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",
+    "gate_proj",
+    "up_proj",
+    "down_proj",
+    "q_proj",
+    "o_proj",
+    "v_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:ebbc6f42f45e913e84d5b690baf6e2520b2c60870937ae7415ecfa488392a3c6
+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 sha256:564199eb7a6ba01bf1296ed89b8579913d83635ee455005fb409a9773369befd
+size 81070011

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d111d20a409c2ef3224a3c514b85c746e518e6429830c80810b09dcfdff9de20
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0d215056425edf23f640b99876fedf124e9110e87a3a60dd2998b353ef73021
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66689dbc7cccabcd97f28c655652a8a06205b7222678de124136b8bc5b6d1fab
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d209b65148729e65dda09b41f5127df9ecc09407167f2ca6738208c8bc71e8a
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f69e0030eb252be0a4dda9aa309d16f745ccf3dbba63b2d69f158d5aa74139fd
+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 +1,2876 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2030,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0024630541871921183,
+      "grad_norm": 1.576782464981079,
+      "learning_rate": 1.639344262295082e-05,
+      "loss": 2.8946464538574217,
+      "step": 5
+    },
+    {
+      "epoch": 0.0049261083743842365,
+      "grad_norm": 0.5424566864967346,
+      "learning_rate": 3.6885245901639346e-05,
+      "loss": 2.8349845886230467,
+      "step": 10
+    },
+    {
+      "epoch": 0.007389162561576354,
+      "grad_norm": 0.2974247932434082,
+      "learning_rate": 5.737704918032787e-05,
+      "loss": 2.5847036361694338,
+      "step": 15
+    },
+    {
+      "epoch": 0.009852216748768473,
+      "grad_norm": 0.3515515923500061,
+      "learning_rate": 7.78688524590164e-05,
+      "loss": 2.4321041107177734,
+      "step": 20
+    },
+    {
+      "epoch": 0.012315270935960592,
+      "grad_norm": 0.2208901196718216,
+      "learning_rate": 9.836065573770491e-05,
+      "loss": 2.349212074279785,
+      "step": 25
+    },
+    {
+      "epoch": 0.014778325123152709,
+      "grad_norm": 0.20292750000953674,
+      "learning_rate": 0.00011885245901639344,
+      "loss": 2.2124969482421877,
+      "step": 30
+    },
+    {
+      "epoch": 0.017241379310344827,
+      "grad_norm": 0.17618690431118011,
+      "learning_rate": 0.00013934426229508196,
+      "loss": 2.0806224822998045,
+      "step": 35
+    },
+    {
+      "epoch": 0.019704433497536946,
+      "grad_norm": 0.23384685814380646,
+      "learning_rate": 0.0001598360655737705,
+      "loss": 2.0179601669311524,
+      "step": 40
+    },
+    {
+      "epoch": 0.022167487684729065,
+      "grad_norm": 0.1721847951412201,
+      "learning_rate": 0.00018032786885245904,
+      "loss": 1.9524045944213868,
+      "step": 45
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "grad_norm": 0.2105543166399002,
+      "learning_rate": 0.00020081967213114754,
+      "loss": 1.8813556671142577,
+      "step": 50
+    },
+    {
+      "epoch": 0.027093596059113302,
+      "grad_norm": 0.1616581231355667,
+      "learning_rate": 0.00022131147540983606,
+      "loss": 1.849898338317871,
+      "step": 55
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": 0.19672377407550812,
+      "learning_rate": 0.00024180327868852458,
+      "loss": 1.8116474151611328,
+      "step": 60
+    },
+    {
+      "epoch": 0.03201970443349754,
+      "grad_norm": 0.18601663410663605,
+      "learning_rate": 0.00024999856804288825,
+      "loss": 1.7615894317626952,
+      "step": 65
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 0.18811668455600739,
+      "learning_rate": 0.0002499898173126826,
+      "loss": 1.7470718383789063,
+      "step": 70
+    },
+    {
+      "epoch": 0.03694581280788178,
+      "grad_norm": 0.21485674381256104,
+      "learning_rate": 0.00024997311194024176,
+      "loss": 1.7718585968017577,
+      "step": 75
+    },
+    {
+      "epoch": 0.03940886699507389,
+      "grad_norm": 0.16910547018051147,
+      "learning_rate": 0.00024994845298873447,
+      "loss": 1.7243595123291016,
+      "step": 80
+    },
+    {
+      "epoch": 0.04187192118226601,
+      "grad_norm": 0.21829535067081451,
+      "learning_rate": 0.0002499158420275136,
+      "loss": 1.6787448883056642,
+      "step": 85
+    },
+    {
+      "epoch": 0.04433497536945813,
+      "grad_norm": 0.19575679302215576,
+      "learning_rate": 0.0002498752811320165,
+      "loss": 1.6730777740478515,
+      "step": 90
+    },
+    {
+      "epoch": 0.046798029556650245,
+      "grad_norm": 0.1603914201259613,
+      "learning_rate": 0.00024982677288363283,
+      "loss": 1.7178722381591798,
+      "step": 95
+    },
+    {
+      "epoch": 0.04926108374384237,
+      "grad_norm": 0.19204729795455933,
+      "learning_rate": 0.00024977032036954,
+      "loss": 1.675705909729004,
+      "step": 100
+    },
+    {
+      "epoch": 0.05172413793103448,
+      "grad_norm": 0.19316811859607697,
+      "learning_rate": 0.0002497059271825072,
+      "loss": 1.67794189453125,
+      "step": 105
+    },
+    {
+      "epoch": 0.054187192118226604,
+      "grad_norm": 0.17815200984477997,
+      "learning_rate": 0.00024963359742066646,
+      "loss": 1.6259672164916992,
+      "step": 110
+    },
+    {
+      "epoch": 0.05665024630541872,
+      "grad_norm": 0.21048253774642944,
+      "learning_rate": 0.0002495533356872516,
+      "loss": 1.6466709136962892,
+      "step": 115
+    },
+    {
+      "epoch": 0.059113300492610835,
+      "grad_norm": 0.1798284500837326,
+      "learning_rate": 0.00024946514709030596,
+      "loss": 1.624470329284668,
+      "step": 120
+    },
+    {
+      "epoch": 0.06157635467980296,
+      "grad_norm": 0.18633724749088287,
+      "learning_rate": 0.00024936903724235643,
+      "loss": 1.6109725952148437,
+      "step": 125
+    },
+    {
+      "epoch": 0.06403940886699508,
+      "grad_norm": 0.18666480481624603,
+      "learning_rate": 0.0002492650122600571,
+      "loss": 1.5855847358703614,
+      "step": 130
+    },
+    {
+      "epoch": 0.0665024630541872,
+      "grad_norm": 0.187570720911026,
+      "learning_rate": 0.00024915307876379925,
+      "loss": 1.614936065673828,
+      "step": 135
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 0.19775646924972534,
+      "learning_rate": 0.0002490332438772907,
+      "loss": 1.6251581192016602,
+      "step": 140
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 0.16423331201076508,
+      "learning_rate": 0.00024890551522710187,
+      "loss": 1.586317253112793,
+      "step": 145
+    },
+    {
+      "epoch": 0.07389162561576355,
+      "grad_norm": 0.18266676366329193,
+      "learning_rate": 0.0002487699009421806,
+      "loss": 1.5819233894348144,
+      "step": 150
+    },
+    {
+      "epoch": 0.07635467980295567,
+      "grad_norm": 0.16824640333652496,
+      "learning_rate": 0.00024862640965333496,
+      "loss": 1.548696231842041,
+      "step": 155
+    },
+    {
+      "epoch": 0.07881773399014778,
+      "grad_norm": 0.20801961421966553,
+      "learning_rate": 0.0002484750504926838,
+      "loss": 1.5585339546203614,
+      "step": 160
+    },
+    {
+      "epoch": 0.0812807881773399,
+      "grad_norm": 0.17362217605113983,
+      "learning_rate": 0.0002483158330930756,
+      "loss": 1.5954392433166504,
+      "step": 165
+    },
+    {
+      "epoch": 0.08374384236453201,
+      "grad_norm": 0.17652060091495514,
+      "learning_rate": 0.0002481487675874754,
+      "loss": 1.523369312286377,
+      "step": 170
+    },
+    {
+      "epoch": 0.08620689655172414,
+      "grad_norm": 0.1657353788614273,
+      "learning_rate": 0.00024797386460832,
+      "loss": 1.564998722076416,
+      "step": 175
+    },
+    {
+      "epoch": 0.08866995073891626,
+      "grad_norm": 0.20407427847385406,
+      "learning_rate": 0.00024779113528684116,
+      "loss": 1.5420802116394043,
+      "step": 180
+    },
+    {
+      "epoch": 0.09113300492610837,
+      "grad_norm": 0.1929025799036026,
+      "learning_rate": 0.00024760059125235724,
+      "loss": 1.5300561904907226,
+      "step": 185
+    },
+    {
+      "epoch": 0.09359605911330049,
+      "grad_norm": 0.2064048945903778,
+      "learning_rate": 0.00024740224463153305,
+      "loss": 1.5291034698486328,
+      "step": 190
+    },
+    {
+      "epoch": 0.0960591133004926,
+      "grad_norm": 0.18626253306865692,
+      "learning_rate": 0.00024719610804760817,
+      "loss": 1.5361968994140625,
+      "step": 195
+    },
+    {
+      "epoch": 0.09852216748768473,
+      "grad_norm": 0.19031359255313873,
+      "learning_rate": 0.0002469821946195935,
+      "loss": 1.5882277488708496,
+      "step": 200
+    },
+    {
+      "epoch": 0.10098522167487685,
+      "grad_norm": 0.19836470484733582,
+      "learning_rate": 0.00024676051796143644,
+      "loss": 1.5806845664978026,
+      "step": 205
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 0.18841883540153503,
+      "learning_rate": 0.0002465310921811543,
+      "loss": 1.5321168899536133,
+      "step": 210
+    },
+    {
+      "epoch": 0.10591133004926108,
+      "grad_norm": 0.19038760662078857,
+      "learning_rate": 0.0002462939318799364,
+      "loss": 1.5261334419250487,
+      "step": 215
+    },
+    {
+      "epoch": 0.10837438423645321,
+      "grad_norm": 0.2101883441209793,
+      "learning_rate": 0.0002460490521512152,
+      "loss": 1.5112834930419923,
+      "step": 220
+    },
+    {
+      "epoch": 0.11083743842364532,
+      "grad_norm": 0.1957591027021408,
+      "learning_rate": 0.0002457964685797052,
+      "loss": 1.5345054626464845,
+      "step": 225
+    },
+    {
+      "epoch": 0.11330049261083744,
+      "grad_norm": 0.2150440812110901,
+      "learning_rate": 0.0002455361972404116,
