Add checkpoint-2200

.gitattributes

@@ -43,3 +43,4 @@ checkpoints/checkpoint-1400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/checkpoint-1600/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/checkpoint-1800/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoints/checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoints/checkpoint-2200/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoints/checkpoint-2200/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-2200/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-2200/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6017d6a57a9d61cdb4ab3c764e99fdda5182b8924d19d9ddbb174d9be756b6e
+size 4724960

checkpoints/checkpoint-2200/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-2200/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22fb918e930deef7d5277370e64b2076b1d1b72923226010eca34a072246c097
+size 2455755

checkpoints/checkpoint-2200/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:088467b6e8877e37ff71e65bf5a42d83a1ebfa158612f81d72eb5d19e5529f81
+size 14645

checkpoints/checkpoint-2200/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a886dd82cf364128e8e1dfbb55927d02ce6f40a0a88febf7c3cfce941bba7fbf
+size 1383

checkpoints/checkpoint-2200/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acb9376b761580e292777ed27ae3b1e1eef03bcc85569865e87f1c75fca4b117
+size 1465

checkpoints/checkpoint-2200/tokenizer.json

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

checkpoints/checkpoint-2200/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-2200/trainer_state.json

@@ -0,0 +1,1574 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.187955711585201,
+  "eval_steps": 500,
+  "global_step": 2200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0054010261949770455,
+      "grad_norm": 1.4275089502334595,
+      "learning_rate": 0.00016,
+      "loss": 3.4877567291259766,
+      "step": 10
+    },
+    {
+      "epoch": 0.010802052389954091,
+      "grad_norm": 1.4062877893447876,
+      "learning_rate": 0.00019971150378651282,
+      "loss": 3.177476501464844,
+      "step": 20
+    },
+    {
+      "epoch": 0.016203078584931137,
+      "grad_norm": 1.4894630908966064,
+      "learning_rate": 0.0001993508835196538,
+      "loss": 2.949508857727051,
+      "step": 30
+    },
+    {
+      "epoch": 0.021604104779908182,
+      "grad_norm": 1.1637152433395386,
+      "learning_rate": 0.00019899026325279482,
+      "loss": 3.2568588256835938,
+      "step": 40
+    },
+    {
+      "epoch": 0.027005130974885227,
+      "grad_norm": 1.0710796117782593,
+      "learning_rate": 0.00019862964298593581,
+      "loss": 3.033162307739258,
+      "step": 50
+    },
+    {
+      "epoch": 0.032406157169862275,
+      "grad_norm": 1.036720633506775,
+      "learning_rate": 0.0001982690227190768,
+      "loss": 2.9209388732910155,
+      "step": 60
+    },
+    {
+      "epoch": 0.03780718336483932,
+      "grad_norm": 1.5094584226608276,
+      "learning_rate": 0.00019790840245221782,
+      "loss": 3.199975776672363,
+      "step": 70
+    },
+    {
+      "epoch": 0.043208209559816364,
+      "grad_norm": 1.25065016746521,
+      "learning_rate": 0.00019754778218535884,
+      "loss": 3.1586023330688477,
+      "step": 80
+    },
+    {
+      "epoch": 0.04860923575479341,
+      "grad_norm": 1.093263864517212,
+      "learning_rate": 0.00019718716191849983,
+      "loss": 3.1673559188842773,
+      "step": 90
+    },
+    {
+      "epoch": 0.054010261949770454,
+      "grad_norm": 1.7025214433670044,
+      "learning_rate": 0.00019682654165164082,
+      "loss": 3.0090349197387694,
+      "step": 100
+    },
+    {
+      "epoch": 0.059411288144747505,
+      "grad_norm": 1.0379327535629272,
+      "learning_rate": 0.00019646592138478184,
+      "loss": 3.0862411499023437,
+      "step": 110
+    },
+    {
+      "epoch": 0.06481231433972455,
+      "grad_norm": 1.0767595767974854,
+      "learning_rate": 0.00019610530111792285,
+      "loss": 2.9345855712890625,
+      "step": 120
+    },
+    {
+      "epoch": 0.07021334053470159,
+      "grad_norm": 1.2473753690719604,
+      "learning_rate": 0.00019574468085106384,
+      "loss": 3.168864440917969,
+      "step": 130
+    },
+    {
+      "epoch": 0.07561436672967864,
+      "grad_norm": 1.1580232381820679,
+      "learning_rate": 0.00019538406058420483,
+      "loss": 3.0444286346435545,
+      "step": 140
+    },
+    {
+      "epoch": 0.08101539292465569,
+      "grad_norm": 1.1562517881393433,
+      "learning_rate": 0.00019502344031734585,
+      "loss": 3.0681676864624023,
+      "step": 150
+    },
+    {
+      "epoch": 0.08641641911963273,
+      "grad_norm": 1.2069370746612549,
+      "learning_rate": 0.00019466282005048684,
+      "loss": 3.147779846191406,
+      "step": 160
+    },
+    {
+      "epoch": 0.09181744531460978,
+      "grad_norm": 1.1520271301269531,
+      "learning_rate": 0.00019430219978362786,
+      "loss": 3.2159664154052736,
+      "step": 170
+    },
+    {
+      "epoch": 0.09721847150958682,
+      "grad_norm": 1.3290963172912598,
+      "learning_rate": 0.00019394157951676885,
+      "loss": 3.17901668548584,
+      "step": 180
+    },
+    {
+      "epoch": 0.10261949770456387,
+      "grad_norm": 1.4537458419799805,
+      "learning_rate": 0.00019358095924990984,
+      "loss": 3.076709747314453,
+      "step": 190
+    },
+    {
+      "epoch": 0.10802052389954091,
+      "grad_norm": 1.6899892091751099,
+      "learning_rate": 0.00019322033898305085,
