Training in progress, step 20, checkpoint

.gitattributes

@@ -34,3 +34,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
 tokenizer.json filter=lfs diff=lfs merge=lfs -text
+last-checkpoint/tokenizer.json filter=lfs diff=lfs merge=lfs -text

last-checkpoint/README.md

@@ -0,0 +1,202 @@
+---
+base_model: Qwen/Qwen3-14B-Base
+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

last-checkpoint/adapter_config.json

@@ -0,0 +1,39 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Qwen/Qwen3-14B-Base",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 64,
+  "lora_bias": false,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj",
+    "gate_proj",
+    "v_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_rslora": false
+}

last-checkpoint/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8b7686fb16026c15b85c74f511e078713d9b7b6029058c372e339052f48dc09
+size 513877864

last-checkpoint/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
+}

last-checkpoint/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1b027b1b0e5e1be6320c1ece5f31111d226c82a888f1cff140ac86971f9d1a4
+size 261573140

last-checkpoint/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e75017e378bdc9f0153cad906c795d720af019c51431cfb79e8a4e23cf2640b5
+size 14244

last-checkpoint/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdf1bdf3216bc493af4f6a2c5abcd1e9626ecd7c83f846df8a668b93dfb05d5a
+size 1064

last-checkpoint/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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

last-checkpoint/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:67cc0080ffd7555f723f423c27cfef314e1ad9d335c8b79f465c5faba1ed478b
+size 11422821

last-checkpoint/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,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