+      "loss": 1.5496223449707032,
+      "step": 230
+    },
+    {
+      "epoch": 0.11576354679802955,
+      "grad_norm": 0.18482013046741486,
+      "learning_rate": 0.00024526825469760674,
+      "loss": 1.491357421875,
+      "step": 235
+    },
+    {
+      "epoch": 0.11822660098522167,
+      "grad_norm": 0.20167887210845947,
+      "learning_rate": 0.00024499265800377633,
+      "loss": 1.499197769165039,
+      "step": 240
+    },
+    {
+      "epoch": 0.1206896551724138,
+      "grad_norm": 0.1861075758934021,
+      "learning_rate": 0.00024470942469853395,
+      "loss": 1.4918067932128907,
+      "step": 245
+    },
+    {
+      "epoch": 0.12315270935960591,
+      "grad_norm": 0.19906744360923767,
+      "learning_rate": 0.0002444185728075049,
+      "loss": 1.4826949119567872,
+      "step": 250
+    },
+    {
+      "epoch": 0.12561576354679804,
+      "grad_norm": 0.18927539885044098,
+      "learning_rate": 0.00024412012084117904,
+      "loss": 1.4690278053283692,
+      "step": 255
+    },
+    {
+      "epoch": 0.12807881773399016,
+      "grad_norm": 0.22364802658557892,
+      "learning_rate": 0.0002438140877937325,
+      "loss": 1.511463737487793,
+      "step": 260
+    },
+    {
+      "epoch": 0.13054187192118227,
+      "grad_norm": 0.17403197288513184,
+      "learning_rate": 0.00024350049314181917,
+      "loss": 1.5138906478881835,
+      "step": 265
+    },
+    {
+      "epoch": 0.1330049261083744,
+      "grad_norm": 0.19757160544395447,
+      "learning_rate": 0.00024317935684333092,
+      "loss": 1.4710895538330078,
+      "step": 270
+    },
+    {
+      "epoch": 0.1354679802955665,
+      "grad_norm": 0.1725938767194748,
+      "learning_rate": 0.00024285069933612752,
+      "loss": 1.4501166343688965,
+      "step": 275
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 0.17984315752983093,
+      "learning_rate": 0.00024251454153673607,
+      "loss": 1.461907196044922,
+      "step": 280
+    },
+    {
+      "epoch": 0.14039408866995073,
+      "grad_norm": 0.17993943393230438,
+      "learning_rate": 0.0002421709048390195,
+      "loss": 1.4890538215637208,
+      "step": 285
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.19029419124126434,
+      "learning_rate": 0.00024181981111281526,
+      "loss": 1.4817827224731446,
+      "step": 290
+    },
+    {
+      "epoch": 0.14532019704433496,
+      "grad_norm": 0.18746912479400635,
+      "learning_rate": 0.00024146128270254347,
+      "loss": 1.454909324645996,
+      "step": 295
+    },
+    {
+      "epoch": 0.1477832512315271,
+      "grad_norm": 0.1737545281648636,
+      "learning_rate": 0.00024109534242578473,
+      "loss": 1.4507439613342286,
+      "step": 300
+    },
+    {
+      "epoch": 0.15024630541871922,
+      "grad_norm": 0.16780607402324677,
+      "learning_rate": 0.0002407220135718281,
+      "loss": 1.4520732879638671,
+      "step": 305
+    },
+    {
+      "epoch": 0.15270935960591134,
+      "grad_norm": 0.185664102435112,
+      "learning_rate": 0.00024034131990018879,
+      "loss": 1.4266855239868164,
+      "step": 310
+    },
+    {
+      "epoch": 0.15517241379310345,
+      "grad_norm": 0.17912675440311432,
+      "learning_rate": 0.00023995328563909617,
+      "loss": 1.4438836097717285,
+      "step": 315
+    },
+    {
+      "epoch": 0.15763546798029557,
+      "grad_norm": 0.16740645468235016,
+      "learning_rate": 0.00023955793548395172,
+      "loss": 1.4362960815429688,
+      "step": 320
+    },
+    {
+      "epoch": 0.16009852216748768,
+      "grad_norm": 0.19105449318885803,
+      "learning_rate": 0.0002391552945957574,
+      "loss": 1.4682472229003907,
+      "step": 325
+    },
+    {
+      "epoch": 0.1625615763546798,
+      "grad_norm": 0.1613941639661789,
+      "learning_rate": 0.00023874538859951444,
+      "loss": 1.451451301574707,
+      "step": 330
+    },
+    {
+      "epoch": 0.16502463054187191,
+      "grad_norm": 0.17451488971710205,
+      "learning_rate": 0.00023832824358259233,
+      "loss": 1.38260498046875,
+      "step": 335
+    },
+    {
+      "epoch": 0.16748768472906403,
+      "grad_norm": 0.18210256099700928,
+      "learning_rate": 0.00023790388609306869,
+      "loss": 1.4864479064941407,
+      "step": 340
+    },
+    {
+      "epoch": 0.16995073891625614,
+      "grad_norm": 0.15857470035552979,
+      "learning_rate": 0.00023747234313803957,
+      "loss": 1.423063087463379,
+      "step": 345
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 0.20868025720119476,
+      "learning_rate": 0.00023703364218190086,
+      "loss": 1.4290130615234375,
+      "step": 350
+    },
+    {
+      "epoch": 0.1748768472906404,
+      "grad_norm": 0.18334713578224182,
+      "learning_rate": 0.00023658781114460015,
+      "loss": 1.4227691650390626,
+      "step": 355
+    },
+    {
+      "epoch": 0.17733990147783252,
+      "grad_norm": 0.1434343308210373,
+      "learning_rate": 0.00023613487839986002,
+      "loss": 1.445096778869629,
+      "step": 360
+    },
+    {
+      "epoch": 0.17980295566502463,
+      "grad_norm": 0.16572657227516174,
+      "learning_rate": 0.00023567487277337224,
+      "loss": 1.4285211563110352,
+      "step": 365
+    },
+    {
+      "epoch": 0.18226600985221675,
+      "grad_norm": 0.1833866387605667,
+      "learning_rate": 0.00023520782354096304,
+      "loss": 1.425662136077881,
+      "step": 370
+    },
+    {
+      "epoch": 0.18472906403940886,
+      "grad_norm": 0.15879110991954803,
+      "learning_rate": 0.00023473376042673023,
+      "loss": 1.3996357917785645,
+      "step": 375
+    },
+    {
+      "epoch": 0.18719211822660098,
+      "grad_norm": 0.19990192353725433,
+      "learning_rate": 0.0002342527136011513,
+      "loss": 1.4143569946289063,
+      "step": 380
+    },
+    {
+      "epoch": 0.1896551724137931,
+      "grad_norm": 0.18486812710762024,
+      "learning_rate": 0.00023376471367916337,
+      "loss": 1.4033607482910155,
+      "step": 385
+    },
+    {
+      "epoch": 0.1921182266009852,
+      "grad_norm": 0.17442306876182556,
+      "learning_rate": 0.00023326979171821476,
+      "loss": 1.3730643272399903,
+      "step": 390
+    },
+    {
+      "epoch": 0.19458128078817735,
+      "grad_norm": 0.173421710729599,
+      "learning_rate": 0.00023276797921628837,
+      "loss": 1.3813364028930664,
+      "step": 395
+    },
+    {
+      "epoch": 0.19704433497536947,
+      "grad_norm": 0.1716538965702057,
+      "learning_rate": 0.0002322593081098972,
+      "loss": 1.422166633605957,
+      "step": 400
+    },
+    {
+      "epoch": 0.19950738916256158,
+      "grad_norm": 0.16969984769821167,
+      "learning_rate": 0.00023174381077205176,
+      "loss": 1.3688505172729493,
+      "step": 405
+    },
+    {
+      "epoch": 0.2019704433497537,
+      "grad_norm": 0.1701720952987671,
+      "learning_rate": 0.00023122152001019968,
+      "loss": 1.42032470703125,
+      "step": 410
+    },
+    {
+      "epoch": 0.2044334975369458,
+      "grad_norm": 0.16210104525089264,
+      "learning_rate": 0.00023069246906413807,
+      "loss": 1.3933750152587892,
+      "step": 415
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 0.1729843020439148,
+      "learning_rate": 0.00023015669160389766,
+      "loss": 1.372517204284668,
+      "step": 420
+    },
+    {
+      "epoch": 0.20935960591133004,
+      "grad_norm": 0.16887453198432922,
+      "learning_rate": 0.00022961422172760023,
+      "loss": 1.3911527633666991,
+      "step": 425
+    },
+    {
+      "epoch": 0.21182266009852216,
+      "grad_norm": 0.19436541199684143,
+      "learning_rate": 0.00022906509395928854,
+      "loss": 1.3760509490966797,
+      "step": 430
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.18449777364730835,
+      "learning_rate": 0.00022850934324672895,
+      "loss": 1.4072185516357423,
+      "step": 435
+    },
+    {
+      "epoch": 0.21674876847290642,
+      "grad_norm": 0.18370717763900757,
+      "learning_rate": 0.0002279470049591874,
+      "loss": 1.3903163909912108,
+      "step": 440
+    },
+    {
+      "epoch": 0.21921182266009853,
+      "grad_norm": 0.16729238629341125,
+      "learning_rate": 0.0002273781148851785,
+      "loss": 1.4293941497802733,
+      "step": 445
+    },
+    {
+      "epoch": 0.22167487684729065,
+      "grad_norm": 0.16858957707881927,
+      "learning_rate": 0.0002268027092301876,
+      "loss": 1.3823756217956542,
+      "step": 450
+    },
+    {
+      "epoch": 0.22413793103448276,
+      "grad_norm": 0.17020873725414276,
+      "learning_rate": 0.00022622082461436682,
+      "loss": 1.3988096237182617,
+      "step": 455
+    },
+    {
+      "epoch": 0.22660098522167488,
+      "grad_norm": 0.17294643819332123,
+      "learning_rate": 0.0002256324980702045,
+      "loss": 1.3739171981811524,
+      "step": 460
+    },
+    {
+      "epoch": 0.229064039408867,
+      "grad_norm": 0.17125867307186127,
+      "learning_rate": 0.0002250377670401681,
+      "loss": 1.3468008041381836,
+      "step": 465
+    },
+    {
+      "epoch": 0.2315270935960591,
+      "grad_norm": 0.17837369441986084,
+      "learning_rate": 0.00022443666937432155,
+      "loss": 1.4052190780639648,
+      "step": 470
+    },
+    {
+      "epoch": 0.23399014778325122,
+      "grad_norm": 0.1752692013978958,
+      "learning_rate": 0.00022382924332791615,
+      "loss": 1.3898029327392578,
+      "step": 475
+    },
+    {
+      "epoch": 0.23645320197044334,
+      "grad_norm": 0.1891223043203354,
+      "learning_rate": 0.00022321552755895618,
+      "loss": 1.354398536682129,
+      "step": 480
+    },
+    {
+      "epoch": 0.23891625615763548,
+      "grad_norm": 0.19426104426383972,
+      "learning_rate": 0.0002225955611257384,
+      "loss": 1.384025764465332,
+      "step": 485
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 0.17275558412075043,
