Upload full trainer checkpoint step=12 (profile=llama3_2_1b_base_grpo, run_type=grpo)

.gitattributes

@@ -85,3 +85,4 @@ meta-llama__llama-3.2-3b/sft/checkpoints/checkpoint-23460/tokenizer.json filter=
 meta-llama__llama-3.2-3b/sft/epoch_0002/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-3b/sft/checkpoints/checkpoint-29325/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-1/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/tokenizer.json filter=lfs diff=lfs merge=lfs -text

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/README.md

@@ -0,0 +1,210 @@
+---
+base_model: unsloth/Llama-3.2-1B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- base_model:adapter:unsloth/Llama-3.2-1B
+- 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__llama-3.2-1b/grpo/checkpoints/checkpoint-12/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/Llama-3.2-1B",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0e2dfa0bd6aeae8ec5364292c5d8ab1899d4a4d88c63c04f9a7f580320bf1d4
+size 45118424

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/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__llama-3.2-1b/grpo/checkpoints/checkpoint-12/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:39c8e2e2ab0d2f5c3a0b898e3072b9c1cd409dcf1a5d3ab2db45bca53bdfe426
+size 23161995

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/resume_sft_best/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/Llama-3.2-1B",
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "k_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj"
+  ],
+  "target_parameters": null,
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/resume_sft_best/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3988685dd9aa68862166af33a4fba581625fb5a9f6e0e3b7421f991aca0134d
+size 45118424

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ba8b2067d00267df2112458b0715bf7e40ce4cc15e3b137aa3b14ee1db6b87
+size 14645

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69f8360bb6bd72f37ab1e8e7dc0ca5c04a2d11d72d258079033a70321d263a8f
+size 1465

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/tokenizer.json

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

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12/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__llama-3.2-1b/grpo/checkpoints/checkpoint-12/trainer_state.json

@@ -0,0 +1,97 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 6.394202589652049e-05,
+  "eval_steps": 500,
+  "global_step": 12,
+  "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": 81.15,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 81.4,
+      "completions/max_terminated_length": 81.4,
+      "completions/mean_length": 81.15,
+      "completions/mean_terminated_length": 81.15,
+      "completions/min_length": 81.0,
+      "completions/min_terminated_length": 81.0,
+      "epoch": 2.664251079021687e-05,
+      "frac_reward_zero_std": 0.4,
+      "grad_norm": 0.3002080023288727,
+      "kl": 0.0,
+      "learning_rate": 6.66045024643666e-09,
+      "loss": -0.0027932614088058473,
+      "num_tokens": 5659.0,
+      "reward": -2.9802322387695314e-09,
+      "reward_std": 0.6928203105926514,
+      "rewards/TranscriptCorrectionGrpoReward/mean": -2.9802322387695314e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.6928203105926514,
+      "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,
+      "completion_length": 72.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 72.0,
+      "completions/max_terminated_length": 72.0,
+      "completions/mean_length": 72.0,
+      "completions/mean_terminated_length": 72.0,
+      "completions/min_length": 72.0,
+      "completions/min_terminated_length": 72.0,
+      "epoch": 5.328502158043374e-05,
+      "frac_reward_zero_std": 1.0,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 1.4986013054482483e-08,
+      "loss": 0.0,
+      "num_tokens": 10775.0,
+      "reward": 0.0,
+      "reward_std": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.0,
+      "step": 10
+    },
+    {
+      "eval_cer_subset": 0.01286498281954826,
+      "eval_cer_subset_edit_distance": 790,
+      "eval_cer_subset_groups": 250,
+      "eval_cer_subset_items": 250,
+      "eval_cer_subset_ref_chars": 61407,
+      "eval_loss": 0.03968677925542445,
+      "step": 12
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 750680,
+  "num_input_tokens_seen": 11992,
+  "num_train_epochs": 4,
+  "save_steps": 23459,
+  "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__llama-3.2-1b/grpo/checkpoints/checkpoint-12/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dc9dcf8fc2cfa2ae39db7cc155f89579dd01760e944ae0b35ff374914bb92fb
+size 6737

meta-llama__llama-3.2-1b/grpo/run_manifest.json

@@ -1,25 +1,25 @@
 {
   "schema_version": 1,
-  "run_id": "3ff7e562-67c6-4ee9-9e2b-6fabb8d102dd",
+  "run_id": "525fad5f-fe8b-4a6f-80c1-1f0dd26b7111",
   "run_type": "grpo",
   "profile_name": "llama3_2_1b_base_grpo",
   "model_name": "meta-llama/Llama-3.2-1B",
   "status": "running",
   "best_metric_name": "eval_cer_subset",
-  "best_metric_value": 1.0,
-  "best_step": 1,
-  "best_checkpoint_step": 1,
-  "latest_checkpoint_step": 1,
+  "best_metric_value": 0.01286498281954826,
+  "best_step": 12,
+  "best_checkpoint_step": 12,
+  "latest_checkpoint_step": 12,
   "checkpoints": [
     {
-      "step": 1,
-      "epoch": 5.328502158043374e-06,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-1",
-      "timestamp": "2026-04-08T18:47:25.950449+00:00"
+      "step": 12,
+      "epoch": 6.394202589652049e-05,
+      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-12",
+      "timestamp": "2026-04-08T19:27:43.963032+00:00"
     }
   ],
   "epoch_artifacts": [],
   "resume_history": [],
-  "created_at": "2026-04-08T18:45:17.085398+00:00",
-  "updated_at": "2026-04-08T18:47:25.950463+00:00"
+  "created_at": "2026-04-08T19:26:15.718549+00:00",
+  "updated_at": "2026-04-08T19:27:43.963049+00:00"
 }