874747474747475, "percentage": 18.75, "elapsed_time": "0:28:13", "remaining_time": "2:02:19"}
+{"current_steps": 590, "total_steps": 3094, "loss": 0.4860210418701172, "lr": 9.47153406421734e-05, "epoch": 0.1907070707070707, "percentage": 19.07, "elapsed_time": "0:28:41", "remaining_time": "2:01:47"}
+{"current_steps": 600, "total_steps": 3094, "loss": 0.4904911994934082, "lr": 9.447364138701823e-05, "epoch": 0.19393939393939394, "percentage": 19.39, "elapsed_time": "0:29:09", "remaining_time": "2:01:10"}
+{"current_steps": 610, "total_steps": 3094, "loss": 0.4915336608886719, "lr": 9.422686054764302e-05, "epoch": 0.19717171717171716, "percentage": 19.72, "elapsed_time": "0:29:46", "remaining_time": "2:01:15"}
+{"current_steps": 620, "total_steps": 3094, "loss": 0.4805011749267578, "lr": 9.397502632137055e-05, "epoch": 0.20040404040404042, "percentage": 20.04, "elapsed_time": "0:30:15", "remaining_time": "2:00:44"}
+{"current_steps": 630, "total_steps": 3094, "loss": 0.47633209228515627, "lr": 9.371816748292641e-05, "epoch": 0.20363636363636364, "percentage": 20.36, "elapsed_time": "0:30:43", "remaining_time": "2:00:11"}
+{"current_steps": 640, "total_steps": 3094, "loss": 0.48993511199951173, "lr": 9.345631338115141e-05, "epoch": 0.20686868686868687, "percentage": 20.69, "elapsed_time": "0:31:11", "remaining_time": "1:59:36"}
+{"current_steps": 650, "total_steps": 3094, "loss": 0.4798978328704834, "lr": 9.318949393564807e-05, "epoch": 0.2101010101010101, "percentage": 21.01, "elapsed_time": "0:31:40", "remaining_time": "1:59:04"}
+{"current_steps": 660, "total_steps": 3094, "loss": 0.4696659564971924, "lr": 9.291773963336193e-05, "epoch": 0.21333333333333335, "percentage": 21.33, "elapsed_time": "0:32:08", "remaining_time": "1:58:32"}
+{"current_steps": 670, "total_steps": 3094, "loss": 0.4955574035644531, "lr": 9.264108152509816e-05, "epoch": 0.21656565656565657, "percentage": 21.65, "elapsed_time": "0:32:35", "remaining_time": "1:57:55"}
+{"current_steps": 680, "total_steps": 3094, "loss": 0.48659563064575195, "lr": 9.235955122197368e-05, "epoch": 0.2197979797979798, "percentage": 21.98, "elapsed_time": "0:33:04", "remaining_time": "1:57:24"}
+{"current_steps": 690, "total_steps": 3094, "loss": 0.4766091823577881, "lr": 9.207318089180524e-05, "epoch": 0.22303030303030302, "percentage": 22.3, "elapsed_time": "0:33:32", "remaining_time": "1:56:51"}
+{"current_steps": 700, "total_steps": 3094, "loss": 0.5022068023681641, "lr": 9.178200325543384e-05, "epoch": 0.22626262626262628, "percentage": 22.62, "elapsed_time": "0:34:00", "remaining_time": "1:56:18"}
+{"current_steps": 710, "total_steps": 3094, "loss": 0.48309478759765623, "lr": 9.148605158298621e-05, "epoch": 0.2294949494949495, "percentage": 22.95, "elapsed_time": "0:34:28", "remaining_time": "1:55:44"}
+{"current_steps": 720, "total_steps": 3094, "loss": 0.4793684959411621, "lr": 9.118535969007314e-05, "epoch": 0.23272727272727273, "percentage": 23.27, "elapsed_time": "0:34:55", "remaining_time": "1:55:09"}
+{"current_steps": 730, "total_steps": 3094, "loss": 0.49844112396240237, "lr": 9.087996193392578e-05, "epoch": 0.23595959595959595, "percentage": 23.59, "elapsed_time": "0:35:23", "remaining_time": "1:54:37"}
+{"current_steps": 740, "total_steps": 3094, "loss": 0.48113102912902833, "lr": 9.056989320947e-05, "epoch": 0.2391919191919192, "percentage": 23.92, "elapsed_time": "0:35:51", "remaining_time": "1:54:03"}
+{"current_steps": 750, "total_steps": 3094, "loss": 0.5048784255981446, "lr": 9.025518894533921e-05, "epoch": 0.24242424242424243, "percentage": 24.24, "elapsed_time": "0:36:19", "remaining_time": "1:53:31"}
+{"current_steps": 760, "total_steps": 3094, "loss": 0.4862624168395996, "lr": 8.99358850998263e-05, "epoch": 0.24565656565656566, "percentage": 24.56, "elapsed_time": "0:36:47", "remaining_time": "1:53:00"}
+{"current_steps": 770, "total_steps": 3094, "loss": 0.48739056587219237, "lr": 8.9612018156775e-05, "epoch": 0.24888888888888888, "percentage": 24.89, "elapsed_time": "0:37:16", "remaining_time": "1:52:30"}
+{"current_steps": 780, "total_steps": 3094, "loss": 0.48689990043640136, "lr": 8.928362512141124e-05, "epoch": 0.25212121212121213, "percentage": 25.21, "elapsed_time": "0:37:44", "remaining_time": "1:51:58"}
+{"current_steps": 790, "total_steps": 3094, "loss": 0.4848791599273682, "lr": 8.895074351611488e-05, "epoch": 0.25535353535353533, "percentage": 25.53, "elapsed_time": "0:38:11", "remaining_time": "1:51:23"}
+{"current_steps": 800, "total_steps": 3094, "loss": 0.49130568504333494, "lr": 8.861341137613242e-05, "epoch": 0.2585858585858586, "percentage": 25.86, "elapsed_time": "0:38:40", "remaining_time": "1:50:53"}
+{"current_steps": 810, "total_steps": 3094, "loss": 0.49056081771850585, "lr": 8.827166724523105e-05, "epoch": 0.26181818181818184, "percentage": 26.18, "elapsed_time": "0:39:13", "remaining_time": "1:50:37"}
+{"current_steps": 820, "total_steps": 3094, "loss": 0.4706866264343262, "lr": 8.792555017129461e-05, "epoch": 0.26505050505050504, "percentage": 26.5, "elapsed_time": "0:39:42", "remaining_time": "1:50:06"}
+{"current_steps": 830, "total_steps": 3094, "loss": 0.48719348907470705, "lr": 8.757509970186196e-05, "epoch": 0.2682828282828283, "percentage": 26.83, "elapsed_time": "0:40:09", "remaining_time": "1:49:32"}
+{"current_steps": 840, "total_steps": 3094, "loss": 0.48200483322143556, "lr": 8.722035587960826e-05, "epoch": 0.27151515151515154, "percentage": 27.15, "elapsed_time": "0:40:38", "remaining_time": "1:49:03"}
+{"current_steps": 850, "total_steps": 3094, "loss": 0.48613176345825193, "lr": 8.686135923776969e-05, "epoch": 0.27474747474747474, "percentage": 27.47, "elapsed_time": "0:41:07", "remaining_time": "1:48:34"}
+{"current_steps": 860, "total_steps": 3094, "loss": 0.4976047515869141, "lr": 8.649815079551205e-05, "epoch": 0.277979797979798, "percentage": 27.8, "elapsed_time": "0:41:36", "remaining_time": "1:48:06"}
+{"current_steps": 870, "total_steps": 3094, "loss": 0.48451838493347166, "lr": 8.613077205324389e-05, "epoch": 0.2812121212121212, "percentage": 28.12, "elapsed_time": "0:42:04", "remaining_time": "1:47:34"}
+{"current_steps": 880, "total_steps": 3094, "loss": 0.5115366458892823, "lr": 8.575926498787476e-05, "epoch": 0.28444444444444444, "percentage": 28.44, "elapsed_time": "0:42:32", "remaining_time": "1:47:02"}
+{"current_steps": 890, "total_steps": 3094, "loss": 0.48187432289123533, "lr": 8.538367204801872e-05, "epoch": 0.2876767676767677, "percentage": 28.77, "elapsed_time": "0:43:01", "remaining_time": "1:46:32"}
+{"current_steps": 900, "total_steps": 3094, "loss": 0.4882505416870117, "lr": 8.500403614914432e-05, "epoch": 0.2909090909090909, "percentage": 29.09, "elapsed_time": "0:43:29", "remaining_time": "1:46:01"}
+{"current_steps": 910, "total_steps": 3094, "loss": 0.49068965911865237, "lr": 8.462040066867089e-05, "epoch": 0.29414141414141415, "percentage": 29.41, "elapsed_time": "0:43:58", "remaining_time": "1:45:32"}
+{"current_steps": 920, "total_steps": 3094, "loss": 0.4966132164001465, "lr": 8.423280944101233e-05, "epoch": 0.2973737373737374, "percentage": 29.73, "elapsed_time": "0:44:26", "remaining_time": "1:44:59"}
+{"current_steps": 930, "total_steps": 3094, "loss": 0.4754981994628906, "lr": 8.384130675256852e-05, "epoch": 0.3006060606060606, "percentage": 30.06, "elapsed_time": "0:44:53", "remaining_time": "1:44:27"}
+{"current_steps": 940, "total_steps": 3094, "loss": 0.4735103130340576, "lr": 8.34459373366651e-05, "epoch": 0.30383838383838385, "percentage": 30.38, "elapsed_time": "0:45:21", "remaining_time": "1:43:55"}
+{"current_steps": 950, "total_steps": 3094, "loss": 0.4809592247009277, "lr": 8.304674636844231e-05, "epoch": 0.30707070707070705, "percentage": 30.7, "elapsed_time": "0:45:49", "remaining_time": "1:43:25"}
+{"current_steps": 960, "total_steps": 3094, "loss": 0.48206100463867185, "lr": 8.264377945969312e-05, "epoch": 0.3103030303030303, "percentage": 31.03, "elapsed_time": "0:46:17", "remaining_time": "1:42:54"}
+{"current_steps": 970, "total_steps": 3094, "loss": 0.48718748092651365, "lr": 8.223708265365174e-05, "epoch": 0.31353535353535356, "percentage": 31.35, "elapsed_time": "0:46:45", "remaining_time": "1:42:23"}
+{"current_steps": 980, "total_steps": 3094, "loss": 0.4952278137207031, "lr": 8.182670241973253e-05, "epoch": 0.31676767676767675, "percentage": 31.67, "elapsed_time": "0:47:13", "remaining_time": "1:41:51"}
+{"current_steps": 990, "total_steps": 3094, "loss": 0.47769975662231445, "lr": 8.141268564822053e-05, "epoch": 0.32, "percentage": 32.0, "elapsed_time": "0:47:40", "remaining_time": "1:41:19"}
+{"current_steps": 1000, "total_steps": 3094, "loss": 0.4862718105316162, "lr": 8.099507964491369e-05, "epoch": 0.32323232323232326, "percentage": 32.32, "elapsed_time": "0:48:08", "remaining_time": "1:40:49"}
+{"current_steps": 1010, "total_steps": 3094, "loss": 0.49833106994628906, "lr": 8.057393212571767e-05, "epoch": 0.32646464646464646, "percentage": 32.64, "elapsed_time": "0:48:42", "remaining_time": "1:40:31"}
+{"current_steps": 1020, "total_steps": 3094, "loss": 0.48829941749572753, "lr": 8.014929121119378e-05, "epoch": 0.3296969696969697, "percentage": 32.97, "elapsed_time": "0:49:11", "remaining_time": "1:40:00"}
+{"current_steps": 1030, "total_steps": 3094, "loss": 0.46506147384643554, "lr": 7.972120542106077e-05, "epoch": 0.3329292929292929, "percentage": 33.29, "elapsed_time": "0:49:39", "remaining_time": "1:39:31"}
+{"current_steps": 1040, "total_steps": 3094, "loss": 0.47866268157958985, "lr": 7.92897236686508e-05, "epoch": 0.33616161616161616, "percentage": 33.61, "elapsed_time": "0:50:07", "remaining_time": "1:38:59"}
+{"current_steps": 1050, "total_steps": 3094, "loss": 0.4966601371765137, "lr": 7.885489525532075e-05, "epoch": 0.3393939393939394, "percentage": 33.94, "elapsed_time": "0:50:35", "remaining_time": "1:38:29"}
+{"current_steps": 1060, "total_steps": 3094, "loss": 0.49251084327697753, "lr": 7.84167698648189e-05, "epoch": 0.3426262626262626, "percentage": 34.26, "elapsed_time": "0:51:04", "remaining_time": "1:37:59"}
+{"current_steps": 1070, "total_steps": 3094, "loss": 0.4816086769104004, "lr": 7.797539755760805e-05, "epoch": 0.34585858585858587, "percentage": 34.58, "elapsed_time": "0:51:32", "remaining_time": "1:37:29"}
+{"current_steps": 1080, "total_steps": 3094, "loss": 0.47102947235107423, "lr": 7.753082876514562e-05, "epoch": 0.3490909090909091, "percentage": 34.91, "elapsed_time": "0:52:00", "remaining_time": "1:36:59"}
+{"current_steps": 1090, "total_steps": 3094, "loss": 0.4810478210449219, "lr": 7.708311428412129e-05, "epoch": 0.3523232323232323, "percentage": 35.23, "elapsed_time": "0:52:29", "remaining_time": "1:36:30"}
+{"current_steps": 1100, "total_steps": 3094, "loss": 0.47051143646240234, "lr": 7.663230527065293e-05, "epoch": 0.35555555555555557, "percentage": 35.55, "elapsed_time": "0:52:57", "remaining_time": "1:35:59"}
+{"current_steps": 1110, "total_steps": 3094, "loss": 0.4780744552612305, "lr": 7.617845323444156e-05, "epoch": 0.35878787878787877, "percentage": 35.88, "elapsed_time": "0:53:24", "remaining_time": "1:35:28"}
+{"current_steps": 1120, "total_steps": 3094, "loss": 0.4804032325744629, "lr": 7.572161003288565e-05, "epoch": 0.362020202020202, "percentage": 36.2, "elapsed_time": "0:53:53", "remaining_time": "1:34:58"}
+{"current_steps": 1130, "total_steps": 3094, "loss": 0.48206367492675783, "lr": 7.526182786515609e-05, "epoch": 0.3652525252525253, "percentage": 36.52, "elapsed_time": "0:54:21", "remaining_time": "1:34:27"}
+{"current_steps": 1140, "total_steps": 3094, "loss": 0.49240264892578123, "lr": 7.479915926623165e-05, "epoch": 0.36848484848484847, "percentage": 36.85, "elapsed_time": "0:54:48", "remaining_time": "1:33:57"}
+{"current_steps": 1150, "total_steps": 3094, "loss": 0.48599681854248045, "lr": 7.433365710089646e-05, "epoch": 0.3717171717171717, "percentage": 37.17, "elapsed_time": "0:55:16", "remaining_time": "1:33:26"}
+{"current_steps": 1160, "total_steps": 3094, "loss": 0.4688436031341553, "lr": 7.386537455769963e-05, "epoch": 0.374949494949495, "percentage": 37.49, "elapsed_time": "0:55:46", "remaining_time": "1:32:58"}
+{"current_steps": 1170, "total_steps": 3094, "loss": 0.47986507415771484, "lr": 7.339436514287783e-05, "epoch": 0.3781818181818182, "percentage": 37.82, "elapsed_time": "0:56:13", "remaining_time": "1:32:28"}
+{"current_steps": 1180, "total_steps": 3094, "loss": 0.4771553993225098, "lr": 7.292068267424165e-05, "epoch": 0.3814141414141414, "percentage": 38.14, "elapsed_time": "0:56:41", "remaining_time": "1:31:57"}
+{"current_steps": 1190, "total_steps": 3094, "loss": 0.4854436874389648, "lr": 7.244438127502647e-05, "epoch": 0.3846464646464646, "percentage": 38.46, "elapsed_time": "0:57:10", "remaining_time": "1:31:28"}
+{"current_steps": 1200, "total_steps": 3094, "loss": 0.4763533592224121, "lr": 7.196551536770807e-05, "epoch": 0.3878787878787879, "percentage": 38.78, "elapsed_time": "0:57:39", "remaining_time": "1:31:00"}
+{"current_steps": 1210, "total_steps": 3094, "loss": 0.47457141876220704, "lr": 7.148413966778451e-05, "epoch": 0.39111111111111113, "percentage": 39.11, "elapsed_time": "0:58:16", "remaining_time": "1:30:43"}
+{"current_steps": 1220, "total_steps": 3094, "loss": 0.4732469081878662, "lr": 7.100030917752423e-05, "epoch": 0.39434343434343433, "percentage": 39.43, "elapsed_time": "0:58:44", "remaining_time": "1:30:13"}
+{"current_steps": 1230, "total_steps": 3094, "loss": 0.47551660537719725, "lr": 7.051407917968138e-05, "epoch": 0.3975757575757576, "percentage": 39.75, "elapsed_time": "0:59:11", "remaining_time": "1:29:42"}
+{"current_steps": 1240, "total_steps": 3094, "loss": 0.4835049629211426, "lr": 7.002550523117926e-05, "epoch": 0.40080808080808084, "percentage": 40.08, "elapsed_time": "0:59:39", "remaining_time": "1:29:12"}
+{"current_steps": 1250, "total_steps": 3094, "loss": 0.4909071922302246, "lr": 6.953464315676241e-05, "epoch": 0.40404040404040403, "percentage": 40.4, "elapsed_time": "1:00:07", "remaining_time": "1:28:42"}
