Upload Phase 2 SFT LoRA adapter for Qwen3-Coder-30B-A3B

.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 +1,210 @@
+---
+base_model: unsloth/qwen3-coder-30b-a3b-instruct
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/qwen3-coder-30b-a3b-instruct
+- lora
+- sft
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Qwen3MoeForCausalLM",
+    "parent_library": "transformers.models.qwen3_moe.modeling_qwen3_moe",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/qwen3-coder-30b-a3b-instruct",
+  "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": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "k_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cde60bd42ba0e2827ba32f16c4fddb2535a5fe4f3fb48cacaa5dc5ecdc51264
+size 53528920

chat_template.jinja

@@ -0,0 +1,117 @@
+{% macro render_extra_keys(json_dict, handled_keys) %}
+    {%- if json_dict is mapping %}
+        {%- for json_key in json_dict if json_key not in handled_keys %}
+            {%- if json_dict[json_key] is mapping or (json_dict[json_key] is sequence and json_dict[json_key] is not string) %}
+                {{- '\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | tojson | safe) ~ '</' ~ json_key ~ '>' }}
+            {%- else %}
+                {{-'\n<' ~ json_key ~ '>' ~ (json_dict[json_key] | string) ~ '</' ~ json_key ~ '>' }}
+            {%- endif %}
+        {%- endfor %}
+    {%- endif %}
+{% endmacro %}
+
+{%- if messages[0]["role"] == "system" %}
+    {%- set system_message = messages[0]["content"] %}
+    {%- set loop_messages = messages[1:] %}
+{%- else %}
+    {%- set loop_messages = messages %}
+{%- endif %}
+
+{%- if not tools is defined %}
+    {%- set tools = [] %}
+{%- endif %}
+
+{%- if system_message is defined %}
+    {{- "<|im_start|>system\n" + system_message }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- "<|im_start|>system\nYou are Qwen, a helpful AI assistant that can interact with a computer to solve tasks." }}
+    {%- endif %}
+{%- endif %}
+{%- if tools is iterable and tools | length > 0 %}
+    {{- "\n\n# Tools\n\nYou have access to the following functions:\n\n" }}
+    {{- "<tools>" }}
+    {%- for tool in tools %}
+        {%- if tool.function is defined %}
+            {%- set tool = tool.function %}
+        {%- endif %}
+        {{- "\n<function>\n<name>" ~ tool.name ~ "</name>" }}
+        {%- if tool.description is defined %}
+            {{- '\n<description>' ~ (tool.description | trim) ~ '</description>' }}
+        {%- endif %}
+        {{- '\n<parameters>' }}
+        {%- if tool.parameters is defined and tool.parameters is mapping and tool.parameters.properties is defined and tool.parameters.properties is mapping %}
+            {%- for param_name, param_fields in tool.parameters.properties|items %}
+                {{- '\n<parameter>' }}
+                {{- '\n<name>' ~ param_name ~ '</name>' }}
+                {%- if param_fields.type is defined %}
+                    {{- '\n<type>' ~ (param_fields.type | string) ~ '</type>' }}
+                {%- endif %}
+                {%- if param_fields.description is defined %}
+                    {{- '\n<description>' ~ (param_fields.description | trim) ~ '</description>' }}
+                {%- endif %}
+                {%- set handled_keys = ['name', 'type', 'description'] %}
+                {{- render_extra_keys(param_fields, handled_keys) }}
+                {{- '\n</parameter>' }}
+            {%- endfor %}
+        {%- endif %}
+        {% set handled_keys = ['type', 'properties'] %}
+        {{- render_extra_keys(tool.parameters, handled_keys) }}
+        {{- '\n</parameters>' }}
+        {%- set handled_keys = ['type', 'name', 'description', 'parameters'] %}
+        {{- render_extra_keys(tool, handled_keys) }}
+        {{- '\n</function>' }}
+    {%- endfor %}
+    {{- "\n</tools>" }}
+    {{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
+{%- endif %}
+{%- if system_message is defined %}
+    {{- '<|im_end|>\n' }}
+{%- else %}
+    {%- if tools is iterable and tools | length > 0 %}
+        {{- '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in loop_messages %}
+    {%- if message.role == "assistant" and message.tool_calls is defined and message.tool_calls is iterable and message.tool_calls | length > 0 %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content is defined and message.content is string and message.content | trim | length > 0 %}
+            {{- '\n' + message.content | trim + '\n' }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
+            {%- if tool_call.arguments is defined %}
+                {%- for args_name, args_value in tool_call.arguments|items %}
+                    {{- '<parameter=' + args_name + '>\n' }}
+                    {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
+                    {{- args_value }}
+                    {{- '\n</parameter>\n' }}
+                {%- endfor %}
+            {%- endif %}
+            {{- '</function>\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "user" or message.role == "system" or message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.previtem and loop.previtem.role != "tool" %}
+            {{- '<|im_start|>user\n' }}
+        {%- endif %}
+        {{- '<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>\n' }}
+        {%- if not loop.last and loop.nextitem.role != "tool" %}
+            {{- '<|im_end|>\n' }}
+        {%- elif loop.last %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- else %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21da1389d90078681f323034462345d391e942ad088bce2d53451c012a89908c
+size 27610661

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4a9f217e852f439efa6bd32fde98d6867f11aa6ea13ddc021ba10af6a0b0934
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfc19035a1a18708d650e2a44796f7e775dd5cdba7d2f40572ec1e950be4568b
+size 1465

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:45c4ffda6666cf6d75d0b1f961f25964e2a52a62e78aaecb2f458e9ba9824112
+size 11422840

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": false,
+  "model_max_length": 262144,
+  "pad_token": "<|PAD_TOKEN|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,2834 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.844950213371266,
+  "eval_steps": 99999,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.007112375533428165,
+      "grad_norm": 0.12396597862243652,
+      "learning_rate": 1.8957345971563984e-07,
+      "loss": 1.4227272987365722,
+      "step": 5
+    },
+    {
+      "epoch": 0.01422475106685633,
+      "grad_norm": 0.1262262761592865,
+      "learning_rate": 4.265402843601896e-07,
+      "loss": 1.4979448318481445,
+      "step": 10
+    },
+    {
+      "epoch": 0.021337126600284494,
+      "grad_norm": 0.10962335765361786,
+      "learning_rate": 6.635071090047394e-07,
+      "loss": 1.398064422607422,
+      "step": 15
+    },
+    {
+      "epoch": 0.02844950213371266,
+      "grad_norm": 0.12247616797685623,
+      "learning_rate": 9.004739336492892e-07,
+      "loss": 1.4452707290649414,
+      "step": 20
+    },
+    {
+      "epoch": 0.03556187766714083,
+      "grad_norm": 0.11095397174358368,
+      "learning_rate": 1.1374407582938388e-06,
+      "loss": 1.4563634872436524,
+      "step": 25
+    },
+    {
+      "epoch": 0.04267425320056899,
+      "grad_norm": 0.11946389079093933,
+      "learning_rate": 1.3744075829383887e-06,
+      "loss": 1.442008113861084,
+      "step": 30
+    },
+    {
+      "epoch": 0.049786628733997154,
+      "grad_norm": 0.09363763779401779,
+      "learning_rate": 1.6113744075829384e-06,
+      "loss": 1.3265527725219726,
+      "step": 35
+    },
+    {
+      "epoch": 0.05689900426742532,
+      "grad_norm": 0.1277642399072647,
+      "learning_rate": 1.8483412322274883e-06,
+      "loss": 1.5192468643188477,
+      "step": 40
+    },
+    {
+      "epoch": 0.06401137980085349,
+      "grad_norm": 0.07470542937517166,
+      "learning_rate": 2.085308056872038e-06,
+      "loss": 1.215554141998291,
+      "step": 45
+    },
+    {
+      "epoch": 0.07112375533428165,
+      "grad_norm": 0.1051228865981102,
+      "learning_rate": 2.322274881516588e-06,
+      "loss": 1.4449579238891601,
+      "step": 50
+    },
+    {
+      "epoch": 0.07823613086770982,
+      "grad_norm": 0.11589594185352325,
+      "learning_rate": 2.5592417061611373e-06,
+      "loss": 1.3515880584716797,
+      "step": 55
+    },
+    {
+      "epoch": 0.08534850640113797,
+      "grad_norm": 0.1121063381433487,
+      "learning_rate": 2.7962085308056874e-06,
+      "loss": 1.4210457801818848,
+      "step": 60
+    },
+    {
+      "epoch": 0.09246088193456614,
+      "grad_norm": 0.11301090568304062,
+      "learning_rate": 3.0331753554502375e-06,
+      "loss": 1.3430145263671875,
+      "step": 65
+    },
+    {
+      "epoch": 0.09957325746799431,
+      "grad_norm": 0.11729142814874649,
+      "learning_rate": 3.2701421800947867e-06,
+      "loss": 1.4662004470825196,
+      "step": 70
+    },
+    {
+      "epoch": 0.10668563300142248,
+      "grad_norm": 0.12315651029348373,
+      "learning_rate": 3.507109004739337e-06,
+      "loss": 1.4467350959777832,
+      "step": 75
+    },
+    {
+      "epoch": 0.11379800853485064,
+      "grad_norm": 0.10574598610401154,
+      "learning_rate": 3.7440758293838865e-06,
+      "loss": 1.3443514823913574,
+      "step": 80
+    },
+    {
+      "epoch": 0.12091038406827881,
+      "grad_norm": 0.10200333595275879,
+      "learning_rate": 3.981042654028436e-06,
+      "loss": 1.3781295776367188,
+      "step": 85
+    },
+    {
+      "epoch": 0.12802275960170698,
+      "grad_norm": 0.11026877164840698,
+      "learning_rate": 4.218009478672986e-06,
+      "loss": 1.2920406341552735,
+      "step": 90
+    },
+    {
+      "epoch": 0.13513513513513514,
+      "grad_norm": 0.09731078147888184,
+      "learning_rate": 4.4549763033175355e-06,
+      "loss": 1.3067164421081543,
+      "step": 95
+    },
+    {
+      "epoch": 0.1422475106685633,
+      "grad_norm": 0.10353145748376846,
+      "learning_rate": 4.691943127962086e-06,
+      "loss": 1.2854823112487792,
+      "step": 100
+    },
+    {
+      "epoch": 0.14935988620199148,
+      "grad_norm": 0.11844628304243088,
+      "learning_rate": 4.928909952606635e-06,
+      "loss": 1.426025104522705,
+      "step": 105
+    },
+    {
+      "epoch": 0.15647226173541964,
+      "grad_norm": 0.11913719028234482,
