Training in progress, step 70, checkpoint

.gitattributes

@@ -40,3 +40,4 @@ checkpoint-30/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-40/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-50/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 checkpoint-60/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-70/tokenizer.json filter=lfs diff=lfs merge=lfs -text

checkpoint-70/README.md

@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Qwen3-14B
+library_name: peft
+---
+
+# 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 0.15.2

checkpoint-70/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Qwen3-14B",
+  "bias": "none",
+  "corda_config": null,
+  "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": 256,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "down_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "o_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": true
+}

checkpoint-70/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6bd633a24eb2cf44c7381db6cc34831bdca7930bc18ab06f40b9ebf6bb8c53f
+size 513877864

checkpoint-70/added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

checkpoint-70/chat_template.jinja

@@ -0,0 +1,98 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for forward_message in messages %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- set message = messages[index] %}
+    {%- set current_content = message.content if message.content is not none else '' %}
+    {%- set tool_start = '<tool_response>' %}
+    {%- set tool_start_length = tool_start|length %}
+    {%- set start_of_message = current_content[:tool_start_length] %}
+    {%- set tool_end = '</tool_response>' %}
+    {%- set tool_end_length = tool_end|length %}
+    {%- set start_pos = (current_content|length) - tool_end_length %}
+    {%- if start_pos < 0 %}
+        {%- set start_pos = 0 %}
+    {%- endif %}
+    {%- set end_of_message = current_content[start_pos:] %}
+    {%- if ns.multi_step_tool and message.role == "user" and not(start_of_message == tool_start and end_of_message == tool_end) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = (message.content.split('</think>')|last).lstrip('\n') %}
+                {%- set reasoning_content = (message.content.split('</think>')|first).rstrip('\n') %}
+                {%- set reasoning_content = (reasoning_content.split('<think>')|last).lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

checkpoint-70/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fd7582d403fcb2dcef72fd055b409b52e6e33ff0b68199670c344f0318a9afc
+size 261573541

checkpoint-70/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcd351f21b85e21c8d16f7af93e2d11681bf86dcc3e7de62eaa1122f6748953f
+size 14581

checkpoint-70/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51f05905443502cc2771a1e39c2f819c6f57bbb38b36e5ecbcb7476426c46ea3
+size 1465

checkpoint-70/special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|vision_pad|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-70/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

checkpoint-70/tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 40960,
+  "pad_token": "<|vision_pad|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-70/trainer_state.json