+      "learning_rate": 0.0002219693834843663,
+      "loss": 1.4047843933105468,
+      "step": 490
+    },
+    {
+      "epoch": 0.2438423645320197,
+      "grad_norm": 0.1689615696668625,
+      "learning_rate": 0.00022133703448623914,
+      "loss": 1.3107892990112304,
+      "step": 495
+    },
+    {
+      "epoch": 0.24630541871921183,
+      "grad_norm": 0.2038181871175766,
+      "learning_rate": 0.00022069855437551573,
+      "loss": 1.3369841575622559,
+      "step": 500
+    },
+    {
+      "epoch": 0.24876847290640394,
+      "grad_norm": 0.17948555946350098,
+      "learning_rate": 0.00022005398378655296,
+      "loss": 1.3794227600097657,
+      "step": 505
+    },
+    {
+      "epoch": 0.2512315270935961,
+      "grad_norm": 0.17501185834407806,
+      "learning_rate": 0.00021940336374131998,
+      "loss": 1.4196930885314942,
+      "step": 510
+    },
+    {
+      "epoch": 0.2536945812807882,
+      "grad_norm": 0.2093033641576767,
+      "learning_rate": 0.0002187467356467875,
+      "loss": 1.3714283943176269,
+      "step": 515
+    },
+    {
+      "epoch": 0.2561576354679803,
+      "grad_norm": 0.16727226972579956,
+      "learning_rate": 0.0002180841412922922,
+      "loss": 1.3726673126220703,
+      "step": 520
+    },
+    {
+      "epoch": 0.25862068965517243,
+      "grad_norm": 0.17903991043567657,
+      "learning_rate": 0.0002174156228468776,
+      "loss": 1.358510971069336,
+      "step": 525
+    },
+    {
+      "epoch": 0.26108374384236455,
+      "grad_norm": 0.17160792648792267,
+      "learning_rate": 0.00021674122285661007,
+      "loss": 1.3609466552734375,
+      "step": 530
+    },
+    {
+      "epoch": 0.26354679802955666,
+      "grad_norm": 0.1898966133594513,
+      "learning_rate": 0.0002160609842418711,
+      "loss": 1.3312295913696288,
+      "step": 535
+    },
+    {
+      "epoch": 0.2660098522167488,
+      "grad_norm": 0.17584620416164398,
+      "learning_rate": 0.00021537495029462584,
+      "loss": 1.3631524085998534,
+      "step": 540
+    },
+    {
+      "epoch": 0.2684729064039409,
+      "grad_norm": 0.18318195641040802,
+      "learning_rate": 0.00021468316467566784,
+      "loss": 1.3585592269897462,
+      "step": 545
+    },
+    {
+      "epoch": 0.270935960591133,
+      "grad_norm": 0.22046172618865967,
+      "learning_rate": 0.00021398567141184044,
+      "loss": 1.3452308654785157,
+      "step": 550
+    },
+    {
+      "epoch": 0.2733990147783251,
+      "grad_norm": 0.18428301811218262,
+      "learning_rate": 0.0002132825148932347,
+      "loss": 1.3319664001464844,
+      "step": 555
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 0.16791480779647827,
+      "learning_rate": 0.00021257373987036444,
+      "loss": 1.3558830261230468,
+      "step": 560
+    },
+    {
+      "epoch": 0.27832512315270935,
+      "grad_norm": 0.16549845039844513,
+      "learning_rate": 0.00021185939145131806,
+      "loss": 1.3690947532653808,
+      "step": 565
+    },
+    {
+      "epoch": 0.28078817733990147,
+      "grad_norm": 0.18301844596862793,
+      "learning_rate": 0.00021113951509888786,
+      "loss": 1.3542755126953125,
+      "step": 570
+    },
+    {
+      "epoch": 0.2832512315270936,
+      "grad_norm": 0.1825488954782486,
+      "learning_rate": 0.00021041415662767662,
+      "loss": 1.3548131942749024,
+      "step": 575
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.16749636828899384,
+      "learning_rate": 0.000209683362201182,
+      "loss": 1.3456719398498536,
+      "step": 580
+    },
+    {
+      "epoch": 0.2881773399014778,
+      "grad_norm": 0.17608295381069183,
+      "learning_rate": 0.0002089471783288584,
+      "loss": 1.3705681800842284,
+      "step": 585
+    },
+    {
+      "epoch": 0.29064039408866993,
+      "grad_norm": 0.17070530354976654,
+      "learning_rate": 0.00020820565186315708,
+      "loss": 1.3699356079101563,
+      "step": 590
+    },
+    {
+      "epoch": 0.29310344827586204,
+      "grad_norm": 0.1745534986257553,
+      "learning_rate": 0.00020745882999654436,
+      "loss": 1.3450947761535645,
+      "step": 595
+    },
+    {
+      "epoch": 0.2955665024630542,
+      "grad_norm": 0.16439899802207947,
+      "learning_rate": 0.0002067067602584981,
+      "loss": 1.3508234024047852,
+      "step": 600
+    },
+    {
+      "epoch": 0.29802955665024633,
+      "grad_norm": 0.1894385665655136,
+      "learning_rate": 0.000205949490512483,
+      "loss": 1.351315402984619,
+      "step": 605
+    },
+    {
+      "epoch": 0.30049261083743845,
+      "grad_norm": 0.1537814885377884,
+      "learning_rate": 0.0002051870689529043,
+      "loss": 1.3379337310791015,
+      "step": 610
+    },
+    {
+      "epoch": 0.30295566502463056,
+      "grad_norm": 0.17749722301959991,
+      "learning_rate": 0.00020441954410204056,
+      "loss": 1.371589183807373,
+      "step": 615
+    },
+    {
+      "epoch": 0.3054187192118227,
+      "grad_norm": 0.1515127718448639,
+      "learning_rate": 0.00020364696480695572,
+      "loss": 1.382241439819336,
+      "step": 620
+    },
+    {
+      "epoch": 0.3078817733990148,
+      "grad_norm": 0.19499871134757996,
+      "learning_rate": 0.00020286938023639025,
+      "loss": 1.321158218383789,
+      "step": 625
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 0.1817796230316162,
+      "learning_rate": 0.00020208683987763202,
+      "loss": 1.2779136657714845,
+      "step": 630
+    },
+    {
+      "epoch": 0.312807881773399,
+      "grad_norm": 0.20046235620975494,
+      "learning_rate": 0.00020129939353336673,
+      "loss": 1.373447799682617,
+      "step": 635
+    },
+    {
+      "epoch": 0.31527093596059114,
+      "grad_norm": 0.17454685270786285,
+      "learning_rate": 0.00020050709131850842,
+      "loss": 1.3511387825012207,
+      "step": 640
+    },
+    {
+      "epoch": 0.31773399014778325,
+      "grad_norm": 0.15645831823349,
+      "learning_rate": 0.00019970998365700994,
+      "loss": 1.3556259155273438,
+      "step": 645
+    },
+    {
+      "epoch": 0.32019704433497537,
+      "grad_norm": 0.23432165384292603,
+      "learning_rate": 0.00019890812127865398,
+      "loss": 1.3702130317687988,
+      "step": 650
+    },
+    {
+      "epoch": 0.3226600985221675,
+      "grad_norm": 0.19228830933570862,
+      "learning_rate": 0.00019810155521582452,
+      "loss": 1.3509254455566406,
+      "step": 655
+    },
+    {
+      "epoch": 0.3251231527093596,
+      "grad_norm": 0.17956726253032684,
+      "learning_rate": 0.0001972903368002588,
+      "loss": 1.3903903007507323,
+      "step": 660
+    },
+    {
+      "epoch": 0.3275862068965517,
+      "grad_norm": 0.1781313717365265,
+      "learning_rate": 0.00019647451765978066,
+      "loss": 1.3841757774353027,
+      "step": 665
+    },
+    {
+      "epoch": 0.33004926108374383,
+      "grad_norm": 0.18768683075904846,
+      "learning_rate": 0.0001956541497150148,
+      "loss": 1.2905200004577637,
+      "step": 670
+    },
+    {
+      "epoch": 0.33251231527093594,
+      "grad_norm": 0.16383622586727142,
+      "learning_rate": 0.00019482928517608236,
+      "loss": 1.360379409790039,
+      "step": 675
+    },
+    {
+      "epoch": 0.33497536945812806,
+      "grad_norm": 0.16578137874603271,
+      "learning_rate": 0.00019399997653927808,
+      "loss": 1.278472900390625,
+      "step": 680
+    },
+    {
+      "epoch": 0.3374384236453202,
+      "grad_norm": 0.1965074986219406,
+      "learning_rate": 0.00019316627658372965,
+      "loss": 1.2946483612060546,
+      "step": 685
+    },
+    {
+      "epoch": 0.3399014778325123,
+      "grad_norm": 0.16846999526023865,
+      "learning_rate": 0.00019232823836803814,
+      "loss": 1.3446279525756837,
+      "step": 690
+    },
+    {
+      "epoch": 0.34236453201970446,
+      "grad_norm": 0.1912621706724167,
+      "learning_rate": 0.00019148591522690186,
+      "loss": 1.286168098449707,
+      "step": 695
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 0.1728268563747406,
+      "learning_rate": 0.00019063936076772165,
+      "loss": 1.310130786895752,
+      "step": 700
+    },
+    {
+      "epoch": 0.3472906403940887,
+      "grad_norm": 0.1802312731742859,
+      "learning_rate": 0.00018978862886718912,
+      "loss": 1.3130574226379395,
+      "step": 705
+    },
+    {
+      "epoch": 0.3497536945812808,
+      "grad_norm": 0.21355324983596802,
+      "learning_rate": 0.0001889337736678582,
+      "loss": 1.315770435333252,
+      "step": 710
+    },
+    {
+      "epoch": 0.3522167487684729,
+      "grad_norm": 0.18635617196559906,
+      "learning_rate": 0.00018807484957469883,
+      "loss": 1.2871192932128905,
+      "step": 715
+    },
+    {
+      "epoch": 0.35467980295566504,
+      "grad_norm": 0.19419880211353302,
+      "learning_rate": 0.0001872119112516351,
+      "loss": 1.349839687347412,
+      "step": 720
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.17950312793254852,
+      "learning_rate": 0.00018634501361806583,
+      "loss": 1.2936307907104492,
+      "step": 725
+    },
+    {
+      "epoch": 0.35960591133004927,
+      "grad_norm": 0.19235140085220337,
+      "learning_rate": 0.00018547421184536954,
+      "loss": 1.3393970489501954,
+      "step": 730
+    },
+    {
+      "epoch": 0.3620689655172414,
+      "grad_norm": 0.17759372293949127,
+      "learning_rate": 0.00018459956135339337,
+      "loss": 1.2816192626953125,
+      "step": 735
+    },
+    {
+      "epoch": 0.3645320197044335,
+      "grad_norm": 0.23250320553779602,
+      "learning_rate": 0.00018372111780692578,
+      "loss": 1.3334604263305665,
+      "step": 740
+    },
+    {
+      "epoch": 0.3669950738916256,
+      "grad_norm": 0.17436301708221436,
+      "learning_rate": 0.00018283893711215404,
+      "loss": 1.3083503723144532,