+      "learning_rate": 5.165876777251185e-06,
+      "loss": 1.2822218894958497,
+      "step": 110
+    },
+    {
+      "epoch": 0.16358463726884778,
+      "grad_norm": 0.078098826110363,
+      "learning_rate": 5.402843601895735e-06,
+      "loss": 1.2596662521362305,
+      "step": 115
+    },
+    {
+      "epoch": 0.17069701280227595,
+      "grad_norm": 0.11063536256551743,
+      "learning_rate": 5.639810426540285e-06,
+      "loss": 1.3071359634399413,
+      "step": 120
+    },
+    {
+      "epoch": 0.17780938833570412,
+      "grad_norm": 0.10192953050136566,
+      "learning_rate": 5.876777251184834e-06,
+      "loss": 1.1887753486633301,
+      "step": 125
+    },
+    {
+      "epoch": 0.18492176386913228,
+      "grad_norm": 0.08962368220090866,
+      "learning_rate": 6.1137440758293845e-06,
+      "loss": 1.1969791412353517,
+      "step": 130
+    },
+    {
+      "epoch": 0.19203413940256045,
+      "grad_norm": 0.08570072054862976,
+      "learning_rate": 6.350710900473935e-06,
+      "loss": 1.1636576652526855,
+      "step": 135
+    },
+    {
+      "epoch": 0.19914651493598862,
+      "grad_norm": 0.0954199954867363,
+      "learning_rate": 6.587677725118484e-06,
+      "loss": 1.2025936126708985,
+      "step": 140
+    },
+    {
+      "epoch": 0.20625889046941678,
+      "grad_norm": 0.09052606672048569,
+      "learning_rate": 6.824644549763034e-06,
+      "loss": 1.0443121910095214,
+      "step": 145
+    },
+    {
+      "epoch": 0.21337126600284495,
+      "grad_norm": 0.07353335618972778,
+      "learning_rate": 7.061611374407583e-06,
+      "loss": 1.157231903076172,
+      "step": 150
+    },
+    {
+      "epoch": 0.22048364153627312,
+      "grad_norm": 0.06493294984102249,
+      "learning_rate": 7.298578199052133e-06,
+      "loss": 1.1911725044250487,
+      "step": 155
+    },
+    {
+      "epoch": 0.22759601706970128,
+      "grad_norm": 0.056515395641326904,
+      "learning_rate": 7.535545023696683e-06,
+      "loss": 1.0279447555541992,
+      "step": 160
+    },
+    {
+      "epoch": 0.23470839260312945,
+      "grad_norm": 0.057359982281923294,
+      "learning_rate": 7.772511848341233e-06,
+      "loss": 1.076847743988037,
+      "step": 165
+    },
+    {
+      "epoch": 0.24182076813655762,
+      "grad_norm": 0.058239951729774475,
+      "learning_rate": 8.009478672985783e-06,
+      "loss": 0.946469497680664,
+      "step": 170
+    },
+    {
+      "epoch": 0.24893314366998578,
+      "grad_norm": 0.05514655262231827,
+      "learning_rate": 8.246445497630333e-06,
+      "loss": 1.063446617126465,
+      "step": 175
+    },
+    {
+      "epoch": 0.25604551920341395,
+      "grad_norm": 0.04826820269227028,
+      "learning_rate": 8.483412322274883e-06,
+      "loss": 1.0174281120300293,
+      "step": 180
+    },
+    {
+      "epoch": 0.2631578947368421,
+      "grad_norm": 0.041520342230796814,
+      "learning_rate": 8.720379146919431e-06,
+      "loss": 0.9851118087768554,
+      "step": 185
+    },
+    {
+      "epoch": 0.2702702702702703,
+      "grad_norm": 0.03696112334728241,
+      "learning_rate": 8.957345971563981e-06,
+      "loss": 0.892978572845459,
+      "step": 190
+    },
+    {
+      "epoch": 0.2773826458036984,
+      "grad_norm": 0.04463537037372589,
+      "learning_rate": 9.194312796208532e-06,
+      "loss": 0.9067799568176269,
+      "step": 195
+    },
+    {
+      "epoch": 0.2844950213371266,
+      "grad_norm": 0.03216946870088577,
+      "learning_rate": 9.431279620853082e-06,
+      "loss": 0.8715072631835937,
+      "step": 200
+    },
+    {
+      "epoch": 0.29160739687055476,
+      "grad_norm": 0.031706444919109344,
+      "learning_rate": 9.668246445497632e-06,
+      "loss": 0.9280688285827636,
+      "step": 205
+    },
+    {
+      "epoch": 0.29871977240398295,
+      "grad_norm": 0.029998933896422386,
+      "learning_rate": 9.905213270142182e-06,
+      "loss": 0.8608943939208984,
+      "step": 210
+    },
+    {
+      "epoch": 0.3058321479374111,
+      "grad_norm": 0.04544912651181221,
+      "learning_rate": 9.999938356263561e-06,
+      "loss": 0.903835391998291,
+      "step": 215
+    },
+    {
+      "epoch": 0.3129445234708393,
+      "grad_norm": 0.024148551747202873,
+      "learning_rate": 9.999561650045317e-06,
+      "loss": 0.8631033897399902,
+      "step": 220
+    },
+    {
+      "epoch": 0.3200568990042674,
+      "grad_norm": 0.024549957364797592,
+      "learning_rate": 9.998842509899456e-06,
+      "loss": 0.8868202209472656,
+      "step": 225
+    },
+    {
+      "epoch": 0.32716927453769556,
+      "grad_norm": 0.020235152915120125,
+      "learning_rate": 9.997780985081892e-06,
+      "loss": 0.8703635215759278,
+      "step": 230
+    },
+    {
+      "epoch": 0.33428165007112376,
+      "grad_norm": 0.041720639914274216,
+      "learning_rate": 9.996377148299425e-06,
+      "loss": 0.7600418090820312,
+      "step": 235
+    },
+    {
+      "epoch": 0.3413940256045519,
+      "grad_norm": 0.02275031991302967,
+      "learning_rate": 9.994631095704752e-06,
+      "loss": 0.7633596420288086,
+      "step": 240
+    },
+    {
+      "epoch": 0.3485064011379801,
+      "grad_norm": 0.018682237714529037,
+      "learning_rate": 9.992542946889888e-06,
+      "loss": 0.8040481567382812,
+      "step": 245
+    },
+    {
+      "epoch": 0.35561877667140823,
+      "grad_norm": 0.024369360879063606,
+      "learning_rate": 9.99011284487797e-06,
+      "loss": 0.7869772434234619,
+      "step": 250
+    },
+    {
+      "epoch": 0.3627311522048364,
+      "grad_norm": 0.021545717492699623,
+      "learning_rate": 9.987340956113467e-06,
+      "loss": 0.8517203330993652,
+      "step": 255
+    },
+    {
+      "epoch": 0.36984352773826457,
+      "grad_norm": 0.01612464152276516,
+      "learning_rate": 9.984227470450775e-06,
+      "loss": 0.8197982788085938,
+      "step": 260
+    },
+    {
+      "epoch": 0.37695590327169276,
+      "grad_norm": 0.015140607953071594,
+      "learning_rate": 9.980772601141213e-06,
+      "loss": 0.7932530879974365,
+      "step": 265
+    },
+    {
+      "epoch": 0.3840682788051209,
+      "grad_norm": 0.015770290046930313,
+      "learning_rate": 9.97697658481842e-06,
+      "loss": 0.7979182720184326,
+      "step": 270
+    },
+    {
+      "epoch": 0.3911806543385491,
+      "grad_norm": 0.01681072637438774,
+      "learning_rate": 9.972839681482149e-06,
+      "loss": 0.8038228034973145,
+      "step": 275
+    },
+    {
+      "epoch": 0.39829302987197723,
+      "grad_norm": 0.017351120710372925,
+      "learning_rate": 9.968362174480451e-06,
+      "loss": 0.8209856033325196,
+      "step": 280
+    },
+    {
+      "epoch": 0.40540540540540543,
+      "grad_norm": 0.014682579785585403,
+      "learning_rate": 9.96354437049027e-06,
+      "loss": 0.8208961486816406,
+      "step": 285
+    },
+    {
+      "epoch": 0.41251778093883357,
+      "grad_norm": 0.015515010803937912,
+      "learning_rate": 9.95838659949645e-06,
+      "loss": 0.7764195442199707,
+      "step": 290
+    },
+    {
+      "epoch": 0.41963015647226176,
+      "grad_norm": 0.01328542921692133,
+      "learning_rate": 9.952889214769116e-06,
+      "loss": 0.7373966693878173,
+      "step": 295
+    },
+    {
+      "epoch": 0.4267425320056899,
+      "grad_norm": 0.013769397512078285,
+      "learning_rate": 9.947052592839488e-06,
+      "loss": 0.7790839195251464,
+      "step": 300
+    },
+    {
+      "epoch": 0.43385490753911804,
+      "grad_norm": 0.013357909396290779,
+      "learning_rate": 9.940877133474087e-06,
+      "loss": 0.7955220222473145,
+      "step": 305
+    },
+    {
+      "epoch": 0.44096728307254623,
+      "grad_norm": 0.01533876545727253,
+      "learning_rate": 9.934363259647355e-06,
+      "loss": 0.8395823478698731,
+      "step": 310
+    },
+    {
+      "epoch": 0.4480796586059744,
+      "grad_norm": 0.013267037458717823,
+      "learning_rate": 9.927511417512687e-06,
+      "loss": 0.7947360038757324,
+      "step": 315
+    },
+    {
+      "epoch": 0.45519203413940257,
+      "grad_norm": 0.014744734391570091,
+      "learning_rate": 9.920322076371871e-06,
+      "loss": 0.7898136138916015,
+      "step": 320
+    },
+    {
+      "epoch": 0.4623044096728307,
+      "grad_norm": 0.015842357650399208,
+      "learning_rate": 9.91279572864294e-06,
+      "loss": 0.7578622341156006,
+      "step": 325
+    },
+    {
+      "epoch": 0.4694167852062589,
+      "grad_norm": 0.015208872966468334,
+      "learning_rate": 9.904932889826451e-06,
+      "loss": 0.7646086692810059,
+      "step": 330
+    },
+    {
+      "epoch": 0.47652916073968704,
+      "grad_norm": 0.012448601424694061,
+      "learning_rate": 9.896734098470175e-06,
+      "loss": 0.804629898071289,
+      "step": 335
+    },
+    {
+      "epoch": 0.48364153627311524,
+      "grad_norm": 0.016085481271147728,
+      "learning_rate": 9.888199916132208e-06,
+      "loss": 0.7498270034790039,
+      "step": 340
+    },
+    {
+      "epoch": 0.4907539118065434,
+      "grad_norm": 0.025318488478660583,
+      "learning_rate": 9.87933092734251e-06,
+      "loss": 0.7498879909515381,
+      "step": 345
+    },
+    {
+      "epoch": 0.49786628733997157,
+      "grad_norm": 0.013470480218529701,
+      "learning_rate": 9.870127739562873e-06,
+      "loss": 0.8381074905395508,
+      "step": 350
+    },
+    {
+      "epoch": 0.5049786628733998,
+      "grad_norm": 0.012390932068228722,
+      "learning_rate": 9.860590983145307e-06,
+      "loss": 0.7959535121917725,
+      "step": 355
+    },
+    {
+      "epoch": 0.5120910384068279,
+      "grad_norm": 0.03908325359225273,
+      "learning_rate": 9.850721311288868e-06,
+      "loss": 0.77716064453125,
+      "step": 360
+    },
+    {
+      "epoch": 0.519203413940256,
+      "grad_norm": 0.01935300976037979,
+      "learning_rate": 9.840519399994921e-06,
+      "loss": 0.810551643371582,
+      "step": 365
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.011727036908268929,
+      "learning_rate": 9.829985948020836e-06,
+      "loss": 0.783443021774292,
+      "step": 370
+    },
+    {
+      "epoch": 0.5334281650071123,
+      "grad_norm": 0.01185957808047533,
+      "learning_rate": 9.819121676832134e-06,
+      "loss": 0.7494336128234863,
+      "step": 375
+    },
+    {
+      "epoch": 0.5405405405405406,
+      "grad_norm": 0.012798828072845936,
+      "learning_rate": 9.807927330553058e-06,
+      "loss": 0.8026717185974122,
