Upload folder using huggingface_hub

.gitattributes

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

README.md

@@ -0,0 +1,208 @@
+---
+base_model: OpenOneRec/OneReason-0.8B-pretrain-competition
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:/inspire/hdd/global_user/zhengkaipeng-240108120123/models/OneReason-0.8B-pretrain-competition
+- 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 0.19.1

adapter_config.json

@@ -0,0 +1,48 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "/inspire/hdd/global_user/zhengkaipeng-240108120123/models/OneReason-0.8B-pretrain-competition",
+  "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": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.19.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "v_proj",
+    "down_proj",
+    "up_proj",
+    "gate_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbd0a8a1e456b7854eada322ef2e63d9e565a1b71a8521aa7885458a496f439b
+size 40422168

chat_template.jinja

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

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d1d7593e74358c3fad8f191c84094d1fb0c664c1d50c43480f5a8162a843bdd
+size 81070011

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7b10b7ade3ff8a895349c3e5b91887c0c18f8b42a46572846ad87b9ee63eace
+size 15365

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ea959a5645f7c5ebc1b91409d990726497c4b54b72eec3b54167a14df820e35
+size 15365

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d611ef6fbd005d5f7db64937f17b255f2e403642dd46e5a9fb2368f2e34d22ab
+size 15365

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74629a8e6f29096edce05b416b5fa3f86ea6a45228b8aa5d8a5d95faf0d45bb5
+size 15365

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2ebc3788a701ccb3344ba5ca5c755cb3a0d8b55468d8ff372ddfc65e68f526
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd4d15f596979aecbc11ba12668cb21c9fb8452ce1235cd9d7878cc950170421
+size 16016554