+      "step": 745
+    },
+    {
+      "epoch": 0.3694581280788177,
+      "grad_norm": 0.18099693953990936,
+      "learning_rate": 0.00018195307541310629,
+      "loss": 1.3178603172302246,
+      "step": 750
+    },
+    {
+      "epoch": 0.37192118226600984,
+      "grad_norm": 0.269329309463501,
+      "learning_rate": 0.00018106358908807817,
+      "loss": 1.3349596023559571,
+      "step": 755
+    },
+    {
+      "epoch": 0.37438423645320196,
+      "grad_norm": 0.18420232832431793,
+      "learning_rate": 0.0001801705347460452,
+      "loss": 1.3219612121582032,
+      "step": 760
+    },
+    {
+      "epoch": 0.3768472906403941,
+      "grad_norm": 0.18118754029273987,
+      "learning_rate": 0.0001792739692230595,
+      "loss": 1.3394298553466797,
+      "step": 765
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 0.17812423408031464,
+      "learning_rate": 0.0001783739495786331,
+      "loss": 1.323796272277832,
+      "step": 770
+    },
+    {
+      "epoch": 0.3817733990147783,
+      "grad_norm": 0.19593380391597748,
+      "learning_rate": 0.0001774705330921062,
+      "loss": 1.286915111541748,
+      "step": 775
+    },
+    {
+      "epoch": 0.3842364532019704,
+      "grad_norm": 0.17664848268032074,
+      "learning_rate": 0.00017656377725900208,
+      "loss": 1.3362086296081543,
+      "step": 780
+    },
+    {
+      "epoch": 0.3866995073891626,
+      "grad_norm": 0.17172090709209442,
+      "learning_rate": 0.00017565373978736763,
+      "loss": 1.3063836097717285,
+      "step": 785
+    },
+    {
+      "epoch": 0.3891625615763547,
+      "grad_norm": 0.18463967740535736,
+      "learning_rate": 0.00017474047859410093,
+      "loss": 1.302729892730713,
+      "step": 790
+    },
+    {
+      "epoch": 0.3916256157635468,
+      "grad_norm": 0.20453161001205444,
+      "learning_rate": 0.00017382405180126518,
+      "loss": 1.3212371826171876,
+      "step": 795
+    },
+    {
+      "epoch": 0.39408866995073893,
+      "grad_norm": 0.2201971560716629,
+      "learning_rate": 0.00017290451773238963,
+      "loss": 1.2563053131103517,
+      "step": 800
+    },
+    {
+      "epoch": 0.39655172413793105,
+      "grad_norm": 0.18436840176582336,
+      "learning_rate": 0.00017198193490875786,
+      "loss": 1.2558401107788086,
+      "step": 805
+    },
+    {
+      "epoch": 0.39901477832512317,
+      "grad_norm": 0.1734287142753601,
+      "learning_rate": 0.00017105636204568333,
+      "loss": 1.2716167449951172,
+      "step": 810
+    },
+    {
+      "epoch": 0.4014778325123153,
+      "grad_norm": 0.2016817331314087,
+      "learning_rate": 0.00017012785804877237,
+      "loss": 1.2854512214660645,
+      "step": 815
+    },
+    {
+      "epoch": 0.4039408866995074,
+      "grad_norm": 0.16567033529281616,
+      "learning_rate": 0.00016919648201017568,
+      "loss": 1.253489112854004,
+      "step": 820
+    },
+    {
+      "epoch": 0.4064039408866995,
+      "grad_norm": 0.20947584509849548,
+      "learning_rate": 0.00016826229320482728,
+      "loss": 1.2323739051818847,
+      "step": 825
+    },
+    {
+      "epoch": 0.4088669950738916,
+      "grad_norm": 0.18364252150058746,
+      "learning_rate": 0.00016732535108667207,
+      "loss": 1.2492031097412108,
+      "step": 830
+    },
+    {
+      "epoch": 0.41133004926108374,
+      "grad_norm": 0.16092689335346222,
+      "learning_rate": 0.00016638571528488244,
+      "loss": 1.2878339767456055,
+      "step": 835
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 0.1873292475938797,
+      "learning_rate": 0.0001654434456000628,
+      "loss": 1.2998780250549316,
+      "step": 840
+    },
+    {
+      "epoch": 0.41625615763546797,
+      "grad_norm": 0.2125275880098343,
+      "learning_rate": 0.0001644986020004442,
+      "loss": 1.2909418106079102,
+      "step": 845
+    },
+    {
+      "epoch": 0.4187192118226601,
+      "grad_norm": 0.17675183713436127,
+      "learning_rate": 0.00016355124461806745,
+      "loss": 1.2425660133361816,
+      "step": 850
+    },
+    {
+      "epoch": 0.4211822660098522,
+      "grad_norm": 0.2152215540409088,
+      "learning_rate": 0.00016260143374495639,
+      "loss": 1.3083280563354491,
+      "step": 855
+    },
+    {
+      "epoch": 0.4236453201970443,
+      "grad_norm": 0.2069772332906723,
+      "learning_rate": 0.00016164922982928073,
+      "loss": 1.2619693756103516,
+      "step": 860
+    },
+    {
+      "epoch": 0.42610837438423643,
+      "grad_norm": 0.19488738477230072,
+      "learning_rate": 0.000160694693471509,
+      "loss": 1.2362824440002442,
+      "step": 865
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.17941637337207794,
+      "learning_rate": 0.00015973788542055162,
+      "loss": 1.2109522819519043,
+      "step": 870
+    },
+    {
+      "epoch": 0.43103448275862066,
+      "grad_norm": 0.18050067126750946,
+      "learning_rate": 0.00015877886656989493,
+      "loss": 1.286395263671875,
+      "step": 875
+    },
+    {
+      "epoch": 0.43349753694581283,
+      "grad_norm": 0.1821620911359787,
+      "learning_rate": 0.0001578176979537258,
+      "loss": 1.248922348022461,
+      "step": 880
+    },
+    {
+      "epoch": 0.43596059113300495,
+      "grad_norm": 0.25863558053970337,
+      "learning_rate": 0.00015685444074304698,
+      "loss": 1.248793125152588,
+      "step": 885
+    },
+    {
+      "epoch": 0.43842364532019706,
+      "grad_norm": 0.19712696969509125,
+      "learning_rate": 0.00015588915624178428,
+      "loss": 1.2442864418029784,
+      "step": 890
+    },
+    {
+      "epoch": 0.4408866995073892,
+      "grad_norm": 0.18720319867134094,
+      "learning_rate": 0.00015492190588288517,
+      "loss": 1.2700700759887695,
+      "step": 895
+    },
+    {
+      "epoch": 0.4433497536945813,
+      "grad_norm": 0.16144616901874542,
+      "learning_rate": 0.00015395275122440856,
+      "loss": 1.2769156455993653,
+      "step": 900
+    },
+    {
+      "epoch": 0.4458128078817734,
+      "grad_norm": 0.193702831864357,
+      "learning_rate": 0.0001529817539456076,
+      "loss": 1.234379482269287,
+      "step": 905
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 0.2000775784254074,
+      "learning_rate": 0.00015200897584300414,
+      "loss": 1.2801446914672852,
+      "step": 910
+    },
+    {
+      "epoch": 0.45073891625615764,
+      "grad_norm": 0.18480932712554932,
+      "learning_rate": 0.00015103447882645554,
+      "loss": 1.2297477722167969,
+      "step": 915
+    },
+    {
+      "epoch": 0.45320197044334976,
+      "grad_norm": 0.242837592959404,
+      "learning_rate": 0.00015005832491521513,
+      "loss": 1.313267421722412,
+      "step": 920
+    },
+    {
+      "epoch": 0.45566502463054187,
+      "grad_norm": 0.16983121633529663,
+      "learning_rate": 0.00014908057623398463,
+      "loss": 1.302457904815674,
+      "step": 925
+    },
+    {
+      "epoch": 0.458128078817734,
+      "grad_norm": 0.19708214700222015,
+      "learning_rate": 0.00014810129500896074,
+      "loss": 1.2397549629211426,
+      "step": 930
+    },
+    {
+      "epoch": 0.4605911330049261,
+      "grad_norm": 0.23579345643520355,
+      "learning_rate": 0.0001471205435638748,
+      "loss": 1.2467019081115722,
+      "step": 935
+    },
+    {
+      "epoch": 0.4630541871921182,
+      "grad_norm": 0.1848316192626953,
+      "learning_rate": 0.00014613838431602635,
+      "loss": 1.2351249694824218,
+      "step": 940
+    },
+    {
+      "epoch": 0.46551724137931033,
+      "grad_norm": 0.18563935160636902,
+      "learning_rate": 0.00014515487977231082,
+      "loss": 1.2387422561645507,
+      "step": 945
+    },
+    {
+      "epoch": 0.46798029556650245,
+      "grad_norm": 0.20925939083099365,
+      "learning_rate": 0.00014417009252524126,
+      "loss": 1.2436027526855469,
+      "step": 950
+    },
+    {
+      "epoch": 0.47044334975369456,
+      "grad_norm": 0.21446797251701355,
+      "learning_rate": 0.00014318408524896506,
+      "loss": 1.189046287536621,
+      "step": 955
+    },
+    {
+      "epoch": 0.4729064039408867,
+      "grad_norm": 0.20368950068950653,
+      "learning_rate": 0.00014219692069527507,
+      "loss": 1.3030234336853028,
+      "step": 960
+    },
+    {
+      "epoch": 0.4753694581280788,
+      "grad_norm": 0.2103145718574524,
+      "learning_rate": 0.000141208661689616,
+      "loss": 1.2151473999023437,
+      "step": 965
+    },
+    {
+      "epoch": 0.47783251231527096,
+      "grad_norm": 0.18451350927352905,
+      "learning_rate": 0.0001402193711270859,
+      "loss": 1.2333395957946778,
+      "step": 970
+    },
+    {
+      "epoch": 0.4802955665024631,
+      "grad_norm": 0.2466631531715393,
+      "learning_rate": 0.00013922911196843362,
+      "loss": 1.2488998413085937,
+      "step": 975
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 0.20584948360919952,
+      "learning_rate": 0.00013823794723605176,
+      "loss": 1.2555919647216798,
+      "step": 980
+    },
+    {
+      "epoch": 0.4852216748768473,
+      "grad_norm": 0.20075443387031555,
+      "learning_rate": 0.0001372459400099655,
+      "loss": 1.2696216583251954,
+      "step": 985
+    },
+    {
+      "epoch": 0.4876847290640394,
+      "grad_norm": 0.19442631304264069,
+      "learning_rate": 0.0001362531534238185,
+      "loss": 1.2640766143798827,
+      "step": 990
+    },
+    {
+      "epoch": 0.49014778325123154,
+      "grad_norm": 0.19115300476551056,
+      "learning_rate": 0.0001352596506608547,
+      "loss": 1.2196426391601562,
+      "step": 995
+    },
+    {
+      "epoch": 0.49261083743842365,
+      "grad_norm": 0.1893470585346222,
+      "learning_rate": 0.000134265494949897,
+      "loss": 1.2342331886291504,
+      "step": 1000
+    },
+    {
+      "epoch": 0.49507389162561577,
+      "grad_norm": 0.21104690432548523,