@@ -0,0 +1,811 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.17654476670870115,
+  "eval_steps": 10,
+  "global_step": 70,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "computed_total": 0.45715999603271484,
+      "epoch": 0.0025220680958385876,
+      "grad_norm": 102.097412109375,
+      "kl_loss": 6.5083294309431494e-09,
+      "learning_rate": 0.0,
+      "loss": 4.3237,
+      "sft_loss": 0.45650917291641235,
+      "step": 1
+    },
+    {
+      "computed_total": 0.555546760559082,
+      "epoch": 0.005044136191677175,
+      "grad_norm": 87.49225616455078,
+      "kl_loss": 5.4945092919922445e-09,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 4.3036,
+      "sft_loss": 0.5549973249435425,
+      "step": 2
+    },
+    {
+      "computed_total": 0.5587829947471619,
+      "epoch": 0.007566204287515763,
+      "grad_norm": 64.52155303955078,
+      "kl_loss": 3.4872137177899276e-08,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 3.5946,
+      "sft_loss": 0.5552957653999329,
+      "step": 3
+    },
+    {
+      "computed_total": 0.4053139090538025,
+      "epoch": 0.01008827238335435,
+      "grad_norm": 79.32300567626953,
+      "kl_loss": 7.649157964806363e-07,
+      "learning_rate": 1.2e-05,
+      "loss": 3.3472,
+      "sft_loss": 0.3288223147392273,
+      "step": 4
+    },
+    {
+      "computed_total": 0.3922015130519867,
+      "epoch": 0.012610340479192938,
+      "grad_norm": 49.438594818115234,
+      "kl_loss": 9.65095068750088e-07,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 3.0682,
+      "sft_loss": 0.29569199681282043,
+      "step": 5
+    },
+    {
+      "computed_total": 0.3126932382583618,
+      "epoch": 0.015132408575031526,
+      "grad_norm": 36.26791000366211,
+      "kl_loss": 9.634337629904621e-07,
+      "learning_rate": 2e-05,
+      "loss": 2.7815,
+      "sft_loss": 0.21634985506534576,
+      "step": 6
+    },
+    {
+      "computed_total": 0.2588472068309784,
+      "epoch": 0.017654476670870115,
+      "grad_norm": 28.21232795715332,
+      "kl_loss": 7.276251494658936e-07,
+      "learning_rate": 1.9948979591836737e-05,
+      "loss": 2.499,
+      "sft_loss": 0.18608468770980835,
+      "step": 7
+    },
+    {
+      "computed_total": 0.32910704612731934,
+      "epoch": 0.0201765447667087,
+      "grad_norm": 24.3712158203125,
+      "kl_loss": 8.822735821922834e-07,
+      "learning_rate": 1.9897959183673473e-05,
+      "loss": 2.4776,
+      "sft_loss": 0.24087969958782196,
+      "step": 8
+    },
+    {
+      "computed_total": 0.3658309280872345,
+      "epoch": 0.02269861286254729,
+      "grad_norm": 31.98260498046875,
+      "kl_loss": 7.195029070317105e-07,
+      "learning_rate": 1.9846938775510205e-05,
+      "loss": 2.3718,
+      "sft_loss": 0.2938806414604187,
+      "step": 9
+    },
+    {
+      "computed_total": 0.22178040444850922,
+      "epoch": 0.025220680958385876,
+      "grad_norm": 34.0799674987793,
+      "kl_loss": 6.166483217384666e-07,
+      "learning_rate": 1.979591836734694e-05,
+      "loss": 2.4129,
+      "sft_loss": 0.1601155698299408,
+      "step": 10
+    },
+    {
+      "computed_total": 2.1096696853637695,
+      "epoch": 0.025220680958385876,
+      "eval_loss": 1.9816868305206299,
+      "eval_runtime": 67.6013,
+      "eval_samples_per_second": 10.429,
+      "eval_steps_per_second": 5.222,
+      "kl_loss": 3.9526437944914505e-07,
+      "sft_loss": 2.070143222808838,
