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": [
+    "gate_proj",
+    "k_proj",
+    "q_proj",
+    "up_proj",
+    "down_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:e9875f35ab45a64db519432d7d3d238330ff24be1364585d6ce9d9c7df788794
+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:bc92ffef0746441591735708001722beac910183ad62143dc29434d252159818
+size 81070011

rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f600ccca4f0f528d0df5152b611aacf1d4edbeddb74891c4a271c71f99c968f6
+size 15429

rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f15419bc734c7524b4499128013169bdb5b8b6f2ba8d3d047039ef06b395e5ad
+size 15429

rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e2cb41950101c5960ea3f2dac3d8e1bb45e287df11580bcd434c3c4aaa30594
+size 15429

rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e286f0fb54d531e13bb5787f97ebb0e09460fefcdbcb7a3c1d03895e8f1d924
+size 15429

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e8808e795f439dacc9daf115974b048ff0e29fbdbbb7fa75fa65df01710e3e2
+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 +1,3450 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 2441,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.002048760499897562,
+      "grad_norm": 1.1812664270401,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 2.8812843322753907,
+      "step": 5
+    },
+    {
+      "epoch": 0.004097520999795124,
+      "grad_norm": 0.8362325429916382,
+      "learning_rate": 1.2162162162162164e-05,
+      "loss": 2.861424446105957,
+      "step": 10
+    },
+    {
+      "epoch": 0.006146281499692686,
+      "grad_norm": 0.5689634084701538,
+      "learning_rate": 1.891891891891892e-05,
+      "loss": 2.7010166168212892,
+      "step": 15
+    },
+    {
+      "epoch": 0.008195041999590248,
+      "grad_norm": 0.4256836473941803,
+      "learning_rate": 2.5675675675675675e-05,
+      "loss": 2.5818761825561523,
+      "step": 20
+    },
+    {
+      "epoch": 0.01024380249948781,
+      "grad_norm": 0.27007684111595154,
+      "learning_rate": 3.2432432432432436e-05,
+      "loss": 2.5209020614624023,
+      "step": 25
+    },
+    {
+      "epoch": 0.012292562999385371,
+      "grad_norm": 0.3387170135974884,
+      "learning_rate": 3.918918918918919e-05,
+      "loss": 2.367527389526367,
+      "step": 30
+    },
+    {
+      "epoch": 0.014341323499282934,
+      "grad_norm": 0.24254447221755981,
+      "learning_rate": 4.594594594594595e-05,
+      "loss": 2.349028396606445,
+      "step": 35
+    },
+    {
+      "epoch": 0.016390083999180495,
+      "grad_norm": 0.17901070415973663,
+      "learning_rate": 5.27027027027027e-05,
+      "loss": 2.2836673736572264,
+      "step": 40
+    },
+    {
+      "epoch": 0.01843884449907806,
+      "grad_norm": 0.23550106585025787,
+      "learning_rate": 5.9459459459459466e-05,
+      "loss": 2.1883352279663084,
+      "step": 45
+    },
+    {
+      "epoch": 0.02048760499897562,
+      "grad_norm": 0.22605213522911072,
+      "learning_rate": 6.621621621621621e-05,
+      "loss": 2.091319274902344,
+      "step": 50
+    },
+    {
+      "epoch": 0.02253636549887318,
+      "grad_norm": 0.24344144761562347,
+      "learning_rate": 7.297297297297297e-05,
+      "loss": 2.050617980957031,
+      "step": 55
+    },
+    {
+      "epoch": 0.024585125998770743,
+      "grad_norm": 0.20058763027191162,
+      "learning_rate": 7.972972972972974e-05,
+      "loss": 2.0248905181884767,
+      "step": 60
+    },
+    {
+      "epoch": 0.026633886498668307,
+      "grad_norm": 0.18873044848442078,
+      "learning_rate": 8.64864864864865e-05,
+      "loss": 1.983725357055664,
+      "step": 65
+    },
+    {
+      "epoch": 0.028682646998565868,
+      "grad_norm": 0.2051159292459488,
+      "learning_rate": 9.324324324324324e-05,
+      "loss": 1.8838939666748047,
+      "step": 70
+    },
+    {
+      "epoch": 0.03073140749846343,
+      "grad_norm": 0.19688092172145844,
+      "learning_rate": 0.0001,
+      "loss": 1.8781766891479492,
+      "step": 75
+    },
+    {
+      "epoch": 0.03278016799836099,
+      "grad_norm": 0.2000727653503418,
+      "learning_rate": 9.99988990143639e-05,
+      "loss": 1.8038059234619142,
+      "step": 80
+    },
+    {
+      "epoch": 0.034828928498258555,
+      "grad_norm": 0.1982649862766266,
+      "learning_rate": 9.999559610594239e-05,
+      "loss": 1.7927516937255858,
+      "step": 85
+    },
+    {
+      "epoch": 0.03687768899815612,
+      "grad_norm": 0.2121347188949585,
+      "learning_rate": 9.999009142019364e-05,
+      "loss": 1.80054931640625,
+      "step": 90
+    },
+    {
+      "epoch": 0.03892644949805368,
+      "grad_norm": 0.19571512937545776,
+      "learning_rate": 9.998238519954086e-05,
+      "loss": 1.7956045150756836,
+      "step": 95
+    },
+    {
+      "epoch": 0.04097520999795124,
+      "grad_norm": 0.26593539118766785,
+      "learning_rate": 9.997247778336158e-05,
+      "loss": 1.783555030822754,
+      "step": 100
+    },
+    {
+      "epoch": 0.0430239704978488,
+      "grad_norm": 0.26111558079719543,
+      "learning_rate": 9.99603696079727e-05,
+      "loss": 1.7082708358764649,
+      "step": 105
+    },
+    {
+      "epoch": 0.04507273099774636,
+      "grad_norm": 0.23216010630130768,
+      "learning_rate": 9.994606120661133e-05,
+      "loss": 1.7185798645019532,
+      "step": 110
+    },
+    {
+      "epoch": 0.04712149149764393,
+      "grad_norm": 0.21356265246868134,
+      "learning_rate": 9.992955320941123e-05,
+      "loss": 1.7029909133911132,
+      "step": 115
+    },
+    {
+      "epoch": 0.049170251997541485,
+      "grad_norm": 0.24489012360572815,
+      "learning_rate": 9.991084634337511e-05,
+      "loss": 1.6960697174072266,
+      "step": 120
+    },
+    {
+      "epoch": 0.05121901249743905,
+      "grad_norm": 0.233820378780365,
+      "learning_rate": 9.988994143234262e-05,
+      "loss": 1.6897468566894531,
+      "step": 125
+    },
+    {
+      "epoch": 0.053267772997336614,
+      "grad_norm": 0.2314917892217636,
+      "learning_rate": 9.986683939695403e-05,
+      "loss": 1.6672828674316407,
+      "step": 130
+    },
+    {
+      "epoch": 0.05531653349723417,
+      "grad_norm": 0.2200533002614975,
+      "learning_rate": 9.984154125460969e-05,
+      "loss": 1.72767333984375,
+      "step": 135
+    },
+    {
+      "epoch": 0.057365293997131736,
+      "grad_norm": 0.2274775505065918,
+      "learning_rate": 9.981404811942525e-05,
+      "loss": 1.6336374282836914,
+      "step": 140
+    },
+    {
+      "epoch": 0.0594140544970293,
+      "grad_norm": 0.24149921536445618,
+      "learning_rate": 9.97843612021826e-05,
+      "loss": 1.677962303161621,
+      "step": 145
+    },
+    {
+      "epoch": 0.06146281499692686,
+      "grad_norm": 0.22468891739845276,
+      "learning_rate": 9.97524818102765e-05,
+      "loss": 1.6040916442871094,
+      "step": 150
+    },
+    {
+      "epoch": 0.06351157549682442,
+      "grad_norm": 0.2458656132221222,
+      "learning_rate": 9.971841134765709e-05,
+      "loss": 1.6422203063964844,
+      "step": 155
+    },
+    {
+      "epoch": 0.06556033599672198,
+      "grad_norm": 0.2329816222190857,
+      "learning_rate": 9.968215131476792e-05,
+      "loss": 1.6500967025756836,
+      "step": 160
+    },
+    {
+      "epoch": 0.06760909649661954,
+      "grad_norm": 0.3145672082901001,
+      "learning_rate": 9.964370330848005e-05,
+      "loss": 1.6491971969604493,
+      "step": 165
+    },
+    {
+      "epoch": 0.06965785699651711,
+      "grad_norm": 0.2482324242591858,
+      "learning_rate": 9.960306902202157e-05,
+      "loss": 1.639816665649414,
+      "step": 170
+    },
+    {
+      "epoch": 0.07170661749641467,
+      "grad_norm": 0.2566273510456085,
+      "learning_rate": 9.95602502449031e-05,
+      "loss": 1.6021163940429688,
+      "step": 175
+    },
+    {
+      "epoch": 0.07375537799631224,
+      "grad_norm": 0.2545284628868103,
+      "learning_rate": 9.951524886283899e-05,
+      "loss": 1.613656997680664,
+      "step": 180
+    },
+    {
+      "epoch": 0.07580413849620979,
+      "grad_norm": 0.22539421916007996,
+      "learning_rate": 9.946806685766425e-05,
+      "loss": 1.6585615158081055,
+      "step": 185
+    },
+    {
+      "epoch": 0.07785289899610735,
+      "grad_norm": 0.24375995993614197,
+      "learning_rate": 9.941870630724728e-05,
+      "loss": 1.5964128494262695,
+      "step": 190
+    },
+    {
+      "epoch": 0.07990165949600492,
+      "grad_norm": 0.21810759603977203,
+      "learning_rate": 9.936716938539834e-05,
+      "loss": 1.641855239868164,
+      "step": 195
+    },
+    {
+      "epoch": 0.08195041999590248,
+      "grad_norm": 0.24955236911773682,
+      "learning_rate": 9.93134583617739e-05,
+      "loss": 1.5914262771606444,
+      "step": 200
+    },
+    {
+      "epoch": 0.08399918049580005,
+      "grad_norm": 0.28465893864631653,
+      "learning_rate": 9.925757560177654e-05,
+      "loss": 1.5576708793640137,
+      "step": 205
+    },
+    {
+      "epoch": 0.0860479409956976,
+      "grad_norm": 0.2932316064834595,
+      "learning_rate": 9.919952356645092e-05,
+      "loss": 1.5997091293334962,
+      "step": 210
+    },
+    {
+      "epoch": 0.08809670149559516,
+      "grad_norm": 0.2858922481536865,
+      "learning_rate": 9.913930481237532e-05,
+      "loss": 1.5274235725402832,
+      "step": 215
+    },
+    {
+      "epoch": 0.09014546199549273,
+      "grad_norm": 0.2401326298713684,
+      "learning_rate": 9.907692199154908e-05,
+      "loss": 1.579271125793457,
+      "step": 220
+    },
+    {
+      "epoch": 0.09219422249539029,
+      "grad_norm": 0.2773420810699463,
+      "learning_rate": 9.901237785127577e-05,
+      "loss": 1.5469179153442383,
+      "step": 225
+    },
+    {
+      "epoch": 0.09424298299528786,
+      "grad_norm": 0.2653924524784088,
+      "learning_rate": 9.894567523404226e-05,
+      "loss": 1.5241682052612304,
+      "step": 230
+    },
+    {
+      "epoch": 0.09629174349518542,
+      "grad_norm": 0.2652921974658966,
+      "learning_rate": 9.887681707739346e-05,
+      "loss": 1.5396958351135255,
+      "step": 235
+    },
+    {
+      "epoch": 0.09834050399508297,
+      "grad_norm": 0.3156124949455261,
+      "learning_rate": 9.880580641380306e-05,
+      "loss": 1.5760322570800782,
+      "step": 240
+    },
+    {
+      "epoch": 0.10038926449498053,
+      "grad_norm": 0.2271326333284378,
+      "learning_rate": 9.873264637053986e-05,
+      "loss": 1.5505045890808105,
+      "step": 245
+    },
+    {
+      "epoch": 0.1024380249948781,
+      "grad_norm": 0.27076372504234314,
+      "learning_rate": 9.865734016953015e-05,
+      "loss": 1.5519193649291991,
+      "step": 250
+    },
+    {
+      "epoch": 0.10448678549477566,
+      "grad_norm": 0.2223425656557083,
+      "learning_rate": 9.857989112721574e-05,
+      "loss": 1.56038818359375,
+      "step": 255
+    },
+    {
+      "epoch": 0.10653554599467323,
+      "grad_norm": 0.2585384249687195,
+      "learning_rate": 9.850030265440796e-05,
+      "loss": 1.6129053115844727,
+      "step": 260
+    },
+    {
+      "epoch": 0.10858430649457078,
+      "grad_norm": 0.21488016843795776,
+      "learning_rate": 9.841857825613742e-05,
+      "loss": 1.5197179794311524,
+      "step": 265
+    },
+    {
+      "epoch": 0.11063306699446834,
+      "grad_norm": 0.2225860208272934,
+      "learning_rate": 9.833472153149968e-05,
+      "loss": 1.5575998306274415,
+      "step": 270
+    },
+    {
+      "epoch": 0.11268182749436591,
+      "grad_norm": 0.2429075390100479,
+      "learning_rate": 9.82487361734967e-05,
+      "loss": 1.5466739654541015,
+      "step": 275
+    },
+    {
+      "epoch": 0.11473058799426347,
+      "grad_norm": 0.2430172562599182,
+      "learning_rate": 9.816062596887425e-05,
+      "loss": 1.5615922927856445,
+      "step": 280
+    },
