Add checkpoint-4200

.gitattributes

@@ -53,3 +53,4 @@ checkpoints/checkpoint-3400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/checkpoint-3600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/checkpoint-3800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/checkpoint-4200/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/checkpoint-4200/README.md

@@ -0,0 +1,210 @@
+---
+base_model: OpenPathAI/Orbit-3-Nano
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:OpenPathAI/Orbit-3-Nano
+- 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 0.20.0

checkpoints/checkpoint-4200/adapter_config.json

@@ -0,0 +1,46 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "Lfm2ForCausalLM",
+    "parent_library": "transformers.models.lfm2.modeling_lfm2",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "OpenPathAI/Orbit-3-Nano",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "lora_ga_config": null,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "monteclora_config": null,
+  "peft_type": "LORA",
+  "peft_version": "0.20.0",
+  "qalora_group_size": 16,
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": "(?:.*?(?:language|text).*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj))|(?:\\bmodel\\.layers\\.[\\d]{1,}(?!.*\\.experts\\.\\d)\\..*?(?:self_attn|attention|attn|mixer|mlp|feed_forward|ffn|dense|mixer).*?\\.(?:(?:q_proj|k_proj|v_proj|o_proj|gate_proj|up_proj|down_proj)))",
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_bdlora": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false,
+  "velora_config": null
+}

checkpoints/checkpoint-4200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0573afa28fabc56164b4ff05b342e0ea92b064043e947d8c71d0f0e9c2f1d1c8
+size 4724960

checkpoints/checkpoint-4200/chat_template.jinja

@@ -0,0 +1,125 @@
+{{- bos_token -}}
+{%- set preserve_thinking = preserve_thinking | default(false) -%}
+
+{%- macro format_arg_value(arg_value) -%}
+    {%- if arg_value is string -%}
+        {{- "'" + (arg_value | replace("\\", "\\\\") | replace("'", "\\'") | replace("\n", "\\n") | replace("\r", "\\r")) + "'" -}}
+    {%- elif arg_value is mapping or arg_value is iterable -%}
+        {{- arg_value | tojson -}}
+    {%- else -%}
+        {{- arg_value | string -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro parse_content(content) -%}
+    {%- if content is string -%}
+        {{- content -}}
+    {%- elif content is mapping -%}
+        {{- content | tojson -}}
+    {%- elif content is iterable -%}
+        {%- set _ns = namespace(result="") -%}
+        {%- for item in content -%}
+            {%- if item is string -%}
+                {%- set _ns.result = _ns.result + item -%}
+            {%- elif item is mapping and item.get("type") == "image" -%}
+                {%- set _ns.result = _ns.result + "<image>" -%}
+            {%- elif item is mapping and item.get("type") == "text" -%}
+                {%- set _ns.result = _ns.result + ((item.get("text") or "") | string) -%}
+            {%- else -%}
+                {%- set _ns.result = _ns.result + (item | tojson) -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {{- _ns.result -}}
+    {%- endif -%}
+{%- endmacro -%}
+
+{%- macro render_tool_calls(tool_calls) -%}
+    {%- set tool_calls_ns = namespace(tool_calls=[]) -%}
+    {%- for tool_call in tool_calls -%}
+        {%- set func = tool_call["function"] if "function" in tool_call else tool_call -%}
+        {%- set func_name = func["name"] -%}
+        {%- set func_args = func.get("arguments") -%}
+        {%- set args_ns = namespace(arg_strings=[]) -%}
+        {%- if func_args is mapping -%}
+            {%- for arg_name, arg_value in func_args.items() -%}
+                {%- set args_ns.arg_strings = args_ns.arg_strings + [arg_name + "=" + format_arg_value(arg_value)] -%}
+            {%- endfor -%}
+        {%- elif func_args is string and (func_args | trim) not in ["", "{}", "null"] -%}
+            {{- raise_exception("Tool call arguments must be a mapping, got a JSON-encoded string: parse arguments with json.loads() before applying the chat template") -}}
+        {%- endif -%}
+        {%- set tool_calls_ns.tool_calls = tool_calls_ns.tool_calls + [func_name + "(" + (args_ns.arg_strings | join(", ")) + ")"] -%}
+    {%- endfor -%}
+    {{- "<|tool_call_start|>[" + (tool_calls_ns.tool_calls | join(", ")) + "]<|tool_call_end|>" -}}
+{%- endmacro -%}
+
+{%- set ns = namespace(system_prompt="", last_user_index=-1) -%}
+{%- if messages and messages[0]["role"] == "system" -%}
+    {%- if messages[0].get("content") -%}
+        {%- set ns.system_prompt = parse_content(messages[0]["content"]) -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- for tool in tools -%}
+        {%- if tool is not string -%}
+            {%- set tool = tool | tojson -%}
+        {%- endif -%}
+        {%- set ns.system_prompt = ns.system_prompt + tool -%}
+        {%- if not loop.last -%}
+            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
+        {%- endif -%}
+    {%- endfor -%}
+    {%- set ns.system_prompt = ns.system_prompt + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "user" -%}
+        {%- set ns.last_user_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message.role + "\n" -}}
+    {%- if message.role == "assistant" -%}
+        {%- generation -%}
+        {%- set keep_thinking = preserve_thinking or loop.index0 > ns.last_user_index -%}
+        {%- set thinking = message.thinking or message.reasoning or message.reasoning_content -%}
+        {%- set thinking = thinking if thinking is string else "" -%}
+        {%- if thinking and keep_thinking -%}
+            {{- "<think>" + thinking + "</think>" -}}
+        {%- endif -%}
+        {%- set _cfm_tag = "CONTINUE_FINAL_MESSAGE_TAG " -%}
+        {%- set _has_cfm = false -%}
+        {%- set content = "" -%}
+        {%- if message.get("content") -%}
+            {%- set content = parse_content(message.content) -%}
+        {%- endif -%}
+        {%- if not keep_thinking and "</think>" in content -%}
+            {%- set content = content.split("</think>")[-1] | trim -%}
+        {%- endif -%}
+        {%- if content.endswith(_cfm_tag) -%}
+            {%- set _has_cfm = true -%}
+            {%- set _trunc_len = (content | length) - (_cfm_tag | length) -%}
+            {%- set content = content[:_trunc_len] -%}
+        {%- endif -%}
+        {{- content -}}
+        {%- if message.tool_calls -%}
+            {{- render_tool_calls(message.tool_calls) -}}
+        {%- endif -%}
+        {%- if _has_cfm -%}
+            {{- _cfm_tag -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+        {%- endgeneration -%}
+    {%- else %}
+        {%- if message.get("content") -%}
+            {{- parse_content(message["content"]) -}}
+        {%- endif -%}
+        {{- "<|im_end|>\n" -}}
+    {%- endif %}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n<think>" -}}
+{%- endif -%}

checkpoints/checkpoint-4200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78812361eff69f7d91e75986dbb23fbd8de3c19b3f504168a84eb376867c9d6f
+size 2578187

checkpoints/checkpoint-4200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:171c1447ce3107eaa6c5e51feafc8bed669c993c07d6859424236902ccc90c4a
+size 14645

checkpoints/checkpoint-4200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:991ff7e75744e335356e4a8ce211ac789c0513e8abf0cdddb0d8aba71ac8a928
+size 1383

checkpoints/checkpoint-4200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2abd90bc03028c3f35590f85e2ccdf62982dff1df005f07c3725b8e6b631467
+size 1465

checkpoints/checkpoint-4200/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:695be7802a0e4b8a81048f0ff5ebb7fc811a0ba5a6be63dbb24deb5a81096f41
+size 17905598

checkpoints/checkpoint-4200/tokenizer_config.json

@@ -0,0 +1,1008 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "added_tokens_decoder": {
+    "124893": {
+      "content": "<|pad|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124894": {
+      "content": "<|startoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124895": {
+      "content": "<|endoftext|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124896": {
+      "content": "<|fim_pre|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124897": {
+      "content": "<|fim_mid|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124898": {
+      "content": "<|fim_suf|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124899": {
+      "content": "<|im_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124900": {
+      "content": "<|im_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124901": {
+      "content": "<think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "124902": {
+      "content": "</think>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "124903": {
+      "content": "<|tool_list_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124904": {
+      "content": "<|tool_list_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124905": {
+      "content": "<|tool_call_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "124906": {
+      "content": "<|tool_call_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": false
+    },
+    "124907": {
+      "content": "<image>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124908": {
+      "content": "<|img_row_1_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124909": {
+      "content": "<|img_row_1_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124910": {
+      "content": "<|img_row_1_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124911": {
+      "content": "<|img_row_1_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124912": {
+      "content": "<|img_row_1_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124913": {
+      "content": "<|img_row_1_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124914": {
+      "content": "<|img_row_1_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124915": {
+      "content": "<|img_row_1_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124916": {
+      "content": "<|img_row_1_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124917": {
+      "content": "<|img_row_1_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124918": {
+      "content": "<|img_row_2_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124919": {
+      "content": "<|img_row_2_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124920": {
+      "content": "<|img_row_2_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124921": {
+      "content": "<|img_row_2_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124922": {
+      "content": "<|img_row_2_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124923": {
+      "content": "<|img_row_2_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124924": {
+      "content": "<|img_row_2_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124925": {
+      "content": "<|img_row_2_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124926": {
+      "content": "<|img_row_2_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124927": {
+      "content": "<|img_row_2_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124928": {
+      "content": "<|img_row_3_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124929": {
+      "content": "<|img_row_3_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124930": {
+      "content": "<|img_row_3_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124931": {
+      "content": "<|img_row_3_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124932": {
+      "content": "<|img_row_3_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124933": {
+      "content": "<|img_row_3_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124934": {
+      "content": "<|img_row_3_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124935": {
+      "content": "<|img_row_3_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124936": {
+      "content": "<|img_row_3_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124937": {
+      "content": "<|img_row_3_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124938": {
+      "content": "<|img_row_4_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124939": {
+      "content": "<|img_row_4_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124940": {
+      "content": "<|img_row_4_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124941": {
+      "content": "<|img_row_4_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124942": {
+      "content": "<|img_row_4_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124943": {
+      "content": "<|img_row_4_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124944": {
+      "content": "<|img_row_4_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124945": {
+      "content": "<|img_row_4_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124946": {
+      "content": "<|img_row_4_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124947": {
+      "content": "<|img_row_4_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124948": {
+      "content": "<|img_row_5_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124949": {
+      "content": "<|img_row_5_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124950": {
+      "content": "<|img_row_5_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124951": {
+      "content": "<|img_row_5_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124952": {
+      "content": "<|img_row_5_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124953": {
+      "content": "<|img_row_5_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124954": {
+      "content": "<|img_row_5_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124955": {
+      "content": "<|img_row_5_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124956": {
+      "content": "<|img_row_5_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124957": {
+      "content": "<|img_row_5_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124958": {
+      "content": "<|img_row_6_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124959": {
+      "content": "<|img_row_6_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124960": {
+      "content": "<|img_row_6_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124961": {
+      "content": "<|img_row_6_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124962": {
+      "content": "<|img_row_6_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124963": {
+      "content": "<|img_row_6_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124964": {
+      "content": "<|img_row_6_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124965": {
+      "content": "<|img_row_6_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124966": {
+      "content": "<|img_row_6_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124967": {
+      "content": "<|img_row_6_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124968": {
+      "content": "<|img_row_7_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124969": {
+      "content": "<|img_row_7_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124970": {
+      "content": "<|img_row_7_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124971": {
+      "content": "<|img_row_7_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124972": {
+      "content": "<|img_row_7_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124973": {
+      "content": "<|img_row_7_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124974": {
+      "content": "<|img_row_7_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124975": {
+      "content": "<|img_row_7_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124976": {
+      "content": "<|img_row_7_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124977": {
+      "content": "<|img_row_7_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124978": {
+      "content": "<|img_row_8_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124979": {
+      "content": "<|img_row_8_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124980": {
+      "content": "<|img_row_8_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124981": {
+      "content": "<|img_row_8_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124982": {
+      "content": "<|img_row_8_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124983": {
+      "content": "<|img_row_8_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124984": {
+      "content": "<|img_row_8_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124985": {
+      "content": "<|img_row_8_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124986": {
+      "content": "<|img_row_8_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124987": {
+      "content": "<|img_row_8_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124988": {
+      "content": "<|img_row_9_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124989": {
+      "content": "<|img_row_9_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124990": {
+      "content": "<|img_row_9_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124991": {
+      "content": "<|img_row_9_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124992": {
+      "content": "<|img_row_9_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124993": {
+      "content": "<|img_row_9_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124994": {
+      "content": "<|img_row_9_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124995": {
+      "content": "<|img_row_9_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124996": {
+      "content": "<|img_row_9_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124997": {
+      "content": "<|img_row_9_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124998": {
+      "content": "<|img_row_10_col_1|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "124999": {
+      "content": "<|img_row_10_col_2|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125000": {
+      "content": "<|img_row_10_col_3|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125001": {
+      "content": "<|img_row_10_col_4|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125002": {
+      "content": "<|img_row_10_col_5|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125003": {
+      "content": "<|img_row_10_col_6|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125004": {
+      "content": "<|img_row_10_col_7|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125005": {
+      "content": "<|img_row_10_col_8|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125006": {
+      "content": "<|img_row_10_col_9|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125007": {
+      "content": "<|img_row_10_col_10|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125008": {
+      "content": "<|img_thumbnail|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125009": {
+      "content": "<|image_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125010": {
+      "content": "<|image_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125011": {
+      "content": "<|image_split|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125012": {
+      "content": "<|audio_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125013": {
+      "content": "<|text_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125014": {
+      "content": "<|text_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125015": {
+      "content": "<|mixed_start|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    },
+    "125016": {
+      "content": "<|mixed_end|>",
+      "single_word": false,
+      "lstrip": false,
+      "rstrip": false,
+      "normalized": false,
+      "special": true
+    }
+  }
+}

