Upload full trainer checkpoint step=220 (profile=llama3_1_8b_base_lessdata_grpo, run_type=grpo)

.gitattributes

@@ -167,3 +167,4 @@ meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5856/tokenizer.json fil
 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-231/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-220/tokenizer.json filter=lfs diff=lfs merge=lfs -text

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-220/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-220/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": [
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "gate_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-220/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba5fe45dd76ba2d63f36843c5ef14d45a725fa248266772d2d818f0d8cbb3e52
+size 83945296

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-220/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-220/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35db5d42d017fc2aef06e381e2a3e16698c00993db064c3030c14561a60328f
+size 43127525

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-220/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c95696854e3fe97ec080b60a38ee1613b968c78f33054560734dd3020bcc4fc
+size 14645

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-220/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c2d5c3dd3aaaae891b57fa0720c44854d12d865a62197aa80e5715094bb26ed
+size 1465

meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-220/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-220/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-220/trainer_state.json

@@ -0,0 +1,259 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.02501136880400182,
+  "eval_steps": 500,
+  "global_step": 220,
+  "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": 40.52,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.69230769230769,
+      "completions/max_terminated_length": 41.69230769230769,
+      "completions/mean_length": 41.5,
+      "completions/mean_terminated_length": 41.5,
+      "completions/min_length": 41.38461538461539,
+      "completions/min_terminated_length": 41.38461538461539,
+      "epoch": 0.002842201000454752,
+      "frac_reward_zero_std": 0.6153846153846154,
+      "grad_norm": 0.3078555464744568,
+      "kl": 0.4130884063243866,
+      "learning_rate": 6.818181818181817e-08,
+      "loss": 0.009083011150360108,
+      "num_tokens": 16252.0,
+      "reward": 6.017776635976938e-09,
+      "reward_std": 0.4111711337016179,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 6.017776635976938e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.4111711337016179,
+      "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": 33.35,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 32.5,
+      "completions/max_terminated_length": 32.5,
+      "completions/mean_length": 31.989583333333332,
+      "completions/mean_terminated_length": 31.989583333333332,
+      "completions/min_length": 31.166666666666668,
+      "completions/min_terminated_length": 31.166666666666668,
+      "epoch": 0.005684402000909504,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.00011760747293010354,
+      "kl": 0.5057662864029407,
+      "learning_rate": 1.3920454545454543e-07,
+      "loss": -0.008437809944152832,
+      "num_tokens": 28507.0,
+      "reward": 2.483526865641276e-09,
+      "reward_std": 0.5345224638779958,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 2.483526865641276e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.5345224738121033,
+      "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": 28.39,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 29.76923076923077,
+      "completions/max_terminated_length": 29.76923076923077,
+      "completions/mean_length": 29.682692307692307,
+      "completions/mean_terminated_length": 29.682692307692307,
+      "completions/min_length": 29.53846153846154,
+      "completions/min_terminated_length": 29.53846153846154,
+      "epoch": 0.008526603001364257,
+      "frac_reward_zero_std": 0.6923076923076923,
+      "grad_norm": 0.1779666692018509,
+      "kl": 0.5825921362638473,
+      "learning_rate": 2.1022727272727273e-07,
+      "loss": 0.005986777544021607,
+      "num_tokens": 40810.0,
+      "reward": 4.584972675030048e-09,
+      "reward_std": 0.32893691613123965,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 4.584972675030048e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.3289369069612943,
+      "step": 75
+    },
+    {
+      "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": 24.25,
+      "completions/max_terminated_length": 24.25,
+      "completions/mean_length": 24.166666666666668,
+      "completions/mean_terminated_length": 24.166666666666668,
+      "completions/min_length": 24.083333333333332,
+      "completions/min_terminated_length": 24.083333333333332,
+      "epoch": 0.011368804001819008,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.0001858328323578462,
+      "kl": 0.5760334812104702,
+      "learning_rate": 2.8125e-07,
+      "loss": -0.0015538424253463746,
+      "num_tokens": 49954.0,
+      "reward": 2.483526865641276e-09,
+      "reward_std": 0.26726123690605164,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 2.483526865641276e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.26726123690605164,
+      "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": 23.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 24.076923076923077,
+      "completions/max_terminated_length": 24.076923076923077,
+      "completions/mean_length": 23.73076923076923,
+      "completions/mean_terminated_length": 23.73076923076923,
+      "completions/min_length": 23.307692307692307,
+      "completions/min_terminated_length": 23.307692307692307,
+      "epoch": 0.014211005002273762,
+      "frac_reward_zero_std": 0.6153846153846154,
+      "grad_norm": 0.00013943837257102132,
+      "kl": 0.6416070720553398,
+      "learning_rate": 3.5227272727272725e-07,
+      "loss": 0.0062805676460266115,
+      "num_tokens": 60550.0,
+      "reward": 5.7312158437875604e-09,
+      "reward_std": 0.4111711337016179,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 5.7312158437875604e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.4111711337016179,
+      "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": 33.42,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 33.25,
+      "completions/max_terminated_length": 33.25,
+      "completions/mean_length": 33.0625,
+      "completions/mean_terminated_length": 33.0625,
+      "completions/min_length": 32.583333333333336,
+      "completions/min_terminated_length": 32.583333333333336,
+      "epoch": 0.017053206002728513,
+      "frac_reward_zero_std": 0.6666666666666666,
+      "grad_norm": 0.00035186903551220894,
+      "kl": 0.47411411479115484,
+      "learning_rate": 4.232954545454545e-07,
+      "loss": 0.0006420502066612244,
+      "num_tokens": 72636.0,
+      "reward": -6.20881716410319e-10,
+      "reward_std": 0.35634831587473553,
+      "rewards/TranscriptCorrectionGrpoReward/mean": -6.20881716410319e-10,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.35634831587473553,
+      "step": 150
+    },
+    {
+      "clip_ratio/high_max": 0.0003773584961891174,
+      "clip_ratio/high_mean": 0.0003773584961891174,
+      "clip_ratio/low_mean": 0.0001886792480945587,
+      "clip_ratio/low_min": 0.0001886792480945587,
+      "clip_ratio/region_mean": 0.0005660377442836762,
+      "completion_length": 47.65,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 46.92307692307692,
+      "completions/max_terminated_length": 46.92307692307692,
+      "completions/mean_length": 46.70192307692308,
+      "completions/mean_terminated_length": 46.70192307692308,
+      "completions/min_length": 46.30769230769231,
+      "completions/min_terminated_length": 46.30769230769231,
+      "epoch": 0.019895407003183267,
+      "frac_reward_zero_std": 0.5384615384615384,
+      "grad_norm": 0.00017194119573105127,
+      "kl": 0.37818876296281817,
+      "learning_rate": 4.943181818181818e-07,
+      "loss": 0.0006822419166564942,
+      "num_tokens": 90573.0,
+      "reward": 2.292486337515024e-09,
+      "reward_std": 0.49340536961188686,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 2.292486337515024e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.4934053604419415,
+      "step": 175
+    },
+    {
+      "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": 25.62,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 25.75,
+      "completions/max_terminated_length": 25.75,
+      "completions/mean_length": 25.729166666666668,
+      "completions/mean_terminated_length": 25.729166666666668,
+      "completions/min_length": 25.666666666666668,
+      "completions/min_terminated_length": 25.666666666666668,
+      "epoch": 0.022737608003638016,
+      "frac_reward_zero_std": 0.9166666666666666,
+      "grad_norm": 0.00034925329964607954,
+      "kl": 0.5583685766160488,
+      "learning_rate": 5.65340909090909e-07,
+      "loss": 0.0031090858578681946,
+      "num_tokens": 100355.0,
+      "reward": 0.0,
+      "reward_std": 0.08908707896868388,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.08908707896868388,
+      "step": 200
+    },
+    {
+      "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": 0.05158098271155596,
+      "step": 220
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 35184,
+  "num_input_tokens_seen": 108278,
+  "num_train_epochs": 4,
+  "save_steps": 220,
+  "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-220/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:129648314bf4204d2156894abc87bea3f3a4a10e3de86dd342e9703104e2b8e7
+size 6801