+    {
+      "epoch": 0.11677934849416104,
+      "grad_norm": 0.2255251258611679,
+      "learning_rate": 9.80703947979551e-05,
+      "loss": 1.5115280151367188,
+      "step": 285
+    },
+    {
+      "epoch": 0.1188281089940586,
+      "grad_norm": 0.2616175711154938,
+      "learning_rate": 9.79780466344682e-05,
+      "loss": 1.573641586303711,
+      "step": 290
+    },
+    {
+      "epoch": 0.12087686949395615,
+      "grad_norm": 0.2805729806423187,
+      "learning_rate": 9.788358554537358e-05,
+      "loss": 1.5845196723937989,
+      "step": 295
+    },
+    {
+      "epoch": 0.12292562999385372,
+      "grad_norm": 0.22521676123142242,
+      "learning_rate": 9.778701569068336e-05,
+      "loss": 1.5359780311584472,
+      "step": 300
+    },
+    {
+      "epoch": 0.12497439049375128,
+      "grad_norm": 0.24305494129657745,
+      "learning_rate": 9.768834132327844e-05,
+      "loss": 1.5254245758056642,
+      "step": 305
+    },
+    {
+      "epoch": 0.12702315099364883,
+      "grad_norm": 0.2404889166355133,
+      "learning_rate": 9.758756678872128e-05,
+      "loss": 1.4859713554382323,
+      "step": 310
+    },
+    {
+      "epoch": 0.1290719114935464,
+      "grad_norm": 0.25355666875839233,
+      "learning_rate": 9.748469652506446e-05,
+      "loss": 1.4936129570007324,
+      "step": 315
+    },
+    {
+      "epoch": 0.13112067199344396,
+      "grad_norm": 0.28046417236328125,
+      "learning_rate": 9.737973506265529e-05,
+      "loss": 1.5300188064575195,
+      "step": 320
+    },
+    {
+      "epoch": 0.13316943249334154,
+      "grad_norm": 0.2746320366859436,
+      "learning_rate": 9.727268702393629e-05,
+      "loss": 1.5447193145751954,
+      "step": 325
+    },
+    {
+      "epoch": 0.1352181929932391,
+      "grad_norm": 0.2745426893234253,
+      "learning_rate": 9.716355712324156e-05,
+      "loss": 1.5363147735595704,
+      "step": 330
+    },
+    {
+      "epoch": 0.13726695349313664,
+      "grad_norm": 0.23082920908927917,
+      "learning_rate": 9.705235016658925e-05,
+      "loss": 1.4468040466308594,
+      "step": 335
+    },
+    {
+      "epoch": 0.13931571399303422,
+      "grad_norm": 0.2235836386680603,
+      "learning_rate": 9.69390710514698e-05,
+      "loss": 1.5173002243041993,
+      "step": 340
+    },
+    {
+      "epoch": 0.14136447449293177,
+      "grad_norm": 0.22597526013851166,
+      "learning_rate": 9.682372476663037e-05,
+      "loss": 1.5097177505493165,
+      "step": 345
+    },
+    {
+      "epoch": 0.14341323499282935,
+      "grad_norm": 0.2789250910282135,
+      "learning_rate": 9.670631639185509e-05,
+      "loss": 1.5475872039794922,
+      "step": 350
+    },
+    {
+      "epoch": 0.1454619954927269,
+      "grad_norm": 0.25009316205978394,
+      "learning_rate": 9.65868510977413e-05,
+      "loss": 1.4735873222351075,
+      "step": 355
+    },
+    {
+      "epoch": 0.14751075599262448,
+      "grad_norm": 0.22186560928821564,
+      "learning_rate": 9.646533414547193e-05,
+      "loss": 1.4516876220703125,
+      "step": 360
+    },
+    {
+      "epoch": 0.14955951649252203,
+      "grad_norm": 0.24449041485786438,
+      "learning_rate": 9.634177088658374e-05,
+      "loss": 1.505819034576416,
+      "step": 365
+    },
+    {
+      "epoch": 0.15160827699241958,
+      "grad_norm": 0.2347445785999298,
+      "learning_rate": 9.621616676273164e-05,
+      "loss": 1.5126794815063476,
+      "step": 370
+    },
+    {
+      "epoch": 0.15365703749231716,
+      "grad_norm": 0.2789207696914673,
+      "learning_rate": 9.60885273054491e-05,
+      "loss": 1.5142856597900392,
+      "step": 375
+    },
+    {
+      "epoch": 0.1557057979922147,
+      "grad_norm": 0.28994739055633545,
+      "learning_rate": 9.595885813590446e-05,
+      "loss": 1.522750473022461,
+      "step": 380
+    },
+    {
+      "epoch": 0.15775455849211228,
+      "grad_norm": 0.24721114337444305,
+      "learning_rate": 9.582716496465347e-05,
+      "loss": 1.4704336166381835,
+      "step": 385
+    },
+    {
+      "epoch": 0.15980331899200984,
+      "grad_norm": 0.22522343695163727,
+      "learning_rate": 9.569345359138771e-05,
+      "loss": 1.487472915649414,
+      "step": 390
+    },
+    {
+      "epoch": 0.16185207949190739,
+      "grad_norm": 0.22770005464553833,
+      "learning_rate": 9.555772990467924e-05,
+      "loss": 1.5006813049316405,
+      "step": 395
+    },
+    {
+      "epoch": 0.16390083999180496,
+      "grad_norm": 0.241038978099823,
+      "learning_rate": 9.541999988172123e-05,
+      "loss": 1.5124264717102052,
+      "step": 400
+    },
+    {
+      "epoch": 0.16594960049170251,
+      "grad_norm": 0.2523846924304962,
+      "learning_rate": 9.528026958806477e-05,
+      "loss": 1.501108169555664,
+      "step": 405
+    },
+    {
+      "epoch": 0.1679983609916001,
+      "grad_norm": 0.26068517565727234,
+      "learning_rate": 9.513854517735172e-05,
+      "loss": 1.4661484718322755,
+      "step": 410
+    },
+    {
+      "epoch": 0.17004712149149764,
+      "grad_norm": 0.264591246843338,
+      "learning_rate": 9.499483289104367e-05,
+      "loss": 1.5129196166992187,
+      "step": 415
+    },
+    {
+      "epoch": 0.1720958819913952,
+      "grad_norm": 0.2815001308917999,
+      "learning_rate": 9.484913905814716e-05,
+      "loss": 1.4661581993103028,
+      "step": 420
+    },
+    {
+      "epoch": 0.17414464249129277,
+      "grad_norm": 0.24772629141807556,
+      "learning_rate": 9.470147009493488e-05,
+      "loss": 1.5515071868896484,
+      "step": 425
+    },
+    {
+      "epoch": 0.17619340299119032,
+      "grad_norm": 0.25829702615737915,
+      "learning_rate": 9.45518325046631e-05,
+      "loss": 1.4784483909606934,
+      "step": 430
+    },
+    {
+      "epoch": 0.1782421634910879,
+      "grad_norm": 0.2560963034629822,
+      "learning_rate": 9.440023287728537e-05,
+      "loss": 1.5046897888183595,
+      "step": 435
+    },
+    {
+      "epoch": 0.18029092399098545,
+      "grad_norm": 0.2387019544839859,
+      "learning_rate": 9.424667788916215e-05,
+      "loss": 1.462269401550293,
+      "step": 440
+    },
+    {
+      "epoch": 0.182339684490883,
+      "grad_norm": 0.24378399550914764,
+      "learning_rate": 9.409117430276687e-05,
+      "loss": 1.4798359870910645,
+      "step": 445
+    },
+    {
+      "epoch": 0.18438844499078058,
+      "grad_norm": 0.3137846887111664,
+      "learning_rate": 9.393372896638816e-05,
+      "loss": 1.4298545837402343,
+      "step": 450
+    },
+    {
+      "epoch": 0.18643720549067813,
+      "grad_norm": 0.24565158784389496,
+      "learning_rate": 9.377434881382816e-05,
+      "loss": 1.466149139404297,
+      "step": 455
+    },
+    {
+      "epoch": 0.1884859659905757,
+      "grad_norm": 0.25670838356018066,
+      "learning_rate": 9.361304086409721e-05,
+      "loss": 1.5145159721374513,
+      "step": 460
+    },
+    {
+      "epoch": 0.19053472649047326,
+      "grad_norm": 0.2447153627872467,
+      "learning_rate": 9.344981222110476e-05,
+      "loss": 1.4741159439086915,
+      "step": 465
+    },
+    {
+      "epoch": 0.19258348699037084,
+      "grad_norm": 0.20866990089416504,
+      "learning_rate": 9.328467007334644e-05,
+      "loss": 1.5097124099731445,
+      "step": 470
+    },
+    {
+      "epoch": 0.1946322474902684,
+      "grad_norm": 0.23041853308677673,
+      "learning_rate": 9.311762169358756e-05,
+      "loss": 1.4168277740478517,
+      "step": 475
+    },
+    {
+      "epoch": 0.19668100799016594,
+      "grad_norm": 0.2880827784538269,
+      "learning_rate": 9.294867443854278e-05,
+      "loss": 1.4393327713012696,
+      "step": 480
+    },
+    {
+      "epoch": 0.19872976849006352,
+      "grad_norm": 0.2284889668226242,
+      "learning_rate": 9.277783574855216e-05,
+      "loss": 1.4856295585632324,
+      "step": 485
+    },
+    {
+      "epoch": 0.20077852898996107,
+      "grad_norm": 0.24570758640766144,
+      "learning_rate": 9.260511314725345e-05,
+      "loss": 1.4248931884765625,
+      "step": 490
+    },
+    {
+      "epoch": 0.20282728948985865,
+      "grad_norm": 0.27798447012901306,
+      "learning_rate": 9.243051424125075e-05,
+      "loss": 1.394399070739746,
+      "step": 495
+    },
+    {
+      "epoch": 0.2048760499897562,
+      "grad_norm": 0.2614104747772217,
+      "learning_rate": 9.225404671977958e-05,
+      "loss": 1.3983064651489259,
+      "step": 500
+    },
+    {
+      "epoch": 0.20692481048965375,
+      "grad_norm": 0.3356623947620392,
+      "learning_rate": 9.207571835436817e-05,
+      "loss": 1.4227911949157714,
+      "step": 505
+    },
+    {
+      "epoch": 0.20897357098955133,
+      "grad_norm": 0.2546500563621521,
+      "learning_rate": 9.189553699849531e-05,
+      "loss": 1.4694543838500977,
+      "step": 510
+    },
+    {
+      "epoch": 0.21102233148944888,
+      "grad_norm": 0.24359320104122162,
+      "learning_rate": 9.171351058724438e-05,
+      "loss": 1.4746439933776856,
+      "step": 515
+    },
+    {
+      "epoch": 0.21307109198934646,
+      "grad_norm": 0.2713043987751007,
+      "learning_rate": 9.152964713695394e-05,
+      "loss": 1.485608959197998,
+      "step": 520
+    },
+    {
+      "epoch": 0.215119852489244,
+      "grad_norm": 0.25672438740730286,
+      "learning_rate": 9.13439547448647e-05,
+      "loss": 1.4169066429138184,
+      "step": 525
+    },
+    {
+      "epoch": 0.21716861298914156,
+      "grad_norm": 0.22777284681797028,
+      "learning_rate": 9.11564415887629e-05,
+      "loss": 1.471420669555664,
+      "step": 530
+    },
+    {
+      "epoch": 0.21921737348903914,
+      "grad_norm": 0.2580239772796631,
+      "learning_rate": 9.096711592662024e-05,
+      "loss": 1.4527959823608398,
+      "step": 535
+    },
+    {
+      "epoch": 0.2212661339889367,
+      "grad_norm": 0.29860880970954895,
+      "learning_rate": 9.077598609623006e-05,
+      "loss": 1.4406033515930177,
+      "step": 540
+    },
+    {
+      "epoch": 0.22331489448883426,
+      "grad_norm": 0.227583110332489,
+      "learning_rate": 9.05830605148403e-05,
+      "loss": 1.4660936355590821,
+      "step": 545
+    },
+    {
+      "epoch": 0.22536365498873182,
+      "grad_norm": 0.2497350126504898,
+      "learning_rate": 9.038834767878271e-05,
+      "loss": 1.404551887512207,
+      "step": 550
+    },
+    {
+      "epoch": 0.22741241548862937,
+      "grad_norm": 0.29901331663131714,
+      "learning_rate": 9.019185616309871e-05,
+      "loss": 1.4354202270507812,
+      "step": 555
+    },
+    {
+      "epoch": 0.22946117598852694,
+      "grad_norm": 0.3162592053413391,
+      "learning_rate": 8.999359462116179e-05,
+      "loss": 1.4384968757629395,
+      "step": 560
+    },
+    {
+      "epoch": 0.2315099364884245,
+      "grad_norm": 0.22549550235271454,
+      "learning_rate": 8.979357178429629e-05,
+      "loss": 1.4681221008300782,
+      "step": 565
+    },
+    {
+      "epoch": 0.23355869698832207,
+      "grad_norm": 0.284475713968277,
+      "learning_rate": 8.959179646139306e-05,
+      "loss": 1.4166464805603027,
+      "step": 570
+    },
+    {
+      "epoch": 0.23560745748821962,
+      "grad_norm": 0.2415207326412201,
+      "learning_rate": 8.938827753852139e-05,
+      "loss": 1.4529620170593263,
+      "step": 575
+    },
+    {
+      "epoch": 0.2376562179881172,
+      "grad_norm": 0.28347429633140564,
+      "learning_rate": 8.918302397853768e-05,
+      "loss": 1.3879154205322266,
+      "step": 580
+    },
+    {
+      "epoch": 0.23970497848801475,
+      "grad_norm": 0.2309315800666809,
+      "learning_rate": 8.89760448206908e-05,
+      "loss": 1.4026724815368652,
+      "step": 585
+    },
+    {
+      "epoch": 0.2417537389879123,
+      "grad_norm": 0.2549407482147217,
+      "learning_rate": 8.876734918022396e-05,
+      "loss": 1.4273411750793457,
+      "step": 590