+      "learning_rate": 0.00013327074956132363,
+      "loss": 1.204904556274414,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4975369458128079,
+      "grad_norm": 0.18888571858406067,
+      "learning_rate": 0.00013227547780304117,
+      "loss": 1.256018829345703,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.1692684292793274,
+      "learning_rate": 0.0001312797430164556,
+      "loss": 1.201275634765625,
+      "step": 1015
+    },
+    {
+      "epoch": 0.5024630541871922,
+      "grad_norm": 0.18483807146549225,
+      "learning_rate": 0.00013028360857244117,
+      "loss": 1.2124223709106445,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5049261083743842,
+      "grad_norm": 0.22120992839336395,
+      "learning_rate": 0.00012928713786730718,
+      "loss": 1.1901243209838868,
+      "step": 1025
+    },
+    {
+      "epoch": 0.5073891625615764,
+      "grad_norm": 0.2057364135980606,
+      "learning_rate": 0.00012829039431876336,
+      "loss": 1.2593475341796876,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5098522167487685,
+      "grad_norm": 0.1822461038827896,
+      "learning_rate": 0.0001272934413618839,
+      "loss": 1.2332374572753906,
+      "step": 1035
+    },
+    {
+      "epoch": 0.5123152709359606,
+      "grad_norm": 0.16532449424266815,
+      "learning_rate": 0.0001262963424450701,
+      "loss": 1.240938377380371,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5147783251231527,
+      "grad_norm": 0.21303096413612366,
+      "learning_rate": 0.00012529916102601267,
+      "loss": 1.2548458099365234,
+      "step": 1045
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 0.18367333710193634,
+      "learning_rate": 0.00012430196056765282,
+      "loss": 1.2288077354431153,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5197044334975369,
+      "grad_norm": 0.18319977819919586,
+      "learning_rate": 0.00012330480453414343,
+      "loss": 1.1961639404296875,
+      "step": 1055
+    },
+    {
+      "epoch": 0.5221674876847291,
+      "grad_norm": 0.2004910558462143,
+      "learning_rate": 0.00012230775638681027,
+      "loss": 1.2295507431030273,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5246305418719212,
+      "grad_norm": 0.1947339028120041,
+      "learning_rate": 0.00012131087958011277,
+      "loss": 1.1608522415161133,
+      "step": 1065
+    },
+    {
+      "epoch": 0.5270935960591133,
+      "grad_norm": 0.18667319416999817,
+      "learning_rate": 0.00012031423755760597,
+      "loss": 1.2403168678283691,
+      "step": 1070
+    },
+    {
+      "epoch": 0.5295566502463054,
+      "grad_norm": 0.21123482286930084,
+      "learning_rate": 0.00011931789374790263,
+      "loss": 1.2123674392700194,
+      "step": 1075
+    },
+    {
+      "epoch": 0.5320197044334976,
+      "grad_norm": 0.1750740259885788,
+      "learning_rate": 0.00011832191156063663,
+      "loss": 1.1695655822753905,
+      "step": 1080
+    },
+    {
+      "epoch": 0.5344827586206896,
+      "grad_norm": 0.22137445211410522,
+      "learning_rate": 0.00011732635438242737,
+      "loss": 1.1810033798217774,
+      "step": 1085
+    },
+    {
+      "epoch": 0.5369458128078818,
+      "grad_norm": 0.21186146140098572,
+      "learning_rate": 0.00011633128557284549,
+      "loss": 1.2429140090942383,
+      "step": 1090
+    },
+    {
+      "epoch": 0.5394088669950738,
+      "grad_norm": 0.1863589733839035,
+      "learning_rate": 0.00011533676846038096,
+      "loss": 1.2485341072082519,
+      "step": 1095
+    },
+    {
+      "epoch": 0.541871921182266,
+      "grad_norm": 0.18336571753025055,
+      "learning_rate": 0.00011434286633841233,
+      "loss": 1.2189826965332031,
+      "step": 1100
+    },
+    {
+      "epoch": 0.5443349753694581,
+      "grad_norm": 0.18501920998096466,
+      "learning_rate": 0.0001133496424611788,
+      "loss": 1.151944923400879,
+      "step": 1105
+    },
+    {
+      "epoch": 0.5467980295566502,
+      "grad_norm": 0.20163634419441223,
+      "learning_rate": 0.00011235716003975446,
+      "loss": 1.220255470275879,
+      "step": 1110
+    },
+    {
+      "epoch": 0.5492610837438424,
+      "grad_norm": 0.2223639190196991,
+      "learning_rate": 0.00011136548223802535,
+      "loss": 1.240659523010254,
+      "step": 1115
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 0.17450086772441864,
+      "learning_rate": 0.0001103746721686698,
+      "loss": 1.1981927871704101,
+      "step": 1120
+    },
+    {
+      "epoch": 0.5541871921182266,
+      "grad_norm": 0.19839145243167877,
+      "learning_rate": 0.00010938479288914156,
+      "loss": 1.197626495361328,
+      "step": 1125
+    },
+    {
+      "epoch": 0.5566502463054187,
+      "grad_norm": 0.1841588318347931,
+      "learning_rate": 0.00010839590739765672,
+      "loss": 1.264552402496338,
+      "step": 1130
+    },
+    {
+      "epoch": 0.5591133004926109,
+      "grad_norm": 0.19713954627513885,
+      "learning_rate": 0.00010740807862918452,
+      "loss": 1.2125371932983398,
+      "step": 1135
+    },
+    {
+      "epoch": 0.5615763546798029,
+      "grad_norm": 0.16765552759170532,
+      "learning_rate": 0.00010642136945144168,
+      "loss": 1.168004035949707,
+      "step": 1140
+    },
+    {
+      "epoch": 0.5640394088669951,
+      "grad_norm": 0.22502478957176208,
+      "learning_rate": 0.00010543584266089172,
+      "loss": 1.241142463684082,
+      "step": 1145
+    },
+    {
+      "epoch": 0.5665024630541872,
+      "grad_norm": 0.20629556477069855,
+      "learning_rate": 0.00010445156097874831,
+      "loss": 1.2195361137390137,
+      "step": 1150
+    },
+    {
+      "epoch": 0.5689655172413793,
+      "grad_norm": 0.18252435326576233,
+      "learning_rate": 0.00010346858704698342,
+      "loss": 1.2338192939758301,
+      "step": 1155
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.20209062099456787,
+      "learning_rate": 0.00010248698342434088,
+      "loss": 1.16652193069458,
+      "step": 1160
+    },
+    {
+      "epoch": 0.5738916256157636,
+      "grad_norm": 0.22693181037902832,
+      "learning_rate": 0.00010150681258235476,
+      "loss": 1.2255271911621093,
+      "step": 1165
+    },
+    {
+      "epoch": 0.5763546798029556,
+      "grad_norm": 0.22251495718955994,
+      "learning_rate": 0.00010052813690137359,
+      "loss": 1.2631017684936523,
+      "step": 1170
+    },
+    {
+      "epoch": 0.5788177339901478,
+      "grad_norm": 0.21778655052185059,
+      "learning_rate": 9.955101866659058e-05,
+      "loss": 1.1939207077026368,
+      "step": 1175
+    },
+    {
+      "epoch": 0.5812807881773399,
+      "grad_norm": 0.18302731215953827,
+      "learning_rate": 9.85755200640793e-05,
+      "loss": 1.2109046936035157,
+      "step": 1180
+    },
+    {
+      "epoch": 0.583743842364532,
+      "grad_norm": 0.16752716898918152,
+      "learning_rate": 9.760170317683622e-05,
+      "loss": 1.2556650161743164,
+      "step": 1185
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 0.230145663022995,
+      "learning_rate": 9.662962998082945e-05,
+      "loss": 1.1849594116210938,
+      "step": 1190
+    },
+    {
+      "epoch": 0.5886699507389163,
+      "grad_norm": 0.19752813875675201,
+      "learning_rate": 9.565936234105469e-05,
+      "loss": 1.2816810607910156,
+      "step": 1195
+    },
+    {
+      "epoch": 0.5911330049261084,
+      "grad_norm": 0.18858280777931213,
+      "learning_rate": 9.469096200759768e-05,
+      "loss": 1.1605751991271973,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5935960591133005,
+      "grad_norm": 0.24590526521205902,
+      "learning_rate": 9.372449061170462e-05,
+      "loss": 1.1848978042602538,
+      "step": 1205
+    },
+    {
+      "epoch": 0.5960591133004927,
+      "grad_norm": 0.21344885230064392,
+      "learning_rate": 9.276000966185957e-05,
+      "loss": 1.2841413497924805,
+      "step": 1210
+    },
+    {
+      "epoch": 0.5985221674876847,
+      "grad_norm": 0.19670014083385468,
+      "learning_rate": 9.179758053986988e-05,
+      "loss": 1.1918867111206055,
+      "step": 1215
+    },
+    {
+      "epoch": 0.6009852216748769,
+      "grad_norm": 0.1846807897090912,
+      "learning_rate": 9.083726449695995e-05,
+      "loss": 1.2194841384887696,
+      "step": 1220
+    },
+    {
+      "epoch": 0.603448275862069,
+      "grad_norm": 0.20464275777339935,
+      "learning_rate": 8.987912264987291e-05,
+      "loss": 1.183926773071289,
+      "step": 1225
+    },
+    {
+      "epoch": 0.6059113300492611,
+      "grad_norm": 0.20124205946922302,
+      "learning_rate": 8.892321597698093e-05,
+      "loss": 1.219172477722168,
+      "step": 1230
+    },
+    {
+      "epoch": 0.6083743842364532,
+      "grad_norm": 0.17859403789043427,
+      "learning_rate": 8.796960531440464e-05,
+      "loss": 1.2153097152709962,
+      "step": 1235
+    },
+    {
+      "epoch": 0.6108374384236454,
+      "grad_norm": 0.18714755773544312,
+      "learning_rate": 8.701835135214107e-05,
+      "loss": 1.162564754486084,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6133004926108374,
+      "grad_norm": 0.22420014441013336,
+      "learning_rate": 8.606951463020144e-05,
+      "loss": 1.183693790435791,
+      "step": 1245
+    },
+    {
+      "epoch": 0.6157635467980296,
+      "grad_norm": 0.21470965445041656,
+      "learning_rate": 8.51231555347583e-05,
+      "loss": 1.2216785430908204,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6182266009852216,
+      "grad_norm": 0.21227896213531494,
+      "learning_rate": 8.417933429430209e-05,
+      "loss": 1.2861865997314452,
+      "step": 1255
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 0.202324777841568,
+      "learning_rate": 8.323811097580848e-05,
+      "loss": 1.2060440063476563,
+      "step": 1260
+    },
+    {
+      "epoch": 0.6231527093596059,