checkpoints/checkpoint-4200/trainer_state.json

@@ -0,0 +1,2974 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.66732830488289,
+  "eval_steps": 500,
+  "global_step": 4200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003969829297340214,
+      "grad_norm": 0.6961175799369812,
+      "learning_rate": 0.00016,
+      "loss": 3.2075271606445312,
+      "step": 10
+    },
+    {
+      "epoch": 0.007939658594680429,
+      "grad_norm": 0.9305199384689331,
+      "learning_rate": 0.00019978799522989268,
+      "loss": 3.1885648727416993,
+      "step": 20
+    },
+    {
+      "epoch": 0.011909487892020643,
+      "grad_norm": 0.8452768325805664,
+      "learning_rate": 0.00019952298926725852,
+      "loss": 2.9959283828735352,
+      "step": 30
+    },
+    {
+      "epoch": 0.015879317189360857,
+      "grad_norm": 0.9384715557098389,
+      "learning_rate": 0.00019925798330462438,
+      "loss": 3.132890510559082,
+      "step": 40
+    },
+    {
+      "epoch": 0.019849146486701073,
+      "grad_norm": 0.9872943162918091,
+      "learning_rate": 0.0001989929773419902,
+      "loss": 3.1314294815063475,
+      "step": 50
+    },
+    {
+      "epoch": 0.023818975784041286,
+      "grad_norm": 0.8298355937004089,
+      "learning_rate": 0.00019872797137935604,
+      "loss": 3.24124755859375,
+      "step": 60
+    },
+    {
+      "epoch": 0.027788805081381502,
+      "grad_norm": 0.8308970928192139,
+      "learning_rate": 0.00019846296541672188,
+      "loss": 3.0996198654174805,
+      "step": 70
+    },
+    {
+      "epoch": 0.031758634378721715,
+      "grad_norm": 0.8442180156707764,
+      "learning_rate": 0.0001981979594540877,
+      "loss": 3.0475082397460938,
+      "step": 80
+    },
+    {
+      "epoch": 0.03572846367606193,
+      "grad_norm": 0.9131914377212524,
+      "learning_rate": 0.00019793295349145357,
+      "loss": 3.1756013870239257,
+      "step": 90
+    },
+    {
+      "epoch": 0.03969829297340215,
+      "grad_norm": 0.9973925352096558,
+      "learning_rate": 0.0001976679475288194,
+      "loss": 3.159317398071289,
+      "step": 100
+    },
+    {
+      "epoch": 0.043668122270742356,
+      "grad_norm": 0.9906535148620605,
+      "learning_rate": 0.00019740294156618524,
+      "loss": 3.086680603027344,
+      "step": 110
+    },
+    {
+      "epoch": 0.04763795156808257,
+      "grad_norm": 0.8675328493118286,
+      "learning_rate": 0.0001971379356035511,
+      "loss": 3.0809303283691407,
+      "step": 120
+    },
+    {
+      "epoch": 0.05160778086542279,
+      "grad_norm": 1.2756576538085938,
+      "learning_rate": 0.00019687292964091694,
+      "loss": 2.965633010864258,
+      "step": 130
+    },
+    {
+      "epoch": 0.055577610162763004,
+      "grad_norm": 0.8540228605270386,
+      "learning_rate": 0.00019660792367828277,
+      "loss": 3.11167049407959,
+      "step": 140
+    },
+    {
+      "epoch": 0.05954743946010321,
+      "grad_norm": 0.8471305966377258,
+      "learning_rate": 0.0001963429177156486,
+      "loss": 2.9493082046508787,
+      "step": 150
+    },
+    {
+      "epoch": 0.06351726875744343,
+      "grad_norm": 1.0690556764602661,
+      "learning_rate": 0.00019607791175301444,
+      "loss": 3.1130550384521483,
+      "step": 160
+    },
+    {
+      "epoch": 0.06748709805478365,
+      "grad_norm": 0.9682918787002563,
+      "learning_rate": 0.0001958129057903803,
+      "loss": 3.041396713256836,
+      "step": 170
+    },
+    {
+      "epoch": 0.07145692735212386,
+      "grad_norm": 0.9328762292861938,
+      "learning_rate": 0.00019554789982774613,
+      "loss": 3.1088594436645507,
+      "step": 180
+    },
+    {
+      "epoch": 0.07542675664946408,
+      "grad_norm": 0.981307327747345,
+      "learning_rate": 0.000195282893865112,
+      "loss": 3.1146469116210938,
+      "step": 190
+    },
+    {
+      "epoch": 0.0793965859468043,
+      "grad_norm": 1.0752034187316895,
+      "learning_rate": 0.00019501788790247783,
+      "loss": 3.0602563858032226,
+      "step": 200
+    },
+    {
+      "epoch": 0.0833664152441445,
+      "grad_norm": 0.8543508052825928,
+      "learning_rate": 0.00019475288193984363,
+      "loss": 2.989186477661133,
+      "step": 210
+    },
+    {
+      "epoch": 0.08733624454148471,
+      "grad_norm": 0.9234327077865601,
+      "learning_rate": 0.0001944878759772095,
+      "loss": 3.0583696365356445,
+      "step": 220
+    },
+    {
+      "epoch": 0.09130607383882493,
+      "grad_norm": 0.8820871710777283,
+      "learning_rate": 0.00019422287001457533,
+      "loss": 2.868353271484375,
+      "step": 230
+    },
+    {
+      "epoch": 0.09527590313616514,
+      "grad_norm": 0.9947519898414612,
+      "learning_rate": 0.0001939578640519412,
+      "loss": 3.110881042480469,
+      "step": 240
+    },
+    {
+      "epoch": 0.09924573243350536,
+      "grad_norm": 0.8357694745063782,
+      "learning_rate": 0.00019369285808930702,
+      "loss": 3.01332950592041,
+      "step": 250
+    },
+    {
+      "epoch": 0.10321556173084558,
+      "grad_norm": 0.9128127694129944,
+      "learning_rate": 0.00019342785212667288,
+      "loss": 3.149305725097656,
+      "step": 260
+    },
+    {
+      "epoch": 0.10718539102818579,
+      "grad_norm": 0.9448281526565552,
+      "learning_rate": 0.0001931628461640387,
+      "loss": 3.172308921813965,
+      "step": 270
+    },
+    {
+      "epoch": 0.11115522032552601,
+      "grad_norm": 1.0875459909439087,
+      "learning_rate": 0.00019289784020140452,
+      "loss": 3.1815589904785155,
+      "step": 280
+    },
+    {
+      "epoch": 0.11512504962286621,
+      "grad_norm": 0.9254504442214966,
+      "learning_rate": 0.00019263283423877038,
+      "loss": 3.1059280395507813,
+      "step": 290
+    },
+    {
+      "epoch": 0.11909487892020643,
+      "grad_norm": 0.9273567795753479,
+      "learning_rate": 0.00019236782827613622,
+      "loss": 3.063690757751465,
+      "step": 300
+    },
+    {
+      "epoch": 0.12306470821754664,
+      "grad_norm": 0.9300341010093689,
+      "learning_rate": 0.00019210282231350208,
+      "loss": 2.989412307739258,
+      "step": 310
+    },
+    {
+      "epoch": 0.12703453751488686,
+      "grad_norm": 1.092647910118103,
+      "learning_rate": 0.0001918378163508679,
+      "loss": 2.9342714309692384,
+      "step": 320
+    },
+    {
+      "epoch": 0.13100436681222707,
+      "grad_norm": 0.7696720361709595,
+      "learning_rate": 0.00019157281038823375,
+      "loss": 2.966893768310547,
+      "step": 330
+    },
+    {
+      "epoch": 0.1349741961095673,
+      "grad_norm": 0.9847505688667297,
+      "learning_rate": 0.00019130780442559958,
+      "loss": 3.054021644592285,
+      "step": 340
+    },
+    {
+      "epoch": 0.1389440254069075,
+      "grad_norm": 1.0354719161987305,
+      "learning_rate": 0.00019104279846296541,
+      "loss": 2.9900562286376955,
+      "step": 350
+    },
+    {
+      "epoch": 0.14291385470424772,
+      "grad_norm": 0.8888474106788635,
+      "learning_rate": 0.00019077779250033128,
+      "loss": 3.1933818817138673,
+      "step": 360
+    },
+    {
+      "epoch": 0.14688368400158794,
+      "grad_norm": 1.0046141147613525,
+      "learning_rate": 0.0001905127865376971,
+      "loss": 2.920476722717285,
+      "step": 370
+    },
+    {
+      "epoch": 0.15085351329892815,
+      "grad_norm": 1.039939522743225,
+      "learning_rate": 0.00019024778057506294,
+      "loss": 3.1360284805297853,
+      "step": 380
+    },
+    {
+      "epoch": 0.15482334259626837,
+      "grad_norm": 0.9551829099655151,
+      "learning_rate": 0.0001899827746124288,
+      "loss": 3.144388198852539,
+      "step": 390
+    },
+    {
+      "epoch": 0.1587931718936086,
+      "grad_norm": 0.9663012027740479,
+      "learning_rate": 0.00018971776864979464,
+      "loss": 2.9875814437866213,
+      "step": 400
+    },
+    {
+      "epoch": 0.1627630011909488,
+      "grad_norm": 0.9962781071662903,
+      "learning_rate": 0.00018945276268716047,
+      "loss": 3.0062061309814454,
+      "step": 410
+    },
+    {
+      "epoch": 0.166732830488289,
+      "grad_norm": 1.001230001449585,
+      "learning_rate": 0.0001891877567245263,
+      "loss": 3.0834712982177734,
+      "step": 420
+    },
+    {
+      "epoch": 0.1707026597856292,
+      "grad_norm": 0.9189774990081787,
+      "learning_rate": 0.00018892275076189214,
+      "loss": 2.885240936279297,
+      "step": 430
+    },
+    {
+      "epoch": 0.17467248908296942,
+      "grad_norm": 1.0268958806991577,
+      "learning_rate": 0.000188657744799258,
+      "loss": 3.1581113815307615,
+      "step": 440
+    },
+    {
+      "epoch": 0.17864231838030964,
+      "grad_norm": 0.9994209408760071,
+      "learning_rate": 0.00018839273883662383,
+      "loss": 2.8793590545654295,
+      "step": 450
+    },
+    {
+      "epoch": 0.18261214767764986,
+      "grad_norm": 1.0613411664962769,
+      "learning_rate": 0.0001881277328739897,
+      "loss": 3.029997444152832,
+      "step": 460
+    },
+    {
+      "epoch": 0.18658197697499007,
+      "grad_norm": 1.0501508712768555,
+      "learning_rate": 0.0001878627269113555,
+      "loss": 3.150674819946289,
+      "step": 470
+    },
+    {
+      "epoch": 0.1905518062723303,
+      "grad_norm": 1.0706281661987305,
+      "learning_rate": 0.00018759772094872134,
+      "loss": 3.0236751556396486,
+      "step": 480
+    },
+    {
+      "epoch": 0.1945216355696705,
+      "grad_norm": 0.856622040271759,
+      "learning_rate": 0.0001873327149860872,
+      "loss": 2.9095502853393556,
+      "step": 490
+    },
+    {
+      "epoch": 0.19849146486701072,
+      "grad_norm": 0.9528838396072388,
+      "learning_rate": 0.00018706770902345303,
+      "loss": 3.001302146911621,
+      "step": 500
+    },
+    {
+      "epoch": 0.20246129416435094,
+      "grad_norm": 1.0344288349151611,
+      "learning_rate": 0.0001868027030608189,
+      "loss": 3.106768035888672,
+      "step": 510
+    },
+    {
+      "epoch": 0.20643112346169115,
+      "grad_norm": 0.9366422891616821,
+      "learning_rate": 0.00018653769709818473,
+      "loss": 2.99255428314209,
+      "step": 520
+    },
+    {
+      "epoch": 0.21040095275903137,
+      "grad_norm": 0.9982316493988037,
+      "learning_rate": 0.00018627269113555056,
+      "loss": 2.904929351806641,
+      "step": 530
+    },
+    {
+      "epoch": 0.21437078205637158,
+      "grad_norm": 1.0310651063919067,
+      "learning_rate": 0.0001860076851729164,
+      "loss": 3.076841926574707,
+      "step": 540
+    },
+    {
+      "epoch": 0.2183406113537118,
+      "grad_norm": 1.015830397605896,
+      "learning_rate": 0.00018574267921028223,
+      "loss": 2.995553398132324,
+      "step": 550
+    },
+    {
+      "epoch": 0.22231044065105202,
+      "grad_norm": 0.9116207957267761,
+      "learning_rate": 0.0001854776732476481,
+      "loss": 3.0907325744628906,
+      "step": 560
+    },
+    {
+      "epoch": 0.22628026994839223,
+      "grad_norm": 0.983268141746521,
+      "learning_rate": 0.00018521266728501392,
+      "loss": 2.9128732681274414,
+      "step": 570
+    },
+    {
+      "epoch": 0.23025009924573242,
+      "grad_norm": 1.0083118677139282,
+      "learning_rate": 0.00018494766132237978,
+      "loss": 3.06164665222168,
+      "step": 580
+    },
+    {
+      "epoch": 0.23421992854307264,
+      "grad_norm": 0.9371793270111084,
+      "learning_rate": 0.00018468265535974562,
+      "loss": 3.110069465637207,
+      "step": 590
+    },
+    {
+      "epoch": 0.23818975784041285,
+      "grad_norm": 0.8907871842384338,
