Upload 100% finished final LoRA adapter (3,381 steps total)

.gitattributes

@@ -36,3 +36,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 fwizzervision.gguf filter=lfs diff=lfs merge=lfs -text
 lora_adapter_step2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 fwizzer-v3-ru-Q4_K_M-preview.gguf filter=lfs diff=lfs merge=lfs -text
+final_lora_adapter/checkpoint-1382/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+final_lora_adapter/tokenizer.json filter=lfs diff=lfs merge=lfs -text

final_lora_adapter/README.md

@@ -0,0 +1,62 @@
+---
+base_model: LiquidAI/LFM2.5-VL-3B
+library_name: peft
+model_name: final_lora_adapter
+tags:
+- base_model:adapter:LiquidAI/LFM2.5-VL-3B
+- lora
+- sft
+- transformers
+- trl
+licence: license
+pipeline_tag: text-generation
+---
+
+# Model Card for final_lora_adapter
+
+This model is a fine-tuned version of [LiquidAI/LFM2.5-VL-3B](https://huggingface.co/LiquidAI/LFM2.5-VL-3B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- PEFT 0.21.0
+- TRL: 1.13.0
+- Transformers: 5.17.0
+- Pytorch: 2.10.0+cu128
+- Datasets: 5.0.0
+- Tokenizers: 0.23.2
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```

final_lora_adapter/adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "LiquidAI/LFM2.5-VL-3B",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "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": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "out_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "fc2",
+    "fc1",
+    "up_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
+}

final_lora_adapter/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc30876e3c4516cd328bcf795010a4bd05a28fcbc310479cc24be4c27c11b7d
+size 47429984

final_lora_adapter/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" -}}
+{%- endif -%}

final_lora_adapter/checkpoint-1382/README.md

@@ -0,0 +1,209 @@
+---
+base_model: LiquidAI/LFM2.5-VL-3B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:LiquidAI/LFM2.5-VL-3B
+- lora
+- sft
+- transformers
+- trl
+---
+
+# 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 0.21.0

final_lora_adapter/checkpoint-1382/adapter_config.json

@@ -0,0 +1,53 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": null,
+  "base_model_name_or_path": "LiquidAI/LFM2.5-VL-3B",
+  "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,
+  "kasa_config": null,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "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": "0.21.0",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "v_proj",
+    "out_proj",
+    "k_proj",
+    "q_proj",
+    "gate_proj",
+    "fc2",
+    "fc1",
+    "up_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
+}

final_lora_adapter/checkpoint-1382/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fc30876e3c4516cd328bcf795010a4bd05a28fcbc310479cc24be4c27c11b7d
+size 47429984

final_lora_adapter/checkpoint-1382/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" -}}
+{%- endif -%}

final_lora_adapter/checkpoint-1382/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2a2339608756eaa0db7eec82f63807ecdbf7bb3eb525e51c5ca41657032173df
+size 12914059

final_lora_adapter/checkpoint-1382/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2aaced3796b22270bfd22b6c2573452d1337b03373f4906264cb15ae76629639
+size 14645

final_lora_adapter/checkpoint-1382/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f887b5cfa418b27872588c389f1f99355ed34a32c9c28f5f78a3a1945323a0e
+size 1465

final_lora_adapter/checkpoint-1382/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4687c0046da6579aba6f9aa713e9bed61e5fd210b0e012028ae57751d028689
+size 17905589

final_lora_adapter/checkpoint-1382/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "processor_class": "Lfm2VlProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false
+}