+      "step": 380
+    },
+    {
+      "epoch": 0.5476529160739687,
+      "grad_norm": 0.019524866715073586,
+      "learning_rate": 9.796403675915622e-06,
+      "loss": 0.7634530544281006,
+      "step": 385
+    },
+    {
+      "epoch": 0.5547652916073968,
+      "grad_norm": 0.013788755051791668,
+      "learning_rate": 9.784551502207087e-06,
+      "loss": 0.7632253646850586,
+      "step": 390
+    },
+    {
+      "epoch": 0.561877667140825,
+      "grad_norm": 0.01305212453007698,
+      "learning_rate": 9.772371621215902e-06,
+      "loss": 0.7682255268096924,
+      "step": 395
+    },
+    {
+      "epoch": 0.5689900426742532,
+      "grad_norm": 0.012975879944860935,
+      "learning_rate": 9.759864867176098e-06,
+      "loss": 0.7581171035766602,
+      "step": 400
+    },
+    {
+      "epoch": 0.5761024182076814,
+      "grad_norm": 0.011801790446043015,
+      "learning_rate": 9.74703209671016e-06,
+      "loss": 0.7882646560668946,
+      "step": 405
+    },
+    {
+      "epoch": 0.5832147937411095,
+      "grad_norm": 0.01298159547150135,
+      "learning_rate": 9.733874188770344e-06,
+      "loss": 0.7816955089569092,
+      "step": 410
+    },
+    {
+      "epoch": 0.5903271692745377,
+      "grad_norm": 0.027532342821359634,
+      "learning_rate": 9.720392044578477e-06,
+      "loss": 0.6961409091949463,
+      "step": 415
+    },
+    {
+      "epoch": 0.5974395448079659,
+      "grad_norm": 0.01297469437122345,
+      "learning_rate": 9.706586587564236e-06,
+      "loss": 0.7911362648010254,
+      "step": 420
+    },
+    {
+      "epoch": 0.604551920341394,
+      "grad_norm": 0.015234866179525852,
+      "learning_rate": 9.692458763301891e-06,
+      "loss": 0.7972568511962891,
+      "step": 425
+    },
+    {
+      "epoch": 0.6116642958748222,
+      "grad_norm": 0.016101600602269173,
+      "learning_rate": 9.678009539445549e-06,
+      "loss": 0.7825101852416992,
+      "step": 430
+    },
+    {
+      "epoch": 0.6187766714082503,
+      "grad_norm": 0.012733902782201767,
+      "learning_rate": 9.663239905662868e-06,
+      "loss": 0.7665041446685791,
+      "step": 435
+    },
+    {
+      "epoch": 0.6258890469416786,
+      "grad_norm": 0.012959662824869156,
+      "learning_rate": 9.648150873567278e-06,
+      "loss": 0.7273931503295898,
+      "step": 440
+    },
+    {
+      "epoch": 0.6330014224751067,
+      "grad_norm": 0.011889465153217316,
+      "learning_rate": 9.632743476648686e-06,
+      "loss": 0.7907261848449707,
+      "step": 445
+    },
+    {
+      "epoch": 0.6401137980085349,
+      "grad_norm": 0.011718220077455044,
+      "learning_rate": 9.617018770202702e-06,
+      "loss": 0.8006930351257324,
+      "step": 450
+    },
+    {
+      "epoch": 0.647226173541963,
+      "grad_norm": 0.013619167730212212,
+      "learning_rate": 9.600977831258347e-06,
+      "loss": 0.7727859497070313,
+      "step": 455
+    },
+    {
+      "epoch": 0.6543385490753911,
+      "grad_norm": 0.015222000889480114,
+      "learning_rate": 9.584621758504286e-06,
+      "loss": 0.770260238647461,
+      "step": 460
+    },
+    {
+      "epoch": 0.6614509246088194,
+      "grad_norm": 0.014281806536018848,
+      "learning_rate": 9.567951672213582e-06,
+      "loss": 0.7328165531158447,
+      "step": 465
+    },
+    {
+      "epoch": 0.6685633001422475,
+      "grad_norm": 0.013101202435791492,
+      "learning_rate": 9.550968714166959e-06,
+      "loss": 0.792152214050293,
+      "step": 470
+    },
+    {
+      "epoch": 0.6756756756756757,
+      "grad_norm": 0.01915375515818596,
+      "learning_rate": 9.5336740475746e-06,
+      "loss": 0.7413363933563233,
+      "step": 475
+    },
+    {
+      "epoch": 0.6827880512091038,
+      "grad_norm": 0.012954477220773697,
+      "learning_rate": 9.516068856996478e-06,
+      "loss": 0.7463040828704834,
+      "step": 480
+    },
+    {
+      "epoch": 0.689900426742532,
+      "grad_norm": 0.015190026722848415,
+      "learning_rate": 9.498154348261217e-06,
+      "loss": 0.7213023185729981,
+      "step": 485
+    },
+    {
+      "epoch": 0.6970128022759602,
+      "grad_norm": 0.015451316721737385,
+      "learning_rate": 9.479931748383511e-06,
+      "loss": 0.7095402717590332,
+      "step": 490
+    },
+    {
+      "epoch": 0.7041251778093883,
+      "grad_norm": 0.01419431809335947,
+      "learning_rate": 9.461402305480067e-06,
+      "loss": 0.7601386547088623,
+      "step": 495
+    },
+    {
+      "epoch": 0.7112375533428165,
+      "grad_norm": 0.012903365306556225,
+      "learning_rate": 9.442567288684134e-06,
+      "loss": 0.7972976207733155,
+      "step": 500
+    },
+    {
+      "epoch": 0.7183499288762447,
+      "grad_norm": 0.014118182472884655,
+      "learning_rate": 9.423427988058569e-06,
+      "loss": 0.7362984657287598,
+      "step": 505
+    },
+    {
+      "epoch": 0.7254623044096729,
+      "grad_norm": 0.01312790997326374,
+      "learning_rate": 9.403985714507476e-06,
+      "loss": 0.7164534091949463,
+      "step": 510
+    },
+    {
+      "epoch": 0.732574679943101,
+      "grad_norm": 0.013149509206414223,
+      "learning_rate": 9.384241799686416e-06,
+      "loss": 0.7581445693969726,
+      "step": 515
+    },
+    {
+      "epoch": 0.7396870554765291,
+      "grad_norm": 0.014509950764477253,
+      "learning_rate": 9.36419759591121e-06,
+      "loss": 0.7607109069824218,
+      "step": 520
+    },
+    {
+      "epoch": 0.7467994310099573,
+      "grad_norm": 0.015734901651740074,
+      "learning_rate": 9.343854476065301e-06,
+      "loss": 0.7364118099212646,
+      "step": 525
+    },
+    {
+      "epoch": 0.7539118065433855,
+      "grad_norm": 0.015109636820852757,
+      "learning_rate": 9.323213833505733e-06,
+      "loss": 0.7244921207427979,
+      "step": 530
+    },
+    {
+      "epoch": 0.7610241820768137,
+      "grad_norm": 0.015012472867965698,
+      "learning_rate": 9.302277081967708e-06,
+      "loss": 0.7567250251770019,
+      "step": 535
+    },
+    {
+      "epoch": 0.7681365576102418,
+      "grad_norm": 0.013028338551521301,
+      "learning_rate": 9.281045655467757e-06,
+      "loss": 0.7913572311401367,
+      "step": 540
+    },
+    {
+      "epoch": 0.7752489331436699,
+      "grad_norm": 0.014547139406204224,
+      "learning_rate": 9.259521008205522e-06,
+      "loss": 0.7506765842437744,
+      "step": 545
+    },
+    {
+      "epoch": 0.7823613086770982,
+      "grad_norm": 0.014500031247735023,
+      "learning_rate": 9.237704614464157e-06,
+      "loss": 0.7631255149841308,
+      "step": 550
+    },
+    {
+      "epoch": 0.7894736842105263,
+      "grad_norm": 0.024208789691329002,
+      "learning_rate": 9.21559796850934e-06,
+      "loss": 0.7228170871734619,
+      "step": 555
+    },
+    {
+      "epoch": 0.7965860597439545,
+      "grad_norm": 0.01767735742032528,
+      "learning_rate": 9.193202584486938e-06,
+      "loss": 0.7594891548156738,
+      "step": 560
+    },
+    {
+      "epoch": 0.8036984352773826,
+      "grad_norm": 0.027131540700793266,
+      "learning_rate": 9.170519996319292e-06,
+      "loss": 0.7311542987823486,
+      "step": 565
+    },
+    {
+      "epoch": 0.8108108108108109,
+      "grad_norm": 0.014019402675330639,
+      "learning_rate": 9.147551757600156e-06,
+      "loss": 0.7342860698699951,
+      "step": 570
+    },
+    {
+      "epoch": 0.817923186344239,
+      "grad_norm": 0.015196071937680244,
+      "learning_rate": 9.124299441488287e-06,
+      "loss": 0.7782781600952149,
+      "step": 575
+    },
+    {
+      "epoch": 0.8250355618776671,
+      "grad_norm": 0.013155009597539902,
+      "learning_rate": 9.100764640599699e-06,
+      "loss": 0.7691669464111328,
+      "step": 580
+    },
+    {
+      "epoch": 0.8321479374110953,
+      "grad_norm": 0.02131805010139942,
+      "learning_rate": 9.076948966898573e-06,
+      "loss": 0.6857946395874024,
+      "step": 585
+    },
+    {
+      "epoch": 0.8392603129445235,
+      "grad_norm": 0.021150261163711548,
+      "learning_rate": 9.05285405158685e-06,
+      "loss": 0.6824939250946045,
+      "step": 590
+    },
+    {
+      "epoch": 0.8463726884779517,
+      "grad_norm": 0.014878728426992893,
+      "learning_rate": 9.028481544992514e-06,
+      "loss": 0.7442028522491455,
+      "step": 595
+    },
+    {
+      "epoch": 0.8534850640113798,
+      "grad_norm": 0.014299673028290272,
+      "learning_rate": 9.003833116456548e-06,
+      "loss": 0.7425227642059327,
+      "step": 600
+    },
+    {
+      "epoch": 0.8605974395448079,
+      "grad_norm": 0.020050186663866043,
+      "learning_rate": 8.9789104542186e-06,
+      "loss": 0.6471955299377441,
+      "step": 605
+    },
+    {
+      "epoch": 0.8677098150782361,
+      "grad_norm": 0.014727029018104076,
+      "learning_rate": 8.953715265301344e-06,
+      "loss": 0.6761772632598877,
+      "step": 610
+    },
+    {
+      "epoch": 0.8748221906116643,
+      "grad_norm": 0.0251702219247818,
+      "learning_rate": 8.928249275393572e-06,
+      "loss": 0.7484918117523194,
+      "step": 615
+    },
+    {
+      "epoch": 0.8819345661450925,
+      "grad_norm": 0.013131954707205296,
+      "learning_rate": 8.902514228731993e-06,
+      "loss": 0.7525879859924316,
+      "step": 620
+    },
+    {
+      "epoch": 0.8890469416785206,
+      "grad_norm": 0.014284606091678143,
+      "learning_rate": 8.876511887981758e-06,
+      "loss": 0.7031543254852295,
+      "step": 625
+    },
+    {
+      "epoch": 0.8961593172119487,
+      "grad_norm": 0.01469456311315298,
+      "learning_rate": 8.85024403411574e-06,
+      "loss": 0.7517221450805665,
+      "step": 630
+    },
+    {
+      "epoch": 0.903271692745377,
+      "grad_norm": 0.014566020108759403,
+      "learning_rate": 8.823712466292547e-06,
+      "loss": 0.7733576774597168,
+      "step": 635
+    },
+    {
+      "epoch": 0.9103840682788051,
+      "grad_norm": 0.01564401015639305,
+      "learning_rate": 8.796919001733286e-06,
+      "loss": 0.7582737445831299,
+      "step": 640
+    },
+    {
+      "epoch": 0.9174964438122333,
+      "grad_norm": 0.014589518308639526,
+      "learning_rate": 8.769865475597107e-06,
+      "loss": 0.7202891826629638,
+      "step": 645
+    },
+    {
+      "epoch": 0.9246088193456614,
+      "grad_norm": 0.014613118954002857,
+      "learning_rate": 8.742553740855507e-06,
+      "loss": 0.7529885292053222,
+      "step": 650
+    },
+    {
+      "epoch": 0.9317211948790897,