+      "learning_rate": 0.00018441764939711142,
+      "loss": 2.9918779373168944,
+      "step": 600
+    },
+    {
+      "epoch": 0.24215958713775307,
+      "grad_norm": 1.2298108339309692,
+      "learning_rate": 0.00018415264343447728,
+      "loss": 2.995768737792969,
+      "step": 610
+    },
+    {
+      "epoch": 0.24612941643509328,
+      "grad_norm": 1.1198155879974365,
+      "learning_rate": 0.00018388763747184312,
+      "loss": 2.905741500854492,
+      "step": 620
+    },
+    {
+      "epoch": 0.25009924573243353,
+      "grad_norm": 0.9270941019058228,
+      "learning_rate": 0.00018362263150920898,
+      "loss": 3.0602294921875,
+      "step": 630
+    },
+    {
+      "epoch": 0.2540690750297737,
+      "grad_norm": 0.907201886177063,
+      "learning_rate": 0.0001833576255465748,
+      "loss": 3.0065471649169924,
+      "step": 640
+    },
+    {
+      "epoch": 0.25803890432711396,
+      "grad_norm": 1.0519545078277588,
+      "learning_rate": 0.00018309261958394065,
+      "loss": 3.029597282409668,
+      "step": 650
+    },
+    {
+      "epoch": 0.26200873362445415,
+      "grad_norm": 0.8725332617759705,
+      "learning_rate": 0.00018282761362130648,
+      "loss": 2.8936578750610353,
+      "step": 660
+    },
+    {
+      "epoch": 0.26597856292179434,
+      "grad_norm": 1.040444254875183,
+      "learning_rate": 0.0001825626076586723,
+      "loss": 3.081193542480469,
+      "step": 670
+    },
+    {
+      "epoch": 0.2699483922191346,
+      "grad_norm": 0.9259696006774902,
+      "learning_rate": 0.00018229760169603817,
+      "loss": 2.9740297317504885,
+      "step": 680
+    },
+    {
+      "epoch": 0.27391822151647477,
+      "grad_norm": 1.0812491178512573,
+      "learning_rate": 0.000182032595733404,
+      "loss": 3.0157501220703127,
+      "step": 690
+    },
+    {
+      "epoch": 0.277888050813815,
+      "grad_norm": 1.0642049312591553,
+      "learning_rate": 0.00018176758977076984,
+      "loss": 2.996814727783203,
+      "step": 700
+    },
+    {
+      "epoch": 0.2818578801111552,
+      "grad_norm": 1.0878177881240845,
+      "learning_rate": 0.0001815025838081357,
+      "loss": 3.0396562576293946,
+      "step": 710
+    },
+    {
+      "epoch": 0.28582770940849545,
+      "grad_norm": 0.8735718131065369,
+      "learning_rate": 0.00018123757784550154,
+      "loss": 2.8770545959472655,
+      "step": 720
+    },
+    {
+      "epoch": 0.28979753870583563,
+      "grad_norm": 0.9658878445625305,
+      "learning_rate": 0.00018097257188286737,
+      "loss": 3.050862121582031,
+      "step": 730
+    },
+    {
+      "epoch": 0.2937673680031759,
+      "grad_norm": 0.958960771560669,
+      "learning_rate": 0.0001807075659202332,
+      "loss": 3.0131216049194336,
+      "step": 740
+    },
+    {
+      "epoch": 0.29773719730051607,
+      "grad_norm": 1.0989668369293213,
+      "learning_rate": 0.00018044255995759904,
+      "loss": 3.0553775787353517,
+      "step": 750
+    },
+    {
+      "epoch": 0.3017070265978563,
+      "grad_norm": 0.9090871214866638,
+      "learning_rate": 0.0001801775539949649,
+      "loss": 2.9768255233764647,
+      "step": 760
+    },
+    {
+      "epoch": 0.3056768558951965,
+      "grad_norm": 0.9842050671577454,
+      "learning_rate": 0.00017991254803233073,
+      "loss": 3.028487205505371,
+      "step": 770
+    },
+    {
+      "epoch": 0.30964668519253674,
+      "grad_norm": 1.1661285161972046,
+      "learning_rate": 0.0001796475420696966,
+      "loss": 2.9407962799072265,
+      "step": 780
+    },
+    {
+      "epoch": 0.31361651448987693,
+      "grad_norm": 1.0115314722061157,
+      "learning_rate": 0.00017938253610706243,
+      "loss": 3.02266845703125,
+      "step": 790
+    },
+    {
+      "epoch": 0.3175863437872172,
+      "grad_norm": 1.1729583740234375,
+      "learning_rate": 0.00017911753014442823,
+      "loss": 2.9814245223999025,
+      "step": 800
+    },
+    {
+      "epoch": 0.32155617308455736,
+      "grad_norm": 0.9609226584434509,
+      "learning_rate": 0.0001788525241817941,
+      "loss": 2.8289106369018553,
+      "step": 810
+    },
+    {
+      "epoch": 0.3255260023818976,
+      "grad_norm": 1.339521050453186,
+      "learning_rate": 0.00017858751821915993,
+      "loss": 3.0263460159301756,
+      "step": 820
+    },
+    {
+      "epoch": 0.3294958316792378,
+      "grad_norm": 0.8593433499336243,
+      "learning_rate": 0.0001783225122565258,
+      "loss": 3.0060649871826173,
+      "step": 830
+    },
+    {
+      "epoch": 0.333465660976578,
+      "grad_norm": 1.0417287349700928,
+      "learning_rate": 0.00017805750629389162,
+      "loss": 3.0265331268310547,
+      "step": 840
+    },
+    {
+      "epoch": 0.3374354902739182,
+      "grad_norm": 1.1134616136550903,
+      "learning_rate": 0.00017779250033125748,
+      "loss": 3.057025146484375,
+      "step": 850
+    },
+    {
+      "epoch": 0.3414053195712584,
+      "grad_norm": 1.0823781490325928,
+      "learning_rate": 0.0001775274943686233,
+      "loss": 3.0840169906616213,
+      "step": 860
+    },
+    {
+      "epoch": 0.34537514886859866,
+      "grad_norm": 1.304033637046814,
+      "learning_rate": 0.00017726248840598913,
+      "loss": 2.9510980606079102,
+      "step": 870
+    },
+    {
+      "epoch": 0.34934497816593885,
+      "grad_norm": 0.9548248052597046,
+      "learning_rate": 0.00017699748244335499,
+      "loss": 3.0062685012817383,
+      "step": 880
+    },
+    {
+      "epoch": 0.3533148074632791,
+      "grad_norm": 0.9844130277633667,
+      "learning_rate": 0.00017673247648072082,
+      "loss": 2.9815792083740233,
+      "step": 890
+    },
+    {
+      "epoch": 0.3572846367606193,
+      "grad_norm": 1.1588873863220215,
+      "learning_rate": 0.00017646747051808668,
+      "loss": 3.143498992919922,
+      "step": 900
+    },
+    {
+      "epoch": 0.3612544660579595,
+      "grad_norm": 0.9818010926246643,
+      "learning_rate": 0.00017620246455545251,
+      "loss": 2.973097229003906,
+      "step": 910
+    },
+    {
+      "epoch": 0.3652242953552997,
+      "grad_norm": 1.0033776760101318,
+      "learning_rate": 0.00017593745859281835,
+      "loss": 3.0639650344848635,
+      "step": 920
+    },
+    {
+      "epoch": 0.36919412465263995,
+      "grad_norm": 1.1256245374679565,
+      "learning_rate": 0.00017567245263018418,
+      "loss": 3.0972034454345705,
+      "step": 930
+    },
+    {
+      "epoch": 0.37316395394998014,
+      "grad_norm": 1.1515825986862183,
+      "learning_rate": 0.00017540744666755002,
+      "loss": 2.954210090637207,
+      "step": 940
+    },
+    {
+      "epoch": 0.3771337832473204,
+      "grad_norm": 1.0679875612258911,
+      "learning_rate": 0.00017514244070491588,
+      "loss": 2.9248802185058596,
+      "step": 950
+    },
+    {
+      "epoch": 0.3811036125446606,
+      "grad_norm": 1.3141388893127441,
+      "learning_rate": 0.0001748774347422817,
+      "loss": 2.9732879638671874,
+      "step": 960
+    },
+    {
+      "epoch": 0.3850734418420008,
+      "grad_norm": 0.9422619938850403,
+      "learning_rate": 0.00017461242877964754,
+      "loss": 2.8527624130249025,
+      "step": 970
+    },
+    {
+      "epoch": 0.389043271139341,
+      "grad_norm": 1.1796400547027588,
+      "learning_rate": 0.0001743474228170134,
+      "loss": 3.081935691833496,
+      "step": 980
+    },
+    {
+      "epoch": 0.3930131004366812,
+      "grad_norm": 0.9901096820831299,
+      "learning_rate": 0.00017408241685437924,
+      "loss": 2.9871950149536133,
+      "step": 990
+    },
+    {
+      "epoch": 0.39698292973402144,
+      "grad_norm": 0.9635742902755737,
+      "learning_rate": 0.00017381741089174507,
+      "loss": 2.909952735900879,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4009527590313616,
+      "grad_norm": 1.094767451286316,
+      "learning_rate": 0.0001735524049291109,
+      "loss": 2.886246681213379,
+      "step": 1010
+    },
+    {
+      "epoch": 0.40492258832870187,
+      "grad_norm": 0.9883092045783997,
+      "learning_rate": 0.00017328739896647674,
+      "loss": 2.941468048095703,
+      "step": 1020
+    },
+    {
+      "epoch": 0.40889241762604206,
+      "grad_norm": 1.082886815071106,
+      "learning_rate": 0.0001730223930038426,
+      "loss": 2.8721885681152344,
+      "step": 1030
+    },
+    {
+      "epoch": 0.4128622469233823,
+      "grad_norm": 0.9654253125190735,
+      "learning_rate": 0.00017275738704120844,
+      "loss": 3.0437408447265626,
+      "step": 1040
+    },
+    {
+      "epoch": 0.4168320762207225,
+      "grad_norm": 0.9620010256767273,
+      "learning_rate": 0.0001724923810785743,
+      "loss": 2.9390357971191405,
+      "step": 1050
+    },
+    {
+      "epoch": 0.42080190551806274,
+      "grad_norm": 1.042639136314392,
+      "learning_rate": 0.0001722273751159401,
+      "loss": 2.928664207458496,
+      "step": 1060
+    },
+    {
+      "epoch": 0.4247717348154029,
+      "grad_norm": 1.1499779224395752,
+      "learning_rate": 0.00017196236915330594,
+      "loss": 2.9631744384765626,
+      "step": 1070
+    },
+    {
+      "epoch": 0.42874156411274317,
+      "grad_norm": 1.0400148630142212,
+      "learning_rate": 0.0001716973631906718,
+      "loss": 2.9788026809692383,
+      "step": 1080
+    },
+    {
+      "epoch": 0.43271139341008336,
+      "grad_norm": 1.0587307214736938,
+      "learning_rate": 0.00017143235722803763,
+      "loss": 2.9872905731201174,
+      "step": 1090
+    },
+    {
+      "epoch": 0.4366812227074236,
+      "grad_norm": 0.9863898158073425,
+      "learning_rate": 0.0001711673512654035,
+      "loss": 2.959150505065918,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4406510520047638,
+      "grad_norm": 1.024854302406311,
+      "learning_rate": 0.00017090234530276933,
+      "loss": 2.906721496582031,
+      "step": 1110
+    },
+    {
+      "epoch": 0.44462088130210403,
+      "grad_norm": 1.2431564331054688,
+      "learning_rate": 0.00017063733934013516,
+      "loss": 2.959243583679199,
+      "step": 1120
+    },
+    {
+      "epoch": 0.4485907105994442,
+      "grad_norm": 1.0118112564086914,
+      "learning_rate": 0.000170372333377501,
+      "loss": 2.837575149536133,
+      "step": 1130
+    },
+    {
+      "epoch": 0.45256053989678446,
+      "grad_norm": 1.1883628368377686,
+      "learning_rate": 0.00017010732741486683,
+      "loss": 3.088572692871094,
+      "step": 1140
+    },
+    {
+      "epoch": 0.45653036919412465,
+      "grad_norm": 0.902087926864624,
+      "learning_rate": 0.0001698423214522327,
+      "loss": 2.870463180541992,
+      "step": 1150
+    },
+    {
+      "epoch": 0.46050019849146484,
+      "grad_norm": 1.1765600442886353,
+      "learning_rate": 0.00016957731548959852,
+      "loss": 2.907725143432617,
+      "step": 1160
+    },
+    {
+      "epoch": 0.4644700277888051,
+      "grad_norm": 0.9849786162376404,
+      "learning_rate": 0.00016931230952696438,
+      "loss": 2.975267791748047,
+      "step": 1170
+    },
+    {
+      "epoch": 0.4684398570861453,
+      "grad_norm": 1.0879027843475342,
+      "learning_rate": 0.00016904730356433022,
+      "loss": 2.9905019760131837,
+      "step": 1180
+    },
+    {
+      "epoch": 0.4724096863834855,
+      "grad_norm": 1.159298300743103,
+      "learning_rate": 0.00016878229760169605,
+      "loss": 2.9706029891967773,
+      "step": 1190
+    },
+    {
+      "epoch": 0.4763795156808257,
+      "grad_norm": 1.0128686428070068,
+      "learning_rate": 0.00016851729163906189,
+      "loss": 2.929449462890625,