last-checkpoint/trainer_state.json

@@ -0,0 +1,534 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0014021312394840158,
+  "eval_steps": 500,
+  "global_step": 20,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.71875,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 199.0,
+      "completions/mean_length": 216.59375,
+      "completions/mean_terminated_length": 115.8888931274414,
+      "completions/min_length": 22.0,
+      "completions/min_terminated_length": 22.0,
+      "epoch": 7.010656197420079e-05,
+      "grad_norm": 0.13658307492733002,
+      "kl": 0.0,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "num_tokens": 12031.0,
+      "reward": -16.35692024230957,
+      "reward_std": 2.696993112564087,
+      "rewards/reward_short_words/mean": -5.5963945388793945,
+      "rewards/reward_short_words/std": 2.8097963333129883,
+      "step": 1
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.59375,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 224.0,
+      "completions/mean_length": 184.71875,
+      "completions/mean_terminated_length": 80.53846740722656,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.00014021312394840157,
+      "grad_norm": 2.418160915374756,
+      "kl": 0.0,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.0,
+      "num_tokens": 30526.0,
+      "reward": -16.925800323486328,
+      "reward_std": 5.625462532043457,
+      "rewards/reward_short_words/mean": -5.791031837463379,
+      "rewards/reward_short_words/std": 3.6131951808929443,
+      "step": 2
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.84375,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 174.0,
+      "completions/mean_length": 228.46875,
+      "completions/mean_terminated_length": 79.80000305175781,
+      "completions/min_length": 31.0,
+      "completions/min_terminated_length": 31.0,
+      "epoch": 0.00021031968592260234,
+      "grad_norm": 0.159947469830513,
+      "kl": 0.0013296040706336498,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.0001,
+      "num_tokens": 47869.0,
+      "reward": -18.348779678344727,
+      "reward_std": 1.9298845529556274,
+      "rewards/reward_short_words/mean": -6.277894020080566,
+      "rewards/reward_short_words/std": 2.424363851547241,
+      "step": 3
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.5625,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 231.0,
+      "completions/mean_length": 182.03125,
+      "completions/mean_terminated_length": 86.92857360839844,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.00028042624789680314,
+      "grad_norm": 0.9018411636352539,
+      "kl": 0.0009629518608562648,
+      "learning_rate": 7.5e-07,
+      "loss": 0.0,
+      "num_tokens": 64250.0,
+      "reward": -18.661287307739258,
+      "reward_std": 5.1295294761657715,
+      "rewards/reward_short_words/mean": -6.384815692901611,
+      "rewards/reward_short_words/std": 3.57678484916687,
+      "step": 4
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.5625,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 204.0,
+      "completions/mean_length": 168.4375,
+      "completions/mean_terminated_length": 55.857147216796875,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.00035053280987100394,
+      "grad_norm": 3.0168304443359375,
+      "kl": 0.0008603320457041264,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.0,
+      "num_tokens": 80600.0,
+      "reward": -19.933547973632812,
+      "reward_std": 6.737860679626465,
+      "rewards/reward_short_words/mean": -6.820110321044922,
+      "rewards/reward_short_words/std": 3.7595303058624268,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.5625,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 251.0,
+      "completions/mean_length": 194.0,
+      "completions/mean_terminated_length": 114.28572082519531,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0004206393718452047,
+      "grad_norm": 1.164302945137024,
+      "kl": 0.0009597770986147225,
+      "learning_rate": 1.25e-06,
+      "loss": 0.0,
+      "num_tokens": 97236.0,
+      "reward": -19.481975555419922,
+      "reward_std": 4.219770431518555,
+      "rewards/reward_short_words/mean": -6.665607452392578,
+      "rewards/reward_short_words/std": 2.5644466876983643,
+      "step": 6
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.5,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 235.0,
+      "completions/mean_length": 169.84375,
+      "completions/mean_terminated_length": 83.6875,
+      "completions/min_length": 29.0,
+      "completions/min_terminated_length": 29.0,
+      "epoch": 0.0004907459338194055,
+      "grad_norm": 0.13596586883068085,
+      "kl": 0.001013980945572257,
+      "learning_rate": 1.5e-06,
+      "loss": 0.0,
+      "num_tokens": 113935.0,
+      "reward": -25.956401824951172,
+      "reward_std": 6.042013168334961,
+      "rewards/reward_short_words/mean": -8.880783081054688,
+      "rewards/reward_short_words/std": 3.9492485523223877,
+      "step": 7
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.71875,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 172.0,
+      "completions/mean_length": 202.875,
+      "completions/mean_terminated_length": 67.11111450195312,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0005608524957936063,
+      "grad_norm": 1.491392731666565,
+      "kl": 0.001194561249576509,
+      "learning_rate": 1.7500000000000002e-06,
+      "loss": 0.0,
+      "num_tokens": 132159.0,
+      "reward": -16.37868309020996,
+      "reward_std": 4.960553169250488,
+      "rewards/reward_short_words/mean": -5.603840351104736,
+      "rewards/reward_short_words/std": 3.197422742843628,
+      "step": 8
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.6875,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 236.0,
+      "completions/mean_length": 194.3125,
+      "completions/mean_terminated_length": 58.60000228881836,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0006309590577678071,
+      "grad_norm": 3.211796283721924,
+      "kl": 0.0011702607152983546,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0001,
+      "num_tokens": 151649.0,
+      "reward": -15.122705459594727,
+      "reward_std": 4.872115135192871,
+      "rewards/reward_short_words/mean": -5.174117088317871,
+      "rewards/reward_short_words/std": 2.5721726417541504,
+      "step": 9
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.78125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 184.0,
+      "completions/mean_length": 220.4375,
+      "completions/mean_terminated_length": 93.42857360839844,
+      "completions/min_length": 54.0,
+      "completions/min_terminated_length": 54.0,
+      "epoch": 0.0007010656197420079,
+      "grad_norm": 0.11666588485240936,
+      "kl": 0.000986904022283852,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0,
+      "num_tokens": 167231.0,
+      "reward": -17.728458404541016,
+      "reward_std": 1.9997084140777588,
+      "rewards/reward_short_words/mean": -6.065655708312988,
+      "rewards/reward_short_words/std": 1.885218620300293,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.8125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 84.0,