+{"current_steps": 1260, "total_steps": 3094, "loss": 0.4842695236206055, "lr": 6.904154904261792e-05, "epoch": 0.4072727272727273, "percentage": 40.72, "elapsed_time": "1:00:36", "remaining_time": "1:28:12"}
+{"current_steps": 1270, "total_steps": 3094, "loss": 0.48967390060424804, "lr": 6.8546279229967e-05, "epoch": 0.4105050505050505, "percentage": 41.05, "elapsed_time": "1:01:03", "remaining_time": "1:27:41"}
+{"current_steps": 1280, "total_steps": 3094, "loss": 0.48658218383789065, "lr": 6.804889030862753e-05, "epoch": 0.41373737373737374, "percentage": 41.37, "elapsed_time": "1:01:31", "remaining_time": "1:27:12"}
+{"current_steps": 1290, "total_steps": 3094, "loss": 0.48893008232116697, "lr": 6.754943911054793e-05, "epoch": 0.416969696969697, "percentage": 41.69, "elapsed_time": "1:01:59", "remaining_time": "1:26:42"}
+{"current_steps": 1300, "total_steps": 3094, "loss": 0.49384117126464844, "lr": 6.704798270331358e-05, "epoch": 0.4202020202020202, "percentage": 42.02, "elapsed_time": "1:02:27", "remaining_time": "1:26:11"}
+{"current_steps": 1310, "total_steps": 3094, "loss": 0.47458324432373045, "lr": 6.654457838362621e-05, "epoch": 0.42343434343434344, "percentage": 42.34, "elapsed_time": "1:02:55", "remaining_time": "1:25:41"}
+{"current_steps": 1320, "total_steps": 3094, "loss": 0.4703402519226074, "lr": 6.603928367075718e-05, "epoch": 0.4266666666666667, "percentage": 42.66, "elapsed_time": "1:03:23", "remaining_time": "1:25:11"}
+{"current_steps": 1330, "total_steps": 3094, "loss": 0.4851715087890625, "lr": 6.553215629997529e-05, "epoch": 0.4298989898989899, "percentage": 42.99, "elapsed_time": "1:03:52", "remaining_time": "1:24:42"}
+{"current_steps": 1340, "total_steps": 3094, "loss": 0.4779622554779053, "lr": 6.502325421594988e-05, "epoch": 0.43313131313131314, "percentage": 43.31, "elapsed_time": "1:04:19", "remaining_time": "1:24:12"}
+{"current_steps": 1350, "total_steps": 3094, "loss": 0.4708548545837402, "lr": 6.451263556613007e-05, "epoch": 0.43636363636363634, "percentage": 43.63, "elapsed_time": "1:04:47", "remaining_time": "1:23:42"}
+{"current_steps": 1360, "total_steps": 3094, "loss": 0.4721970558166504, "lr": 6.40003586941008e-05, "epoch": 0.4395959595959596, "percentage": 43.96, "elapsed_time": "1:05:16", "remaining_time": "1:23:13"}
+{"current_steps": 1370, "total_steps": 3094, "loss": 0.4798272132873535, "lr": 6.348648213291642e-05, "epoch": 0.44282828282828285, "percentage": 44.28, "elapsed_time": "1:05:44", "remaining_time": "1:22:43"}
+{"current_steps": 1380, "total_steps": 3094, "loss": 0.471483039855957, "lr": 6.297106459841272e-05, "epoch": 0.44606060606060605, "percentage": 44.6, "elapsed_time": "1:06:12", "remaining_time": "1:22:13"}
+{"current_steps": 1390, "total_steps": 3094, "loss": 0.4772329330444336, "lr": 6.245416498249801e-05, "epoch": 0.4492929292929293, "percentage": 44.93, "elapsed_time": "1:06:39", "remaining_time": "1:21:43"}
+{"current_steps": 1400, "total_steps": 3094, "loss": 0.48812179565429686, "lr": 6.193584234642403e-05, "epoch": 0.45252525252525255, "percentage": 45.25, "elapsed_time": "1:07:07", "remaining_time": "1:21:13"}
+{"current_steps": 1410, "total_steps": 3094, "loss": 0.48897976875305177, "lr": 6.141615591403771e-05, "epoch": 0.45575757575757575, "percentage": 45.57, "elapsed_time": "1:07:46", "remaining_time": "1:20:57"}
+{"current_steps": 1420, "total_steps": 3094, "loss": 0.4850447654724121, "lr": 6.0895165065014106e-05, "epoch": 0.458989898989899, "percentage": 45.9, "elapsed_time": "1:08:14", "remaining_time": "1:20:26"}
+{"current_steps": 1430, "total_steps": 3094, "loss": 0.4857158660888672, "lr": 6.037292932807167e-05, "epoch": 0.4622222222222222, "percentage": 46.22, "elapsed_time": "1:08:42", "remaining_time": "1:19:57"}
+{"current_steps": 1440, "total_steps": 3094, "loss": 0.4844364166259766, "lr": 5.984950837417048e-05, "epoch": 0.46545454545454545, "percentage": 46.54, "elapsed_time": "1:09:10", "remaining_time": "1:19:27"}
+{"current_steps": 1450, "total_steps": 3094, "loss": 0.47542514801025393, "lr": 5.932496200969422e-05, "epoch": 0.4686868686868687, "percentage": 46.86, "elapsed_time": "1:09:38", "remaining_time": "1:18:57"}
+{"current_steps": 1460, "total_steps": 3094, "loss": 0.48579182624816897, "lr": 5.879935016961661e-05, "epoch": 0.4719191919191919, "percentage": 47.19, "elapsed_time": "1:10:05", "remaining_time": "1:18:27"}
+{"current_steps": 1470, "total_steps": 3094, "loss": 0.48273677825927735, "lr": 5.827273291065326e-05, "epoch": 0.47515151515151516, "percentage": 47.51, "elapsed_time": "1:10:33", "remaining_time": "1:17:57"}
+{"current_steps": 1480, "total_steps": 3094, "loss": 0.46429009437561036, "lr": 5.7745170404399484e-05, "epoch": 0.4783838383838384, "percentage": 47.83, "elapsed_time": "1:11:01", "remaining_time": "1:17:27"}
+{"current_steps": 1490, "total_steps": 3094, "loss": 0.49172677993774416, "lr": 5.721672293045518e-05, "epoch": 0.4816161616161616, "percentage": 48.16, "elapsed_time": "1:11:29", "remaining_time": "1:16:57"}
+{"current_steps": 1500, "total_steps": 3094, "loss": 0.4934688568115234, "lr": 5.668745086953712e-05, "epoch": 0.48484848484848486, "percentage": 48.48, "elapsed_time": "1:11:56", "remaining_time": "1:16:27"}
+{"current_steps": 1510, "total_steps": 3094, "loss": 0.4826413631439209, "lr": 5.615741469657985e-05, "epoch": 0.48808080808080806, "percentage": 48.8, "elapsed_time": "1:12:24", "remaining_time": "1:15:57"}
+{"current_steps": 1520, "total_steps": 3094, "loss": 0.48468503952026365, "lr": 5.562667497382582e-05, "epoch": 0.4913131313131313, "percentage": 49.13, "elapsed_time": "1:12:52", "remaining_time": "1:15:27"}
+{"current_steps": 1530, "total_steps": 3094, "loss": 0.47773942947387693, "lr": 5.509529234390553e-05, "epoch": 0.49454545454545457, "percentage": 49.45, "elapsed_time": "1:13:19", "remaining_time": "1:14:57"}
+{"current_steps": 1540, "total_steps": 3094, "loss": 0.47507562637329104, "lr": 5.456332752290837e-05, "epoch": 0.49777777777777776, "percentage": 49.77, "elapsed_time": "1:13:48", "remaining_time": "1:14:28"}
+{"current_steps": 1550, "total_steps": 3094, "loss": 0.486495304107666, "lr": 5.4030841293445244e-05, "epoch": 0.501010101010101, "percentage": 50.1, "elapsed_time": "1:14:16", "remaining_time": "1:13:58"}
+{"current_steps": 1560, "total_steps": 3094, "loss": 0.48320484161376953, "lr": 5.349789449770351e-05, "epoch": 0.5042424242424243, "percentage": 50.42, "elapsed_time": "1:14:44", "remaining_time": "1:13:29"}
+{"current_steps": 1570, "total_steps": 3094, "loss": 0.48847188949584963, "lr": 5.2964548030495065e-05, "epoch": 0.5074747474747475, "percentage": 50.74, "elapsed_time": "1:15:12", "remaining_time": "1:12:59"}
+{"current_steps": 1580, "total_steps": 3094, "loss": 0.47591514587402345, "lr": 5.243086283229852e-05, "epoch": 0.5107070707070707, "percentage": 51.07, "elapsed_time": "1:15:40", "remaining_time": "1:12:30"}
+{"current_steps": 1590, "total_steps": 3094, "loss": 0.48136124610900877, "lr": 5.18968998822961e-05, "epoch": 0.5139393939393939, "percentage": 51.39, "elapsed_time": "1:16:08", "remaining_time": "1:12:01"}
+{"current_steps": 1600, "total_steps": 3094, "loss": 0.48076438903808594, "lr": 5.1362720191406065e-05, "epoch": 0.5171717171717172, "percentage": 51.71, "elapsed_time": "1:16:35", "remaining_time": "1:11:31"}
+{"current_steps": 1610, "total_steps": 3094, "loss": 0.5004307270050049, "lr": 5.082838479531169e-05, "epoch": 0.5204040404040404, "percentage": 52.04, "elapsed_time": "1:17:10", "remaining_time": "1:11:07"}
+{"current_steps": 1620, "total_steps": 3094, "loss": 0.4812767028808594, "lr": 5.029395474748714e-05, "epoch": 0.5236363636363637, "percentage": 52.36, "elapsed_time": "1:17:37", "remaining_time": "1:10:38"}
+{"current_steps": 1630, "total_steps": 3094, "loss": 0.4887521743774414, "lr": 4.975949111222158e-05, "epoch": 0.5268686868686868, "percentage": 52.68, "elapsed_time": "1:18:05", "remaining_time": "1:10:08"}
+{"current_steps": 1640, "total_steps": 3094, "loss": 0.48248910903930664, "lr": 4.9225054957641916e-05, "epoch": 0.5301010101010101, "percentage": 53.01, "elapsed_time": "1:18:34", "remaining_time": "1:09:39"}
+{"current_steps": 1650, "total_steps": 3094, "loss": 0.4855649948120117, "lr": 4.8690707348735035e-05, "epoch": 0.5333333333333333, "percentage": 53.33, "elapsed_time": "1:19:02", "remaining_time": "1:09:10"}
+{"current_steps": 1660, "total_steps": 3094, "loss": 0.47187280654907227, "lr": 4.8156509340370605e-05, "epoch": 0.5365656565656566, "percentage": 53.65, "elapsed_time": "1:19:31", "remaining_time": "1:08:41"}
+{"current_steps": 1670, "total_steps": 3094, "loss": 0.46579513549804685, "lr": 4.762252197032482e-05, "epoch": 0.5397979797979798, "percentage": 53.98, "elapsed_time": "1:19:59", "remaining_time": "1:08:12"}
+{"current_steps": 1680, "total_steps": 3094, "loss": 0.47946829795837403, "lr": 4.7088806252306224e-05, "epoch": 0.5430303030303031, "percentage": 54.3, "elapsed_time": "1:20:27", "remaining_time": "1:07:43"}
+{"current_steps": 1690, "total_steps": 3094, "loss": 0.4593667030334473, "lr": 4.655542316898423e-05, "epoch": 0.5462626262626262, "percentage": 54.62, "elapsed_time": "1:20:57", "remaining_time": "1:07:15"}
+{"current_steps": 1700, "total_steps": 3094, "loss": 0.48582897186279295, "lr": 4.6022433665021246e-05, "epoch": 0.5494949494949495, "percentage": 54.95, "elapsed_time": "1:21:26", "remaining_time": "1:06:46"}
+{"current_steps": 1710, "total_steps": 3094, "loss": 0.4849580764770508, "lr": 4.548989864010902e-05, "epoch": 0.5527272727272727, "percentage": 55.27, "elapsed_time": "1:21:55", "remaining_time": "1:06:18"}
+{"current_steps": 1720, "total_steps": 3094, "loss": 0.49089298248291013, "lr": 4.495787894201031e-05, "epoch": 0.555959595959596, "percentage": 55.59, "elapsed_time": "1:22:23", "remaining_time": "1:05:48"}
+{"current_steps": 1730, "total_steps": 3094, "loss": 0.48010549545288084, "lr": 4.442643535960631e-05, "epoch": 0.5591919191919192, "percentage": 55.91, "elapsed_time": "1:22:50", "remaining_time": "1:05:19"}
+{"current_steps": 1740, "total_steps": 3094, "loss": 0.47594566345214845, "lr": 4.3895628615950864e-05, "epoch": 0.5624242424242424, "percentage": 56.24, "elapsed_time": "1:23:19", "remaining_time": "1:04:50"}
+{"current_steps": 1750, "total_steps": 3094, "loss": 0.48056421279907224, "lr": 4.3365519361332345e-05, "epoch": 0.5656565656565656, "percentage": 56.56, "elapsed_time": "1:23:47", "remaining_time": "1:04:21"}
+{"current_steps": 1760, "total_steps": 3094, "loss": 0.47501134872436523, "lr": 4.283616816634353e-05, "epoch": 0.5688888888888889, "percentage": 56.88, "elapsed_time": "1:24:15", "remaining_time": "1:03:52"}
+{"current_steps": 1770, "total_steps": 3094, "loss": 0.478366756439209, "lr": 4.230763551496089e-05, "epoch": 0.5721212121212121, "percentage": 57.21, "elapsed_time": "1:24:43", "remaining_time": "1:03:22"}
+{"current_steps": 1780, "total_steps": 3094, "loss": 0.478058385848999, "lr": 4.1779981797633645e-05, "epoch": 0.5753535353535354, "percentage": 57.53, "elapsed_time": "1:25:11", "remaining_time": "1:02:53"}
+{"current_steps": 1790, "total_steps": 3094, "loss": 0.48466057777404786, "lr": 4.1253267304383455e-05, "epoch": 0.5785858585858585, "percentage": 57.85, "elapsed_time": "1:25:39", "remaining_time": "1:02:23"}
+{"current_steps": 1800, "total_steps": 3094, "loss": 0.4769908905029297, "lr": 4.072755221791572e-05, "epoch": 0.5818181818181818, "percentage": 58.18, "elapsed_time": "1:26:07", "remaining_time": "1:01:54"}
+{"current_steps": 1810, "total_steps": 3094, "loss": 0.47162666320800783, "lr": 4.020289660674306e-05, "epoch": 0.585050505050505, "percentage": 58.5, "elapsed_time": "1:26:46", "remaining_time": "1:01:33"}
+{"current_steps": 1820, "total_steps": 3094, "loss": 0.46282405853271485, "lr": 3.967936041832173e-05, "epoch": 0.5882828282828283, "percentage": 58.82, "elapsed_time": "1:27:15", "remaining_time": "1:01:04"}
+{"current_steps": 1830, "total_steps": 3094, "loss": 0.4794480323791504, "lr": 3.9157003472202246e-05, "epoch": 0.5915151515151515, "percentage": 59.15, "elapsed_time": "1:27:42", "remaining_time": "1:00:35"}
+{"current_steps": 1840, "total_steps": 3094, "loss": 0.4729412078857422, "lr": 3.863588545319407e-05, "epoch": 0.5947474747474748, "percentage": 59.47, "elapsed_time": "1:28:11", "remaining_time": "1:00:06"}
+{"current_steps": 1850, "total_steps": 3094, "loss": 0.47380704879760743, "lr": 3.8116065904546196e-05, "epoch": 0.597979797979798, "percentage": 59.79, "elapsed_time": "1:28:40", "remaining_time": "0:59:37"}
+{"current_steps": 1860, "total_steps": 3094, "loss": 0.47751388549804685, "lr": 3.759760422114362e-05, "epoch": 0.6012121212121212, "percentage": 60.12, "elapsed_time": "1:29:08", "remaining_time": "0:59:08"}
+{"current_steps": 1870, "total_steps": 3094, "loss": 0.47801823616027833, "lr": 3.708055964272088e-05, "epoch": 0.6044444444444445, "percentage": 60.44, "elapsed_time": "1:29:36", "remaining_time": "0:58:39"}
+{"current_steps": 1880, "total_steps": 3094, "loss": 0.4800426483154297, "lr": 3.6564991247093234e-05, "epoch": 0.6076767676767677, "percentage": 60.76, "elapsed_time": "1:30:05", "remaining_time": "0:58:10"}
+{"current_steps": 1890, "total_steps": 3094, "loss": 0.4812753677368164, "lr": 3.6050957943406465e-05, "epoch": 0.610909090909091, "percentage": 61.09, "elapsed_time": "1:30:33", "remaining_time": "0:57:41"}
+{"current_steps": 1900, "total_steps": 3094, "loss": 0.47804956436157225, "lr": 3.553851846540584e-05, "epoch": 0.6141414141414141, "percentage": 61.41, "elapsed_time": "1:31:01", "remaining_time": "0:57:11"}
+{"current_steps": 1910, "total_steps": 3094, "loss": 0.4772273063659668, "lr": 3.50277313647252e-05, "epoch": 0.6173737373737374, "percentage": 61.73, "elapsed_time": "1:31:29", "remaining_time": "0:56:42"}
+{"current_steps": 1920, "total_steps": 3094, "loss": 0.4892144203186035, "lr": 3.451865500419676e-05, "epoch": 0.6206060606060606, "percentage": 62.06, "elapsed_time": "1:31:57", "remaining_time": "0:56:13"}
+{"current_steps": 1930, "total_steps": 3094, "loss": 0.48959059715270997, "lr": 3.401134755118256e-05, "epoch": 0.6238383838383839, "percentage": 62.38, "elapsed_time": "1:32:26", "remaining_time": "0:55:44"}