+      "loss": 2.9362957000732424,
+      "step": 200
+    },
+    {
+      "epoch": 0.11342155009451796,
+      "grad_norm": 1.218902349472046,
+      "learning_rate": 0.00019289578074287774,
+      "loss": 3.0862009048461916,
+      "step": 210
+    },
+    {
+      "epoch": 0.11882257628949501,
+      "grad_norm": 1.253646969795227,
+      "learning_rate": 0.00019253516047601876,
+      "loss": 3.0416831970214844,
+      "step": 220
+    },
+    {
+      "epoch": 0.12422360248447205,
+      "grad_norm": 1.1816236972808838,
+      "learning_rate": 0.00019217454020915977,
+      "loss": 3.09185791015625,
+      "step": 230
+    },
+    {
+      "epoch": 0.1296246286794491,
+      "grad_norm": 1.2364989519119263,
+      "learning_rate": 0.00019181391994230076,
+      "loss": 3.1257530212402345,
+      "step": 240
+    },
+    {
+      "epoch": 0.13502565487442614,
+      "grad_norm": 1.3117403984069824,
+      "learning_rate": 0.00019145329967544175,
+      "loss": 3.0078147888183593,
+      "step": 250
+    },
+    {
+      "epoch": 0.14042668106940318,
+      "grad_norm": 1.060840368270874,
+      "learning_rate": 0.00019109267940858277,
+      "loss": 3.205386734008789,
+      "step": 260
+    },
+    {
+      "epoch": 0.14582770726438024,
+      "grad_norm": 1.0836883783340454,
+      "learning_rate": 0.0001907320591417238,
+      "loss": 3.00787410736084,
+      "step": 270
+    },
+    {
+      "epoch": 0.15122873345935728,
+      "grad_norm": 1.1705331802368164,
+      "learning_rate": 0.00019037143887486478,
+      "loss": 3.1415082931518556,
+      "step": 280
+    },
+    {
+      "epoch": 0.15662975965433432,
+      "grad_norm": 1.1469744443893433,
+      "learning_rate": 0.00019001081860800577,
+      "loss": 3.0711442947387697,
+      "step": 290
+    },
+    {
+      "epoch": 0.16203078584931138,
+      "grad_norm": 1.7230859994888306,
+      "learning_rate": 0.00018965019834114679,
+      "loss": 3.0760629653930662,
+      "step": 300
+    },
+    {
+      "epoch": 0.16743181204428842,
+      "grad_norm": 1.3305317163467407,
+      "learning_rate": 0.00018928957807428778,
+      "loss": 3.0109764099121095,
+      "step": 310
+    },
+    {
+      "epoch": 0.17283283823926546,
+      "grad_norm": 1.1433296203613281,
+      "learning_rate": 0.0001889289578074288,
+      "loss": 2.900168228149414,
+      "step": 320
+    },
+    {
+      "epoch": 0.1782338644342425,
+      "grad_norm": 1.4017837047576904,
+      "learning_rate": 0.00018856833754056978,
+      "loss": 2.9257192611694336,
+      "step": 330
+    },
+    {
+      "epoch": 0.18363489062921956,
+      "grad_norm": 1.418676495552063,
+      "learning_rate": 0.00018820771727371077,
+      "loss": 3.1230239868164062,
+      "step": 340
+    },
+    {
+      "epoch": 0.1890359168241966,
+      "grad_norm": 1.2229913473129272,
+      "learning_rate": 0.0001878470970068518,
+      "loss": 2.8634975433349608,
+      "step": 350
+    },
+    {
+      "epoch": 0.19443694301917364,
+      "grad_norm": 1.2936865091323853,
+      "learning_rate": 0.0001874864767399928,
+      "loss": 3.0415794372558596,
+      "step": 360
+    },
+    {
+      "epoch": 0.1998379692141507,
+      "grad_norm": 1.3978519439697266,
+      "learning_rate": 0.0001871258564731338,
+      "loss": 2.9328636169433593,
+      "step": 370
+    },
+    {
+      "epoch": 0.20523899540912774,
+      "grad_norm": 1.0732481479644775,
+      "learning_rate": 0.0001867652362062748,
+      "loss": 3.147154426574707,
+      "step": 380
+    },
+    {
+      "epoch": 0.21064002160410478,
+      "grad_norm": 1.304332971572876,
+      "learning_rate": 0.0001864046159394158,
+      "loss": 2.98757266998291,
+      "step": 390
+    },
+    {
+      "epoch": 0.21604104779908181,
+      "grad_norm": 1.2670519351959229,
+      "learning_rate": 0.00018604399567255682,
+      "loss": 3.0830259323120117,
+      "step": 400
+    },
+    {
+      "epoch": 0.22144207399405888,
+      "grad_norm": 1.3472830057144165,
+      "learning_rate": 0.0001856833754056978,
+      "loss": 3.0725728988647463,
+      "step": 410
+    },
+    {
+      "epoch": 0.22684310018903592,
+      "grad_norm": 1.5913994312286377,
+      "learning_rate": 0.0001853227551388388,
+      "loss": 2.872740936279297,
+      "step": 420
+    },
+    {
+      "epoch": 0.23224412638401296,
+      "grad_norm": 1.4995367527008057,
+      "learning_rate": 0.00018496213487197982,
+      "loss": 3.1985055923461916,
+      "step": 430
+    },
+    {
+      "epoch": 0.23764515257899002,
+      "grad_norm": 1.3097314834594727,
+      "learning_rate": 0.0001846015146051208,
+      "loss": 2.9131542205810548,
+      "step": 440
+    },
+    {
+      "epoch": 0.24304617877396706,
+      "grad_norm": 1.2168841361999512,
+      "learning_rate": 0.00018424089433826182,
+      "loss": 3.0022405624389648,
+      "step": 450
+    },
+    {
+      "epoch": 0.2484472049689441,
+      "grad_norm": 1.2428247928619385,
+      "learning_rate": 0.00018388027407140281,
+      "loss": 3.13458194732666,
+      "step": 460
+    },
+    {
+      "epoch": 0.25384823116392113,
+      "grad_norm": 1.0732594728469849,
+      "learning_rate": 0.00018351965380454383,
+      "loss": 2.995112991333008,
+      "step": 470
+    },
+    {
+      "epoch": 0.2592492573588982,
+      "grad_norm": 1.0187745094299316,
+      "learning_rate": 0.00018315903353768482,
+      "loss": 2.9637735366821287,
+      "step": 480
+    },
+    {
+      "epoch": 0.2646502835538752,
+      "grad_norm": 1.2797402143478394,