+      "step": 1200
+    },
+    {
+      "epoch": 0.48034934497816595,
+      "grad_norm": 1.3239126205444336,
+      "learning_rate": 0.00016825228567642772,
+      "loss": 2.854958343505859,
+      "step": 1210
+    },
+    {
+      "epoch": 0.48431917427550614,
+      "grad_norm": 1.1641817092895508,
+      "learning_rate": 0.00016798727971379358,
+      "loss": 2.8924772262573244,
+      "step": 1220
+    },
+    {
+      "epoch": 0.4882890035728464,
+      "grad_norm": 1.0055742263793945,
+      "learning_rate": 0.00016772227375115941,
+      "loss": 2.9655168533325194,
+      "step": 1230
+    },
+    {
+      "epoch": 0.49225883287018657,
+      "grad_norm": 1.029150128364563,
+      "learning_rate": 0.00016745726778852525,
+      "loss": 2.953019905090332,
+      "step": 1240
+    },
+    {
+      "epoch": 0.4962286621675268,
+      "grad_norm": 1.0731725692749023,
+      "learning_rate": 0.00016719226182589108,
+      "loss": 2.8922054290771486,
+      "step": 1250
+    },
+    {
+      "epoch": 0.5001984914648671,
+      "grad_norm": 1.1343021392822266,
+      "learning_rate": 0.00016692725586325692,
+      "loss": 2.944770622253418,
+      "step": 1260
+    },
+    {
+      "epoch": 0.5041683207622072,
+      "grad_norm": 1.2642573118209839,
+      "learning_rate": 0.00016666224990062278,
+      "loss": 3.03311710357666,
+      "step": 1270
+    },
+    {
+      "epoch": 0.5081381500595474,
+      "grad_norm": 1.0998749732971191,
+      "learning_rate": 0.0001663972439379886,
+      "loss": 2.901491165161133,
+      "step": 1280
+    },
+    {
+      "epoch": 0.5121079793568877,
+      "grad_norm": 1.1051859855651855,
+      "learning_rate": 0.00016613223797535444,
+      "loss": 3.012837600708008,
+      "step": 1290
+    },
+    {
+      "epoch": 0.5160778086542279,
+      "grad_norm": 1.2365621328353882,
+      "learning_rate": 0.0001658672320127203,
+      "loss": 2.9026336669921875,
+      "step": 1300
+    },
+    {
+      "epoch": 0.520047637951568,
+      "grad_norm": 1.0339555740356445,
+      "learning_rate": 0.00016560222605008614,
+      "loss": 2.922551727294922,
+      "step": 1310
+    },
+    {
+      "epoch": 0.5240174672489083,
+      "grad_norm": 1.0754799842834473,
+      "learning_rate": 0.00016533722008745197,
+      "loss": 3.07440071105957,
+      "step": 1320
+    },
+    {
+      "epoch": 0.5279872965462485,
+      "grad_norm": 0.9746431708335876,
+      "learning_rate": 0.0001650722141248178,
+      "loss": 3.0004465103149416,
+      "step": 1330
+    },
+    {
+      "epoch": 0.5319571258435887,
+      "grad_norm": 1.1726387739181519,
+      "learning_rate": 0.00016480720816218364,
+      "loss": 2.94736270904541,
+      "step": 1340
+    },
+    {
+      "epoch": 0.5359269551409289,
+      "grad_norm": 1.149013638496399,
+      "learning_rate": 0.0001645422021995495,
+      "loss": 2.9215377807617187,
+      "step": 1350
+    },
+    {
+      "epoch": 0.5398967844382692,
+      "grad_norm": 1.0117363929748535,
+      "learning_rate": 0.00016427719623691533,
+      "loss": 2.914345932006836,
+      "step": 1360
+    },
+    {
+      "epoch": 0.5438666137356094,
+      "grad_norm": 1.356374979019165,
+      "learning_rate": 0.0001640121902742812,
+      "loss": 2.9556610107421877,
+      "step": 1370
+    },
+    {
+      "epoch": 0.5478364430329495,
+      "grad_norm": 1.0233981609344482,
+      "learning_rate": 0.00016374718431164703,
+      "loss": 2.7411882400512697,
+      "step": 1380
+    },
+    {
+      "epoch": 0.5518062723302898,
+      "grad_norm": 0.9782310128211975,
+      "learning_rate": 0.00016348217834901286,
+      "loss": 2.8227493286132814,
+      "step": 1390
+    },
+    {
+      "epoch": 0.55577610162763,
+      "grad_norm": 1.1206411123275757,
+      "learning_rate": 0.0001632171723863787,
+      "loss": 2.9366016387939453,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5597459309249703,
+      "grad_norm": 1.059769868850708,
+      "learning_rate": 0.00016295216642374453,
+      "loss": 2.877486228942871,
+      "step": 1410
+    },
+    {
+      "epoch": 0.5637157602223104,
+      "grad_norm": 1.1128787994384766,
+      "learning_rate": 0.0001626871604611104,
+      "loss": 2.9680269241333006,
+      "step": 1420
+    },
+    {
+      "epoch": 0.5676855895196506,
+      "grad_norm": 1.0075215101242065,
+      "learning_rate": 0.00016242215449847623,
+      "loss": 2.9732336044311523,
+      "step": 1430
+    },
+    {
+      "epoch": 0.5716554188169909,
+      "grad_norm": 1.111331820487976,
+      "learning_rate": 0.00016215714853584209,
+      "loss": 2.8879764556884764,
+      "step": 1440
+    },
+    {
+      "epoch": 0.5756252481143311,
+      "grad_norm": 0.9936279654502869,
+      "learning_rate": 0.0001618921425732079,
+      "loss": 2.8723777770996093,
+      "step": 1450
+    },
+    {
+      "epoch": 0.5795950774116713,
+      "grad_norm": 1.0727992057800293,
+      "learning_rate": 0.00016162713661057373,
+      "loss": 2.7799137115478514,
+      "step": 1460
+    },
+    {
+      "epoch": 0.5835649067090115,
+      "grad_norm": 1.067679762840271,
+      "learning_rate": 0.0001613621306479396,
+      "loss": 2.932950019836426,
+      "step": 1470
+    },
+    {
+      "epoch": 0.5875347360063518,
+      "grad_norm": 1.2709579467773438,
+      "learning_rate": 0.00016109712468530542,
+      "loss": 3.027512550354004,
+      "step": 1480
+    },
+    {
+      "epoch": 0.5915045653036919,
+      "grad_norm": 1.0046635866165161,
+      "learning_rate": 0.00016083211872267128,
+      "loss": 2.834365463256836,
+      "step": 1490
+    },
+    {
+      "epoch": 0.5954743946010321,
+      "grad_norm": 1.0839996337890625,
+      "learning_rate": 0.00016056711276003712,
+      "loss": 2.955361747741699,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5994442238983724,
+      "grad_norm": 1.0332610607147217,
+      "learning_rate": 0.00016030210679740295,
+      "loss": 2.892449378967285,
+      "step": 1510
+    },
+    {
+      "epoch": 0.6034140531957126,
+      "grad_norm": 1.1940085887908936,
+      "learning_rate": 0.00016003710083476878,
+      "loss": 3.0406375885009767,
+      "step": 1520
+    },
+    {
+      "epoch": 0.6073838824930528,
+      "grad_norm": 1.4349676370620728,
+      "learning_rate": 0.00015977209487213462,
+      "loss": 2.868655204772949,
+      "step": 1530
+    },
+    {
+      "epoch": 0.611353711790393,
+      "grad_norm": 0.98362797498703,
+      "learning_rate": 0.00015950708890950048,
+      "loss": 3.0159059524536134,
+      "step": 1540
+    },
+    {
+      "epoch": 0.6153235410877332,
+      "grad_norm": 1.1385223865509033,
+      "learning_rate": 0.0001592420829468663,
+      "loss": 2.9185848236083984,
+      "step": 1550
+    },
+    {
+      "epoch": 0.6192933703850735,
+      "grad_norm": 1.0622061491012573,
+      "learning_rate": 0.00015897707698423215,
+      "loss": 2.963969612121582,
+      "step": 1560
+    },
+    {
+      "epoch": 0.6232631996824136,
+      "grad_norm": 1.1907509565353394,
+      "learning_rate": 0.000158712071021598,
+      "loss": 3.0108991622924806,
+      "step": 1570
+    },
+    {
+      "epoch": 0.6272330289797539,
+      "grad_norm": 1.0997110605239868,
+      "learning_rate": 0.00015844706505896384,
+      "loss": 2.965668869018555,
+      "step": 1580
+    },
+    {
+      "epoch": 0.6312028582770941,
+      "grad_norm": 1.212643027305603,
+      "learning_rate": 0.00015818205909632967,
+      "loss": 2.953110694885254,
+      "step": 1590
+    },
+    {
+      "epoch": 0.6351726875744343,
+      "grad_norm": 1.0768868923187256,
+      "learning_rate": 0.0001579170531336955,
+      "loss": 3.17305850982666,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6391425168717745,
+      "grad_norm": 1.4662688970565796,
+      "learning_rate": 0.00015765204717106134,
+      "loss": 2.972339057922363,
+      "step": 1610
+    },
+    {
+      "epoch": 0.6431123461691147,
+      "grad_norm": 1.34614896774292,
+      "learning_rate": 0.0001573870412084272,
+      "loss": 2.957012176513672,
+      "step": 1620
+    },
+    {
+      "epoch": 0.647082175466455,
+      "grad_norm": 1.0535542964935303,
+      "learning_rate": 0.00015712203524579304,
+      "loss": 3.014488410949707,
+      "step": 1630
+    },
+    {
+      "epoch": 0.6510520047637952,
+      "grad_norm": 1.0424102544784546,
+      "learning_rate": 0.0001568570292831589,
+      "loss": 2.882272720336914,
+      "step": 1640
+    },
+    {
+      "epoch": 0.6550218340611353,
+      "grad_norm": 1.021438717842102,
+      "learning_rate": 0.0001565920233205247,
+      "loss": 3.1003211975097655,
+      "step": 1650
+    },
+    {
+      "epoch": 0.6589916633584756,
+      "grad_norm": 1.237534761428833,
+      "learning_rate": 0.00015632701735789057,
+      "loss": 2.9361820220947266,
+      "step": 1660
+    },
+    {
+      "epoch": 0.6629614926558158,
+      "grad_norm": 1.1335283517837524,
+      "learning_rate": 0.0001560620113952564,
+      "loss": 2.932353401184082,
+      "step": 1670
+    },
+    {
+      "epoch": 0.666931321953156,
+      "grad_norm": 1.2225456237792969,
+      "learning_rate": 0.00015579700543262223,
+      "loss": 2.871927833557129,
+      "step": 1680
+    },
+    {
+      "epoch": 0.6709011512504962,
+      "grad_norm": 1.6691526174545288,
+      "learning_rate": 0.0001555319994699881,
+      "loss": 2.9645782470703126,
+      "step": 1690
+    },
+    {
+      "epoch": 0.6748709805478365,
+      "grad_norm": 0.9732962250709534,
+      "learning_rate": 0.00015526699350735393,
+      "loss": 2.8384857177734375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6788408098451767,
+      "grad_norm": 0.9814636707305908,
+      "learning_rate": 0.00015500198754471976,
+      "loss": 2.9634319305419923,
+      "step": 1710
+    },
+    {
+      "epoch": 0.6828106391425168,
+      "grad_norm": 1.2787647247314453,
+      "learning_rate": 0.0001547369815820856,
+      "loss": 2.973423957824707,
+      "step": 1720
+    },
+    {
+      "epoch": 0.6867804684398571,
+      "grad_norm": 1.2211189270019531,
+      "learning_rate": 0.00015447197561945143,
+      "loss": 3.0307428359985353,
+      "step": 1730
+    },
+    {
+      "epoch": 0.6907502977371973,
+      "grad_norm": 1.0328019857406616,
+      "learning_rate": 0.0001542069696568173,
+      "loss": 2.8718870162963865,
+      "step": 1740
+    },
+    {
+      "epoch": 0.6947201270345376,
+      "grad_norm": 1.0765776634216309,
+      "learning_rate": 0.00015394196369418312,
+      "loss": 3.050098991394043,
+      "step": 1750
+    },
+    {
+      "epoch": 0.6986899563318777,
+      "grad_norm": 1.0749907493591309,
+      "learning_rate": 0.00015367695773154899,
+      "loss": 3.0334381103515624,
+      "step": 1760
+    },
+    {
+      "epoch": 0.7026597856292179,
+      "grad_norm": 1.123230218887329,
+      "learning_rate": 0.00015341195176891482,
+      "loss": 2.948457717895508,
+      "step": 1770
+    },
+    {
+      "epoch": 0.7066296149265582,
+      "grad_norm": 1.2905099391937256,
+      "learning_rate": 0.00015314694580628065,
+      "loss": 2.968699264526367,
+      "step": 1780
+    },
+    {
+      "epoch": 0.7105994442238984,
+      "grad_norm": 1.1446195840835571,
+      "learning_rate": 0.0001528819398436465,
+      "loss": 2.848519706726074,
+      "step": 1790
+    },
+    {
+      "epoch": 0.7145692735212386,
+      "grad_norm": 1.073853611946106,
+      "learning_rate": 0.00015261693388101232,
+      "loss": 2.9441722869873046,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7185391028185788,