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": true,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2239 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1578,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0031685678073510772,
+      "grad_norm": 7.043147563934326,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 2.981099319458008,
+      "step": 5
+    },
+    {
+      "epoch": 0.0063371356147021544,
+      "grad_norm": 3.7476859092712402,
+      "learning_rate": 1.8750000000000002e-05,
+      "loss": 2.8805755615234374,
+      "step": 10
+    },
+    {
+      "epoch": 0.009505703422053232,
+      "grad_norm": 2.1162047386169434,
+      "learning_rate": 2.916666666666667e-05,
+      "loss": 2.704869270324707,
+      "step": 15
+    },
+    {
+      "epoch": 0.012674271229404309,
+      "grad_norm": 1.3651797771453857,
+      "learning_rate": 3.958333333333333e-05,
+      "loss": 2.654892921447754,
+      "step": 20
+    },
+    {
+      "epoch": 0.015842839036755388,
+      "grad_norm": 1.0428181886672974,
+      "learning_rate": 5e-05,
+      "loss": 2.4319393157958986,
+      "step": 25
+    },
+    {
+      "epoch": 0.019011406844106463,
+      "grad_norm": 0.8075228333473206,
+      "learning_rate": 6.041666666666667e-05,
+      "loss": 2.356492042541504,
+      "step": 30
+    },
+    {
+      "epoch": 0.022179974651457542,
+      "grad_norm": 0.8686707615852356,
+      "learning_rate": 7.083333333333334e-05,
+      "loss": 2.2213909149169924,
+      "step": 35
+    },
+    {
+      "epoch": 0.025348542458808618,
+      "grad_norm": 0.6699849963188171,
+      "learning_rate": 8.125000000000001e-05,
+      "loss": 2.1557392120361327,
+      "step": 40
+    },
+    {
+      "epoch": 0.028517110266159697,
+      "grad_norm": 0.7378506660461426,
+      "learning_rate": 9.166666666666667e-05,
+      "loss": 1.993387794494629,
+      "step": 45
+    },
+    {
+      "epoch": 0.031685678073510776,
+      "grad_norm": 0.7126041054725647,
+      "learning_rate": 9.999989459608555e-05,
+      "loss": 2.005228614807129,
+      "step": 50
+    },
+    {
+      "epoch": 0.03485424588086185,
+      "grad_norm": 0.7284029126167297,
+      "learning_rate": 9.999620550574153e-05,
+      "loss": 1.9586082458496095,
+      "step": 55
+    },
+    {
+      "epoch": 0.03802281368821293,
+      "grad_norm": 0.6403422355651855,
+      "learning_rate": 9.998724666406601e-05,
+      "loss": 1.843195915222168,
+      "step": 60
+    },
+    {
+      "epoch": 0.041191381495564006,
+      "grad_norm": 0.8365342020988464,
+      "learning_rate": 9.997301901534797e-05,
+      "loss": 1.8246192932128906,
+      "step": 65
+    },
+    {
+      "epoch": 0.044359949302915085,
+      "grad_norm": 0.704372227191925,
+      "learning_rate": 9.995352405922467e-05,
+      "loss": 1.8255279541015625,
+      "step": 70
+    },
+    {
+      "epoch": 0.04752851711026616,
+      "grad_norm": 0.7694789171218872,
+      "learning_rate": 9.992876385052345e-05,
+      "loss": 1.7635623931884765,
+      "step": 75
+    },
+    {
+      "epoch": 0.050697084917617236,
+      "grad_norm": 0.8334874510765076,
+      "learning_rate": 9.989874099904524e-05,
+      "loss": 1.7773487091064453,
+      "step": 80
+    },
+    {
+      "epoch": 0.053865652724968315,
+      "grad_norm": 0.7224839925765991,
+      "learning_rate": 9.986345866928941e-05,
+      "loss": 1.7267620086669921,
+      "step": 85
+    },
+    {
+      "epoch": 0.057034220532319393,
+      "grad_norm": 0.8135210871696472,
+      "learning_rate": 9.982292058012027e-05,
+      "loss": 1.7537405014038085,
+      "step": 90
+    },
+    {
+      "epoch": 0.060202788339670466,
+      "grad_norm": 0.7969468235969543,
+      "learning_rate": 9.977713100437509e-05,
+      "loss": 1.7349861145019532,
+      "step": 95
+    },
+    {
+      "epoch": 0.06337135614702155,
+      "grad_norm": 0.8676604628562927,
+      "learning_rate": 9.972609476841367e-05,
+      "loss": 1.7168376922607422,
+      "step": 100
+    },
+    {
+      "epoch": 0.06653992395437262,
+      "grad_norm": 0.7579165697097778,
+      "learning_rate": 9.966981725160973e-05,
+      "loss": 1.674065399169922,
+      "step": 105
+    },
+    {
+      "epoch": 0.0697084917617237,
+      "grad_norm": 0.7227125763893127,
+      "learning_rate": 9.960830438578378e-05,
+      "loss": 1.7271408081054687,
+      "step": 110
+    },
+    {
+      "epoch": 0.07287705956907478,
+      "grad_norm": 0.7979081869125366,
+      "learning_rate": 9.954156265457801e-05,
+      "loss": 1.6801246643066405,
+      "step": 115
+    },
+    {
+      "epoch": 0.07604562737642585,
+      "grad_norm": 0.6576427221298218,
+      "learning_rate": 9.946959909277285e-05,
+      "loss": 1.6519655227661132,
+      "step": 120
+    },
+    {
+      "epoch": 0.07921419518377694,
+      "grad_norm": 0.8050142526626587,
+      "learning_rate": 9.939242128554542e-05,
+      "loss": 1.6250421524047851,
+      "step": 125
+    },
+    {
+      "epoch": 0.08238276299112801,
+      "grad_norm": 0.7610289454460144,
+      "learning_rate": 9.931003736767013e-05,
+      "loss": 1.646671676635742,
+      "step": 130
+    },
+    {
+      "epoch": 0.08555133079847908,
+      "grad_norm": 0.7286546230316162,
+      "learning_rate": 9.922245602266118e-05,
+      "loss": 1.6335386276245116,
+      "step": 135
+    },
+    {
+      "epoch": 0.08871989860583017,
+      "grad_norm": 0.8246539235115051,
+      "learning_rate": 9.912968648185734e-05,
+      "loss": 1.6397796630859376,
+      "step": 140
+    },
+    {
+      "epoch": 0.09188846641318124,
+      "grad_norm": 0.8313826322555542,
+      "learning_rate": 9.903173852344889e-05,
+      "loss": 1.6269981384277343,
+      "step": 145
+    },
+    {
+      "epoch": 0.09505703422053231,
+      "grad_norm": 0.8203248977661133,
+      "learning_rate": 9.892862247144701e-05,
+      "loss": 1.5818193435668946,
+      "step": 150
+    },
+    {
+      "epoch": 0.0982256020278834,
+      "grad_norm": 0.8538872599601746,
+      "learning_rate": 9.882034919459555e-05,
+      "loss": 1.5892969131469727,
+      "step": 155
+    },
+    {
+      "epoch": 0.10139416983523447,
+      "grad_norm": 1.470503568649292,
+      "learning_rate": 9.870693010522552e-05,
+      "loss": 1.5248340606689452,
+      "step": 160
+    },
+    {
+      "epoch": 0.10456273764258556,
+      "grad_norm": 0.8072368502616882,
+      "learning_rate": 9.858837715805208e-05,
+      "loss": 1.5973053932189942,
+      "step": 165
+    },
+    {
+      "epoch": 0.10773130544993663,
+      "grad_norm": 0.8948448300361633,
+      "learning_rate": 9.846470284891456e-05,
+      "loss": 1.6363914489746094,
+      "step": 170
+    },
+    {
+      "epoch": 0.1108998732572877,
+      "grad_norm": 0.8655192255973816,
+      "learning_rate": 9.833592021345937e-05,
+      "loss": 1.6859859466552733,
+      "step": 175
+    },
+    {
+      "epoch": 0.11406844106463879,
+      "grad_norm": 0.9880424737930298,
+      "learning_rate": 9.820204282576593e-05,
+      "loss": 1.574641799926758,
+      "step": 180
+    },
+    {
+      "epoch": 0.11723700887198986,
+      "grad_norm": 0.7979195713996887,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 1.593592929840088,
+      "step": 185
+    },
+    {
+      "epoch": 0.12040557667934093,
+      "grad_norm": 0.8876345157623291,
+      "learning_rate": 9.791906077350612e-05,
+      "loss": 1.5453405380249023,
+      "step": 190
+    },
+    {
+      "epoch": 0.12357414448669202,
+      "grad_norm": 0.7818175554275513,
+      "learning_rate": 9.776998593610428e-05,
+      "loss": 1.6270465850830078,
+      "step": 195
+    },
+    {
+      "epoch": 0.1267427122940431,
+      "grad_norm": 0.8810750246047974,
+      "learning_rate": 9.761587599764932e-05,
+      "loss": 1.5692276000976562,
+      "step": 200
+    },
+    {
+      "epoch": 0.12991128010139416,
+      "grad_norm": 0.8968422412872314,
+      "learning_rate": 9.745674720179508e-05,
+      "loss": 1.5278916358947754,
+      "step": 205
+    },
+    {
+      "epoch": 0.13307984790874525,
+      "grad_norm": 0.8381748795509338,
+      "learning_rate": 9.729261632119806e-05,
+      "loss": 1.5704171180725097,
+      "step": 210
+    },
+    {
+      "epoch": 0.13624841571609633,
+      "grad_norm": 1.0442235469818115,
+      "learning_rate": 9.71235006557497e-05,
+      "loss": 1.5022503852844238,
+      "step": 215
+    },
+    {
+      "epoch": 0.1394169835234474,
+      "grad_norm": 0.7912348508834839,
+      "learning_rate": 9.694941803075283e-05,
+      "loss": 1.5598048210144042,
+      "step": 220
+    },
+    {
+      "epoch": 0.14258555133079848,