+      "learning_rate": 0.00018279841327082584,
+      "loss": 2.9933282852172853,
+      "step": 490
+    },
+    {
+      "epoch": 0.2700513097488523,
+      "grad_norm": 0.9948688745498657,
+      "learning_rate": 0.00018243779300396683,
+      "loss": 3.078018569946289,
+      "step": 500
+    },
+    {
+      "epoch": 0.27545233594382934,
+      "grad_norm": 1.0406428575515747,
+      "learning_rate": 0.00018207717273710782,
+      "loss": 2.9701290130615234,
+      "step": 510
+    },
+    {
+      "epoch": 0.28085336213880635,
+      "grad_norm": 1.184054970741272,
+      "learning_rate": 0.00018171655247024884,
+      "loss": 3.094232368469238,
+      "step": 520
+    },
+    {
+      "epoch": 0.2862543883337834,
+      "grad_norm": 1.2439318895339966,
+      "learning_rate": 0.00018135593220338985,
+      "loss": 3.0941631317138674,
+      "step": 530
+    },
+    {
+      "epoch": 0.2916554145287605,
+      "grad_norm": 1.3002263307571411,
+      "learning_rate": 0.00018099531193653084,
+      "loss": 2.9608373641967773,
+      "step": 540
+    },
+    {
+      "epoch": 0.2970564407237375,
+      "grad_norm": 1.5705729722976685,
+      "learning_rate": 0.00018063469166967183,
+      "loss": 3.026919364929199,
+      "step": 550
+    },
+    {
+      "epoch": 0.30245746691871456,
+      "grad_norm": 1.1658886671066284,
+      "learning_rate": 0.00018027407140281285,
+      "loss": 2.9997627258300783,
+      "step": 560
+    },
+    {
+      "epoch": 0.3078584931136916,
+      "grad_norm": 1.0013272762298584,
+      "learning_rate": 0.00017991345113595387,
+      "loss": 2.919036865234375,
+      "step": 570
+    },
+    {
+      "epoch": 0.31325951930866863,
+      "grad_norm": 1.1810517311096191,
+      "learning_rate": 0.00017955283086909486,
+      "loss": 3.0280284881591797,
+      "step": 580
+    },
+    {
+      "epoch": 0.3186605455036457,
+      "grad_norm": 1.4247483015060425,
+      "learning_rate": 0.00017919221060223585,
+      "loss": 2.944463920593262,
+      "step": 590
+    },
+    {
+      "epoch": 0.32406157169862276,
+      "grad_norm": 1.1780109405517578,
+      "learning_rate": 0.00017883159033537686,
+      "loss": 3.165457534790039,
+      "step": 600
+    },
+    {
+      "epoch": 0.3294625978935998,
+      "grad_norm": 1.082470417022705,
+      "learning_rate": 0.00017847097006851785,
+      "loss": 2.7378583908081056,
+      "step": 610
+    },
+    {
+      "epoch": 0.33486362408857684,
+      "grad_norm": 1.1170358657836914,
+      "learning_rate": 0.00017811034980165887,
+      "loss": 3.1393898010253904,
+      "step": 620
+    },
+    {
+      "epoch": 0.34026465028355385,
+      "grad_norm": 1.0197583436965942,
+      "learning_rate": 0.00017774972953479986,
+      "loss": 2.8996389389038084,
+      "step": 630
+    },
+    {
+      "epoch": 0.3456656764785309,
+      "grad_norm": 0.9194260835647583,
+      "learning_rate": 0.00017738910926794085,
+      "loss": 3.0526611328125,
+      "step": 640
+    },
+    {
+      "epoch": 0.351066702673508,
+      "grad_norm": 1.3681086301803589,
+      "learning_rate": 0.00017702848900108187,
+      "loss": 2.85855770111084,
+      "step": 650
+    },
+    {
+      "epoch": 0.356467728868485,
+      "grad_norm": 1.3217997550964355,
+      "learning_rate": 0.00017666786873422289,
+      "loss": 2.9244100570678713,
+      "step": 660
+    },
+    {
+      "epoch": 0.36186875506346206,
+      "grad_norm": 1.0755029916763306,
+      "learning_rate": 0.00017630724846736388,
+      "loss": 2.989073944091797,
+      "step": 670
+    },
+    {
+      "epoch": 0.3672697812584391,
+      "grad_norm": 1.2188295125961304,
+      "learning_rate": 0.00017594662820050487,
+      "loss": 3.005179023742676,
+      "step": 680
+    },
+    {
+      "epoch": 0.37267080745341613,
+      "grad_norm": 1.0459349155426025,
+      "learning_rate": 0.00017558600793364588,
+      "loss": 2.9304704666137695,
+      "step": 690
+    },
+    {
+      "epoch": 0.3780718336483932,
+      "grad_norm": 1.1236655712127686,
+      "learning_rate": 0.0001752253876667869,
+      "loss": 3.048674964904785,
+      "step": 700
+    },
+    {
+      "epoch": 0.38347285984337026,
+      "grad_norm": 1.0007507801055908,
+      "learning_rate": 0.00017486476739992786,
+      "loss": 3.1241172790527343,
+      "step": 710
+    },
+    {
+      "epoch": 0.38887388603834727,
+      "grad_norm": 1.2311853170394897,
+      "learning_rate": 0.00017450414713306888,
+      "loss": 2.8489208221435547,
+      "step": 720
+    },
+    {
+      "epoch": 0.39427491223332434,
+      "grad_norm": 1.1284152269363403,
+      "learning_rate": 0.0001741435268662099,
+      "loss": 2.889890670776367,
+      "step": 730
+    },
+    {
+      "epoch": 0.3996759384283014,
+      "grad_norm": 1.0716314315795898,
+      "learning_rate": 0.0001737829065993509,
+      "loss": 3.019309234619141,
+      "step": 740
+    },
+    {
+      "epoch": 0.4050769646232784,
+      "grad_norm": 1.3626065254211426,
+      "learning_rate": 0.00017342228633249188,
+      "loss": 2.8685939788818358,
+      "step": 750
+    },
+    {
+      "epoch": 0.4104779908182555,
+      "grad_norm": 1.133290410041809,
+      "learning_rate": 0.0001730616660656329,
+      "loss": 2.813917541503906,
+      "step": 760
+    },
+    {
+      "epoch": 0.4158790170132325,
+      "grad_norm": 1.2982553243637085,
+      "learning_rate": 0.0001727010457987739,
+      "loss": 3.066880798339844,
+      "step": 770
+    },
+    {
+      "epoch": 0.42128004320820955,