final_lora_adapter/checkpoint-1382/trainer_state.json

@@ -0,0 +1,1414 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 1382,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "entropy": 0.8322479248046875,
+      "epoch": 0.007239163876572256,
+      "grad_norm": 0.484375,
+      "learning_rate": 1.8e-05,
+      "loss": 0.9479166030883789,
+      "mean_token_accuracy": 0.8360646463930607,
+      "num_tokens": 70611.0,
+      "step": 10
+    },
+    {
+      "entropy": 0.816314697265625,
+      "epoch": 0.014478327753144511,
+      "grad_norm": 0.412109375,
+      "learning_rate": 3.8e-05,
+      "loss": 0.8869314193725586,
+      "mean_token_accuracy": 0.8404601871967315,
+      "num_tokens": 156340.0,
+      "step": 20
+    },
+    {
+      "entropy": 0.810443115234375,
+      "epoch": 0.021717491629716767,
+      "grad_norm": 0.404296875,
+      "learning_rate": 5.8e-05,
+      "loss": 0.9257671356201171,
+      "mean_token_accuracy": 0.8386005595326423,
+      "num_tokens": 242898.0,
+      "step": 30
+    },
+    {
+      "entropy": 0.8588623046875,
+      "epoch": 0.028956655506289022,
+      "grad_norm": 0.419921875,
+      "learning_rate": 5.99934399551023e-05,
+      "loss": 0.9337856292724609,
+      "mean_token_accuracy": 0.8272521700710058,
+      "num_tokens": 327862.0,
+      "step": 40
+    },
+    {
+      "entropy": 0.7262451171875,
+      "epoch": 0.03619581938286128,
+      "grad_norm": 0.294921875,
+      "learning_rate": 5.9970766939959345e-05,
+      "loss": 0.8554183959960937,
+      "mean_token_accuracy": 0.8505584582686424,
+      "num_tokens": 420672.0,
+      "step": 50
+    },
+    {
+      "entropy": 0.84827880859375,
+      "epoch": 0.043434983259433534,
+      "grad_norm": 0.359375,
+      "learning_rate": 5.9931912204988425e-05,
+      "loss": 0.9263783454895019,
+      "mean_token_accuracy": 0.8337412521243095,
+      "num_tokens": 513793.0,
+      "step": 60
+    },
+    {
+      "entropy": 0.721160888671875,
+      "epoch": 0.05067414713600579,
+      "grad_norm": 0.58984375,
+      "learning_rate": 5.987689672851273e-05,
+      "loss": 0.772972822189331,
+      "mean_token_accuracy": 0.8562263607978821,
+      "num_tokens": 595163.0,
+      "step": 70
+    },
+    {
+      "entropy": 0.6296539306640625,
+      "epoch": 0.057913311012578045,
+      "grad_norm": 0.390625,
+      "learning_rate": 5.980575021431089e-05,
+      "loss": 0.6224020957946778,
+      "mean_token_accuracy": 0.8738353997468948,
+      "num_tokens": 662097.0,
+      "step": 80
+    },
+    {
+      "entropy": 0.8087860107421875,
+      "epoch": 0.0651524748891503,
+      "grad_norm": 0.38671875,
+      "learning_rate": 5.971851107557941e-05,
+      "loss": 0.7844776630401611,
+      "mean_token_accuracy": 0.8436112560331821,
+      "num_tokens": 753051.0,
+      "step": 90
+    },
+    {
+      "entropy": 0.7270965576171875,
+      "epoch": 0.07239163876572256,
+      "grad_norm": 0.416015625,
+      "learning_rate": 5.96152264141927e-05,
+      "loss": 0.7176575183868408,
+      "mean_token_accuracy": 0.8571018680930138,
+      "num_tokens": 835622.0,
+      "step": 100
+    },
+    {
+      "entropy": 0.8564697265625,
+      "epoch": 0.07963080264229482,
+      "grad_norm": 0.44921875,
+      "learning_rate": 5.949595199527205e-05,
+      "loss": 0.9645451545715332,
+      "mean_token_accuracy": 0.8332631971687079,
+      "num_tokens": 928257.0,
+      "step": 110
+    },
+    {
+      "entropy": 0.7866668701171875,
+      "epoch": 0.08686996651886707,
+      "grad_norm": 0.40234375,
+      "learning_rate": 5.9360752217077046e-05,
+      "loss": 0.8222699165344238,
+      "mean_token_accuracy": 0.842054869607091,
+      "num_tokens": 1014257.0,
+      "step": 120
+    },
+    {
+      "entropy": 0.842718505859375,
+      "epoch": 0.09410913039543933,
+      "grad_norm": 0.546875,
+      "learning_rate": 5.92097000762359e-05,
+      "loss": 0.9575251579284668,
+      "mean_token_accuracy": 0.8313341937959194,
+      "num_tokens": 1094225.0,
+      "step": 130
+    },
+    {
+      "entropy": 0.769342041015625,
+      "epoch": 0.10134829427201159,
+      "grad_norm": 0.3359375,
+      "learning_rate": 5.904287712833335e-05,
+      "loss": 0.8275895118713379,
+      "mean_token_accuracy": 0.8427873060107232,
+      "num_tokens": 1172166.0,
+      "step": 140
+    },
+    {
+      "entropy": 0.7505462646484375,
+      "epoch": 0.10858745814858384,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.886037344387739e-05,
+      "loss": 0.7423648834228516,
+      "mean_token_accuracy": 0.8507181469351053,
+      "num_tokens": 1256456.0,
+      "step": 150
+    },
+    {
+      "entropy": 0.7898834228515625,
+      "epoch": 0.11582662202515609,
+      "grad_norm": 0.470703125,
+      "learning_rate": 5.8662287559668767e-05,
+      "loss": 0.8192078590393066,
+      "mean_token_accuracy": 0.8396460119634866,
+      "num_tokens": 1339982.0,
+      "step": 160
+    },
+    {
+      "entropy": 0.7197906494140625,
+      "epoch": 0.12306578590172836,
+      "grad_norm": 0.3515625,
+      "learning_rate": 5.844872642559922e-05,
+      "loss": 0.7335642337799072,
+      "mean_token_accuracy": 0.8542032733559608,
+      "num_tokens": 1426973.0,
+      "step": 170
+    },
+    {
+      "entropy": 0.762115478515625,
+      "epoch": 0.1303049497783006,
+      "grad_norm": 0.4609375,
+      "learning_rate": 5.82198053469075e-05,
+      "loss": 0.801086711883545,
+      "mean_token_accuracy": 0.8482539534568787,
+      "num_tokens": 1520858.0,
+      "step": 180
+    },
+    {
+      "entropy": 0.7031097412109375,
+      "epoch": 0.13754411365487287,
+      "grad_norm": 0.43359375,
+      "learning_rate": 5.797564792192415e-05,
+      "loss": 0.6864665031433106,
+      "mean_token_accuracy": 0.8647237375378609,
+      "num_tokens": 1603986.0,
+      "step": 190
+    },
+    {
+      "entropy": 0.696856689453125,
+      "epoch": 0.14478327753144513,
+      "grad_norm": 0.40234375,
+      "learning_rate": 5.7716385975338605e-05,
+      "loss": 0.6935067176818848,
+      "mean_token_accuracy": 0.8612518757581711,
+      "num_tokens": 1682597.0,
+      "step": 200
+    },
+    {
+      "entropy": 0.7810882568359375,
+      "epoch": 0.15202244140801738,
+      "grad_norm": 0.35546875,
+      "learning_rate": 5.744215948702495e-05,
+      "loss": 0.9324642181396484,
+      "mean_token_accuracy": 0.8469463251531124,
+      "num_tokens": 1767455.0,
+      "step": 210
+    },
+    {
+      "entropy": 0.8328704833984375,
+      "epoch": 0.15926160528458963,
+      "grad_norm": 0.419921875,
+      "learning_rate": 5.715311651646433e-05,
+      "loss": 0.9347438812255859,
+      "mean_token_accuracy": 0.831748116761446,
+      "num_tokens": 1853662.0,
+      "step": 220
+    },
+    {
+      "entropy": 0.9211517333984375,
+      "epoch": 0.16650076916116188,
+      "grad_norm": 0.408203125,
+      "learning_rate": 5.684941312280525e-05,
+      "loss": 0.9761329650878906,
+      "mean_token_accuracy": 0.8147442992776632,