+    },
+    {
+      "epoch": 0.24380249948780988,
+      "grad_norm": 0.26534315943717957,
+      "learning_rate": 8.855694624797323e-05,
+      "loss": 1.435719871520996,
+      "step": 595
+    },
+    {
+      "epoch": 0.24585125998770743,
+      "grad_norm": 0.24261313676834106,
+      "learning_rate": 8.834484528996287e-05,
+      "loss": 1.4434633255004883,
+      "step": 600
+    },
+    {
+      "epoch": 0.247900020487605,
+      "grad_norm": 0.2663251459598541,
+      "learning_rate": 8.81310556469972e-05,
+      "loss": 1.4197578430175781,
+      "step": 605
+    },
+    {
+      "epoch": 0.24994878098750256,
+      "grad_norm": 0.29551461338996887,
+      "learning_rate": 8.791558673424927e-05,
+      "loss": 1.4145501136779786,
+      "step": 610
+    },
+    {
+      "epoch": 0.2519975414874001,
+      "grad_norm": 0.26111581921577454,
+      "learning_rate": 8.769844804084619e-05,
+      "loss": 1.3836070060729981,
+      "step": 615
+    },
+    {
+      "epoch": 0.25404630198729766,
+      "grad_norm": 0.2754769027233124,
+      "learning_rate": 8.747964912945126e-05,
+      "loss": 1.375813102722168,
+      "step": 620
+    },
+    {
+      "epoch": 0.25609506248719527,
+      "grad_norm": 0.2979014813899994,
+      "learning_rate": 8.725919963584284e-05,
+      "loss": 1.404350185394287,
+      "step": 625
+    },
+    {
+      "epoch": 0.2581438229870928,
+      "grad_norm": 0.25742533802986145,
+      "learning_rate": 8.703710926848995e-05,
+      "loss": 1.4270490646362304,
+      "step": 630
+    },
+    {
+      "epoch": 0.26019258348699037,
+      "grad_norm": 0.2671586871147156,
+      "learning_rate": 8.681338780812478e-05,
+      "loss": 1.4215302467346191,
+      "step": 635
+    },
+    {
+      "epoch": 0.2622413439868879,
+      "grad_norm": 0.24798347055912018,
+      "learning_rate": 8.65880451073119e-05,
+      "loss": 1.3883832931518554,
+      "step": 640
+    },
+    {
+      "epoch": 0.26429010448678547,
+      "grad_norm": 0.25624319911003113,
+      "learning_rate": 8.636109109001438e-05,
+      "loss": 1.3987154006958007,
+      "step": 645
+    },
+    {
+      "epoch": 0.2663388649866831,
+      "grad_norm": 0.2776278257369995,
+      "learning_rate": 8.613253575115674e-05,
+      "loss": 1.4250391006469727,
+      "step": 650
+    },
+    {
+      "epoch": 0.2683876254865806,
+      "grad_norm": 0.24240653216838837,
+      "learning_rate": 8.590238915618478e-05,
+      "loss": 1.3983430862426758,
+      "step": 655
+    },
+    {
+      "epoch": 0.2704363859864782,
+      "grad_norm": 0.313040167093277,
+      "learning_rate": 8.567066144062232e-05,
+      "loss": 1.4165125846862794,
+      "step": 660
+    },
+    {
+      "epoch": 0.27248514648637573,
+      "grad_norm": 0.2239057719707489,
+      "learning_rate": 8.543736280962482e-05,
+      "loss": 1.4146951675415038,
+      "step": 665
+    },
+    {
+      "epoch": 0.2745339069862733,
+      "grad_norm": 0.24279819428920746,
+      "learning_rate": 8.520250353752994e-05,
+      "loss": 1.374000072479248,
+      "step": 670
+    },
+    {
+      "epoch": 0.2765826674861709,
+      "grad_norm": 0.2530207335948944,
+      "learning_rate": 8.496609396740506e-05,
+      "loss": 1.3910686492919921,
+      "step": 675
+    },
+    {
+      "epoch": 0.27863142798606844,
+      "grad_norm": 0.2640305459499359,
+      "learning_rate": 8.472814451059185e-05,
+      "loss": 1.414646053314209,
+      "step": 680
+    },
+    {
+      "epoch": 0.280680188485966,
+      "grad_norm": 0.30423691868782043,
+      "learning_rate": 8.448866564624767e-05,
+      "loss": 1.385770320892334,
+      "step": 685
+    },
+    {
+      "epoch": 0.28272894898586354,
+      "grad_norm": 0.2550116181373596,
+      "learning_rate": 8.424766792088408e-05,
+      "loss": 1.4430712699890136,
+      "step": 690
+    },
+    {
+      "epoch": 0.2847777094857611,
+      "grad_norm": 0.2585057318210602,
+      "learning_rate": 8.400516194790248e-05,
+      "loss": 1.431678009033203,
+      "step": 695
+    },
+    {
+      "epoch": 0.2868264699856587,
+      "grad_norm": 0.23218859732151031,
+      "learning_rate": 8.376115840712655e-05,
+      "loss": 1.428140640258789,
+      "step": 700
+    },
+    {
+      "epoch": 0.28887523048555624,
+      "grad_norm": 0.2256380021572113,
+      "learning_rate": 8.351566804433207e-05,
+      "loss": 1.387028694152832,
+      "step": 705
+    },
+    {
+      "epoch": 0.2909239909854538,
+      "grad_norm": 0.2610380947589874,
+      "learning_rate": 8.326870167077354e-05,
+      "loss": 1.3684893608093263,
+      "step": 710
+    },
+    {
+      "epoch": 0.29297275148535135,
+      "grad_norm": 0.23140601813793182,
+      "learning_rate": 8.302027016270816e-05,
+      "loss": 1.441634464263916,
+      "step": 715
+    },
+    {
+      "epoch": 0.29502151198524895,
+      "grad_norm": 0.26682963967323303,
+      "learning_rate": 8.277038446091683e-05,
+      "loss": 1.397985076904297,
+      "step": 720
+    },
+    {
+      "epoch": 0.2970702724851465,
+      "grad_norm": 0.24728651344776154,
+      "learning_rate": 8.251905557022225e-05,
+      "loss": 1.4176549911499023,
+      "step": 725
+    },
+    {
+      "epoch": 0.29911903298504405,
+      "grad_norm": 0.2417927235364914,
+      "learning_rate": 8.226629455900439e-05,
+      "loss": 1.4267874717712403,
+      "step": 730
+    },
+    {
+      "epoch": 0.3011677934849416,
+      "grad_norm": 0.2424582988023758,
+      "learning_rate": 8.201211255871293e-05,
+      "loss": 1.4091911315917969,
+      "step": 735
+    },
+    {
+      "epoch": 0.30321655398483915,
+      "grad_norm": 0.2556217610836029,
+      "learning_rate": 8.175652076337716e-05,
+      "loss": 1.3907686233520509,
+      "step": 740
+    },
+    {
+      "epoch": 0.30526531448473676,
+      "grad_norm": 0.29587826132774353,
+      "learning_rate": 8.149953042911285e-05,
+      "loss": 1.334212875366211,
+      "step": 745
+    },
+    {
+      "epoch": 0.3073140749846343,
+      "grad_norm": 0.25268369913101196,
+      "learning_rate": 8.12411528736267e-05,
+      "loss": 1.3741695404052734,
+      "step": 750
+    },
+    {
+      "epoch": 0.30936283548453186,
+      "grad_norm": 0.24352218210697174,
+      "learning_rate": 8.098139947571781e-05,
+      "loss": 1.413456630706787,
+      "step": 755
+    },
+    {
+      "epoch": 0.3114115959844294,
+      "grad_norm": 0.3103497326374054,
+      "learning_rate": 8.072028167477653e-05,
+      "loss": 1.3564380645751952,
+      "step": 760
+    },
+    {
+      "epoch": 0.31346035648432696,
+      "grad_norm": 0.23528125882148743,
+      "learning_rate": 8.045781097028083e-05,
+      "loss": 1.3844446182250976,
+      "step": 765
+    },
+    {
+      "epoch": 0.31550911698422457,
+      "grad_norm": 0.23526157438755035,
+      "learning_rate": 8.019399892128973e-05,
+      "loss": 1.4341442108154296,
+      "step": 770
+    },
+    {
+      "epoch": 0.3175578774841221,
+      "grad_norm": 0.2674661874771118,
+      "learning_rate": 7.992885714593428e-05,
+      "loss": 1.3701774597167968,
+      "step": 775
+    },
+    {
+      "epoch": 0.31960663798401967,
+      "grad_norm": 0.3181021511554718,
+      "learning_rate": 7.966239732090592e-05,
+      "loss": 1.392444133758545,
+      "step": 780
+    },
+    {
+      "epoch": 0.3216553984839172,
+      "grad_norm": 0.23052622377872467,
+      "learning_rate": 7.939463118094226e-05,
+      "loss": 1.3783914566040039,
+      "step": 785
+    },
+    {
+      "epoch": 0.32370415898381477,
+      "grad_norm": 0.24676229059696198,
+      "learning_rate": 7.912557051831026e-05,
+      "loss": 1.3894118309020995,
+      "step": 790
+    },
+    {
+      "epoch": 0.3257529194837124,
+      "grad_norm": 0.26313456892967224,
+      "learning_rate": 7.88552271822869e-05,
+      "loss": 1.3717985153198242,
+      "step": 795
+    },
+    {
+      "epoch": 0.32780167998360993,
+      "grad_norm": 0.23142893612384796,
+      "learning_rate": 7.85836130786374e-05,
+      "loss": 1.3737470626831054,
+      "step": 800
+    },
+    {
+      "epoch": 0.3298504404835075,
+      "grad_norm": 0.28132501244544983,
+      "learning_rate": 7.831074016909079e-05,
+      "loss": 1.393061065673828,
+      "step": 805
+    },
+    {
+      "epoch": 0.33189920098340503,
+      "grad_norm": 0.23959563672542572,
+      "learning_rate": 7.803662047081323e-05,
+      "loss": 1.4265385627746583,
+      "step": 810
+    },
+    {
+      "epoch": 0.3339479614833026,
+      "grad_norm": 0.2802128493785858,
+      "learning_rate": 7.776126605587877e-05,
+      "loss": 1.3852554321289063,
+      "step": 815
+    },
+    {
+      "epoch": 0.3359967219832002,
+      "grad_norm": 0.23754750192165375,
+      "learning_rate": 7.748468905073762e-05,
+      "loss": 1.3224260330200195,
+      "step": 820
+    },
+    {
+      "epoch": 0.33804548248309774,
+      "grad_norm": 0.3146839141845703,
+      "learning_rate": 7.720690163568214e-05,
+      "loss": 1.3887696266174316,
+      "step": 825
+    },
+    {
+      "epoch": 0.3400942429829953,
+      "grad_norm": 0.2297493815422058,
+      "learning_rate": 7.692791604431053e-05,
+      "loss": 1.4230521202087403,
+      "step": 830
+    },
+    {
+      "epoch": 0.34214300348289284,
+      "grad_norm": 0.24353939294815063,
+      "learning_rate": 7.664774456298794e-05,
+      "loss": 1.4169343948364257,
+      "step": 835
+    },
+    {
+      "epoch": 0.3441917639827904,
+      "grad_norm": 0.24568147957324982,
+      "learning_rate": 7.636639953030541e-05,
+      "loss": 1.41996488571167,
+      "step": 840
+    },
+    {
+      "epoch": 0.346240524482688,
+      "grad_norm": 0.29424890875816345,
+      "learning_rate": 7.608389333653654e-05,
+      "loss": 1.4314729690551757,
+      "step": 845
+    },
+    {
+      "epoch": 0.34828928498258555,
+      "grad_norm": 0.2366134524345398,
+      "learning_rate": 7.580023842309179e-05,
+      "loss": 1.4061026573181152,
+      "step": 850
+    },
+    {
+      "epoch": 0.3503380454824831,
+      "grad_norm": 0.2897055745124817,
+      "learning_rate": 7.551544728197057e-05,
+      "loss": 1.3732454299926757,
+      "step": 855
+    },
+    {
+      "epoch": 0.35238680598238065,
+      "grad_norm": 0.24869121611118317,
+      "learning_rate": 7.522953245521111e-05,
+      "loss": 1.3359421730041503,
+      "step": 860
+    },
+    {
+      "epoch": 0.3544355664822782,
+      "grad_norm": 0.24955961108207703,
+      "learning_rate": 7.49425065343381e-05,
+      "loss": 1.3852300643920898,
+      "step": 865
+    },
+    {
+      "epoch": 0.3564843269821758,
+      "grad_norm": 0.2611676752567291,
+      "learning_rate": 7.465438215980819e-05,
+      "loss": 1.3831953048706054,
+      "step": 870
+    },
+    {
+      "epoch": 0.35853308748207335,
+      "grad_norm": 0.24830710887908936,
+      "learning_rate": 7.43651720204533e-05,
+      "loss": 1.3709842681884765,
+      "step": 875
+    },
+    {
+      "epoch": 0.3605818479819709,
+      "grad_norm": 0.27635136246681213,
+      "learning_rate": 7.407488885292176e-05,
+      "loss": 1.395904541015625,
+      "step": 880
+    },
+    {
+      "epoch": 0.36263060848186845,
+      "grad_norm": 0.23471049964427948,
+      "learning_rate": 7.378354544111755e-05,
+      "loss": 1.3872676849365235,
+      "step": 885
+    },
+    {
+      "epoch": 0.364679368981766,
+      "grad_norm": 0.22868774831295013,
+      "learning_rate": 7.349115461563706e-05,
+      "loss": 1.3842597007751465,
+      "step": 890
+    },
+    {
+      "epoch": 0.3667281294816636,
+      "grad_norm": 0.28394395112991333,
+      "learning_rate": 7.319772925320429e-05,
+      "loss": 1.3023405075073242,
+      "step": 895
+    },
+    {
+      "epoch": 0.36877688998156116,
+      "grad_norm": 0.3127804398536682,
+      "learning_rate": 7.290328227610362e-05,
+      "loss": 1.380778694152832,
+      "step": 900
+    },
+    {