+      "grad_norm": 1.0441523790359497,
+      "learning_rate": 0.0001723404255319149,
+      "loss": 2.8972396850585938,
+      "step": 780
+    },
+    {
+      "epoch": 0.4266810694031866,
+      "grad_norm": 1.1574914455413818,
+      "learning_rate": 0.0001719798052650559,
+      "loss": 3.0566661834716795,
+      "step": 790
+    },
+    {
+      "epoch": 0.43208209559816363,
+      "grad_norm": 1.146910309791565,
+      "learning_rate": 0.0001716191849981969,
+      "loss": 2.9340593338012697,
+      "step": 800
+    },
+    {
+      "epoch": 0.4374831217931407,
+      "grad_norm": 1.1724562644958496,
+      "learning_rate": 0.0001712585647313379,
+      "loss": 2.9801464080810547,
+      "step": 810
+    },
+    {
+      "epoch": 0.44288414798811776,
+      "grad_norm": 1.3650254011154175,
+      "learning_rate": 0.00017089794446447892,
+      "loss": 2.9490041732788086,
+      "step": 820
+    },
+    {
+      "epoch": 0.44828517418309477,
+      "grad_norm": 1.0346980094909668,
+      "learning_rate": 0.00017053732419761993,
+      "loss": 2.971526336669922,
+      "step": 830
+    },
+    {
+      "epoch": 0.45368620037807184,
+      "grad_norm": 0.9564275741577148,
+      "learning_rate": 0.00017017670393076092,
+      "loss": 3.0509788513183596,
+      "step": 840
+    },
+    {
+      "epoch": 0.4590872265730489,
+      "grad_norm": 1.4447107315063477,
+      "learning_rate": 0.0001698160836639019,
+      "loss": 2.9528224945068358,
+      "step": 850
+    },
+    {
+      "epoch": 0.4644882527680259,
+      "grad_norm": 1.0819096565246582,
+      "learning_rate": 0.00016945546339704293,
+      "loss": 3.0397647857666015,
+      "step": 860
+    },
+    {
+      "epoch": 0.469889278963003,
+      "grad_norm": 1.3749688863754272,
+      "learning_rate": 0.00016909484313018395,
+      "loss": 2.9335342407226563,
+      "step": 870
+    },
+    {
+      "epoch": 0.47529030515798004,
+      "grad_norm": 0.9845815300941467,
+      "learning_rate": 0.0001687342228633249,
+      "loss": 3.1886215209960938,
+      "step": 880
+    },
+    {
+      "epoch": 0.48069133135295705,
+      "grad_norm": 1.0727243423461914,
+      "learning_rate": 0.00016837360259646593,
+      "loss": 3.071747970581055,
+      "step": 890
+    },
+    {
+      "epoch": 0.4860923575479341,
+      "grad_norm": 1.0900219678878784,
+      "learning_rate": 0.00016801298232960694,
+      "loss": 2.9294233322143555,
+      "step": 900
+    },
+    {
+      "epoch": 0.4914933837429111,
+      "grad_norm": 1.5818015336990356,
+      "learning_rate": 0.00016765236206274793,
+      "loss": 2.7862874984741213,
+      "step": 910
+    },
+    {
+      "epoch": 0.4968944099378882,
+      "grad_norm": 1.1314663887023926,
+      "learning_rate": 0.00016729174179588892,
+      "loss": 2.8420650482177736,
+      "step": 920
+    },
+    {
+      "epoch": 0.5022954361328652,
+      "grad_norm": 1.2435640096664429,
+      "learning_rate": 0.00016693112152902994,
+      "loss": 2.8855379104614256,
+      "step": 930
+    },
+    {
+      "epoch": 0.5076964623278423,
+      "grad_norm": 1.0684075355529785,
+      "learning_rate": 0.00016657050126217096,
+      "loss": 2.908370018005371,
+      "step": 940
+    },
+    {
+      "epoch": 0.5130974885228193,
+      "grad_norm": 1.4429422616958618,
+      "learning_rate": 0.00016620988099531195,
+      "loss": 3.0200515747070313,
+      "step": 950
+    },
+    {
+      "epoch": 0.5184985147177964,
+      "grad_norm": 1.3540408611297607,
+      "learning_rate": 0.00016584926072845294,
+      "loss": 2.653054428100586,
+      "step": 960
+    },
+    {
+      "epoch": 0.5238995409127735,
+      "grad_norm": 1.1349395513534546,
+      "learning_rate": 0.00016548864046159395,
+      "loss": 3.068928909301758,
+      "step": 970
+    },
+    {
+      "epoch": 0.5293005671077504,
+      "grad_norm": 1.0107704401016235,
+      "learning_rate": 0.00016512802019473494,
+      "loss": 2.912160110473633,
+      "step": 980
+    },
+    {
+      "epoch": 0.5347015933027275,
+      "grad_norm": 1.402188777923584,
+      "learning_rate": 0.00016476739992787596,
+      "loss": 3.3307727813720702,
+      "step": 990
+    },
+    {
+      "epoch": 0.5401026194977046,
+      "grad_norm": 1.200325608253479,
+      "learning_rate": 0.00016440677966101695,
+      "loss": 3.0100019454956053,
+      "step": 1000
+    },
+    {
+      "epoch": 0.5455036456926816,
+      "grad_norm": 1.1472864151000977,
+      "learning_rate": 0.00016404615939415794,
+      "loss": 2.938519096374512,
+      "step": 1010
+    },
+    {
+      "epoch": 0.5509046718876587,
+      "grad_norm": 1.184414267539978,
+      "learning_rate": 0.00016368553912729896,
+      "loss": 2.9431873321533204,
+      "step": 1020
+    },
+    {
+      "epoch": 0.5563056980826357,
+      "grad_norm": 1.0453943014144897,
+      "learning_rate": 0.00016332491886043998,
+      "loss": 2.98077335357666,
+      "step": 1030
+    },
+    {
+      "epoch": 0.5617067242776127,
+      "grad_norm": 1.1441236734390259,
+      "learning_rate": 0.00016296429859358097,
+      "loss": 3.0176897048950195,
+      "step": 1040
+    },
+    {
+      "epoch": 0.5671077504725898,
+      "grad_norm": 0.9775217771530151,
+      "learning_rate": 0.00016260367832672196,
+      "loss": 3.0514453887939452,
+      "step": 1050
+    },
+    {
+      "epoch": 0.5725087766675668,
+      "grad_norm": 1.6667460203170776,
+      "learning_rate": 0.00016224305805986297,
+      "loss": 2.9403846740722654,
+      "step": 1060
+    },
+    {