+      "num_tokens": 1950241.0,
+      "step": 230
+    },
+    {
+      "entropy": 0.7584136962890625,
+      "epoch": 0.17373993303773413,
+      "grad_norm": 0.44140625,
+      "learning_rate": 5.653121328060451e-05,
+      "loss": 0.8082932472229004,
+      "mean_token_accuracy": 0.84579848498106,
+      "num_tokens": 2035756.0,
+      "step": 240
+    },
+    {
+      "entropy": 0.8130584716796875,
+      "epoch": 0.1809790969143064,
+      "grad_norm": 0.484375,
+      "learning_rate": 5.6198688791294725e-05,
+      "loss": 0.8762928962707519,
+      "mean_token_accuracy": 0.8388490982353687,
+      "num_tokens": 2114523.0,
+      "step": 250
+    },
+    {
+      "entropy": 0.86767578125,
+      "epoch": 0.18821826079087867,
+      "grad_norm": 0.4453125,
+      "learning_rate": 5.585201919042573e-05,
+      "loss": 0.931730079650879,
+      "mean_token_accuracy": 0.8247872211039067,
+      "num_tokens": 2199118.0,
+      "step": 260
+    },
+    {
+      "entropy": 0.700244140625,
+      "epoch": 0.19545742466745092,
+      "grad_norm": 0.33984375,
+      "learning_rate": 5.5491391650730376e-05,
+      "loss": 0.6926840305328369,
+      "mean_token_accuracy": 0.8568826846778392,
+      "num_tokens": 2268183.0,
+      "step": 270
+    },
+    {
+      "entropy": 0.7199005126953125,
+      "epoch": 0.20269658854402317,
+      "grad_norm": 0.318359375,
+      "learning_rate": 5.511700088106686e-05,
+      "loss": 0.7880847930908204,
+      "mean_token_accuracy": 0.8556432791054249,
+      "num_tokens": 2350924.0,
+      "step": 280
+    },
+    {
+      "entropy": 0.8306976318359375,
+      "epoch": 0.20993575242059542,
+      "grad_norm": 0.40625,
+      "learning_rate": 5.4729049021292075e-05,
+      "loss": 0.8660375595092773,
+      "mean_token_accuracy": 0.835714265704155,
+      "num_tokens": 2428629.0,
+      "step": 290
+    },
+    {
+      "entropy": 0.7435699462890625,
+      "epoch": 0.21717491629716767,
+      "grad_norm": 0.41796875,
+      "learning_rate": 5.432774553312299e-05,
+      "loss": 0.7700780391693115,
+      "mean_token_accuracy": 0.8517562672495842,
+      "num_tokens": 2518414.0,
+      "step": 300
+    },
+    {
+      "entropy": 0.8248382568359375,
+      "epoch": 0.22441408017373993,
+      "grad_norm": 0.451171875,
+      "learning_rate": 5.39133070870447e-05,
+      "loss": 0.8359769821166992,
+      "mean_token_accuracy": 0.8345334623008966,
+      "num_tokens": 2607283.0,
+      "step": 310
+    },
+    {
+      "entropy": 0.811962890625,
+      "epoch": 0.23165324405031218,
+      "grad_norm": 0.349609375,
+      "learning_rate": 5.34859574453264e-05,
+      "loss": 0.8170008659362793,
+      "mean_token_accuracy": 0.8426620949059724,
+      "num_tokens": 2687578.0,
+      "step": 320
+    },
+    {
+      "entropy": 0.7136322021484375,
+      "epoch": 0.23889240792688443,
+      "grad_norm": 0.361328125,
+      "learning_rate": 5.304592734120842e-05,
+      "loss": 0.7813081264495849,
+      "mean_token_accuracy": 0.8557253245264291,
+      "num_tokens": 2775165.0,
+      "step": 330
+    },
+    {
+      "entropy": 0.8272216796875,
+      "epoch": 0.2461315718034567,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.2593454354325427e-05,
+      "loss": 0.9407460212707519,
+      "mean_token_accuracy": 0.8336556099355221,
+      "num_tokens": 2864918.0,
+      "step": 340
+    },
+    {
+      "entropy": 0.6231170654296875,
+      "epoch": 0.25337073568002894,
+      "grad_norm": 0.34765625,
+      "learning_rate": 5.212878278243325e-05,
+      "loss": 0.6186163902282715,
+      "mean_token_accuracy": 0.8784980282187462,
+      "num_tokens": 2936251.0,
+      "step": 350
+    },
+    {
+      "entropy": 0.843853759765625,
+      "epoch": 0.2606098995566012,
+      "grad_norm": 0.435546875,
+      "learning_rate": 5.165216350950839e-05,
+      "loss": 0.8939202308654786,
+      "mean_token_accuracy": 0.8307482793927192,
+      "num_tokens": 3033669.0,
+      "step": 360
+    },
+    {
+      "entropy": 0.8030517578125,
+      "epoch": 0.2678490634331735,
+      "grad_norm": 0.421875,
+      "learning_rate": 5.116385387029151e-05,
+      "loss": 0.7158105373382568,
+      "mean_token_accuracy": 0.8397417701780796,
+      "num_tokens": 3120871.0,
+      "step": 370
+    },
+    {
+      "entropy": 0.7248138427734375,
+      "epoch": 0.27508822730974575,
+      "grad_norm": 0.3828125,
+      "learning_rate": 5.066411751134821e-05,
+      "loss": 0.7462657928466797,
+      "mean_token_accuracy": 0.8572716169059277,
+      "num_tokens": 3195794.0,
+      "step": 380
+    },
+    {
+      "entropy": 0.7069610595703125,
+      "epoch": 0.282327391186318,
+      "grad_norm": 0.478515625,
+      "learning_rate": 5.0153224248721696e-05,
+      "loss": 0.7200709819793701,
+      "mean_token_accuracy": 0.856803335249424,
+      "num_tokens": 3273902.0,
+      "step": 390
+    },
+    {
+      "entropy": 0.767657470703125,
+      "epoch": 0.28956655506289025,
+      "grad_norm": 0.361328125,
+      "learning_rate": 4.963144992225468e-05,
+      "loss": 0.8185941696166992,
+      "mean_token_accuracy": 0.8499114356935025,
+      "num_tokens": 3362421.0,
+      "step": 400
+    },
+    {
+      "entropy": 0.8690216064453125,
+      "epoch": 0.2968057189394625,
+      "grad_norm": 0.326171875,
+      "learning_rate": 4.9099076246658705e-05,
+      "loss": 1.0170391082763672,
+      "mean_token_accuracy": 0.8240880731493234,
+      "num_tokens": 3443822.0,
+      "step": 410
+    },
+    {
+      "entropy": 0.7837860107421875,
+      "epoch": 0.30404488281603476,
+      "grad_norm": 0.5859375,
+      "learning_rate": 4.855639065941178e-05,
+      "loss": 0.8953167915344238,
+      "mean_token_accuracy": 0.8427618652582168,
+      "num_tokens": 3520352.0,
+      "step": 420
+    },
+    {
+      "entropy": 0.7201446533203125,
+      "epoch": 0.311284046692607,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.800368616556595e-05,
+      "loss": 0.743995189666748,
+      "mean_token_accuracy": 0.8577177945524455,
+      "num_tokens": 3611533.0,
+      "step": 430
+    },
+    {
+      "entropy": 0.786016845703125,
+      "epoch": 0.31852321056917926,
+      "grad_norm": 0.4453125,
+      "learning_rate": 4.7441261179549005e-05,
+      "loss": 0.8680895805358887,
+      "mean_token_accuracy": 0.841073314845562,
+      "num_tokens": 3697902.0,
+      "step": 440
+    },
+    {
+      "entropy": 0.7629608154296875,
+      "epoch": 0.3257623744457515,
+      "grad_norm": 0.353515625,
+      "learning_rate": 4.686941936404555e-05,
+      "loss": 0.8256475448608398,
+      "mean_token_accuracy": 0.8525758445262909,
+      "num_tokens": 3780888.0,
+      "step": 450
+    },
+    {
+      "entropy": 0.7036102294921875,
+      "epoch": 0.33300153832232376,
+      "grad_norm": 0.49609375,
+      "learning_rate": 4.628846946604436e-05,
+      "loss": 0.6705307006835938,
+      "mean_token_accuracy": 0.8582501776516438,
+      "num_tokens": 3855476.0,