+      "epoch": 0.3708256504814587,
+      "grad_norm": 0.2542979121208191,
+      "learning_rate": 7.260782665161071e-05,
+      "loss": 1.3942995071411133,
+      "step": 905
+    },
+    {
+      "epoch": 0.37287441098135626,
+      "grad_norm": 0.25020891427993774,
+      "learning_rate": 7.231137539142154e-05,
+      "loss": 1.3625518798828125,
+      "step": 910
+    },
+    {
+      "epoch": 0.3749231714812538,
+      "grad_norm": 0.23338639736175537,
+      "learning_rate": 7.201394155107928e-05,
+      "loss": 1.3762397766113281,
+      "step": 915
+    },
+    {
+      "epoch": 0.3769719319811514,
+      "grad_norm": 0.27335304021835327,
+      "learning_rate": 7.171553822939934e-05,
+      "loss": 1.368981170654297,
+      "step": 920
+    },
+    {
+      "epoch": 0.37902069248104897,
+      "grad_norm": 0.22844389081001282,
+      "learning_rate": 7.141617856789256e-05,
+      "loss": 1.3485469818115234,
+      "step": 925
+    },
+    {
+      "epoch": 0.3810694529809465,
+      "grad_norm": 0.2914579212665558,
+      "learning_rate": 7.111587575018648e-05,
+      "loss": 1.3404122352600099,
+      "step": 930
+    },
+    {
+      "epoch": 0.38311821348084407,
+      "grad_norm": 0.2583613395690918,
+      "learning_rate": 7.081464300144459e-05,
+      "loss": 1.384856605529785,
+      "step": 935
+    },
+    {
+      "epoch": 0.3851669739807417,
+      "grad_norm": 0.2729097008705139,
+      "learning_rate": 7.05124935877841e-05,
+      "loss": 1.3637308120727538,
+      "step": 940
+    },
+    {
+      "epoch": 0.38721573448063923,
+      "grad_norm": 0.2922956645488739,
+      "learning_rate": 7.020944081569158e-05,
+      "loss": 1.3832178115844727,
+      "step": 945
+    },
+    {
+      "epoch": 0.3892644949805368,
+      "grad_norm": 0.2305232137441635,
+      "learning_rate": 6.990549803143702e-05,
+      "loss": 1.3829986572265625,
+      "step": 950
+    },
+    {
+      "epoch": 0.39131325548043433,
+      "grad_norm": 0.319938600063324,
+      "learning_rate": 6.960067862048596e-05,
+      "loss": 1.356369972229004,
+      "step": 955
+    },
+    {
+      "epoch": 0.3933620159803319,
+      "grad_norm": 0.2918975353240967,
+      "learning_rate": 6.929499600691014e-05,
+      "loss": 1.3989985466003418,
+      "step": 960
+    },
+    {
+      "epoch": 0.3954107764802295,
+      "grad_norm": 0.2598877251148224,
+      "learning_rate": 6.898846365279625e-05,
+      "loss": 1.386563205718994,
+      "step": 965
+    },
+    {
+      "epoch": 0.39745953698012704,
+      "grad_norm": 0.26635628938674927,
+      "learning_rate": 6.868109505765302e-05,
+      "loss": 1.4037010192871093,
+      "step": 970
+    },
+    {
+      "epoch": 0.3995082974800246,
+      "grad_norm": 0.2128853052854538,
+      "learning_rate": 6.837290375781678e-05,
+      "loss": 1.3343305587768555,
+      "step": 975
+    },
+    {
+      "epoch": 0.40155705797992214,
+      "grad_norm": 0.27108311653137207,
+      "learning_rate": 6.806390332585531e-05,
+      "loss": 1.3232428550720214,
+      "step": 980
+    },
+    {
+      "epoch": 0.4036058184798197,
+      "grad_norm": 0.30043405294418335,
+      "learning_rate": 6.775410736997011e-05,
+      "loss": 1.3404928207397462,
+      "step": 985
+    },
+    {
+      "epoch": 0.4056545789797173,
+      "grad_norm": 0.2834998667240143,
+      "learning_rate": 6.744352953339706e-05,
+      "loss": 1.349217128753662,
+      "step": 990
+    },
+    {
+      "epoch": 0.40770333947961485,
+      "grad_norm": 0.26514801383018494,
+      "learning_rate": 6.713218349380565e-05,
+      "loss": 1.413687801361084,
+      "step": 995
+    },
+    {
+      "epoch": 0.4097520999795124,
+      "grad_norm": 0.2575552761554718,
+      "learning_rate": 6.682008296269655e-05,
+      "loss": 1.3566946029663085,
+      "step": 1000
+    },
+    {
+      "epoch": 0.41180086047940995,
+      "grad_norm": 0.21779005229473114,
+      "learning_rate": 6.650724168479789e-05,
+      "loss": 1.3173069953918457,
+      "step": 1005
+    },
+    {
+      "epoch": 0.4138496209793075,
+      "grad_norm": 0.24155494570732117,
+      "learning_rate": 6.619367343745974e-05,
+      "loss": 1.3530547142028808,
+      "step": 1010
+    },
+    {
+      "epoch": 0.4158983814792051,
+      "grad_norm": 0.29116934537887573,
+      "learning_rate": 6.587939203004758e-05,
+      "loss": 1.3223274230957032,
+      "step": 1015
+    },
+    {
+      "epoch": 0.41794714197910265,
+      "grad_norm": 0.22972193360328674,
+      "learning_rate": 6.556441130333403e-05,
+      "loss": 1.3388238906860352,
+      "step": 1020
+    },
+    {
+      "epoch": 0.4199959024790002,
+      "grad_norm": 0.2570706009864807,
+      "learning_rate": 6.52487451288893e-05,
+      "loss": 1.3459800720214843,
+      "step": 1025
+    },
+    {
+      "epoch": 0.42204466297889776,
+      "grad_norm": 0.29197683930397034,
+      "learning_rate": 6.493240740847036e-05,
+      "loss": 1.3437597274780273,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4240934234787953,
+      "grad_norm": 0.263208270072937,
+      "learning_rate": 6.461541207340866e-05,
+      "loss": 1.3420764923095703,
+      "step": 1035
+    },
+    {
+      "epoch": 0.4261421839786929,
+      "grad_norm": 0.25823986530303955,
+      "learning_rate": 6.429777308399661e-05,
+      "loss": 1.2823150634765625,
+      "step": 1040
+    },
+    {
+      "epoch": 0.42819094447859046,
+      "grad_norm": 0.250011146068573,
+      "learning_rate": 6.397950442887282e-05,
+      "loss": 1.3275934219360352,
+      "step": 1045
+    },
+    {
+      "epoch": 0.430239704978488,
+      "grad_norm": 0.24056175351142883,
+      "learning_rate": 6.366062012440599e-05,
+      "loss": 1.3687356948852538,
+      "step": 1050
+    },
+    {
+      "epoch": 0.43228846547838556,
+      "grad_norm": 0.24977155029773712,
+      "learning_rate": 6.334113421407768e-05,
+      "loss": 1.348299503326416,
+      "step": 1055
+    },
+    {
+      "epoch": 0.4343372259782831,
+      "grad_norm": 0.2569001317024231,
+      "learning_rate": 6.302106076786381e-05,
+      "loss": 1.3371658325195312,
+      "step": 1060
+    },
+    {
+      "epoch": 0.4363859864781807,
+      "grad_norm": 0.24413055181503296,
+      "learning_rate": 6.270041388161503e-05,
+      "loss": 1.3305369377136231,
+      "step": 1065
+    },
+    {
+      "epoch": 0.43843474697807827,
+      "grad_norm": 0.26988592743873596,
+      "learning_rate": 6.237920767643603e-05,
+      "loss": 1.317184066772461,
+      "step": 1070
+    },
+    {
+      "epoch": 0.4404835074779758,
+      "grad_norm": 0.2695789933204651,
+      "learning_rate": 6.205745629806351e-05,
+      "loss": 1.4001937866210938,
+      "step": 1075
+    },
+    {
+      "epoch": 0.4425322679778734,
+      "grad_norm": 0.2830488979816437,
+      "learning_rate": 6.173517391624331e-05,
+      "loss": 1.3247421264648438,
+      "step": 1080
+    },
+    {
+      "epoch": 0.4445810284777709,
+      "grad_norm": 0.2438943237066269,
+      "learning_rate": 6.141237472410633e-05,
+      "loss": 1.3202712059020996,
+      "step": 1085
+    },
+    {
+      "epoch": 0.44662978897766853,
+      "grad_norm": 0.26069164276123047,
+      "learning_rate": 6.108907293754356e-05,
+      "loss": 1.3685693740844727,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4486785494775661,
+      "grad_norm": 0.25841134786605835,
+      "learning_rate": 6.0765282794579934e-05,
+      "loss": 1.3607157707214355,
+      "step": 1095
+    },
+    {
+      "epoch": 0.45072730997746363,
+      "grad_norm": 0.2689521610736847,
+      "learning_rate": 6.0441018554747283e-05,
+      "loss": 1.3058736801147461,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4527760704773612,
+      "grad_norm": 0.2704612612724304,
+      "learning_rate": 6.0116294498456436e-05,
+      "loss": 1.2852808952331543,
+      "step": 1105
+    },
+    {
+      "epoch": 0.45482483097725873,
+      "grad_norm": 0.3054133355617523,
+      "learning_rate": 5.979112492636824e-05,
+      "loss": 1.2694639205932616,
+      "step": 1110
+    },
+    {
+      "epoch": 0.45687359147715634,
+      "grad_norm": 0.25625643134117126,
+      "learning_rate": 5.946552415876385e-05,
+      "loss": 1.399122428894043,
+      "step": 1115
+    },
+    {
+      "epoch": 0.4589223519770539,
+      "grad_norm": 0.27514946460723877,
+      "learning_rate": 5.913950653491398e-05,
+      "loss": 1.32147216796875,
+      "step": 1120
+    },
+    {
+      "epoch": 0.46097111247695144,
+      "grad_norm": 0.2821177542209625,
+      "learning_rate": 5.881308641244747e-05,
+      "loss": 1.3212553024291993,
+      "step": 1125
+    },
+    {
+      "epoch": 0.463019872976849,
+      "grad_norm": 0.2913643717765808,
+      "learning_rate": 5.848627816671896e-05,
+      "loss": 1.307069683074951,
+      "step": 1130
+    },
+    {
+      "epoch": 0.4650686334767466,
+      "grad_norm": 0.2578153610229492,
+      "learning_rate": 5.815909619017586e-05,
+      "loss": 1.360389518737793,
+      "step": 1135
+    },
+    {
+      "epoch": 0.46711739397664415,
+      "grad_norm": 0.2550489008426666,
+      "learning_rate": 5.783155489172437e-05,
+      "loss": 1.3405406951904297,
+      "step": 1140
+    },
+    {
+      "epoch": 0.4691661544765417,
+      "grad_norm": 0.2353593111038208,
+      "learning_rate": 5.7503668696095134e-05,
+      "loss": 1.3537275314331054,
+      "step": 1145
+    },
+    {
+      "epoch": 0.47121491497643925,
+      "grad_norm": 0.26253747940063477,
+      "learning_rate": 5.71754520432078e-05,
+      "loss": 1.3509612083435059,
+      "step": 1150
+    },
+    {
+      "epoch": 0.4732636754763368,
+      "grad_norm": 0.2936980426311493,
+      "learning_rate": 5.684691938753517e-05,
+      "loss": 1.3521942138671874,
+      "step": 1155
+    },
+    {
+      "epoch": 0.4753124359762344,
+      "grad_norm": 0.28643450140953064,
+      "learning_rate": 5.6518085197466666e-05,
+      "loss": 1.2855645179748536,
+      "step": 1160
+    },
+    {
+      "epoch": 0.47736119647613195,
+      "grad_norm": 0.24552711844444275,
+      "learning_rate": 5.618896395467106e-05,
+      "loss": 1.3012152671813966,
+      "step": 1165
+    },
+    {
+      "epoch": 0.4794099569760295,
+      "grad_norm": 0.2718487083911896,
+      "learning_rate": 5.585957015345882e-05,
+      "loss": 1.2932754516601563,
+      "step": 1170
+    },
+    {
+      "epoch": 0.48145871747592706,
+      "grad_norm": 0.2751079201698303,
+      "learning_rate": 5.5529918300143646e-05,
+      "loss": 1.3228282928466797,
+      "step": 1175
+    },
+    {
+      "epoch": 0.4835074779758246,
+      "grad_norm": 0.30440232157707214,
+      "learning_rate": 5.520002291240379e-05,
+      "loss": 1.2851292610168457,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4855562384757222,
+      "grad_norm": 0.26172778010368347,
+      "learning_rate": 5.486989851864258e-05,
+      "loss": 1.3420797348022462,
+      "step": 1185
+    },
+    {
+      "epoch": 0.48760499897561976,
+      "grad_norm": 0.2193116545677185,
+      "learning_rate": 5.453955965734865e-05,
+      "loss": 1.3628318786621094,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4896537594755173,
+      "grad_norm": 0.22195489704608917,
+      "learning_rate": 5.4209020876455616e-05,
+      "loss": 1.342047119140625,
+      "step": 1195
+    },
+    {
+      "epoch": 0.49170251997541486,
+      "grad_norm": 0.3061356544494629,
+      "learning_rate": 5.3878296732701515e-05,
+      "loss": 1.3385862350463866,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4937512804753124,
+      "grad_norm": 0.29457172751426697,
+      "learning_rate": 5.3547401790987614e-05,
+      "loss": 1.331954002380371,
+      "step": 1205
+    },
+    {
+      "epoch": 0.49580004097521,
+      "grad_norm": 0.28309834003448486,
+      "learning_rate": 5.321635062373701e-05,
+      "loss": 1.313936996459961,