+{"current_steps": 1940, "total_steps": 3094, "loss": 0.46478729248046874, "lr": 3.350586697092826e-05, "epoch": 0.6270707070707071, "percentage": 62.7, "elapsed_time": "1:32:54", "remaining_time": "0:55:16"}
+{"current_steps": 1950, "total_steps": 3094, "loss": 0.5046152114868164, "lr": 3.300227101993998e-05, "epoch": 0.6303030303030303, "percentage": 63.03, "elapsed_time": "1:33:23", "remaining_time": "0:54:47"}
+{"current_steps": 1960, "total_steps": 3094, "loss": 0.4698008060455322, "lr": 3.2500617239384947e-05, "epoch": 0.6335353535353535, "percentage": 63.35, "elapsed_time": "1:33:51", "remaining_time": "0:54:18"}
+{"current_steps": 1970, "total_steps": 3094, "loss": 0.4716217041015625, "lr": 3.200096294851691e-05, "epoch": 0.6367676767676768, "percentage": 63.67, "elapsed_time": "1:34:20", "remaining_time": "0:53:49"}
+{"current_steps": 1980, "total_steps": 3094, "loss": 0.47135162353515625, "lr": 3.150336523812674e-05, "epoch": 0.64, "percentage": 63.99, "elapsed_time": "1:34:49", "remaining_time": "0:53:21"}
+{"current_steps": 1990, "total_steps": 3094, "loss": 0.4799614906311035, "lr": 3.100788096401925e-05, "epoch": 0.6432323232323233, "percentage": 64.32, "elapsed_time": "1:35:18", "remaining_time": "0:52:52"}
+{"current_steps": 2000, "total_steps": 3094, "loss": 0.4682164192199707, "lr": 3.051456674051677e-05, "epoch": 0.6464646464646465, "percentage": 64.64, "elapsed_time": "1:35:46", "remaining_time": "0:52:23"}
+{"current_steps": 2010, "total_steps": 3094, "loss": 0.4750208854675293, "lr": 3.0023478933990347e-05, "epoch": 0.6496969696969697, "percentage": 64.96, "elapsed_time": "1:36:20", "remaining_time": "0:51:57"}
+{"current_steps": 2020, "total_steps": 3094, "loss": 0.48034076690673827, "lr": 2.9534673656419377e-05, "epoch": 0.6529292929292929, "percentage": 65.29, "elapsed_time": "1:36:49", "remaining_time": "0:51:28"}
+{"current_steps": 2030, "total_steps": 3094, "loss": 0.46314101219177245, "lr": 2.9048206758980136e-05, "epoch": 0.6561616161616162, "percentage": 65.61, "elapsed_time": "1:37:17", "remaining_time": "0:50:59"}
+{"current_steps": 2040, "total_steps": 3094, "loss": 0.4783937454223633, "lr": 2.856413382566425e-05, "epoch": 0.6593939393939394, "percentage": 65.93, "elapsed_time": "1:37:45", "remaining_time": "0:50:30"}
+{"current_steps": 2050, "total_steps": 3094, "loss": 0.4792025089263916, "lr": 2.8082510166927583e-05, "epoch": 0.6626262626262627, "percentage": 66.26, "elapsed_time": "1:38:12", "remaining_time": "0:50:01"}
+{"current_steps": 2060, "total_steps": 3094, "loss": 0.4722686767578125, "lr": 2.760339081337041e-05, "epoch": 0.6658585858585858, "percentage": 66.58, "elapsed_time": "1:38:41", "remaining_time": "0:49:32"}
+{"current_steps": 2070, "total_steps": 3094, "loss": 0.4884464263916016, "lr": 2.7126830509449773e-05, "epoch": 0.6690909090909091, "percentage": 66.9, "elapsed_time": "1:39:09", "remaining_time": "0:49:03"}
+{"current_steps": 2080, "total_steps": 3094, "loss": 0.4804549217224121, "lr": 2.6652883707224075e-05, "epoch": 0.6723232323232323, "percentage": 67.23, "elapsed_time": "1:39:38", "remaining_time": "0:48:34"}
+{"current_steps": 2090, "total_steps": 3094, "loss": 0.4781071186065674, "lr": 2.618160456013153e-05, "epoch": 0.6755555555555556, "percentage": 67.55, "elapsed_time": "1:40:06", "remaining_time": "0:48:05"}
+{"current_steps": 2100, "total_steps": 3094, "loss": 0.48059587478637694, "lr": 2.571304691680255e-05, "epoch": 0.6787878787878788, "percentage": 67.87, "elapsed_time": "1:40:34", "remaining_time": "0:47:36"}
+{"current_steps": 2110, "total_steps": 3094, "loss": 0.4706240177154541, "lr": 2.5247264314906917e-05, "epoch": 0.682020202020202, "percentage": 68.2, "elapsed_time": "1:41:01", "remaining_time": "0:47:06"}
+{"current_steps": 2120, "total_steps": 3094, "loss": 0.4885101318359375, "lr": 2.4784309975036513e-05, "epoch": 0.6852525252525252, "percentage": 68.52, "elapsed_time": "1:41:29", "remaining_time": "0:46:37"}
+{"current_steps": 2130, "total_steps": 3094, "loss": 0.4882383346557617, "lr": 2.4324236794624456e-05, "epoch": 0.6884848484848485, "percentage": 68.84, "elapsed_time": "1:41:57", "remaining_time": "0:46:08"}
+{"current_steps": 2140, "total_steps": 3094, "loss": 0.4768857479095459, "lr": 2.386709734190079e-05, "epoch": 0.6917171717171717, "percentage": 69.17, "elapsed_time": "1:42:26", "remaining_time": "0:45:40"}
+{"current_steps": 2150, "total_steps": 3094, "loss": 0.4802837371826172, "lr": 2.34129438498862e-05, "epoch": 0.694949494949495, "percentage": 69.49, "elapsed_time": "1:42:54", "remaining_time": "0:45:10"}
+{"current_steps": 2160, "total_steps": 3094, "loss": 0.4874839782714844, "lr": 2.296182821042374e-05, "epoch": 0.6981818181818182, "percentage": 69.81, "elapsed_time": "1:43:23", "remaining_time": "0:44:42"}
+{"current_steps": 2170, "total_steps": 3094, "loss": 0.4758561134338379, "lr": 2.2513801968249644e-05, "epoch": 0.7014141414141414, "percentage": 70.14, "elapsed_time": "1:43:51", "remaining_time": "0:44:13"}
+{"current_steps": 2180, "total_steps": 3094, "loss": 0.4686488151550293, "lr": 2.2068916315103783e-05, "epoch": 0.7046464646464646, "percentage": 70.46, "elapsed_time": "1:44:20", "remaining_time": "0:43:44"}
+{"current_steps": 2190, "total_steps": 3094, "loss": 0.4782154083251953, "lr": 2.162722208388057e-05, "epoch": 0.7078787878787879, "percentage": 70.78, "elapsed_time": "1:44:48", "remaining_time": "0:43:15"}
+{"current_steps": 2200, "total_steps": 3094, "loss": 0.4773773193359375, "lr": 2.1188769742820625e-05, "epoch": 0.7111111111111111, "percentage": 71.11, "elapsed_time": "1:45:16", "remaining_time": "0:42:46"}
+{"current_steps": 2210, "total_steps": 3094, "loss": 0.4733907222747803, "lr": 2.075360938974429e-05, "epoch": 0.7143434343434344, "percentage": 71.43, "elapsed_time": "1:45:54", "remaining_time": "0:42:21"}
+{"current_steps": 2220, "total_steps": 3094, "loss": 0.47564210891723635, "lr": 2.03217907463275e-05, "epoch": 0.7175757575757575, "percentage": 71.75, "elapsed_time": "1:46:23", "remaining_time": "0:41:53"}
+{"current_steps": 2230, "total_steps": 3094, "loss": 0.4784512519836426, "lr": 1.989336315242048e-05, "epoch": 0.7208080808080808, "percentage": 72.07, "elapsed_time": "1:46:51", "remaining_time": "0:41:23"}
+{"current_steps": 2240, "total_steps": 3094, "loss": 0.4808964729309082, "lr": 1.9468375560410117e-05, "epoch": 0.724040404040404, "percentage": 72.4, "elapsed_time": "1:47:19", "remaining_time": "0:40:55"}
+{"current_steps": 2250, "total_steps": 3094, "loss": 0.49031834602355956, "lr": 1.90468765296267e-05, "epoch": 0.7272727272727273, "percentage": 72.72, "elapsed_time": "1:47:47", "remaining_time": "0:40:26"}
+{"current_steps": 2260, "total_steps": 3094, "loss": 0.48055601119995117, "lr": 1.8628914220795494e-05, "epoch": 0.7305050505050505, "percentage": 73.04, "elapsed_time": "1:48:14", "remaining_time": "0:39:56"}
+{"current_steps": 2270, "total_steps": 3094, "loss": 0.47170586585998536, "lr": 1.8214536390533822e-05, "epoch": 0.7337373737373737, "percentage": 73.37, "elapsed_time": "1:48:43", "remaining_time": "0:39:28"}
+{"current_steps": 2280, "total_steps": 3094, "loss": 0.4660043716430664, "lr": 1.7803790385894387e-05, "epoch": 0.7369696969696969, "percentage": 73.69, "elapsed_time": "1:49:12", "remaining_time": "0:38:59"}
+{"current_steps": 2290, "total_steps": 3094, "loss": 0.4599196434020996, "lr": 1.7396723138955428e-05, "epoch": 0.7402020202020202, "percentage": 74.01, "elapsed_time": "1:49:41", "remaining_time": "0:38:30"}
+{"current_steps": 2300, "total_steps": 3094, "loss": 0.46491589546203616, "lr": 1.699338116145811e-05, "epoch": 0.7434343434343434, "percentage": 74.34, "elapsed_time": "1:50:09", "remaining_time": "0:38:01"}
+{"current_steps": 2310, "total_steps": 3094, "loss": 0.47761125564575196, "lr": 1.6593810539492195e-05, "epoch": 0.7466666666666667, "percentage": 74.66, "elapsed_time": "1:50:37", "remaining_time": "0:37:32"}
+{"current_steps": 2320, "total_steps": 3094, "loss": 0.49956817626953126, "lr": 1.619805692823016e-05, "epoch": 0.74989898989899, "percentage": 74.98, "elapsed_time": "1:51:05", "remaining_time": "0:37:03"}
+{"current_steps": 2330, "total_steps": 3094, "loss": 0.4716916084289551, "lr": 1.580616554671057e-05, "epoch": 0.7531313131313131, "percentage": 75.31, "elapsed_time": "1:51:35", "remaining_time": "0:36:35"}
+{"current_steps": 2340, "total_steps": 3094, "loss": 0.4909040451049805, "lr": 1.5418181172671382e-05, "epoch": 0.7563636363636363, "percentage": 75.63, "elapsed_time": "1:52:03", "remaining_time": "0:36:06"}
+{"current_steps": 2350, "total_steps": 3094, "loss": 0.47939190864562986, "lr": 1.5034148137433623e-05, "epoch": 0.7595959595959596, "percentage": 75.95, "elapsed_time": "1:52:31", "remaining_time": "0:35:37"}
+{"current_steps": 2360, "total_steps": 3094, "loss": 0.48291826248168945, "lr": 1.4654110320836017e-05, "epoch": 0.7628282828282829, "percentage": 76.28, "elapsed_time": "1:53:00", "remaining_time": "0:35:08"}
+{"current_steps": 2370, "total_steps": 3094, "loss": 0.49179973602294924, "lr": 1.4278111146221263e-05, "epoch": 0.7660606060606061, "percentage": 76.6, "elapsed_time": "1:53:28", "remaining_time": "0:34:39"}
+{"current_steps": 2380, "total_steps": 3094, "loss": 0.4716278076171875, "lr": 1.3906193575474508e-05, "epoch": 0.7692929292929293, "percentage": 76.92, "elapsed_time": "1:53:56", "remaining_time": "0:34:10"}
+{"current_steps": 2390, "total_steps": 3094, "loss": 0.47190055847167967, "lr": 1.3538400104114446e-05, "epoch": 0.7725252525252525, "percentage": 77.25, "elapsed_time": "1:54:25", "remaining_time": "0:33:42"}
+{"current_steps": 2400, "total_steps": 3094, "loss": 0.4703176498413086, "lr": 1.3174772756437742e-05, "epoch": 0.7757575757575758, "percentage": 77.57, "elapsed_time": "1:54:53", "remaining_time": "0:33:13"}
+{"current_steps": 2410, "total_steps": 3094, "loss": 0.47541141510009766, "lr": 1.2815353080717379e-05, "epoch": 0.778989898989899, "percentage": 77.89, "elapsed_time": "1:55:30", "remaining_time": "0:32:47"}
+{"current_steps": 2420, "total_steps": 3094, "loss": 0.4860015869140625, "lr": 1.246018214445525e-05, "epoch": 0.7822222222222223, "percentage": 78.22, "elapsed_time": "1:55:58", "remaining_time": "0:32:18"}
+{"current_steps": 2430, "total_steps": 3094, "loss": 0.49062480926513674, "lr": 1.210930052968981e-05, "epoch": 0.7854545454545454, "percentage": 78.54, "elapsed_time": "1:56:26", "remaining_time": "0:31:49"}
+{"current_steps": 2440, "total_steps": 3094, "loss": 0.4694485664367676, "lr": 1.1762748328359152e-05, "epoch": 0.7886868686868687, "percentage": 78.86, "elapsed_time": "1:56:54", "remaining_time": "0:31:20"}
+{"current_steps": 2450, "total_steps": 3094, "loss": 0.47275629043579104, "lr": 1.1420565137720045e-05, "epoch": 0.7919191919191919, "percentage": 79.19, "elapsed_time": "1:57:22", "remaining_time": "0:30:51"}
+{"current_steps": 2460, "total_steps": 3094, "loss": 0.4670067310333252, "lr": 1.1082790055823533e-05, "epoch": 0.7951515151515152, "percentage": 79.51, "elapsed_time": "1:57:50", "remaining_time": "0:30:22"}
+{"current_steps": 2470, "total_steps": 3094, "loss": 0.4700475692749023, "lr": 1.0749461677047624e-05, "epoch": 0.7983838383838384, "percentage": 79.83, "elapsed_time": "1:58:18", "remaining_time": "0:29:53"}
+{"current_steps": 2480, "total_steps": 3094, "loss": 0.46589016914367676, "lr": 1.0420618087687418e-05, "epoch": 0.8016161616161617, "percentage": 80.16, "elapsed_time": "1:58:47", "remaining_time": "0:29:24"}
+{"current_steps": 2490, "total_steps": 3094, "loss": 0.4704419136047363, "lr": 1.0096296861603321e-05, "epoch": 0.8048484848484848, "percentage": 80.48, "elapsed_time": "1:59:16", "remaining_time": "0:28:56"}
+{"current_steps": 2500, "total_steps": 3094, "loss": 0.47326183319091797, "lr": 9.776535055927931e-06, "epoch": 0.8080808080808081, "percentage": 80.8, "elapsed_time": "1:59:44", "remaining_time": "0:28:27"}
+{"current_steps": 2510, "total_steps": 3094, "loss": 0.48441619873046876, "lr": 9.461369206831772e-06, "epoch": 0.8113131313131313, "percentage": 81.12, "elapsed_time": "2:00:12", "remaining_time": "0:27:58"}
+{"current_steps": 2520, "total_steps": 3094, "loss": 0.45856351852416993, "lr": 9.150835325348678e-06, "epoch": 0.8145454545454546, "percentage": 81.45, "elapsed_time": "2:00:40", "remaining_time": "0:27:29"}
+{"current_steps": 2530, "total_steps": 3094, "loss": 0.48114948272705077, "lr": 8.844968893261197e-06, "epoch": 0.8177777777777778, "percentage": 81.77, "elapsed_time": "2:01:09", "remaining_time": "0:27:00"}
+{"current_steps": 2540, "total_steps": 3094, "loss": 0.4930680274963379, "lr": 8.543804859046345e-06, "epoch": 0.821010101010101, "percentage": 82.09, "elapsed_time": "2:01:36", "remaining_time": "0:26:31"}
+{"current_steps": 2550, "total_steps": 3094, "loss": 0.46875743865966796, "lr": 8.247377633882463e-06, "epoch": 0.8242424242424242, "percentage": 82.42, "elapsed_time": "2:02:04", "remaining_time": "0:26:02"}
+{"current_steps": 2560, "total_steps": 3094, "loss": 0.4768000602722168, "lr": 7.95572108771726e-06, "epoch": 0.8274747474747475, "percentage": 82.74, "elapsed_time": "2:02:33", "remaining_time": "0:25:33"}
+{"current_steps": 2570, "total_steps": 3094, "loss": 0.479974365234375, "lr": 7.66886854539795e-06, "epoch": 0.8307070707070707, "percentage": 83.06, "elapsed_time": "2:03:01", "remaining_time": "0:25:04"}
+{"current_steps": 2580, "total_steps": 3094, "loss": 0.4684715270996094, "lr": 7.386852782863407e-06, "epoch": 0.833939393939394, "percentage": 83.39, "elapsed_time": "2:03:28", "remaining_time": "0:24:36"}
+{"current_steps": 2590, "total_steps": 3094, "loss": 0.47191972732543946, "lr": 7.109706023399232e-06, "epoch": 0.8371717171717171, "percentage": 83.71, "elapsed_time": "2:03:56", "remaining_time": "0:24:07"}
+{"current_steps": 2600, "total_steps": 3094, "loss": 0.4766803741455078, "lr": 6.837459933955936e-06, "epoch": 0.8404040404040404, "percentage": 84.03, "elapsed_time": "2:04:24", "remaining_time": "0:23:38"}
+{"current_steps": 2610, "total_steps": 3094, "loss": 0.4592133045196533, "lr": 6.5701456215305656e-06, "epoch": 0.8436363636363636, "percentage": 84.36, "elapsed_time": "2:05:01", "remaining_time": "0:23:11"}