+      "step": 460
+    },
+    {
+      "entropy": 0.7460968017578125,
+      "epoch": 0.340240702198896,
+      "grad_norm": 0.4296875,
+      "learning_rate": 4.569872515014075e-05,
+      "loss": 0.8553385734558105,
+      "mean_token_accuracy": 0.8557162567973137,
+      "num_tokens": 3931261.0,
+      "step": 470
+    },
+    {
+      "entropy": 0.833587646484375,
+      "epoch": 0.34747986607546827,
+      "grad_norm": 0.5078125,
+      "learning_rate": 4.510050482918379e-05,
+      "loss": 0.9107108116149902,
+      "mean_token_accuracy": 0.8283740486949682,
+      "num_tokens": 4012572.0,
+      "step": 480
+    },
+    {
+      "entropy": 0.8649169921875,
+      "epoch": 0.3547190299520405,
+      "grad_norm": 0.357421875,
+      "learning_rate": 4.449413149235987e-05,
+      "loss": 1.0045209884643556,
+      "mean_token_accuracy": 0.8251449435949325,
+      "num_tokens": 4101452.0,
+      "step": 490
+    },
+    {
+      "entropy": 0.7789398193359375,
+      "epoch": 0.3619581938286128,
+      "grad_norm": 0.416015625,
+      "learning_rate": 4.3879932530805374e-05,
+      "loss": 0.8723062515258789,
+      "mean_token_accuracy": 0.842498754709959,
+      "num_tokens": 4180794.0,
+      "step": 500
+    },
+    {
+      "entropy": 0.729541015625,
+      "epoch": 0.369197357705185,
+      "grad_norm": 0.271484375,
+      "learning_rate": 4.325823956084282e-05,
+      "loss": 0.8393686294555665,
+      "mean_token_accuracy": 0.857572266459465,
+      "num_tokens": 4268891.0,
+      "step": 510
+    },
+    {
+      "entropy": 0.798614501953125,
+      "epoch": 0.37643652158175733,
+      "grad_norm": 0.447265625,
+      "learning_rate": 4.262938824493551e-05,
+      "loss": 0.8622625350952149,
+      "mean_token_accuracy": 0.8415737390518189,
+      "num_tokens": 4361394.0,
+      "step": 520
+    },
+    {
+      "entropy": 0.88697509765625,
+      "epoch": 0.3836756854583296,
+      "grad_norm": 0.330078125,
+      "learning_rate": 4.1993718110457826e-05,
+      "loss": 0.8443498611450195,
+      "mean_token_accuracy": 0.8264718905091286,
+      "num_tokens": 4460920.0,
+      "step": 530
+    },
+    {
+      "entropy": 0.6903717041015625,
+      "epoch": 0.39091484933490184,
+      "grad_norm": 0.369140625,
+      "learning_rate": 4.135157236637871e-05,
+      "loss": 0.7598116397857666,
+      "mean_token_accuracy": 0.8594527304172516,
+      "num_tokens": 4541148.0,
+      "step": 540
+    },
+    {
+      "entropy": 0.721282958984375,
+      "epoch": 0.3981540132114741,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.070329771795732e-05,
+      "loss": 0.7740339279174805,
+      "mean_token_accuracy": 0.8610655214637518,
+      "num_tokens": 4635444.0,
+      "step": 550
+    },
+    {
+      "entropy": 0.8269500732421875,
+      "epoch": 0.40539317708804634,
+      "grad_norm": 0.353515625,
+      "learning_rate": 4.004924417955108e-05,
+      "loss": 0.825250244140625,
+      "mean_token_accuracy": 0.8331068232655525,
+      "num_tokens": 4721251.0,
+      "step": 560
+    },
+    {
+      "entropy": 0.7193084716796875,
+      "epoch": 0.4126323409646186,
+      "grad_norm": 0.458984375,
+      "learning_rate": 3.938976488563708e-05,
+      "loss": 0.8023367881774902,
+      "mean_token_accuracy": 0.8562697798013688,
+      "num_tokens": 4806719.0,
+      "step": 570
+    },
+    {
+      "entropy": 0.7294952392578125,
+      "epoch": 0.41987150484119085,
+      "grad_norm": 0.390625,
+      "learning_rate": 3.8725215900148826e-05,
+      "loss": 0.8293789863586426,
+      "mean_token_accuracy": 0.8541061274707318,
+      "num_tokens": 4886949.0,
+      "step": 580
+    },
+    {
+      "entropy": 0.697576904296875,
+      "epoch": 0.4271106687177631,
+      "grad_norm": 0.53515625,
+      "learning_rate": 3.8055956024231304e-05,
+      "loss": 0.8334012985229492,
+      "mean_token_accuracy": 0.8646453101187944,
+      "num_tokens": 4957317.0,
+      "step": 590
+    },
+    {
+      "entropy": 0.8054443359375,
+      "epoch": 0.43434983259433535,
+      "grad_norm": 0.59765625,
+      "learning_rate": 3.738234660251832e-05,
+      "loss": 0.8302848815917969,
+      "mean_token_accuracy": 0.8361291415989399,
+      "num_tokens": 5043100.0,
+      "step": 600
+    },
+    {
+      "entropy": 0.85704345703125,
+      "epoch": 0.4415889964709076,
+      "grad_norm": 0.421875,
+      "learning_rate": 3.6704751328036406e-05,
+      "loss": 0.941845703125,
+      "mean_token_accuracy": 0.8305374506860972,
+      "num_tokens": 5138853.0,
+      "step": 610
+    },
+    {
+      "entropy": 0.782891845703125,
+      "epoch": 0.44882816034747985,
+      "grad_norm": 0.37890625,
+      "learning_rate": 3.602353604584084e-05,
+      "loss": 0.8551918029785156,
+      "mean_token_accuracy": 0.841140752658248,
+      "num_tokens": 5220494.0,
+      "step": 620
+    },
+    {
+      "entropy": 0.6114044189453125,
+      "epoch": 0.4560673242240521,
+      "grad_norm": 0.43359375,
+      "learning_rate": 3.533906855548981e-05,
+      "loss": 0.6463155746459961,
+      "mean_token_accuracy": 0.8827056974172592,
+      "num_tokens": 5299489.0,
+      "step": 630
+    },
+    {
+      "entropy": 0.8378082275390625,
+      "epoch": 0.46330648810062436,
+      "grad_norm": 0.435546875,
+      "learning_rate": 3.465171841246326e-05,
+      "loss": 0.9589820861816406,
+      "mean_token_accuracy": 0.8343375381082296,
+      "num_tokens": 5393982.0,
+      "step": 640
+    },
+    {
+      "entropy": 0.7419464111328125,
+      "epoch": 0.4705456519771966,
+      "grad_norm": 0.3515625,
+      "learning_rate": 3.3961856728633635e-05,
+      "loss": 0.6938281536102295,
+      "mean_token_accuracy": 0.8505682967603206,
+      "num_tokens": 5477833.0,
+      "step": 650
+    },
+    {
+      "entropy": 0.7317962646484375,
+      "epoch": 0.47778481585376886,
+      "grad_norm": 0.3984375,
+      "learning_rate": 3.32698559718964e-05,
+      "loss": 0.7451235771179199,
+      "mean_token_accuracy": 0.8580109473317862,
+      "num_tokens": 5565147.0,
+      "step": 660
+    },
+    {
+      "entropy": 0.8810272216796875,
+      "epoch": 0.48502397973034117,
+      "grad_norm": 0.35546875,
+      "learning_rate": 3.257608976506838e-05,
+      "loss": 0.8695181846618653,
+      "mean_token_accuracy": 0.8218458566814661,
+      "num_tokens": 5663447.0,
+      "step": 670
+    },
+    {
+      "entropy": 0.773126220703125,
+      "epoch": 0.4922631436069134,
+      "grad_norm": 0.40625,
+      "learning_rate": 3.188093268416252e-05,
+      "loss": 0.8328439712524414,
+      "mean_token_accuracy": 0.8455472465604543,
+      "num_tokens": 5750977.0,
+      "step": 680
+    },
+    {
+      "entropy": 0.77906494140625,
+      "epoch": 0.4995023074834857,
+      "grad_norm": 0.4296875,
+      "learning_rate": 3.118476005614799e-05,
+      "loss": 0.8249894142150879,
+      "mean_token_accuracy": 0.8479911275207996,
+      "num_tokens": 5837819.0,
+      "step": 690
+    },
+    {