+      "epoch": 0.5779098028625439,
+      "grad_norm": 1.2570966482162476,
+      "learning_rate": 0.000161882437793004,
+      "loss": 2.7937477111816404,
+      "step": 1070
+    },
+    {
+      "epoch": 0.583310829057521,
+      "grad_norm": 1.3722922801971436,
+      "learning_rate": 0.00016152181752614498,
+      "loss": 2.8590538024902346,
+      "step": 1080
+    },
+    {
+      "epoch": 0.588711855252498,
+      "grad_norm": 1.0699330568313599,
+      "learning_rate": 0.00016116119725928597,
+      "loss": 2.8490627288818358,
+      "step": 1090
+    },
+    {
+      "epoch": 0.594112881447475,
+      "grad_norm": 1.2045018672943115,
+      "learning_rate": 0.000160800576992427,
+      "loss": 2.920571708679199,
+      "step": 1100
+    },
+    {
+      "epoch": 0.599513907642452,
+      "grad_norm": 1.2119923830032349,
+      "learning_rate": 0.00016043995672556798,
+      "loss": 2.8805025100708006,
+      "step": 1110
+    },
+    {
+      "epoch": 0.6049149338374291,
+      "grad_norm": 1.1207152605056763,
+      "learning_rate": 0.000160079336458709,
+      "loss": 2.937060737609863,
+      "step": 1120
+    },
+    {
+      "epoch": 0.6103159600324062,
+      "grad_norm": 1.3675578832626343,
+      "learning_rate": 0.00015971871619184998,
+      "loss": 2.9657745361328125,
+      "step": 1130
+    },
+    {
+      "epoch": 0.6157169862273832,
+      "grad_norm": 1.3562731742858887,
+      "learning_rate": 0.000159358095924991,
+      "loss": 3.0127033233642577,
+      "step": 1140
+    },
+    {
+      "epoch": 0.6211180124223602,
+      "grad_norm": 1.0387409925460815,
+      "learning_rate": 0.000158997475658132,
+      "loss": 2.876498794555664,
+      "step": 1150
+    },
+    {
+      "epoch": 0.6265190386173373,
+      "grad_norm": 1.2561172246932983,
+      "learning_rate": 0.000158636855391273,
+      "loss": 2.8820684432983397,
+      "step": 1160
+    },
+    {
+      "epoch": 0.6319200648123143,
+      "grad_norm": 1.293705701828003,
+      "learning_rate": 0.000158276235124414,
+      "loss": 2.9766061782836912,
+      "step": 1170
+    },
+    {
+      "epoch": 0.6373210910072914,
+      "grad_norm": 1.2604966163635254,
+      "learning_rate": 0.000157915614857555,
+      "loss": 3.119212341308594,
+      "step": 1180
+    },
+    {
+      "epoch": 0.6427221172022685,
+      "grad_norm": 1.094990611076355,
+      "learning_rate": 0.000157554994590696,
+      "loss": 3.071938133239746,
+      "step": 1190
+    },
+    {
+      "epoch": 0.6481231433972455,
+      "grad_norm": 1.1782667636871338,
+      "learning_rate": 0.00015719437432383702,
+      "loss": 3.0528400421142576,
+      "step": 1200
+    },
+    {
+      "epoch": 0.6535241695922225,
+      "grad_norm": 1.467441201210022,
+      "learning_rate": 0.000156833754056978,
+      "loss": 2.967136764526367,
+      "step": 1210
+    },
+    {
+      "epoch": 0.6589251957871995,
+      "grad_norm": 1.3159500360488892,
+      "learning_rate": 0.000156473133790119,
+      "loss": 2.9709142684936523,
+      "step": 1220
+    },
+    {
+      "epoch": 0.6643262219821766,
+      "grad_norm": 1.1980047225952148,
+      "learning_rate": 0.00015611251352326002,
+      "loss": 3.0129560470581054,
+      "step": 1230
+    },
+    {
+      "epoch": 0.6697272481771537,
+      "grad_norm": 1.125895619392395,
+      "learning_rate": 0.00015575189325640104,
+      "loss": 2.962136077880859,
+      "step": 1240
+    },
+    {
+      "epoch": 0.6751282743721307,
+      "grad_norm": 1.5294994115829468,
+      "learning_rate": 0.00015539127298954203,
+      "loss": 3.139348793029785,
+      "step": 1250
+    },
+    {
+      "epoch": 0.6805293005671077,
+      "grad_norm": 1.2642886638641357,
+      "learning_rate": 0.00015503065272268302,
+      "loss": 3.018353080749512,
+      "step": 1260
+    },
+    {
+      "epoch": 0.6859303267620848,
+      "grad_norm": 1.0708301067352295,
+      "learning_rate": 0.00015467003245582403,
+      "loss": 2.9507617950439453,
+      "step": 1270
+    },
+    {
+      "epoch": 0.6913313529570618,
+      "grad_norm": 1.2057912349700928,
+      "learning_rate": 0.00015430941218896502,
+      "loss": 2.8525314331054688,
+      "step": 1280
+    },
+    {
+      "epoch": 0.6967323791520389,
+      "grad_norm": 1.003139615058899,
+      "learning_rate": 0.00015394879192210604,
+      "loss": 2.952615737915039,
+      "step": 1290
+    },
+    {
+      "epoch": 0.702133405347016,
+      "grad_norm": 1.3539371490478516,
+      "learning_rate": 0.00015358817165524703,
+      "loss": 2.994022560119629,
+      "step": 1300
+    },
+    {
+      "epoch": 0.707534431541993,
+      "grad_norm": 0.9936187863349915,
+      "learning_rate": 0.00015322755138838802,
+      "loss": 3.0847434997558594,
+      "step": 1310
+    },
+    {
+      "epoch": 0.71293545773697,
+      "grad_norm": 1.077620267868042,
+      "learning_rate": 0.00015286693112152904,
+      "loss": 3.066029930114746,
+      "step": 1320
+    },
+    {
+      "epoch": 0.718336483931947,
+      "grad_norm": 1.4198359251022339,
+      "learning_rate": 0.00015250631085467005,
+      "loss": 2.7741952896118165,
+      "step": 1330
+    },
+    {
+      "epoch": 0.7237375101269241,
+      "grad_norm": 1.1443026065826416,
+      "learning_rate": 0.00015214569058781104,
+      "loss": 2.9916961669921873,
+      "step": 1340
+    },
+    {
+      "epoch": 0.7291385363219012,
+      "grad_norm": 1.142872929573059,
+      "learning_rate": 0.00015178507032095203,
+      "loss": 2.9340869903564455,