+      "grad_norm": 0.017528263852000237,
+      "learning_rate": 8.714985668165399e-06,
+      "loss": 0.7535917282104492,
+      "step": 655
+    },
+    {
+      "epoch": 0.9388335704125178,
+      "grad_norm": 0.01572534441947937,
+      "learning_rate": 8.687163145741008e-06,
+      "loss": 0.6831246852874756,
+      "step": 660
+    },
+    {
+      "epoch": 0.9459459459459459,
+      "grad_norm": 0.01505051925778389,
+      "learning_rate": 8.659088079224528e-06,
+      "loss": 0.7192672252655029,
+      "step": 665
+    },
+    {
+      "epoch": 0.9530583214793741,
+      "grad_norm": 0.014804129488766193,
+      "learning_rate": 8.630762391555601e-06,
+      "loss": 0.7272192955017089,
+      "step": 670
+    },
+    {
+      "epoch": 0.9601706970128022,
+      "grad_norm": 0.014921215362846851,
+      "learning_rate": 8.602188022839612e-06,
+      "loss": 0.7498035430908203,
+      "step": 675
+    },
+    {
+      "epoch": 0.9672830725462305,
+      "grad_norm": 0.01385109405964613,
+      "learning_rate": 8.573366930214807e-06,
+      "loss": 0.7332922935485839,
+      "step": 680
+    },
+    {
+      "epoch": 0.9743954480796586,
+      "grad_norm": 0.01615496724843979,
+      "learning_rate": 8.544301087718234e-06,
+      "loss": 0.7189756393432617,
+      "step": 685
+    },
+    {
+      "epoch": 0.9815078236130867,
+      "grad_norm": 0.014931720681488514,
+      "learning_rate": 8.514992486150554e-06,
+      "loss": 0.7482341766357422,
+      "step": 690
+    },
+    {
+      "epoch": 0.9886201991465149,
+      "grad_norm": 0.016770832240581512,
+      "learning_rate": 8.485443132939664e-06,
+      "loss": 0.7097194194793701,
+      "step": 695
+    },
+    {
+      "epoch": 0.9957325746799431,
+      "grad_norm": 0.014345219358801842,
+      "learning_rate": 8.455655052003216e-06,
+      "loss": 0.6710967540740966,
+      "step": 700
+    },
+    {
+      "epoch": 1.0028449502133712,
+      "grad_norm": 0.014812275767326355,
+      "learning_rate": 8.425630283609995e-06,
+      "loss": 0.7616248607635498,
+      "step": 705
+    },
+    {
+      "epoch": 1.0099573257467995,
+      "grad_norm": 0.022520147264003754,
+      "learning_rate": 8.395370884240161e-06,
+      "loss": 0.6915517807006836,
+      "step": 710
+    },
+    {
+      "epoch": 1.0170697012802277,
+      "grad_norm": 0.014687804505228996,
+      "learning_rate": 8.36487892644441e-06,
+      "loss": 0.7760564804077148,
+      "step": 715
+    },
+    {
+      "epoch": 1.0241820768136558,
+      "grad_norm": 0.015282604843378067,
+      "learning_rate": 8.334156498702015e-06,
+      "loss": 0.7448132514953614,
+      "step": 720
+    },
+    {
+      "epoch": 1.031294452347084,
+      "grad_norm": 0.016149410977959633,
+      "learning_rate": 8.303205705277776e-06,
+      "loss": 0.7295210838317872,
+      "step": 725
+    },
+    {
+      "epoch": 1.038406827880512,
+      "grad_norm": 0.0175002608448267,
+      "learning_rate": 8.272028666077893e-06,
+      "loss": 0.715207576751709,
+      "step": 730
+    },
+    {
+      "epoch": 1.0455192034139402,
+      "grad_norm": 0.015501333400607109,
+      "learning_rate": 8.240627516504778e-06,
+      "loss": 0.7610238552093506,
+      "step": 735
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 0.014466507360339165,
+      "learning_rate": 8.209004407310782e-06,
+      "loss": 0.682843017578125,
+      "step": 740
+    },
+    {
+      "epoch": 1.0597439544807965,
+      "grad_norm": 0.01729828491806984,
+      "learning_rate": 8.177161504450887e-06,
+      "loss": 0.7697264671325683,
+      "step": 745
+    },
+    {
+      "epoch": 1.0668563300142249,
+      "grad_norm": 0.01606452651321888,
+      "learning_rate": 8.145100988934369e-06,
+      "loss": 0.7051825046539306,
+      "step": 750
+    },
+    {
+      "epoch": 1.073968705547653,
+      "grad_norm": 0.017853980883955956,
+      "learning_rate": 8.112825056675386e-06,
+      "loss": 0.7393856525421143,
+      "step": 755
+    },
+    {
+      "epoch": 1.0810810810810811,
+      "grad_norm": 0.01651955395936966,
+      "learning_rate": 8.0803359183426e-06,
+      "loss": 0.740062665939331,
+      "step": 760
+    },
+    {
+      "epoch": 1.0881934566145093,
+      "grad_norm": 0.01589570939540863,
+      "learning_rate": 8.04763579920775e-06,
+      "loss": 0.7486938953399658,
+      "step": 765
+    },
+    {
+      "epoch": 1.0953058321479374,
+      "grad_norm": 0.01882278174161911,
+      "learning_rate": 8.01472693899324e-06,
+      "loss": 0.7593507766723633,
+      "step": 770
+    },
+    {
+      "epoch": 1.1024182076813656,
+      "grad_norm": 0.017779262736439705,
+      "learning_rate": 7.98161159171873e-06,
+      "loss": 0.7369762897491455,
+      "step": 775
+    },
+    {
+      "epoch": 1.1095305832147937,
+      "grad_norm": 0.01958276890218258,
+      "learning_rate": 7.948292025546754e-06,
+      "loss": 0.7430673599243164,
+      "step": 780
+    },
+    {
+      "epoch": 1.1166429587482218,
+      "grad_norm": 0.01635376177728176,
+      "learning_rate": 7.91477052262737e-06,
+      "loss": 0.749770212173462,
+      "step": 785
+    },
+    {
+      "epoch": 1.12375533428165,
+      "grad_norm": 0.019017737358808517,
+      "learning_rate": 7.881049378941851e-06,
+      "loss": 0.6917729854583741,
+      "step": 790
+    },
+    {
+      "epoch": 1.1308677098150781,
+      "grad_norm": 0.017745498567819595,
+      "learning_rate": 7.847130904145418e-06,
+      "loss": 0.7209823131561279,
+      "step": 795
+    },
+    {
+      "epoch": 1.1379800853485065,
+      "grad_norm": 0.022607974708080292,
+      "learning_rate": 7.81301742140905e-06,
+      "loss": 0.7285879135131836,
+      "step": 800
+    },
+    {
+      "epoch": 1.1450924608819346,
+      "grad_norm": 0.01610717363655567,
+      "learning_rate": 7.778711267260371e-06,
+      "loss": 0.7201016426086426,
+      "step": 805
+    },
+    {
+      "epoch": 1.1522048364153628,
+      "grad_norm": 0.016487758606672287,
+      "learning_rate": 7.744214791423597e-06,
+      "loss": 0.7271471977233886,
+      "step": 810
+    },
+    {
+      "epoch": 1.159317211948791,
+      "grad_norm": 0.01821993477642536,
+      "learning_rate": 7.709530356658616e-06,
+      "loss": 0.6985025882720948,
+      "step": 815
+    },
+    {
+      "epoch": 1.166429587482219,
+      "grad_norm": 0.01631130650639534,
+      "learning_rate": 7.674660338599144e-06,
+      "loss": 0.760840368270874,
+      "step": 820
+    },
+    {
+      "epoch": 1.1735419630156472,
+      "grad_norm": 0.017514122650027275,
+      "learning_rate": 7.639607125590017e-06,
+      "loss": 0.6543985366821289,
+      "step": 825
+    },
+    {
+      "epoch": 1.1806543385490753,
+      "grad_norm": 0.014640039764344692,
+      "learning_rate": 7.604373118523598e-06,
+      "loss": 0.7778742790222168,
+      "step": 830
+    },
+    {
+      "epoch": 1.1877667140825037,
+      "grad_norm": 0.03316516801714897,
+      "learning_rate": 7.5689607306753465e-06,
+      "loss": 0.7553888320922851,
+      "step": 835
+    },
+    {
+      "epoch": 1.1948790896159318,
+      "grad_norm": 0.016899485141038895,
+      "learning_rate": 7.533372387538518e-06,
+      "loss": 0.7549580097198486,
+      "step": 840
+    },
+    {
+      "epoch": 1.20199146514936,
+      "grad_norm": 0.017853831872344017,
+      "learning_rate": 7.497610526658035e-06,
+      "loss": 0.7460854530334473,
+      "step": 845
+    },
+    {
+      "epoch": 1.209103840682788,
+      "grad_norm": 0.016394775360822678,
+      "learning_rate": 7.4616775974635346e-06,
+      "loss": 0.7119558811187744,
+      "step": 850
+    },
+    {
+      "epoch": 1.2162162162162162,
+      "grad_norm": 0.018164537847042084,
+      "learning_rate": 7.425576061101599e-06,
+      "loss": 0.711454200744629,
+      "step": 855
+    },
+    {
+      "epoch": 1.2233285917496444,
+      "grad_norm": 0.025621753185987473,
+      "learning_rate": 7.389308390267191e-06,
+      "loss": 0.7418702125549317,
+      "step": 860
+    },
+    {
+      "epoch": 1.2304409672830725,
+      "grad_norm": 0.018322646617889404,
+      "learning_rate": 7.352877069034279e-06,
+      "loss": 0.7104067802429199,
+      "step": 865
+    },
+    {
+      "epoch": 1.2375533428165006,
+      "grad_norm": 0.01565595157444477,
+      "learning_rate": 7.316284592685712e-06,
+      "loss": 0.7560728073120118,
+      "step": 870
+    },
+    {
+      "epoch": 1.2446657183499288,
+      "grad_norm": 0.0181591659784317,
+      "learning_rate": 7.279533467542295e-06,
+      "loss": 0.6743175029754639,
+      "step": 875
+    },
+    {
+      "epoch": 1.251778093883357,
+      "grad_norm": 0.01698802225291729,
+      "learning_rate": 7.242626210791137e-06,
+      "loss": 0.7210459232330322,
+      "step": 880
+    },
+    {
+      "epoch": 1.2588904694167853,
+      "grad_norm": 0.015113065019249916,
+      "learning_rate": 7.205565350313234e-06,
+      "loss": 0.7054549217224121,
+      "step": 885
+    },
+    {
+      "epoch": 1.2660028449502134,
+      "grad_norm": 0.01659173145890236,
+      "learning_rate": 7.16835342451033e-06,
+      "loss": 0.7842894077301026,
+      "step": 890
+    },
+    {
+      "epoch": 1.2731152204836416,
+      "grad_norm": 0.016503192484378815,
+      "learning_rate": 7.130992982131059e-06,
+      "loss": 0.7237984657287597,
+      "step": 895
+    },
+    {
+      "epoch": 1.2802275960170697,
+      "grad_norm": 0.015096175484359264,
+      "learning_rate": 7.093486582096361e-06,
+      "loss": 0.7442319869995118,
+      "step": 900
+    },
+    {
+      "epoch": 1.2873399715504978,
+      "grad_norm": 0.01692996546626091,
+      "learning_rate": 7.05583679332423e-06,
+      "loss": 0.678685998916626,
+      "step": 905
+    },
+    {
+      "epoch": 1.294452347083926,
+      "grad_norm": 0.016276616603136063,
+      "learning_rate": 7.018046194553751e-06,
+      "loss": 0.6846030712127685,
+      "step": 910
+    },
+    {
+      "epoch": 1.3015647226173541,
+      "grad_norm": 0.01619255170226097,
+      "learning_rate": 6.980117374168485e-06,
+      "loss": 0.7147863864898681,
+      "step": 915
+    },
+    {
+      "epoch": 1.3086770981507825,
+      "grad_norm": 0.01654823124408722,
+      "learning_rate": 6.942052930019168e-06,
+      "loss": 0.7425489902496338,
+      "step": 920
+    },
+    {
+      "epoch": 1.3157894736842106,
+      "grad_norm": 0.015968745574355125,
+      "learning_rate": 6.9038554692457906e-06,