+{"current_steps": 2620, "total_steps": 3094, "loss": 0.4658504009246826, "lr": 6.307793629612452e-06, "epoch": 0.8468686868686869, "percentage": 84.68, "elapsed_time": "2:05:29", "remaining_time": "0:22:42"}
+{"current_steps": 2630, "total_steps": 3094, "loss": 0.4936856269836426, "lr": 6.050433934693339e-06, "epoch": 0.8501010101010101, "percentage": 85.0, "elapsed_time": "2:05:58", "remaining_time": "0:22:13"}
+{"current_steps": 2640, "total_steps": 3094, "loss": 0.4765117645263672, "lr": 5.798095942842141e-06, "epoch": 0.8533333333333334, "percentage": 85.33, "elapsed_time": "2:06:26", "remaining_time": "0:21:44"}
+{"current_steps": 2650, "total_steps": 3094, "loss": 0.47063379287719725, "lr": 5.550808486345072e-06, "epoch": 0.8565656565656565, "percentage": 85.65, "elapsed_time": "2:06:53", "remaining_time": "0:21:15"}
+{"current_steps": 2660, "total_steps": 3094, "loss": 0.4614537715911865, "lr": 5.308599820411247e-06, "epoch": 0.8597979797979798, "percentage": 85.97, "elapsed_time": "2:07:22", "remaining_time": "0:20:46"}
+{"current_steps": 2670, "total_steps": 3094, "loss": 0.48136143684387206, "lr": 5.071497619944171e-06, "epoch": 0.863030303030303, "percentage": 86.3, "elapsed_time": "2:07:50", "remaining_time": "0:20:18"}
+{"current_steps": 2680, "total_steps": 3094, "loss": 0.47299985885620116, "lr": 4.839528976379648e-06, "epoch": 0.8662626262626263, "percentage": 86.62, "elapsed_time": "2:08:18", "remaining_time": "0:19:49"}
+{"current_steps": 2690, "total_steps": 3094, "loss": 0.4829209327697754, "lr": 4.612720394590286e-06, "epoch": 0.8694949494949495, "percentage": 86.94, "elapsed_time": "2:08:46", "remaining_time": "0:19:20"}
+{"current_steps": 2700, "total_steps": 3094, "loss": 0.4762550354003906, "lr": 4.391097789856985e-06, "epoch": 0.8727272727272727, "percentage": 87.27, "elapsed_time": "2:09:14", "remaining_time": "0:18:51"}
+{"current_steps": 2710, "total_steps": 3094, "loss": 0.4898251533508301, "lr": 4.174686484907908e-06, "epoch": 0.8759595959595959, "percentage": 87.59, "elapsed_time": "2:09:42", "remaining_time": "0:18:22"}
+{"current_steps": 2720, "total_steps": 3094, "loss": 0.47261548042297363, "lr": 3.963511207025078e-06, "epoch": 0.8791919191919192, "percentage": 87.91, "elapsed_time": "2:10:12", "remaining_time": "0:17:54"}
+{"current_steps": 2730, "total_steps": 3094, "loss": 0.4839645862579346, "lr": 3.7575960852189728e-06, "epoch": 0.8824242424242424, "percentage": 88.24, "elapsed_time": "2:10:40", "remaining_time": "0:17:25"}
+{"current_steps": 2740, "total_steps": 3094, "loss": 0.46989760398864744, "lr": 3.5569646474715722e-06, "epoch": 0.8856565656565657, "percentage": 88.56, "elapsed_time": "2:11:09", "remaining_time": "0:16:56"}
+{"current_steps": 2750, "total_steps": 3094, "loss": 0.47272281646728515, "lr": 3.361639818048068e-06, "epoch": 0.8888888888888888, "percentage": 88.88, "elapsed_time": "2:11:37", "remaining_time": "0:16:27"}
+{"current_steps": 2760, "total_steps": 3094, "loss": 0.47122917175292967, "lr": 3.1716439148774534e-06, "epoch": 0.8921212121212121, "percentage": 89.2, "elapsed_time": "2:12:06", "remaining_time": "0:15:59"}
+{"current_steps": 2770, "total_steps": 3094, "loss": 0.4727674961090088, "lr": 2.986998647002498e-06, "epoch": 0.8953535353535353, "percentage": 89.53, "elapsed_time": "2:12:35", "remaining_time": "0:15:30"}
+{"current_steps": 2780, "total_steps": 3094, "loss": 0.46461896896362304, "lr": 2.8077251120992742e-06, "epoch": 0.8985858585858586, "percentage": 89.85, "elapsed_time": "2:13:04", "remaining_time": "0:15:01"}
+{"current_steps": 2790, "total_steps": 3094, "loss": 0.46602635383605956, "lr": 2.633843794066515e-06, "epoch": 0.9018181818181819, "percentage": 90.17, "elapsed_time": "2:13:32", "remaining_time": "0:14:33"}
+{"current_steps": 2800, "total_steps": 3094, "loss": 0.4705932140350342, "lr": 2.465374560685091e-06, "epoch": 0.9050505050505051, "percentage": 90.5, "elapsed_time": "2:14:01", "remaining_time": "0:14:04"}
+{"current_steps": 2810, "total_steps": 3094, "loss": 0.4687389373779297, "lr": 2.302336661347926e-06, "epoch": 0.9082828282828282, "percentage": 90.82, "elapsed_time": "2:14:36", "remaining_time": "0:13:36"}
+{"current_steps": 2820, "total_steps": 3094, "loss": 0.4906333923339844, "lr": 2.1447487248605513e-06, "epoch": 0.9115151515151515, "percentage": 91.14, "elapsed_time": "2:15:04", "remaining_time": "0:13:07"}
+{"current_steps": 2830, "total_steps": 3094, "loss": 0.47768077850341795, "lr": 1.9926287573125537e-06, "epoch": 0.9147474747474748, "percentage": 91.47, "elapsed_time": "2:15:33", "remaining_time": "0:12:38"}
+{"current_steps": 2840, "total_steps": 3094, "loss": 0.47643141746520995, "lr": 1.845994140020213e-06, "epoch": 0.917979797979798, "percentage": 91.79, "elapsed_time": "2:16:01", "remaining_time": "0:12:09"}
+{"current_steps": 2850, "total_steps": 3094, "loss": 0.4636590003967285, "lr": 1.7048616275404771e-06, "epoch": 0.9212121212121213, "percentage": 92.11, "elapsed_time": "2:16:30", "remaining_time": "0:11:41"}
+{"current_steps": 2860, "total_steps": 3094, "loss": 0.4707911014556885, "lr": 1.5692473457565748e-06, "epoch": 0.9244444444444444, "percentage": 92.44, "elapsed_time": "2:16:59", "remaining_time": "0:11:12"}
+{"current_steps": 2870, "total_steps": 3094, "loss": 0.45751228332519533, "lr": 1.439166790035501e-06, "epoch": 0.9276767676767677, "percentage": 92.76, "elapsed_time": "2:17:29", "remaining_time": "0:10:43"}
+{"current_steps": 2880, "total_steps": 3094, "loss": 0.4842953681945801, "lr": 1.3146348234574724e-06, "epoch": 0.9309090909090909, "percentage": 93.08, "elapsed_time": "2:17:58", "remaining_time": "0:10:15"}
+{"current_steps": 2890, "total_steps": 3094, "loss": 0.482682991027832, "lr": 1.1956656751176577e-06, "epoch": 0.9341414141414142, "percentage": 93.41, "elapsed_time": "2:18:26", "remaining_time": "0:09:46"}
+{"current_steps": 2900, "total_steps": 3094, "loss": 0.48476057052612304, "lr": 1.0822729385003727e-06, "epoch": 0.9373737373737374, "percentage": 93.73, "elapsed_time": "2:18:54", "remaining_time": "0:09:17"}
+{"current_steps": 2910, "total_steps": 3094, "loss": 0.4767448425292969, "lr": 9.744695699258955e-07, "epoch": 0.9406060606060606, "percentage": 94.05, "elapsed_time": "2:19:22", "remaining_time": "0:08:48"}
+{"current_steps": 2920, "total_steps": 3094, "loss": 0.4663360118865967, "lr": 8.722678870700274e-07, "epoch": 0.9438383838383838, "percentage": 94.38, "elapsed_time": "2:19:51", "remaining_time": "0:08:20"}
+{"current_steps": 2930, "total_steps": 3094, "loss": 0.48151307106018065, "lr": 7.756795675566919e-07, "epoch": 0.9470707070707071, "percentage": 94.7, "elapsed_time": "2:20:19", "remaining_time": "0:07:51"}
+{"current_steps": 2940, "total_steps": 3094, "loss": 0.48086977005004883, "lr": 6.847156476236516e-07, "epoch": 0.9503030303030303, "percentage": 95.02, "elapsed_time": "2:20:48", "remaining_time": "0:07:22"}
+{"current_steps": 2950, "total_steps": 3094, "loss": 0.4648440361022949, "lr": 5.993865208614835e-07, "epoch": 0.9535353535353536, "percentage": 95.35, "elapsed_time": "2:21:17", "remaining_time": "0:06:53"}
+{"current_steps": 2960, "total_steps": 3094, "loss": 0.46828551292419435, "lr": 5.197019370260125e-07, "epoch": 0.9567676767676768, "percentage": 95.67, "elapsed_time": "2:21:46", "remaining_time": "0:06:25"}
+{"current_steps": 2970, "total_steps": 3094, "loss": 0.48481130599975586, "lr": 4.4567100092429704e-07, "epoch": 0.96, "percentage": 95.99, "elapsed_time": "2:22:14", "remaining_time": "0:05:56"}
+{"current_steps": 2980, "total_steps": 3094, "loss": 0.47917518615722654, "lr": 3.7730217137428857e-07, "epoch": 0.9632323232323232, "percentage": 96.32, "elapsed_time": "2:22:43", "remaining_time": "0:05:27"}
+{"current_steps": 2990, "total_steps": 3094, "loss": 0.48064794540405276, "lr": 3.1460326023836083e-07, "epoch": 0.9664646464646465, "percentage": 96.64, "elapsed_time": "2:23:11", "remaining_time": "0:04:58"}
+{"current_steps": 3000, "total_steps": 3094, "loss": 0.4831876754760742, "lr": 2.575814315306846e-07, "epoch": 0.9696969696969697, "percentage": 96.96, "elapsed_time": "2:23:40", "remaining_time": "0:04:30"}
+{"current_steps": 3010, "total_steps": 3094, "loss": 0.4821047306060791, "lr": 2.0624320059869918e-07, "epoch": 0.972929292929293, "percentage": 97.29, "elapsed_time": "2:24:17", "remaining_time": "0:04:01"}
+{"current_steps": 3020, "total_steps": 3094, "loss": 0.46325201988220216, "lr": 1.6059443337861912e-07, "epoch": 0.9761616161616161, "percentage": 97.61, "elapsed_time": "2:24:46", "remaining_time": "0:03:32"}
+{"current_steps": 3030, "total_steps": 3094, "loss": 0.4779689788818359, "lr": 1.2064034572523142e-07, "epoch": 0.9793939393939394, "percentage": 97.93, "elapsed_time": "2:25:15", "remaining_time": "0:03:04"}
+{"current_steps": 3040, "total_steps": 3094, "loss": 0.4866930484771729, "lr": 8.638550281591107e-08, "epoch": 0.9826262626262626, "percentage": 98.25, "elapsed_time": "2:25:43", "remaining_time": "0:02:35"}
+{"current_steps": 3050, "total_steps": 3094, "loss": 0.48350844383239744, "lr": 5.7833818629005054e-08, "epoch": 0.9858585858585859, "percentage": 98.58, "elapsed_time": "2:26:11", "remaining_time": "0:02:06"}
+{"current_steps": 3060, "total_steps": 3094, "loss": 0.4722591400146484, "lr": 3.498855549660118e-08, "epoch": 0.9890909090909091, "percentage": 98.9, "elapsed_time": "2:26:40", "remaining_time": "0:01:37"}
+{"current_steps": 3070, "total_steps": 3094, "loss": 0.48914670944213867, "lr": 1.785232373180401e-08, "epoch": 0.9923232323232323, "percentage": 99.22, "elapsed_time": "2:27:09", "remaining_time": "0:01:09"}
+{"current_steps": 3080, "total_steps": 3094, "loss": 0.4730827331542969, "lr": 6.427081330456774e-09, "epoch": 0.9955555555555555, "percentage": 99.55, "elapsed_time": "2:27:37", "remaining_time": "0:00:40"}
+{"current_steps": 3090, "total_steps": 3094, "loss": 0.4666846752166748, "lr": 7.141337474148025e-10, "epoch": 0.9987878787878788, "percentage": 99.87, "elapsed_time": "2:28:05", "remaining_time": "0:00:11"}
+{"current_steps": 3094, "total_steps": 3094, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "2:28:23", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2206 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 200,
+  "global_step": 3094,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0032323232323232323,
+      "grad_norm": 0.032284051179885864,
+      "learning_rate": 5.806451612903226e-06,
+      "loss": 0.6013355255126953,
+      "step": 10
+    },
+    {
+      "epoch": 0.006464646464646465,
+      "grad_norm": 0.01937970519065857,
+      "learning_rate": 1.2258064516129032e-05,
+      "loss": 0.5758121490478516,
+      "step": 20
+    },
+    {
+      "epoch": 0.009696969696969697,
+      "grad_norm": 0.014327733777463436,
+      "learning_rate": 1.870967741935484e-05,
+      "loss": 0.5787662506103516,
+      "step": 30
+    },
+    {
+      "epoch": 0.01292929292929293,
+      "grad_norm": 0.012254982255399227,
+      "learning_rate": 2.5161290322580645e-05,
+      "loss": 0.5327143669128418,
+      "step": 40
+    },
+    {
+      "epoch": 0.01616161616161616,
+      "grad_norm": 0.014536243863403797,
+      "learning_rate": 3.161290322580645e-05,
+      "loss": 0.5393171310424805,
+      "step": 50
+    },
+    {
+      "epoch": 0.019393939393939394,
+      "grad_norm": 0.011900736019015312,
+      "learning_rate": 3.8064516129032254e-05,
+      "loss": 0.5058945178985595,
+      "step": 60
+    },
+    {
+      "epoch": 0.022626262626262626,
+      "grad_norm": 0.01210293360054493,
+      "learning_rate": 4.451612903225807e-05,
+      "loss": 0.517607593536377,
+      "step": 70
+    },
+    {
+      "epoch": 0.02585858585858586,
+      "grad_norm": 0.017207792028784752,
+      "learning_rate": 5.096774193548387e-05,
+      "loss": 0.5269095420837402,
+      "step": 80
+    },
+    {
+      "epoch": 0.02909090909090909,
+      "grad_norm": 0.013736969791352749,
+      "learning_rate": 5.7419354838709685e-05,
+      "loss": 0.5040688514709473,
+      "step": 90
+    },
+    {
+      "epoch": 0.03232323232323232,
+      "grad_norm": 0.011664404533803463,
+      "learning_rate": 6.387096774193548e-05,
+      "loss": 0.5147775173187256,
+      "step": 100
+    },
+    {
+      "epoch": 0.035555555555555556,
+      "grad_norm": 0.014052552171051502,
+      "learning_rate": 7.03225806451613e-05,
+      "loss": 0.5230005741119385,
+      "step": 110
+    },
+    {
+      "epoch": 0.03878787878787879,
+      "grad_norm": 0.011644740588963032,
+      "learning_rate": 7.67741935483871e-05,
+      "loss": 0.5105222702026367,
+      "step": 120
+    },
+    {
+      "epoch": 0.04202020202020202,
+      "grad_norm": 0.011730308644473553,
+      "learning_rate": 8.32258064516129e-05,
+      "loss": 0.4989170074462891,
+      "step": 130
+    },
+    {
+      "epoch": 0.04525252525252525,
+      "grad_norm": 0.012009115889668465,
+      "learning_rate": 8.967741935483871e-05,
+      "loss": 0.5003124713897705,
+      "step": 140
+    },
+    {
+      "epoch": 0.048484848484848485,
+      "grad_norm": 0.012424134649336338,
+      "learning_rate": 9.612903225806452e-05,
+      "loss": 0.5077538013458252,
+      "step": 150
+    },
+    {
+      "epoch": 0.05171717171717172,
+      "grad_norm": 0.011461800895631313,
+      "learning_rate": 9.999954295400999e-05,
+      "loss": 0.5061477661132813,
+      "step": 160
+    },
+    {
+      "epoch": 0.05494949494949495,
+      "grad_norm": 0.011583201587200165,
+      "learning_rate": 9.999440128258112e-05,
+      "loss": 0.5013481140136719,
+      "step": 170
+    },
+    {
+      "epoch": 0.05818181818181818,
+      "grad_norm": 0.011583367362618446,
+      "learning_rate": 9.998354722168459e-05,
+      "loss": 0.48343815803527834,
+      "step": 180
+    },
+    {
+      "epoch": 0.061414141414141414,
+      "grad_norm": 0.011094105429947376,
+      "learning_rate": 9.996698201151175e-05,
+      "loss": 0.507840633392334,
+      "step": 190
+    },
+    {
+      "epoch": 0.06464646464646465,
+      "grad_norm": 0.011715452186763287,