+      "grad_norm": 1.2332338094711304,
+      "learning_rate": 0.00015235192791837818,
+      "loss": 2.9227483749389647,
+      "step": 1810
+    },
+    {
+      "epoch": 0.722508932115919,
+      "grad_norm": 1.0547096729278564,
+      "learning_rate": 0.00015208692195574402,
+      "loss": 3.0400369644165037,
+      "step": 1820
+    },
+    {
+      "epoch": 0.7264787614132592,
+      "grad_norm": 1.2107875347137451,
+      "learning_rate": 0.00015182191599310985,
+      "loss": 2.932765007019043,
+      "step": 1830
+    },
+    {
+      "epoch": 0.7304485907105994,
+      "grad_norm": 1.1923927068710327,
+      "learning_rate": 0.00015155691003047568,
+      "loss": 2.8786020278930664,
+      "step": 1840
+    },
+    {
+      "epoch": 0.7344184200079397,
+      "grad_norm": 1.3000658750534058,
+      "learning_rate": 0.00015129190406784152,
+      "loss": 3.0670289993286133,
+      "step": 1850
+    },
+    {
+      "epoch": 0.7383882493052799,
+      "grad_norm": 1.079545259475708,
+      "learning_rate": 0.00015102689810520738,
+      "loss": 2.9120521545410156,
+      "step": 1860
+    },
+    {
+      "epoch": 0.74235807860262,
+      "grad_norm": 1.164806604385376,
+      "learning_rate": 0.0001507618921425732,
+      "loss": 3.098134422302246,
+      "step": 1870
+    },
+    {
+      "epoch": 0.7463279078999603,
+      "grad_norm": 1.0587846040725708,
+      "learning_rate": 0.00015049688617993905,
+      "loss": 2.889917182922363,
+      "step": 1880
+    },
+    {
+      "epoch": 0.7502977371973005,
+      "grad_norm": 1.6976264715194702,
+      "learning_rate": 0.0001502318802173049,
+      "loss": 2.9458736419677733,
+      "step": 1890
+    },
+    {
+      "epoch": 0.7542675664946408,
+      "grad_norm": 1.0733898878097534,
+      "learning_rate": 0.00014996687425467074,
+      "loss": 2.872547912597656,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7582373957919809,
+      "grad_norm": 1.560863971710205,
+      "learning_rate": 0.00014970186829203657,
+      "loss": 2.8400611877441406,
+      "step": 1910
+    },
+    {
+      "epoch": 0.7622072250893211,
+      "grad_norm": 1.3527973890304565,
+      "learning_rate": 0.0001494368623294024,
+      "loss": 2.9421205520629883,
+      "step": 1920
+    },
+    {
+      "epoch": 0.7661770543866614,
+      "grad_norm": 1.0963633060455322,
+      "learning_rate": 0.00014917185636676827,
+      "loss": 2.890008544921875,
+      "step": 1930
+    },
+    {
+      "epoch": 0.7701468836840016,
+      "grad_norm": 0.93892902135849,
+      "learning_rate": 0.0001489068504041341,
+      "loss": 2.8861242294311524,
+      "step": 1940
+    },
+    {
+      "epoch": 0.7741167129813418,
+      "grad_norm": 1.233338713645935,
+      "learning_rate": 0.00014864184444149994,
+      "loss": 2.9477554321289063,
+      "step": 1950
+    },
+    {
+      "epoch": 0.778086542278682,
+      "grad_norm": 1.2628257274627686,
+      "learning_rate": 0.0001483768384788658,
+      "loss": 2.8417577743530273,
+      "step": 1960
+    },
+    {
+      "epoch": 0.7820563715760223,
+      "grad_norm": 1.0811272859573364,
+      "learning_rate": 0.00014811183251623163,
+      "loss": 2.887801933288574,
+      "step": 1970
+    },
+    {
+      "epoch": 0.7860262008733624,
+      "grad_norm": 1.088047981262207,
+      "learning_rate": 0.00014784682655359746,
+      "loss": 3.039769744873047,
+      "step": 1980
+    },
+    {
+      "epoch": 0.7899960301707026,
+      "grad_norm": 1.2557246685028076,
+      "learning_rate": 0.0001475818205909633,
+      "loss": 2.9063520431518555,
+      "step": 1990
+    },
+    {
+      "epoch": 0.7939658594680429,
+      "grad_norm": 1.131279706954956,
+      "learning_rate": 0.00014731681462832913,
+      "loss": 2.995278549194336,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7979356887653831,
+      "grad_norm": 1.127064824104309,
+      "learning_rate": 0.0001470783092619584,
+      "loss": 2.8959430694580077,
+      "step": 2010
+    },
+    {
+      "epoch": 0.8019055180627233,
+      "grad_norm": 1.1206923723220825,
+      "learning_rate": 0.00014681330329932425,
+      "loss": 2.988982009887695,
+      "step": 2020
+    },
+    {
+      "epoch": 0.8058753473600635,
+      "grad_norm": 1.2321375608444214,
+      "learning_rate": 0.00014654829733669008,
+      "loss": 2.886695671081543,
+      "step": 2030
+    },
+    {
+      "epoch": 0.8098451766574037,
+      "grad_norm": 1.0987670421600342,
+      "learning_rate": 0.00014628329137405591,
+      "loss": 2.9366876602172853,
+      "step": 2040
+    },
+    {
+      "epoch": 0.813815005954744,
+      "grad_norm": 1.2729072570800781,
+      "learning_rate": 0.00014601828541142177,
+      "loss": 2.733133316040039,
+      "step": 2050
+    },
+    {
+      "epoch": 0.8177848352520841,
+      "grad_norm": 1.4275444746017456,
+      "learning_rate": 0.0001457532794487876,
+      "loss": 2.9442211151123048,
+      "step": 2060
+    },
+    {
+      "epoch": 0.8217546645494244,
+      "grad_norm": 1.1997590065002441,
+      "learning_rate": 0.00014548827348615344,
+      "loss": 2.8335521697998045,
+      "step": 2070
+    },
+    {
+      "epoch": 0.8257244938467646,
+      "grad_norm": 1.4380601644515991,
+      "learning_rate": 0.0001452232675235193,
+      "loss": 3.0139677047729494,
+      "step": 2080
+    },
+    {
+      "epoch": 0.8296943231441049,
+      "grad_norm": 1.0848125219345093,
+      "learning_rate": 0.0001449582615608851,
+      "loss": 2.9831415176391602,
+      "step": 2090
+    },
+    {
+      "epoch": 0.833664152441445,
+      "grad_norm": 1.0817651748657227,
+      "learning_rate": 0.00014469325559825097,
+      "loss": 3.0775167465209963,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8376339817387852,
+      "grad_norm": 1.1604492664337158,
+      "learning_rate": 0.0001444282496356168,
+      "loss": 2.9208209991455076,
+      "step": 2110
+    },
+    {
+      "epoch": 0.8416038110361255,
+      "grad_norm": 1.03305184841156,
+      "learning_rate": 0.00014416324367298264,
+      "loss": 2.9657546997070314,
+      "step": 2120
+    },
+    {
+      "epoch": 0.8455736403334657,
+      "grad_norm": 1.5073528289794922,
+      "learning_rate": 0.0001438982377103485,
+      "loss": 2.9726272583007813,
+      "step": 2130
+    },
+    {
+      "epoch": 0.8495434696308058,
+      "grad_norm": 1.332560420036316,
+      "learning_rate": 0.00014363323174771433,
+      "loss": 2.933932876586914,
+      "step": 2140
+    },
+    {
+      "epoch": 0.8535132989281461,
+      "grad_norm": 1.1734390258789062,
+      "learning_rate": 0.00014336822578508017,
+      "loss": 2.8562877655029295,
+      "step": 2150
+    },
+    {
+      "epoch": 0.8574831282254863,
+      "grad_norm": 1.1189327239990234,
+      "learning_rate": 0.000143103219822446,
+      "loss": 2.9401512145996094,
+      "step": 2160
+    },
+    {
+      "epoch": 0.8614529575228265,
+      "grad_norm": 1.2062342166900635,
+      "learning_rate": 0.00014283821385981183,
+      "loss": 3.0194915771484374,
+      "step": 2170
+    },
+    {
+      "epoch": 0.8654227868201667,
+      "grad_norm": 1.0934343338012695,
+      "learning_rate": 0.0001425732078971777,
+      "loss": 2.8667329788208007,
+      "step": 2180
+    },
+    {
+      "epoch": 0.869392616117507,
+      "grad_norm": 1.0804356336593628,
+      "learning_rate": 0.00014230820193454353,
+      "loss": 2.8640270233154297,
+      "step": 2190
+    },
+    {
+      "epoch": 0.8733624454148472,
+      "grad_norm": 1.1175063848495483,
+      "learning_rate": 0.0001420431959719094,
+      "loss": 2.998785400390625,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8773322747121873,
+      "grad_norm": 1.038718819618225,
+      "learning_rate": 0.00014177819000927522,
+      "loss": 2.9121694564819336,
+      "step": 2210
+    },
+    {
+      "epoch": 0.8813021040095276,
+      "grad_norm": 1.2699339389801025,
+      "learning_rate": 0.00014151318404664106,
+      "loss": 2.925882339477539,
+      "step": 2220
+    },
+    {
+      "epoch": 0.8852719333068678,
+      "grad_norm": 1.0924122333526611,
+      "learning_rate": 0.0001412481780840069,
+      "loss": 2.883635902404785,
+      "step": 2230
+    },
+    {
+      "epoch": 0.8892417626042081,
+      "grad_norm": 1.1971683502197266,
+      "learning_rate": 0.00014098317212137273,
+      "loss": 2.8960296630859377,
+      "step": 2240
+    },
+    {
+      "epoch": 0.8932115919015482,
+      "grad_norm": 1.0126338005065918,
+      "learning_rate": 0.0001407181661587386,
+      "loss": 2.889109420776367,
+      "step": 2250
+    },
+    {
+      "epoch": 0.8971814211988884,
+      "grad_norm": 1.2543033361434937,
+      "learning_rate": 0.00014045316019610442,
+      "loss": 2.887612724304199,
+      "step": 2260
+    },
+    {
+      "epoch": 0.9011512504962287,
+      "grad_norm": 1.394667387008667,
+      "learning_rate": 0.00014018815423347028,
+      "loss": 2.9344444274902344,
+      "step": 2270
+    },
+    {
+      "epoch": 0.9051210797935689,
+      "grad_norm": 1.413507103919983,
+      "learning_rate": 0.00013992314827083612,
+      "loss": 2.91464900970459,
+      "step": 2280
+    },
+    {
+      "epoch": 0.9090909090909091,
+      "grad_norm": 1.258139729499817,
+      "learning_rate": 0.00013965814230820192,
+      "loss": 2.9243486404418944,
+      "step": 2290
+    },
+    {
+      "epoch": 0.9130607383882493,
+      "grad_norm": 0.8673571348190308,
+      "learning_rate": 0.00013939313634556778,
+      "loss": 2.7983678817749023,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9170305676855895,
+      "grad_norm": 1.285875678062439,
+      "learning_rate": 0.00013912813038293362,
+      "loss": 3.068038558959961,
+      "step": 2310
+    },
+    {
+      "epoch": 0.9210003969829297,
+      "grad_norm": 1.1456619501113892,
+      "learning_rate": 0.00013886312442029948,
+      "loss": 2.982662010192871,
+      "step": 2320
+    },
+    {
+      "epoch": 0.9249702262802699,
+      "grad_norm": 1.028979778289795,
+      "learning_rate": 0.0001385981184576653,
+      "loss": 2.831150245666504,
+      "step": 2330
+    },
+    {
+      "epoch": 0.9289400555776102,
+      "grad_norm": 1.103188157081604,
+      "learning_rate": 0.00013833311249503115,
+      "loss": 2.891666603088379,
+      "step": 2340
+    },
+    {
+      "epoch": 0.9329098848749504,
+      "grad_norm": 1.105437159538269,
+      "learning_rate": 0.00013806810653239698,
+      "loss": 2.8475828170776367,
+      "step": 2350
+    },
+    {
+      "epoch": 0.9368797141722905,
+      "grad_norm": 1.1804033517837524,
+      "learning_rate": 0.0001378031005697628,
+      "loss": 2.9830224990844725,
+      "step": 2360
+    },
+    {
+      "epoch": 0.9408495434696308,
+      "grad_norm": 1.031882405281067,
+      "learning_rate": 0.00013753809460712867,
+      "loss": 2.820730781555176,
+      "step": 2370
+    },
+    {
+      "epoch": 0.944819372766971,
+      "grad_norm": 1.071161150932312,
+      "learning_rate": 0.0001372730886444945,
+      "loss": 2.9033863067626955,
+      "step": 2380
+    },
+    {
+      "epoch": 0.9487892020643113,
+      "grad_norm": 1.1234395503997803,
+      "learning_rate": 0.00013700808268186034,
+      "loss": 2.983052444458008,
+      "step": 2390
+    },
+    {
+      "epoch": 0.9527590313616514,
+      "grad_norm": 1.198830485343933,
+      "learning_rate": 0.0001367430767192262,
+      "loss": 3.0303747177124025,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9567288606589917,
+      "grad_norm": 1.5915600061416626,
+      "learning_rate": 0.00013647807075659204,