+      "grad_norm": 0.8984694480895996,
+      "learning_rate": 9.677038679504285e-05,
+      "loss": 1.6556865692138671,
+      "step": 225
+    },
+    {
+      "epoch": 0.14575411913814956,
+      "grad_norm": 0.9488692879676819,
+      "learning_rate": 9.658642581905366e-05,
+      "loss": 1.6171920776367188,
+      "step": 230
+    },
+    {
+      "epoch": 0.14892268694550062,
+      "grad_norm": 0.8743675947189331,
+      "learning_rate": 9.639755449282875e-05,
+      "loss": 1.5999393463134766,
+      "step": 235
+    },
+    {
+      "epoch": 0.1520912547528517,
+      "grad_norm": 1.178044080734253,
+      "learning_rate": 9.620379272397735e-05,
+      "loss": 1.5196931838989258,
+      "step": 240
+    },
+    {
+      "epoch": 0.1552598225602028,
+      "grad_norm": 0.863906741142273,
+      "learning_rate": 9.600516093557617e-05,
+      "loss": 1.5039121627807617,
+      "step": 245
+    },
+    {
+      "epoch": 0.15842839036755388,
+      "grad_norm": 1.0000500679016113,
+      "learning_rate": 9.580168006401668e-05,
+      "loss": 1.4933100700378419,
+      "step": 250
+    },
+    {
+      "epoch": 0.16159695817490494,
+      "grad_norm": 0.8667544722557068,
+      "learning_rate": 9.559337155679842e-05,
+      "loss": 1.5648080825805664,
+      "step": 255
+    },
+    {
+      "epoch": 0.16476552598225602,
+      "grad_norm": 0.8225997090339661,
+      "learning_rate": 9.538025737026832e-05,
+      "loss": 1.4912095069885254,
+      "step": 260
+    },
+    {
+      "epoch": 0.1679340937896071,
+      "grad_norm": 0.8068106174468994,
+      "learning_rate": 9.516235996730645e-05,
+      "loss": 1.4858381271362304,
+      "step": 265
+    },
+    {
+      "epoch": 0.17110266159695817,
+      "grad_norm": 0.9467447400093079,
+      "learning_rate": 9.493970231495835e-05,
+      "loss": 1.524880313873291,
+      "step": 270
+    },
+    {
+      "epoch": 0.17427122940430925,
+      "grad_norm": 0.8453680276870728,
+      "learning_rate": 9.471230788201429e-05,
+      "loss": 1.5124773979187012,
+      "step": 275
+    },
+    {
+      "epoch": 0.17743979721166034,
+      "grad_norm": 0.9061563014984131,
+      "learning_rate": 9.448020063653549e-05,
+      "loss": 1.49342622756958,
+      "step": 280
+    },
+    {
+      "epoch": 0.1806083650190114,
+      "grad_norm": 0.8865219950675964,
+      "learning_rate": 9.424340504332791e-05,
+      "loss": 1.4923158645629884,
+      "step": 285
+    },
+    {
+      "epoch": 0.18377693282636248,
+      "grad_norm": 0.9014965295791626,
+      "learning_rate": 9.400194606136354e-05,
+      "loss": 1.523708438873291,
+      "step": 290
+    },
+    {
+      "epoch": 0.18694550063371357,
+      "grad_norm": 0.8378658890724182,
+      "learning_rate": 9.375584914114963e-05,
+      "loss": 1.5758267402648927,
+      "step": 295
+    },
+    {
+      "epoch": 0.19011406844106463,
+      "grad_norm": 0.8867623805999756,
+      "learning_rate": 9.350514022204622e-05,
+      "loss": 1.5432629585266113,
+      "step": 300
+    },
+    {
+      "epoch": 0.1932826362484157,
+      "grad_norm": 0.995186448097229,
+      "learning_rate": 9.32498457295319e-05,
+      "loss": 1.5024199485778809,
+      "step": 305
+    },
+    {
+      "epoch": 0.1964512040557668,
+      "grad_norm": 0.894067108631134,
+      "learning_rate": 9.298999257241863e-05,
+      "loss": 1.4737892150878906,
+      "step": 310
+    },
+    {
+      "epoch": 0.19961977186311788,
+      "grad_norm": 0.9223262667655945,
+      "learning_rate": 9.272560814001539e-05,
+      "loss": 1.5003498077392579,
+      "step": 315
+    },
+    {
+      "epoch": 0.20278833967046894,
+      "grad_norm": 1.0859758853912354,
+      "learning_rate": 9.245672029924128e-05,
+      "loss": 1.4052498817443848,
+      "step": 320
+    },
+    {
+      "epoch": 0.20595690747782003,
+      "grad_norm": 0.8554385900497437,
+      "learning_rate": 9.218335739168833e-05,
+      "loss": 1.4594630241394042,
+      "step": 325
+    },
+    {
+      "epoch": 0.20912547528517111,
+      "grad_norm": 0.9641969203948975,
+      "learning_rate": 9.190554823063403e-05,
+      "loss": 1.5072848320007324,
+      "step": 330
+    },
+    {
+      "epoch": 0.21229404309252217,
+      "grad_norm": 1.013372778892517,
+      "learning_rate": 9.162332209800455e-05,
+      "loss": 1.466813850402832,
+      "step": 335
+    },
+    {
+      "epoch": 0.21546261089987326,
+      "grad_norm": 0.886248767375946,
+      "learning_rate": 9.133670874128817e-05,
+      "loss": 1.4878669738769532,
+      "step": 340
+    },
+    {
+      "epoch": 0.21863117870722434,
+      "grad_norm": 0.9179723262786865,
+      "learning_rate": 9.104573837039992e-05,
+      "loss": 1.4538299560546875,
+      "step": 345
+    },
+    {
+      "epoch": 0.2217997465145754,
+      "grad_norm": 0.8039515018463135,
+      "learning_rate": 9.075044165449719e-05,
+      "loss": 1.4979578971862793,
+      "step": 350
+    },
+    {
+      "epoch": 0.2249683143219265,
+      "grad_norm": 1.012426733970642,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 1.4779088973999024,
+      "step": 355
+    },
+    {
+      "epoch": 0.22813688212927757,
+      "grad_norm": 0.986335813999176,
+      "learning_rate": 9.014699414104692e-05,
+      "loss": 1.465938186645508,
+      "step": 360
+    },
+    {
+      "epoch": 0.23130544993662863,
+      "grad_norm": 0.9080740809440613,
+      "learning_rate": 8.983890694869312e-05,
+      "loss": 1.4629207611083985,
+      "step": 365
+    },
+    {
+      "epoch": 0.23447401774397972,
+      "grad_norm": 0.934339702129364,
+      "learning_rate": 8.952662061500817e-05,
+      "loss": 1.457223892211914,
+      "step": 370
+    },
+    {
+      "epoch": 0.2376425855513308,
+      "grad_norm": 0.8736027479171753,
+      "learning_rate": 8.921016805591654e-05,
+      "loss": 1.4560219764709472,
+      "step": 375
+    },
+    {
+      "epoch": 0.24081115335868186,
+      "grad_norm": 0.9550614356994629,
+      "learning_rate": 8.88895826264754e-05,
+      "loss": 1.5248393058776855,
+      "step": 380
+    },
+    {
+      "epoch": 0.24397972116603295,
+      "grad_norm": 0.9169988036155701,
+      "learning_rate": 8.856489811735903e-05,
+      "loss": 1.5106586456298827,
+      "step": 385
+    },
+    {
+      "epoch": 0.24714828897338403,
+      "grad_norm": 0.8996412754058838,
+      "learning_rate": 8.823614875129706e-05,
+      "loss": 1.4565364837646484,
+      "step": 390
+    },
+    {
+      "epoch": 0.2503168567807351,
+      "grad_norm": 0.8500154614448547,
+      "learning_rate": 8.790336917946737e-05,
+      "loss": 1.4416918754577637,
+      "step": 395
+    },
+    {
+      "epoch": 0.2534854245880862,
+      "grad_norm": 0.7929876446723938,
+      "learning_rate": 8.756659447784368e-05,
+      "loss": 1.4593412399291992,
+      "step": 400
+    },
+    {
+      "epoch": 0.25665399239543724,
+      "grad_norm": 1.167829155921936,
+      "learning_rate": 8.72258601434985e-05,
+      "loss": 1.4202542304992676,
+      "step": 405
+    },
+    {
+      "epoch": 0.2598225602027883,
+      "grad_norm": 0.8008830547332764,
+      "learning_rate": 8.688120209086165e-05,
+      "loss": 1.4504500389099122,
+      "step": 410
+    },
+    {
+      "epoch": 0.2629911280101394,
+      "grad_norm": 0.936578094959259,
+      "learning_rate": 8.653265664793467e-05,
+      "loss": 1.4489995956420898,
+      "step": 415
+    },
+    {
+      "epoch": 0.2661596958174905,
+      "grad_norm": 0.9912587404251099,
+      "learning_rate": 8.618026055246183e-05,
+      "loss": 1.4207334518432617,
+      "step": 420
+    },
+    {
+      "epoch": 0.2693282636248416,
+      "grad_norm": 1.0229488611221313,
+      "learning_rate": 8.58240509480578e-05,
+      "loss": 1.5463509559631348,
+      "step": 425
+    },
+    {
+      "epoch": 0.27249683143219267,
+      "grad_norm": 0.8335016965866089,
+      "learning_rate": 8.546406538029269e-05,
+      "loss": 1.4976566314697266,
+      "step": 430
+    },
+    {
+      "epoch": 0.27566539923954375,
+      "grad_norm": 1.0242607593536377,
+      "learning_rate": 8.510034179273449e-05,
+      "loss": 1.4665711402893067,
+      "step": 435
+    },
+    {
+      "epoch": 0.2788339670468948,
+      "grad_norm": 0.833751380443573,
+      "learning_rate": 8.473291852294987e-05,
+      "loss": 1.5367077827453612,
+      "step": 440
+    },
+    {
+      "epoch": 0.28200253485424587,
+      "grad_norm": 0.9694119691848755,
+      "learning_rate": 8.436183429846313e-05,
+      "loss": 1.420050811767578,
+      "step": 445
+    },
+    {
+      "epoch": 0.28517110266159695,
+      "grad_norm": 0.9861839413642883,
+      "learning_rate": 8.398712823267434e-05,