+      "entropy": 0.6968475341796875,
+      "epoch": 0.5067414713600579,
+      "grad_norm": 0.431640625,
+      "learning_rate": 3.048794775630489e-05,
+      "loss": 0.8187706947326661,
+      "mean_token_accuracy": 0.8634788691997528,
+      "num_tokens": 5922880.0,
+      "step": 700
+    },
+    {
+      "entropy": 0.866217041015625,
+      "epoch": 0.5139806352366302,
+      "grad_norm": 0.412109375,
+      "learning_rate": 2.9790872005282897e-05,
+      "loss": 0.9423279762268066,
+      "mean_token_accuracy": 0.8238799467682838,
+      "num_tokens": 6014378.0,
+      "step": 710
+    },
+    {
+      "entropy": 0.7442413330078125,
+      "epoch": 0.5212197991132024,
+      "grad_norm": 0.474609375,
+      "learning_rate": 2.909390916597334e-05,
+      "loss": 0.7882026195526123,
+      "mean_token_accuracy": 0.8526062082499266,
+      "num_tokens": 6102696.0,
+      "step": 720
+    },
+    {
+      "entropy": 0.8602020263671875,
+      "epoch": 0.5284589629897747,
+      "grad_norm": 0.400390625,
+      "learning_rate": 2.8397435540304674e-05,
+      "loss": 0.9652918815612793,
+      "mean_token_accuracy": 0.8206243008375168,
+      "num_tokens": 6186735.0,
+      "step": 730
+    },
+    {
+      "entropy": 0.6321136474609375,
+      "epoch": 0.535698126866347,
+      "grad_norm": 0.2890625,
+      "learning_rate": 2.770182716607068e-05,
+      "loss": 0.6824097633361816,
+      "mean_token_accuracy": 0.8776404835283756,
+      "num_tokens": 6267516.0,
+      "step": 740
+    },
+    {
+      "entropy": 0.695721435546875,
+      "epoch": 0.5429372907429192,
+      "grad_norm": 0.33984375,
+      "learning_rate": 2.700745961390138e-05,
+      "loss": 0.7164861679077148,
+      "mean_token_accuracy": 0.8648113217204809,
+      "num_tokens": 6362433.0,
+      "step": 750
+    },
+    {
+      "entropy": 0.7808319091796875,
+      "epoch": 0.5501764546194915,
+      "grad_norm": 0.306640625,
+      "learning_rate": 2.6314707784486147e-05,
+      "loss": 0.8339343070983887,
+      "mean_token_accuracy": 0.8476159241050482,
+      "num_tokens": 6451213.0,
+      "step": 760
+    },
+    {
+      "entropy": 0.69156494140625,
+      "epoch": 0.5574156184960637,
+      "grad_norm": 0.388671875,
+      "learning_rate": 2.5623945706158537e-05,
+      "loss": 0.6374184131622315,
+      "mean_token_accuracy": 0.862713135033846,
+      "num_tokens": 6534069.0,
+      "step": 770
+    },
+    {
+      "entropy": 0.71236572265625,
+      "epoch": 0.564654782372636,
+      "grad_norm": 0.291015625,
+      "learning_rate": 2.4935546332952122e-05,
+      "loss": 0.7573229312896729,
+      "mean_token_accuracy": 0.855223524197936,
+      "num_tokens": 6603326.0,
+      "step": 780
+    },
+    {
+      "entropy": 0.7222381591796875,
+      "epoch": 0.5718939462492082,
+      "grad_norm": 0.40625,
+      "learning_rate": 2.4249881343236318e-05,
+      "loss": 0.8560401916503906,
+      "mean_token_accuracy": 0.8581994403153658,
+      "num_tokens": 6668995.0,
+      "step": 790
+    },
+    {
+      "entropy": 0.7733428955078125,
+      "epoch": 0.5791331101257805,
+      "grad_norm": 0.314453125,
+      "learning_rate": 2.3567320939041053e-05,
+      "loss": 0.8729860305786132,
+      "mean_token_accuracy": 0.842813192307949,
+      "num_tokens": 6757448.0,
+      "step": 800
+    },
+    {
+      "entropy": 0.84246826171875,
+      "epoch": 0.5863722740023527,
+      "grad_norm": 0.384765625,
+      "learning_rate": 2.2888233646178453e-05,
+      "loss": 0.849764633178711,
+      "mean_token_accuracy": 0.8327675368636847,
+      "num_tokens": 6862564.0,
+      "step": 810
+    },
+    {
+      "entropy": 0.73311767578125,
+      "epoch": 0.593611437878925,
+      "grad_norm": 0.39453125,
+      "learning_rate": 2.221298611526956e-05,
+      "loss": 0.7988199234008789,
+      "mean_token_accuracy": 0.8525001965463161,
+      "num_tokens": 6957319.0,
+      "step": 820
+    },
+    {
+      "entropy": 0.78294677734375,
+      "epoch": 0.6008506017554972,
+      "grad_norm": 0.38671875,
+      "learning_rate": 2.1541942923783534e-05,
+      "loss": 0.8634878158569336,
+      "mean_token_accuracy": 0.8401406228542327,
+      "num_tokens": 7050152.0,
+      "step": 830
+    },
+    {
+      "entropy": 0.7700408935546875,
+      "epoch": 0.6080897656320695,
+      "grad_norm": 0.478515625,
+      "learning_rate": 2.0875466379196156e-05,
+      "loss": 0.8850546836853027,
+      "mean_token_accuracy": 0.8405523877590895,
+      "num_tokens": 7134401.0,
+      "step": 840
+    },
+    {
+      "entropy": 0.7931365966796875,
+      "epoch": 0.6153289295086417,
+      "grad_norm": 0.287109375,
+      "learning_rate": 2.0213916323373927e-05,
+      "loss": 0.8856608390808105,
+      "mean_token_accuracy": 0.8434151880443096,
+      "num_tokens": 7220092.0,
+      "step": 850
+    },
+    {
+      "entropy": 0.6447265625,
+      "epoch": 0.622568093385214,
+      "grad_norm": 0.443359375,
+      "learning_rate": 1.955764993828943e-05,
+      "loss": 0.6205445766448975,
+      "mean_token_accuracy": 0.8717406071722508,
+      "num_tokens": 7296158.0,
+      "step": 860
+    },
+    {
+      "entropy": 0.8651702880859375,
+      "epoch": 0.6298072572617862,
+      "grad_norm": 0.376953125,
+      "learning_rate": 1.8907021553172797e-05,
+      "loss": 0.9644915580749511,
+      "mean_token_accuracy": 0.82748286947608,
+      "num_tokens": 7379693.0,
+      "step": 870
+    },
+    {
+      "entropy": 0.67086181640625,
+      "epoch": 0.6370464211383585,
+      "grad_norm": 0.408203125,
+      "learning_rate": 1.826238245320338e-05,
+      "loss": 0.7624139785766602,
+      "mean_token_accuracy": 0.8707406416535377,
+      "num_tokens": 7453389.0,
+      "step": 880
+    },
+    {
+      "entropy": 0.6929962158203125,
+      "epoch": 0.6442855850149308,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.7624080689845023e-05,
+      "loss": 0.7496961116790771,
+      "mean_token_accuracy": 0.8618962876498699,
+      "num_tokens": 7523792.0,
+      "step": 890
+    },
+    {
+      "entropy": 0.6874267578125,
+      "epoch": 0.651524748891503,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.6992460892927223e-05,
+      "loss": 0.7529423713684082,
+      "mean_token_accuracy": 0.869031174480915,
+      "num_tokens": 7592461.0,
+      "step": 900
+    },
+    {
+      "entropy": 0.77420654296875,
+      "epoch": 0.6587639127680753,
+      "grad_norm": 0.40625,
+      "learning_rate": 1.6367864084573703e-05,
+      "loss": 0.7879415512084961,
+      "mean_token_accuracy": 0.8437226686626673,
+      "num_tokens": 7669219.0,
+      "step": 910
+    },
+    {
+      "entropy": 0.6737091064453125,
+      "epoch": 0.6660030766446475,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 1.5750627495078837e-05,
+      "loss": 0.766674280166626,
+      "mean_token_accuracy": 0.8683875583112239,
+      "num_tokens": 7759058.0,
+      "step": 920
+    },
+    {
+      "entropy": 0.778375244140625,
+      "epoch": 0.6732422405212198,