+      "loss": 2.9372890472412108,
+      "step": 2410
+    },
+    {
+      "epoch": 0.9606986899563319,
+      "grad_norm": 1.2830276489257812,
+      "learning_rate": 0.00013621306479395787,
+      "loss": 2.769970703125,
+      "step": 2420
+    },
+    {
+      "epoch": 0.9646685192536721,
+      "grad_norm": 1.1718764305114746,
+      "learning_rate": 0.0001359480588313237,
+      "loss": 2.947464942932129,
+      "step": 2430
+    },
+    {
+      "epoch": 0.9686383485510123,
+      "grad_norm": 1.3351068496704102,
+      "learning_rate": 0.00013568305286868954,
+      "loss": 3.0664255142211916,
+      "step": 2440
+    },
+    {
+      "epoch": 0.9726081778483525,
+      "grad_norm": 1.2922847270965576,
+      "learning_rate": 0.0001354180469060554,
+      "loss": 2.882719039916992,
+      "step": 2450
+    },
+    {
+      "epoch": 0.9765780071456928,
+      "grad_norm": 1.3131754398345947,
+      "learning_rate": 0.00013515304094342123,
+      "loss": 2.906990814208984,
+      "step": 2460
+    },
+    {
+      "epoch": 0.9805478364430329,
+      "grad_norm": 1.2137771844863892,
+      "learning_rate": 0.0001348880349807871,
+      "loss": 2.9342098236083984,
+      "step": 2470
+    },
+    {
+      "epoch": 0.9845176657403731,
+      "grad_norm": 1.352759599685669,
+      "learning_rate": 0.0001346230290181529,
+      "loss": 2.8431310653686523,
+      "step": 2480
+    },
+    {
+      "epoch": 0.9884874950377134,
+      "grad_norm": 1.0442841053009033,
+      "learning_rate": 0.00013435802305551873,
+      "loss": 2.929820251464844,
+      "step": 2490
+    },
+    {
+      "epoch": 0.9924573243350536,
+      "grad_norm": 1.130361557006836,
+      "learning_rate": 0.0001340930170928846,
+      "loss": 2.9055503845214843,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9964271536323938,
+      "grad_norm": 1.461983323097229,
+      "learning_rate": 0.00013382801113025043,
+      "loss": 2.9048336029052733,
+      "step": 2510
+    },
+    {
+      "epoch": 1.0003969829297341,
+      "grad_norm": 1.2407251596450806,
+      "learning_rate": 0.0001335630051676163,
+      "loss": 2.888891410827637,
+      "step": 2520
+    },
+    {
+      "epoch": 1.0043668122270741,
+      "grad_norm": 1.3580700159072876,
+      "learning_rate": 0.00013329799920498212,
+      "loss": 2.927655029296875,
+      "step": 2530
+    },
+    {
+      "epoch": 1.0083366415244144,
+      "grad_norm": 1.0742342472076416,
+      "learning_rate": 0.00013303299324234796,
+      "loss": 2.9614290237426757,
+      "step": 2540
+    },
+    {
+      "epoch": 1.0123064708217546,
+      "grad_norm": 1.2635444402694702,
+      "learning_rate": 0.0001327679872797138,
+      "loss": 2.7592201232910156,
+      "step": 2550
+    },
+    {
+      "epoch": 1.0162763001190949,
+      "grad_norm": 1.331705927848816,
+      "learning_rate": 0.00013250298131707962,
+      "loss": 2.8516969680786133,
+      "step": 2560
+    },
+    {
+      "epoch": 1.020246129416435,
+      "grad_norm": 1.1936160326004028,
+      "learning_rate": 0.00013223797535444549,
+      "loss": 3.008740234375,
+      "step": 2570
+    },
+    {
+      "epoch": 1.0242159587137754,
+      "grad_norm": 1.1526603698730469,
+      "learning_rate": 0.00013197296939181132,
+      "loss": 2.7761598587036134,
+      "step": 2580
+    },
+    {
+      "epoch": 1.0281857880111156,
+      "grad_norm": 1.0937445163726807,
+      "learning_rate": 0.00013170796342917718,
+      "loss": 2.8639547348022463,
+      "step": 2590
+    },
+    {
+      "epoch": 1.0321556173084558,
+      "grad_norm": 1.1443973779678345,
+      "learning_rate": 0.00013144295746654301,
+      "loss": 2.841537284851074,
+      "step": 2600
+    },
+    {
+      "epoch": 1.0361254466057959,
+      "grad_norm": 1.246218204498291,
+      "learning_rate": 0.00013117795150390885,
+      "loss": 2.89624137878418,
+      "step": 2610
+    },
+    {
+      "epoch": 1.040095275903136,
+      "grad_norm": 1.2295280694961548,
+      "learning_rate": 0.00013091294554127468,
+      "loss": 2.7112895965576174,
+      "step": 2620
+    },
+    {
+      "epoch": 1.0440651052004764,
+      "grad_norm": 1.1867451667785645,
+      "learning_rate": 0.00013064793957864052,
+      "loss": 2.817560577392578,
+      "step": 2630
+    },
+    {
+      "epoch": 1.0480349344978166,
+      "grad_norm": 1.3577598333358765,
+      "learning_rate": 0.00013038293361600638,
+      "loss": 2.899570846557617,
+      "step": 2640
+    },
+    {
+      "epoch": 1.0520047637951568,
+      "grad_norm": 1.1519272327423096,
+      "learning_rate": 0.0001301179276533722,
+      "loss": 2.899755096435547,
+      "step": 2650
+    },
+    {
+      "epoch": 1.055974593092497,
+      "grad_norm": 1.1014765501022339,
+      "learning_rate": 0.00012985292169073804,
+      "loss": 2.949821662902832,
+      "step": 2660
+    },
+    {
+      "epoch": 1.0599444223898373,
+      "grad_norm": 1.1649622917175293,
+      "learning_rate": 0.0001295879157281039,
+      "loss": 3.0167802810668944,
+      "step": 2670
+    },
+    {
+      "epoch": 1.0639142516871773,
+      "grad_norm": 1.4407117366790771,
+      "learning_rate": 0.0001293229097654697,
+      "loss": 2.934400177001953,
+      "step": 2680
+    },
+    {
+      "epoch": 1.0678840809845176,
+      "grad_norm": 1.1467158794403076,
+      "learning_rate": 0.00012905790380283557,
+      "loss": 2.8859203338623045,
+      "step": 2690
+    },
+    {
+      "epoch": 1.0718539102818578,
+      "grad_norm": 1.1657541990280151,
+      "learning_rate": 0.0001287928978402014,
+      "loss": 2.9197870254516602,
+      "step": 2700
+    },
+    {
+      "epoch": 1.075823739579198,
+      "grad_norm": 1.137046217918396,
+      "learning_rate": 0.00012852789187756724,
+      "loss": 2.9437820434570314,
+      "step": 2710
+    },
+    {
+      "epoch": 1.0797935688765383,
+      "grad_norm": 1.2877311706542969,
+      "learning_rate": 0.0001282628859149331,
+      "loss": 2.861769104003906,
+      "step": 2720
+    },
+    {
+      "epoch": 1.0837633981738786,
+      "grad_norm": 1.4007761478424072,
+      "learning_rate": 0.00012799787995229893,
+      "loss": 2.888690376281738,
+      "step": 2730
+    },
+    {
+      "epoch": 1.0877332274712188,
+      "grad_norm": 1.1097158193588257,
+      "learning_rate": 0.00012773287398966477,
+      "loss": 2.829306793212891,
+      "step": 2740
+    },
+    {
+      "epoch": 1.091703056768559,
+      "grad_norm": 1.3691431283950806,
+      "learning_rate": 0.0001274678680270306,
+      "loss": 2.900307846069336,
+      "step": 2750
+    },
+    {
+      "epoch": 1.095672886065899,
+      "grad_norm": 1.4336342811584473,
+      "learning_rate": 0.00012720286206439644,
+      "loss": 2.7967662811279297,
+      "step": 2760
+    },
+    {
+      "epoch": 1.0996427153632393,
+      "grad_norm": 1.2973034381866455,
+      "learning_rate": 0.0001269378561017623,
+      "loss": 2.774248504638672,
+      "step": 2770
+    },
+    {
+      "epoch": 1.1036125446605796,
+      "grad_norm": 1.5863878726959229,
+      "learning_rate": 0.00012667285013912813,
+      "loss": 2.7378374099731446,
+      "step": 2780
+    },
+    {
+      "epoch": 1.1075823739579198,
+      "grad_norm": 1.4274410009384155,
+      "learning_rate": 0.000126407844176494,
+      "loss": 3.0109136581420897,
+      "step": 2790
+    },
+    {
+      "epoch": 1.11155220325526,
+      "grad_norm": 1.1030832529067993,
+      "learning_rate": 0.00012614283821385983,
+      "loss": 2.7925899505615233,
+      "step": 2800
+    },
+    {
+      "epoch": 1.1155220325526003,
+      "grad_norm": 1.1131644248962402,
+      "learning_rate": 0.00012587783225122566,
+      "loss": 2.9009119033813477,
+      "step": 2810
+    },
+    {
+      "epoch": 1.1194918618499405,
+      "grad_norm": 1.3609836101531982,
+      "learning_rate": 0.0001256128262885915,
+      "loss": 2.8956506729125975,
+      "step": 2820
+    },
+    {
+      "epoch": 1.1234616911472806,
+      "grad_norm": 1.1545202732086182,
+      "learning_rate": 0.00012534782032595733,
+      "loss": 2.876191520690918,
+      "step": 2830
+    },
+    {
+      "epoch": 1.1274315204446208,
+      "grad_norm": 1.2126272916793823,
+      "learning_rate": 0.0001250828143633232,
+      "loss": 2.7961231231689454,
+      "step": 2840
+    },
+    {
+      "epoch": 1.131401349741961,
+      "grad_norm": 1.1984245777130127,
+      "learning_rate": 0.00012481780840068902,
+      "loss": 2.7959896087646485,
+      "step": 2850
+    },
+    {
+      "epoch": 1.1353711790393013,
+      "grad_norm": 1.2016088962554932,
+      "learning_rate": 0.00012455280243805488,
+      "loss": 2.867430305480957,
+      "step": 2860
+    },
+    {
+      "epoch": 1.1393410083366415,
+      "grad_norm": 1.1378740072250366,
+      "learning_rate": 0.00012428779647542072,
+      "loss": 2.741920280456543,
+      "step": 2870
+    },
+    {
+      "epoch": 1.1433108376339818,
+      "grad_norm": 1.2212181091308594,
+      "learning_rate": 0.00012402279051278652,
+      "loss": 2.7447364807128904,
+      "step": 2880
+    },
+    {
+      "epoch": 1.147280666931322,
+      "grad_norm": 1.0747908353805542,
+      "learning_rate": 0.00012375778455015238,
+      "loss": 2.98239688873291,
+      "step": 2890
+    },
+    {
+      "epoch": 1.1512504962286623,
+      "grad_norm": 1.3732624053955078,
+      "learning_rate": 0.00012349277858751822,
+      "loss": 2.932689094543457,
+      "step": 2900
+    },
+    {
+      "epoch": 1.1552203255260023,
+      "grad_norm": 1.2373459339141846,
+      "learning_rate": 0.00012322777262488408,
+      "loss": 2.8869907379150392,
+      "step": 2910
+    },
+    {
+      "epoch": 1.1591901548233425,
+      "grad_norm": 1.3174314498901367,
+      "learning_rate": 0.0001229627666622499,
+      "loss": 2.9600086212158203,
+      "step": 2920
+    },
+    {
+      "epoch": 1.1631599841206828,
+      "grad_norm": 1.3416168689727783,
+      "learning_rate": 0.00012269776069961575,
+      "loss": 2.840256118774414,
+      "step": 2930
+    },
+    {
+      "epoch": 1.167129813418023,
+      "grad_norm": 1.149091362953186,
+      "learning_rate": 0.00012243275473698158,
+      "loss": 2.807183265686035,
+      "step": 2940
+    },
+    {
+      "epoch": 1.1710996427153633,
+      "grad_norm": 1.1443051099777222,
+      "learning_rate": 0.00012216774877434741,
+      "loss": 2.9720365524291994,
+      "step": 2950
+    },
+    {
+      "epoch": 1.1750694720127035,
+      "grad_norm": 1.3129942417144775,
+      "learning_rate": 0.00012190274281171328,
+      "loss": 2.9757314682006837,
+      "step": 2960
+    },
+    {
+      "epoch": 1.1790393013100438,
+      "grad_norm": 1.098672866821289,
+      "learning_rate": 0.00012163773684907911,
+      "loss": 2.753942680358887,
+      "step": 2970
+    },
+    {
+      "epoch": 1.1830091306073838,
+      "grad_norm": 1.1337664127349854,
+      "learning_rate": 0.00012137273088644494,
+      "loss": 2.827354621887207,
+      "step": 2980
+    },
+    {
+      "epoch": 1.186978959904724,
+      "grad_norm": 1.1231764554977417,
+      "learning_rate": 0.00012110772492381079,
+      "loss": 2.711290740966797,
+      "step": 2990
+    },
+    {
+      "epoch": 1.1909487892020643,
+      "grad_norm": 1.1375696659088135,
+      "learning_rate": 0.00012084271896117662,
+      "loss": 2.904682731628418,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1949186184994045,
+      "grad_norm": 1.1674156188964844,
+      "learning_rate": 0.00012057771299854248,
+      "loss": 2.884379768371582,
+      "step": 3010
+    },