+      "step": 10
+    },
+    {
+      "computed_total": 0.4089103043079376,
+      "epoch": 0.027742749054224466,
+      "grad_norm": 26.954879760742188,
+      "kl_loss": 4.996533107259893e-07,
+      "learning_rate": 1.9744897959183677e-05,
+      "loss": 2.277,
+      "sft_loss": 0.35894498229026794,
+      "step": 11
+    },
+    {
+      "computed_total": 0.23354634642601013,
+      "epoch": 0.03026481715006305,
+      "grad_norm": 18.464841842651367,
+      "kl_loss": 5.376580816118803e-07,
+      "learning_rate": 1.969387755102041e-05,
+      "loss": 2.2583,
+      "sft_loss": 0.17978054285049438,
+      "step": 12
+    },
+    {
+      "computed_total": 0.30147990584373474,
+      "epoch": 0.03278688524590164,
+      "grad_norm": 26.595727920532227,
+      "kl_loss": 5.573554062721087e-07,
+      "learning_rate": 1.9642857142857145e-05,
+      "loss": 2.2624,
+      "sft_loss": 0.24574437737464905,
+      "step": 13
+    },
+    {
+      "computed_total": 0.24872392416000366,
+      "epoch": 0.03530895334174023,
+      "grad_norm": 16.613079071044922,
+      "kl_loss": 4.973371687810868e-07,
+      "learning_rate": 1.9591836734693877e-05,
+      "loss": 2.1151,
+      "sft_loss": 0.19899021089076996,
+      "step": 14
+    },
+    {
+      "computed_total": 0.19776779413223267,
+      "epoch": 0.03783102143757881,
+      "grad_norm": 15.080662727355957,
+      "kl_loss": 4.196848806259368e-07,
+      "learning_rate": 1.9540816326530613e-05,
+      "loss": 2.0897,
+      "sft_loss": 0.15579931437969208,
+      "step": 15
+    },
+    {
+      "computed_total": 0.284699946641922,
+      "epoch": 0.0403530895334174,
+      "grad_norm": 11.973522186279297,
+      "kl_loss": 4.3317794506947394e-07,
+      "learning_rate": 1.948979591836735e-05,
+      "loss": 2.216,
+      "sft_loss": 0.2413821518421173,
+      "step": 16
+    },
+    {
+      "computed_total": 0.21680015325546265,
+      "epoch": 0.04287515762925599,
+      "grad_norm": 11.934453964233398,
+      "kl_loss": 3.477235850368743e-07,
+      "learning_rate": 1.9438775510204085e-05,
+      "loss": 1.9235,
+      "sft_loss": 0.18202780187129974,
+      "step": 17
+    },
+    {
+      "computed_total": 0.18643273413181305,
+      "epoch": 0.04539722572509458,
+      "grad_norm": 10.074520111083984,
+      "kl_loss": 2.590618919384724e-07,
+      "learning_rate": 1.9387755102040817e-05,
+      "loss": 1.8522,
+      "sft_loss": 0.16052654385566711,
+      "step": 18
+    },
+    {
+      "computed_total": 0.22932234406471252,
+      "epoch": 0.04791929382093316,
+      "grad_norm": 15.449592590332031,
+      "kl_loss": 2.511018522000086e-07,
+      "learning_rate": 1.9336734693877553e-05,
+      "loss": 1.7982,
+      "sft_loss": 0.20421215891838074,
+      "step": 19
+    },
+    {
+      "computed_total": 0.29722726345062256,
+      "epoch": 0.05044136191677175,
+      "grad_norm": 12.395018577575684,
+      "kl_loss": 2.6658420892999857e-07,
+      "learning_rate": 1.928571428571429e-05,
+      "loss": 1.817,
+      "sft_loss": 0.27056884765625,
+      "step": 20
+    },
+    {
+      "computed_total": 1.6116889715194702,
+      "epoch": 0.05044136191677175,
+      "eval_loss": 1.5718247890472412,
+      "eval_runtime": 69.8078,
+      "eval_samples_per_second": 10.099,
+      "eval_steps_per_second": 5.057,
+      "kl_loss": 3.4212027344437956e-07,
+      "sft_loss": 1.577476978302002,
+      "step": 20
+    },
+    {