+      "loss": 0.706316614151001,
+      "step": 925
+    },
+    {
+      "epoch": 1.3229018492176388,
+      "grad_norm": 0.017116257920861244,
+      "learning_rate": 6.865527608099025e-06,
+      "loss": 0.7231118679046631,
+      "step": 930
+    },
+    {
+      "epoch": 1.330014224751067,
+      "grad_norm": 0.019141439348459244,
+      "learning_rate": 6.8270719717610255e-06,
+      "loss": 0.6829496383666992,
+      "step": 935
+    },
+    {
+      "epoch": 1.337126600284495,
+      "grad_norm": 0.017003817483782768,
+      "learning_rate": 6.788491194165629e-06,
+      "loss": 0.7045816421508789,
+      "step": 940
+    },
+    {
+      "epoch": 1.3442389758179232,
+      "grad_norm": 0.018398337066173553,
+      "learning_rate": 6.749787917817942e-06,
+      "loss": 0.7236195087432862,
+      "step": 945
+    },
+    {
+      "epoch": 1.3513513513513513,
+      "grad_norm": 0.01609586924314499,
+      "learning_rate": 6.710964793613355e-06,
+      "loss": 0.7134823799133301,
+      "step": 950
+    },
+    {
+      "epoch": 1.3584637268847795,
+      "grad_norm": 0.015588617883622646,
+      "learning_rate": 6.672024480655973e-06,
+      "loss": 0.7059481143951416,
+      "step": 955
+    },
+    {
+      "epoch": 1.3655761024182076,
+      "grad_norm": 0.01707872562110424,
+      "learning_rate": 6.6329696460764854e-06,
+      "loss": 0.7315536499023437,
+      "step": 960
+    },
+    {
+      "epoch": 1.3726884779516357,
+      "grad_norm": 0.015458762645721436,
+      "learning_rate": 6.593802964849487e-06,
+      "loss": 0.6769055843353271,
+      "step": 965
+    },
+    {
+      "epoch": 1.379800853485064,
+      "grad_norm": 0.01659971848130226,
+      "learning_rate": 6.55452711961026e-06,
+      "loss": 0.692983865737915,
+      "step": 970
+    },
+    {
+      "epoch": 1.3869132290184922,
+      "grad_norm": 0.020152278244495392,
+      "learning_rate": 6.515144800471037e-06,
+      "loss": 0.7136699199676514,
+      "step": 975
+    },
+    {
+      "epoch": 1.3940256045519204,
+      "grad_norm": 0.019839296117424965,
+      "learning_rate": 6.475658704836742e-06,
+      "loss": 0.7655652523040771,
+      "step": 980
+    },
+    {
+      "epoch": 1.4011379800853485,
+      "grad_norm": 0.016899431124329567,
+      "learning_rate": 6.436071537220245e-06,
+      "loss": 0.7531155109405517,
+      "step": 985
+    },
+    {
+      "epoch": 1.4082503556187767,
+      "grad_norm": 0.017267396673560143,
+      "learning_rate": 6.3963860090571136e-06,
+      "loss": 0.7064692497253418,
+      "step": 990
+    },
+    {
+      "epoch": 1.4153627311522048,
+      "grad_norm": 0.016033947467803955,
+      "learning_rate": 6.3566048385199065e-06,
+      "loss": 0.6782587051391602,
+      "step": 995
+    },
+    {
+      "epoch": 1.422475106685633,
+      "grad_norm": 0.016765275970101357,
+      "learning_rate": 6.3167307503319945e-06,
+      "loss": 0.7408823013305664,
+      "step": 1000
+    },
+    {
+      "epoch": 1.4295874822190613,
+      "grad_norm": 0.016634974628686905,
+      "learning_rate": 6.276766475580935e-06,
+      "loss": 0.6982696533203125,
+      "step": 1005
+    },
+    {
+      "epoch": 1.4366998577524894,
+      "grad_norm": 0.015438280068337917,
+      "learning_rate": 6.236714751531423e-06,
+      "loss": 0.7227981567382813,
+      "step": 1010
+    },
+    {
+      "epoch": 1.4438122332859176,
+      "grad_norm": 0.018462039530277252,
+      "learning_rate": 6.1965783214377895e-06,
+      "loss": 0.7196823596954346,
+      "step": 1015
+    },
+    {
+      "epoch": 1.4509246088193457,
+      "grad_norm": 0.015660835430026054,
+      "learning_rate": 6.1563599343561254e-06,
+      "loss": 0.7268499374389649,
+      "step": 1020
+    },
+    {
+      "epoch": 1.4580369843527738,
+      "grad_norm": 0.01876399666070938,
+      "learning_rate": 6.116062344955984e-06,
+      "loss": 0.6868331432342529,
+      "step": 1025
+    },
+    {
+      "epoch": 1.465149359886202,
+      "grad_norm": 0.01660033129155636,
+      "learning_rate": 6.075688313331704e-06,
+      "loss": 0.6909028053283691,
+      "step": 1030
+    },
+    {
+      "epoch": 1.4722617354196301,
+      "grad_norm": 0.01642961986362934,
+      "learning_rate": 6.035240604813366e-06,
+      "loss": 0.6916821479797364,
+      "step": 1035
+    },
+    {
+      "epoch": 1.4793741109530583,
+      "grad_norm": 0.01772296614944935,
+      "learning_rate": 5.994721989777387e-06,
+      "loss": 0.7245942115783691,
+      "step": 1040
+    },
+    {
+      "epoch": 1.4864864864864864,
+      "grad_norm": 0.01825345866382122,
+      "learning_rate": 5.954135243456769e-06,
+      "loss": 0.7016736030578613,
+      "step": 1045
+    },
+    {
+      "epoch": 1.4935988620199145,
+      "grad_norm": 0.01610652171075344,
+      "learning_rate": 5.913483145751018e-06,
+      "loss": 0.6654571533203125,
+      "step": 1050
+    },
+    {
+      "epoch": 1.5007112375533427,
+      "grad_norm": 0.017010604962706566,
+      "learning_rate": 5.872768481035736e-06,
+      "loss": 0.7061189651489258,
+      "step": 1055
+    },
+    {
+      "epoch": 1.5078236130867708,
+      "grad_norm": 0.017414411529898643,
+      "learning_rate": 5.831994037971914e-06,
+      "loss": 0.7226849555969238,
+      "step": 1060
+    },
+    {
+      "epoch": 1.5149359886201992,
+      "grad_norm": 0.01917360909283161,
+      "learning_rate": 5.79116260931493e-06,
+      "loss": 0.733070707321167,
+      "step": 1065
+    },
+    {
+      "epoch": 1.5220483641536273,
+      "grad_norm": 0.016919942572712898,
+      "learning_rate": 5.7502769917232635e-06,
+      "loss": 0.7204188823699951,
+      "step": 1070
+    },
+    {
+      "epoch": 1.5291607396870555,
+      "grad_norm": 0.018161717802286148,
+      "learning_rate": 5.70933998556695e-06,
+      "loss": 0.6771541118621827,
+      "step": 1075
+    },
+    {
+      "epoch": 1.5362731152204836,
+      "grad_norm": 0.018309131264686584,
+      "learning_rate": 5.668354394735761e-06,
+      "loss": 0.7210025787353516,
+      "step": 1080
+    },
+    {
+      "epoch": 1.543385490753912,
+      "grad_norm": 0.015957120805978775,
+      "learning_rate": 5.627323026447176e-06,
+      "loss": 0.7394068717956543,
+      "step": 1085
+    },
+    {
+      "epoch": 1.55049786628734,
+      "grad_norm": 0.01799791492521763,
+      "learning_rate": 5.586248691054101e-06,
+      "loss": 0.7240789413452149,
+      "step": 1090
+    },
+    {
+      "epoch": 1.5576102418207682,
+      "grad_norm": 0.018541524186730385,
+      "learning_rate": 5.5451342018523755e-06,
+      "loss": 0.7141832828521728,
+      "step": 1095
+    },
+    {
+      "epoch": 1.5647226173541964,
+      "grad_norm": 0.018332267180085182,
+      "learning_rate": 5.5039823748880835e-06,
+      "loss": 0.716184663772583,
+      "step": 1100
+    },
+    {
+      "epoch": 1.5718349928876245,
+      "grad_norm": 0.018345907330513,
+      "learning_rate": 5.462796028764682e-06,
+      "loss": 0.7993448734283447,
+      "step": 1105
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 0.018153423443436623,
+      "learning_rate": 5.421577984449938e-06,
+      "loss": 0.704335880279541,
+      "step": 1110
+    },
+    {
+      "epoch": 1.5860597439544808,
+      "grad_norm": 0.018131373450160027,
+      "learning_rate": 5.380331065082713e-06,
+      "loss": 0.7410067558288574,
+      "step": 1115
+    },
+    {
+      "epoch": 1.593172119487909,
+      "grad_norm": 0.016608260571956635,
+      "learning_rate": 5.339058095779611e-06,
+      "loss": 0.72489333152771,
+      "step": 1120
+    },
+    {
+      "epoch": 1.600284495021337,
+      "grad_norm": 0.01760363206267357,
+      "learning_rate": 5.297761903441458e-06,
+      "loss": 0.6614501953125,
+      "step": 1125
+    },
+    {
+      "epoch": 1.6073968705547652,
+      "grad_norm": 0.10889118164777756,
+      "learning_rate": 5.2564453165597e-06,
+      "loss": 0.6915824890136719,
+      "step": 1130
+    },
+    {
+      "epoch": 1.6145092460881934,
+      "grad_norm": 0.01632538251578808,
+      "learning_rate": 5.215111165022653e-06,
+      "loss": 0.7460376739501953,
+      "step": 1135
+    },
+    {
+      "epoch": 1.6216216216216215,
+      "grad_norm": 0.016797514632344246,
+      "learning_rate": 5.1737622799216925e-06,
+      "loss": 0.6096005439758301,
+      "step": 1140
+    },
+    {
+      "epoch": 1.6287339971550496,
+      "grad_norm": 0.018422367051243782,
+      "learning_rate": 5.132401493357335e-06,
+      "loss": 0.6219287395477295,
+      "step": 1145
+    },
+    {
+      "epoch": 1.635846372688478,
+      "grad_norm": 0.018563445657491684,
+      "learning_rate": 5.091031638245257e-06,
+      "loss": 0.7117269515991211,
+      "step": 1150
+    },
+    {
+      "epoch": 1.6429587482219061,
+      "grad_norm": 0.016881493851542473,
+      "learning_rate": 5.0496555481222745e-06,
+      "loss": 0.7350698471069336,
+      "step": 1155
+    },
+    {
+      "epoch": 1.6500711237553343,
+      "grad_norm": 0.017679262906312943,
+      "learning_rate": 5.008276056952246e-06,
+      "loss": 0.7411237239837647,
+      "step": 1160
+    },
+    {
+      "epoch": 1.6571834992887624,
+      "grad_norm": 0.01986612007021904,
+      "learning_rate": 4.966895998931985e-06,
+      "loss": 0.7164942741394043,
+      "step": 1165
+    },
+    {
+      "epoch": 1.6642958748221908,
+      "grad_norm": 0.018696364015340805,
+      "learning_rate": 4.925518208297124e-06,
+      "loss": 0.7227424621582031,
+      "step": 1170
+    },
+    {
+      "epoch": 1.671408250355619,
+      "grad_norm": 0.019415175542235374,
+      "learning_rate": 4.884145519128005e-06,
+      "loss": 0.6967507839202881,
+      "step": 1175
+    },
+    {
+      "epoch": 1.678520625889047,
+      "grad_norm": 0.017584005370736122,
+      "learning_rate": 4.842780765155549e-06,
+      "loss": 0.7481791019439697,
+      "step": 1180
+    },
+    {
+      "epoch": 1.6856330014224752,
+      "grad_norm": 0.019177937880158424,
+      "learning_rate": 4.8014267795671726e-06,
+      "loss": 0.7086362361907959,
+      "step": 1185
+    },
+    {
+      "epoch": 1.6927453769559033,
+      "grad_norm": 0.017238428816199303,
+      "learning_rate": 4.760086394812739e-06,
+      "loss": 0.6951438903808593,
+      "step": 1190
+    },
+    {
+      "epoch": 1.6998577524893315,
+      "grad_norm": 0.018072783946990967,
+      "learning_rate": 4.718762442410553e-06,
+      "loss": 0.7370012760162353,