+      "grad_norm": 0.3828125,
+      "learning_rate": 1.5141084380831403e-05,
+      "loss": 0.8818301200866699,
+      "mean_token_accuracy": 0.8441133990883827,
+      "num_tokens": 7844937.0,
+      "step": 930
+    },
+    {
+      "entropy": 0.6036346435546875,
+      "epoch": 0.680481404397792,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.453956384438382e-05,
+      "loss": 0.5891834735870362,
+      "mean_token_accuracy": 0.8856886304914952,
+      "num_tokens": 7929552.0,
+      "step": 940
+    },
+    {
+      "entropy": 0.75638427734375,
+      "epoch": 0.6877205682743643,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.3946390656764174e-05,
+      "loss": 0.7903366565704346,
+      "mean_token_accuracy": 0.8432751290500164,
+      "num_tokens": 8016561.0,
+      "step": 950
+    },
+    {
+      "entropy": 0.6901397705078125,
+      "epoch": 0.6949597321509365,
+      "grad_norm": 0.42578125,
+      "learning_rate": 1.336188508212687e-05,
+      "loss": 0.779489278793335,
+      "mean_token_accuracy": 0.8635132625699043,
+      "num_tokens": 8082578.0,
+      "step": 960
+    },
+    {
+      "entropy": 0.7031890869140625,
+      "epoch": 0.7021988960275088,
+      "grad_norm": 0.28125,
+      "learning_rate": 1.2786362704836703e-05,
+      "loss": 0.7171487808227539,
+      "mean_token_accuracy": 0.8617708794772625,
+      "num_tokens": 8177241.0,
+      "step": 970
+    },
+    {
+      "entropy": 0.839459228515625,
+      "epoch": 0.709438059904081,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.22201342590795e-05,
+      "loss": 0.8655356407165528,
+      "mean_token_accuracy": 0.8327946338802577,
+      "num_tokens": 8273815.0,
+      "step": 980
+    },
+    {
+      "entropy": 0.7335845947265625,
+      "epoch": 0.7166772237806533,
+      "grad_norm": 0.248046875,
+      "learning_rate": 1.166350546109156e-05,
+      "loss": 0.7076152801513672,
+      "mean_token_accuracy": 0.8533464554697275,
+      "num_tokens": 8369479.0,
+      "step": 990
+    },
+    {
+      "entropy": 0.79669189453125,
+      "epoch": 0.7239163876572255,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.1116776844098338e-05,
+      "loss": 0.9288304328918457,
+      "mean_token_accuracy": 0.841159836575389,
+      "num_tokens": 8453141.0,
+      "step": 1000
+    },
+    {
+      "entropy": 0.6672760009765625,
+      "epoch": 0.7311555515337979,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.0580243596051457e-05,
+      "loss": 0.7350835800170898,
+      "mean_token_accuracy": 0.8683274779468775,
+      "num_tokens": 8535389.0,
+      "step": 1010
+    },
+    {
+      "entropy": 0.6170654296875,
+      "epoch": 0.73839471541037,
+      "grad_norm": 0.28515625,
+      "learning_rate": 1.005419540025185e-05,
+      "loss": 0.6454466342926025,
+      "mean_token_accuracy": 0.8817882314324379,
+      "num_tokens": 8617148.0,
+      "step": 1020
+    },
+    {
+      "entropy": 0.7197113037109375,
+      "epoch": 0.7456338792869424,
+      "grad_norm": 0.375,
+      "learning_rate": 9.53891627894483e-06,
+      "loss": 0.7777271747589112,
+      "mean_token_accuracy": 0.8586556639522314,
+      "num_tokens": 8702751.0,
+      "step": 1030
+    },
+    {
+      "entropy": 0.7601898193359375,
+      "epoch": 0.7528730431635147,
+      "grad_norm": 0.462890625,
+      "learning_rate": 9.034684439971757e-06,
+      "loss": 0.843805980682373,
+      "mean_token_accuracy": 0.8539392966777086,
+      "num_tokens": 8786998.0,
+      "step": 1040
+    },
+    {
+      "entropy": 0.69510498046875,
+      "epoch": 0.7601122070400869,
+      "grad_norm": 0.4296875,
+      "learning_rate": 8.54177212656093e-06,
+      "loss": 0.8157782554626465,
+      "mean_token_accuracy": 0.8642242655158043,
+      "num_tokens": 8861754.0,
+      "step": 1050
+    },
+    {
+      "entropy": 0.758831787109375,
+      "epoch": 0.7673513709166592,
+      "grad_norm": 0.412109375,
+      "learning_rate": 8.060445470338945e-06,
+      "loss": 0.7891167640686035,
+      "mean_token_accuracy": 0.8463997758924962,
+      "num_tokens": 8950386.0,
+      "step": 1060
+    },
+    {
+      "entropy": 0.707177734375,
+      "epoch": 0.7745905347932314,
+      "grad_norm": 0.31640625,
+      "learning_rate": 7.590964347641698e-06,
+      "loss": 0.6831569671630859,
+      "mean_token_accuracy": 0.8668574962764979,
+      "num_tokens": 9039368.0,
+      "step": 1070
+    },
+    {
+      "entropy": 0.720458984375,
+      "epoch": 0.7818296986698037,
+      "grad_norm": 0.5390625,
+      "learning_rate": 7.133582239202852e-06,
+      "loss": 0.789151668548584,
+      "mean_token_accuracy": 0.859419421851635,
+      "num_tokens": 9121973.0,
+      "step": 1080
+    },
+    {
+      "entropy": 0.7022918701171875,
+      "epoch": 0.7890688625463759,
+      "grad_norm": 0.27734375,
+      "learning_rate": 6.688546093295274e-06,
+      "loss": 0.7421200275421143,
+      "mean_token_accuracy": 0.8614181064069271,
+      "num_tokens": 9223666.0,
+      "step": 1090
+    },
+    {
+      "entropy": 0.788519287109375,
+      "epoch": 0.7963080264229482,
+      "grad_norm": 0.392578125,
+      "learning_rate": 6.2560961923995995e-06,
+      "loss": 0.829339599609375,
+      "mean_token_accuracy": 0.8434589348733426,
+      "num_tokens": 9325648.0,
+      "step": 1100
+    },
+    {
+      "entropy": 0.8034423828125,
+      "epoch": 0.8035471902995204,
+      "grad_norm": 0.3359375,
+      "learning_rate": 5.8364660234716195e-06,
+      "loss": 0.8599503517150879,
+      "mean_token_accuracy": 0.8430331826210022,
+      "num_tokens": 9420763.0,
+      "step": 1110
+    },
+    {
+      "entropy": 0.700750732421875,
+      "epoch": 0.8107863541760927,
+      "grad_norm": 0.625,
+      "learning_rate": 5.42988215187882e-06,
+      "loss": 0.8167227745056153,
+      "mean_token_accuracy": 0.8588984727859497,
+      "num_tokens": 9501901.0,
+      "step": 1120
+    },
+    {
+      "entropy": 0.8838165283203125,
+      "epoch": 0.8180255180526649,
+      "grad_norm": 0.4296875,
+      "learning_rate": 5.03656409907387e-06,
+      "loss": 0.9279158592224122,
+      "mean_token_accuracy": 0.8224485643208027,
+      "num_tokens": 9601491.0,
+      "step": 1130
+    },
+    {
+      "entropy": 0.5804473876953125,
+      "epoch": 0.8252646819292372,
+      "grad_norm": 0.2890625,
+      "learning_rate": 4.656724224071364e-06,
+      "loss": 0.6006618499755859,
+      "mean_token_accuracy": 0.8917888589203358,
+      "num_tokens": 9679222.0,
+      "step": 1140
+    },
+    {
+      "entropy": 0.7591644287109375,
+      "epoch": 0.8325038458058094,
+      "grad_norm": 0.3203125,
+      "learning_rate": 4.290567608791596e-06,
+      "loss": 0.8360663414001465,
+      "mean_token_accuracy": 0.8491391457617283,
+      "num_tokens": 9770587.0,
+      "step": 1150
+    },
+    {
+      "entropy": 0.8829345703125,
+      "epoch": 0.8397430096823817,
+      "grad_norm": 0.318359375,
+      "learning_rate": 3.9382919473333945e-06,