+    {
+      "epoch": 1.1988884477967447,
+      "grad_norm": 1.4644557237625122,
+      "learning_rate": 0.00012031270703590832,
+      "loss": 2.801077461242676,
+      "step": 3020
+    },
+    {
+      "epoch": 1.202858277094085,
+      "grad_norm": 1.285089135169983,
+      "learning_rate": 0.00012004770107327414,
+      "loss": 2.8604631423950195,
+      "step": 3030
+    },
+    {
+      "epoch": 1.2068281063914252,
+      "grad_norm": 1.1116204261779785,
+      "learning_rate": 0.00011978269511064,
+      "loss": 2.8972236633300783,
+      "step": 3040
+    },
+    {
+      "epoch": 1.2107979356887655,
+      "grad_norm": 1.3030141592025757,
+      "learning_rate": 0.00011951768914800583,
+      "loss": 2.8783727645874024,
+      "step": 3050
+    },
+    {
+      "epoch": 1.2147677649861055,
+      "grad_norm": 1.0779145956039429,
+      "learning_rate": 0.00011925268318537168,
+      "loss": 2.85146427154541,
+      "step": 3060
+    },
+    {
+      "epoch": 1.2187375942834457,
+      "grad_norm": 1.7380479574203491,
+      "learning_rate": 0.00011898767722273751,
+      "loss": 2.8459522247314455,
+      "step": 3070
+    },
+    {
+      "epoch": 1.222707423580786,
+      "grad_norm": 1.0546619892120361,
+      "learning_rate": 0.00011872267126010336,
+      "loss": 2.805705451965332,
+      "step": 3080
+    },
+    {
+      "epoch": 1.2266772528781262,
+      "grad_norm": 1.533992052078247,
+      "learning_rate": 0.0001184576652974692,
+      "loss": 2.975359344482422,
+      "step": 3090
+    },
+    {
+      "epoch": 1.2306470821754665,
+      "grad_norm": 1.2582201957702637,
+      "learning_rate": 0.00011819265933483503,
+      "loss": 2.9268173217773437,
+      "step": 3100
+    },
+    {
+      "epoch": 1.2346169114728067,
+      "grad_norm": 1.2494417428970337,
+      "learning_rate": 0.00011792765337220089,
+      "loss": 2.7564210891723633,
+      "step": 3110
+    },
+    {
+      "epoch": 1.238586740770147,
+      "grad_norm": 1.40061354637146,
+      "learning_rate": 0.00011766264740956671,
+      "loss": 2.877336311340332,
+      "step": 3120
+    },
+    {
+      "epoch": 1.242556570067487,
+      "grad_norm": 1.36153244972229,
+      "learning_rate": 0.00011739764144693257,
+      "loss": 2.876156044006348,
+      "step": 3130
+    },
+    {
+      "epoch": 1.2465263993648272,
+      "grad_norm": 1.7986162900924683,
+      "learning_rate": 0.0001171326354842984,
+      "loss": 2.9214223861694335,
+      "step": 3140
+    },
+    {
+      "epoch": 1.2504962286621675,
+      "grad_norm": 1.1867148876190186,
+      "learning_rate": 0.00011686762952166424,
+      "loss": 2.8030139923095705,
+      "step": 3150
+    },
+    {
+      "epoch": 1.2544660579595077,
+      "grad_norm": 1.1623351573944092,
+      "learning_rate": 0.00011660262355903009,
+      "loss": 2.854610633850098,
+      "step": 3160
+    },
+    {
+      "epoch": 1.258435887256848,
+      "grad_norm": 1.1789515018463135,
+      "learning_rate": 0.00011633761759639592,
+      "loss": 2.840734672546387,
+      "step": 3170
+    },
+    {
+      "epoch": 1.2624057165541882,
+      "grad_norm": 1.3448714017868042,
+      "learning_rate": 0.00011607261163376177,
+      "loss": 2.942055511474609,
+      "step": 3180
+    },
+    {
+      "epoch": 1.2663755458515285,
+      "grad_norm": 1.2870416641235352,
+      "learning_rate": 0.0001158076056711276,
+      "loss": 2.928165245056152,
+      "step": 3190
+    },
+    {
+      "epoch": 1.2703453751488687,
+      "grad_norm": 1.1872483491897583,
+      "learning_rate": 0.00011554259970849344,
+      "loss": 2.935594940185547,
+      "step": 3200
+    },
+    {
+      "epoch": 1.274315204446209,
+      "grad_norm": 1.4787572622299194,
+      "learning_rate": 0.0001152775937458593,
+      "loss": 2.8724430084228514,
+      "step": 3210
+    },
+    {
+      "epoch": 1.278285033743549,
+      "grad_norm": 1.4164690971374512,
+      "learning_rate": 0.00011501258778322512,
+      "loss": 2.9088714599609373,
+      "step": 3220
+    },
+    {
+      "epoch": 1.2822548630408892,
+      "grad_norm": 1.1791913509368896,
+      "learning_rate": 0.00011474758182059098,
+      "loss": 2.8589361190795897,
+      "step": 3230
+    },
+    {
+      "epoch": 1.2862246923382294,
+      "grad_norm": 1.3528516292572021,
+      "learning_rate": 0.00011448257585795681,
+      "loss": 2.8930646896362306,
+      "step": 3240
+    },
+    {
+      "epoch": 1.2901945216355697,
+      "grad_norm": 1.3224010467529297,
+      "learning_rate": 0.00011421756989532265,
+      "loss": 2.8452373504638673,
+      "step": 3250
+    },
+    {
+      "epoch": 1.29416435093291,
+      "grad_norm": 1.2920061349868774,
+      "learning_rate": 0.00011395256393268849,
+      "loss": 2.8752540588378905,
+      "step": 3260
+    },
+    {
+      "epoch": 1.2981341802302502,
+      "grad_norm": 1.2639166116714478,
+      "learning_rate": 0.00011368755797005433,
+      "loss": 2.88561954498291,
+      "step": 3270
+    },
+    {
+      "epoch": 1.3021040095275902,
+      "grad_norm": 1.2361299991607666,
+      "learning_rate": 0.00011342255200742017,
+      "loss": 2.9272403717041016,
+      "step": 3280
+    },
+    {
+      "epoch": 1.3060738388249304,
+      "grad_norm": 1.5476930141448975,
+      "learning_rate": 0.00011315754604478601,
+      "loss": 2.994682502746582,
+      "step": 3290
+    },
+    {
+      "epoch": 1.3100436681222707,
+      "grad_norm": 1.3958719968795776,
+      "learning_rate": 0.00011289254008215184,
+      "loss": 2.810057830810547,
+      "step": 3300
+    },
+    {
+      "epoch": 1.314013497419611,
+      "grad_norm": 1.2481234073638916,
+      "learning_rate": 0.0001126275341195177,
+      "loss": 2.8198265075683593,
+      "step": 3310
+    },
+    {
+      "epoch": 1.3179833267169512,
+      "grad_norm": 1.5658928155899048,
+      "learning_rate": 0.00011236252815688352,
+      "loss": 2.9725709915161134,
+      "step": 3320
+    },
+    {
+      "epoch": 1.3219531560142914,
+      "grad_norm": 1.1179542541503906,
+      "learning_rate": 0.00011209752219424938,
+      "loss": 2.855281448364258,
+      "step": 3330
+    },
+    {
+      "epoch": 1.3259229853116317,
+      "grad_norm": 1.2543385028839111,
+      "learning_rate": 0.00011183251623161522,
+      "loss": 2.870030403137207,
+      "step": 3340
+    },
+    {
+      "epoch": 1.329892814608972,
+      "grad_norm": 1.2362663745880127,
+      "learning_rate": 0.00011156751026898106,
+      "loss": 2.867103385925293,
+      "step": 3350
+    },
+    {
+      "epoch": 1.3338626439063122,
+      "grad_norm": 1.5475022792816162,
+      "learning_rate": 0.0001113025043063469,
+      "loss": 3.038361740112305,
+      "step": 3360
+    },
+    {
+      "epoch": 1.3378324732036522,
+      "grad_norm": 1.2643401622772217,
+      "learning_rate": 0.00011103749834371273,
+      "loss": 2.880583381652832,
+      "step": 3370
+    },
+    {
+      "epoch": 1.3418023025009924,
+      "grad_norm": 1.1639227867126465,
+      "learning_rate": 0.00011077249238107858,
+      "loss": 2.7907382965087892,
+      "step": 3380
+    },
+    {
+      "epoch": 1.3457721317983327,
+      "grad_norm": 1.1745330095291138,
+      "learning_rate": 0.00011050748641844441,
+      "loss": 2.7494991302490233,
+      "step": 3390
+    },
+    {
+      "epoch": 1.349741961095673,
+      "grad_norm": 1.2324411869049072,
+      "learning_rate": 0.00011024248045581027,
+      "loss": 2.938181686401367,
+      "step": 3400
+    },
+    {
+      "epoch": 1.3537117903930131,
+      "grad_norm": 1.1418648958206177,
+      "learning_rate": 0.00010997747449317611,
+      "loss": 2.9696788787841797,
+      "step": 3410
+    },
+    {
+      "epoch": 1.3576816196903534,
+      "grad_norm": 1.3676928281784058,
+      "learning_rate": 0.00010971246853054193,
+      "loss": 2.930206298828125,
+      "step": 3420
+    },
+    {
+      "epoch": 1.3616514489876934,
+      "grad_norm": 1.2266117334365845,
+      "learning_rate": 0.00010944746256790779,
+      "loss": 2.9436601638793944,
+      "step": 3430
+    },
+    {
+      "epoch": 1.3656212782850337,
+      "grad_norm": 1.296379566192627,
+      "learning_rate": 0.00010918245660527362,
+      "loss": 2.822721481323242,
+      "step": 3440
+    },
+    {
+      "epoch": 1.369591107582374,
+      "grad_norm": 1.5747238397598267,
+      "learning_rate": 0.00010891745064263947,
+      "loss": 2.7970211029052736,
+      "step": 3450
+    },
+    {
+      "epoch": 1.3735609368797141,
+      "grad_norm": 1.11448335647583,
+      "learning_rate": 0.0001086524446800053,
+      "loss": 2.850177764892578,
+      "step": 3460
+    },
+    {
+      "epoch": 1.3775307661770544,
+      "grad_norm": 1.585570216178894,
+      "learning_rate": 0.00010838743871737114,
+      "loss": 2.7775524139404295,
+      "step": 3470
+    },
+    {
+      "epoch": 1.3815005954743946,
+      "grad_norm": 1.3851438760757446,
+      "learning_rate": 0.00010812243275473699,
+      "loss": 2.841839599609375,
+      "step": 3480
+    },
+    {
+      "epoch": 1.3854704247717349,
+      "grad_norm": 2.0213372707366943,
+      "learning_rate": 0.00010785742679210282,
+      "loss": 2.8476282119750977,
+      "step": 3490
+    },
+    {
+      "epoch": 1.3894402540690751,
+      "grad_norm": 1.1296862363815308,
+      "learning_rate": 0.00010759242082946868,
+      "loss": 2.796487045288086,
+      "step": 3500
+    },
+    {
+      "epoch": 1.3934100833664154,
+      "grad_norm": 1.2621263265609741,
+      "learning_rate": 0.00010732741486683451,
+      "loss": 2.8717994689941406,
+      "step": 3510
+    },
+    {
+      "epoch": 1.3973799126637554,
+      "grad_norm": 1.1782283782958984,
+      "learning_rate": 0.00010706240890420033,
+      "loss": 2.894154167175293,
+      "step": 3520
+    },
+    {
+      "epoch": 1.4013497419610956,
+      "grad_norm": 1.2578155994415283,
+      "learning_rate": 0.0001067974029415662,
+      "loss": 2.699532890319824,
+      "step": 3530
+    },
+    {
+      "epoch": 1.4053195712584359,
+      "grad_norm": 1.1540583372116089,
+      "learning_rate": 0.00010653239697893203,
+      "loss": 2.8674644470214843,
+      "step": 3540
+    },
+    {
+      "epoch": 1.4092894005557761,
+      "grad_norm": 1.5898374319076538,
+      "learning_rate": 0.00010626739101629788,
+      "loss": 2.887256622314453,
+      "step": 3550
+    },
+    {
+      "epoch": 1.4132592298531164,
+      "grad_norm": 1.2546888589859009,
+      "learning_rate": 0.00010600238505366371,
+      "loss": 2.912336730957031,
+      "step": 3560
+    },
+    {
+      "epoch": 1.4172290591504566,
+      "grad_norm": 1.3821418285369873,
+      "learning_rate": 0.00010573737909102954,
+      "loss": 2.7670663833618163,
+      "step": 3570
+    },
+    {
+      "epoch": 1.4211988884477966,
+      "grad_norm": 1.3685969114303589,
+      "learning_rate": 0.00010547237312839539,
+      "loss": 2.8921297073364256,
+      "step": 3580
+    },
+    {
+      "epoch": 1.4251687177451369,
+      "grad_norm": 2.0592007637023926,
+      "learning_rate": 0.00010520736716576123,
+      "loss": 2.8367937088012694,
+      "step": 3590
+    },
+    {
+      "epoch": 1.4291385470424771,
+      "grad_norm": 1.2717535495758057,
+      "learning_rate": 0.00010494236120312709,
+      "loss": 2.8397924423217775,
+      "step": 3600
+    },
+    {
+      "epoch": 1.4331083763398174,
+      "grad_norm": 1.1194345951080322,
+      "learning_rate": 0.00010467735524049292,
+      "loss": 2.8019588470458983,
+      "step": 3610
+    },
+    {
+      "epoch": 1.4370782056371576,