+      "step": 1195
+    },
+    {
+      "epoch": 1.7069701280227596,
+      "grad_norm": 0.017421068623661995,
+      "learning_rate": 4.6774577527534195e-06,
+      "loss": 0.7456617832183838,
+      "step": 1200
+    },
+    {
+      "epoch": 1.7140825035561877,
+      "grad_norm": 0.01825086958706379,
+      "learning_rate": 4.636175154914784e-06,
+      "loss": 0.668549633026123,
+      "step": 1205
+    },
+    {
+      "epoch": 1.7211948790896159,
+      "grad_norm": 0.020828979089856148,
+      "learning_rate": 4.5949174764549635e-06,
+      "loss": 0.7580900192260742,
+      "step": 1210
+    },
+    {
+      "epoch": 1.728307254623044,
+      "grad_norm": 0.01653103157877922,
+      "learning_rate": 4.553687543227478e-06,
+      "loss": 0.6961758613586426,
+      "step": 1215
+    },
+    {
+      "epoch": 1.7354196301564722,
+      "grad_norm": 0.01879982091486454,
+      "learning_rate": 4.512488179185496e-06,
+      "loss": 0.7488185882568359,
+      "step": 1220
+    },
+    {
+      "epoch": 1.7425320056899003,
+      "grad_norm": 0.018451698124408722,
+      "learning_rate": 4.471322206188417e-06,
+      "loss": 0.7315212726593018,
+      "step": 1225
+    },
+    {
+      "epoch": 1.7496443812233284,
+      "grad_norm": 0.018766777589917183,
+      "learning_rate": 4.430192443808599e-06,
+      "loss": 0.6953035354614258,
+      "step": 1230
+    },
+    {
+      "epoch": 1.7567567567567568,
+      "grad_norm": 0.018258344382047653,
+      "learning_rate": 4.389101709138232e-06,
+      "loss": 0.7278485298156738,
+      "step": 1235
+    },
+    {
+      "epoch": 1.763869132290185,
+      "grad_norm": 0.020150160416960716,
+      "learning_rate": 4.348052816596383e-06,
+      "loss": 0.7310956001281739,
+      "step": 1240
+    },
+    {
+      "epoch": 1.770981507823613,
+      "grad_norm": 0.01763993687927723,
+      "learning_rate": 4.307048577736248e-06,
+      "loss": 0.703087854385376,
+      "step": 1245
+    },
+    {
+      "epoch": 1.7780938833570412,
+      "grad_norm": 0.017417753115296364,
+      "learning_rate": 4.266091801052555e-06,
+      "loss": 0.6739617347717285,
+      "step": 1250
+    },
+    {
+      "epoch": 1.7852062588904696,
+      "grad_norm": 0.016840264201164246,
+      "learning_rate": 4.225185291789222e-06,
+      "loss": 0.7178611278533935,
+      "step": 1255
+    },
+    {
+      "epoch": 1.7923186344238977,
+      "grad_norm": 0.02682637609541416,
+      "learning_rate": 4.184331851747205e-06,
+      "loss": 0.6898033618927002,
+      "step": 1260
+    },
+    {
+      "epoch": 1.7994310099573259,
+      "grad_norm": 0.018944881856441498,
+      "learning_rate": 4.143534279092613e-06,
+      "loss": 0.7165655136108399,
+      "step": 1265
+    },
+    {
+      "epoch": 1.806543385490754,
+      "grad_norm": 0.017222313210368156,
+      "learning_rate": 4.102795368165029e-06,
+      "loss": 0.7229360580444336,
+      "step": 1270
+    },
+    {
+      "epoch": 1.8136557610241821,
+      "grad_norm": 0.015961620956659317,
+      "learning_rate": 4.062117909286134e-06,
+      "loss": 0.7315521240234375,
+      "step": 1275
+    },
+    {
+      "epoch": 1.8207681365576103,
+      "grad_norm": 0.018907621502876282,
+      "learning_rate": 4.021504688568594e-06,
+      "loss": 0.701743221282959,
+      "step": 1280
+    },
+    {
+      "epoch": 1.8278805120910384,
+      "grad_norm": 0.016745159402489662,
+      "learning_rate": 3.980958487725215e-06,
+      "loss": 0.6797786712646484,
+      "step": 1285
+    },
+    {
+      "epoch": 1.8349928876244666,
+      "grad_norm": 0.01896943338215351,
+      "learning_rate": 3.9404820838784275e-06,
+      "loss": 0.6718417644500733,
+      "step": 1290
+    },
+    {
+      "epoch": 1.8421052631578947,
+      "grad_norm": 0.02180975303053856,
+      "learning_rate": 3.9000782493700716e-06,
+      "loss": 0.700644588470459,
+      "step": 1295
+    },
+    {
+      "epoch": 1.8492176386913228,
+      "grad_norm": 0.018243227154016495,
+      "learning_rate": 3.859749751571514e-06,
+      "loss": 0.6863976955413819,
+      "step": 1300
+    },
+    {
+      "epoch": 1.856330014224751,
+      "grad_norm": 0.02434358559548855,
+      "learning_rate": 3.819499352694094e-06,
+      "loss": 0.6976716041564941,
+      "step": 1305
+    },
+    {
+      "epoch": 1.863442389758179,
+      "grad_norm": 0.01888590306043625,
+      "learning_rate": 3.779329809599942e-06,
+      "loss": 0.6664153575897217,
+      "step": 1310
+    },
+    {
+      "epoch": 1.8705547652916072,
+      "grad_norm": 0.016964025795459747,
+      "learning_rate": 3.7392438736131497e-06,
+      "loss": 0.6734464168548584,
+      "step": 1315
+    },
+    {
+      "epoch": 1.8776671408250356,
+      "grad_norm": 0.018329400569200516,
+      "learning_rate": 3.699244290331322e-06,
+      "loss": 0.7545855045318604,
+      "step": 1320
+    },
+    {
+      "epoch": 1.8847795163584637,
+      "grad_norm": 0.018177052959799767,
+      "learning_rate": 3.65933379943753e-06,
+      "loss": 0.7079776763916016,
+      "step": 1325
+    },
+    {
+      "epoch": 1.8918918918918919,
+      "grad_norm": 0.0189554113894701,
+      "learning_rate": 3.6195151345126556e-06,
+      "loss": 0.6924773216247558,
+      "step": 1330
+    },
+    {
+      "epoch": 1.89900426742532,
+      "grad_norm": 0.01662875898182392,
+      "learning_rate": 3.579791022848167e-06,
+      "loss": 0.7359196186065674,
+      "step": 1335
+    },
+    {
+      "epoch": 1.9061166429587484,
+      "grad_norm": 0.016495555639266968,
+      "learning_rate": 3.5401641852593115e-06,
+      "loss": 0.7219737529754638,
+      "step": 1340
+    },
+    {
+      "epoch": 1.9132290184921765,
+      "grad_norm": 0.019022326916456223,
+      "learning_rate": 3.5006373358987642e-06,
+      "loss": 0.7027291297912598,
+      "step": 1345
+    },
+    {
+      "epoch": 1.9203413940256047,
+      "grad_norm": 0.018207021057605743,
+      "learning_rate": 3.4612131820707338e-06,
+      "loss": 0.6637937545776367,
+      "step": 1350
+    },
+    {
+      "epoch": 1.9274537695590328,
+      "grad_norm": 0.017069589346647263,
+      "learning_rate": 3.4218944240455178e-06,
+      "loss": 0.6664155006408692,
+      "step": 1355
+    },
+    {
+      "epoch": 1.934566145092461,
+      "grad_norm": 0.01894293539226055,
+      "learning_rate": 3.3826837548745615e-06,
+      "loss": 0.7506007671356201,
+      "step": 1360
+    },
+    {
+      "epoch": 1.941678520625889,
+      "grad_norm": 0.020717022940516472,
+      "learning_rate": 3.343583860206011e-06,
+      "loss": 0.6753596305847168,
+      "step": 1365
+    },
+    {
+      "epoch": 1.9487908961593172,
+      "grad_norm": 0.017604727298021317,
+      "learning_rate": 3.304597418100749e-06,
+      "loss": 0.7200678825378418,
+      "step": 1370
+    },
+    {
+      "epoch": 1.9559032716927454,
+      "grad_norm": 0.020626943558454514,
+      "learning_rate": 3.265727098848978e-06,
+      "loss": 0.7199074268341065,
+      "step": 1375
+    },
+    {
+      "epoch": 1.9630156472261735,
+      "grad_norm": 0.01797352358698845,
+      "learning_rate": 3.226975564787322e-06,
+      "loss": 0.6880961418151855,
+      "step": 1380
+    },
+    {
+      "epoch": 1.9701280227596016,
+      "grad_norm": 0.022289294749498367,
+      "learning_rate": 3.1883454701164798e-06,
+      "loss": 0.7005917072296143,
+      "step": 1385
+    },
+    {
+      "epoch": 1.9772403982930298,
+      "grad_norm": 0.019266175106167793,
+      "learning_rate": 3.1498394607194227e-06,
+      "loss": 0.7002647399902344,
+      "step": 1390
+    },
+    {
+      "epoch": 1.984352773826458,
+      "grad_norm": 0.01799497939646244,
+      "learning_rate": 3.111460173980175e-06,
+      "loss": 0.7084723949432373,
+      "step": 1395
+    },
+    {
+      "epoch": 1.991465149359886,
+      "grad_norm": 0.018403980880975723,
+      "learning_rate": 3.07321023860318e-06,
+      "loss": 0.7116297721862793,
+      "step": 1400
+    },
+    {
+      "epoch": 1.9985775248933144,
+      "grad_norm": 0.020092466846108437,
+      "learning_rate": 3.0350922744332354e-06,
+      "loss": 0.6756275177001954,
+      "step": 1405
+    },
+    {
+      "epoch": 2.0056899004267423,
+      "grad_norm": 0.016876336187124252,
+      "learning_rate": 2.9971088922760694e-06,
+      "loss": 0.6916736602783203,
+      "step": 1410
+    },
+    {
+      "epoch": 2.012802275960171,
+      "grad_norm": 0.0186183899641037,
+      "learning_rate": 2.959262693719507e-06,
+      "loss": 0.7194989681243896,
+      "step": 1415
+    },
+    {
+      "epoch": 2.019914651493599,
+      "grad_norm": 0.018291359767317772,
+      "learning_rate": 2.9215562709552936e-06,
+      "loss": 0.7254909992218017,
+      "step": 1420
+    },
+    {
+      "epoch": 2.027027027027027,
+      "grad_norm": 0.018498683348298073,
+      "learning_rate": 2.8839922066015337e-06,
+      "loss": 0.7562304496765136,
+      "step": 1425
+    },
+    {
+      "epoch": 2.0341394025604553,
+      "grad_norm": 0.0183123629540205,
+      "learning_rate": 2.846573073525809e-06,
+      "loss": 0.6986132621765136,
+      "step": 1430
+    },
+    {
+      "epoch": 2.0412517780938835,
+      "grad_norm": 0.01785789616405964,
+      "learning_rate": 2.8093014346689547e-06,
+      "loss": 0.7192048072814942,
+      "step": 1435
+    },
+    {
+      "epoch": 2.0483641536273116,
+      "grad_norm": 0.023237911984324455,
+      "learning_rate": 2.7721798428695164e-06,
+      "loss": 0.6775825023651123,
+      "step": 1440
+    },
+    {
+      "epoch": 2.0554765291607398,
+      "grad_norm": 0.020147794857621193,
+      "learning_rate": 2.7352108406888923e-06,
+      "loss": 0.6980232238769531,
+      "step": 1445
+    },
+    {
+      "epoch": 2.062588904694168,
+      "grad_norm": 0.02223370037972927,
+      "learning_rate": 2.6983969602371983e-06,
+      "loss": 0.713938570022583,
+      "step": 1450
+    },
+    {
+      "epoch": 2.069701280227596,
+      "grad_norm": 0.016787713393568993,
+      "learning_rate": 2.661740722999827e-06,
+      "loss": 0.7800277709960938,
+      "step": 1455
+    },
+    {
+      "epoch": 2.076813655761024,
+      "grad_norm": 0.018036190420389175,
+      "learning_rate": 2.6252446396647503e-06,
+      "loss": 0.6451656818389893,
+      "step": 1460
+    },
+    {
+      "epoch": 2.0839260312944523,
+      "grad_norm": 0.01903928630053997,
+      "learning_rate": 2.5889112099505452e-06,
+      "loss": 0.6771600246429443,