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

@@ -1,37 +1,25 @@
 {
   "schema_version": 1,
-  "run_id": "2f808075-59c7-4825-afda-13ec73ace137",
+  "run_id": "aa5ad4e1-1030-4baf-82ab-6949c69a6216",
   "run_type": "grpo",
   "profile_name": "llama3_1_8b_base_lessdata_grpo",
   "model_name": "meta-llama/Meta-Llama-3.1-8B",
   "status": "running",
   "best_metric_name": "eval_cer_subset",
   "best_metric_value": 0.016214743153018123,
-  "best_step": 77,
-  "best_checkpoint_step": 77,
-  "latest_checkpoint_step": 231,
+  "best_step": 220,
+  "best_checkpoint_step": 220,
+  "latest_checkpoint_step": 220,
   "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"
-    },
-    {
-      "step": 231,
-      "epoch": 0.02626193724420191,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-231",
-      "timestamp": "2026-04-09T23:27:40.426505+00:00"
+      "step": 220,
+      "epoch": 0.02501136880400182,
+      "repo_path": "meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-220",
+      "timestamp": "2026-04-09T23:34:20.553650+00:00"
     }
   ],
   "epoch_artifacts": [],
   "resume_history": [],
-  "created_at": "2026-04-09T23:20:32.422192+00:00",
-  "updated_at": "2026-04-09T23:27:40.426520+00:00"
+  "created_at": "2026-04-09T23:28:11.374630+00:00",
+  "updated_at": "2026-04-09T23:34:20.553666+00:00"
 }