+      "loss": 1.3972441673278808,
+      "step": 450
+    },
+    {
+      "epoch": 0.28833967046894804,
+      "grad_norm": 0.7589554190635681,
+      "learning_rate": 8.360883982073653e-05,
+      "loss": 1.4342703819274902,
+      "step": 455
+    },
+    {
+      "epoch": 0.2915082382762991,
+      "grad_norm": 1.1326944828033447,
+      "learning_rate": 8.32270089353929e-05,
+      "loss": 1.4997499465942383,
+      "step": 460
+    },
+    {
+      "epoch": 0.2946768060836502,
+      "grad_norm": 0.9897761940956116,
+      "learning_rate": 8.284167582277406e-05,
+      "loss": 1.366450881958008,
+      "step": 465
+    },
+    {
+      "epoch": 0.29784537389100124,
+      "grad_norm": 0.9775916337966919,
+      "learning_rate": 8.245288109815596e-05,
+      "loss": 1.407801628112793,
+      "step": 470
+    },
+    {
+      "epoch": 0.3010139416983523,
+      "grad_norm": 0.8449367880821228,
+      "learning_rate": 8.206066574167892e-05,
+      "loss": 1.4435958862304688,
+      "step": 475
+    },
+    {
+      "epoch": 0.3041825095057034,
+      "grad_norm": 0.9615752100944519,
+      "learning_rate": 8.166507109402825e-05,
+      "loss": 1.4394434928894042,
+      "step": 480
+    },
+    {
+      "epoch": 0.3073510773130545,
+      "grad_norm": 0.8721709251403809,
+      "learning_rate": 8.12661388520767e-05,
+      "loss": 1.544541358947754,
+      "step": 485
+    },
+    {
+      "epoch": 0.3105196451204056,
+      "grad_norm": 0.8040366768836975,
+      "learning_rate": 8.086391106448965e-05,
+      "loss": 1.4437169075012206,
+      "step": 490
+    },
+    {
+      "epoch": 0.31368821292775667,
+      "grad_norm": 0.9599743485450745,
+      "learning_rate": 8.045843012729288e-05,
+      "loss": 1.4029827117919922,
+      "step": 495
+    },
+    {
+      "epoch": 0.31685678073510776,
+      "grad_norm": 0.973711371421814,
+      "learning_rate": 8.004973877940405e-05,
+      "loss": 1.432126808166504,
+      "step": 500
+    },
+    {
+      "epoch": 0.3200253485424588,
+      "grad_norm": 1.2315587997436523,
+      "learning_rate": 7.963788009812775e-05,
+      "loss": 1.4067696571350097,
+      "step": 505
+    },
+    {
+      "epoch": 0.3231939163498099,
+      "grad_norm": 0.9294511079788208,
+      "learning_rate": 7.922289749461516e-05,
+      "loss": 1.3776613235473634,
+      "step": 510
+    },
+    {
+      "epoch": 0.32636248415716096,
+      "grad_norm": 0.967047929763794,
+      "learning_rate": 7.880483470928823e-05,
+      "loss": 1.3882503509521484,
+      "step": 515
+    },
+    {
+      "epoch": 0.32953105196451205,
+      "grad_norm": 0.8325267434120178,
+      "learning_rate": 7.83837358072295e-05,
+      "loss": 1.4678791999816894,
+      "step": 520
+    },
+    {
+      "epoch": 0.33269961977186313,
+      "grad_norm": 1.0061659812927246,
+      "learning_rate": 7.795964517353735e-05,
+      "loss": 1.4159486770629883,
+      "step": 525
+    },
+    {
+      "epoch": 0.3358681875792142,
+      "grad_norm": 1.040426254272461,
+      "learning_rate": 7.753260750864768e-05,
+      "loss": 1.4096446990966798,
+      "step": 530
+    },
+    {
+      "epoch": 0.33903675538656525,
+      "grad_norm": 0.9612278342247009,
+      "learning_rate": 7.710266782362247e-05,
+      "loss": 1.4248369216918946,
+      "step": 535
+    },
+    {
+      "epoch": 0.34220532319391633,
+      "grad_norm": 0.9438225626945496,
+      "learning_rate": 7.666987143540536e-05,
+      "loss": 1.4191057205200195,
+      "step": 540
+    },
+    {
+      "epoch": 0.3453738910012674,
+      "grad_norm": 0.8708591461181641,
+      "learning_rate": 7.623426396204516e-05,
+      "loss": 1.4026036262512207,
+      "step": 545
+    },
+    {
+      "epoch": 0.3485424588086185,
+      "grad_norm": 0.8831802010536194,
+      "learning_rate": 7.579589131788755e-05,
+      "loss": 1.3681581497192383,
+      "step": 550
+    },
+    {
+      "epoch": 0.3517110266159696,
+      "grad_norm": 0.8993585705757141,
+      "learning_rate": 7.535479970873562e-05,
+      "loss": 1.421323871612549,
+      "step": 555
+    },
+    {
+      "epoch": 0.3548795944233207,
+      "grad_norm": 0.9270035624504089,
+      "learning_rate": 7.491103562697953e-05,
+      "loss": 1.4405481338500976,
+      "step": 560
+    },
+    {
+      "epoch": 0.35804816223067176,
+      "grad_norm": 0.7752518057823181,
+      "learning_rate": 7.446464584669618e-05,
+      "loss": 1.4336222648620605,
+      "step": 565
+    },
+    {
+      "epoch": 0.3612167300380228,
+      "grad_norm": 0.8551792502403259,
+      "learning_rate": 7.401567741871905e-05,
+      "loss": 1.4587442398071289,
+      "step": 570
+    },
+    {
+      "epoch": 0.3643852978453739,
+      "grad_norm": 1.0400238037109375,
+      "learning_rate": 7.356417766567887e-05,
+      "loss": 1.3435915946960448,
+      "step": 575
+    },
+    {
+      "epoch": 0.36755386565272496,
+      "grad_norm": 1.0843302011489868,
+      "learning_rate": 7.311019417701566e-05,
+      "loss": 1.388375473022461,
+      "step": 580
+    },
+    {
+      "epoch": 0.37072243346007605,
+      "grad_norm": 1.1198105812072754,
+      "learning_rate": 7.265377480396277e-05,
+      "loss": 1.364163303375244,
+      "step": 585
+    },
+    {
+      "epoch": 0.37389100126742714,
+      "grad_norm": 0.9389685392379761,
+      "learning_rate": 7.219496765450304e-05,
+      "loss": 1.4237895965576173,
+      "step": 590
+    },
+    {
+      "epoch": 0.3770595690747782,
+      "grad_norm": 0.8364915251731873,
+      "learning_rate": 7.173382108829826e-05,
+      "loss": 1.4080724716186523,
+      "step": 595
+    },
+    {
+      "epoch": 0.38022813688212925,
+      "grad_norm": 0.9814357161521912,
+      "learning_rate": 7.127038371159174e-05,
+      "loss": 1.3742491722106933,
+      "step": 600
+    },
+    {
+      "epoch": 0.38339670468948034,
+      "grad_norm": 0.8945198655128479,
+      "learning_rate": 7.08047043720852e-05,
+      "loss": 1.3940475463867188,
+      "step": 605
+    },
+    {
+      "epoch": 0.3865652724968314,
+      "grad_norm": 0.9399378895759583,
+      "learning_rate": 7.033683215379002e-05,
+      "loss": 1.427070426940918,
+      "step": 610
+    },
+    {
+      "epoch": 0.3897338403041825,
+      "grad_norm": 0.8892331719398499,
+      "learning_rate": 6.986681637185361e-05,
+      "loss": 1.3754430770874024,
+      "step": 615
+    },
+    {
+      "epoch": 0.3929024081115336,
+      "grad_norm": 1.1722021102905273,
+      "learning_rate": 6.939470656736148e-05,
+      "loss": 1.3428964614868164,
+      "step": 620
+    },
+    {
+      "epoch": 0.3960709759188847,
+      "grad_norm": 0.9018204212188721,
+      "learning_rate": 6.892055250211552e-05,
+      "loss": 1.416018009185791,
+      "step": 625
+    },
+    {
+      "epoch": 0.39923954372623577,
+      "grad_norm": 0.8684733510017395,
+      "learning_rate": 6.844440415338879e-05,
+      "loss": 1.4170392990112304,
+      "step": 630
+    },
+    {
+      "epoch": 0.4024081115335868,
+      "grad_norm": 1.0637812614440918,
+      "learning_rate": 6.796631170865789e-05,
+      "loss": 1.412844181060791,
+      "step": 635
+    },
+    {
+      "epoch": 0.4055766793409379,
+      "grad_norm": 1.0007359981536865,
+      "learning_rate": 6.748632556031305e-05,
+      "loss": 1.4430639266967773,
+      "step": 640
+    },
+    {
+      "epoch": 0.40874524714828897,
+      "grad_norm": 0.9914920330047607,
+      "learning_rate": 6.700449630034662e-05,
+      "loss": 1.3914289474487305,
+      "step": 645
+    },
+    {
+      "epoch": 0.41191381495564006,
+      "grad_norm": 1.1350955963134766,
+      "learning_rate": 6.65208747150204e-05,
+      "loss": 1.3682466506958009,
+      "step": 650
+    },
+    {
+      "epoch": 0.41508238276299114,
+      "grad_norm": 1.0775210857391357,
+      "learning_rate": 6.603551177951276e-05,
+      "loss": 1.391181755065918,
+      "step": 655
+    },
+    {
+      "epoch": 0.41825095057034223,
+      "grad_norm": 1.0117769241333008,
+      "learning_rate": 6.554845865254565e-05,
+      "loss": 1.3873372077941895,
+      "step": 660
+    },
+    {
+      "epoch": 0.42141951837769326,
+      "grad_norm": 0.9027493596076965,
+      "learning_rate": 6.505976667099233e-05,
+      "loss": 1.4179336547851562,
+      "step": 665
+    },
+    {
+      "epoch": 0.42458808618504434,
+      "grad_norm": 0.8727158904075623,
+      "learning_rate": 6.456948734446624e-05,
+      "loss": 1.3837886810302735,
+      "step": 670
+    },
+    {
+      "epoch": 0.42775665399239543,
+      "grad_norm": 1.070072889328003,
+      "learning_rate": 6.407767234989182e-05,
+      "loss": 1.4333530426025392,
