Upload full trainer checkpoint step=154 (profile=llama3_1_8b_base_lessdata_grpo, run_type=grpo)

.gitattributes

@@ -165,3 +165,4 @@ meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5124/tokenizer.json fil
 meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5490/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5856/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-77/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/tokenizer.json filter=lfs diff=lfs merge=lfs -text

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Meta-Llama-3.1-8B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Meta-Llama-3.1-8B
+- grpo
+- lora
+- transformers
+- trl
+- unsloth
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.18.1

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/adapter_config.json

@@ -0,0 +1,50 @@
+{
+  "alora_invocation_tokens": null,
+  "alpha_pattern": {},
+  "arrow_config": null,
+  "auto_mapping": {
+    "base_model_class": "LlamaForCausalLM",
+    "parent_library": "transformers.models.llama.modeling_llama",
+    "unsloth_fixed": true
+  },
+  "base_model_name_or_path": "unsloth/Meta-Llama-3.1-8B",
+  "bias": "none",
+  "corda_config": null,
+  "ensure_weight_tying": false,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0.0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "peft_version": "0.18.1",
+  "qalora_group_size": 16,
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "v_proj",
+    "up_proj",
+    "o_proj",
+    "q_proj",
+    "k_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12e4a7dc95ee2cb04f06af5cdbfbe2e8e7c41605953a4f04c685d9b9982b5056
+size 83945296

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/chat_template.jinja

@@ -0,0 +1,12 @@
+{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ messages[0]['content'] + '
+
+' }}{% set loop_messages = messages[1:] %}{% else %}{{ '' + '
+
+' }}{% set loop_messages = messages %}{% endif %}{% for message in loop_messages %}{% if message['role'] == 'user' %}{{ '### Instruction:
+' + message['content'] + '
+
+' }}{% elif message['role'] == 'assistant' %}{{ '### Response:
+' + message['content'] + eos_token + '
+
+' }}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '### Response:
+' }}{% endif %}

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a13f861bc833f582105852a52e31b4e90799e5083a241f0e9bb5dc4a5770da20
+size 43127525

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f6f51f0c100dcd16a1ec0e3ccf85e2a48a2d69b37becbf2ff91e32e4f5b020d
+size 14645

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e522fe56be3228993f884952559035a284237ea37c12679b3010f1dd8ca789f
+size 1465

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a65c6c5f9764771aa485e6a1f5e63d7d9af8477fe0777148c17476ecb2e09a05
+size 17210099

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/tokenizer_config.json

@@ -0,0 +1,18 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|begin_of_text|>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|end_of_text|>",
+  "from_slow": true,
+  "is_local": false,
+  "legacy": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": null
+}