+      "step": 1465
+    },
+    {
+      "epoch": 2.0910384068278804,
+      "grad_norm": 0.01969575695693493,
+      "learning_rate": 2.5527429224352006e-06,
+      "loss": 0.7296658515930176,
+      "step": 1470
+    },
+    {
+      "epoch": 2.0981507823613086,
+      "grad_norm": 0.02083515003323555,
+      "learning_rate": 2.5167422543856424e-06,
+      "loss": 0.6964072704315185,
+      "step": 1475
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.019397174939513206,
+      "learning_rate": 2.4809116715880792e-06,
+      "loss": 0.6488191604614257,
+      "step": 1480
+    },
+    {
+      "epoch": 2.112375533428165,
+      "grad_norm": 0.019878752529621124,
+      "learning_rate": 2.4452536281791056e-06,
+      "loss": 0.6778024673461914,
+      "step": 1485
+    },
+    {
+      "epoch": 2.119487908961593,
+      "grad_norm": 0.01916521228849888,
+      "learning_rate": 2.409770566477611e-06,
+      "loss": 0.7552609920501709,
+      "step": 1490
+    },
+    {
+      "epoch": 2.126600284495021,
+      "grad_norm": 0.018846770748496056,
+      "learning_rate": 2.3744649168174966e-06,
+      "loss": 0.6998651027679443,
+      "step": 1495
+    },
+    {
+      "epoch": 2.1337126600284497,
+      "grad_norm": 0.021791398525238037,
+      "learning_rate": 2.339339097381222e-06,
+      "loss": 0.7401346206665039,
+      "step": 1500
+    },
+    {
+      "epoch": 2.140825035561878,
+      "grad_norm": 0.018046008422970772,
+      "learning_rate": 2.304395514034172e-06,
+      "loss": 0.6855841636657715,
+      "step": 1505
+    },
+    {
+      "epoch": 2.147937411095306,
+      "grad_norm": 0.017584893852472305,
+      "learning_rate": 2.2696365601598714e-06,
+      "loss": 0.76700758934021,
+      "step": 1510
+    },
+    {
+      "epoch": 2.155049786628734,
+      "grad_norm": 0.020246658474206924,
+      "learning_rate": 2.235064616496059e-06,
+      "loss": 0.70643630027771,
+      "step": 1515
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.018499314785003662,
+      "learning_rate": 2.200682050971622e-06,
+      "loss": 0.7396338939666748,
+      "step": 1520
+    },
+    {
+      "epoch": 2.1692745376955904,
+      "grad_norm": 0.023796167224645615,
+      "learning_rate": 2.1664912185444127e-06,
+      "loss": 0.6971643447875977,
+      "step": 1525
+    },
+    {
+      "epoch": 2.1763869132290186,
+      "grad_norm": 0.019194869324564934,
+      "learning_rate": 2.1324944610399423e-06,
+      "loss": 0.7047183990478516,
+      "step": 1530
+    },
+    {
+      "epoch": 2.1834992887624467,
+      "grad_norm": 0.018008023500442505,
+      "learning_rate": 2.0986941069909937e-06,
+      "loss": 0.7083112239837647,
+      "step": 1535
+    },
+    {
+      "epoch": 2.190611664295875,
+      "grad_norm": 0.021395748481154442,
+      "learning_rate": 2.06509247147813e-06,
+      "loss": 0.7210383415222168,
+      "step": 1540
+    },
+    {
+      "epoch": 2.197724039829303,
+      "grad_norm": 0.0217084139585495,
+      "learning_rate": 2.0316918559711264e-06,
+      "loss": 0.7158208847045898,
+      "step": 1545
+    },
+    {
+      "epoch": 2.204836415362731,
+      "grad_norm": 0.02183559723198414,
+      "learning_rate": 1.9984945481713308e-06,
+      "loss": 0.6984762668609619,
+      "step": 1550
+    },
+    {
+      "epoch": 2.2119487908961593,
+      "grad_norm": 0.020434515550732613,
+      "learning_rate": 1.9655028218549925e-06,
+      "loss": 0.6603986263275147,
+      "step": 1555
+    },
+    {
+      "epoch": 2.2190611664295874,
+      "grad_norm": 0.021293608471751213,
+      "learning_rate": 1.932718936717497e-06,
+      "loss": 0.6903936862945557,
+      "step": 1560
+    },
+    {
+      "epoch": 2.2261735419630155,
+      "grad_norm": 0.019045505672693253,
+      "learning_rate": 1.900145138218617e-06,
+      "loss": 0.7222468852996826,
+      "step": 1565
+    },
+    {
+      "epoch": 2.2332859174964437,
+      "grad_norm": 0.020146358758211136,
+      "learning_rate": 1.8677836574286978e-06,
+      "loss": 0.757137680053711,
+      "step": 1570
+    },
+    {
+      "epoch": 2.240398293029872,
+      "grad_norm": 0.019575543701648712,
+      "learning_rate": 1.8356367108758628e-06,
+      "loss": 0.7008779525756836,
+      "step": 1575
+    },
+    {
+      "epoch": 2.2475106685633,
+      "grad_norm": 0.018083350732922554,
+      "learning_rate": 1.803706500394175e-06,
+      "loss": 0.7534774780273438,
+      "step": 1580
+    },
+    {
+      "epoch": 2.2546230440967285,
+      "grad_norm": 0.021902941167354584,
+      "learning_rate": 1.771995212972847e-06,
+      "loss": 0.6821448326110839,
+      "step": 1585
+    },
+    {
+      "epoch": 2.2617354196301562,
+      "grad_norm": 0.021106917411088943,
+      "learning_rate": 1.7405050206064372e-06,
+      "loss": 0.7266870498657226,
+      "step": 1590
+    },
+    {
+      "epoch": 2.268847795163585,
+      "grad_norm": 0.020212018862366676,
+      "learning_rate": 1.70923808014609e-06,
+      "loss": 0.7044878959655761,
+      "step": 1595
+    },
+    {
+      "epoch": 2.275960170697013,
+      "grad_norm": 0.017820734530687332,
+      "learning_rate": 1.6781965331517975e-06,
+      "loss": 0.6944470405578613,
+      "step": 1600
+    },
+    {
+      "epoch": 2.283072546230441,
+      "grad_norm": 0.017846427857875824,
+      "learning_rate": 1.6473825057457293e-06,
+      "loss": 0.6674845695495606,
+      "step": 1605
+    },
+    {
+      "epoch": 2.2901849217638692,
+      "grad_norm": 0.018820255994796753,
+      "learning_rate": 1.616798108466603e-06,
+      "loss": 0.7415022850036621,
+      "step": 1610
+    },
+    {
+      "epoch": 2.2972972972972974,
+      "grad_norm": 0.0177475456148386,
+      "learning_rate": 1.586445436125127e-06,
+      "loss": 0.7364046096801757,
+      "step": 1615
+    },
+    {
+      "epoch": 2.3044096728307255,
+      "grad_norm": 0.02009609155356884,
+      "learning_rate": 1.5563265676605228e-06,
+      "loss": 0.6232909202575684,
+      "step": 1620
+    },
+    {
+      "epoch": 2.3115220483641536,
+      "grad_norm": 0.01963597536087036,
+      "learning_rate": 1.5264435659981335e-06,
+      "loss": 0.7436121940612793,
+      "step": 1625
+    },
+    {
+      "epoch": 2.318634423897582,
+      "grad_norm": 0.01879408396780491,
+      "learning_rate": 1.496798477908122e-06,
+      "loss": 0.6992465019226074,
+      "step": 1630
+    },
+    {
+      "epoch": 2.32574679943101,
+      "grad_norm": 0.018343554809689522,
+      "learning_rate": 1.4673933338652907e-06,
+      "loss": 0.690833330154419,
+      "step": 1635
+    },
+    {
+      "epoch": 2.332859174964438,
+      "grad_norm": 0.018954213708639145,
+      "learning_rate": 1.4382301479100048e-06,
+      "loss": 0.7103327751159668,
+      "step": 1640
+    },
+    {
+      "epoch": 2.339971550497866,
+      "grad_norm": 0.01864561438560486,
+      "learning_rate": 1.4093109175102432e-06,
+      "loss": 0.7096752166748047,
+      "step": 1645
+    },
+    {
+      "epoch": 2.3470839260312943,
+      "grad_norm": 0.018006840720772743,
+      "learning_rate": 1.380637623424791e-06,
+      "loss": 0.7237026214599609,
+      "step": 1650
+    },
+    {
+      "epoch": 2.3541963015647225,
+      "grad_norm": 0.01974598504602909,
+      "learning_rate": 1.3522122295675616e-06,
+      "loss": 0.7115821361541748,
+      "step": 1655
+    },
+    {
+      "epoch": 2.3613086770981506,
+      "grad_norm": 0.01914205215871334,
+      "learning_rate": 1.324036682873102e-06,
+      "loss": 0.721008586883545,
+      "step": 1660
+    },
+    {
+      "epoch": 2.3684210526315788,
+      "grad_norm": 0.019481945782899857,
+      "learning_rate": 1.2961129131632183e-06,
+      "loss": 0.7210357666015625,
+      "step": 1665
+    },
+    {
+      "epoch": 2.3755334281650073,
+      "grad_norm": 0.0294849444180727,
+      "learning_rate": 1.2684428330148164e-06,
+      "loss": 0.7165197372436524,
+      "step": 1670
+    },
+    {
+      "epoch": 2.382645803698435,
+      "grad_norm": 0.019714608788490295,
+      "learning_rate": 1.241028337628888e-06,
+      "loss": 0.7028004646301269,
+      "step": 1675
+    },
+    {
+      "epoch": 2.3897581792318636,
+      "grad_norm": 0.017666790634393692,
+      "learning_rate": 1.2138713047007229e-06,
+      "loss": 0.6465110301971435,
+      "step": 1680
+    },
+    {
+      "epoch": 2.3968705547652918,
+      "grad_norm": 0.020633701235055923,
+      "learning_rate": 1.1869735942912768e-06,
+      "loss": 0.6445804595947265,
+      "step": 1685
+    },
+    {
+      "epoch": 2.40398293029872,
+      "grad_norm": 0.019184108823537827,
+      "learning_rate": 1.1603370486997912e-06,
+      "loss": 0.6999986171722412,
+      "step": 1690
+    },
+    {
+      "epoch": 2.411095305832148,
+      "grad_norm": 0.018636522814631462,
+      "learning_rate": 1.1339634923375958e-06,
+      "loss": 0.7130412578582763,
+      "step": 1695
+    },
+    {
+      "epoch": 2.418207681365576,
+      "grad_norm": 0.02027011662721634,
+      "learning_rate": 1.107854731603158e-06,
+      "loss": 0.7074708938598633,
+      "step": 1700
+    },
+    {
+      "epoch": 2.4253200568990043,
+      "grad_norm": 0.01711525022983551,
+      "learning_rate": 1.082012554758346e-06,
+      "loss": 0.7176192283630372,
+      "step": 1705
+    },
+    {
+      "epoch": 2.4324324324324325,
+      "grad_norm": 0.01916031911969185,
+      "learning_rate": 1.0564387318059654e-06,
+      "loss": 0.7125048637390137,
+      "step": 1710
+    },
+    {
+      "epoch": 2.4395448079658606,
+      "grad_norm": 0.018072018399834633,
+      "learning_rate": 1.031135014368504e-06,
+      "loss": 0.7297768115997314,
+      "step": 1715
+    },
+    {
+      "epoch": 2.4466571834992887,
+      "grad_norm": 0.017285477370023727,
+      "learning_rate": 1.0061031355681766e-06,
+      "loss": 0.6963360786437989,
+      "step": 1720
+    },
+    {
+      "epoch": 2.453769559032717,
+      "grad_norm": 0.020556973293423653,
+      "learning_rate": 9.813448099082047e-07,
+      "loss": 0.7077793598175048,
+      "step": 1725
+    },
+    {
+      "epoch": 2.460881934566145,
+      "grad_norm": 0.0190748143941164,
+      "learning_rate": 9.568617331553997e-07,
+      "loss": 0.6809517860412597,
+      "step": 1730
+    },
+    {
+      "epoch": 2.467994310099573,
+      "grad_norm": 0.020035238936543465,
+      "learning_rate": 9.326555822240002e-07,
+      "loss": 0.7002559185028077,
+      "step": 1735
+    },
+    {