+      "loss": 0.8953950881958008,
+      "mean_token_accuracy": 0.821895894408226,
+      "num_tokens": 9867927.0,
+      "step": 1160
+    },
+    {
+      "entropy": 0.821685791015625,
+      "epoch": 0.8469821735589539,
+      "grad_norm": 0.337890625,
+      "learning_rate": 3.6000874392357787e-06,
+      "loss": 0.8167933464050293,
+      "mean_token_accuracy": 0.8376239359378814,
+      "num_tokens": 9970981.0,
+      "step": 1170
+    },
+    {
+      "entropy": 0.9026397705078125,
+      "epoch": 0.8542213374355262,
+      "grad_norm": 0.58984375,
+      "learning_rate": 3.2761366867860154e-06,
+      "loss": 0.9733218193054199,
+      "mean_token_accuracy": 0.8199248895049095,
+      "num_tokens": 10076507.0,
+      "step": 1180
+    },
+    {
+      "entropy": 0.7585784912109375,
+      "epoch": 0.8614605013120985,
+      "grad_norm": 0.310546875,
+      "learning_rate": 2.9666145964296152e-06,
+      "loss": 0.8911943435668945,
+      "mean_token_accuracy": 0.8528259593993426,
+      "num_tokens": 10148539.0,
+      "step": 1190
+    },
+    {
+      "entropy": 0.905035400390625,
+      "epoch": 0.8686996651886707,
+      "grad_norm": 0.3046875,
+      "learning_rate": 2.671688284335362e-06,
+      "loss": 0.9361907958984375,
+      "mean_token_accuracy": 0.8157149743288755,
+      "num_tokens": 10241645.0,
+      "step": 1200
+    },
+    {
+      "entropy": 0.7633880615234375,
+      "epoch": 0.875938829065243,
+      "grad_norm": 0.4140625,
+      "learning_rate": 2.3915169861665198e-06,
+      "loss": 0.835942268371582,
+      "mean_token_accuracy": 0.8504331212490797,
+      "num_tokens": 10329935.0,
+      "step": 1210
+    },
+    {
+      "entropy": 0.765997314453125,
+      "epoch": 0.8831779929418152,
+      "grad_norm": 0.294921875,
+      "learning_rate": 2.126251971106812e-06,
+      "loss": 0.8076752662658692,
+      "mean_token_accuracy": 0.8466157495975495,
+      "num_tokens": 10420969.0,
+      "step": 1220
+    },
+    {
+      "entropy": 0.76702880859375,
+      "epoch": 0.8904171568183875,
+      "grad_norm": 0.380859375,
+      "learning_rate": 1.8760364601876756e-06,
+      "loss": 0.8637797355651855,
+      "mean_token_accuracy": 0.8468801237642765,
+      "num_tokens": 10511686.0,
+      "step": 1230
+    },
+    {
+      "entropy": 0.86865234375,
+      "epoch": 0.8976563206949597,
+      "grad_norm": 0.3984375,
+      "learning_rate": 1.64100554896079e-06,
+      "loss": 1.0514280319213867,
+      "mean_token_accuracy": 0.82753996104002,
+      "num_tokens": 10587241.0,
+      "step": 1240
+    },
+    {
+      "entropy": 0.8745208740234375,
+      "epoch": 0.904895484571532,
+      "grad_norm": 0.50390625,
+      "learning_rate": 1.4212861345577644e-06,
+      "loss": 0.9617470741271973,
+      "mean_token_accuracy": 0.8237643454223871,
+      "num_tokens": 10672418.0,
+      "step": 1250
+    },
+    {
+      "entropy": 0.7360260009765625,
+      "epoch": 0.9121346484481042,
+      "grad_norm": 0.451171875,
+      "learning_rate": 1.2169968471762039e-06,
+      "loss": 0.7651317119598389,
+      "mean_token_accuracy": 0.851446995139122,
+      "num_tokens": 10754089.0,
+      "step": 1260
+    },
+    {
+      "entropy": 0.7201263427734375,
+      "epoch": 0.9193738123246765,
+      "grad_norm": 0.302734375,
+      "learning_rate": 1.0282479860292982e-06,
+      "loss": 0.7677529811859131,
+      "mean_token_accuracy": 0.8598325382918119,
+      "num_tokens": 10846490.0,
+      "step": 1270
+    },
+    {
+      "entropy": 0.8267181396484375,
+      "epoch": 0.9266129762012487,
+      "grad_norm": 0.431640625,
+      "learning_rate": 8.551414597934348e-07,
+      "loss": 0.8606924057006836,
+      "mean_token_accuracy": 0.8425934970378876,
+      "num_tokens": 10937843.0,
+      "step": 1280
+    },
+    {
+      "entropy": 0.748846435546875,
+      "epoch": 0.933852140077821,
+      "grad_norm": 0.458984375,
+      "learning_rate": 6.97770731585966e-07,
+      "loss": 0.8599045753479004,
+      "mean_token_accuracy": 0.8498176697641611,
+      "num_tokens": 11027978.0,
+      "step": 1290
+    },
+    {
+      "entropy": 0.849554443359375,
+      "epoch": 0.9410913039543932,
+      "grad_norm": 0.369140625,
+      "learning_rate": 5.562207685029308e-07,
+      "loss": 0.9216291427612304,
+      "mean_token_accuracy": 0.8287993773818016,
+      "num_tokens": 11114226.0,
+      "step": 1300
+    },
+    {
+      "entropy": 0.9060333251953125,
+      "epoch": 0.9483304678309655,
+      "grad_norm": 0.388671875,
+      "learning_rate": 4.305679957438946e-07,
+      "loss": 0.9749002456665039,
+      "mean_token_accuracy": 0.8171696797013283,
+      "num_tokens": 11206224.0,
+      "step": 1310
+    },
+    {
+      "entropy": 0.7624542236328125,
+      "epoch": 0.9555696317075377,
+      "grad_norm": 0.390625,
+      "learning_rate": 3.2088025534868336e-07,
+      "loss": 0.8972819328308106,
+      "mean_token_accuracy": 0.845363051444292,
+      "num_tokens": 11287151.0,
+      "step": 1320
+    },
+    {
+      "entropy": 0.992388916015625,
+      "epoch": 0.96280879558411,
+      "grad_norm": 0.34375,
+      "learning_rate": 2.272167695683336e-07,
+      "loss": 1.0389726638793946,
+      "mean_token_accuracy": 0.8012281119823456,
+      "num_tokens": 11389819.0,
+      "step": 1330
+    },
+    {
+      "entropy": 0.8194122314453125,
+      "epoch": 0.9700479594606823,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.4962810889001975e-07,
+      "loss": 0.9017257690429688,
+      "mean_token_accuracy": 0.8311506144702434,
+      "num_tokens": 11473789.0,
+      "step": 1340
+    },
+    {
+      "entropy": 0.8580810546875,
+      "epoch": 0.9772871233372545,
+      "grad_norm": 0.57421875,
+      "learning_rate": 8.815616473318855e-08,
+      "loss": 1.085977268218994,
+      "mean_token_accuracy": 0.825254475697875,
+      "num_tokens": 11548426.0,
+      "step": 1350
+    },
+    {
+      "entropy": 0.776300048828125,
+      "epoch": 0.9845262872138268,
+      "grad_norm": 0.416015625,
+      "learning_rate": 4.2834126831667874e-08,
+      "loss": 0.885800552368164,
+      "mean_token_accuracy": 0.8478683464229106,
+      "num_tokens": 11626873.0,
+      "step": 1360
+    },
+    {
+      "entropy": 0.8324432373046875,
+      "epoch": 0.991765451090399,
+      "grad_norm": 0.5546875,
+      "learning_rate": 1.3686465313997865e-08,
+      "loss": 0.8458555221557618,
+      "mean_token_accuracy": 0.836217162758112,
+      "num_tokens": 11711674.0,
+      "step": 1370
+    },
+    {
+      "entropy": 0.8818603515625,
+      "epoch": 0.9990046149669713,
+      "grad_norm": 0.486328125,
+      "learning_rate": 7.289174915858787e-10,
+      "loss": 0.9346182823181153,
+      "mean_token_accuracy": 0.8219814684242011,
+      "num_tokens": 11799438.0,
+      "step": 1380
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1382,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.043840635412096e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