+      "step": 675
+    },
+    {
+      "epoch": 0.4309252217997465,
+      "grad_norm": 1.224215030670166,
+      "learning_rate": 6.358437352605754e-05,
+      "loss": 1.3491156578063965,
+      "step": 680
+    },
+    {
+      "epoch": 0.4340937896070976,
+      "grad_norm": 1.051694393157959,
+      "learning_rate": 6.308964286815203e-05,
+      "loss": 1.3815348625183106,
+      "step": 685
+    },
+    {
+      "epoch": 0.4372623574144487,
+      "grad_norm": 0.849431574344635,
+      "learning_rate": 6.259353252228346e-05,
+      "loss": 1.4776974678039552,
+      "step": 690
+    },
+    {
+      "epoch": 0.4404309252217998,
+      "grad_norm": 0.8869721293449402,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 1.4064318656921386,
+      "step": 695
+    },
+    {
+      "epoch": 0.4435994930291508,
+      "grad_norm": 1.0174022912979126,
+      "learning_rate": 6.159738207269491e-05,
+      "loss": 1.4444948196411134,
+      "step": 700
+    },
+    {
+      "epoch": 0.4467680608365019,
+      "grad_norm": 0.86573326587677,
+      "learning_rate": 6.109744696624631e-05,
+      "loss": 1.4351720809936523,
+      "step": 705
+    },
+    {
+      "epoch": 0.449936628643853,
+      "grad_norm": 0.9726159572601318,
+      "learning_rate": 6.0596342155310426e-05,
+      "loss": 1.337043571472168,
+      "step": 710
+    },
+    {
+      "epoch": 0.45310519645120406,
+      "grad_norm": 1.0437583923339844,
+      "learning_rate": 6.009412045785051e-05,
+      "loss": 1.4287454605102539,
+      "step": 715
+    },
+    {
+      "epoch": 0.45627376425855515,
+      "grad_norm": 0.8963989615440369,
+      "learning_rate": 5.959083480955303e-05,
+      "loss": 1.365916633605957,
+      "step": 720
+    },
+    {
+      "epoch": 0.45944233206590623,
+      "grad_norm": 1.2865248918533325,
+      "learning_rate": 5.908653825824808e-05,
+      "loss": 1.3705638885498046,
+      "step": 725
+    },
+    {
+      "epoch": 0.46261089987325726,
+      "grad_norm": 0.8341432213783264,
+      "learning_rate": 5.858128395831799e-05,
+      "loss": 1.4411558151245116,
+      "step": 730
+    },
+    {
+      "epoch": 0.46577946768060835,
+      "grad_norm": 0.9079269766807556,
+      "learning_rate": 5.807512516509468e-05,
+      "loss": 1.4041607856750489,
+      "step": 735
+    },
+    {
+      "epoch": 0.46894803548795944,
+      "grad_norm": 1.1083649396896362,
+      "learning_rate": 5.7568115229246455e-05,
+      "loss": 1.3649417877197265,
+      "step": 740
+    },
+    {
+      "epoch": 0.4721166032953105,
+      "grad_norm": 1.0868420600891113,
+      "learning_rate": 5.706030759115457e-05,
+      "loss": 1.3609169960021972,
+      "step": 745
+    },
+    {
+      "epoch": 0.4752851711026616,
+      "grad_norm": 1.1324069499969482,
+      "learning_rate": 5.6551755775280535e-05,
+      "loss": 1.3742989540100097,
+      "step": 750
+    },
+    {
+      "epoch": 0.4784537389100127,
+      "grad_norm": 0.8875950574874878,
+      "learning_rate": 5.604251338452443e-05,
+      "loss": 1.3568942070007324,
+      "step": 755
+    },
+    {
+      "epoch": 0.4816223067173637,
+      "grad_norm": 0.85218745470047,
+      "learning_rate": 5.553263409457504e-05,
+      "loss": 1.4398767471313476,
+      "step": 760
+    },
+    {
+      "epoch": 0.4847908745247148,
+      "grad_norm": 1.0838654041290283,
+      "learning_rate": 5.502217164825226e-05,
+      "loss": 1.3630851745605468,
+      "step": 765
+    },
+    {
+      "epoch": 0.4879594423320659,
+      "grad_norm": 0.9310572743415833,
+      "learning_rate": 5.4511179849842396e-05,
+      "loss": 1.4191320419311524,
+      "step": 770
+    },
+    {
+      "epoch": 0.491128010139417,
+      "grad_norm": 1.1072568893432617,
+      "learning_rate": 5.399971255942709e-05,
+      "loss": 1.332352352142334,
+      "step": 775
+    },
+    {
+      "epoch": 0.49429657794676807,
+      "grad_norm": 1.0503177642822266,
+      "learning_rate": 5.348782368720626e-05,
+      "loss": 1.3583803176879883,
+      "step": 780
+    },
+    {
+      "epoch": 0.49746514575411915,
+      "grad_norm": 0.9713006615638733,
+      "learning_rate": 5.297556718781588e-05,
+      "loss": 1.4059024810791017,
+      "step": 785
+    },
+    {
+      "epoch": 0.5006337135614702,
+      "grad_norm": 0.8210018873214722,
+      "learning_rate": 5.246299705464085e-05,
+      "loss": 1.375057315826416,
+      "step": 790
+    },
+    {
+      "epoch": 0.5038022813688213,
+      "grad_norm": 0.9948434829711914,
+      "learning_rate": 5.1950167314124085e-05,
+      "loss": 1.362550926208496,
+      "step": 795
+    },
+    {
+      "epoch": 0.5069708491761724,
+      "grad_norm": 1.2584747076034546,
+      "learning_rate": 5.1437132020071886e-05,
+      "loss": 1.37750301361084,
+      "step": 800
+    },
+    {
+      "epoch": 0.5101394169835235,
+      "grad_norm": 0.8576092720031738,
+      "learning_rate": 5.092394524795649e-05,
+      "loss": 1.3371183395385742,
+      "step": 805
+    },
+    {
+      "epoch": 0.5133079847908745,
+      "grad_norm": 0.9512493014335632,
+      "learning_rate": 5.041066108921645e-05,
+      "loss": 1.503910732269287,
+      "step": 810
+    },
+    {
+      "epoch": 0.5164765525982256,
+      "grad_norm": 1.3466845750808716,
+      "learning_rate": 4.9897333645555066e-05,
+      "loss": 1.3664363861083983,
+      "step": 815
+    },
+    {
+      "epoch": 0.5196451204055766,
+      "grad_norm": 0.8851462602615356,
+      "learning_rate": 4.9384017023238085e-05,
+      "loss": 1.3612781524658204,
+      "step": 820
+    },
+    {
+      "epoch": 0.5228136882129277,
+      "grad_norm": 1.0494959354400635,
+      "learning_rate": 4.8870765327390605e-05,
+      "loss": 1.3557121276855468,
+      "step": 825
+    },
+    {
+      "epoch": 0.5259822560202788,
+      "grad_norm": 1.1948227882385254,
+      "learning_rate": 4.835763265629428e-05,
+      "loss": 1.3239543914794922,
+      "step": 830
+    },
+    {
+      "epoch": 0.5291508238276299,
+      "grad_norm": 0.8744856119155884,
+      "learning_rate": 4.784467309568523e-05,
+      "loss": 1.3509840011596679,
+      "step": 835
+    },
+    {
+      "epoch": 0.532319391634981,
+      "grad_norm": 1.2883540391921997,
+      "learning_rate": 4.733194071305315e-05,
+      "loss": 1.3368789672851562,
+      "step": 840
+    },
+    {
+      "epoch": 0.5354879594423321,
+      "grad_norm": 1.0098083019256592,
+      "learning_rate": 4.681948955194255e-05,
+      "loss": 1.3610082626342774,
+      "step": 845
+    },
+    {
+      "epoch": 0.5386565272496832,
+      "grad_norm": 0.8575060367584229,
+      "learning_rate": 4.6307373626256306e-05,
+      "loss": 1.4005903244018554,
+      "step": 850
+    },
+    {
+      "epoch": 0.5418250950570342,
+      "grad_norm": 0.9120677709579468,
+      "learning_rate": 4.579564691456245e-05,
+      "loss": 1.361180877685547,
+      "step": 855
+    },
+    {
+      "epoch": 0.5449936628643853,
+      "grad_norm": 0.8237045407295227,
+      "learning_rate": 4.528436335440473e-05,
+      "loss": 1.3133733749389649,
+      "step": 860
+    },
+    {
+      "epoch": 0.5481622306717364,
+      "grad_norm": 0.9122887253761292,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.3374805450439453,
+      "step": 865
+    },
+    {
+      "epoch": 0.5513307984790875,
+      "grad_norm": 0.8085625767707825,
+      "learning_rate": 4.4263341199644696e-05,
+      "loss": 1.3378860473632812,
+      "step": 870
+    },
+    {
+      "epoch": 0.5544993662864385,
+      "grad_norm": 0.862529456615448,
+      "learning_rate": 4.375371022386677e-05,
+      "loss": 1.355858325958252,
+      "step": 875
+    },
+    {
+      "epoch": 0.5576679340937896,
+      "grad_norm": 1.1068962812423706,
+      "learning_rate": 4.324473762593036e-05,
+      "loss": 1.3223381042480469,
+      "step": 880
+    },
+    {
+      "epoch": 0.5608365019011406,
+      "grad_norm": 0.9751445055007935,
+      "learning_rate": 4.2736477053087265e-05,
+      "loss": 1.3480128288269042,
+      "step": 885
+    },
+    {
+      "epoch": 0.5640050697084917,
+      "grad_norm": 0.844694197177887,
+      "learning_rate": 4.2228982077539655e-05,
+      "loss": 1.3501531600952148,
+      "step": 890
+    },
+    {
+      "epoch": 0.5671736375158428,
+      "grad_norm": 1.0401661396026611,
+      "learning_rate": 4.1722306190793495e-05,
+      "loss": 1.3577798843383788,
+      "step": 895
+    },
+    {
+      "epoch": 0.5703422053231939,
+      "grad_norm": 0.9297835826873779,
+      "learning_rate": 4.121650279802027e-05,
+      "loss": 1.3129751205444335,
+      "step": 900
+    },
+    {
+      "epoch": 0.573510773130545,