+      "computed_total": 0.1908552497625351,
+      "epoch": 0.05296343001261034,
+      "grad_norm": 23.406896591186523,
+      "kl_loss": 2.7672922442434356e-07,
+      "learning_rate": 1.9234693877551024e-05,
+      "loss": 1.7865,
+      "sft_loss": 0.163182333111763,
+      "step": 21
+    },
+    {
+      "computed_total": 0.2098204642534256,
+      "epoch": 0.05548549810844893,
+      "grad_norm": 12.387871742248535,
+      "kl_loss": 1.9662114425500477e-07,
+      "learning_rate": 1.9183673469387756e-05,
+      "loss": 1.6599,
+      "sft_loss": 0.19015835225582123,
+      "step": 22
+    },
+    {
+      "computed_total": 0.27859383821487427,
+      "epoch": 0.058007566204287514,
+      "grad_norm": 17.064393997192383,
+      "kl_loss": 2.6223989380014245e-07,
+      "learning_rate": 1.9132653061224492e-05,
+      "loss": 1.7114,
+      "sft_loss": 0.25236985087394714,
+      "step": 23
+    },
+    {
+      "computed_total": 0.2661365270614624,
+      "epoch": 0.0605296343001261,
+      "grad_norm": 14.536602973937988,
+      "kl_loss": 3.302961033568863e-07,
+      "learning_rate": 1.9081632653061225e-05,
+      "loss": 1.7381,
+      "sft_loss": 0.23310692608356476,
+      "step": 24
+    },
+    {
+      "computed_total": 0.21774020791053772,
+      "epoch": 0.06305170239596469,
+      "grad_norm": 10.612632751464844,
+      "kl_loss": 2.2093004758971801e-07,
+      "learning_rate": 1.903061224489796e-05,
+      "loss": 1.6493,
+      "sft_loss": 0.195647194981575,
+      "step": 25
+    },
+    {
+      "computed_total": 0.21532197296619415,
+      "epoch": 0.06557377049180328,
+      "grad_norm": 13.36475944519043,
+      "kl_loss": 1.9050941091336426e-07,
+      "learning_rate": 1.8979591836734696e-05,
+      "loss": 1.65,
+      "sft_loss": 0.19627103209495544,
+      "step": 26
+    },
+    {
+      "computed_total": 0.21690420806407928,
+      "epoch": 0.06809583858764187,
+      "grad_norm": 13.064225196838379,
+      "kl_loss": 2.1687725393348956e-07,
+      "learning_rate": 1.892857142857143e-05,
+      "loss": 1.7006,
+      "sft_loss": 0.19521647691726685,
+      "step": 27
+    },
+    {
+      "computed_total": 0.19565589725971222,
+      "epoch": 0.07061790668348046,
+      "grad_norm": 12.320195198059082,
+      "kl_loss": 2.17976335648018e-07,
+      "learning_rate": 1.8877551020408164e-05,
+      "loss": 1.6652,
+      "sft_loss": 0.17385827004909515,
+      "step": 28
+    },
+    {
+      "computed_total": 0.27470341324806213,
+      "epoch": 0.07313997477931904,
+      "grad_norm": 11.224297523498535,
+      "kl_loss": 2.520193618238409e-07,
+      "learning_rate": 1.88265306122449e-05,
+      "loss": 1.6883,
+      "sft_loss": 0.24950148165225983,
+      "step": 29
+    },
+    {
+      "computed_total": 0.1886218637228012,
+      "epoch": 0.07566204287515763,
+      "grad_norm": 14.4179048538208,
+      "kl_loss": 3.655400746538362e-07,
+      "learning_rate": 1.8775510204081636e-05,
+      "loss": 1.7232,
+      "sft_loss": 0.1520678550004959,
+      "step": 30
+    },
+    {
+      "computed_total": 1.3417655229568481,
+      "epoch": 0.07566204287515763,
+      "eval_loss": 1.4369149208068848,
+      "eval_runtime": 67.0852,
+      "eval_samples_per_second": 10.509,
+      "eval_steps_per_second": 5.262,
+      "kl_loss": 2.1116991888447956e-07,
+      "sft_loss": 1.3206485509872437,
+      "step": 30
+    },
+    {
+      "computed_total": 0.19783087074756622,
+      "epoch": 0.07818411097099622,