+      "learning_rate": 9.994470754481315e-05,
+      "loss": 0.49884777069091796,
+      "step": 200
+    },
+    {
+      "epoch": 0.06787878787878789,
+      "grad_norm": 0.010746965184807777,
+      "learning_rate": 9.991672636668239e-05,
+      "loss": 0.5068713188171386,
+      "step": 210
+    },
+    {
+      "epoch": 0.07111111111111111,
+      "grad_norm": 0.012883410789072514,
+      "learning_rate": 9.988304167426519e-05,
+      "loss": 0.4920186519622803,
+      "step": 220
+    },
+    {
+      "epoch": 0.07434343434343435,
+      "grad_norm": 0.011187366209924221,
+      "learning_rate": 9.984365731639419e-05,
+      "loss": 0.5021648406982422,
+      "step": 230
+    },
+    {
+      "epoch": 0.07757575757575758,
+      "grad_norm": 0.010671757161617279,
+      "learning_rate": 9.979857779314906e-05,
+      "loss": 0.5038897514343261,
+      "step": 240
+    },
+    {
+      "epoch": 0.08080808080808081,
+      "grad_norm": 0.01044373121112585,
+      "learning_rate": 9.974780825534246e-05,
+      "loss": 0.4965065956115723,
+      "step": 250
+    },
+    {
+      "epoch": 0.08404040404040404,
+      "grad_norm": 0.010565251111984253,
+      "learning_rate": 9.969135450393141e-05,
+      "loss": 0.5145994186401367,
+      "step": 260
+    },
+    {
+      "epoch": 0.08727272727272728,
+      "grad_norm": 0.010024026967585087,
+      "learning_rate": 9.96292229893545e-05,
+      "loss": 0.505019235610962,
+      "step": 270
+    },
+    {
+      "epoch": 0.0905050505050505,
+      "grad_norm": 0.010430407710373402,
+      "learning_rate": 9.956142081079484e-05,
+      "loss": 0.5115808010101318,
+      "step": 280
+    },
+    {
+      "epoch": 0.09373737373737374,
+      "grad_norm": 0.010048807598650455,
+      "learning_rate": 9.948795571536891e-05,
+      "loss": 0.48525152206420896,
+      "step": 290
+    },
+    {
+      "epoch": 0.09696969696969697,
+      "grad_norm": 0.010108387097716331,
+      "learning_rate": 9.94088360972414e-05,
+      "loss": 0.5002010822296142,
+      "step": 300
+    },
+    {
+      "epoch": 0.10020202020202021,
+      "grad_norm": 0.010273640975356102,
+      "learning_rate": 9.932407099666608e-05,
+      "loss": 0.49662046432495116,
+      "step": 310
+    },
+    {
+      "epoch": 0.10343434343434343,
+      "grad_norm": 0.00995971355587244,
+      "learning_rate": 9.923367009895274e-05,
+      "loss": 0.48578290939331054,
+      "step": 320
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.010459775105118752,
+      "learning_rate": 9.913764373336079e-05,
+      "loss": 0.48862767219543457,
+      "step": 330
+    },
+    {
+      "epoch": 0.1098989898989899,
+      "grad_norm": 0.009838269092142582,
+      "learning_rate": 9.903600287191875e-05,
+      "loss": 0.5034208774566651,
+      "step": 340
+    },
+    {
+      "epoch": 0.11313131313131314,
+      "grad_norm": 0.00978950597345829,
+      "learning_rate": 9.892875912817079e-05,
+      "loss": 0.4870161533355713,
+      "step": 350
+    },
+    {
+      "epoch": 0.11636363636363636,
+      "grad_norm": 0.01030043140053749,
+      "learning_rate": 9.881592475584964e-05,
+      "loss": 0.5026071548461915,
+      "step": 360
+    },
+    {
+      "epoch": 0.1195959595959596,
+      "grad_norm": 0.010531975887715816,
+      "learning_rate": 9.869751264747656e-05,
+      "loss": 0.4883917808532715,
+      "step": 370
+    },
+    {
+      "epoch": 0.12282828282828283,
+      "grad_norm": 0.00986825954169035,
+      "learning_rate": 9.857353633288814e-05,
+      "loss": 0.4927018165588379,
+      "step": 380
+    },
+    {
+      "epoch": 0.12606060606060607,
+      "grad_norm": 0.009432349354028702,
+      "learning_rate": 9.844400997769043e-05,
+      "loss": 0.4908174514770508,
+      "step": 390
+    },
+    {
+      "epoch": 0.1292929292929293,
+      "grad_norm": 0.01057665515691042,
+      "learning_rate": 9.83089483816404e-05,
+      "loss": 0.5069625854492188,
+      "step": 400
+    },
+    {
+      "epoch": 0.13252525252525252,
+      "grad_norm": 0.010007908567786217,
+      "learning_rate": 9.816836697695482e-05,
+      "loss": 0.4988056182861328,
+      "step": 410
+    },
+    {
+      "epoch": 0.13575757575757577,
+      "grad_norm": 0.010027808137238026,
+      "learning_rate": 9.802228182654702e-05,
+      "loss": 0.5007385730743408,
+      "step": 420
+    },
+    {
+      "epoch": 0.138989898989899,
+      "grad_norm": 0.009953738190233707,
+      "learning_rate": 9.787070962219156e-05,
+      "loss": 0.5130783081054687,
+      "step": 430
+    },
+    {
+      "epoch": 0.14222222222222222,
+      "grad_norm": 0.010204462334513664,
+      "learning_rate": 9.771366768261696e-05,
+      "loss": 0.4947535514831543,
+      "step": 440
+    },
+    {
+      "epoch": 0.14545454545454545,
+      "grad_norm": 0.009612451307475567,
+      "learning_rate": 9.755117395152689e-05,
+      "loss": 0.4917112350463867,
+      "step": 450
+    },
+    {
+      "epoch": 0.1486868686868687,
+      "grad_norm": 0.00995573028922081,
+      "learning_rate": 9.73832469955499e-05,
+      "loss": 0.4882859230041504,
+      "step": 460
+    },
+    {
+      "epoch": 0.15191919191919193,
+      "grad_norm": 0.009584570303559303,
+      "learning_rate": 9.720990600211797e-05,
+      "loss": 0.500526762008667,
+      "step": 470
+    },
+    {
+      "epoch": 0.15515151515151515,
+      "grad_norm": 0.010585076175630093,
+      "learning_rate": 9.703117077727419e-05,
+      "loss": 0.496882963180542,
+      "step": 480
+    },
+    {
+      "epoch": 0.15838383838383838,
+      "grad_norm": 0.009859723038971424,
+      "learning_rate": 9.684706174340965e-05,
+      "loss": 0.48728485107421876,
+      "step": 490
+    },
+    {
+      "epoch": 0.16161616161616163,
+      "grad_norm": 0.010212041437625885,
+      "learning_rate": 9.665759993693e-05,
+      "loss": 0.49378366470336915,
+      "step": 500
+    },
+    {
+      "epoch": 0.16484848484848486,
+      "grad_norm": 0.009744231589138508,
+      "learning_rate": 9.646280700585185e-05,
+      "loss": 0.4663555145263672,
+      "step": 510
+    },
+    {
+      "epoch": 0.16808080808080808,
+      "grad_norm": 0.009789686650037766,
+      "learning_rate": 9.626270520732916e-05,
+      "loss": 0.4879913330078125,
+      "step": 520
+    },
+    {
+      "epoch": 0.1713131313131313,
+      "grad_norm": 0.009891769848763943,
+      "learning_rate": 9.605731740511022e-05,
+      "loss": 0.48809428215026857,
+      "step": 530
+    },
+    {
+      "epoch": 0.17454545454545456,
+      "grad_norm": 0.01002143882215023,
+      "learning_rate": 9.584666706692517e-05,
+      "loss": 0.4959606170654297,
+      "step": 540
+    },
+    {
+      "epoch": 0.17777777777777778,
+      "grad_norm": 0.009208496659994125,
+      "learning_rate": 9.56307782618046e-05,
+      "loss": 0.4878594398498535,
+      "step": 550
+    },
+    {
+      "epoch": 0.181010101010101,
+      "grad_norm": 0.009645081125199795,
+      "learning_rate": 9.540967565732937e-05,
+      "loss": 0.4769869804382324,
+      "step": 560
+    },
+    {
+      "epoch": 0.18424242424242424,
+      "grad_norm": 0.010497638955712318,
+      "learning_rate": 9.51833845168121e-05,
+      "loss": 0.4970097064971924,
+      "step": 570
+    },
+    {
+      "epoch": 0.1874747474747475,
+      "grad_norm": 0.010612033307552338,
+      "learning_rate": 9.495193069641057e-05,
+      "loss": 0.4945381164550781,
+      "step": 580
+    },
+    {
+      "epoch": 0.1907070707070707,
+      "grad_norm": 0.009433986619114876,
+      "learning_rate": 9.47153406421734e-05,
+      "loss": 0.4860210418701172,
+      "step": 590
+    },
+    {
+      "epoch": 0.19393939393939394,
+      "grad_norm": 0.009995914995670319,
+      "learning_rate": 9.447364138701823e-05,
+      "loss": 0.4904911994934082,
+      "step": 600
+    },
+    {
+      "epoch": 0.19717171717171716,
+      "grad_norm": 0.009814019314944744,
+      "learning_rate": 9.422686054764302e-05,
+      "loss": 0.4915336608886719,
+      "step": 610
+    },
+    {
+      "epoch": 0.20040404040404042,
+      "grad_norm": 0.010199982672929764,
+      "learning_rate": 9.397502632137055e-05,
+      "loss": 0.4805011749267578,
+      "step": 620
+    },
+    {
+      "epoch": 0.20363636363636364,
+      "grad_norm": 0.010121874511241913,
+      "learning_rate": 9.371816748292641e-05,
+      "loss": 0.47633209228515627,
+      "step": 630
+    },
+    {
+      "epoch": 0.20686868686868687,
+      "grad_norm": 0.009638865478336811,
+      "learning_rate": 9.345631338115141e-05,
+      "loss": 0.48993511199951173,
+      "step": 640
+    },
+    {
+      "epoch": 0.2101010101010101,
+      "grad_norm": 0.010041174478828907,
+      "learning_rate": 9.318949393564807e-05,
+      "loss": 0.4798978328704834,
+      "step": 650
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.010145517997443676,
+      "learning_rate": 9.291773963336193e-05,
+      "loss": 0.4696659564971924,
+      "step": 660
+    },
+    {
+      "epoch": 0.21656565656565657,
+      "grad_norm": 0.01043335534632206,
+      "learning_rate": 9.264108152509816e-05,
+      "loss": 0.4955574035644531,
+      "step": 670
+    },
+    {
+      "epoch": 0.2197979797979798,
+      "grad_norm": 0.010406569577753544,
+      "learning_rate": 9.235955122197368e-05,
+      "loss": 0.48659563064575195,
+      "step": 680
+    },
+    {
+      "epoch": 0.22303030303030302,
+      "grad_norm": 0.009870355017483234,
+      "learning_rate": 9.207318089180524e-05,
+      "loss": 0.4766091823577881,
+      "step": 690
+    },
+    {
+      "epoch": 0.22626262626262628,
+      "grad_norm": 0.009980005212128162,
+      "learning_rate": 9.178200325543384e-05,
+      "loss": 0.5022068023681641,
+      "step": 700
+    },
+    {
+      "epoch": 0.2294949494949495,
+      "grad_norm": 0.009765878319740295,
+      "learning_rate": 9.148605158298621e-05,
+      "loss": 0.48309478759765623,
+      "step": 710
+    },
+    {
+      "epoch": 0.23272727272727273,
+      "grad_norm": 0.009879437275230885,
+      "learning_rate": 9.118535969007314e-05,
+      "loss": 0.4793684959411621,
+      "step": 720
+    },
+    {
+      "epoch": 0.23595959595959595,
+      "grad_norm": 0.009907045401632786,
+      "learning_rate": 9.087996193392578e-05,
+      "loss": 0.49844112396240237,
+      "step": 730
+    },
+    {
+      "epoch": 0.2391919191919192,
+      "grad_norm": 0.009958872571587563,
+      "learning_rate": 9.056989320947e-05,
+      "loss": 0.48113102912902833,
+      "step": 740
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.010206855833530426,
+      "learning_rate": 9.025518894533921e-05,
+      "loss": 0.5048784255981446,
+      "step": 750
+    },
+    {
+      "epoch": 0.24565656565656566,
+      "grad_norm": 0.009286429733037949,
+      "learning_rate": 8.99358850998263e-05,
+      "loss": 0.4862624168395996,
+      "step": 760
+    },
+    {
+      "epoch": 0.24888888888888888,
+      "grad_norm": 0.009919015690684319,
+      "learning_rate": 8.9612018156775e-05,
+      "loss": 0.48739056587219237,
+      "step": 770
+    },
+    {
+      "epoch": 0.25212121212121213,
+      "grad_norm": 0.010435211472213268,
+      "learning_rate": 8.928362512141124e-05,
+      "loss": 0.48689990043640136,
+      "step": 780
+    },
+    {
+      "epoch": 0.25535353535353533,
+      "grad_norm": 0.009992080740630627,
+      "learning_rate": 8.895074351611488e-05,
+      "loss": 0.4848791599273682,
+      "step": 790
+    },
+    {
+      "epoch": 0.2585858585858586,
+      "grad_norm": 0.010449117980897427,
+      "learning_rate": 8.861341137613242e-05,
+      "loss": 0.49130568504333494,
+      "step": 800
+    },
+    {
+      "epoch": 0.26181818181818184,
+      "grad_norm": 0.010061345063149929,
+      "learning_rate": 8.827166724523105e-05,
+      "loss": 0.49056081771850585,
+      "step": 810
+    },
+    {
+      "epoch": 0.26505050505050504,
+      "grad_norm": 0.009908635169267654,
+      "learning_rate": 8.792555017129461e-05,
+      "loss": 0.4706866264343262,
+      "step": 820
+    },
+    {
+      "epoch": 0.2682828282828283,
+      "grad_norm": 0.010003669187426567,
+      "learning_rate": 8.757509970186196e-05,
+      "loss": 0.48719348907470705,
+      "step": 830
+    },
+    {
+      "epoch": 0.27151515151515154,
+      "grad_norm": 0.009513127617537975,
+      "learning_rate": 8.722035587960826e-05,
+      "loss": 0.48200483322143556,
+      "step": 840
+    },
+    {
+      "epoch": 0.27474747474747474,
+      "grad_norm": 0.009142451919615269,
+      "learning_rate": 8.686135923776969e-05,
+      "loss": 0.48613176345825193,
+      "step": 850
+    },
+    {
+      "epoch": 0.277979797979798,
+      "grad_norm": 0.00980432890355587,
+      "learning_rate": 8.649815079551205e-05,
+      "loss": 0.4976047515869141,
+      "step": 860
+    },
+    {
+      "epoch": 0.2812121212121212,
+      "grad_norm": 0.010442109778523445,
+      "learning_rate": 8.613077205324389e-05,
+      "loss": 0.48451838493347166,
+      "step": 870
+    },
+    {
+      "epoch": 0.28444444444444444,
+      "grad_norm": 0.009309548884630203,
+      "learning_rate": 8.575926498787476e-05,
+      "loss": 0.5115366458892823,
+      "step": 880
+    },
+    {
+      "epoch": 0.2876767676767677,
+      "grad_norm": 0.009093924425542355,
+      "learning_rate": 8.538367204801872e-05,
+      "loss": 0.48187432289123533,
+      "step": 890
+    },
+    {
+      "epoch": 0.2909090909090909,
+      "grad_norm": 0.009757987223565578,
+      "learning_rate": 8.500403614914432e-05,
+      "loss": 0.4882505416870117,
+      "step": 900
+    },
+    {
+      "epoch": 0.29414141414141415,
+      "grad_norm": 0.010261048562824726,
+      "learning_rate": 8.462040066867089e-05,
+      "loss": 0.49068965911865237,
+      "step": 910
+    },
+    {
+      "epoch": 0.2973737373737374,
+      "grad_norm": 0.009317740797996521,
+      "learning_rate": 8.423280944101233e-05,
+      "loss": 0.4966132164001465,
+      "step": 920
+    },
+    {
+      "epoch": 0.3006060606060606,
+      "grad_norm": 0.009787693619728088,