+      "step": 1350
+    },
+    {
+      "epoch": 0.7345395625168782,
+      "grad_norm": 1.061112403869629,
+      "learning_rate": 0.00015142445005409305,
+      "loss": 2.909784126281738,
+      "step": 1360
+    },
+    {
+      "epoch": 0.7399405887118553,
+      "grad_norm": 1.5785682201385498,
+      "learning_rate": 0.00015106382978723407,
+      "loss": 2.6537490844726563,
+      "step": 1370
+    },
+    {
+      "epoch": 0.7453416149068323,
+      "grad_norm": 1.0441385507583618,
+      "learning_rate": 0.00015070320952037503,
+      "loss": 3.0098087310791017,
+      "step": 1380
+    },
+    {
+      "epoch": 0.7507426411018093,
+      "grad_norm": 1.1422723531723022,
+      "learning_rate": 0.00015034258925351605,
+      "loss": 3.039506721496582,
+      "step": 1390
+    },
+    {
+      "epoch": 0.7561436672967864,
+      "grad_norm": 1.1552327871322632,
+      "learning_rate": 0.00014998196898665707,
+      "loss": 2.951033020019531,
+      "step": 1400
+    },
+    {
+      "epoch": 0.7615446934917635,
+      "grad_norm": 1.0944606065750122,
+      "learning_rate": 0.00014962134871979806,
+      "loss": 3.106746482849121,
+      "step": 1410
+    },
+    {
+      "epoch": 0.7669457196867405,
+      "grad_norm": 1.4111071825027466,
+      "learning_rate": 0.00014926072845293905,
+      "loss": 2.958788299560547,
+      "step": 1420
+    },
+    {
+      "epoch": 0.7723467458817175,
+      "grad_norm": 1.4764567613601685,
+      "learning_rate": 0.00014890010818608006,
+      "loss": 2.830558013916016,
+      "step": 1430
+    },
+    {
+      "epoch": 0.7777477720766945,
+      "grad_norm": 1.925668716430664,
+      "learning_rate": 0.00014853948791922108,
+      "loss": 2.8127283096313476,
+      "step": 1440
+    },
+    {
+      "epoch": 0.7831487982716716,
+      "grad_norm": 1.1639180183410645,
+      "learning_rate": 0.00014817886765236207,
+      "loss": 2.997245025634766,
+      "step": 1450
+    },
+    {
+      "epoch": 0.7885498244666487,
+      "grad_norm": 0.9844375252723694,
+      "learning_rate": 0.00014781824738550306,
+      "loss": 2.9099292755126953,
+      "step": 1460
+    },
+    {
+      "epoch": 0.7939508506616257,
+      "grad_norm": 1.1210323572158813,
+      "learning_rate": 0.00014745762711864408,
+      "loss": 3.145793342590332,
+      "step": 1470
+    },
+    {
+      "epoch": 0.7993518768566028,
+      "grad_norm": 1.2205151319503784,
+      "learning_rate": 0.000147133068878471,
+      "loss": 2.8995004653930665,
+      "step": 1480
+    },
+    {
+      "epoch": 0.8047529030515798,
+      "grad_norm": 1.321806788444519,
+      "learning_rate": 0.00014677244861161198,
+      "loss": 2.916131019592285,
+      "step": 1490
+    },
+    {
+      "epoch": 0.8101539292465568,
+      "grad_norm": 1.5386055707931519,
+      "learning_rate": 0.00014641182834475297,
+      "loss": 2.925608253479004,
+      "step": 1500
+    },
+    {
+      "epoch": 0.8155549554415339,
+      "grad_norm": 1.0212986469268799,
+      "learning_rate": 0.000146051208077894,
+      "loss": 2.9698795318603515,
+      "step": 1510
+    },
+    {
+      "epoch": 0.820955981636511,
+      "grad_norm": 1.1042375564575195,
+      "learning_rate": 0.000145690587811035,
+      "loss": 2.856062126159668,
+      "step": 1520
+    },
+    {
+      "epoch": 0.826357007831488,
+      "grad_norm": 1.3728346824645996,
+      "learning_rate": 0.000145329967544176,
+      "loss": 2.9228466033935545,
+      "step": 1530
+    },
+    {
+      "epoch": 0.831758034026465,
+      "grad_norm": 1.203946828842163,
+      "learning_rate": 0.00014496934727731698,
+      "loss": 2.8147531509399415,
+      "step": 1540
+    },
+    {
+      "epoch": 0.837159060221442,
+      "grad_norm": 1.2796454429626465,
+      "learning_rate": 0.000144608727010458,
+      "loss": 2.8535860061645506,
+      "step": 1550
+    },
+    {
+      "epoch": 0.8425600864164191,
+      "grad_norm": 1.708990216255188,
+      "learning_rate": 0.000144248106743599,
+      "loss": 2.9603645324707033,
+      "step": 1560
+    },
+    {
+      "epoch": 0.8479611126113962,
+      "grad_norm": 1.1417936086654663,
+      "learning_rate": 0.00014388748647674,
+      "loss": 2.927590560913086,
+      "step": 1570
+    },
+    {
+      "epoch": 0.8533621388063732,
+      "grad_norm": 1.289814829826355,
+      "learning_rate": 0.000143526866209881,
+      "loss": 3.0022300720214843,
+      "step": 1580
+    },
+    {
+      "epoch": 0.8587631650013503,
+      "grad_norm": 1.4492555856704712,
+      "learning_rate": 0.00014316624594302202,
+      "loss": 2.9754718780517577,
+      "step": 1590
+    },
+    {
+      "epoch": 0.8641641911963273,
+      "grad_norm": 1.4755349159240723,
+      "learning_rate": 0.000142805625676163,
+      "loss": 2.852312469482422,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 1.0230276584625244,
+      "learning_rate": 0.00014244500540930402,
+      "loss": 3.0102075576782226,
+      "step": 1610
+    },
+    {
+      "epoch": 0.8749662435862814,
+      "grad_norm": 1.3246142864227295,
+      "learning_rate": 0.000142084385142445,
+      "loss": 2.9929609298706055,
+      "step": 1620
+    },
+    {
+      "epoch": 0.8803672697812585,
+      "grad_norm": 1.339630365371704,
+      "learning_rate": 0.000141723764875586,
+      "loss": 3.0588592529296874,
+      "step": 1630
+    },
+    {
+      "epoch": 0.8857682959762355,
+      "grad_norm": 1.2536578178405762,
+      "learning_rate": 0.00014136314460872702,
+      "loss": 2.7730195999145506,
+      "step": 1640