+      "grad_norm": 14.451069831848145,
+      "kl_loss": 1.4020483263266215e-07,
+      "learning_rate": 1.8724489795918368e-05,
+      "loss": 1.6225,
+      "sft_loss": 0.18381038308143616,
+      "step": 31
+    },
+    {
+      "computed_total": 0.2664089798927307,
+      "epoch": 0.0807061790668348,
+      "grad_norm": 10.6675443649292,
+      "kl_loss": 2.558473113367654e-07,
+      "learning_rate": 1.8673469387755104e-05,
+      "loss": 1.6656,
+      "sft_loss": 0.24082423746585846,
+      "step": 32
+    },
+    {
+      "computed_total": 0.16216596961021423,
+      "epoch": 0.0832282471626734,
+      "grad_norm": 10.89920711517334,
+      "kl_loss": 3.102907157881418e-07,
+      "learning_rate": 1.862244897959184e-05,
+      "loss": 1.7422,
+      "sft_loss": 0.13113689422607422,
+      "step": 33
+    },
+    {
+      "computed_total": 0.18052271008491516,
+      "epoch": 0.08575031525851198,
+      "grad_norm": 10.312054634094238,
+      "kl_loss": 2.5258012215090275e-07,
+      "learning_rate": 1.8571428571428575e-05,
+      "loss": 1.5284,
+      "sft_loss": 0.1552647054195404,
+      "step": 34
+    },
+    {
+      "computed_total": 0.13403812050819397,
+      "epoch": 0.08827238335435057,
+      "grad_norm": 9.937405586242676,
+      "kl_loss": 1.9699928088812158e-07,
+      "learning_rate": 1.8520408163265307e-05,
+      "loss": 1.6276,
+      "sft_loss": 0.11433819681406021,
+      "step": 35
+    },
+    {
+      "computed_total": 0.21145765483379364,
+      "epoch": 0.09079445145018916,
+      "grad_norm": 10.810340881347656,
+      "kl_loss": 2.5251029001083225e-07,
+      "learning_rate": 1.8469387755102043e-05,
+      "loss": 1.5674,
+      "sft_loss": 0.1862066239118576,
+      "step": 36
+    },
+    {
+      "computed_total": 0.28667497634887695,
+      "epoch": 0.09331651954602774,
+      "grad_norm": 13.322245597839355,
+      "kl_loss": 2.524957380956039e-07,
+      "learning_rate": 1.8418367346938776e-05,
+      "loss": 1.6924,
+      "sft_loss": 0.2614254057407379,
+      "step": 37
+    },
+    {
+      "computed_total": 0.17698872089385986,
+      "epoch": 0.09583858764186633,
+      "grad_norm": 12.67447566986084,
+      "kl_loss": 1.8715130067903374e-07,
+      "learning_rate": 1.836734693877551e-05,
+      "loss": 1.6326,
+      "sft_loss": 0.1582735925912857,
+      "step": 38
+    },
+    {
+      "computed_total": 0.218657985329628,
+      "epoch": 0.09836065573770492,
+      "grad_norm": 10.07801342010498,
+      "kl_loss": 2.1152843032723467e-07,
+      "learning_rate": 1.8316326530612247e-05,
+      "loss": 1.5745,
+      "sft_loss": 0.1975051462650299,
+      "step": 39
+    },
+    {
+      "computed_total": 0.1585373878479004,
+      "epoch": 0.1008827238335435,
+      "grad_norm": 10.709808349609375,
+      "kl_loss": 1.5567046318665234e-07,
+      "learning_rate": 1.826530612244898e-05,
+      "loss": 1.4899,
+      "sft_loss": 0.14297033846378326,
+      "step": 40
+    },
+    {
+      "computed_total": 1.3272018432617188,
+      "epoch": 0.1008827238335435,
+      "eval_loss": 1.3992165327072144,
+      "eval_runtime": 67.3288,
+      "eval_samples_per_second": 10.471,
+      "eval_steps_per_second": 5.243,
+      "kl_loss": 1.587673352787533e-07,
+      "sft_loss": 1.3113250732421875,
+      "step": 40
+    },
+    {
+      "computed_total": 0.16187940537929535,
+      "epoch": 0.1034047919293821,
+      "grad_norm": 12.045276641845703,