+      "learning_rate": 8.384130675256852e-05,
+      "loss": 0.4754981994628906,
+      "step": 930
+    },
+    {
+      "epoch": 0.30383838383838385,
+      "grad_norm": 0.010005015879869461,
+      "learning_rate": 8.34459373366651e-05,
+      "loss": 0.4735103130340576,
+      "step": 940
+    },
+    {
+      "epoch": 0.30707070707070705,
+      "grad_norm": 0.009837017394602299,
+      "learning_rate": 8.304674636844231e-05,
+      "loss": 0.4809592247009277,
+      "step": 950
+    },
+    {
+      "epoch": 0.3103030303030303,
+      "grad_norm": 0.009590484201908112,
+      "learning_rate": 8.264377945969312e-05,
+      "loss": 0.48206100463867185,
+      "step": 960
+    },
+    {
+      "epoch": 0.31353535353535356,
+      "grad_norm": 0.009699508547782898,
+      "learning_rate": 8.223708265365174e-05,
+      "loss": 0.48718748092651365,
+      "step": 970
+    },
+    {
+      "epoch": 0.31676767676767675,
+      "grad_norm": 0.010278215631842613,
+      "learning_rate": 8.182670241973253e-05,
+      "loss": 0.4952278137207031,
+      "step": 980
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.010104077868163586,
+      "learning_rate": 8.141268564822053e-05,
+      "loss": 0.47769975662231445,
+      "step": 990
+    },
+    {
+      "epoch": 0.32323232323232326,
+      "grad_norm": 0.009301737882196903,
+      "learning_rate": 8.099507964491369e-05,
+      "loss": 0.4862718105316162,
+      "step": 1000
+    },
+    {
+      "epoch": 0.32646464646464646,
+      "grad_norm": 0.009307135827839375,
+      "learning_rate": 8.057393212571767e-05,
+      "loss": 0.49833106994628906,
+      "step": 1010
+    },
+    {
+      "epoch": 0.3296969696969697,
+      "grad_norm": 0.009420682676136494,
+      "learning_rate": 8.014929121119378e-05,
+      "loss": 0.48829941749572753,
+      "step": 1020
+    },
+    {
+      "epoch": 0.3329292929292929,
+      "grad_norm": 0.010058379732072353,
+      "learning_rate": 7.972120542106077e-05,
+      "loss": 0.46506147384643554,
+      "step": 1030
+    },
+    {
+      "epoch": 0.33616161616161616,
+      "grad_norm": 0.009461579844355583,
+      "learning_rate": 7.92897236686508e-05,
+      "loss": 0.47866268157958985,
+      "step": 1040
+    },
+    {
+      "epoch": 0.3393939393939394,
+      "grad_norm": 0.010341835208237171,
+      "learning_rate": 7.885489525532075e-05,
+      "loss": 0.4966601371765137,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3426262626262626,
+      "grad_norm": 0.01042103860527277,
+      "learning_rate": 7.84167698648189e-05,
+      "loss": 0.49251084327697753,
+      "step": 1060
+    },
+    {
+      "epoch": 0.34585858585858587,
+      "grad_norm": 0.010442749597132206,
+      "learning_rate": 7.797539755760805e-05,
+      "loss": 0.4816086769104004,
+      "step": 1070
+    },
+    {
+      "epoch": 0.3490909090909091,
+      "grad_norm": 0.010256553068757057,
+      "learning_rate": 7.753082876514562e-05,
+      "loss": 0.47102947235107423,
+      "step": 1080
+    },
+    {
+      "epoch": 0.3523232323232323,
+      "grad_norm": 0.009399017319083214,
+      "learning_rate": 7.708311428412129e-05,
+      "loss": 0.4810478210449219,
+      "step": 1090
+    },
+    {
+      "epoch": 0.35555555555555557,
+      "grad_norm": 0.009499317966401577,
+      "learning_rate": 7.663230527065293e-05,
+      "loss": 0.47051143646240234,
+      "step": 1100
+    },
+    {
+      "epoch": 0.35878787878787877,
+      "grad_norm": 0.009759469889104366,
+      "learning_rate": 7.617845323444156e-05,
+      "loss": 0.4780744552612305,
+      "step": 1110
+    },
+    {
+      "epoch": 0.362020202020202,
+      "grad_norm": 0.00987281370908022,
+      "learning_rate": 7.572161003288565e-05,
+      "loss": 0.4804032325744629,
+      "step": 1120
+    },
+    {
+      "epoch": 0.3652525252525253,
+      "grad_norm": 0.00963522493839264,
+      "learning_rate": 7.526182786515609e-05,
+      "loss": 0.48206367492675783,
+      "step": 1130
+    },
+    {
+      "epoch": 0.36848484848484847,
+      "grad_norm": 0.009587026201188564,
+      "learning_rate": 7.479915926623165e-05,
+      "loss": 0.49240264892578123,
+      "step": 1140
+    },
+    {
+      "epoch": 0.3717171717171717,
+      "grad_norm": 0.009810036048293114,
+      "learning_rate": 7.433365710089646e-05,
+      "loss": 0.48599681854248045,
+      "step": 1150
+    },
+    {
+      "epoch": 0.374949494949495,
+      "grad_norm": 0.00978278461843729,
+      "learning_rate": 7.386537455769963e-05,
+      "loss": 0.4688436031341553,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3781818181818182,
+      "grad_norm": 0.00925996620208025,
+      "learning_rate": 7.339436514287783e-05,
+      "loss": 0.47986507415771484,
+      "step": 1170
+    },
+    {
+      "epoch": 0.3814141414141414,
+      "grad_norm": 0.010006657801568508,
+      "learning_rate": 7.292068267424165e-05,
+      "loss": 0.4771553993225098,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3846464646464646,
+      "grad_norm": 0.010299976915121078,
+      "learning_rate": 7.244438127502647e-05,
+      "loss": 0.4854436874389648,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3878787878787879,
+      "grad_norm": 0.009807374328374863,
+      "learning_rate": 7.196551536770807e-05,
+      "loss": 0.4763533592224121,
+      "step": 1200
+    },
+    {
+      "epoch": 0.39111111111111113,
+      "grad_norm": 0.010062369517982006,
+      "learning_rate": 7.148413966778451e-05,
+      "loss": 0.47457141876220704,
+      "step": 1210
+    },
+    {
+      "epoch": 0.39434343434343433,
+      "grad_norm": 0.009904388338327408,
+      "learning_rate": 7.100030917752423e-05,
+      "loss": 0.4732469081878662,
+      "step": 1220
+    },
+    {
+      "epoch": 0.3975757575757576,
+      "grad_norm": 0.009578046388924122,
+      "learning_rate": 7.051407917968138e-05,
+      "loss": 0.47551660537719725,
+      "step": 1230
+    },
+    {
+      "epoch": 0.40080808080808084,
+      "grad_norm": 0.010024272836744785,
+      "learning_rate": 7.002550523117926e-05,
+      "loss": 0.4835049629211426,
+      "step": 1240
+    },
+    {
+      "epoch": 0.40404040404040403,
+      "grad_norm": 0.010056886821985245,
+      "learning_rate": 6.953464315676241e-05,
+      "loss": 0.4909071922302246,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4072727272727273,
+      "grad_norm": 0.009707778692245483,
+      "learning_rate": 6.904154904261792e-05,
+      "loss": 0.4842695236206055,
+      "step": 1260
+    },
+    {
+      "epoch": 0.4105050505050505,
+      "grad_norm": 0.00976107269525528,
+      "learning_rate": 6.8546279229967e-05,
+      "loss": 0.48967390060424804,
+      "step": 1270
+    },
+    {
+      "epoch": 0.41373737373737374,
+      "grad_norm": 0.010392800904810429,
+      "learning_rate": 6.804889030862753e-05,
+      "loss": 0.48658218383789065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.416969696969697,
+      "grad_norm": 0.009267269633710384,
+      "learning_rate": 6.754943911054793e-05,
+      "loss": 0.48893008232116697,
+      "step": 1290
+    },
+    {
+      "epoch": 0.4202020202020202,
+      "grad_norm": 0.009753459133207798,
+      "learning_rate": 6.704798270331358e-05,
+      "loss": 0.49384117126464844,
+      "step": 1300
+    },
+    {
+      "epoch": 0.42343434343434344,
+      "grad_norm": 0.011121846735477448,
+      "learning_rate": 6.654457838362621e-05,
+      "loss": 0.47458324432373045,
+      "step": 1310
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.009406324476003647,
+      "learning_rate": 6.603928367075718e-05,
+      "loss": 0.4703402519226074,
+      "step": 1320
+    },
+    {
+      "epoch": 0.4298989898989899,
+      "grad_norm": 0.010009719990193844,
+      "learning_rate": 6.553215629997529e-05,
+      "loss": 0.4851715087890625,
+      "step": 1330
+    },
+    {
+      "epoch": 0.43313131313131314,
+      "grad_norm": 0.009798573330044746,
+      "learning_rate": 6.502325421594988e-05,
+      "loss": 0.4779622554779053,
+      "step": 1340
+    },
+    {
+      "epoch": 0.43636363636363634,
+      "grad_norm": 0.0098969591781497,
+      "learning_rate": 6.451263556613007e-05,
+      "loss": 0.4708548545837402,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4395959595959596,
+      "grad_norm": 0.009853474795818329,
+      "learning_rate": 6.40003586941008e-05,
+      "loss": 0.4721970558166504,
+      "step": 1360
+    },
+    {
+      "epoch": 0.44282828282828285,
+      "grad_norm": 0.009663710370659828,
+      "learning_rate": 6.348648213291642e-05,
+      "loss": 0.4798272132873535,
+      "step": 1370
+    },
+    {
+      "epoch": 0.44606060606060605,
+      "grad_norm": 0.009419051930308342,
+      "learning_rate": 6.297106459841272e-05,
+      "loss": 0.471483039855957,
+      "step": 1380
+    },
+    {
+      "epoch": 0.4492929292929293,
+      "grad_norm": 0.009978282265365124,
+      "learning_rate": 6.245416498249801e-05,
+      "loss": 0.4772329330444336,
+      "step": 1390
+    },
+    {
+      "epoch": 0.45252525252525255,
+      "grad_norm": 0.009491856209933758,
+      "learning_rate": 6.193584234642403e-05,
+      "loss": 0.48812179565429686,
+      "step": 1400
+    },
+    {
+      "epoch": 0.45575757575757575,
+      "grad_norm": 0.010496517643332481,
+      "learning_rate": 6.141615591403771e-05,
+      "loss": 0.48897976875305177,
+      "step": 1410
+    },
+    {
+      "epoch": 0.458989898989899,
+      "grad_norm": 0.01015474647283554,
+      "learning_rate": 6.0895165065014106e-05,
+      "loss": 0.4850447654724121,
+      "step": 1420
+    },
+    {
+      "epoch": 0.4622222222222222,
+      "grad_norm": 0.009763741865754128,
+      "learning_rate": 6.037292932807167e-05,
+      "loss": 0.4857158660888672,
+      "step": 1430
+    },
+    {
+      "epoch": 0.46545454545454545,
+      "grad_norm": 0.009874231182038784,
+      "learning_rate": 5.984950837417048e-05,
+      "loss": 0.4844364166259766,
+      "step": 1440
+    },
+    {
+      "epoch": 0.4686868686868687,
+      "grad_norm": 0.010104037821292877,
+      "learning_rate": 5.932496200969422e-05,
+      "loss": 0.47542514801025393,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4719191919191919,
+      "grad_norm": 0.009445435367524624,
+      "learning_rate": 5.879935016961661e-05,
+      "loss": 0.48579182624816897,
+      "step": 1460
+    },
+    {
+      "epoch": 0.47515151515151516,
+      "grad_norm": 0.010507128201425076,
+      "learning_rate": 5.827273291065326e-05,
+      "loss": 0.48273677825927735,
+      "step": 1470
+    },
+    {
+      "epoch": 0.4783838383838384,
+      "grad_norm": 0.009411566890776157,
+      "learning_rate": 5.7745170404399484e-05,
+      "loss": 0.46429009437561036,
+      "step": 1480
+    },
+    {
+      "epoch": 0.4816161616161616,
+      "grad_norm": 0.010377817787230015,
+      "learning_rate": 5.721672293045518e-05,
+      "loss": 0.49172677993774416,
+      "step": 1490
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.009920118376612663,
+      "learning_rate": 5.668745086953712e-05,
+      "loss": 0.4934688568115234,
+      "step": 1500
+    },
+    {
+      "epoch": 0.48808080808080806,
+      "grad_norm": 0.012272641994059086,
+      "learning_rate": 5.615741469657985e-05,
+      "loss": 0.4826413631439209,
+      "step": 1510
+    },
+    {
+      "epoch": 0.4913131313131313,
+      "grad_norm": 0.00981989037245512,
+      "learning_rate": 5.562667497382582e-05,
+      "loss": 0.48468503952026365,
+      "step": 1520
+    },
+    {
+      "epoch": 0.49454545454545457,
+      "grad_norm": 0.010148138739168644,
+      "learning_rate": 5.509529234390553e-05,
+      "loss": 0.47773942947387693,
+      "step": 1530
+    },
+    {
+      "epoch": 0.49777777777777776,
+      "grad_norm": 0.010528397746384144,
+      "learning_rate": 5.456332752290837e-05,
+      "loss": 0.47507562637329104,
+      "step": 1540
+    },
+    {
+      "epoch": 0.501010101010101,
+      "grad_norm": 0.01076479908078909,
+      "learning_rate": 5.4030841293445244e-05,
+      "loss": 0.486495304107666,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5042424242424243,
+      "grad_norm": 0.009976644068956375,
+      "learning_rate": 5.349789449770351e-05,
+      "loss": 0.48320484161376953,
+      "step": 1560
+    },
+    {
+      "epoch": 0.5074747474747475,
+      "grad_norm": 0.010504718869924545,
+      "learning_rate": 5.2964548030495065e-05,
+      "loss": 0.48847188949584963,
+      "step": 1570
+    },
+    {
+      "epoch": 0.5107070707070707,
+      "grad_norm": 0.010325642302632332,
+      "learning_rate": 5.243086283229852e-05,
+      "loss": 0.47591514587402345,
+      "step": 1580
+    },
+    {
+      "epoch": 0.5139393939393939,
+      "grad_norm": 0.010260741226375103,
+      "learning_rate": 5.18968998822961e-05,
+      "loss": 0.48136124610900877,
+      "step": 1590
+    },
+    {
+      "epoch": 0.5171717171717172,
+      "grad_norm": 0.010797196067869663,
+      "learning_rate": 5.1362720191406065e-05,
+      "loss": 0.48076438903808594,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5204040404040404,
+      "grad_norm": 0.010010522790253162,
+      "learning_rate": 5.082838479531169e-05,
+      "loss": 0.5004307270050049,
+      "step": 1610
+    },
+    {
+      "epoch": 0.5236363636363637,
+      "grad_norm": 0.010120037943124771,
+      "learning_rate": 5.029395474748714e-05,
+      "loss": 0.4812767028808594,
+      "step": 1620
+    },
+    {
+      "epoch": 0.5268686868686868,
+      "grad_norm": 0.009431752376258373,
+      "learning_rate": 4.975949111222158e-05,
+      "loss": 0.4887521743774414,
+      "step": 1630
+    },
+    {
+      "epoch": 0.5301010101010101,
+      "grad_norm": 0.010080527514219284,
+      "learning_rate": 4.9225054957641916e-05,
+      "loss": 0.48248910903930664,
+      "step": 1640
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.009522376582026482,
+      "learning_rate": 4.8690707348735035e-05,
+      "loss": 0.4855649948120117,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5365656565656566,
+      "grad_norm": 0.009686745703220367,