+      "completions/mean_length": 217.1875,
+      "completions/mean_terminated_length": 49.0,
+      "completions/min_length": 30.0,
+      "completions/min_terminated_length": 30.0,
+      "epoch": 0.0007711721817162087,
+      "grad_norm": 0.13888925313949585,
+      "kl": 0.0012066997587680817,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0,
+      "num_tokens": 184969.0,
+      "reward": -19.939603805541992,
+      "reward_std": 2.765538215637207,
+      "rewards/reward_short_words/mean": -6.822181701660156,
+      "rewards/reward_short_words/std": 2.9305803775787354,
+      "step": 11
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.75,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 207.0,
+      "completions/mean_length": 218.8125,
+      "completions/mean_terminated_length": 107.25,
+      "completions/min_length": 16.0,
+      "completions/min_terminated_length": 16.0,
+      "epoch": 0.0008412787436904094,
+      "grad_norm": 0.16707061231136322,
+      "kl": 0.0009350845939479768,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.0,
+      "num_tokens": 202067.0,
+      "reward": -20.632661819458008,
+      "reward_std": 7.002403736114502,
+      "rewards/reward_short_words/mean": -7.059307098388672,
+      "rewards/reward_short_words/std": 4.558341026306152,
+      "step": 12
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.5,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 254.0,
+      "completions/mean_length": 184.09375,
+      "completions/mean_terminated_length": 112.1875,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0009113853056646102,
+      "grad_norm": 1.1818095445632935,
+      "kl": 0.0009267741697840393,
+      "learning_rate": 3e-06,
+      "loss": 0.0,
+      "num_tokens": 218190.0,
+      "reward": -21.259138107299805,
+      "reward_std": 5.966151237487793,
+      "rewards/reward_short_words/mean": -7.273650169372559,
+      "rewards/reward_short_words/std": 4.308831691741943,
+      "step": 13
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.65625,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 150.0,
+      "completions/mean_length": 205.96875,
+      "completions/mean_terminated_length": 110.45455169677734,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.000981491867638811,
+      "grad_norm": 0.5406622290611267,
+      "kl": 0.0010281066643074155,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.0001,
+      "num_tokens": 236777.0,
+      "reward": -20.823211669921875,
+      "reward_std": 6.621612071990967,
+      "rewards/reward_short_words/mean": -7.124502182006836,
+      "rewards/reward_short_words/std": 4.3875226974487305,
+      "step": 14
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.625,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 173.0,
+      "completions/mean_length": 191.34375,
+      "completions/mean_terminated_length": 83.58333587646484,
+      "completions/min_length": 18.0,
+      "completions/min_terminated_length": 18.0,
+      "epoch": 0.0010515984296130118,
+      "grad_norm": 0.34566256403923035,
+      "kl": 0.0011082870187237859,
+      "learning_rate": 3.5000000000000004e-06,
+      "loss": 0.0,
+      "num_tokens": 253192.0,
+      "reward": -23.05975341796875,
+      "reward_std": 9.964019775390625,
+      "rewards/reward_short_words/mean": -7.889717102050781,
+      "rewards/reward_short_words/std": 7.6198835372924805,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.625,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 245.0,
+      "completions/mean_length": 183.3125,
+      "completions/mean_terminated_length": 62.16666793823242,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0011217049915872126,
+      "grad_norm": 1.9921596050262451,
+      "kl": 0.0009369402541778982,
+      "learning_rate": 3.75e-06,
+      "loss": 0.0001,
+      "num_tokens": 271130.0,
+      "reward": -16.921245574951172,
+      "reward_std": 4.846298694610596,
+      "rewards/reward_short_words/mean": -5.789474010467529,
+      "rewards/reward_short_words/std": 3.046598196029663,
+      "step": 16
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.3125,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 220.0,
+      "completions/mean_length": 159.5625,
+      "completions/mean_terminated_length": 115.72727966308594,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0011918115535614134,
+      "grad_norm": 0.6873171925544739,
+      "kl": 0.0005745217204093933,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.0,
+      "num_tokens": 287180.0,
+      "reward": -23.344005584716797,
+      "reward_std": 9.127889633178711,
+      "rewards/reward_short_words/mean": -7.986971378326416,
+      "rewards/reward_short_words/std": 4.011465549468994,
+      "step": 17
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.75,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 219.0,
+      "completions/mean_length": 207.59375,
+      "completions/mean_terminated_length": 62.375,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0012619181155356142,
+      "grad_norm": 1.8942995071411133,
+      "kl": 0.0013139176880940795,
+      "learning_rate": 4.250000000000001e-06,
+      "loss": 0.0002,
+      "num_tokens": 306515.0,
+      "reward": -13.720466613769531,
+      "reward_std": 3.606645345687866,
+      "rewards/reward_short_words/mean": -4.694352149963379,
+      "rewards/reward_short_words/std": 2.2922067642211914,
+      "step": 18
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.5625,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 245.0,
+      "completions/mean_length": 186.3125,
+      "completions/mean_terminated_length": 96.71428680419922,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.001332024677509815,
+      "grad_norm": 1.4690767526626587,
+      "kl": 0.0007615434005856514,
+      "learning_rate": 4.5e-06,
+      "loss": 0.0003,
+      "num_tokens": 323785.0,
+      "reward": -15.320701599121094,
+      "reward_std": 4.215565204620361,
+      "rewards/reward_short_words/mean": -5.2418599128723145,
+      "rewards/reward_short_words/std": 3.346675157546997,
+      "step": 19
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.6875,
+      "completions/max_length": 256.0,
+      "completions/max_terminated_length": 83.0,
+      "completions/mean_length": 183.46875,
+      "completions/mean_terminated_length": 23.899999618530273,
+      "completions/min_length": 1.0,
+      "completions/min_terminated_length": 1.0,
+      "epoch": 0.0014021312394840158,
+      "grad_norm": 0.9161757230758667,
+      "kl": 0.001246627070941031,
+      "learning_rate": 4.75e-06,
+      "loss": 0.0005,
+      "num_tokens": 341852.0,
+      "reward": -14.605607032775879,
+      "reward_std": 2.5197999477386475,
+      "rewards/reward_short_words/mean": -4.997196197509766,
+      "rewards/reward_short_words/std": 3.3148984909057617,
+      "step": 20
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 20,
+  "num_input_tokens_seen": 341852,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}

last-checkpoint/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71ce4a691922b7a5910e909a16440e5f68df6d53b9c2a7fd230468c23e3446c0
+size 7928