+      "grad_norm": 0.2296363115310669,
+      "learning_rate": 8.229954548091516e-05,
+      "loss": 1.1578837394714356,
+      "step": 1265
+    },
+    {
+      "epoch": 0.625615763546798,
+      "grad_norm": 0.20132364332675934,
+      "learning_rate": 8.136369754210983e-05,
+      "loss": 1.1610750198364257,
+      "step": 1270
+    },
+    {
+      "epoch": 0.6280788177339901,
+      "grad_norm": 0.2226463258266449,
+      "learning_rate": 8.043062671892864e-05,
+      "loss": 1.2300620079040527,
+      "step": 1275
+    },
+    {
+      "epoch": 0.6305418719211823,
+      "grad_norm": 0.22128857672214508,
+      "learning_rate": 7.950039239416567e-05,
+      "loss": 1.1859933853149414,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6330049261083743,
+      "grad_norm": 0.2043779343366623,
+      "learning_rate": 7.857305377009362e-05,
+      "loss": 1.186697769165039,
+      "step": 1285
+    },
+    {
+      "epoch": 0.6354679802955665,
+      "grad_norm": 0.25842151045799255,
+      "learning_rate": 7.764866986469597e-05,
+      "loss": 1.2317033767700196,
+      "step": 1290
+    },
+    {
+      "epoch": 0.6379310344827587,
+      "grad_norm": 0.2195252776145935,
+      "learning_rate": 7.672729950791119e-05,
+      "loss": 1.249120330810547,
+      "step": 1295
+    },
+    {
+      "epoch": 0.6403940886699507,
+      "grad_norm": 0.2110535055398941,
+      "learning_rate": 7.580900133788846e-05,
+      "loss": 1.2321800231933593,
+      "step": 1300
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.20861026644706726,
+      "learning_rate": 7.489383379725593e-05,
+      "loss": 1.19771089553833,
+      "step": 1305
+    },
+    {
+      "epoch": 0.645320197044335,
+      "grad_norm": 0.1993318647146225,
+      "learning_rate": 7.398185512940108e-05,
+      "loss": 1.2615684509277343,
+      "step": 1310
+    },
+    {
+      "epoch": 0.6477832512315271,
+      "grad_norm": 0.2071300446987152,
+      "learning_rate": 7.30731233747642e-05,
+      "loss": 1.145263385772705,
+      "step": 1315
+    },
+    {
+      "epoch": 0.6502463054187192,
+      "grad_norm": 0.19091857969760895,
+      "learning_rate": 7.216769636714453e-05,
+      "loss": 1.1866063117980956,
+      "step": 1320
+    },
+    {
+      "epoch": 0.6527093596059114,
+      "grad_norm": 0.22963383793830872,
+      "learning_rate": 7.126563173001948e-05,
+      "loss": 1.1944002151489257,
+      "step": 1325
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 0.2336658239364624,
+      "learning_rate": 7.03669868728774e-05,
+      "loss": 1.1321887969970703,
+      "step": 1330
+    },
+    {
+      "epoch": 0.6576354679802956,
+      "grad_norm": 0.21361377835273743,
+      "learning_rate": 6.947181898756391e-05,
+      "loss": 1.1836668014526368,
+      "step": 1335
+    },
+    {
+      "epoch": 0.6600985221674877,
+      "grad_norm": 0.18105630576610565,
+      "learning_rate": 6.858018504464206e-05,
+      "loss": 1.174211311340332,
+      "step": 1340
+    },
+    {
+      "epoch": 0.6625615763546798,
+      "grad_norm": 0.20631127059459686,
+      "learning_rate": 6.769214178976659e-05,
+      "loss": 1.1820557594299317,
+      "step": 1345
+    },
+    {
+      "epoch": 0.6650246305418719,
+      "grad_norm": 0.20737133920192719,
+      "learning_rate": 6.680774574007248e-05,
+      "loss": 1.1477078437805175,
+      "step": 1350
+    },
+    {
+      "epoch": 0.6674876847290641,
+      "grad_norm": 0.2014138400554657,
+      "learning_rate": 6.592705318057829e-05,
+      "loss": 1.1958050727844238,
+      "step": 1355
+    },
+    {
+      "epoch": 0.6699507389162561,
+      "grad_norm": 0.1984228491783142,
+      "learning_rate": 6.505012016060359e-05,
+      "loss": 1.2013264656066895,
+      "step": 1360
+    },
+    {
+      "epoch": 0.6724137931034483,
+      "grad_norm": 0.21650835871696472,
+      "learning_rate": 6.417700249020225e-05,
+      "loss": 1.067345428466797,
+      "step": 1365
+    },
+    {
+      "epoch": 0.6748768472906403,
+      "grad_norm": 0.22816705703735352,
+      "learning_rate": 6.330775573661052e-05,
+      "loss": 1.079237461090088,
+      "step": 1370
+    },
+    {
+      "epoch": 0.6773399014778325,
+      "grad_norm": 0.281549334526062,
+      "learning_rate": 6.244243522071042e-05,
+      "loss": 1.130068588256836,
+      "step": 1375
+    },
+    {
+      "epoch": 0.6798029556650246,
+      "grad_norm": 0.19611990451812744,
+      "learning_rate": 6.158109601350904e-05,
+      "loss": 1.0488746643066407,
+      "step": 1380
+    },
+    {
+      "epoch": 0.6822660098522167,
+      "grad_norm": 0.17916269600391388,
+      "learning_rate": 6.072379293263386e-05,
+      "loss": 1.1391111373901368,
+      "step": 1385
+    },
+    {
+      "epoch": 0.6847290640394089,
+      "grad_norm": 0.23221410810947418,
+      "learning_rate": 5.987058053884381e-05,
+      "loss": 1.2475336074829102,
+      "step": 1390
+    },
+    {
+      "epoch": 0.687192118226601,
+      "grad_norm": 0.20093056559562683,
+      "learning_rate": 5.9021513132557e-05,
+      "loss": 1.1227322578430177,
+      "step": 1395
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 0.24799276888370514,
+      "learning_rate": 5.817664475039503e-05,
+      "loss": 1.165380096435547,
+      "step": 1400
+    },
+    {
+      "epoch": 0.6921182266009852,
+      "grad_norm": 0.20954038202762604,
+      "learning_rate": 5.733602916174373e-05,
+      "loss": 1.2067898750305175,
+      "step": 1405
+    },
+    {
+      "epoch": 0.6945812807881774,
+      "grad_norm": 0.18297694623470306,
+      "learning_rate": 5.64997198653312e-05,
+      "loss": 1.1730698585510253,
+      "step": 1410
+    },
+    {
+      "epoch": 0.6970443349753694,
+      "grad_norm": 0.2150280922651291,
+      "learning_rate": 5.566777008582336e-05,
+      "loss": 1.1436220169067384,
+      "step": 1415
+    },
+    {
+      "epoch": 0.6995073891625616,
+      "grad_norm": 0.18874844908714294,
+      "learning_rate": 5.484023277043611e-05,
+      "loss": 1.286226177215576,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7019704433497537,
+      "grad_norm": 0.213956817984581,
+      "learning_rate": 5.401716058556595e-05,
+      "loss": 1.1404090881347657,
+      "step": 1425
+    },
+    {
+      "epoch": 0.7044334975369458,
+      "grad_norm": 0.2290380448102951,
+      "learning_rate": 5.319860591343828e-05,
+      "loss": 1.1688507080078125,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7068965517241379,
+      "grad_norm": 0.21498431265354156,
+      "learning_rate": 5.238462084877319e-05,
+      "loss": 1.1721858978271484,
+      "step": 1435
+    },
+    {
+      "epoch": 0.7093596059113301,
+      "grad_norm": 0.1930016726255417,
+      "learning_rate": 5.15752571954705e-05,
+      "loss": 1.1049509048461914,
+      "step": 1440
+    },
+    {
+      "epoch": 0.7118226600985221,
+      "grad_norm": 0.2106369286775589,
+      "learning_rate": 5.0770566463312784e-05,
+      "loss": 1.186049461364746,
+      "step": 1445
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.19549567997455597,
+      "learning_rate": 4.99705998646869e-05,
+      "loss": 1.0876874923706055,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7167487684729064,
+      "grad_norm": 0.19752028584480286,
+      "learning_rate": 4.917540831132491e-05,
+      "loss": 1.1264894485473633,
+      "step": 1455
+    },
+    {
+      "epoch": 0.7192118226600985,
+      "grad_norm": 0.20645610988140106,
+      "learning_rate": 4.8385042411063964e-05,
+      "loss": 1.1941204071044922,
+      "step": 1460
+    },
+    {
+      "epoch": 0.7216748768472906,
+      "grad_norm": 0.19582952558994293,
+      "learning_rate": 4.759955246462537e-05,
+      "loss": 1.1740989685058594,
+      "step": 1465
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 0.21208184957504272,
+      "learning_rate": 4.6818988462413474e-05,
+      "loss": 1.1448843002319335,
+      "step": 1470
+    },
+    {
+      "epoch": 0.7266009852216748,
+      "grad_norm": 0.24020442366600037,
+      "learning_rate": 4.604340008133401e-05,
+      "loss": 1.1888654708862305,
+      "step": 1475
+    },
+    {
+      "epoch": 0.729064039408867,
+      "grad_norm": 0.19123804569244385,
+      "learning_rate": 4.527283668163282e-05,
+      "loss": 1.0766042709350585,
+      "step": 1480
+    },
+    {
+      "epoch": 0.7315270935960592,
+      "grad_norm": 0.1896355152130127,
+      "learning_rate": 4.4507347303753945e-05,
+      "loss": 1.160280418395996,
+      "step": 1485
+    },
+    {
+      "epoch": 0.7339901477832512,
+      "grad_norm": 0.19653399288654327,
+      "learning_rate": 4.3746980665219194e-05,
+      "loss": 1.1807693481445312,
+      "step": 1490
+    },
+    {
+      "epoch": 0.7364532019704434,
+      "grad_norm": 0.21867699921131134,
+      "learning_rate": 4.2991785157527206e-05,
+      "loss": 1.174069595336914,
+      "step": 1495
+    },
+    {
+      "epoch": 0.7389162561576355,
+      "grad_norm": 0.23333442211151123,
+      "learning_rate": 4.2241808843073856e-05,
+      "loss": 1.1655208587646484,
+      "step": 1500
+    },
+    {
+      "epoch": 0.7413793103448276,
+      "grad_norm": 0.1968652606010437,
+      "learning_rate": 4.149709945209346e-05,
+      "loss": 1.140891170501709,
+      "step": 1505
+    },
+    {
+      "epoch": 0.7438423645320197,
+      "grad_norm": 0.1928500235080719,
+      "learning_rate": 4.075770437962107e-05,
+      "loss": 1.149114990234375,
+      "step": 1510
+    },
+    {
+      "epoch": 0.7463054187192119,
+      "grad_norm": 0.22657066583633423,
+      "learning_rate": 4.002367068247618e-05,
+      "loss": 1.188311767578125,
+      "step": 1515
+    },
+    {
+      "epoch": 0.7487684729064039,
+      "grad_norm": 0.18601438403129578,
+      "learning_rate": 3.929504507626788e-05,
+      "loss": 1.1293941497802735,