+    },
+    {
+      "epoch": 0.8911693221712126,
+      "grad_norm": 0.9663991332054138,
+      "learning_rate": 0.00014100252434186804,
+      "loss": 2.8569766998291017,
+      "step": 1650
+    },
+    {
+      "epoch": 0.8965703483661895,
+      "grad_norm": 1.0282679796218872,
+      "learning_rate": 0.000140641904075009,
+      "loss": 3.037453460693359,
+      "step": 1660
+    },
+    {
+      "epoch": 0.9019713745611666,
+      "grad_norm": 1.2708044052124023,
+      "learning_rate": 0.00014028128380815002,
+      "loss": 2.9699851989746096,
+      "step": 1670
+    },
+    {
+      "epoch": 0.9073724007561437,
+      "grad_norm": 1.4541798830032349,
+      "learning_rate": 0.00013992066354129103,
+      "loss": 2.8832717895507813,
+      "step": 1680
+    },
+    {
+      "epoch": 0.9127734269511207,
+      "grad_norm": 1.4256030321121216,
+      "learning_rate": 0.00013956004327443205,
+      "loss": 2.948398208618164,
+      "step": 1690
+    },
+    {
+      "epoch": 0.9181744531460978,
+      "grad_norm": 1.3157241344451904,
+      "learning_rate": 0.00013919942300757301,
+      "loss": 2.836800384521484,
+      "step": 1700
+    },
+    {
+      "epoch": 0.9235754793410748,
+      "grad_norm": 1.3309694528579712,
+      "learning_rate": 0.00013883880274071403,
+      "loss": 2.900766944885254,
+      "step": 1710
+    },
+    {
+      "epoch": 0.9289765055360518,
+      "grad_norm": 0.9171543121337891,
+      "learning_rate": 0.00013847818247385505,
+      "loss": 2.8924545288085937,
+      "step": 1720
+    },
+    {
+      "epoch": 0.9343775317310289,
+      "grad_norm": 1.0325075387954712,
+      "learning_rate": 0.00013811756220699604,
+      "loss": 2.9084177017211914,
+      "step": 1730
+    },
+    {
+      "epoch": 0.939778557926006,
+      "grad_norm": 1.4920449256896973,
+      "learning_rate": 0.00013775694194013703,
+      "loss": 2.810170555114746,
+      "step": 1740
+    },
+    {
+      "epoch": 0.945179584120983,
+      "grad_norm": 1.1236705780029297,
+      "learning_rate": 0.00013739632167327804,
+      "loss": 3.0464658737182617,
+      "step": 1750
+    },
+    {
+      "epoch": 0.9505806103159601,
+      "grad_norm": 1.1558237075805664,
+      "learning_rate": 0.00013703570140641903,
+      "loss": 3.0324066162109373,
+      "step": 1760
+    },
+    {
+      "epoch": 0.955981636510937,
+      "grad_norm": 1.1385915279388428,
+      "learning_rate": 0.00013667508113956005,
+      "loss": 2.9241012573242187,
+      "step": 1770
+    },
+    {
+      "epoch": 0.9613826627059141,
+      "grad_norm": 1.3047113418579102,
+      "learning_rate": 0.00013631446087270104,
+      "loss": 2.9352169036865234,
+      "step": 1780
+    },
+    {
+      "epoch": 0.9667836889008912,
+      "grad_norm": 1.548905849456787,
+      "learning_rate": 0.00013595384060584206,
+      "loss": 3.0046308517456053,
+      "step": 1790
+    },
+    {
+      "epoch": 0.9721847150958682,
+      "grad_norm": 1.1485257148742676,
+      "learning_rate": 0.00013559322033898305,
+      "loss": 2.868555450439453,
+      "step": 1800
+    },
+    {
+      "epoch": 0.9775857412908453,
+      "grad_norm": 1.366213083267212,
+      "learning_rate": 0.00013523260007212407,
+      "loss": 3.086391067504883,
+      "step": 1810
+    },
+    {
+      "epoch": 0.9829867674858223,
+      "grad_norm": 2.4089717864990234,
+      "learning_rate": 0.00013487197980526506,
+      "loss": 3.0984577178955077,
+      "step": 1820
+    },
+    {
+      "epoch": 0.9883877936807993,
+      "grad_norm": 1.1161662340164185,
+      "learning_rate": 0.00013451135953840605,
+      "loss": 2.915675163269043,
+      "step": 1830
+    },
+    {
+      "epoch": 0.9937888198757764,
+      "grad_norm": 1.1393717527389526,
+      "learning_rate": 0.00013415073927154706,
+      "loss": 2.879562568664551,
+      "step": 1840
+    },
+    {
+      "epoch": 0.9991898460707535,
+      "grad_norm": 1.4226765632629395,
+      "learning_rate": 0.00013379011900468808,
+      "loss": 2.8654153823852537,
+      "step": 1850
+    },
+    {
+      "epoch": 1.0043208209559817,
+      "grad_norm": 1.7910537719726562,
+      "learning_rate": 0.00013342949873782907,
+      "loss": 3.015969085693359,
+      "step": 1860
+    },
+    {
+      "epoch": 1.0097218471509586,
+      "grad_norm": 1.1190510988235474,
+      "learning_rate": 0.00013306887847097006,
+      "loss": 2.87933235168457,
+      "step": 1870
+    },
+    {
+      "epoch": 1.0151228733459357,
+      "grad_norm": 1.1738801002502441,
+      "learning_rate": 0.00013270825820411108,
+      "loss": 2.7941356658935548,
+      "step": 1880
+    },
+    {
+      "epoch": 1.0205238995409127,
+      "grad_norm": 1.0437875986099243,
+      "learning_rate": 0.0001323476379372521,
+      "loss": 2.896015167236328,
+      "step": 1890
+    },
+    {
+      "epoch": 1.0259249257358898,
+      "grad_norm": 1.4144948720932007,
+      "learning_rate": 0.00013198701767039308,
+      "loss": 2.843356704711914,
+      "step": 1900
+    },
+    {
+      "epoch": 1.0313259519308668,
+      "grad_norm": 1.732194423675537,
+      "learning_rate": 0.00013162639740353407,
+      "loss": 2.8961923599243162,
+      "step": 1910
+    },
+    {
+      "epoch": 1.036726978125844,
+      "grad_norm": 1.227655291557312,
+      "learning_rate": 0.0001312657771366751,
+      "loss": 2.8469051361083983,
+      "step": 1920
+    },
+    {
+      "epoch": 1.042128004320821,
+      "grad_norm": 1.2534716129302979,
+      "learning_rate": 0.00013090515686981608,