+      "grad_norm": 0.9704940319061279,
+      "learning_rate": 4.071162521242796e-05,
+      "loss": 1.3801716804504394,
+      "step": 905
+    },
+    {
+      "epoch": 0.5766793409378961,
+      "grad_norm": 0.8439595699310303,
+      "learning_rate": 4.0207726649641666e-05,
+      "loss": 1.353194522857666,
+      "step": 910
+    },
+    {
+      "epoch": 0.5798479087452472,
+      "grad_norm": 1.001358985900879,
+      "learning_rate": 3.970486022209451e-05,
+      "loss": 1.4151784896850585,
+      "step": 915
+    },
+    {
+      "epoch": 0.5830164765525983,
+      "grad_norm": 0.8582479953765869,
+      "learning_rate": 3.920307893342949e-05,
+      "loss": 1.3958765029907227,
+      "step": 920
+    },
+    {
+      "epoch": 0.5861850443599493,
+      "grad_norm": 0.9078862071037292,
+      "learning_rate": 3.8702435672912626e-05,
+      "loss": 1.4149696350097656,
+      "step": 925
+    },
+    {
+      "epoch": 0.5893536121673004,
+      "grad_norm": 1.0525516271591187,
+      "learning_rate": 3.8202983209858356e-05,
+      "loss": 1.3368765830993652,
+      "step": 930
+    },
+    {
+      "epoch": 0.5925221799746515,
+      "grad_norm": 0.9519181251525879,
+      "learning_rate": 3.770477418806744e-05,
+      "loss": 1.3330938339233398,
+      "step": 935
+    },
+    {
+      "epoch": 0.5956907477820025,
+      "grad_norm": 0.7788481712341309,
+      "learning_rate": 3.720786112027822e-05,
+      "loss": 1.3294697761535645,
+      "step": 940
+    },
+    {
+      "epoch": 0.5988593155893536,
+      "grad_norm": 0.9929976463317871,
+      "learning_rate": 3.671229638263151e-05,
+      "loss": 1.4216012001037597,
+      "step": 945
+    },
+    {
+      "epoch": 0.6020278833967047,
+      "grad_norm": 1.1244455575942993,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 1.3404890060424806,
+      "step": 950
+    },
+    {
+      "epoch": 0.6051964512040557,
+      "grad_norm": 1.0040193796157837,
+      "learning_rate": 3.57254206862329e-05,
+      "loss": 1.3190261840820312,
+      "step": 955
+    },
+    {
+      "epoch": 0.6083650190114068,
+      "grad_norm": 0.8877851366996765,
+      "learning_rate": 3.523421374716537e-05,
+      "loss": 1.3281331062316895,
+      "step": 960
+    },
+    {
+      "epoch": 0.6115335868187579,
+      "grad_norm": 0.7751623392105103,
+      "learning_rate": 3.4744563166645037e-05,
+      "loss": 1.334850025177002,
+      "step": 965
+    },
+    {
+      "epoch": 0.614702154626109,
+      "grad_norm": 1.3870421648025513,
+      "learning_rate": 3.425652055532461e-05,
+      "loss": 1.3271892547607422,
+      "step": 970
+    },
+    {
+      "epoch": 0.6178707224334601,
+      "grad_norm": 1.065826416015625,
+      "learning_rate": 3.377013735437198e-05,
+      "loss": 1.4464192390441895,
+      "step": 975
+    },
+    {
+      "epoch": 0.6210392902408112,
+      "grad_norm": 1.0614964962005615,
+      "learning_rate": 3.328546483004814e-05,
+      "loss": 1.3625066757202149,
+      "step": 980
+    },
+    {
+      "epoch": 0.6242078580481623,
+      "grad_norm": 1.0641158819198608,
+      "learning_rate": 3.2802554068303596e-05,
+      "loss": 1.2995372772216798,
+      "step": 985
+    },
+    {
+      "epoch": 0.6273764258555133,
+      "grad_norm": 1.1293580532073975,
+      "learning_rate": 3.2321455969393784e-05,
+      "loss": 1.3447973251342773,
+      "step": 990
+    },
+    {
+      "epoch": 0.6305449936628644,
+      "grad_norm": 0.8212258815765381,
+      "learning_rate": 3.1842221242513944e-05,
+      "loss": 1.3622364044189452,
+      "step": 995
+    },
+    {
+      "epoch": 0.6337135614702155,
+      "grad_norm": 0.9654073119163513,
+      "learning_rate": 3.13649004004543e-05,
+      "loss": 1.339268684387207,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6368821292775665,
+      "grad_norm": 1.0687123537063599,
+      "learning_rate": 3.088954375427582e-05,
+      "loss": 1.3421677589416503,
+      "step": 1005
+    },
+    {
+      "epoch": 0.6400506970849176,
+      "grad_norm": 1.1498644351959229,
+      "learning_rate": 3.0416201408007237e-05,
+      "loss": 1.2978170394897461,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6432192648922687,
+      "grad_norm": 1.1247986555099487,
+      "learning_rate": 2.9944923253364066e-05,
+      "loss": 1.3145835876464844,
+      "step": 1015
+    },
+    {
+      "epoch": 0.6463878326996197,
+      "grad_norm": 1.085307002067566,
+      "learning_rate": 2.9475758964489707e-05,
+      "loss": 1.28936824798584,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6495564005069708,
+      "grad_norm": 0.9060108065605164,
+      "learning_rate": 2.9008757992719732e-05,
+      "loss": 1.3310838699340821,
+      "step": 1025
+    },
+    {
+      "epoch": 0.6527249683143219,
+      "grad_norm": 0.8243566155433655,
+      "learning_rate": 2.8543969561369556e-05,
+      "loss": 1.3718022346496581,
+      "step": 1030
+    },
+    {
+      "epoch": 0.655893536121673,
+      "grad_norm": 0.8411113023757935,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.413943099975586,
+      "step": 1035
+    },
+    {
+      "epoch": 0.6590621039290241,
+      "grad_norm": 0.9290187358856201,
+      "learning_rate": 2.762122604198424e-05,
+      "loss": 1.3513057708740235,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6622306717363752,
+      "grad_norm": 1.080499529838562,
+      "learning_rate": 2.7163368213907973e-05,
+      "loss": 1.32059907913208,
+      "step": 1045
+    },
+    {
+      "epoch": 0.6653992395437263,
+      "grad_norm": 1.1765803098678589,
+      "learning_rate": 2.6707917435917685e-05,
+      "loss": 1.3292306900024413,
+      "step": 1050
+    },
+    {
+      "epoch": 0.6685678073510773,
+      "grad_norm": 0.970851480960846,
+      "learning_rate": 2.6254921713903446e-05,
+      "loss": 1.345045280456543,
+      "step": 1055
+    },
+    {
+      "epoch": 0.6717363751584284,
+      "grad_norm": 1.1229257583618164,
+      "learning_rate": 2.5804428794984924e-05,
+      "loss": 1.3488195419311524,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6749049429657795,
+      "grad_norm": 1.0836807489395142,
+      "learning_rate": 2.5356486162478844e-05,
+      "loss": 1.324122714996338,
+      "step": 1065
+    },
+    {
+      "epoch": 0.6780735107731305,
+      "grad_norm": 1.0663892030715942,
+      "learning_rate": 2.4911141030893994e-05,
+      "loss": 1.3661954879760743,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6812420785804816,
+      "grad_norm": 1.1285103559494019,
+      "learning_rate": 2.446844034095466e-05,
+      "loss": 1.3212727546691894,
+      "step": 1075
+    },
+    {
+      "epoch": 0.6844106463878327,
+      "grad_norm": 0.8290923833847046,
+      "learning_rate": 2.4028430754653065e-05,
+      "loss": 1.3932605743408204,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6875792141951838,
+      "grad_norm": 0.9139001965522766,
+      "learning_rate": 2.3591158650330898e-05,
+      "loss": 1.3588622093200684,
+      "step": 1085
+    },
+    {
+      "epoch": 0.6907477820025348,
+      "grad_norm": 0.9368664026260376,
+      "learning_rate": 2.3156670117790996e-05,
+      "loss": 1.3890501976013183,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6939163498098859,
+      "grad_norm": 1.2055789232254028,
+      "learning_rate": 2.2725010953439324e-05,
+      "loss": 1.3423537254333495,
+      "step": 1095
+    },
+    {
+      "epoch": 0.697084917617237,
+      "grad_norm": 0.9319270253181458,
+      "learning_rate": 2.2296226655457814e-05,
+      "loss": 1.258255672454834,
+      "step": 1100
+    },
+    {
+      "epoch": 0.7002534854245881,
+      "grad_norm": 0.9653268456459045,
+      "learning_rate": 2.1870362419008845e-05,
+      "loss": 1.3396060943603516,
+      "step": 1105
+    },
+    {
+      "epoch": 0.7034220532319392,
+      "grad_norm": 1.0389213562011719,
+      "learning_rate": 2.144746313147148e-05,
+      "loss": 1.2651769638061523,
+      "step": 1110
+    },
+    {
+      "epoch": 0.7065906210392903,
+      "grad_norm": 1.0994007587432861,
+      "learning_rate": 2.1027573367710122e-05,
+      "loss": 1.3021663665771483,
+      "step": 1115
+    },
+    {
+      "epoch": 0.7097591888466414,
+      "grad_norm": 1.009810209274292,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 1.331705093383789,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7129277566539924,
+      "grad_norm": 1.1909452676773071,
+      "learning_rate": 2.0196999120243886e-05,
+      "loss": 1.4106544494628905,
+      "step": 1125
+    },
+    {
+      "epoch": 0.7160963244613435,
+      "grad_norm": 1.0456634759902954,