+      "step": 1210
+    },
+    {
+      "epoch": 0.49784880147510757,
+      "grad_norm": 0.22304044663906097,
+      "learning_rate": 5.2885157810252915e-05,
+      "loss": 1.273549747467041,
+      "step": 1215
+    },
+    {
+      "epoch": 0.4998975619750051,
+      "grad_norm": 0.2599666714668274,
+      "learning_rate": 5.255383793607652e-05,
+      "loss": 1.3385022163391114,
+      "step": 1220
+    },
+    {
+      "epoch": 0.5019463224749027,
+      "grad_norm": 0.32061707973480225,
+      "learning_rate": 5.222240559234478e-05,
+      "loss": 1.29484281539917,
+      "step": 1225
+    },
+    {
+      "epoch": 0.5039950829748002,
+      "grad_norm": 0.27749156951904297,
+      "learning_rate": 5.189087537514763e-05,
+      "loss": 1.3214826583862305,
+      "step": 1230
+    },
+    {
+      "epoch": 0.5060438434746978,
+      "grad_norm": 0.2755792737007141,
+      "learning_rate": 5.1559261884885365e-05,
+      "loss": 1.3251422882080077,
+      "step": 1235
+    },
+    {
+      "epoch": 0.5080926039745953,
+      "grad_norm": 0.25735047459602356,
+      "learning_rate": 5.122757972562559e-05,
+      "loss": 1.305452537536621,
+      "step": 1240
+    },
+    {
+      "epoch": 0.510141364474493,
+      "grad_norm": 0.2969847321510315,
+      "learning_rate": 5.0895843504460005e-05,
+      "loss": 1.3473756790161133,
+      "step": 1245
+    },
+    {
+      "epoch": 0.5121901249743905,
+      "grad_norm": 0.2501281499862671,
+      "learning_rate": 5.056406783086119e-05,
+      "loss": 1.3407386779785155,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5142388854742881,
+      "grad_norm": 0.2557857930660248,
+      "learning_rate": 5.0232267316039194e-05,
+      "loss": 1.3123600006103515,
+      "step": 1255
+    },
+    {
+      "epoch": 0.5162876459741856,
+      "grad_norm": 0.2559100091457367,
+      "learning_rate": 4.9900456572298055e-05,
+      "loss": 1.3318202018737793,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5183364064740832,
+      "grad_norm": 0.2925871014595032,
+      "learning_rate": 4.956865021239229e-05,
+      "loss": 1.3344091415405273,
+      "step": 1265
+    },
+    {
+      "epoch": 0.5203851669739807,
+      "grad_norm": 0.30870094895362854,
+      "learning_rate": 4.9236862848883307e-05,
+      "loss": 1.355853271484375,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5224339274738783,
+      "grad_norm": 0.22683072090148926,
+      "learning_rate": 4.890510909349602e-05,
+      "loss": 1.3050634384155273,
+      "step": 1275
+    },
+    {
+      "epoch": 0.5244826879737758,
+      "grad_norm": 0.2503475248813629,
+      "learning_rate": 4.8573403556475174e-05,
+      "loss": 1.2940337181091308,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5265314484736734,
+      "grad_norm": 0.24663148820400238,
+      "learning_rate": 4.824176084594202e-05,
+      "loss": 1.317142868041992,
+      "step": 1285
+    },
+    {
+      "epoch": 0.5285802089735709,
+      "grad_norm": 0.2633092403411865,
+      "learning_rate": 4.791019556725104e-05,
+      "loss": 1.331963062286377,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5306289694734686,
+      "grad_norm": 0.2536119222640991,
+      "learning_rate": 4.757872232234654e-05,
+      "loss": 1.3190467834472657,
+      "step": 1295
+    },
+    {
+      "epoch": 0.5326777299733662,
+      "grad_norm": 0.25456032156944275,
+      "learning_rate": 4.72473557091198e-05,
+      "loss": 1.3109964370727538,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5347264904732637,
+      "grad_norm": 0.27136334776878357,
+      "learning_rate": 4.691611032076611e-05,
+      "loss": 1.3283430099487306,
+      "step": 1305
+    },
+    {
+      "epoch": 0.5367752509731613,
+      "grad_norm": 0.32845261693000793,
+      "learning_rate": 4.6585000745142e-05,
+      "loss": 1.3527785301208497,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5388240114730588,
+      "grad_norm": 0.2597561478614807,
+      "learning_rate": 4.6254041564122974e-05,
+      "loss": 1.337641143798828,
+      "step": 1315
+    },
+    {
+      "epoch": 0.5408727719729564,
+      "grad_norm": 0.23634375631809235,
+      "learning_rate": 4.592324735296122e-05,
+      "loss": 1.3620846748352051,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5429215324728539,
+      "grad_norm": 0.2323814034461975,
+      "learning_rate": 4.559263267964369e-05,
+      "loss": 1.3232294082641602,
+      "step": 1325
+    },
+    {
+      "epoch": 0.5449702929727515,
+      "grad_norm": 0.3491435647010803,
+      "learning_rate": 4.526221210425068e-05,
+      "loss": 1.342482852935791,
+      "step": 1330
+    },
+    {
+      "epoch": 0.547019053472649,
+      "grad_norm": 0.24202945828437805,
+      "learning_rate": 4.493200017831448e-05,
+      "loss": 1.3122220039367676,
+      "step": 1335
+    },
+    {
+      "epoch": 0.5490678139725466,
+      "grad_norm": 0.2727183699607849,
+      "learning_rate": 4.460201144417856e-05,
+      "loss": 1.2724044799804688,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5511165744724442,
+      "grad_norm": 0.3009723424911499,
+      "learning_rate": 4.427226043435721e-05,
+      "loss": 1.3199892044067383,
+      "step": 1345
+    },
+    {
+      "epoch": 0.5531653349723418,
+      "grad_norm": 0.2472936362028122,
+      "learning_rate": 4.3942761670895416e-05,
+      "loss": 1.2971452713012694,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5552140954722393,
+      "grad_norm": 0.2375025898218155,
+      "learning_rate": 4.361352966472942e-05,
+      "loss": 1.2770438194274902,
+      "step": 1355
+    },
+    {
+      "epoch": 0.5572628559721369,
+      "grad_norm": 0.2597000300884247,
+      "learning_rate": 4.328457891504759e-05,
+      "loss": 1.336366844177246,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5593116164720344,
+      "grad_norm": 0.24963222444057465,
+      "learning_rate": 4.295592390865194e-05,
+      "loss": 1.2757173538208009,
+      "step": 1365
+    },
+    {
+      "epoch": 0.561360376971932,
+      "grad_norm": 0.2574042081832886,
+      "learning_rate": 4.262757911932017e-05,
+      "loss": 1.315561866760254,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5634091374718295,
+      "grad_norm": 0.3084658980369568,
+      "learning_rate": 4.22995590071681e-05,
+      "loss": 1.334895706176758,
+      "step": 1375
+    },
+    {
+      "epoch": 0.5654578979717271,
+      "grad_norm": 0.27679547667503357,
+      "learning_rate": 4.197187801801301e-05,
+      "loss": 1.2854586601257325,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5675066584716246,
+      "grad_norm": 0.2964513301849365,
+      "learning_rate": 4.1644550582737425e-05,
+      "loss": 1.2758905410766601,
+      "step": 1385
+    },
+    {
+      "epoch": 0.5695554189715222,
+      "grad_norm": 0.253574937582016,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.3365299224853515,
+      "step": 1390
+    },
+    {
+      "epoch": 0.5716041794714198,
+      "grad_norm": 0.23930352926254272,
+      "learning_rate": 4.0991014018868255e-05,
+      "loss": 1.2856715202331543,
+      "step": 1395
+    },
+    {
+      "epoch": 0.5736529399713174,
+      "grad_norm": 0.32823678851127625,
+      "learning_rate": 4.066483367164944e-05,
+      "loss": 1.3103887557983398,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5757017004712149,
+      "grad_norm": 0.27578920125961304,
+      "learning_rate": 4.0339064439792154e-05,
+      "loss": 1.3238027572631836,
+      "step": 1405
+    },
+    {
+      "epoch": 0.5777504609711125,
+      "grad_norm": 0.27465036511421204,
+      "learning_rate": 4.001372066998621e-05,
+      "loss": 1.2640934944152833,
+      "step": 1410
+    },
+    {
+      "epoch": 0.57979922147101,
+      "grad_norm": 0.32577401399612427,
+      "learning_rate": 3.9688816690184254e-05,
+      "loss": 1.2457879066467286,
+      "step": 1415
+    },
+    {
+      "epoch": 0.5818479819709076,
+      "grad_norm": 0.2472367286682129,
+      "learning_rate": 3.936436680897093e-05,
+      "loss": 1.2836155891418457,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5838967424708051,
+      "grad_norm": 0.2659171521663666,
+      "learning_rate": 3.904038531493257e-05,
+      "loss": 1.3078968048095703,
+      "step": 1425
+    },
+    {
+      "epoch": 0.5859455029707027,
+      "grad_norm": 0.242190420627594,
+      "learning_rate": 3.871688647602801e-05,
+      "loss": 1.3004875183105469,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5879942634706002,
+      "grad_norm": 0.28040608763694763,
+      "learning_rate": 3.8393884538960276e-05,
+      "loss": 1.3254682540893554,
+      "step": 1435
+    },
+    {
+      "epoch": 0.5900430239704979,
+      "grad_norm": 0.31349673867225647,
+      "learning_rate": 3.8071393728549074e-05,
+      "loss": 1.3339305877685548,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5920917844703955,
+      "grad_norm": 0.293557345867157,
+      "learning_rate": 3.7749428247104425e-05,
+      "loss": 1.3391931533813477,
+      "step": 1445
+    },
+    {
+      "epoch": 0.594140544970293,
+      "grad_norm": 0.2590584456920624,
+      "learning_rate": 3.742800227380113e-05,
+      "loss": 1.2496644020080567,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5961893054701906,
+      "grad_norm": 0.26042333245277405,
+      "learning_rate": 3.7107129964054366e-05,
+      "loss": 1.295633029937744,
+      "step": 1455
+    },
+    {
+      "epoch": 0.5982380659700881,
+      "grad_norm": 0.27969884872436523,
+      "learning_rate": 3.678682544889633e-05,
+      "loss": 1.3115250587463378,
+      "step": 1460
+    },
+    {
+      "epoch": 0.6002868264699857,
+      "grad_norm": 0.2707354426383972,
+      "learning_rate": 3.646710283435381e-05,
+      "loss": 1.3354633331298829,
+      "step": 1465
+    },
+    {
+      "epoch": 0.6023355869698832,
+      "grad_norm": 0.2651318311691284,
+      "learning_rate": 3.614797620082703e-05,
+      "loss": 1.2992894172668457,
+      "step": 1470
+    },
+    {
+      "epoch": 0.6043843474697808,
+      "grad_norm": 0.33234038949012756,
+      "learning_rate": 3.582945960246963e-05,
+      "loss": 1.2405622482299805,
+      "step": 1475
+    },
+    {
+      "epoch": 0.6064331079696783,
+      "grad_norm": 0.24927560985088348,
+      "learning_rate": 3.5511567066569556e-05,
+      "loss": 1.3072126388549805,
+      "step": 1480
+    },
+    {
+      "epoch": 0.6084818684695759,
+      "grad_norm": 0.24822548031806946,
+      "learning_rate": 3.519431259293147e-05,
+      "loss": 1.3031463623046875,
+      "step": 1485
+    },
+    {
+      "epoch": 0.6105306289694735,
+      "grad_norm": 0.275709331035614,
+      "learning_rate": 3.4877710153260055e-05,
+      "loss": 1.300545883178711,
+      "step": 1490
+    },
+    {
+      "epoch": 0.6125793894693711,
+      "grad_norm": 0.31339898705482483,
+      "learning_rate": 3.4561773690544916e-05,
+      "loss": 1.2730562210083007,
+      "step": 1495
+    },
+    {
+      "epoch": 0.6146281499692686,
+      "grad_norm": 0.29074031114578247,
+      "learning_rate": 3.424651711844632e-05,
+      "loss": 1.2959768295288085,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6166769104691662,
+      "grad_norm": 0.2879445254802704,
+      "learning_rate": 3.393195432068255e-05,
+      "loss": 1.3154520988464355,
+      "step": 1505
+    },
+    {
+      "epoch": 0.6187256709690637,
+      "grad_norm": 0.24617347121238708,
+      "learning_rate": 3.3618099150418496e-05,
+      "loss": 1.2540883064270019,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6207744314689613,
+      "grad_norm": 0.28609418869018555,
+      "learning_rate": 3.330496542965556e-05,
+      "loss": 1.326852035522461,
+      "step": 1515
+    },
+    {
+      "epoch": 0.6228231919688588,
+      "grad_norm": 0.3080059289932251,
+      "learning_rate": 3.299256694862286e-05,