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/trainer_state.json

@@ -0,0 +1,214 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.017507958162801273,
+  "eval_steps": 500,
+  "global_step": 154,
+  "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,
+      "completion_length": 40.51,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.61538461538461,
+      "completions/max_terminated_length": 41.61538461538461,
+      "completions/mean_length": 41.49038461538461,
+      "completions/mean_terminated_length": 41.49038461538461,
+      "completions/min_length": 41.46153846153846,
+      "completions/min_terminated_length": 41.46153846153846,
+      "epoch": 0.002842201000454752,
+      "frac_reward_zero_std": 0.8461538461538461,
+      "grad_norm": 0.00010901527275564149,
+      "kl": 0.3738707254827023,
+      "learning_rate": 6.818181818181817e-08,
+      "loss": 0.0017362165451049805,
+      "num_tokens": 16251.0,
+      "reward": 1.146243168757512e-09,
+      "reward_std": 0.16446845348064715,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 1.146243168757512e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.16446845348064715,
+      "step": 25
+    },
+    {
+      "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,
+      "completion_length": 33.46,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 32.5,
+      "completions/max_terminated_length": 32.5,
+      "completions/mean_length": 32.104166666666664,
+      "completions/mean_terminated_length": 32.104166666666664,
+      "completions/min_length": 31.833333333333332,
+      "completions/min_terminated_length": 31.833333333333332,
+      "epoch": 0.005684402000909504,
+      "frac_reward_zero_std": 0.6666666666666666,
+      "grad_norm": 2.2870442990097217e-05,
+      "kl": 0.45336965084075925,
+      "learning_rate": 1.3920454545454543e-07,
+      "loss": 0.003446932137012482,
+      "num_tokens": 28517.0,
+      "reward": 3.104408582051595e-09,
+      "reward_std": 0.35634831587473553,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 3.104408582051595e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.35634831587473553,
+      "step": 50
+    },
+    {
+      "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,
+      "completion_length": 28.4,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 29.692307692307693,
+      "completions/max_terminated_length": 29.692307692307693,
+      "completions/mean_length": 29.692307692307693,
+      "completions/mean_terminated_length": 29.692307692307693,
+      "completions/min_length": 29.692307692307693,
+      "completions/min_terminated_length": 29.692307692307693,
+      "epoch": 0.008526603001364257,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.00023519636306446046,
+      "kl": 0.5306798231601715,
+      "learning_rate": 2.1022727272727273e-07,
+      "loss": 0.0026533985137939453,
+      "num_tokens": 40821.0,
+      "reward": 0.0,
+      "reward_std": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.0,
+      "step": 75
+    },
+    {
+      "eval_cer_subset": 0.016214743153018123,
+      "eval_cer_subset_edit_distance": 119,
+      "eval_cer_subset_groups": 75,
+      "eval_cer_subset_items": 75,
+      "eval_cer_subset_ref_chars": 7339,
+      "eval_loss": 0.051239763421292085,
+      "step": 77
+    },
+    {
+      "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,
+      "completion_length": 25.68,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 24.166666666666668,
+      "completions/max_terminated_length": 24.166666666666668,
+      "completions/mean_length": 24.166666666666668,
+      "completions/mean_terminated_length": 24.166666666666668,
+      "completions/min_length": 24.166666666666668,
+      "completions/min_terminated_length": 24.166666666666668,
+      "epoch": 0.011368804001819008,
+      "frac_reward_zero_std": 0.9166666666666666,
+      "grad_norm": 2.2544394596479833e-05,
+      "kl": 0.518502562046051,
+      "learning_rate": 2.8125e-07,
+      "loss": 0.002607444524765015,
+      "num_tokens": 49965.0,
+      "reward": 1.241763432820638e-09,
+      "reward_std": 0.08908707896868388,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 1.241763432820638e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.08908707896868388,
+      "step": 100
+    },
+    {
+      "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,
+      "completion_length": 22.88,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 23.615384615384617,
+      "completions/max_terminated_length": 23.615384615384617,
+      "completions/mean_length": 23.615384615384617,
+      "completions/mean_terminated_length": 23.615384615384617,
+      "completions/min_length": 23.615384615384617,
+      "completions/min_terminated_length": 23.615384615384617,
+      "epoch": 0.014211005002273762,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 2.1615845980704762e-05,
+      "kl": 0.5622372037172317,
+      "learning_rate": 3.5227272727272725e-07,
+      "loss": 0.002811187207698822,
+      "num_tokens": 60549.0,
+      "reward": 0.0,
+      "reward_std": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.0,
+      "step": 125
+    },
+    {
+      "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,
+      "completion_length": 33.45,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 33.166666666666664,
+      "completions/max_terminated_length": 33.166666666666664,
+      "completions/mean_length": 33.09375,
+      "completions/mean_terminated_length": 33.09375,
+      "completions/min_length": 33.0,
+      "completions/min_terminated_length": 33.0,
+      "epoch": 0.017053206002728513,
+      "frac_reward_zero_std": 0.6666666666666666,
+      "grad_norm": 7.148436998249963e-05,
+      "kl": 0.4329612571001053,
+      "learning_rate": 4.232954545454545e-07,
+      "loss": 0.000653979480266571,
+      "num_tokens": 72638.0,
+      "reward": 6.20881716410319e-09,
+      "reward_std": 0.35634831587473553,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 6.20881716410319e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.35634831587473553,
+      "step": 150
+    },
+    {
+      "eval_cer_subset": 0.016214743153018123,
+      "eval_cer_subset_edit_distance": 119,
+      "eval_cer_subset_groups": 75,
+      "eval_cer_subset_items": 75,
+      "eval_cer_subset_ref_chars": 7339,
+      "eval_loss": 0.05146724294813467,
+      "step": 154
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 35184,
+  "num_input_tokens_seen": 75796,
+  "num_train_epochs": 4,
+  "save_steps": 77,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9d48113b20a2ef8290461b5ffcb3e02222cf53b552d5e8b965683a2b76768a0
+size 6801

meta-llama__meta-llama-3.1-8b/grpo/run_manifest.json

@@ -9,17 +9,23 @@
   "best_metric_value": 0.016214743153018123,
   "best_step": 77,
   "best_checkpoint_step": 77,
-  "latest_checkpoint_step": 77,
+  "latest_checkpoint_step": 154,
   "checkpoints": [
     {
       "step": 77,
       "epoch": 0.008753979081400637,
       "repo_path": "meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-77",
       "timestamp": "2026-04-09T23:23:53.593935+00:00"
+    },
+    {
+      "step": 154,
+      "epoch": 0.017507958162801273,
+      "repo_path": "meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-154",
+      "timestamp": "2026-04-09T23:25:43.129048+00:00"
     }
   ],
   "epoch_artifacts": [],
   "resume_history": [],
   "created_at": "2026-04-09T23:20:32.422192+00:00",
-  "updated_at": "2026-04-09T23:23:53.593951+00:00"
+  "updated_at": "2026-04-09T23:25:43.129063+00:00"
 }