+      "step": 1520
+    },
+    {
+      "epoch": 0.7512315270935961,
+      "grad_norm": 0.2474275827407837,
+      "learning_rate": 3.85718739324219e-05,
+      "loss": 1.1833365440368653,
+      "step": 1525
+    },
+    {
+      "epoch": 0.7536945812807881,
+      "grad_norm": 0.2521296441555023,
+      "learning_rate": 3.78542032752292e-05,
+      "loss": 1.2554161071777343,
+      "step": 1530
+    },
+    {
+      "epoch": 0.7561576354679803,
+      "grad_norm": 0.19266285002231598,
+      "learning_rate": 3.714207877891702e-05,
+      "loss": 1.199503231048584,
+      "step": 1535
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 0.1857539564371109,
+      "learning_rate": 3.643554576474209e-05,
+      "loss": 1.1698965072631835,
+      "step": 1540
+    },
+    {
+      "epoch": 0.7610837438423645,
+      "grad_norm": 0.20553693175315857,
+      "learning_rate": 3.5734649198106176e-05,
+      "loss": 1.133984375,
+      "step": 1545
+    },
+    {
+      "epoch": 0.7635467980295566,
+      "grad_norm": 0.20273086428642273,
+      "learning_rate": 3.503943368569443e-05,
+      "loss": 1.1508802413940429,
+      "step": 1550
+    },
+    {
+      "epoch": 0.7660098522167488,
+      "grad_norm": 0.21074187755584717,
+      "learning_rate": 3.4349943472636645e-05,
+      "loss": 1.1422389030456543,
+      "step": 1555
+    },
+    {
+      "epoch": 0.7684729064039408,
+      "grad_norm": 0.20370303094387054,
+      "learning_rate": 3.366622243969107e-05,
+      "loss": 1.1365758895874023,
+      "step": 1560
+    },
+    {
+      "epoch": 0.770935960591133,
+      "grad_norm": 0.22188185155391693,
+      "learning_rate": 3.2988314100452025e-05,
+      "loss": 1.200836753845215,
+      "step": 1565
+    },
+    {
+      "epoch": 0.7733990147783252,
+      "grad_norm": 0.22201508283615112,
+      "learning_rate": 3.23162615985806e-05,
+      "loss": 1.1412124633789062,
+      "step": 1570
+    },
+    {
+      "epoch": 0.7758620689655172,
+      "grad_norm": 0.2054172307252884,
+      "learning_rate": 3.1650107705058675e-05,
+      "loss": 1.1819982528686523,
+      "step": 1575
+    },
+    {
+      "epoch": 0.7783251231527094,
+      "grad_norm": 0.19441308081150055,
+      "learning_rate": 3.098989481546701e-05,
+      "loss": 1.0897558212280274,
+      "step": 1580
+    },
+    {
+      "epoch": 0.7807881773399015,
+      "grad_norm": 0.1917772740125656,
+      "learning_rate": 3.0335664947287096e-05,
+      "loss": 1.1094754219055176,
+      "step": 1585
+    },
+    {
+      "epoch": 0.7832512315270936,
+      "grad_norm": 0.26108071208000183,
+      "learning_rate": 2.968745973722707e-05,
+      "loss": 1.1879570007324218,
+      "step": 1590
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.2175268679857254,
+      "learning_rate": 2.9045320438571762e-05,
+      "loss": 1.1659234046936036,
+      "step": 1595
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.23715537786483765,
+      "learning_rate": 2.8409287918557443e-05,
+      "loss": 1.1726749420166016,
+      "step": 1600
+    },
+    {
+      "epoch": 0.7906403940886699,
+      "grad_norm": 0.22927704453468323,
+      "learning_rate": 2.777940265577074e-05,
+      "loss": 1.116994285583496,
+      "step": 1605
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 0.20285972952842712,
+      "learning_rate": 2.7155704737572437e-05,
+      "loss": 1.214838695526123,
+      "step": 1610
+    },
+    {
+      "epoch": 0.7955665024630542,
+      "grad_norm": 0.18570181727409363,
+      "learning_rate": 2.6538233857546544e-05,
+      "loss": 1.0953670501708985,
+      "step": 1615
+    },
+    {
+      "epoch": 0.7980295566502463,
+      "grad_norm": 0.2491133213043213,
+      "learning_rate": 2.5927029312973792e-05,
+      "loss": 1.239107894897461,
+      "step": 1620
+    },
+    {
+      "epoch": 0.8004926108374384,
+      "grad_norm": 0.2205798178911209,
+      "learning_rate": 2.5322130002330758e-05,
+      "loss": 1.1664484024047852,
+      "step": 1625
+    },
+    {
+      "epoch": 0.8029556650246306,
+      "grad_norm": 0.19911938905715942,
+      "learning_rate": 2.4723574422814338e-05,
+      "loss": 1.1730329513549804,
+      "step": 1630
+    },
+    {
+      "epoch": 0.8054187192118226,
+      "grad_norm": 0.20067468285560608,
+      "learning_rate": 2.4131400667891616e-05,
+      "loss": 1.2024543762207032,
+      "step": 1635
+    },
+    {
+      "epoch": 0.8078817733990148,
+      "grad_norm": 0.2556314766407013,
+      "learning_rate": 2.3545646424875527e-05,
+      "loss": 1.0958398818969726,
+      "step": 1640
+    },
+    {
+      "epoch": 0.8103448275862069,
+      "grad_norm": 0.23883827030658722,
+      "learning_rate": 2.2966348972526447e-05,
+      "loss": 1.1237594604492187,
+      "step": 1645
+    },
+    {
+      "epoch": 0.812807881773399,
+      "grad_norm": 0.24573266506195068,
+      "learning_rate": 2.2393545178679518e-05,
+      "loss": 1.1463817596435546,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8152709359605911,
+      "grad_norm": 0.21328045427799225,
+      "learning_rate": 2.1827271497898317e-05,
+      "loss": 1.1861235618591308,
+      "step": 1655
+    },
+    {
+      "epoch": 0.8177339901477833,
+      "grad_norm": 0.2581596374511719,
+      "learning_rate": 2.1267563969155008e-05,
+      "loss": 1.1785642623901367,
+      "step": 1660
+    },
+    {
+      "epoch": 0.8201970443349754,
+      "grad_norm": 0.21597856283187866,
+      "learning_rate": 2.07144582135365e-05,
+      "loss": 1.1577519416809081,
+      "step": 1665
+    },
+    {
+      "epoch": 0.8226600985221675,
+      "grad_norm": 0.20064803957939148,
+      "learning_rate": 2.0167989431977547e-05,
+      "loss": 1.1182676315307618,
+      "step": 1670
+    },
+    {
+      "epoch": 0.8251231527093597,
+      "grad_norm": 0.21915578842163086,
+      "learning_rate": 1.9628192403020452e-05,
+      "loss": 1.1464277267456056,
+      "step": 1675
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 0.2068677693605423,
+      "learning_rate": 1.9095101480601716e-05,
+      "loss": 1.1752894401550293,
+      "step": 1680
+    },
+    {
+      "epoch": 0.8300492610837439,
+      "grad_norm": 0.1970977783203125,
+      "learning_rate": 1.856875059186558e-05,
+      "loss": 1.1746513366699218,
+      "step": 1685
+    },
+    {
+      "epoch": 0.8325123152709359,
+      "grad_norm": 0.2244248390197754,
+      "learning_rate": 1.8049173235005005e-05,
+      "loss": 1.193491554260254,
+      "step": 1690
+    },
+    {
+      "epoch": 0.8349753694581281,
+      "grad_norm": 0.22854915261268616,
+      "learning_rate": 1.7536402477129565e-05,
+      "loss": 1.0891584396362304,
+      "step": 1695
+    },
+    {
+      "epoch": 0.8374384236453202,
+      "grad_norm": 0.24586863815784454,
+      "learning_rate": 1.7030470952161066e-05,
+      "loss": 1.2139921188354492,
+      "step": 1700
+    },
+    {
+      "epoch": 0.8399014778325123,
+      "grad_norm": 0.2310931384563446,
+      "learning_rate": 1.6531410858756686e-05,
+      "loss": 1.1562270164489745,
+      "step": 1705
+    },
+    {
+      "epoch": 0.8423645320197044,
+      "grad_norm": 0.21044319868087769,
+      "learning_rate": 1.603925395825974e-05,
+      "loss": 1.1029083251953125,
+      "step": 1710
+    },
+    {
+      "epoch": 0.8448275862068966,
+      "grad_norm": 0.21446605026721954,
+      "learning_rate": 1.5554031572678276e-05,
+      "loss": 1.125635814666748,
+      "step": 1715
+    },
+    {
+      "epoch": 0.8472906403940886,
+      "grad_norm": 0.24440473318099976,
+      "learning_rate": 1.5075774582691714e-05,
+      "loss": 1.1181723594665527,
+      "step": 1720
+    },
+    {
+      "epoch": 0.8497536945812808,
+      "grad_norm": 0.2670726180076599,
+      "learning_rate": 1.460451342568564e-05,
+      "loss": 1.0882012367248535,
+      "step": 1725
+    },
+    {
+      "epoch": 0.8522167487684729,
+      "grad_norm": 0.23288647830486298,
+      "learning_rate": 1.4140278093814393e-05,
+      "loss": 1.090647315979004,
+      "step": 1730
+    },
+    {
+      "epoch": 0.854679802955665,
+      "grad_norm": 0.231570303440094,
+      "learning_rate": 1.3683098132092578e-05,
+      "loss": 1.1397241592407226,
+      "step": 1735
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.22689397633075714,
+      "learning_rate": 1.3233002636514723e-05,
+      "loss": 1.1933679580688477,
+      "step": 1740
+    },
+    {
+      "epoch": 0.8596059113300493,
+      "grad_norm": 0.21905820071697235,
+      "learning_rate": 1.2790020252203368e-05,
+      "loss": 1.1338354110717774,
+      "step": 1745
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 0.20308807492256165,
+      "learning_rate": 1.2354179171586197e-05,
+      "loss": 1.2108822822570802,
+      "step": 1750
+    },
+    {
+      "epoch": 0.8645320197044335,
+      "grad_norm": 0.21823200583457947,
+      "learning_rate": 1.1925507132601724e-05,
+      "loss": 1.1565272331237793,
+      "step": 1755
+    },
+    {
+      "epoch": 0.8669950738916257,
+      "grad_norm": 0.2614777684211731,
+      "learning_rate": 1.1504031416934e-05,
+      "loss": 1.2234196662902832,
+      "step": 1760
+    },
+    {
+      "epoch": 0.8694581280788177,
+      "grad_norm": 0.21617333590984344,
+      "learning_rate": 1.1089778848276332e-05,
+      "loss": 1.1068148612976074,
+      "step": 1765
+    },
+    {
+      "epoch": 0.8719211822660099,
+      "grad_norm": 0.205158993601799,
+      "learning_rate": 1.0682775790624238e-05,
+      "loss": 1.1436782836914063,
+      "step": 1770
+    },
+    {
+      "epoch": 0.874384236453202,
+      "grad_norm": 0.19994309544563293,
+      "learning_rate": 1.0283048146597514e-05,
+      "loss": 1.1077436447143554,
+      "step": 1775
+    },
+    {
+      "epoch": 0.8768472906403941,
+      "grad_norm": 0.23480737209320068,
+      "learning_rate": 9.890621355791608e-06,