+      "loss": 1.2670875549316407,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6248719524687564,
+      "grad_norm": 0.2557651698589325,
+      "learning_rate": 3.268091746517003e-05,
+      "loss": 1.3000967025756835,
+      "step": 1525
+    },
+    {
+      "epoch": 0.6269207129686539,
+      "grad_norm": 0.26694655418395996,
+      "learning_rate": 3.237003070416122e-05,
+      "loss": 1.3506081581115723,
+      "step": 1530
+    },
+    {
+      "epoch": 0.6289694734685515,
+      "grad_norm": 0.25305208563804626,
+      "learning_rate": 3.205992035687082e-05,
+      "loss": 1.2666000366210937,
+      "step": 1535
+    },
+    {
+      "epoch": 0.6310182339684491,
+      "grad_norm": 0.2855704724788666,
+      "learning_rate": 3.1750600080380324e-05,
+      "loss": 1.2966244697570801,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6330669944683467,
+      "grad_norm": 0.34034767746925354,
+      "learning_rate": 3.144208349697696e-05,
+      "loss": 1.3045336723327636,
+      "step": 1545
+    },
+    {
+      "epoch": 0.6351157549682442,
+      "grad_norm": 0.23100696504116058,
+      "learning_rate": 3.1134384193553846e-05,
+      "loss": 1.2965570449829102,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6371645154681418,
+      "grad_norm": 0.31095659732818604,
+      "learning_rate": 3.082751572101148e-05,
+      "loss": 1.2695819854736328,
+      "step": 1555
+    },
+    {
+      "epoch": 0.6392132759680393,
+      "grad_norm": 0.30058884620666504,
+      "learning_rate": 3.052149159366109e-05,
+      "loss": 1.3026172637939453,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6412620364679369,
+      "grad_norm": 0.2729285955429077,
+      "learning_rate": 3.0216325288629434e-05,
+      "loss": 1.297075080871582,
+      "step": 1565
+    },
+    {
+      "epoch": 0.6433107969678344,
+      "grad_norm": 0.22582866251468658,
+      "learning_rate": 2.991203024526522e-05,
+      "loss": 1.2851219177246094,
+      "step": 1570
+    },
+    {
+      "epoch": 0.645359557467732,
+      "grad_norm": 0.2653510570526123,
+      "learning_rate": 2.9608619864547337e-05,
+      "loss": 1.3354564666748048,
+      "step": 1575
+    },
+    {
+      "epoch": 0.6474083179676295,
+      "grad_norm": 0.31849929690361023,
+      "learning_rate": 2.930610750849465e-05,
+      "loss": 1.3141709327697755,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6494570784675271,
+      "grad_norm": 0.2686974108219147,
+      "learning_rate": 2.9004506499577467e-05,
+      "loss": 1.303685188293457,
+      "step": 1585
+    },
+    {
+      "epoch": 0.6515058389674248,
+      "grad_norm": 0.2840675115585327,
+      "learning_rate": 2.8703830120130976e-05,
+      "loss": 1.3127184867858888,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6535545994673223,
+      "grad_norm": 0.2510277330875397,
+      "learning_rate": 2.8404091611770112e-05,
+      "loss": 1.284514808654785,
+      "step": 1595
+    },
+    {
+      "epoch": 0.6556033599672199,
+      "grad_norm": 0.252000093460083,
+      "learning_rate": 2.8105304174806622e-05,
+      "loss": 1.296556282043457,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6576521204671174,
+      "grad_norm": 0.2759515047073364,
+      "learning_rate": 2.7807480967667576e-05,
+      "loss": 1.2639286994934082,
+      "step": 1605
+    },
+    {
+      "epoch": 0.659700880967015,
+      "grad_norm": 0.28356698155403137,
+      "learning_rate": 2.7510635106315818e-05,
+      "loss": 1.2562575340270996,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6617496414669125,
+      "grad_norm": 0.22170349955558777,
+      "learning_rate": 2.7214779663672613e-05,
+      "loss": 1.2881322860717774,
+      "step": 1615
+    },
+    {
+      "epoch": 0.6637984019668101,
+      "grad_norm": 0.26950734853744507,
+      "learning_rate": 2.691992766904161e-05,
+      "loss": 1.292411994934082,
+      "step": 1620
+    },
+    {
+      "epoch": 0.6658471624667076,
+      "grad_norm": 0.2663452625274658,
+      "learning_rate": 2.6626092107535255e-05,
+      "loss": 1.3220889091491699,
+      "step": 1625
+    },
+    {
+      "epoch": 0.6678959229666052,
+      "grad_norm": 0.24590684473514557,
+      "learning_rate": 2.6333285919502904e-05,
+      "loss": 1.2977161407470703,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6699446834665027,
+      "grad_norm": 0.25957298278808594,
+      "learning_rate": 2.604152199996077e-05,
+      "loss": 1.3181549072265626,
+      "step": 1635
+    },
+    {
+      "epoch": 0.6719934439664004,
+      "grad_norm": 0.26257196068763733,
+      "learning_rate": 2.5750813198024258e-05,
+      "loss": 1.2938770294189452,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6740422044662979,
+      "grad_norm": 0.22499914467334747,
+      "learning_rate": 2.546117231634203e-05,
+      "loss": 1.2501792907714844,
+      "step": 1645
+    },
+    {
+      "epoch": 0.6760909649661955,
+      "grad_norm": 0.25946611166000366,
+      "learning_rate": 2.5172612110532012e-05,
+      "loss": 1.2768983840942383,
+      "step": 1650
+    },
+    {
+      "epoch": 0.678139725466093,
+      "grad_norm": 0.2690495550632477,
+      "learning_rate": 2.4885145288619954e-05,
+      "loss": 1.2538825035095216,
+      "step": 1655
+    },
+    {
+      "epoch": 0.6801884859659906,
+      "grad_norm": 0.2518579065799713,
+      "learning_rate": 2.4598784510479478e-05,
+      "loss": 1.2962369918823242,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6822372464658881,
+      "grad_norm": 0.2591659426689148,
+      "learning_rate": 2.4313542387274717e-05,
+      "loss": 1.2961651802062988,
+      "step": 1665
+    },
+    {
+      "epoch": 0.6842860069657857,
+      "grad_norm": 0.25808605551719666,
+      "learning_rate": 2.402943148090495e-05,
+      "loss": 1.3074354171752929,
+      "step": 1670
+    },
+    {
+      "epoch": 0.6863347674656832,
+      "grad_norm": 0.3189685344696045,
+      "learning_rate": 2.3746464303451195e-05,
+      "loss": 1.2566020011901855,
+      "step": 1675
+    },
+    {
+      "epoch": 0.6883835279655808,
+      "grad_norm": 0.2833169102668762,
+      "learning_rate": 2.3464653316625385e-05,
+      "loss": 1.2559724807739259,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6904322884654784,
+      "grad_norm": 0.2548830509185791,
+      "learning_rate": 2.3184010931221467e-05,
+      "loss": 1.29913272857666,
+      "step": 1685
+    },
+    {
+      "epoch": 0.692481048965376,
+      "grad_norm": 0.311108261346817,
+      "learning_rate": 2.2904549506568845e-05,
+      "loss": 1.318597412109375,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6945298094652735,
+      "grad_norm": 0.28917980194091797,
+      "learning_rate": 2.2626281349988103e-05,
+      "loss": 1.275995635986328,
+      "step": 1695
+    },
+    {
+      "epoch": 0.6965785699651711,
+      "grad_norm": 0.3064703941345215,
+      "learning_rate": 2.2349218716248965e-05,
+      "loss": 1.277532958984375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6986273304650686,
+      "grad_norm": 0.26498550176620483,
+      "learning_rate": 2.2073373807030645e-05,
+      "loss": 1.2777314186096191,
+      "step": 1705
+    },
+    {
+      "epoch": 0.7006760909649662,
+      "grad_norm": 0.3053685128688812,
+      "learning_rate": 2.1798758770384442e-05,
+      "loss": 1.3030251502990722,
+      "step": 1710
+    },
+    {
+      "epoch": 0.7027248514648637,
+      "grad_norm": 0.2815582752227783,
+      "learning_rate": 2.15253857001988e-05,
+      "loss": 1.275032138824463,
+      "step": 1715
+    },
+    {
+      "epoch": 0.7047736119647613,
+      "grad_norm": 0.2703726291656494,
+      "learning_rate": 2.125326663566666e-05,
+      "loss": 1.282528781890869,
+      "step": 1720
+    },
+    {
+      "epoch": 0.7068223724646588,
+      "grad_norm": 0.27605587244033813,
+      "learning_rate": 2.0982413560755272e-05,
+      "loss": 1.3028643608093262,
+      "step": 1725
+    },
+    {
+      "epoch": 0.7088711329645564,
+      "grad_norm": 0.2783604562282562,
+      "learning_rate": 2.0712838403678437e-05,
+      "loss": 1.2267531394958495,
+      "step": 1730
+    },
+    {
+      "epoch": 0.7109198934644541,
+      "grad_norm": 0.26805320382118225,
+      "learning_rate": 2.0444553036371184e-05,
+      "loss": 1.2264631271362305,
+      "step": 1735
+    },
+    {
+      "epoch": 0.7129686539643516,
+      "grad_norm": 0.2512497901916504,
+      "learning_rate": 2.0177569273966945e-05,
+      "loss": 1.2998706817626953,
+      "step": 1740
+    },
+    {
+      "epoch": 0.7150174144642492,
+      "grad_norm": 0.22863002121448517,
+      "learning_rate": 1.991189887427723e-05,
+      "loss": 1.2844582557678224,
+      "step": 1745
+    },
+    {
+      "epoch": 0.7170661749641467,
+      "grad_norm": 0.3078356385231018,
+      "learning_rate": 1.9647553537273784e-05,
+      "loss": 1.3187359809875487,
+      "step": 1750
+    },
+    {
+      "epoch": 0.7191149354640443,
+      "grad_norm": 0.2768361270427704,
+      "learning_rate": 1.938454490457337e-05,
+      "loss": 1.261814498901367,
+      "step": 1755
+    },
+    {
+      "epoch": 0.7211636959639418,
+      "grad_norm": 0.2588041424751282,
+      "learning_rate": 1.912288455892507e-05,
+      "loss": 1.2723341941833497,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7232124564638394,
+      "grad_norm": 0.29791882634162903,
+      "learning_rate": 1.8862584023700152e-05,
+      "loss": 1.2284412384033203,
+      "step": 1765
+    },
+    {
+      "epoch": 0.7252612169637369,
+      "grad_norm": 0.2947942912578583,
+      "learning_rate": 1.8603654762384642e-05,
+      "loss": 1.2617098808288574,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7273099774636345,
+      "grad_norm": 0.2487948089838028,
+      "learning_rate": 1.8346108178074432e-05,
+      "loss": 1.255106544494629,
+      "step": 1775
+    },
+    {
+      "epoch": 0.729358737963532,
+      "grad_norm": 0.3134167790412903,
+      "learning_rate": 1.808995561297313e-05,
+      "loss": 1.2975893020629883,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7314074984634297,
+      "grad_norm": 0.2561521530151367,
+      "learning_rate": 1.7835208347892535e-05,
+      "loss": 1.299635887145996,
+      "step": 1785
+    },
+    {
+      "epoch": 0.7334562589633272,
+      "grad_norm": 0.26338133215904236,
+      "learning_rate": 1.7581877601755786e-05,
+      "loss": 1.2896413803100586,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7355050194632248,
+      "grad_norm": 0.25681066513061523,
+      "learning_rate": 1.7329974531103445e-05,
+      "loss": 1.3228384017944337,
+      "step": 1795
+    },
+    {
+      "epoch": 0.7375537799631223,
+      "grad_norm": 0.2786136865615845,
+      "learning_rate": 1.707951022960199e-05,
+      "loss": 1.2736244201660156,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7396025404630199,
+      "grad_norm": 0.31009337306022644,
+      "learning_rate": 1.6830495727555356e-05,
+      "loss": 1.2667587280273438,
+      "step": 1805
+    },
+    {
+      "epoch": 0.7416513009629174,
+      "grad_norm": 0.29153525829315186,
+      "learning_rate": 1.6582941991419155e-05,
+      "loss": 1.2426738739013672,
+      "step": 1810
+    },
+    {
+      "epoch": 0.743700061462815,
+      "grad_norm": 0.289066344499588,
+      "learning_rate": 1.6336859923317643e-05,
+      "loss": 1.2665628433227538,
+      "step": 1815
+    },
+    {
+      "epoch": 0.7457488219627125,
+      "grad_norm": 0.2895960211753845,
+      "learning_rate": 1.6092260360563764e-05,
+      "loss": 1.308458137512207,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7477975824626101,
+      "grad_norm": 0.3129257559776306,
+      "learning_rate": 1.584915407518172e-05,
+      "loss": 1.278462028503418,
+      "step": 1825
+    },
+    {
+      "epoch": 0.7498463429625076,
+      "grad_norm": 0.2577885687351227,
+      "learning_rate": 1.56075517734326e-05,