+      "kl_loss": 1.6272514358206536e-07,
+      "learning_rate": 1.8214285714285715e-05,
+      "loss": 1.4241,
+      "sft_loss": 0.1456068903207779,
+      "step": 41
+    },
+    {
+      "computed_total": 0.16236107051372528,
+      "epoch": 0.10592686002522068,
+      "grad_norm": 9.8399658203125,
+      "kl_loss": 1.7566540577718115e-07,
+      "learning_rate": 1.816326530612245e-05,
+      "loss": 1.557,
+      "sft_loss": 0.1447945237159729,
+      "step": 42
+    },
+    {
+      "computed_total": 0.15767036378383636,
+      "epoch": 0.10844892812105927,
+      "grad_norm": 12.114518165588379,
+      "kl_loss": 1.7348739334011043e-07,
+      "learning_rate": 1.8112244897959187e-05,
+      "loss": 1.583,
+      "sft_loss": 0.14032162725925446,
+      "step": 43
+    },
+    {
+      "computed_total": 0.09624896198511124,
+      "epoch": 0.11097099621689786,
+      "grad_norm": 9.963354110717773,
+      "kl_loss": 1.7239732130747143e-07,
+      "learning_rate": 1.806122448979592e-05,
+      "loss": 1.4214,
+      "sft_loss": 0.07900922745466232,
+      "step": 44
+    },
+    {
+      "computed_total": 0.2713112533092499,
+      "epoch": 0.11349306431273644,
+      "grad_norm": 10.126675605773926,
+      "kl_loss": 1.4448913532305596e-07,
+      "learning_rate": 1.8010204081632655e-05,
+      "loss": 1.5783,
+      "sft_loss": 0.2568623423576355,
+      "step": 45
+    },
+    {
+      "computed_total": 0.1786537766456604,
+      "epoch": 0.11601513240857503,
+      "grad_norm": 9.506120681762695,
+      "kl_loss": 1.1718055503706637e-07,
+      "learning_rate": 1.795918367346939e-05,
+      "loss": 1.5218,
+      "sft_loss": 0.1669357270002365,
+      "step": 46
+    },
+    {
+      "computed_total": 0.15938213467597961,
+      "epoch": 0.11853720050441362,
+      "grad_norm": 11.758268356323242,
+      "kl_loss": 1.7643755256813165e-07,
+      "learning_rate": 1.7908163265306123e-05,
+      "loss": 1.479,
+      "sft_loss": 0.1417383849620819,
+      "step": 47
+    },
+    {
+      "computed_total": 0.15835891664028168,
+      "epoch": 0.1210592686002522,
+      "grad_norm": 10.227970123291016,
+      "kl_loss": 1.3144477861715131e-07,
+      "learning_rate": 1.785714285714286e-05,
+      "loss": 1.5222,
+      "sft_loss": 0.14521443843841553,
+      "step": 48
+    },
+    {
+      "computed_total": 0.1753772348165512,
+      "epoch": 0.1235813366960908,
+      "grad_norm": 9.49471378326416,
+      "kl_loss": 1.2467818066852487e-07,
+      "learning_rate": 1.780612244897959e-05,
+      "loss": 1.4884,
+      "sft_loss": 0.16290941834449768,
+      "step": 49
+    },
+    {
+      "computed_total": 0.14545822143554688,
+      "epoch": 0.12610340479192939,
+      "grad_norm": 9.987504005432129,
+      "kl_loss": 1.3850477387222782e-07,
+      "learning_rate": 1.7755102040816327e-05,
+      "loss": 1.5382,
+      "sft_loss": 0.13160774111747742,
+      "step": 50
+    },
+    {
+      "computed_total": 1.2876274585723877,
+      "epoch": 0.12610340479192939,
+      "eval_loss": 1.3761128187179565,
+      "eval_runtime": 65.8814,
+      "eval_samples_per_second": 10.701,
+      "eval_steps_per_second": 5.358,
+      "kl_loss": 1.1736652538729686e-07,
+      "sft_loss": 1.275890827178955,
+      "step": 50
+    },
+    {
+      "computed_total": 0.13572491705417633,
+      "epoch": 0.12862547288776796,
+      "grad_norm": 8.282198905944824,
+      "kl_loss": 1.2732888876598736e-07,