+      "epoch": 2.4751066856330013,
+      "grad_norm": 0.02111983671784401,
+      "learning_rate": 9.087280150608263e-07,
+      "loss": 0.6911906719207763,
+      "step": 1740
+    },
+    {
+      "epoch": 2.4822190611664294,
+      "grad_norm": 0.01914399489760399,
+      "learning_rate": 8.850806705317183e-07,
+      "loss": 0.7122188568115234,
+      "step": 1745
+    },
+    {
+      "epoch": 2.4893314366998576,
+      "grad_norm": 0.019931111484766006,
+      "learning_rate": 8.617151683092856e-07,
+      "loss": 0.6926873683929443,
+      "step": 1750
+    },
+    {
+      "epoch": 2.496443812233286,
+      "grad_norm": 0.042251236736774445,
+      "learning_rate": 8.386331087619726e-07,
+      "loss": 0.701508903503418,
+      "step": 1755
+    },
+    {
+      "epoch": 2.503556187766714,
+      "grad_norm": 0.019246656447649002,
+      "learning_rate": 8.158360728444404e-07,
+      "loss": 0.7105617523193359,
+      "step": 1760
+    },
+    {
+      "epoch": 2.5106685633001424,
+      "grad_norm": 0.018132740631699562,
+      "learning_rate": 7.933256219892938e-07,
+      "loss": 0.7254996299743652,
+      "step": 1765
+    },
+    {
+      "epoch": 2.5177809388335706,
+      "grad_norm": 0.020589511841535568,
+      "learning_rate": 7.711032980001182e-07,
+      "loss": 0.6329239845275879,
+      "step": 1770
+    },
+    {
+      "epoch": 2.5248933143669987,
+      "grad_norm": 0.017706142738461494,
+      "learning_rate": 7.491706229458923e-07,
+      "loss": 0.6217228889465332,
+      "step": 1775
+    },
+    {
+      "epoch": 2.532005689900427,
+      "grad_norm": 0.019098540768027306,
+      "learning_rate": 7.275290990567286e-07,
+      "loss": 0.6849424362182617,
+      "step": 1780
+    },
+    {
+      "epoch": 2.539118065433855,
+      "grad_norm": 0.017864609137177467,
+      "learning_rate": 7.061802086209857e-07,
+      "loss": 0.6907006740570069,
+      "step": 1785
+    },
+    {
+      "epoch": 2.546230440967283,
+      "grad_norm": 0.01882258802652359,
+      "learning_rate": 6.851254138837366e-07,
+      "loss": 0.7112642765045166,
+      "step": 1790
+    },
+    {
+      "epoch": 2.5533428165007113,
+      "grad_norm": 0.017759790644049644,
+      "learning_rate": 6.643661569466225e-07,
+      "loss": 0.6860599994659424,
+      "step": 1795
+    },
+    {
+      "epoch": 2.5604551920341394,
+      "grad_norm": 0.04660586640238762,
+      "learning_rate": 6.439038596690756e-07,
+      "loss": 0.6946640968322754,
+      "step": 1800
+    },
+    {
+      "epoch": 2.5675675675675675,
+      "grad_norm": 0.018053406849503517,
+      "learning_rate": 6.237399235709335e-07,
+      "loss": 0.70596923828125,
+      "step": 1805
+    },
+    {
+      "epoch": 2.5746799431009957,
+      "grad_norm": 0.01948445849120617,
+      "learning_rate": 6.038757297364389e-07,
+      "loss": 0.6995176792144775,
+      "step": 1810
+    },
+    {
+      "epoch": 2.581792318634424,
+      "grad_norm": 0.017586836591362953,
+      "learning_rate": 5.843126387196591e-07,
+      "loss": 0.7351008892059326,
+      "step": 1815
+    },
+    {
+      "epoch": 2.588904694167852,
+      "grad_norm": 0.018592992797493935,
+      "learning_rate": 5.650519904512814e-07,
+      "loss": 0.6893433570861817,
+      "step": 1820
+    },
+    {
+      "epoch": 2.59601706970128,
+      "grad_norm": 0.01698880083858967,
+      "learning_rate": 5.460951041468493e-07,
+      "loss": 0.6391551494598389,
+      "step": 1825
+    },
+    {
+      "epoch": 2.6031294452347082,
+      "grad_norm": 0.019620927050709724,
+      "learning_rate": 5.27443278216399e-07,
+      "loss": 0.688290023803711,
+      "step": 1830
+    },
+    {
+      "epoch": 2.6102418207681364,
+      "grad_norm": 0.019304607063531876,
+      "learning_rate": 5.090977901755362e-07,
+      "loss": 0.7163221359252929,
+      "step": 1835
+    },
+    {
+      "epoch": 2.617354196301565,
+      "grad_norm": 0.0220966674387455,
+      "learning_rate": 4.910598965579228e-07,
+      "loss": 0.7392453670501709,
+      "step": 1840
+    },
+    {
+      "epoch": 2.6244665718349927,
+      "grad_norm": 0.01833263970911503,
+      "learning_rate": 4.7333083282922463e-07,
+      "loss": 0.6708541870117187,
+      "step": 1845
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.020094405859708786,
+      "learning_rate": 4.5591181330248534e-07,
+      "loss": 0.6930543422698975,
+      "step": 1850
+    },
+    {
+      "epoch": 2.6386913229018494,
+      "grad_norm": 0.020695924758911133,
+      "learning_rate": 4.3880403105495793e-07,
+      "loss": 0.6685608863830567,
+      "step": 1855
+    },
+    {
+      "epoch": 2.6458036984352775,
+      "grad_norm": 0.018926840275526047,
+      "learning_rate": 4.220086578463806e-07,
+      "loss": 0.6826137065887451,
+      "step": 1860
+    },
+    {
+      "epoch": 2.6529160739687057,
+      "grad_norm": 0.01943895034492016,
+      "learning_rate": 4.0552684403873274e-07,
+      "loss": 0.6445528030395508,
+      "step": 1865
+    },
+    {
+      "epoch": 2.660028449502134,
+      "grad_norm": 0.019336692988872528,
+      "learning_rate": 3.8935971851742746e-07,
+      "loss": 0.6931255340576172,
+      "step": 1870
+    },
+    {
+      "epoch": 2.667140825035562,
+      "grad_norm": 0.017861362546682358,
+      "learning_rate": 3.7350838861400454e-07,
+      "loss": 0.680919075012207,
+      "step": 1875
+    },
+    {
+      "epoch": 2.67425320056899,
+      "grad_norm": 0.01909296214580536,
+      "learning_rate": 3.579739400302773e-07,
+      "loss": 0.756756591796875,
+      "step": 1880
+    },
+    {
+      "epoch": 2.681365576102418,
+      "grad_norm": 0.022265156731009483,
+      "learning_rate": 3.4275743676397633e-07,
+      "loss": 0.7306240558624267,
+      "step": 1885
+    },
+    {
+      "epoch": 2.6884779516358464,
+      "grad_norm": 0.019674202427268028,
+      "learning_rate": 3.278599210358685e-07,
+      "loss": 0.7194355964660645,
+      "step": 1890
+    },
+    {
+      "epoch": 2.6955903271692745,
+      "grad_norm": 0.02009180188179016,
+      "learning_rate": 3.132824132183726e-07,
+      "loss": 0.6854644298553467,
+      "step": 1895
+    },
+    {
+      "epoch": 2.7027027027027026,
+      "grad_norm": 0.019245633855462074,
+      "learning_rate": 2.9902591176567743e-07,
+      "loss": 0.7046674728393555,
+      "step": 1900
+    },
+    {
+      "epoch": 2.7098150782361308,
+      "grad_norm": 0.019660472869873047,
+      "learning_rate": 2.850913931453447e-07,
+      "loss": 0.6495515823364257,
+      "step": 1905
+    },
+    {
+      "epoch": 2.716927453769559,
+      "grad_norm": 0.018463047221302986,
+      "learning_rate": 2.714798117714373e-07,
+      "loss": 0.7126041889190674,
+      "step": 1910
+    },
+    {
+      "epoch": 2.724039829302987,
+      "grad_norm": 0.020338578149676323,
+      "learning_rate": 2.5819209993914185e-07,
+      "loss": 0.6964741706848144,
+      "step": 1915
+    },
+    {
+      "epoch": 2.731152204836415,
+      "grad_norm": 0.025541720911860466,
+      "learning_rate": 2.4522916776092144e-07,
+      "loss": 0.6981581211090088,
+      "step": 1920
+    },
+    {
+      "epoch": 2.7382645803698438,
+      "grad_norm": 0.03043808415532112,
+      "learning_rate": 2.3259190310416847e-07,
+      "loss": 0.6668709278106689,
+      "step": 1925
+    },
+    {
+      "epoch": 2.7453769559032715,
+      "grad_norm": 0.017312461510300636,
+      "learning_rate": 2.2028117153040208e-07,
+      "loss": 0.6342219829559326,
+      "step": 1930
+    },
+    {
+      "epoch": 2.7524893314367,
+      "grad_norm": 0.022723648697137833,
+      "learning_rate": 2.082978162359778e-07,
+      "loss": 0.7471845149993896,
+      "step": 1935
+    },
+    {
+      "epoch": 2.759601706970128,
+      "grad_norm": 0.01946732960641384,
+      "learning_rate": 1.9664265799433758e-07,
+      "loss": 0.727109432220459,
+      "step": 1940
+    },
+    {
+      "epoch": 2.7667140825035563,
+      "grad_norm": 0.019219428300857544,
+      "learning_rate": 1.8531649509978933e-07,
+      "loss": 0.6843738079071044,
+      "step": 1945
+    },
+    {
+      "epoch": 2.7738264580369845,
+      "grad_norm": 0.017926136031746864,
+      "learning_rate": 1.7432010331283388e-07,
+      "loss": 0.7088566780090332,
+      "step": 1950
+    },
+    {
+      "epoch": 2.7809388335704126,
+      "grad_norm": 0.01807708479464054,
+      "learning_rate": 1.63654235807027e-07,
+      "loss": 0.7071962833404541,
+      "step": 1955
+    },
+    {
+      "epoch": 2.7880512091038407,
+      "grad_norm": 0.019878104329109192,
+      "learning_rate": 1.5331962311739668e-07,
+      "loss": 0.7710360527038574,
+      "step": 1960
+    },
+    {
+      "epoch": 2.795163584637269,
+      "grad_norm": 0.02000255696475506,
+      "learning_rate": 1.4331697309039937e-07,
+      "loss": 0.6493950366973877,
+      "step": 1965
+    },
+    {
+      "epoch": 2.802275960170697,
+      "grad_norm": 0.01814078353345394,
+      "learning_rate": 1.336469708354493e-07,
+      "loss": 0.69231276512146,
+      "step": 1970
+    },
+    {
+      "epoch": 2.809388335704125,
+      "grad_norm": 0.02213713899254799,
+      "learning_rate": 1.243102786779804e-07,
+      "loss": 0.6923561096191406,
+      "step": 1975
+    },
+    {
+      "epoch": 2.8165007112375533,
+      "grad_norm": 0.01917503960430622,
+      "learning_rate": 1.1530753611409151e-07,
+      "loss": 0.7251245498657226,
+      "step": 1980
+    },
+    {
+      "epoch": 2.8236130867709814,
+      "grad_norm": 0.01758253388106823,
+      "learning_rate": 1.0663935976674145e-07,
+      "loss": 0.7662966251373291,
+      "step": 1985
+    },
+    {
+      "epoch": 2.8307254623044096,
+      "grad_norm": 0.020537367090582848,
+      "learning_rate": 9.830634334351385e-08,
+      "loss": 0.6968005180358887,
+      "step": 1990
+    },
+    {
+      "epoch": 2.8378378378378377,
+      "grad_norm": 0.01874646171927452,
+      "learning_rate": 9.030905759595643e-08,
+      "loss": 0.7220873355865478,
+      "step": 1995
+    },
+    {
+      "epoch": 2.844950213371266,
+      "grad_norm": 0.019075002521276474,
+      "learning_rate": 8.264805028048384e-08,
+      "loss": 0.749581241607666,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 2109,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.1755490933791949e+19,
+  "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:b701895e0ecc6dc61c92935f1a1b2fb2a7193e239271c6f23fe3f96a402f9d59
+size 5713