+      "loss": 1.2392581939697265,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7518951034624053,
+      "grad_norm": 0.2576925456523895,
+      "learning_rate": 1.5367464095343004e-05,
+      "loss": 1.2508735656738281,
+      "step": 1835
+    },
+    {
+      "epoch": 0.7539438639623028,
+      "grad_norm": 0.28750625252723694,
+      "learning_rate": 1.512890161423633e-05,
+      "loss": 1.2708032608032227,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7559926244622004,
+      "grad_norm": 0.3189471364021301,
+      "learning_rate": 1.4891874836267127e-05,
+      "loss": 1.2719980239868165,
+      "step": 1845
+    },
+    {
+      "epoch": 0.7580413849620979,
+      "grad_norm": 0.28972774744033813,
+      "learning_rate": 1.465639419995858e-05,
+      "loss": 1.2980030059814454,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7600901454619955,
+      "grad_norm": 0.23746366798877716,
+      "learning_rate": 1.4422470075742566e-05,
+      "loss": 1.264305877685547,
+      "step": 1855
+    },
+    {
+      "epoch": 0.762138905961893,
+      "grad_norm": 0.26893913745880127,
+      "learning_rate": 1.4190112765503117e-05,
+      "loss": 1.200902557373047,
+      "step": 1860
+    },
+    {
+      "epoch": 0.7641876664617906,
+      "grad_norm": 0.3206225633621216,
+      "learning_rate": 1.3959332502122718e-05,
+      "loss": 1.2565690994262695,
+      "step": 1865
+    },
+    {
+      "epoch": 0.7662364269616881,
+      "grad_norm": 0.3166133463382721,
+      "learning_rate": 1.3730139449031504e-05,
+      "loss": 1.3032503128051758,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7682851874615857,
+      "grad_norm": 0.25825440883636475,
+      "learning_rate": 1.3502543699759917e-05,
+      "loss": 1.2491080284118652,
+      "step": 1875
+    },
+    {
+      "epoch": 0.7703339479614834,
+      "grad_norm": 0.31449419260025024,
+      "learning_rate": 1.3276555277493946e-05,
+      "loss": 1.246892261505127,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7723827084613809,
+      "grad_norm": 0.2545924782752991,
+      "learning_rate": 1.3052184134633855e-05,
+      "loss": 1.2655725479125977,
+      "step": 1885
+    },
+    {
+      "epoch": 0.7744314689612785,
+      "grad_norm": 0.227932870388031,
+      "learning_rate": 1.2829440152355915e-05,
+      "loss": 1.3136140823364257,
+      "step": 1890
+    },
+    {
+      "epoch": 0.776480229461176,
+      "grad_norm": 0.2593846321105957,
+      "learning_rate": 1.2608333140177076e-05,
+      "loss": 1.2817180633544922,
+      "step": 1895
+    },
+    {
+      "epoch": 0.7785289899610736,
+      "grad_norm": 0.26868492364883423,
+      "learning_rate": 1.2388872835523119e-05,
+      "loss": 1.3057626724243163,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7805777504609711,
+      "grad_norm": 0.25460517406463623,
+      "learning_rate": 1.217106890329981e-05,
+      "loss": 1.268224334716797,
+      "step": 1905
+    },
+    {
+      "epoch": 0.7826265109608687,
+      "grad_norm": 0.333560049533844,
+      "learning_rate": 1.1954930935467146e-05,
+      "loss": 1.2454710006713867,
+      "step": 1910
+    },
+    {
+      "epoch": 0.7846752714607662,
+      "grad_norm": 0.3333158791065216,
+      "learning_rate": 1.1740468450617054e-05,
+      "loss": 1.2856892585754394,
+      "step": 1915
+    },
+    {
+      "epoch": 0.7867240319606638,
+      "grad_norm": 0.28260311484336853,
+      "learning_rate": 1.1527690893554156e-05,
+      "loss": 1.2880863189697265,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7887727924605613,
+      "grad_norm": 0.2771768867969513,
+      "learning_rate": 1.1316607634879783e-05,
+      "loss": 1.1994852066040038,
+      "step": 1925
+    },
+    {
+      "epoch": 0.790821552960459,
+      "grad_norm": 0.3035411536693573,
+      "learning_rate": 1.1107227970579426e-05,
+      "loss": 1.3171918869018555,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7928703134603565,
+      "grad_norm": 0.2470470666885376,
+      "learning_rate": 1.0899561121613145e-05,
+      "loss": 1.261275291442871,
+      "step": 1935
+    },
+    {
+      "epoch": 0.7949190739602541,
+      "grad_norm": 0.2612347900867462,
+      "learning_rate": 1.0693616233509673e-05,
+      "loss": 1.2847448348999024,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7969678344601516,
+      "grad_norm": 0.23703554272651672,
+      "learning_rate": 1.0489402375963558e-05,
+      "loss": 1.2919179916381835,
+      "step": 1945
+    },
+    {
+      "epoch": 0.7990165949600492,
+      "grad_norm": 0.2935525178909302,
+      "learning_rate": 1.0286928542435754e-05,
+      "loss": 1.3142457008361816,
+      "step": 1950
+    },
+    {
+      "epoch": 0.8010653554599467,
+      "grad_norm": 0.2707836627960205,
+      "learning_rate": 1.0086203649757547e-05,
+      "loss": 1.3001995086669922,
+      "step": 1955
+    },
+    {
+      "epoch": 0.8031141159598443,
+      "grad_norm": 0.3044240474700928,
+      "learning_rate": 9.887236537737893e-06,
+      "loss": 1.2901924133300782,
+      "step": 1960
+    },
+    {
+      "epoch": 0.8051628764597418,
+      "grad_norm": 0.31032100319862366,
+      "learning_rate": 9.69003596877408e-06,
+      "loss": 1.2298809051513673,
+      "step": 1965
+    },
+    {
+      "epoch": 0.8072116369596394,
+      "grad_norm": 0.3038262128829956,
+      "learning_rate": 9.494610627465873e-06,
+      "loss": 1.320767593383789,
+      "step": 1970
+    },
+    {
+      "epoch": 0.8092603974595369,
+      "grad_norm": 0.28116574883461,
+      "learning_rate": 9.300969120233011e-06,
+      "loss": 1.245682716369629,
+      "step": 1975
+    },
+    {
+      "epoch": 0.8113091579594346,
+      "grad_norm": 0.3026755154132843,
+      "learning_rate": 9.109119974936214e-06,
+      "loss": 1.2956615447998048,
+      "step": 1980
+    },
+    {
+      "epoch": 0.8133579184593321,
+      "grad_norm": 0.3298123776912689,
+      "learning_rate": 8.91907164050162e-06,
+      "loss": 1.216292381286621,
+      "step": 1985
+    },
+    {
+      "epoch": 0.8154066789592297,
+      "grad_norm": 0.31193673610687256,
+      "learning_rate": 8.73083248654868e-06,
+      "loss": 1.315388011932373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.8174554394591272,
+      "grad_norm": 0.28355783224105835,
+      "learning_rate": 8.544410803021574e-06,
+      "loss": 1.2899145126342773,
+      "step": 1995
+    },
+    {
+      "epoch": 0.8195041999590248,
+      "grad_norm": 0.2982524633407593,
+      "learning_rate": 8.359814799824151e-06,
+      "loss": 1.2231454849243164,
+      "step": 2000
+    },
+    {
+      "epoch": 0.8215529604589223,
+      "grad_norm": 0.28412801027297974,
+      "learning_rate": 8.177052606458313e-06,
+      "loss": 1.2293264389038085,
+      "step": 2005
+    },
+    {
+      "epoch": 0.8236017209588199,
+      "grad_norm": 0.23140159249305725,
+      "learning_rate": 7.996132271666062e-06,
+      "loss": 1.270032024383545,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8256504814587174,
+      "grad_norm": 0.23607365787029266,
+      "learning_rate": 7.817061763074989e-06,
+      "loss": 1.2720687866210938,
+      "step": 2015
+    },
+    {
+      "epoch": 0.827699241958615,
+      "grad_norm": 0.25011885166168213,
+      "learning_rate": 7.639848966847401e-06,
+      "loss": 1.274172878265381,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8297480024585125,
+      "grad_norm": 0.24104824662208557,
+      "learning_rate": 7.4645016873330366e-06,
+      "loss": 1.2375362396240235,
+      "step": 2025
+    },
+    {
+      "epoch": 0.8317967629584102,
+      "grad_norm": 0.2356707602739334,
+      "learning_rate": 7.2910276467253235e-06,
+      "loss": 1.2449207305908203,
+      "step": 2030
+    },
+    {
+      "epoch": 0.8338455234583078,
+      "grad_norm": 0.263530969619751,
+      "learning_rate": 7.1194344847213546e-06,
+      "loss": 1.2540871620178222,
+      "step": 2035
+    },
+    {
+      "epoch": 0.8358942839582053,
+      "grad_norm": 0.28406116366386414,
+      "learning_rate": 6.949729758185386e-06,
+      "loss": 1.2791433334350586,
+      "step": 2040
+    },
+    {
+      "epoch": 0.8379430444581029,
+      "grad_norm": 0.2656693160533905,
+      "learning_rate": 6.781920940816084e-06,
+      "loss": 1.2917613983154297,
+      "step": 2045
+    },
+    {
+      "epoch": 0.8399918049580004,
+      "grad_norm": 0.26287469267845154,
+      "learning_rate": 6.616015422817312e-06,
+      "loss": 1.2640438079833984,
+      "step": 2050
+    },
+    {
+      "epoch": 0.842040565457898,
+      "grad_norm": 0.26781660318374634,
+      "learning_rate": 6.452020510572798e-06,
+      "loss": 1.2651849746704102,
+      "step": 2055
+    },
+    {
+      "epoch": 0.8440893259577955,
+      "grad_norm": 0.27933159470558167,
+      "learning_rate": 6.289943426324252e-06,
+      "loss": 1.2664341926574707,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8461380864576931,
+      "grad_norm": 0.2520369589328766,
+      "learning_rate": 6.129791307853311e-06,
+      "loss": 1.2497535705566407,
+      "step": 2065
+    },
+    {
+      "epoch": 0.8481868469575906,
+      "grad_norm": 0.32474976778030396,
+      "learning_rate": 5.971571208167298e-06,
+      "loss": 1.2943989753723144,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8502356074574883,
+      "grad_norm": 0.24403078854084015,
+      "learning_rate": 5.815290095188452e-06,
+      "loss": 1.2382102966308595,
+      "step": 2075
+    },
+    {
+      "epoch": 0.8522843679573858,
+      "grad_norm": 0.4058358669281006,
+      "learning_rate": 5.660954851447231e-06,
+      "loss": 1.284989833831787,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8543331284572834,
+      "grad_norm": 0.2560180723667145,
+      "learning_rate": 5.508572273779089e-06,
+      "loss": 1.2697216987609863,
+      "step": 2085
+    },
+    {
+      "epoch": 0.8563818889571809,
+      "grad_norm": 0.3305165469646454,
+      "learning_rate": 5.358149073025176e-06,
+      "loss": 1.294536304473877,
+      "step": 2090
+    },
+    {
+      "epoch": 0.8584306494570785,
+      "grad_norm": 0.272367388010025,
+      "learning_rate": 5.209691873736844e-06,
+      "loss": 1.2944642066955567,
+      "step": 2095
+    },
+    {
+      "epoch": 0.860479409956976,
+      "grad_norm": 0.3072604238986969,
+      "learning_rate": 5.0632072138838584e-06,
+      "loss": 1.2385089874267579,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8625281704568736,
+      "grad_norm": 0.3105360269546509,
+      "learning_rate": 4.918701544566445e-06,
+      "loss": 1.3222164154052733,
+      "step": 2105
+    },
+    {
+      "epoch": 0.8645769309567711,
+      "grad_norm": 0.2450399100780487,
+      "learning_rate": 4.776181229731297e-06,
+      "loss": 1.3005769729614258,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8666256914566687,
+      "grad_norm": 0.29846152663230896,
+      "learning_rate": 4.635652545891156e-06,
+      "loss": 1.243008518218994,
+      "step": 2115
+    },
+    {
+      "epoch": 0.8686744519565662,
+      "grad_norm": 0.27357882261276245,
+      "learning_rate": 4.497121681848521e-06,
+      "loss": 1.2400178909301758,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8707232124564639,
+      "grad_norm": 0.28386640548706055,
+      "learning_rate": 4.360594738423085e-06,
+      "loss": 1.2798059463500977,
+      "step": 2125
+    },
+    {
+      "epoch": 0.8727719729563614,
+      "grad_norm": 0.2667112648487091,
+      "learning_rate": 4.226077728182959e-06,
+      "loss": 1.2321090698242188,
+      "step": 2130
+    },
+    {
+      "epoch": 0.874820733456259,
+      "grad_norm": 0.2955249845981598,
+      "learning_rate": 4.093576575179997e-06,
+      "loss": 1.2780116081237793,
+      "step": 2135
+    },
+    {
+      "epoch": 0.8768694939561565,
+      "grad_norm": 0.25143980979919434,