+      "learning_rate": 1.9786402181577714e-05,
+      "loss": 1.2929454803466798,
+      "step": 1130
+    },
+    {
+      "epoch": 0.7192648922686945,
+      "grad_norm": 1.154612421989441,
+      "learning_rate": 1.937898984753751e-05,
+      "loss": 1.3293749809265136,
+      "step": 1135
+    },
+    {
+      "epoch": 0.7224334600760456,
+      "grad_norm": 0.8952815532684326,
+      "learning_rate": 1.897480506061593e-05,
+      "loss": 1.3869823455810546,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7256020278833967,
+      "grad_norm": 0.918984591960907,
+      "learning_rate": 1.857389042311246e-05,
+      "loss": 1.3285282135009766,
+      "step": 1145
+    },
+    {
+      "epoch": 0.7287705956907478,
+      "grad_norm": 0.9093521237373352,
+      "learning_rate": 1.8176288192642944e-05,
+      "loss": 1.286917018890381,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7319391634980988,
+      "grad_norm": 0.9459413290023804,
+      "learning_rate": 1.7782040277685436e-05,
+      "loss": 1.284006690979004,
+      "step": 1155
+    },
+    {
+      "epoch": 0.7351077313054499,
+      "grad_norm": 0.7686821222305298,
+      "learning_rate": 1.7391188233163052e-05,
+      "loss": 1.3963065147399902,
+      "step": 1160
+    },
+    {
+      "epoch": 0.738276299112801,
+      "grad_norm": 0.9745455384254456,
+      "learning_rate": 1.700377325606388e-05,
+      "loss": 1.3169967651367187,
+      "step": 1165
+    },
+    {
+      "epoch": 0.7414448669201521,
+      "grad_norm": 0.896531343460083,
+      "learning_rate": 1.6619836181098668e-05,
+      "loss": 1.2857364654541015,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7446134347275032,
+      "grad_norm": 1.1586496829986572,
+      "learning_rate": 1.623941747639679e-05,
+      "loss": 1.3532679557800293,
+      "step": 1175
+    },
+    {
+      "epoch": 0.7477820025348543,
+      "grad_norm": 1.0042097568511963,
+      "learning_rate": 1.5862557239240728e-05,
+      "loss": 1.3450308799743653,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7509505703422054,
+      "grad_norm": 1.227421522140503,
+      "learning_rate": 1.5489295191839736e-05,
+      "loss": 1.2885151863098145,
+      "step": 1185
+    },
+    {
+      "epoch": 0.7541191381495564,
+      "grad_norm": 1.0154186487197876,
+      "learning_rate": 1.5119670677142983e-05,
+      "loss": 1.3617592811584474,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7572877059569075,
+      "grad_norm": 1.1962554454803467,
+      "learning_rate": 1.4753722654692647e-05,
+      "loss": 1.3216251373291015,
+      "step": 1195
+    },
+    {
+      "epoch": 0.7604562737642585,
+      "grad_norm": 0.9843072295188904,
+      "learning_rate": 1.4391489696517535e-05,
+      "loss": 1.322807502746582,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7636248415716096,
+      "grad_norm": 1.023239254951477,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.3661455154418944,
+      "step": 1205
+    },
+    {
+      "epoch": 0.7667934093789607,
+      "grad_norm": 0.9753304719924927,
+      "learning_rate": 1.3678321299188801e-05,
+      "loss": 1.2892273902893066,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7699619771863118,
+      "grad_norm": 1.631977915763855,
+      "learning_rate": 1.3327461030142036e-05,
+      "loss": 1.2959428787231446,
+      "step": 1215
+    },
+    {
+      "epoch": 0.7731305449936628,
+      "grad_norm": 0.9189720749855042,
+      "learning_rate": 1.298046615766112e-05,
+      "loss": 1.3217609405517579,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7762991128010139,
+      "grad_norm": 0.9295359253883362,
+      "learning_rate": 1.2637373256055446e-05,
+      "loss": 1.354560661315918,
+      "step": 1225
+    },
+    {
+      "epoch": 0.779467680608365,
+      "grad_norm": 0.8047182559967041,
+      "learning_rate": 1.229821848835499e-05,
+      "loss": 1.3275278091430665,
+      "step": 1230
+    },
+    {
+      "epoch": 0.7826362484157161,
+      "grad_norm": 1.093078374862671,
+      "learning_rate": 1.1963037602498384e-05,
+      "loss": 1.329340362548828,
+      "step": 1235
+    },
+    {
+      "epoch": 0.7858048162230672,
+      "grad_norm": 1.3584924936294556,
+      "learning_rate": 1.1631865927565149e-05,
+      "loss": 1.2881906509399415,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7889733840304183,
+      "grad_norm": 0.9902975559234619,
+      "learning_rate": 1.130473837005186e-05,
+      "loss": 1.3978662490844727,
+      "step": 1245
+    },
+    {
+      "epoch": 0.7921419518377694,
+      "grad_norm": 1.096245288848877,
+      "learning_rate": 1.0981689410192813e-05,
+      "loss": 1.2938296318054199,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7953105196451205,
+      "grad_norm": 1.063981056213379,
+      "learning_rate": 1.066275309832584e-05,
+      "loss": 1.3088212966918946,
+      "step": 1255
+    },
+    {
+      "epoch": 0.7984790874524715,
+      "grad_norm": 0.9275028705596924,
+      "learning_rate": 1.03479630513032e-05,
+      "loss": 1.264383316040039,
+      "step": 1260
+    },
+    {
+      "epoch": 0.8016476552598225,
+      "grad_norm": 1.3804821968078613,
+      "learning_rate": 1.0037352448948279e-05,
+      "loss": 1.2914956092834473,
+      "step": 1265
+    },
+    {
+      "epoch": 0.8048162230671736,
+      "grad_norm": 0.8959029316902161,
+      "learning_rate": 9.73095403055837e-06,
+      "loss": 1.3482831954956054,
+      "step": 1270
+    },
+    {
+      "epoch": 0.8079847908745247,
+      "grad_norm": 0.9850245118141174,
+      "learning_rate": 9.428800091453838e-06,
+      "loss": 1.331840419769287,
+      "step": 1275
+    },
+    {
+      "epoch": 0.8111533586818758,
+      "grad_norm": 0.9934479594230652,
+      "learning_rate": 9.130922479574067e-06,
+      "loss": 1.3903246879577638,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8143219264892269,
+      "grad_norm": 0.8619696497917175,
+      "learning_rate": 8.837352592120645e-06,
+      "loss": 1.3167320251464845,
+      "step": 1285
+    },
+    {
+      "epoch": 0.8174904942965779,
+      "grad_norm": 0.8320128321647644,
+      "learning_rate": 8.548121372247918e-06,
+      "loss": 1.2873162269592284,
+      "step": 1290
+    },
+    {
+      "epoch": 0.820659062103929,
+      "grad_norm": 1.2043529748916626,
+      "learning_rate": 8.26325930580159e-06,
+      "loss": 1.283571720123291,
+      "step": 1295
+    },
+    {
+      "epoch": 0.8238276299112801,
+      "grad_norm": 1.070096731185913,
+      "learning_rate": 7.982796418105371e-06,
+      "loss": 1.2654370307922362,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8269961977186312,
+      "grad_norm": 1.011426329612732,
+      "learning_rate": 7.706762270796186e-06,
+      "loss": 1.387790584564209,
+      "step": 1305
+    },
+    {
+      "epoch": 0.8301647655259823,
+      "grad_norm": 1.0511480569839478,
+      "learning_rate": 7.435185958708351e-06,
+      "loss": 1.37603759765625,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.9717739820480347,
+      "learning_rate": 7.168096106806871e-06,
+      "loss": 1.2307350158691406,
+      "step": 1315
+    },
+    {
+      "epoch": 0.8365019011406845,
+      "grad_norm": 0.9008772969245911,
+      "learning_rate": 6.905520867170223e-06,
+      "loss": 1.4192010879516601,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8396704689480355,
+      "grad_norm": 1.2221213579177856,
+      "learning_rate": 6.647487916023177e-06,
+      "loss": 1.4267322540283203,
+      "step": 1325
+    },
+    {
+      "epoch": 0.8428390367553865,
+      "grad_norm": 0.789287805557251,
+      "learning_rate": 6.394024450819458e-06,
+      "loss": 1.3336950302124024,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8460076045627376,
+      "grad_norm": 0.8760536909103394,
+      "learning_rate": 6.145157187375211e-06,
+      "loss": 1.2808075904846192,
+      "step": 1335
+    },
+    {
+      "epoch": 0.8491761723700887,
+      "grad_norm": 1.1593248844146729,
+      "learning_rate": 5.900912357052996e-06,
+      "loss": 1.3868263244628907,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8523447401774398,
+      "grad_norm": 0.8710156679153442,
+      "learning_rate": 5.6613157039969055e-06,
+      "loss": 1.3790958404541016,
+      "step": 1345
+    },
+    {
+      "epoch": 0.8555133079847909,
+      "grad_norm": 1.0077850818634033,
+      "learning_rate": 5.426392482419124e-06,
+      "loss": 1.2981806755065919,
+      "step": 1350
+    },
+    {
+      "epoch": 0.858681875792142,
+      "grad_norm": 1.0064268112182617,
+      "learning_rate": 5.196167453938011e-06,
+      "loss": 1.3274435997009277,
+      "step": 1355
+    },