+      "loss": 2.8952392578125,
+      "step": 1930
+    },
+    {
+      "epoch": 1.047529030515798,
+      "grad_norm": 1.2732499837875366,
+      "learning_rate": 0.0001305445366029571,
+      "loss": 2.9137599945068358,
+      "step": 1940
+    },
+    {
+      "epoch": 1.052930056710775,
+      "grad_norm": 1.1516661643981934,
+      "learning_rate": 0.0001301839163360981,
+      "loss": 2.8422595977783205,
+      "step": 1950
+    },
+    {
+      "epoch": 1.0583310829057522,
+      "grad_norm": 1.7162693738937378,
+      "learning_rate": 0.00012982329606923908,
+      "loss": 3.0195697784423827,
+      "step": 1960
+    },
+    {
+      "epoch": 1.0637321091007292,
+      "grad_norm": 1.1824109554290771,
+      "learning_rate": 0.0001294626758023801,
+      "loss": 2.830906867980957,
+      "step": 1970
+    },
+    {
+      "epoch": 1.069133135295706,
+      "grad_norm": 1.246450424194336,
+      "learning_rate": 0.0001291020555355211,
+      "loss": 2.925843048095703,
+      "step": 1980
+    },
+    {
+      "epoch": 1.0745341614906831,
+      "grad_norm": 1.919395923614502,
+      "learning_rate": 0.0001287414352686621,
+      "loss": 2.845474433898926,
+      "step": 1990
+    },
+    {
+      "epoch": 1.0799351876856602,
+      "grad_norm": 1.2120916843414307,
+      "learning_rate": 0.0001283808150018031,
+      "loss": 2.9256092071533204,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0853362138806373,
+      "grad_norm": 1.1324710845947266,
+      "learning_rate": 0.0001280201947349441,
+      "loss": 2.9663860321044924,
+      "step": 2010
+    },
+    {
+      "epoch": 1.0907372400756143,
+      "grad_norm": 1.6326500177383423,
+      "learning_rate": 0.00012765957446808513,
+      "loss": 2.7034042358398436,
+      "step": 2020
+    },
+    {
+      "epoch": 1.0961382662705914,
+      "grad_norm": 1.3509035110473633,
+      "learning_rate": 0.00012729895420122612,
+      "loss": 2.633696746826172,
+      "step": 2030
+    },
+    {
+      "epoch": 1.1015392924655685,
+      "grad_norm": 1.0838254690170288,
+      "learning_rate": 0.0001269383339343671,
+      "loss": 2.8899274826049806,
+      "step": 2040
+    },
+    {
+      "epoch": 1.1069403186605455,
+      "grad_norm": 1.6641477346420288,
+      "learning_rate": 0.00012657771366750812,
+      "loss": 2.909597396850586,
+      "step": 2050
+    },
+    {
+      "epoch": 1.1123413448555226,
+      "grad_norm": 1.1637628078460693,
+      "learning_rate": 0.00012621709340064914,
+      "loss": 2.804787826538086,
+      "step": 2060
+    },
+    {
+      "epoch": 1.1177423710504997,
+      "grad_norm": 1.4898242950439453,
+      "learning_rate": 0.00012585647313379013,
+      "loss": 2.9821834564208984,
+      "step": 2070
+    },
+    {
+      "epoch": 1.1231433972454767,
+      "grad_norm": 1.4179521799087524,
+      "learning_rate": 0.00012549585286693112,
+      "loss": 3.029928779602051,
+      "step": 2080
+    },
+    {
+      "epoch": 1.1285444234404536,
+      "grad_norm": 1.3157166242599487,
+      "learning_rate": 0.00012513523260007214,
+      "loss": 2.682559585571289,
+      "step": 2090
+    },
+    {
+      "epoch": 1.1339454496354306,
+      "grad_norm": 1.190956950187683,
+      "learning_rate": 0.00012477461233321313,
+      "loss": 3.0344194412231444,
+      "step": 2100
+    },
+    {
+      "epoch": 1.1393464758304077,
+      "grad_norm": 1.0837123394012451,
+      "learning_rate": 0.00012441399206635415,
+      "loss": 2.693293571472168,
+      "step": 2110
+    },
+    {
+      "epoch": 1.1447475020253848,
+      "grad_norm": 1.190393328666687,
+      "learning_rate": 0.00012405337179949514,
+      "loss": 2.816008949279785,
+      "step": 2120
+    },
+    {
+      "epoch": 1.1501485282203618,
+      "grad_norm": 1.0684547424316406,
+      "learning_rate": 0.00012369275153263613,
+      "loss": 2.9440284729003907,
+      "step": 2130
+    },
+    {
+      "epoch": 1.155549554415339,
+      "grad_norm": 1.1556187868118286,
+      "learning_rate": 0.00012333213126577714,
+      "loss": 3.132794952392578,
+      "step": 2140
+    },
+    {
+      "epoch": 1.160950580610316,
+      "grad_norm": 1.0935251712799072,
+      "learning_rate": 0.00012297151099891816,
+      "loss": 2.6665658950805664,
+      "step": 2150
+    },
+    {
+      "epoch": 1.166351606805293,
+      "grad_norm": 1.1952039003372192,
+      "learning_rate": 0.00012261089073205915,
+      "loss": 2.918911933898926,
+      "step": 2160
+    },
+    {
+      "epoch": 1.17175263300027,
+      "grad_norm": 1.1767187118530273,
+      "learning_rate": 0.00012225027046520014,
+      "loss": 2.9808664321899414,
+      "step": 2170
+    },
+    {
+      "epoch": 1.1771536591952472,
+      "grad_norm": 1.0405514240264893,
+      "learning_rate": 0.00012188965019834116,
+      "loss": 2.7352481842041017,
+      "step": 2180
+    },
+    {
+      "epoch": 1.1825546853902242,
+      "grad_norm": 1.058395266532898,
+      "learning_rate": 0.00012152902993148216,
+      "loss": 2.8880331039428713,
+      "step": 2190
+    },
+    {
+      "epoch": 1.187955711585201,
+      "grad_norm": 1.2822115421295166,
+      "learning_rate": 0.00012116840966462315,
+      "loss": 2.978183937072754,
+      "step": 2200
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 5556,
+  "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": 7.900983909282816e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoints/checkpoint-2200/training_args.bin

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