+      "learning_rate": 3.963097114688846e-06,
+      "loss": 1.2406365394592285,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8789182544560541,
+      "grad_norm": 0.2803260087966919,
+      "learning_rate": 3.834645092949973e-06,
+      "loss": 1.31375732421875,
+      "step": 2145
+    },
+    {
+      "epoch": 0.8809670149559516,
+      "grad_norm": 0.3295106589794159,
+      "learning_rate": 3.7082261669166398e-06,
+      "loss": 1.2383207321166991,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8830157754558492,
+      "grad_norm": 0.2879765033721924,
+      "learning_rate": 3.5838459040056836e-06,
+      "loss": 1.2484712600708008,
+      "step": 2155
+    },
+    {
+      "epoch": 0.8850645359557467,
+      "grad_norm": 0.31380727887153625,
+      "learning_rate": 3.4615097818524235e-06,
+      "loss": 1.234403133392334,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8871132964556443,
+      "grad_norm": 0.25417637825012207,
+      "learning_rate": 3.3412231880694145e-06,
+      "loss": 1.2650720596313476,
+      "step": 2165
+    },
+    {
+      "epoch": 0.8891620569555418,
+      "grad_norm": 0.26758092641830444,
+      "learning_rate": 3.2229914200091083e-06,
+      "loss": 1.276659870147705,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8912108174554395,
+      "grad_norm": 0.26037827134132385,
+      "learning_rate": 3.1068196845306487e-06,
+      "loss": 1.248143768310547,
+      "step": 2175
+    },
+    {
+      "epoch": 0.8932595779553371,
+      "grad_norm": 0.2570255398750305,
+      "learning_rate": 2.992713097770522e-06,
+      "loss": 1.2920123100280763,
+      "step": 2180
+    },
+    {
+      "epoch": 0.8953083384552346,
+      "grad_norm": 0.286891907453537,
+      "learning_rate": 2.880676684917244e-06,
+      "loss": 1.2495945930480956,
+      "step": 2185
+    },
+    {
+      "epoch": 0.8973570989551322,
+      "grad_norm": 0.31210505962371826,
+      "learning_rate": 2.770715379990069e-06,
+      "loss": 1.2536087036132812,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8994058594550297,
+      "grad_norm": 0.31883350014686584,
+      "learning_rate": 2.66283402562168e-06,
+      "loss": 1.2216848373413085,
+      "step": 2195
+    },
+    {
+      "epoch": 0.9014546199549273,
+      "grad_norm": 0.2685450613498688,
+      "learning_rate": 2.5570373728449504e-06,
+      "loss": 1.3227145195007324,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9035033804548248,
+      "grad_norm": 0.27641502022743225,
+      "learning_rate": 2.4533300808836757e-06,
+      "loss": 1.2525005340576172,
+      "step": 2205
+    },
+    {
+      "epoch": 0.9055521409547224,
+      "grad_norm": 0.31477051973342896,
+      "learning_rate": 2.351716716947411e-06,
+      "loss": 1.26199951171875,
+      "step": 2210
+    },
+    {
+      "epoch": 0.9076009014546199,
+      "grad_norm": 0.23617668449878693,
+      "learning_rate": 2.2522017560303198e-06,
+      "loss": 1.2411357879638671,
+      "step": 2215
+    },
+    {
+      "epoch": 0.9096496619545175,
+      "grad_norm": 0.31558552384376526,
+      "learning_rate": 2.1547895807141004e-06,
+      "loss": 1.2805794715881347,
+      "step": 2220
+    },
+    {
+      "epoch": 0.9116984224544151,
+      "grad_norm": 0.3144230842590332,
+      "learning_rate": 2.0594844809749938e-06,
+      "loss": 1.2999591827392578,
+      "step": 2225
+    },
+    {
+      "epoch": 0.9137471829543127,
+      "grad_norm": 0.264559268951416,
+      "learning_rate": 1.9662906539948288e-06,
+      "loss": 1.2680883407592773,
+      "step": 2230
+    },
+    {
+      "epoch": 0.9157959434542102,
+      "grad_norm": 0.2973203659057617,
+      "learning_rate": 1.875212203976201e-06,
+      "loss": 1.2254125595092773,
+      "step": 2235
+    },
+    {
+      "epoch": 0.9178447039541078,
+      "grad_norm": 0.2835392653942108,
+      "learning_rate": 1.786253141961719e-06,
+      "loss": 1.2514814376831054,
+      "step": 2240
+    },
+    {
+      "epoch": 0.9198934644540053,
+      "grad_norm": 0.29778075218200684,
+      "learning_rate": 1.6994173856573592e-06,
+      "loss": 1.2244014739990234,
+      "step": 2245
+    },
+    {
+      "epoch": 0.9219422249539029,
+      "grad_norm": 0.2697012722492218,
+      "learning_rate": 1.614708759259942e-06,
+      "loss": 1.2447286605834962,
+      "step": 2250
+    },
+    {
+      "epoch": 0.9239909854538004,
+      "grad_norm": 0.24340657889842987,
+      "learning_rate": 1.532130993288705e-06,
+      "loss": 1.2689023971557618,
+      "step": 2255
+    },
+    {
+      "epoch": 0.926039745953698,
+      "grad_norm": 0.2958049178123474,
+      "learning_rate": 1.4516877244210137e-06,
+      "loss": 1.2526524543762207,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9280885064535955,
+      "grad_norm": 0.2687614858150482,
+      "learning_rate": 1.373382495332215e-06,
+      "loss": 1.2677976608276367,
+      "step": 2265
+    },
+    {
+      "epoch": 0.9301372669534932,
+      "grad_norm": 0.3570196330547333,
+      "learning_rate": 1.297218754539592e-06,
+      "loss": 1.261516284942627,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9321860274533907,
+      "grad_norm": 0.2557203471660614,
+      "learning_rate": 1.2231998562505397e-06,
+      "loss": 1.2441003799438477,
+      "step": 2275
+    },
+    {
+      "epoch": 0.9342347879532883,
+      "grad_norm": 0.29218870401382446,
+      "learning_rate": 1.1513290602148174e-06,
+      "loss": 1.2222956657409667,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9362835484531858,
+      "grad_norm": 0.2782398760318756,
+      "learning_rate": 1.0816095315809739e-06,
+      "loss": 1.3262025833129882,
+      "step": 2285
+    },
+    {
+      "epoch": 0.9383323089530834,
+      "grad_norm": 0.30014920234680176,
+      "learning_rate": 1.0140443407570034e-06,
+      "loss": 1.3017868041992187,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9403810694529809,
+      "grad_norm": 0.3028185963630676,
+      "learning_rate": 9.486364632750878e-07,
+      "loss": 1.2263371467590332,
+      "step": 2295
+    },
+    {
+      "epoch": 0.9424298299528785,
+      "grad_norm": 0.2702455520629883,
+      "learning_rate": 8.853887796605675e-07,
+      "loss": 1.3050615310668945,
+      "step": 2300
+    },
+    {
+      "epoch": 0.944478590452776,
+      "grad_norm": 0.32353973388671875,
+      "learning_rate": 8.243040753050935e-07,
+      "loss": 1.2997408866882325,
+      "step": 2305
+    },
+    {
+      "epoch": 0.9465273509526736,
+      "grad_norm": 0.266697496175766,
+      "learning_rate": 7.653850403439411e-07,
+      "loss": 1.258549690246582,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9485761114525711,
+      "grad_norm": 0.27494311332702637,
+      "learning_rate": 7.086342695375669e-07,
+      "loss": 1.2512704849243164,
+      "step": 2315
+    },
+    {
+      "epoch": 0.9506248719524688,
+      "grad_norm": 0.27287960052490234,
+      "learning_rate": 6.540542621573109e-07,
+      "loss": 1.2699396133422851,
+      "step": 2320
+    },
+    {
+      "epoch": 0.9526736324523664,
+      "grad_norm": 0.3075219988822937,
+      "learning_rate": 6.016474218753288e-07,
+      "loss": 1.2208845138549804,
+      "step": 2325
+    },
+    {
+      "epoch": 0.9547223929522639,
+      "grad_norm": 0.27103209495544434,
+      "learning_rate": 5.514160566587711e-07,
+      "loss": 1.2631036758422851,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9567711534521615,
+      "grad_norm": 0.3261513113975525,
+      "learning_rate": 5.033623786680874e-07,
+      "loss": 1.2267972946166992,
+      "step": 2335
+    },
+    {
+      "epoch": 0.958819913952059,
+      "grad_norm": 0.27564314007759094,
+      "learning_rate": 4.5748850415964774e-07,
+      "loss": 1.3072431564331055,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9608686744519566,
+      "grad_norm": 0.2567191421985626,
+      "learning_rate": 4.137964533925398e-07,
+      "loss": 1.2828784942626954,
+      "step": 2345
+    },
+    {
+      "epoch": 0.9629174349518541,
+      "grad_norm": 0.26112931966781616,
+      "learning_rate": 3.7228815053956255e-07,
+      "loss": 1.2677101135253905,
+      "step": 2350
+    },
+    {
+      "epoch": 0.9649661954517517,
+      "grad_norm": 0.2793757915496826,
+      "learning_rate": 3.3296542360253256e-07,
+      "loss": 1.2765470504760743,
+      "step": 2355
+    },
+    {
+      "epoch": 0.9670149559516492,
+      "grad_norm": 0.2792360484600067,
+      "learning_rate": 2.958300043317541e-07,
+      "loss": 1.3070873260498046,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9690637164515468,
+      "grad_norm": 0.2682648301124573,
+      "learning_rate": 2.6088352814974127e-07,
+      "loss": 1.251203727722168,
+      "step": 2365
+    },
+    {
+      "epoch": 0.9711124769514444,
+      "grad_norm": 0.2484222948551178,
+      "learning_rate": 2.281275340792477e-07,
+      "loss": 1.2386321067810058,
+      "step": 2370
+    },
+    {
+      "epoch": 0.973161237451342,
+      "grad_norm": 0.2918150722980499,
+      "learning_rate": 1.975634646754154e-07,
+      "loss": 1.2277518272399903,
+      "step": 2375
+    },
+    {
+      "epoch": 0.9752099979512395,
+      "grad_norm": 0.3734853267669678,
+      "learning_rate": 1.6919266596229777e-07,
+      "loss": 1.2296463012695313,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9772587584511371,
+      "grad_norm": 0.2560795843601227,
+      "learning_rate": 1.4301638737358459e-07,
+      "loss": 1.2675661087036132,
+      "step": 2385
+    },
+    {
+      "epoch": 0.9793075189510346,
+      "grad_norm": 0.24018852412700653,
+      "learning_rate": 1.190357816975407e-07,
+      "loss": 1.2632686614990234,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9813562794509322,
+      "grad_norm": 0.2847444415092468,
+      "learning_rate": 9.725190502625215e-08,
+      "loss": 1.2432889938354492,
+      "step": 2395
+    },
+    {
+      "epoch": 0.9834050399508297,
+      "grad_norm": 0.30964258313179016,
+      "learning_rate": 7.766571670913547e-08,
+      "loss": 1.2989116668701173,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9854538004507273,
+      "grad_norm": 0.24274787306785583,
+      "learning_rate": 6.02780793106772e-08,
+      "loss": 1.2039080619812013,
+      "step": 2405
+    },
+    {
+      "epoch": 0.9875025609506248,
+      "grad_norm": 0.2885257303714752,
+      "learning_rate": 4.508975857243636e-08,
+      "loss": 1.336316204071045,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9895513214505224,
+      "grad_norm": 0.2866789996623993,
+      "learning_rate": 3.210142337932709e-08,
+      "loss": 1.2880182266235352,
+      "step": 2415
+    },
+    {
+      "epoch": 0.99160008195042,
+      "grad_norm": 0.3208368122577667,
+      "learning_rate": 2.1313645730169917e-08,
+      "loss": 1.2637825012207031,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9936488424503176,
+      "grad_norm": 0.2772391438484192,
+      "learning_rate": 1.2726900712495271e-08,
+      "loss": 1.2483304977416991,
+      "step": 2425
+    },
+    {
+      "epoch": 0.9956976029502151,
+      "grad_norm": 0.29975342750549316,
+      "learning_rate": 6.341566481626871e-09,
+      "loss": 1.2414230346679687,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9977463634501127,
+      "grad_norm": 0.2714863419532776,
+      "learning_rate": 2.1579242440006307e-09,
+      "loss": 1.2581830024719238,
+      "step": 2435
+    },
+    {
+      "epoch": 0.9997951239500102,
+      "grad_norm": 0.24638843536376953,
+      "learning_rate": 1.7615824483008248e-10,
+      "loss": 1.2846127510070802,
+      "step": 2440
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2441,
+  "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": 3.005761252417864e+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 sha256:53a1caa92795dc020690be4a76262afd1c5de97fa26fe1da95c477089bcfc273
+size 5969