+      "learning_rate": 4.8156509340370605e-05,
+      "loss": 0.47187280654907227,
+      "step": 1660
+    },
+    {
+      "epoch": 0.5397979797979798,
+      "grad_norm": 0.011875285767018795,
+      "learning_rate": 4.762252197032482e-05,
+      "loss": 0.46579513549804685,
+      "step": 1670
+    },
+    {
+      "epoch": 0.5430303030303031,
+      "grad_norm": 0.009932303801178932,
+      "learning_rate": 4.7088806252306224e-05,
+      "loss": 0.47946829795837403,
+      "step": 1680
+    },
+    {
+      "epoch": 0.5462626262626262,
+      "grad_norm": 0.017099183052778244,
+      "learning_rate": 4.655542316898423e-05,
+      "loss": 0.4593667030334473,
+      "step": 1690
+    },
+    {
+      "epoch": 0.5494949494949495,
+      "grad_norm": 0.010512005537748337,
+      "learning_rate": 4.6022433665021246e-05,
+      "loss": 0.48582897186279295,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5527272727272727,
+      "grad_norm": 0.00989206787198782,
+      "learning_rate": 4.548989864010902e-05,
+      "loss": 0.4849580764770508,
+      "step": 1710
+    },
+    {
+      "epoch": 0.555959595959596,
+      "grad_norm": 0.010284029878675938,
+      "learning_rate": 4.495787894201031e-05,
+      "loss": 0.49089298248291013,
+      "step": 1720
+    },
+    {
+      "epoch": 0.5591919191919192,
+      "grad_norm": 0.00992760993540287,
+      "learning_rate": 4.442643535960631e-05,
+      "loss": 0.48010549545288084,
+      "step": 1730
+    },
+    {
+      "epoch": 0.5624242424242424,
+      "grad_norm": 0.00978371873497963,
+      "learning_rate": 4.3895628615950864e-05,
+      "loss": 0.47594566345214845,
+      "step": 1740
+    },
+    {
+      "epoch": 0.5656565656565656,
+      "grad_norm": 0.00981004349887371,
+      "learning_rate": 4.3365519361332345e-05,
+      "loss": 0.48056421279907224,
+      "step": 1750
+    },
+    {
+      "epoch": 0.5688888888888889,
+      "grad_norm": 0.010216868482530117,
+      "learning_rate": 4.283616816634353e-05,
+      "loss": 0.47501134872436523,
+      "step": 1760
+    },
+    {
+      "epoch": 0.5721212121212121,
+      "grad_norm": 0.010267022997140884,
+      "learning_rate": 4.230763551496089e-05,
+      "loss": 0.478366756439209,
+      "step": 1770
+    },
+    {
+      "epoch": 0.5753535353535354,
+      "grad_norm": 0.009910739958286285,
+      "learning_rate": 4.1779981797633645e-05,
+      "loss": 0.478058385848999,
+      "step": 1780
+    },
+    {
+      "epoch": 0.5785858585858585,
+      "grad_norm": 0.011339185759425163,
+      "learning_rate": 4.1253267304383455e-05,
+      "loss": 0.48466057777404786,
+      "step": 1790
+    },
+    {
+      "epoch": 0.5818181818181818,
+      "grad_norm": 0.009522072039544582,
+      "learning_rate": 4.072755221791572e-05,
+      "loss": 0.4769908905029297,
+      "step": 1800
+    },
+    {
+      "epoch": 0.585050505050505,
+      "grad_norm": 0.009808518923819065,
+      "learning_rate": 4.020289660674306e-05,
+      "loss": 0.47162666320800783,
+      "step": 1810
+    },
+    {
+      "epoch": 0.5882828282828283,
+      "grad_norm": 0.009962448850274086,
+      "learning_rate": 3.967936041832173e-05,
+      "loss": 0.46282405853271485,
+      "step": 1820
+    },
+    {
+      "epoch": 0.5915151515151515,
+      "grad_norm": 0.009498678147792816,
+      "learning_rate": 3.9157003472202246e-05,
+      "loss": 0.4794480323791504,
+      "step": 1830
+    },
+    {
+      "epoch": 0.5947474747474748,
+      "grad_norm": 0.009407177567481995,
+      "learning_rate": 3.863588545319407e-05,
+      "loss": 0.4729412078857422,
+      "step": 1840
+    },
+    {
+      "epoch": 0.597979797979798,
+      "grad_norm": 0.009899895638227463,
+      "learning_rate": 3.8116065904546196e-05,
+      "loss": 0.47380704879760743,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6012121212121212,
+      "grad_norm": 0.009560837410390377,
+      "learning_rate": 3.759760422114362e-05,
+      "loss": 0.47751388549804685,
+      "step": 1860
+    },
+    {
+      "epoch": 0.6044444444444445,
+      "grad_norm": 0.010970192961394787,
+      "learning_rate": 3.708055964272088e-05,
+      "loss": 0.47801823616027833,
+      "step": 1870
+    },
+    {
+      "epoch": 0.6076767676767677,
+      "grad_norm": 0.00964390765875578,
+      "learning_rate": 3.6564991247093234e-05,
+      "loss": 0.4800426483154297,
+      "step": 1880
+    },
+    {
+      "epoch": 0.610909090909091,
+      "grad_norm": 0.009764602407813072,
+      "learning_rate": 3.6050957943406465e-05,
+      "loss": 0.4812753677368164,
+      "step": 1890
+    },
+    {
+      "epoch": 0.6141414141414141,
+      "grad_norm": 0.009959314949810505,
+      "learning_rate": 3.553851846540584e-05,
+      "loss": 0.47804956436157225,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6173737373737374,
+      "grad_norm": 0.010666392743587494,
+      "learning_rate": 3.50277313647252e-05,
+      "loss": 0.4772273063659668,
+      "step": 1910
+    },
+    {
+      "epoch": 0.6206060606060606,
+      "grad_norm": 0.009173358790576458,
+      "learning_rate": 3.451865500419676e-05,
+      "loss": 0.4892144203186035,
+      "step": 1920
+    },
+    {
+      "epoch": 0.6238383838383839,
+      "grad_norm": 0.010000358335673809,
+      "learning_rate": 3.401134755118256e-05,
+      "loss": 0.48959059715270997,
+      "step": 1930
+    },
+    {
+      "epoch": 0.6270707070707071,
+      "grad_norm": 0.010190536268055439,
+      "learning_rate": 3.350586697092826e-05,
+      "loss": 0.46478729248046874,
+      "step": 1940
+    },
+    {
+      "epoch": 0.6303030303030303,
+      "grad_norm": 0.010812178254127502,
+      "learning_rate": 3.300227101993998e-05,
+      "loss": 0.5046152114868164,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6335353535353535,
+      "grad_norm": 0.01017849799245596,
+      "learning_rate": 3.2500617239384947e-05,
+      "loss": 0.4698008060455322,
+      "step": 1960
+    },
+    {
+      "epoch": 0.6367676767676768,
+      "grad_norm": 0.011103908531367779,
+      "learning_rate": 3.200096294851691e-05,
+      "loss": 0.4716217041015625,
+      "step": 1970
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.009982883930206299,
+      "learning_rate": 3.150336523812674e-05,
+      "loss": 0.47135162353515625,
+      "step": 1980
+    },
+    {
+      "epoch": 0.6432323232323233,
+      "grad_norm": 0.01043197326362133,
+      "learning_rate": 3.100788096401925e-05,
+      "loss": 0.4799614906311035,
+      "step": 1990
+    },
+    {
+      "epoch": 0.6464646464646465,
+      "grad_norm": 0.010667623952031136,
+      "learning_rate": 3.051456674051677e-05,
+      "loss": 0.4682164192199707,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6496969696969697,
+      "grad_norm": 0.010620036162436008,
+      "learning_rate": 3.0023478933990347e-05,
+      "loss": 0.4750208854675293,
+      "step": 2010
+    },
+    {
+      "epoch": 0.6529292929292929,
+      "grad_norm": 0.010374991223216057,
+      "learning_rate": 2.9534673656419377e-05,
+      "loss": 0.48034076690673827,
+      "step": 2020
+    },
+    {
+      "epoch": 0.6561616161616162,
+      "grad_norm": 0.011932817287743092,
+      "learning_rate": 2.9048206758980136e-05,
+      "loss": 0.46314101219177245,
+      "step": 2030
+    },
+    {
+      "epoch": 0.6593939393939394,
+      "grad_norm": 0.01039852574467659,
+      "learning_rate": 2.856413382566425e-05,
+      "loss": 0.4783937454223633,
+      "step": 2040
+    },
+    {
+      "epoch": 0.6626262626262627,
+      "grad_norm": 0.010200604796409607,
+      "learning_rate": 2.8082510166927583e-05,
+      "loss": 0.4792025089263916,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6658585858585858,
+      "grad_norm": 0.009561127051711082,
+      "learning_rate": 2.760339081337041e-05,
+      "loss": 0.4722686767578125,
+      "step": 2060
+    },
+    {
+      "epoch": 0.6690909090909091,
+      "grad_norm": 0.00924921128898859,
+      "learning_rate": 2.7126830509449773e-05,
+      "loss": 0.4884464263916016,
+      "step": 2070
+    },
+    {
+      "epoch": 0.6723232323232323,
+      "grad_norm": 0.00991444569081068,
+      "learning_rate": 2.6652883707224075e-05,
+      "loss": 0.4804549217224121,
+      "step": 2080
+    },
+    {
+      "epoch": 0.6755555555555556,
+      "grad_norm": 0.009902069345116615,
+      "learning_rate": 2.618160456013153e-05,
+      "loss": 0.4781071186065674,
+      "step": 2090
+    },
+    {
+      "epoch": 0.6787878787878788,
+      "grad_norm": 0.010504493489861488,
+      "learning_rate": 2.571304691680255e-05,
+      "loss": 0.48059587478637694,
+      "step": 2100
+    },
+    {
+      "epoch": 0.682020202020202,
+      "grad_norm": 0.009641965851187706,
+      "learning_rate": 2.5247264314906917e-05,
+      "loss": 0.4706240177154541,
+      "step": 2110
+    },
+    {
+      "epoch": 0.6852525252525252,
+      "grad_norm": 0.010276644490659237,
+      "learning_rate": 2.4784309975036513e-05,
+      "loss": 0.4885101318359375,
+      "step": 2120
+    },
+    {
+      "epoch": 0.6884848484848485,
+      "grad_norm": 0.010960405692458153,
+      "learning_rate": 2.4324236794624456e-05,
+      "loss": 0.4882383346557617,
+      "step": 2130
+    },
+    {
+      "epoch": 0.6917171717171717,
+      "grad_norm": 0.010282796807587147,
+      "learning_rate": 2.386709734190079e-05,
+      "loss": 0.4768857479095459,
+      "step": 2140
+    },
+    {
+      "epoch": 0.694949494949495,
+      "grad_norm": 0.010104385204613209,
+      "learning_rate": 2.34129438498862e-05,
+      "loss": 0.4802837371826172,
+      "step": 2150
+    },
+    {
+      "epoch": 0.6981818181818182,
+      "grad_norm": 0.010027035139501095,
+      "learning_rate": 2.296182821042374e-05,
+      "loss": 0.4874839782714844,
+      "step": 2160
+    },
+    {
+      "epoch": 0.7014141414141414,
+      "grad_norm": 0.010018851608037949,
+      "learning_rate": 2.2513801968249644e-05,
+      "loss": 0.4758561134338379,
+      "step": 2170
+    },
+    {
+      "epoch": 0.7046464646464646,
+      "grad_norm": 0.009862969629466534,
+      "learning_rate": 2.2068916315103783e-05,
+      "loss": 0.4686488151550293,
+      "step": 2180
+    },
+    {
+      "epoch": 0.7078787878787879,
+      "grad_norm": 0.00952910166233778,
+      "learning_rate": 2.162722208388057e-05,
+      "loss": 0.4782154083251953,
+      "step": 2190
+    },
+    {
+      "epoch": 0.7111111111111111,
+      "grad_norm": 0.010213647037744522,
+      "learning_rate": 2.1188769742820625e-05,
+      "loss": 0.4773773193359375,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7143434343434344,
+      "grad_norm": 0.010498392395675182,
+      "learning_rate": 2.075360938974429e-05,
+      "loss": 0.4733907222747803,
+      "step": 2210
+    },
+    {
+      "epoch": 0.7175757575757575,
+      "grad_norm": 0.009394815191626549,
+      "learning_rate": 2.03217907463275e-05,
+      "loss": 0.47564210891723635,
+      "step": 2220
+    },
+    {
+      "epoch": 0.7208080808080808,
+      "grad_norm": 0.010383618995547295,
+      "learning_rate": 1.989336315242048e-05,
+      "loss": 0.4784512519836426,
+      "step": 2230
+    },
+    {
+      "epoch": 0.724040404040404,
+      "grad_norm": 0.01043599285185337,
+      "learning_rate": 1.9468375560410117e-05,
+      "loss": 0.4808964729309082,
+      "step": 2240
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.009953988716006279,
+      "learning_rate": 1.90468765296267e-05,
+      "loss": 0.49031834602355956,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7305050505050505,
+      "grad_norm": 0.010356656275689602,
+      "learning_rate": 1.8628914220795494e-05,
+      "loss": 0.48055601119995117,
+      "step": 2260
+    },
+    {
+      "epoch": 0.7337373737373737,
+      "grad_norm": 0.009841440245509148,
+      "learning_rate": 1.8214536390533822e-05,
+      "loss": 0.47170586585998536,
+      "step": 2270
+    },
+    {
+      "epoch": 0.7369696969696969,
+      "grad_norm": 0.010102550499141216,
+      "learning_rate": 1.7803790385894387e-05,
+      "loss": 0.4660043716430664,
+      "step": 2280
+    },
+    {
+      "epoch": 0.7402020202020202,
+      "grad_norm": 0.010421738028526306,
+      "learning_rate": 1.7396723138955428e-05,
+      "loss": 0.4599196434020996,
+      "step": 2290
+    },
+    {
+      "epoch": 0.7434343434343434,
+      "grad_norm": 0.009896540082991123,
+      "learning_rate": 1.699338116145811e-05,
+      "loss": 0.46491589546203616,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.010468855500221252,
+      "learning_rate": 1.6593810539492195e-05,
+      "loss": 0.47761125564575196,
+      "step": 2310
+    },
+    {
+      "epoch": 0.74989898989899,
+      "grad_norm": 0.010416937991976738,
+      "learning_rate": 1.619805692823016e-05,
+      "loss": 0.49956817626953126,
+      "step": 2320
+    },
+    {
+      "epoch": 0.7531313131313131,
+      "grad_norm": 0.010007611475884914,
+      "learning_rate": 1.580616554671057e-05,
+      "loss": 0.4716916084289551,
+      "step": 2330
+    },
+    {
+      "epoch": 0.7563636363636363,
+      "grad_norm": 0.010231648571789265,
+      "learning_rate": 1.5418181172671382e-05,
+      "loss": 0.4909040451049805,
+      "step": 2340
+    },
+    {
+      "epoch": 0.7595959595959596,
+      "grad_norm": 0.010324012488126755,
+      "learning_rate": 1.5034148137433623e-05,
+      "loss": 0.47939190864562986,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7628282828282829,
+      "grad_norm": 0.011009547859430313,
+      "learning_rate": 1.4654110320836017e-05,
+      "loss": 0.48291826248168945,
+      "step": 2360
+    },
+    {
+      "epoch": 0.7660606060606061,
+      "grad_norm": 0.010392943397164345,
+      "learning_rate": 1.4278111146221263e-05,
+      "loss": 0.49179973602294924,
+      "step": 2370
+    },
+    {
+      "epoch": 0.7692929292929293,
+      "grad_norm": 0.010355197824537754,
+      "learning_rate": 1.3906193575474508e-05,
+      "loss": 0.4716278076171875,
+      "step": 2380
+    },
+    {
+      "epoch": 0.7725252525252525,
+      "grad_norm": 0.009932084940373898,