+      "loss": 1.1043251991271972,
+      "step": 1780
+    },
+    {
+      "epoch": 0.8793103448275862,
+      "grad_norm": 0.22875778377056122,
+      "learning_rate": 9.505520393158884e-06,
+      "loss": 1.1661962509155273,
+      "step": 1785
+    },
+    {
+      "epoch": 0.8817733990147784,
+      "grad_norm": 0.22975754737854004,
+      "learning_rate": 9.1277697674189e-06,
+      "loss": 1.1384613990783692,
+      "step": 1790
+    },
+    {
+      "epoch": 0.8842364532019704,
+      "grad_norm": 0.1951616257429123,
+      "learning_rate": 8.757393519498696e-06,
+      "loss": 1.1530138015747071,
+      "step": 1795
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.20783555507659912,
+      "learning_rate": 8.394415221002871e-06,
+      "loss": 1.2157105445861816,
+      "step": 1800
+    },
+    {
+      "epoch": 0.8891625615763546,
+      "grad_norm": 0.2325158715248108,
+      "learning_rate": 8.038857972713212e-06,
+      "loss": 1.1464594841003417,
+      "step": 1805
+    },
+    {
+      "epoch": 0.8916256157635468,
+      "grad_norm": 0.2125118523836136,
+      "learning_rate": 7.690744403118719e-06,
+      "loss": 1.1035504341125488,
+      "step": 1810
+    },
+    {
+      "epoch": 0.8940886699507389,
+      "grad_norm": 0.24947774410247803,
+      "learning_rate": 7.3500966669754064e-06,
+      "loss": 1.0717124938964844,
+      "step": 1815
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 0.23735353350639343,
+      "learning_rate": 7.016936443896255e-06,
+      "loss": 1.120765495300293,
+      "step": 1820
+    },
+    {
+      "epoch": 0.8990147783251231,
+      "grad_norm": 0.22857430577278137,
+      "learning_rate": 6.691284936971576e-06,
+      "loss": 1.1590867042541504,
+      "step": 1825
+    },
+    {
+      "epoch": 0.9014778325123153,
+      "grad_norm": 0.19644860923290253,
+      "learning_rate": 6.373162871419494e-06,
+      "loss": 1.1249679565429687,
+      "step": 1830
+    },
+    {
+      "epoch": 0.9039408866995073,
+      "grad_norm": 0.22863984107971191,
+      "learning_rate": 6.062590493267059e-06,
+      "loss": 1.1595049858093263,
+      "step": 1835
+    },
+    {
+      "epoch": 0.9064039408866995,
+      "grad_norm": 0.20936983823776245,
+      "learning_rate": 5.759587568061609e-06,
+      "loss": 1.1055160522460938,
+      "step": 1840
+    },
+    {
+      "epoch": 0.9088669950738916,
+      "grad_norm": 0.20197199285030365,
+      "learning_rate": 5.464173379613024e-06,
+      "loss": 1.12583646774292,
+      "step": 1845
+    },
+    {
+      "epoch": 0.9113300492610837,
+      "grad_norm": 0.19483184814453125,
+      "learning_rate": 5.176366728766258e-06,
+      "loss": 1.0874908447265625,
+      "step": 1850
+    },
+    {
+      "epoch": 0.9137931034482759,
+      "grad_norm": 0.22472688555717468,
+      "learning_rate": 4.896185932204922e-06,
+      "loss": 1.1422042846679688,
+      "step": 1855
+    },
+    {
+      "epoch": 0.916256157635468,
+      "grad_norm": 0.2273848056793213,
+      "learning_rate": 4.6236488212856035e-06,
+      "loss": 1.1064237594604491,
+      "step": 1860
+    },
+    {
+      "epoch": 0.9187192118226601,
+      "grad_norm": 0.23189832270145416,
+      "learning_rate": 4.35877274090292e-06,
+      "loss": 1.1726006507873534,
+      "step": 1865
+    },
+    {
+      "epoch": 0.9211822660098522,
+      "grad_norm": 0.29500818252563477,
+      "learning_rate": 4.10157454838575e-06,
+      "loss": 1.101616096496582,
+      "step": 1870
+    },
+    {
+      "epoch": 0.9236453201970444,
+      "grad_norm": 0.23515431582927704,
+      "learning_rate": 3.852070612424374e-06,
+      "loss": 1.1767086029052733,
+      "step": 1875
+    },
+    {
+      "epoch": 0.9261083743842364,
+      "grad_norm": 0.26111993193626404,
+      "learning_rate": 3.610276812028662e-06,
+      "loss": 1.13806095123291,
+      "step": 1880
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.2352493703365326,
+      "learning_rate": 3.376208535517608e-06,
+      "loss": 1.162950325012207,
+      "step": 1885
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 0.19875593483448029,
+      "learning_rate": 3.1498806795398764e-06,
+      "loss": 1.1662640571594238,
+      "step": 1890
+    },
+    {
+      "epoch": 0.9334975369458128,
+      "grad_norm": 0.24564425647258759,
+      "learning_rate": 2.931307648125839e-06,
+      "loss": 1.0638365745544434,
+      "step": 1895
+    },
+    {
+      "epoch": 0.9359605911330049,
+      "grad_norm": 0.2120126485824585,
+      "learning_rate": 2.720503351770806e-06,
+      "loss": 1.1321612358093263,
+      "step": 1900
+    },
+    {
+      "epoch": 0.9384236453201971,
+      "grad_norm": 0.2155761867761612,
+      "learning_rate": 2.5174812065497378e-06,
+      "loss": 1.1385221481323242,
+      "step": 1905
+    },
+    {
+      "epoch": 0.9408866995073891,
+      "grad_norm": 0.22777077555656433,
+      "learning_rate": 2.322254133263424e-06,
+      "loss": 1.1761194229125977,
+      "step": 1910
+    },
+    {
+      "epoch": 0.9433497536945813,
+      "grad_norm": 0.2683568298816681,
+      "learning_rate": 2.134834556616186e-06,
+      "loss": 1.1717534065246582,
+      "step": 1915
+    },
+    {
+      "epoch": 0.9458128078817734,
+      "grad_norm": 0.214491605758667,
+      "learning_rate": 1.955234404425105e-06,
+      "loss": 1.1074954986572265,
+      "step": 1920
+    },
+    {
+      "epoch": 0.9482758620689655,
+      "grad_norm": 0.23508760333061218,
+      "learning_rate": 1.7834651068610041e-06,
+      "loss": 1.2219199180603026,
+      "step": 1925
+    },
+    {
+      "epoch": 0.9507389162561576,
+      "grad_norm": 0.24593816697597504,
+      "learning_rate": 1.6195375957208102e-06,
+      "loss": 1.1418069839477538,
+      "step": 1930
+    },
+    {
+      "epoch": 0.9532019704433498,
+      "grad_norm": 0.19407442212104797,
+      "learning_rate": 1.4634623037320383e-06,
+      "loss": 1.1674427032470702,
+      "step": 1935
+    },
+    {
+      "epoch": 0.9556650246305419,
+      "grad_norm": 0.2106153517961502,
+      "learning_rate": 1.3152491638887543e-06,
+      "loss": 1.1927571296691895,
+      "step": 1940
+    },
+    {
+      "epoch": 0.958128078817734,
+      "grad_norm": 0.23988743126392365,
+      "learning_rate": 1.1749076088193312e-06,
+      "loss": 1.1137849807739257,
+      "step": 1945
+    },
+    {
+      "epoch": 0.9605911330049262,
+      "grad_norm": 0.23574206233024597,
+      "learning_rate": 1.0424465701862478e-06,
+      "loss": 1.0699432373046875,
+      "step": 1950
+    },
+    {
+      "epoch": 0.9630541871921182,
+      "grad_norm": 0.2534239888191223,
+      "learning_rate": 9.178744781176418e-07,
+      "loss": 1.09190673828125,
+      "step": 1955
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.2221975326538086,
+      "learning_rate": 8.011992606707236e-07,
+      "loss": 1.1216561317443847,
+      "step": 1960
+    },
+    {
+      "epoch": 0.9679802955665024,
+      "grad_norm": 0.2233847677707672,
+      "learning_rate": 6.924283433272921e-07,
+      "loss": 1.1997761726379395,
+      "step": 1965
+    },
+    {
+      "epoch": 0.9704433497536946,
+      "grad_norm": 0.28760743141174316,
+      "learning_rate": 5.915686485211125e-07,
+      "loss": 1.1746740341186523,
+      "step": 1970
+    },
+    {
+      "epoch": 0.9729064039408867,
+      "grad_norm": 0.25115734338760376,
+      "learning_rate": 4.986265951973934e-07,
+      "loss": 1.0726459503173829,
+      "step": 1975
+    },
+    {
+      "epoch": 0.9753694581280788,
+      "grad_norm": 0.20638005435466766,
+      "learning_rate": 4.136080984042528e-07,
+      "loss": 1.04449462890625,
+      "step": 1980
+    },
+    {
+      "epoch": 0.9778325123152709,
+      "grad_norm": 0.24163977801799774,
+      "learning_rate": 3.3651856891625533e-07,
+      "loss": 1.1729721069335937,
+      "step": 1985
+    },
+    {
+      "epoch": 0.9802955665024631,
+      "grad_norm": 0.20855331420898438,
+      "learning_rate": 2.673629128900762e-07,
+      "loss": 1.1981142044067383,
+      "step": 1990
+    },
+    {
+      "epoch": 0.9827586206896551,
+      "grad_norm": 0.2020869255065918,
+      "learning_rate": 2.061455315522792e-07,
+      "loss": 1.146130084991455,
+      "step": 1995
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.26678571105003357,
+      "learning_rate": 1.5287032091916565e-07,
+      "loss": 1.1893404006958008,
+      "step": 2000
+    },
+    {
+      "epoch": 0.9876847290640394,
+      "grad_norm": 0.2091265618801117,
+      "learning_rate": 1.0754067154886138e-07,
+      "loss": 1.0911357879638672,
+      "step": 2005
+    },
+    {
+      "epoch": 0.9901477832512315,
+      "grad_norm": 0.24951723217964172,
+      "learning_rate": 7.015946832551745e-08,
+      "loss": 1.1647552490234374,
+      "step": 2010
+    },
+    {
+      "epoch": 0.9926108374384236,
+      "grad_norm": 0.22353601455688477,
+      "learning_rate": 4.0729090275720695e-08,
+      "loss": 1.1812686920166016,
+      "step": 2015
+    },
+    {
+      "epoch": 0.9950738916256158,
+      "grad_norm": 0.2677609622478485,
+      "learning_rate": 1.9251410417087113e-08,
+      "loss": 1.1279336929321289,
+      "step": 2020
+    },
+    {
+      "epoch": 0.9975369458128078,
+      "grad_norm": 0.2693481147289276,
+      "learning_rate": 5.727795639023925e-09,
+      "loss": 1.215308380126953,
+      "step": 2025
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2215091586112976,
+      "learning_rate": 1.5910661577134277e-10,
+      "loss": 1.2273775100708009,
+      "step": 2030
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2030,
+  "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": 1.951955862809477e+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 sha256:86878db61fc22c18139e8b1f12ce49f881704a72f4aedc0dd11fafd10881fd31
+size 5905