+      "grad_norm": 1.3213400840759277,
+      "learning_rate": 0.00010441234927785877,
+      "loss": 2.8019805908203126,
+      "step": 3620
+    },
+    {
+      "epoch": 1.4410480349344978,
+      "grad_norm": 1.2584818601608276,
+      "learning_rate": 0.0001041473433152246,
+      "loss": 2.9595170974731446,
+      "step": 3630
+    },
+    {
+      "epoch": 1.445017864231838,
+      "grad_norm": 1.346086859703064,
+      "learning_rate": 0.00010388233735259044,
+      "loss": 2.8712783813476563,
+      "step": 3640
+    },
+    {
+      "epoch": 1.4489876935291783,
+      "grad_norm": 1.279360294342041,
+      "learning_rate": 0.00010361733138995628,
+      "loss": 2.8931833267211915,
+      "step": 3650
+    },
+    {
+      "epoch": 1.4529575228265186,
+      "grad_norm": 1.466051459312439,
+      "learning_rate": 0.00010335232542732212,
+      "loss": 2.963275146484375,
+      "step": 3660
+    },
+    {
+      "epoch": 1.4569273521238586,
+      "grad_norm": 1.3183846473693848,
+      "learning_rate": 0.00010308731946468796,
+      "loss": 2.8601329803466795,
+      "step": 3670
+    },
+    {
+      "epoch": 1.4608971814211988,
+      "grad_norm": 2.090052604675293,
+      "learning_rate": 0.0001028223135020538,
+      "loss": 2.9438711166381837,
+      "step": 3680
+    },
+    {
+      "epoch": 1.464867010718539,
+      "grad_norm": 1.3010114431381226,
+      "learning_rate": 0.00010255730753941963,
+      "loss": 2.701998710632324,
+      "step": 3690
+    },
+    {
+      "epoch": 1.4688368400158793,
+      "grad_norm": 1.1416301727294922,
+      "learning_rate": 0.00010229230157678549,
+      "loss": 2.846023178100586,
+      "step": 3700
+    },
+    {
+      "epoch": 1.4728066693132196,
+      "grad_norm": 1.3570079803466797,
+      "learning_rate": 0.00010202729561415131,
+      "loss": 3.026602554321289,
+      "step": 3710
+    },
+    {
+      "epoch": 1.4767764986105598,
+      "grad_norm": 1.3911274671554565,
+      "learning_rate": 0.00010176228965151717,
+      "loss": 2.9053327560424806,
+      "step": 3720
+    },
+    {
+      "epoch": 1.4807463279078998,
+      "grad_norm": 1.360430359840393,
+      "learning_rate": 0.00010149728368888301,
+      "loss": 2.736703872680664,
+      "step": 3730
+    },
+    {
+      "epoch": 1.48471615720524,
+      "grad_norm": 1.4576371908187866,
+      "learning_rate": 0.00010123227772624884,
+      "loss": 2.8896203994750977,
+      "step": 3740
+    },
+    {
+      "epoch": 1.4886859865025803,
+      "grad_norm": 1.4311631917953491,
+      "learning_rate": 0.00010096727176361469,
+      "loss": 2.8624494552612303,
+      "step": 3750
+    },
+    {
+      "epoch": 1.4926558157999206,
+      "grad_norm": 1.5123578310012817,
+      "learning_rate": 0.00010070226580098052,
+      "loss": 2.809356689453125,
+      "step": 3760
+    },
+    {
+      "epoch": 1.4966256450972608,
+      "grad_norm": 1.2829740047454834,
+      "learning_rate": 0.00010043725983834637,
+      "loss": 2.8745845794677733,
+      "step": 3770
+    },
+    {
+      "epoch": 1.500595474394601,
+      "grad_norm": 1.7028263807296753,
+      "learning_rate": 0.0001001722538757122,
+      "loss": 2.8838785171508787,
+      "step": 3780
+    },
+    {
+      "epoch": 1.5045653036919413,
+      "grad_norm": 1.5197185277938843,
+      "learning_rate": 9.990724791307805e-05,
+      "loss": 2.881943130493164,
+      "step": 3790
+    },
+    {
+      "epoch": 1.5085351329892815,
+      "grad_norm": 1.223615050315857,
+      "learning_rate": 9.96422419504439e-05,
+      "loss": 2.7202972412109374,
+      "step": 3800
+    },
+    {
+      "epoch": 1.5125049622866218,
+      "grad_norm": 1.8343837261199951,
+      "learning_rate": 9.937723598780973e-05,
+      "loss": 2.8640880584716797,
+      "step": 3810
+    },
+    {
+      "epoch": 1.516474791583962,
+      "grad_norm": 1.5116796493530273,
+      "learning_rate": 9.911223002517557e-05,
+      "loss": 2.924713134765625,
+      "step": 3820
+    },
+    {
+      "epoch": 1.520444620881302,
+      "grad_norm": 1.6535507440567017,
+      "learning_rate": 9.884722406254141e-05,
+      "loss": 2.7902399063110352,
+      "step": 3830
+    },
+    {
+      "epoch": 1.5244144501786423,
+      "grad_norm": 1.398630976676941,
+      "learning_rate": 9.858221809990725e-05,
+      "loss": 2.8293262481689454,
+      "step": 3840
+    },
+    {
+      "epoch": 1.5283842794759825,
+      "grad_norm": 1.4054690599441528,
+      "learning_rate": 9.83172121372731e-05,
+      "loss": 2.8115062713623047,
+      "step": 3850
+    },
+    {
+      "epoch": 1.5323541087733228,
+      "grad_norm": 1.4996291399002075,
+      "learning_rate": 9.805220617463894e-05,
+      "loss": 2.832067108154297,
+      "step": 3860
+    },
+    {
+      "epoch": 1.5363239380706628,
+      "grad_norm": 1.0884090662002563,
+      "learning_rate": 9.778720021200478e-05,
+      "loss": 2.6115888595581054,
+      "step": 3870
+    },
+    {
+      "epoch": 1.540293767368003,
+      "grad_norm": 1.2034204006195068,
+      "learning_rate": 9.752219424937061e-05,
+      "loss": 2.7569812774658202,
+      "step": 3880
+    },
+    {
+      "epoch": 1.5442635966653433,
+      "grad_norm": 1.3871127367019653,
+      "learning_rate": 9.725718828673646e-05,
+      "loss": 3.050065612792969,
+      "step": 3890
+    },
+    {
+      "epoch": 1.5482334259626835,
+      "grad_norm": 1.5501118898391724,
+      "learning_rate": 9.69921823241023e-05,
+      "loss": 2.8175943374633787,
+      "step": 3900
+    },
+    {
+      "epoch": 1.5522032552600238,
+      "grad_norm": 1.2360347509384155,
+      "learning_rate": 9.672717636146814e-05,
+      "loss": 2.7722763061523437,
+      "step": 3910
+    },
+    {
+      "epoch": 1.556173084557364,
+      "grad_norm": 1.2444398403167725,
+      "learning_rate": 9.646217039883397e-05,
+      "loss": 2.861615753173828,
+      "step": 3920
+    },
+    {
+      "epoch": 1.5601429138547043,
+      "grad_norm": 1.3740792274475098,
+      "learning_rate": 9.619716443619982e-05,
+      "loss": 2.81121826171875,
+      "step": 3930
+    },
+    {
+      "epoch": 1.5641127431520445,
+      "grad_norm": 1.429770588874817,
+      "learning_rate": 9.593215847356565e-05,
+      "loss": 2.922770309448242,
+      "step": 3940
+    },
+    {
+      "epoch": 1.5680825724493848,
+      "grad_norm": 1.2474150657653809,
+      "learning_rate": 9.56671525109315e-05,
+      "loss": 2.9116376876831054,
+      "step": 3950
+    },
+    {
+      "epoch": 1.572052401746725,
+      "grad_norm": 1.431827425956726,
+      "learning_rate": 9.540214654829735e-05,
+      "loss": 2.917964553833008,
+      "step": 3960
+    },
+    {
+      "epoch": 1.5760222310440652,
+      "grad_norm": 1.3315114974975586,
+      "learning_rate": 9.513714058566318e-05,
+      "loss": 2.8786062240600585,
+      "step": 3970
+    },
+    {
+      "epoch": 1.5799920603414053,
+      "grad_norm": 1.1765938997268677,
+      "learning_rate": 9.487213462302902e-05,
+      "loss": 2.8044477462768556,
+      "step": 3980
+    },
+    {
+      "epoch": 1.5839618896387455,
+      "grad_norm": 1.348409652709961,
+      "learning_rate": 9.460712866039486e-05,
+      "loss": 2.8915786743164062,
+      "step": 3990
+    },
+    {
+      "epoch": 1.5879317189360858,
+      "grad_norm": 1.4071879386901855,
+      "learning_rate": 9.434212269776071e-05,
+      "loss": 2.8507789611816405,
+      "step": 4000
+    },
+    {
+      "epoch": 1.591901548233426,
+      "grad_norm": 1.3064533472061157,
+      "learning_rate": 9.410361733138996e-05,
+      "loss": 2.7582677841186523,
+      "step": 4010
+    },
+    {
+      "epoch": 1.595871377530766,
+      "grad_norm": 1.2912938594818115,
+      "learning_rate": 9.38386113687558e-05,
+      "loss": 2.882757568359375,
+      "step": 4020
+    },
+    {
+      "epoch": 1.5998412068281063,
+      "grad_norm": 1.1329375505447388,
+      "learning_rate": 9.357360540612164e-05,
+      "loss": 2.815750312805176,
+      "step": 4030
+    },
+    {
+      "epoch": 1.6038110361254465,
+      "grad_norm": 1.337375521659851,
+      "learning_rate": 9.330859944348749e-05,
+      "loss": 2.8128747940063477,
+      "step": 4040
+    },
+    {
+      "epoch": 1.6077808654227868,
+      "grad_norm": 1.2815532684326172,
+      "learning_rate": 9.304359348085333e-05,
+      "loss": 2.7639719009399415,
+      "step": 4050
+    },
+    {
+      "epoch": 1.611750694720127,
+      "grad_norm": 1.1914876699447632,
+      "learning_rate": 9.277858751821916e-05,
+      "loss": 2.894421195983887,
+      "step": 4060
+    },
+    {
+      "epoch": 1.6157205240174672,
+      "grad_norm": 1.2822132110595703,
+      "learning_rate": 9.2513581555585e-05,
+      "loss": 2.754531669616699,
+      "step": 4070
+    },
+    {
+      "epoch": 1.6196903533148075,
+      "grad_norm": 1.2767010927200317,
+      "learning_rate": 9.224857559295085e-05,
+      "loss": 2.884870719909668,
+      "step": 4080
+    },
+    {
+      "epoch": 1.6236601826121477,
+      "grad_norm": 1.5516023635864258,
+      "learning_rate": 9.198356963031669e-05,
+      "loss": 2.928493309020996,
+      "step": 4090
+    },
+    {
+      "epoch": 1.627630011909488,
+      "grad_norm": 1.2238390445709229,
+      "learning_rate": 9.171856366768252e-05,
+      "loss": 2.753667449951172,
+      "step": 4100
+    },
+    {
+      "epoch": 1.6315998412068282,
+      "grad_norm": 1.3094969987869263,
+      "learning_rate": 9.145355770504837e-05,
+      "loss": 2.8846521377563477,
+      "step": 4110
+    },
+    {
+      "epoch": 1.6355696705041685,
+      "grad_norm": 1.1217821836471558,
+      "learning_rate": 9.11885517424142e-05,
+      "loss": 2.8405046463012695,
+      "step": 4120
+    },
+    {
+      "epoch": 1.6395394998015085,
+      "grad_norm": 1.1809136867523193,
+      "learning_rate": 9.092354577978005e-05,
+      "loss": 2.8990488052368164,
+      "step": 4130
+    },
+    {
+      "epoch": 1.6435093290988487,
+      "grad_norm": 1.4486050605773926,
+      "learning_rate": 9.06585398171459e-05,
+      "loss": 2.801529884338379,
+      "step": 4140
+    },
+    {
+      "epoch": 1.647479158396189,
+      "grad_norm": 1.3603150844573975,
+      "learning_rate": 9.039353385451173e-05,
+      "loss": 2.7627063751220704,
+      "step": 4150
+    },
+    {
+      "epoch": 1.6514489876935292,
+      "grad_norm": 1.3169219493865967,
+      "learning_rate": 9.012852789187757e-05,
+      "loss": 2.844338798522949,
+      "step": 4160
+    },
+    {
+      "epoch": 1.6554188169908692,
+      "grad_norm": 1.4041424989700317,
+      "learning_rate": 8.986352192924341e-05,
+      "loss": 2.820200729370117,
+      "step": 4170
+    },
+    {
+      "epoch": 1.6593886462882095,
+      "grad_norm": 1.900181531906128,
+      "learning_rate": 8.959851596660926e-05,
+      "loss": 2.798480415344238,
+      "step": 4180
+    },
+    {
+      "epoch": 1.6633584755855497,
+      "grad_norm": 1.3303025960922241,
+      "learning_rate": 8.93335100039751e-05,
+      "loss": 2.7450151443481445,
+      "step": 4190
+    },
+    {
+      "epoch": 1.66732830488289,
+      "grad_norm": 1.173895239830017,
+      "learning_rate": 8.906850404134094e-05,
+      "loss": 2.807242584228516,
+      "step": 4200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 7557,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 200,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.8447580799594496e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-4200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae591a3a6737084c7522dfc1a295aa9ab6a59d7dface3e3999a058ffc77e97fc
+size 5841