+      "learning_rate": 1.7704081632653062e-05,
+      "loss": 1.4672,
+      "sft_loss": 0.12299202382564545,
+      "step": 51
+    },
+    {
+      "computed_total": 0.2022746205329895,
+      "epoch": 0.13114754098360656,
+      "grad_norm": 8.850266456604004,
+      "kl_loss": 9.734989703247265e-08,
+      "learning_rate": 1.7653061224489798e-05,
+      "loss": 1.4807,
+      "sft_loss": 0.19253963232040405,
+      "step": 52
+    },
+    {
+      "computed_total": 0.2428017556667328,
+      "epoch": 0.13366960907944514,
+      "grad_norm": 7.4850568771362305,
+      "kl_loss": 1.472172925787163e-07,
+      "learning_rate": 1.760204081632653e-05,
+      "loss": 1.4415,
+      "sft_loss": 0.22808003425598145,
+      "step": 53
+    },
+    {
+      "computed_total": 0.22275952994823456,
+      "epoch": 0.13619167717528374,
+      "grad_norm": 9.871981620788574,
+      "kl_loss": 1.480846094636945e-07,
+      "learning_rate": 1.7551020408163266e-05,
+      "loss": 1.6587,
+      "sft_loss": 0.20795106887817383,
+      "step": 54
+    },
+    {
+      "computed_total": 0.1835995763540268,
+      "epoch": 0.13871374527112232,
+      "grad_norm": 8.844654083251953,
+      "kl_loss": 1.2977692165350163e-07,
+      "learning_rate": 1.7500000000000002e-05,
+      "loss": 1.5753,
+      "sft_loss": 0.17062188684940338,
+      "step": 55
+    },
+    {
+      "computed_total": 0.19904766976833344,
+      "epoch": 0.14123581336696092,
+      "grad_norm": 7.038422584533691,
+      "kl_loss": 1.1099445629270122e-07,
+      "learning_rate": 1.7448979591836738e-05,
+      "loss": 1.4909,
+      "sft_loss": 0.18794822692871094,
+      "step": 56
+    },
+    {
+      "computed_total": 0.14884871244430542,
+      "epoch": 0.1437578814627995,
+      "grad_norm": 7.760448455810547,
+      "kl_loss": 1.0769576164193495e-07,
+      "learning_rate": 1.7397959183673473e-05,
+      "loss": 1.5988,
+      "sft_loss": 0.13807913661003113,
+      "step": 57
+    },
+    {
+      "computed_total": 0.22467643022537231,
+      "epoch": 0.14627994955863807,
+      "grad_norm": 8.861936569213867,
+      "kl_loss": 1.3167736767627503e-07,
+      "learning_rate": 1.7346938775510206e-05,
+      "loss": 1.4759,
+      "sft_loss": 0.21150869131088257,
+      "step": 58
+    },
+    {
+      "computed_total": 0.1402980089187622,
+      "epoch": 0.14880201765447668,
+      "grad_norm": 8.389931678771973,
+      "kl_loss": 1.2574119523378613e-07,
+      "learning_rate": 1.729591836734694e-05,
+      "loss": 1.4478,
+      "sft_loss": 0.12772388756275177,
+      "step": 59
+    },
+    {
+      "computed_total": 0.2214464396238327,
+      "epoch": 0.15132408575031525,
+      "grad_norm": 11.03455924987793,
+      "kl_loss": 1.229836925631389e-07,
+      "learning_rate": 1.7244897959183674e-05,
+      "loss": 1.542,
+      "sft_loss": 0.20914806425571442,
+      "step": 60
+    },
+    {
+      "computed_total": 1.2934421300888062,
+      "epoch": 0.15132408575031525,
+      "eval_loss": 1.3563388586044312,
+      "eval_runtime": 66.808,
+      "eval_samples_per_second": 10.553,
+      "eval_steps_per_second": 5.284,
+      "kl_loss": 1.0278420603526683e-07,
+      "sft_loss": 1.2831636667251587,
+      "step": 60
+    },
+    {
+      "computed_total": 0.19582681357860565,
+      "epoch": 0.15384615384615385,
+      "grad_norm": 8.09454345703125,
+      "kl_loss": 1.0761530688796483e-07,
+      "learning_rate": 1.719387755102041e-05,
+      "loss": 1.4979,