final_lora_adapter/checkpoint-1382/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b49bece7d2169d6365ccf64de856b1fb498c9665326ded341209e070fac6980
+size 5777

final_lora_adapter/processor_config.json

@@ -0,0 +1,39 @@
+{
+  "image_processor": {
+    "data_format": "channels_first",
+    "do_image_splitting": true,
+    "do_normalize": true,
+    "do_pad": true,
+    "do_rescale": true,
+    "do_resize": true,
+    "downsample_factor": 2,
+    "encoder_patch_size": 16,
+    "image_mean": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "image_processor_type": "Lfm2VlImageProcessor",
+    "image_std": [
+      0.5,
+      0.5,
+      0.5
+    ],
+    "max_image_tokens": 256,
+    "max_num_patches": 1024,
+    "max_pixels_tolerance": 2.0,
+    "max_tiles": 10,
+    "min_image_tokens": 64,
+    "min_tiles": 2,
+    "resample": 3,
+    "rescale_factor": 0.00392156862745098,
+    "return_row_col_info": true,
+    "size": {
+      "height": 512,
+      "width": 512
+    },
+    "tile_size": 512,
+    "use_thumbnail": true
+  },
+  "processor_class": "Lfm2VlProcessor"
+}

final_lora_adapter/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8096ecb9f54599d756c8de728a598a340bc1e43c0deb77ddd62456c38349fcee
+size 17905750

final_lora_adapter/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "max_length": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "<|pad|>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "processor_class": "Lfm2VlProcessor",
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false
+}