+      "learning_rate": 1.3538400104114446e-05,
+      "loss": 0.47190055847167967,
+      "step": 2390
+    },
+    {
+      "epoch": 0.7757575757575758,
+      "grad_norm": 0.010710643604397774,
+      "learning_rate": 1.3174772756437742e-05,
+      "loss": 0.4703176498413086,
+      "step": 2400
+    },
+    {
+      "epoch": 0.778989898989899,
+      "grad_norm": 0.010614068247377872,
+      "learning_rate": 1.2815353080717379e-05,
+      "loss": 0.47541141510009766,
+      "step": 2410
+    },
+    {
+      "epoch": 0.7822222222222223,
+      "grad_norm": 0.011346950195729733,
+      "learning_rate": 1.246018214445525e-05,
+      "loss": 0.4860015869140625,
+      "step": 2420
+    },
+    {
+      "epoch": 0.7854545454545454,
+      "grad_norm": 0.009824907407164574,
+      "learning_rate": 1.210930052968981e-05,
+      "loss": 0.49062480926513674,
+      "step": 2430
+    },
+    {
+      "epoch": 0.7886868686868687,
+      "grad_norm": 0.010624224320054054,
+      "learning_rate": 1.1762748328359152e-05,
+      "loss": 0.4694485664367676,
+      "step": 2440
+    },
+    {
+      "epoch": 0.7919191919191919,
+      "grad_norm": 0.01044746395200491,
+      "learning_rate": 1.1420565137720045e-05,
+      "loss": 0.47275629043579104,
+      "step": 2450
+    },
+    {
+      "epoch": 0.7951515151515152,
+      "grad_norm": 0.010226710699498653,
+      "learning_rate": 1.1082790055823533e-05,
+      "loss": 0.4670067310333252,
+      "step": 2460
+    },
+    {
+      "epoch": 0.7983838383838384,
+      "grad_norm": 0.010427460074424744,
+      "learning_rate": 1.0749461677047624e-05,
+      "loss": 0.4700475692749023,
+      "step": 2470
+    },
+    {
+      "epoch": 0.8016161616161617,
+      "grad_norm": 0.010494428686797619,
+      "learning_rate": 1.0420618087687418e-05,
+      "loss": 0.46589016914367676,
+      "step": 2480
+    },
+    {
+      "epoch": 0.8048484848484848,
+      "grad_norm": 0.010100893676280975,
+      "learning_rate": 1.0096296861603321e-05,
+      "loss": 0.4704419136047363,
+      "step": 2490
+    },
+    {
+      "epoch": 0.8080808080808081,
+      "grad_norm": 0.010682797059416771,
+      "learning_rate": 9.776535055927931e-06,
+      "loss": 0.47326183319091797,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8113131313131313,
+      "grad_norm": 0.00972407590597868,
+      "learning_rate": 9.461369206831772e-06,
+      "loss": 0.48441619873046876,
+      "step": 2510
+    },
+    {
+      "epoch": 0.8145454545454546,
+      "grad_norm": 0.010327558033168316,
+      "learning_rate": 9.150835325348678e-06,
+      "loss": 0.45856351852416993,
+      "step": 2520
+    },
+    {
+      "epoch": 0.8177777777777778,
+      "grad_norm": 0.010118944570422173,
+      "learning_rate": 8.844968893261197e-06,
+      "loss": 0.48114948272705077,
+      "step": 2530
+    },
+    {
+      "epoch": 0.821010101010101,
+      "grad_norm": 0.010876161977648735,
+      "learning_rate": 8.543804859046345e-06,
+      "loss": 0.4930680274963379,
+      "step": 2540
+    },
+    {
+      "epoch": 0.8242424242424242,
+      "grad_norm": 0.010722608305513859,
+      "learning_rate": 8.247377633882463e-06,
+      "loss": 0.46875743865966796,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8274747474747475,
+      "grad_norm": 0.01088438369333744,
+      "learning_rate": 7.95572108771726e-06,
+      "loss": 0.4768000602722168,
+      "step": 2560
+    },
+    {
+      "epoch": 0.8307070707070707,
+      "grad_norm": 0.01026720181107521,
+      "learning_rate": 7.66886854539795e-06,
+      "loss": 0.479974365234375,
+      "step": 2570
+    },
+    {
+      "epoch": 0.833939393939394,
+      "grad_norm": 0.009710075333714485,
+      "learning_rate": 7.386852782863407e-06,
+      "loss": 0.4684715270996094,
+      "step": 2580
+    },
+    {
+      "epoch": 0.8371717171717171,
+      "grad_norm": 0.009966167621314526,
+      "learning_rate": 7.109706023399232e-06,
+      "loss": 0.47191972732543946,
+      "step": 2590
+    },
+    {
+      "epoch": 0.8404040404040404,
+      "grad_norm": 0.010125650092959404,
+      "learning_rate": 6.837459933955936e-06,
+      "loss": 0.4766803741455078,
+      "step": 2600
+    },
+    {
+      "epoch": 0.8436363636363636,
+      "grad_norm": 0.009984518401324749,
+      "learning_rate": 6.5701456215305656e-06,
+      "loss": 0.4592133045196533,
+      "step": 2610
+    },
+    {
+      "epoch": 0.8468686868686869,
+      "grad_norm": 0.010836348868906498,
+      "learning_rate": 6.307793629612452e-06,
+      "loss": 0.4658504009246826,
+      "step": 2620
+    },
+    {
+      "epoch": 0.8501010101010101,
+      "grad_norm": 0.010431919246912003,
+      "learning_rate": 6.050433934693339e-06,
+      "loss": 0.4936856269836426,
+      "step": 2630
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.01049034669995308,
+      "learning_rate": 5.798095942842141e-06,
+      "loss": 0.4765117645263672,
+      "step": 2640
+    },
+    {
+      "epoch": 0.8565656565656565,
+      "grad_norm": 0.009596607647836208,
+      "learning_rate": 5.550808486345072e-06,
+      "loss": 0.47063379287719725,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8597979797979798,
+      "grad_norm": 0.01032214518636465,
+      "learning_rate": 5.308599820411247e-06,
+      "loss": 0.4614537715911865,
+      "step": 2660
+    },
+    {
+      "epoch": 0.863030303030303,
+      "grad_norm": 0.009960100054740906,
+      "learning_rate": 5.071497619944171e-06,
+      "loss": 0.48136143684387206,
+      "step": 2670
+    },
+    {
+      "epoch": 0.8662626262626263,
+      "grad_norm": 0.010326167568564415,
+      "learning_rate": 4.839528976379648e-06,
+      "loss": 0.47299985885620116,
+      "step": 2680
+    },
+    {
+      "epoch": 0.8694949494949495,
+      "grad_norm": 0.010867294855415821,
+      "learning_rate": 4.612720394590286e-06,
+      "loss": 0.4829209327697754,
+      "step": 2690
+    },
+    {
+      "epoch": 0.8727272727272727,
+      "grad_norm": 0.01050047017633915,
+      "learning_rate": 4.391097789856985e-06,
+      "loss": 0.4762550354003906,
+      "step": 2700
+    },
+    {
+      "epoch": 0.8759595959595959,
+      "grad_norm": 0.010378929786384106,
+      "learning_rate": 4.174686484907908e-06,
+      "loss": 0.4898251533508301,
+      "step": 2710
+    },
+    {
+      "epoch": 0.8791919191919192,
+      "grad_norm": 0.01060938648879528,
+      "learning_rate": 3.963511207025078e-06,
+      "loss": 0.47261548042297363,
+      "step": 2720
+    },
+    {
+      "epoch": 0.8824242424242424,
+      "grad_norm": 0.01075353566557169,
+      "learning_rate": 3.7575960852189728e-06,
+      "loss": 0.4839645862579346,
+      "step": 2730
+    },
+    {
+      "epoch": 0.8856565656565657,
+      "grad_norm": 0.010416378267109394,
+      "learning_rate": 3.5569646474715722e-06,
+      "loss": 0.46989760398864744,
+      "step": 2740
+    },
+    {
+      "epoch": 0.8888888888888888,
+      "grad_norm": 0.010806340724229813,
+      "learning_rate": 3.361639818048068e-06,
+      "loss": 0.47272281646728515,
+      "step": 2750
+    },
+    {
+      "epoch": 0.8921212121212121,
+      "grad_norm": 0.009753530845046043,
+      "learning_rate": 3.1716439148774534e-06,
+      "loss": 0.47122917175292967,
+      "step": 2760
+    },
+    {
+      "epoch": 0.8953535353535353,
+      "grad_norm": 0.01022200658917427,
+      "learning_rate": 2.986998647002498e-06,
+      "loss": 0.4727674961090088,
+      "step": 2770
+    },
+    {
+      "epoch": 0.8985858585858586,
+      "grad_norm": 0.010225590318441391,
+      "learning_rate": 2.8077251120992742e-06,
+      "loss": 0.46461896896362304,
+      "step": 2780
+    },
+    {
+      "epoch": 0.9018181818181819,
+      "grad_norm": 0.010752941481769085,
+      "learning_rate": 2.633843794066515e-06,
+      "loss": 0.46602635383605956,
+      "step": 2790
+    },
+    {
+      "epoch": 0.9050505050505051,
+      "grad_norm": 0.011064955033361912,
+      "learning_rate": 2.465374560685091e-06,
+      "loss": 0.4705932140350342,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9082828282828282,
+      "grad_norm": 0.00982996542006731,
+      "learning_rate": 2.302336661347926e-06,
+      "loss": 0.4687389373779297,
+      "step": 2810
+    },
+    {
+      "epoch": 0.9115151515151515,
+      "grad_norm": 0.010190518572926521,
+      "learning_rate": 2.1447487248605513e-06,
+      "loss": 0.4906333923339844,
+      "step": 2820
+    },
+    {
+      "epoch": 0.9147474747474748,
+      "grad_norm": 0.01034579798579216,
+      "learning_rate": 1.9926287573125537e-06,
+      "loss": 0.47768077850341795,
+      "step": 2830
+    },
+    {
+      "epoch": 0.917979797979798,
+      "grad_norm": 0.010615529492497444,
+      "learning_rate": 1.845994140020213e-06,
+      "loss": 0.47643141746520995,
+      "step": 2840
+    },
+    {
+      "epoch": 0.9212121212121213,
+      "grad_norm": 0.010776858776807785,
+      "learning_rate": 1.7048616275404771e-06,
+      "loss": 0.4636590003967285,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9244444444444444,
+      "grad_norm": 0.010271280072629452,
+      "learning_rate": 1.5692473457565748e-06,
+      "loss": 0.4707911014556885,
+      "step": 2860
+    },
+    {
+      "epoch": 0.9276767676767677,
+      "grad_norm": 0.009596684016287327,
+      "learning_rate": 1.439166790035501e-06,
+      "loss": 0.45751228332519533,
+      "step": 2870
+    },
+    {
+      "epoch": 0.9309090909090909,
+      "grad_norm": 0.009914812631905079,
+      "learning_rate": 1.3146348234574724e-06,
+      "loss": 0.4842953681945801,
+      "step": 2880
+    },
+    {
+      "epoch": 0.9341414141414142,
+      "grad_norm": 0.01014726422727108,
+      "learning_rate": 1.1956656751176577e-06,
+      "loss": 0.482682991027832,
+      "step": 2890
+    },
+    {
+      "epoch": 0.9373737373737374,
+      "grad_norm": 0.010660757310688496,
+      "learning_rate": 1.0822729385003727e-06,
+      "loss": 0.48476057052612304,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9406060606060606,
+      "grad_norm": 0.010105855762958527,
+      "learning_rate": 9.744695699258955e-07,
+      "loss": 0.4767448425292969,
+      "step": 2910
+    },
+    {
+      "epoch": 0.9438383838383838,
+      "grad_norm": 0.010221844539046288,
+      "learning_rate": 8.722678870700274e-07,
+      "loss": 0.4663360118865967,
+      "step": 2920
+    },
+    {
+      "epoch": 0.9470707070707071,
+      "grad_norm": 0.011003104969859123,
+      "learning_rate": 7.756795675566919e-07,
+      "loss": 0.48151307106018065,
+      "step": 2930
+    },
+    {
+      "epoch": 0.9503030303030303,
+      "grad_norm": 0.01029619574546814,
+      "learning_rate": 6.847156476236516e-07,
+      "loss": 0.48086977005004883,
+      "step": 2940
+    },
+    {
+      "epoch": 0.9535353535353536,
+      "grad_norm": 0.010033480823040009,
+      "learning_rate": 5.993865208614835e-07,
+      "loss": 0.4648440361022949,
+      "step": 2950
+    },
+    {
+      "epoch": 0.9567676767676768,
+      "grad_norm": 0.010539564304053783,
+      "learning_rate": 5.197019370260125e-07,
+      "loss": 0.46828551292419435,
+      "step": 2960
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.009619071148335934,
+      "learning_rate": 4.4567100092429704e-07,
+      "loss": 0.48481130599975586,
+      "step": 2970
+    },
+    {
+      "epoch": 0.9632323232323232,
+      "grad_norm": 0.010197056457400322,
+      "learning_rate": 3.7730217137428857e-07,
+      "loss": 0.47917518615722654,
+      "step": 2980
+    },
+    {
+      "epoch": 0.9664646464646465,
+      "grad_norm": 0.01057458110153675,
+      "learning_rate": 3.1460326023836083e-07,
+      "loss": 0.48064794540405276,
+      "step": 2990
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.01009963545948267,
+      "learning_rate": 2.575814315306846e-07,
+      "loss": 0.4831876754760742,
+      "step": 3000
+    },
+    {
+      "epoch": 0.972929292929293,
+      "grad_norm": 0.010343736037611961,
+      "learning_rate": 2.0624320059869918e-07,
+      "loss": 0.4821047306060791,
+      "step": 3010
+    },
+    {
+      "epoch": 0.9761616161616161,
+      "grad_norm": 0.010384611785411835,
+      "learning_rate": 1.6059443337861912e-07,
+      "loss": 0.46325201988220216,
+      "step": 3020
+    },
+    {
+      "epoch": 0.9793939393939394,
+      "grad_norm": 0.010477159172296524,
+      "learning_rate": 1.2064034572523142e-07,
+      "loss": 0.4779689788818359,
+      "step": 3030
+    },
+    {
+      "epoch": 0.9826262626262626,
+      "grad_norm": 0.010612626560032368,
+      "learning_rate": 8.638550281591107e-08,
+      "loss": 0.4866930484771729,
+      "step": 3040
+    },
+    {
+      "epoch": 0.9858585858585859,
+      "grad_norm": 0.01027057133615017,
+      "learning_rate": 5.7833818629005054e-08,
+      "loss": 0.48350844383239744,
+      "step": 3050
+    },
+    {
+      "epoch": 0.9890909090909091,
+      "grad_norm": 0.010666116140782833,
+      "learning_rate": 3.498855549660118e-08,
+      "loss": 0.4722591400146484,
+      "step": 3060
+    },
+    {
+      "epoch": 0.9923232323232323,
+      "grad_norm": 0.009852438233792782,
+      "learning_rate": 1.785232373180401e-08,
+      "loss": 0.48914670944213867,
+      "step": 3070
+    },
+    {
+      "epoch": 0.9955555555555555,
+      "grad_norm": 0.010089240968227386,
+      "learning_rate": 6.427081330456774e-09,
+      "loss": 0.4730827331542969,
+      "step": 3080
+    },
+    {
+      "epoch": 0.9987878787878788,
+      "grad_norm": 0.010913597419857979,
+      "learning_rate": 7.141337474148025e-10,
+      "loss": 0.4666846752166748,
+      "step": 3090
+    },
+    {
+      "epoch": 1.0,
+      "step": 3094,
+      "total_flos": 4.3887930550675046e+18,
+      "train_loss": 0.4842414558126453,
+      "train_runtime": 8903.7116,
+      "train_samples_per_second": 22.238,
+      "train_steps_per_second": 0.347
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3094,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.3887930550675046e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}