+      "sft_loss": 0.18506528437137604,
+      "step": 61
+    },
+    {
+      "computed_total": 0.15016137063503265,
+      "epoch": 0.15636822194199243,
+      "grad_norm": 6.767925262451172,
+      "kl_loss": 9.817436819048453e-08,
+      "learning_rate": 1.7142857142857142e-05,
+      "loss": 1.3421,
+      "sft_loss": 0.14034393429756165,
+      "step": 62
+    },
+    {
+      "computed_total": 0.23630164563655853,
+      "epoch": 0.15889029003783103,
+      "grad_norm": 6.9385552406311035,
+      "kl_loss": 1.2005209271137574e-07,
+      "learning_rate": 1.7091836734693878e-05,
+      "loss": 1.4917,
+      "sft_loss": 0.224296435713768,
+      "step": 63
+    },
+    {
+      "computed_total": 0.23200978338718414,
+      "epoch": 0.1614123581336696,
+      "grad_norm": 7.448540210723877,
+      "kl_loss": 8.879172952447334e-08,
+      "learning_rate": 1.7040816326530613e-05,
+      "loss": 1.4776,
+      "sft_loss": 0.22313061356544495,
+      "step": 64
+    },
+    {
+      "computed_total": 0.16305182874202728,
+      "epoch": 0.16393442622950818,
+      "grad_norm": 7.1528401374816895,
+      "kl_loss": 9.930875677355289e-08,
+      "learning_rate": 1.698979591836735e-05,
+      "loss": 1.3943,
+      "sft_loss": 0.1531209498643875,
+      "step": 65
+    },
+    {
+      "computed_total": 0.14623767137527466,
+      "epoch": 0.1664564943253468,
+      "grad_norm": 7.3966474533081055,
+      "kl_loss": 7.404720037129664e-08,
+      "learning_rate": 1.6938775510204085e-05,
+      "loss": 1.5426,
+      "sft_loss": 0.1388329565525055,
+      "step": 66
+    },
+    {
+      "computed_total": 0.14071843028068542,
+      "epoch": 0.16897856242118536,
+      "grad_norm": 7.82870626449585,
+      "kl_loss": 9.07349146928027e-08,
+      "learning_rate": 1.6887755102040817e-05,
+      "loss": 1.4386,
+      "sft_loss": 0.13164493441581726,
+      "step": 67
+    },
+    {
+      "computed_total": 0.14310967922210693,
+      "epoch": 0.17150063051702397,
+      "grad_norm": 6.757770538330078,
+      "kl_loss": 7.598376328132872e-08,
+      "learning_rate": 1.6836734693877553e-05,
+      "loss": 1.3732,
+      "sft_loss": 0.13551130890846252,
+      "step": 68
+    },
+    {
+      "computed_total": 0.14132973551750183,
+      "epoch": 0.17402269861286254,
+      "grad_norm": 8.344841957092285,
+      "kl_loss": 1.0905234404390285e-07,
+      "learning_rate": 1.678571428571429e-05,
+      "loss": 1.4286,
+      "sft_loss": 0.13042449951171875,
+      "step": 69
+    },
+    {
+      "computed_total": 0.13716241717338562,
+      "epoch": 0.17654476670870115,
+      "grad_norm": 7.953212738037109,
+      "kl_loss": 7.554955061550572e-08,
+      "learning_rate": 1.673469387755102e-05,
+      "loss": 1.3187,
+      "sft_loss": 0.12960746884346008,
+      "step": 70
+    },
+    {
+      "computed_total": 1.2660552263259888,
+      "epoch": 0.17654476670870115,
+      "eval_loss": 1.348509669303894,
+      "eval_runtime": 66.6809,
+      "eval_samples_per_second": 10.573,
+      "eval_steps_per_second": 5.294,
+      "kl_loss": 5.885167198016461e-08,
+      "sft_loss": 1.2601701021194458,
+      "step": 70
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 397,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.283301394808832e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-70/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6de66e3fe852c1e00b5bef4ae321a94f547f2c407241301f03edce25795f2a
+size 5969