+    {
+      "epoch": 0.861850443599493,
+      "grad_norm": 1.074414610862732,
+      "learning_rate": 4.970664884968135e-06,
+      "loss": 1.3398886680603028,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8650190114068441,
+      "grad_norm": 0.9940077066421509,
+      "learning_rate": 4.749908544162551e-06,
+      "loss": 1.3527451515197755,
+      "step": 1365
+    },
+    {
+      "epoch": 0.8681875792141952,
+      "grad_norm": 1.0884714126586914,
+      "learning_rate": 4.533921699907534e-06,
+      "loss": 1.2722294807434082,
+      "step": 1370
+    },
+    {
+      "epoch": 0.8713561470215463,
+      "grad_norm": 0.8487538695335388,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.3465628623962402,
+      "step": 1375
+    },
+    {
+      "epoch": 0.8745247148288974,
+      "grad_norm": 0.9994097352027893,
+      "learning_rate": 4.116347058597769e-06,
+      "loss": 1.2989694595336914,
+      "step": 1380
+    },
+    {
+      "epoch": 0.8776932826362485,
+      "grad_norm": 1.4533636569976807,
+      "learning_rate": 3.9148032751736565e-06,
+      "loss": 1.2593950271606444,
+      "step": 1385
+    },
+    {
+      "epoch": 0.8808618504435995,
+      "grad_norm": 1.2208831310272217,
+      "learning_rate": 3.71811701092219e-06,
+      "loss": 1.3306990623474122,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8840304182509505,
+      "grad_norm": 0.7860085964202881,
+      "learning_rate": 3.526308997170724e-06,
+      "loss": 1.3549036979675293,
+      "step": 1395
+    },
+    {
+      "epoch": 0.8871989860583016,
+      "grad_norm": 0.9392310976982117,
+      "learning_rate": 3.3393994510642567e-06,
+      "loss": 1.3818175315856933,
+      "step": 1400
+    },
+    {
+      "epoch": 0.8903675538656527,
+      "grad_norm": 1.0431451797485352,
+      "learning_rate": 3.157408073434476e-06,
+      "loss": 1.2601960182189942,
+      "step": 1405
+    },
+    {
+      "epoch": 0.8935361216730038,
+      "grad_norm": 1.0251599550247192,
+      "learning_rate": 2.980354046723216e-06,
+      "loss": 1.2811641693115234,
+      "step": 1410
+    },
+    {
+      "epoch": 0.8967046894803549,
+      "grad_norm": 0.974606990814209,
+      "learning_rate": 2.8082560329605934e-06,
+      "loss": 1.3238912582397462,
+      "step": 1415
+    },
+    {
+      "epoch": 0.899873257287706,
+      "grad_norm": 0.9117522835731506,
+      "learning_rate": 2.641132171797989e-06,
+      "loss": 1.3850933074951173,
+      "step": 1420
+    },
+    {
+      "epoch": 0.903041825095057,
+      "grad_norm": 0.9673117995262146,
+      "learning_rate": 2.479000078596011e-06,
+      "loss": 1.2810011863708497,
+      "step": 1425
+    },
+    {
+      "epoch": 0.9062103929024081,
+      "grad_norm": 0.935701310634613,
+      "learning_rate": 2.321876842567844e-06,
+      "loss": 1.3237515449523927,
+      "step": 1430
+    },
+    {
+      "epoch": 0.9093789607097592,
+      "grad_norm": 1.1298409700393677,
+      "learning_rate": 2.1697790249779636e-06,
+      "loss": 1.348030185699463,
+      "step": 1435
+    },
+    {
+      "epoch": 0.9125475285171103,
+      "grad_norm": 1.2701897621154785,
+      "learning_rate": 2.0227226573965364e-06,
+      "loss": 1.2942058563232421,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9157160963244614,
+      "grad_norm": 1.2197922468185425,
+      "learning_rate": 1.8807232400096575e-06,
+      "loss": 1.3446466445922851,
+      "step": 1445
+    },
+    {
+      "epoch": 0.9188846641318125,
+      "grad_norm": 1.1077975034713745,
+      "learning_rate": 1.7437957399855487e-06,
+      "loss": 1.2483136177062988,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9220532319391636,
+      "grad_norm": 0.973805844783783,
+      "learning_rate": 1.6119545898970135e-06,
+      "loss": 1.2563264846801758,
+      "step": 1455
+    },
+    {
+      "epoch": 0.9252217997465145,
+      "grad_norm": 1.1137876510620117,
+      "learning_rate": 1.4852136862001764e-06,
+      "loss": 1.3047880172729491,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9283903675538656,
+      "grad_norm": 1.1174026727676392,
+      "learning_rate": 1.3635863877697607e-06,
+      "loss": 1.3538530349731446,
+      "step": 1465
+    },
+    {
+      "epoch": 0.9315589353612167,
+      "grad_norm": 1.254982352256775,
+      "learning_rate": 1.247085514491031e-06,
+      "loss": 1.3151609420776367,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9347275031685678,
+      "grad_norm": 0.9658820033073425,
+      "learning_rate": 1.135723345908507e-06,
+      "loss": 1.3587602615356444,
+      "step": 1475
+    },
+    {
+      "epoch": 0.9378960709759189,
+      "grad_norm": 1.3376219272613525,
+      "learning_rate": 1.0295116199317057e-06,
+      "loss": 1.342695426940918,
+      "step": 1480
+    },
+    {
+      "epoch": 0.94106463878327,
+      "grad_norm": 0.9864044785499573,
+      "learning_rate": 9.284615315979128e-07,
+      "loss": 1.346114158630371,
+      "step": 1485
+    },
+    {
+      "epoch": 0.944233206590621,
+      "grad_norm": 1.00253164768219,
+      "learning_rate": 8.32583731892178e-07,
+      "loss": 1.386203670501709,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9474017743979721,
+      "grad_norm": 1.2469029426574707,
+      "learning_rate": 7.418883266246734e-07,
+      "loss": 1.2846878051757813,
+      "step": 1495
+    },
+    {
+      "epoch": 0.9505703422053232,
+      "grad_norm": 1.0144803524017334,
+      "learning_rate": 6.563848753655455e-07,
+      "loss": 1.3169589996337892,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9537389100126743,
+      "grad_norm": 1.387046217918396,
+      "learning_rate": 5.760823904372436e-07,
+      "loss": 1.3220189094543457,
+      "step": 1505
+    },
+    {
+      "epoch": 0.9569074778200254,
+      "grad_norm": 0.8839166760444641,
+      "learning_rate": 5.009893359646523e-07,
+      "loss": 1.2524205207824708,
+      "step": 1510
+    },
+    {
+      "epoch": 0.9600760456273765,
+      "grad_norm": 0.9231826066970825,
+      "learning_rate": 4.311136269829208e-07,
+      "loss": 1.2773988723754883,
+      "step": 1515
+    },
+    {
+      "epoch": 0.9632446134347274,
+      "grad_norm": 0.761739194393158,
+      "learning_rate": 3.66462628603198e-07,
+      "loss": 1.3505694389343261,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9664131812420785,
+      "grad_norm": 0.9646550416946411,
+      "learning_rate": 3.0704315523631953e-07,
+      "loss": 1.336940383911133,
+      "step": 1525
+    },
+    {
+      "epoch": 0.9695817490494296,
+      "grad_norm": 0.8002787232398987,
+      "learning_rate": 2.528614698745602e-07,
+      "loss": 1.373541259765625,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9727503168567807,
+      "grad_norm": 0.7745749354362488,
+      "learning_rate": 2.0392328343149525e-07,
+      "loss": 1.3964224815368653,
+      "step": 1535
+    },
+    {
+      "epoch": 0.9759188846641318,
+      "grad_norm": 0.9030261039733887,
+      "learning_rate": 1.6023375414004894e-07,
+      "loss": 1.373337459564209,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9790874524714829,
+      "grad_norm": 1.1446213722229004,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.379157829284668,
+      "step": 1545
+    },
+    {
+      "epoch": 0.982256020278834,
+      "grad_norm": 0.9039878249168396,
+      "learning_rate": 8.861853333657077e-08,
+      "loss": 1.2705472946166991,
+      "step": 1550
+    },
+    {
+      "epoch": 0.985424588086185,
+      "grad_norm": 1.1875966787338257,
+      "learning_rate": 6.070039028550633e-08,
+      "loss": 1.2417927742004395,
+      "step": 1555
+    },
+    {
+      "epoch": 0.9885931558935361,
+      "grad_norm": 0.8743357062339783,
+      "learning_rate": 3.8046000512326206e-08,
+      "loss": 1.3056893348693848,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9917617237008872,
+      "grad_norm": 0.9445528984069824,
+      "learning_rate": 2.065775185827734e-08,
+      "loss": 1.3818035125732422,
+      "step": 1565
+    },
+    {
+      "epoch": 0.9949302915082383,
+      "grad_norm": 0.9100821018218994,
+      "learning_rate": 8.537477097364522e-09,
+      "loss": 1.3335657119750977,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9980988593155894,
+      "grad_norm": 1.2100127935409546,
+      "learning_rate": 1.6864537432270677e-09,
+      "loss": 1.3559389114379883,
+      "step": 1575
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1578,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.9473863044969267e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d7ee3557ea2f42831dff2061cafdfbc0cf8415dcf13d4c40fa0fd6f933e0e2f
+size 5905