Upload full trainer checkpoint step=507 (profile=llama3_2_1b_base_grpo, run_type=grpo)

.gitattributes

@@ -99,3 +99,4 @@ meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-7038/tokenizer.json filter=
 meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-8211/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-9384/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-10557/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507/tokenizer.json filter=lfs diff=lfs merge=lfs -text

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507/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-507/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": [
+    "down_proj",
+    "o_proj",
+    "q_proj",
+    "gate_proj",
+    "k_proj",
+    "up_proj",
+    "v_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-507/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3488c462f9a16c18f77b6c50b23298751f3403f3423e962979e7384a0b50041
+size 45118424

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507/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-507/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c45fddad6005039ed09a90bd9a0a4a1ce76c7945d53ffdefb831f35b22894d8
+size 23162187

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bba30b3c53bec237646fa7befb0d9754bb02d88a3b5c49b2dc26db53253a23c0
+size 14645

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48205f86f7675d7ee9e083ac48b20843b9d59809cc4035576cf13ff625869f20
+size 1465

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507/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-507/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-507/trainer_state.json

@@ -0,0 +1,313 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.0009005200636580653,
+  "eval_steps": 500,
+  "global_step": 507,
+  "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": 65.67,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 93.75,
+      "completions/max_terminated_length": 93.75,
+      "completions/mean_length": 63.3203125,
+      "completions/mean_terminated_length": 63.3203125,
+      "completions/min_length": 38.25,
+      "completions/min_terminated_length": 38.25,
+      "epoch": 8.88086847789019e-05,
+      "frac_reward_zero_std": 0.5625,
+      "grad_norm": 0.007002627942711115,
+      "kl": 0.0,
+      "learning_rate": 2.7197442330321267e-08,
+      "loss": -0.0006554330885410309,
+      "num_tokens": 57618.0,
+      "reward": -6.51925802230835e-09,
+      "reward_std": 0.48731958121061325,
+      "rewards/TranscriptCorrectionGrpoReward/mean": -8.381903171539307e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.007905274629593,
+      "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": 52.34,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 84.33333333333333,
+      "completions/max_terminated_length": 84.33333333333333,
+      "completions/mean_length": 51.208333333333336,
+      "completions/mean_terminated_length": 51.208333333333336,
+      "completions/min_length": 26.0,
+      "completions/min_terminated_length": 26.0,
+      "epoch": 0.0001776173695578038,
+      "frac_reward_zero_std": 0.6666666666666666,
+      "grad_norm": 0.0,
+      "kl": 0.0,
+      "learning_rate": 5.494993450411847e-08,
+      "loss": 0.0013675823807716369,
+      "num_tokens": 94074.0,
+      "reward": 1.4901161193847656e-08,
+      "reward_std": 0.44680649042129517,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 1.179675261179606e-08,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052845637004,
+      "step": 100
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.00017899675294756888,
+      "clip_ratio/low_min": 0.00017899675294756888,
+      "clip_ratio/region_mean": 0.00017899675294756888,
+      "completion_length": 64.945,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 119.33333333333333,
+      "completions/max_terminated_length": 119.33333333333333,
+      "completions/mean_length": 66.65625,
+      "completions/mean_terminated_length": 66.65625,
+      "completions/min_length": 39.0,
+      "completions/min_terminated_length": 39.0,
+      "epoch": 0.0002664260543367057,
+      "frac_reward_zero_std": 0.7083333333333334,
+      "grad_norm": 0.015731461346149445,
+      "kl": 0.0,
+      "learning_rate": 8.270242667791569e-08,
+      "loss": 0.0017325745522975922,
+      "num_tokens": 139152.0,
+      "reward": 2.483526865641276e-09,
+      "reward_std": 0.2613494098186493,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052448272705,
+      "step": 150
+    },
+    {
+      "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": 60.15,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 99.0,
+      "completions/max_terminated_length": 99.0,
+      "completions/mean_length": 63.015625,
+      "completions/mean_terminated_length": 63.015625,
+      "completions/min_length": 32.666666666666664,
+      "completions/min_terminated_length": 32.666666666666664,
+      "epoch": 0.0003552347391156076,
+      "frac_reward_zero_std": 0.4583333333333333,
+      "grad_norm": 0.039579447358846664,
+      "kl": 0.0,
+      "learning_rate": 1.1045491885171288e-07,
+      "loss": -0.0044269835948944096,
+      "num_tokens": 182803.0,
+      "reward": -4.967053731282552e-09,
+      "reward_std": 0.5628267228603363,
+      "rewards/TranscriptCorrectionGrpoReward/mean": -2.483526865641276e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052845637004,
+      "step": 200
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.00016559829469770193,
+      "clip_ratio/low_min": 0.00016559829469770193,
+      "clip_ratio/region_mean": 0.00016559829469770193,
+      "completion_length": 64.905,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 98.66666666666667,
+      "completions/max_terminated_length": 98.66666666666667,
+      "completions/mean_length": 64.203125,
+      "completions/mean_terminated_length": 64.203125,
+      "completions/min_length": 35.666666666666664,
+      "completions/min_terminated_length": 35.666666666666664,
+      "epoch": 0.0004440434238945095,
+      "frac_reward_zero_std": 0.4166666666666667,
+      "grad_norm": 0.011699045076966286,
+      "kl": 0.0,
+      "learning_rate": 1.382074110255101e-07,
+      "loss": 0.00223430335521698,
+      "num_tokens": 227314.0,
+      "reward": 2.2351741790771484e-08,
+      "reward_std": 0.4298504690329234,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 1.241763432820638e-08,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052448272705,
+      "step": 250
+    },
+    {
+      "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": 70.07,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 108.0,
+      "completions/max_terminated_length": 108.0,
+      "completions/mean_length": 70.63541666666667,
+      "completions/mean_terminated_length": 70.63541666666667,
+      "completions/min_length": 34.0,
+      "completions/min_terminated_length": 34.0,
+      "epoch": 0.0005328521086734114,
+      "frac_reward_zero_std": 0.5833333333333334,
+      "grad_norm": 0.0456908717751503,
+      "kl": 0.0,
+      "learning_rate": 1.659599031993073e-07,
+      "loss": -0.0011175717413425446,
+      "num_tokens": 275956.0,
+      "reward": 5.587935447692871e-09,
+      "reward_std": 0.4012269576390584,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 3.104408582051595e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052448272705,
+      "step": 300
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 5.8139534667134284e-05,
+      "clip_ratio/low_min": 5.8139534667134284e-05,
+      "clip_ratio/region_mean": 5.8139534667134284e-05,
+      "completion_length": 62.93,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 95.66666666666667,
+      "completions/max_terminated_length": 95.66666666666667,
+      "completions/mean_length": 61.6875,
+      "completions/mean_terminated_length": 61.6875,
+      "completions/min_length": 29.333333333333332,
+      "completions/min_terminated_length": 29.333333333333332,
+      "epoch": 0.0006216607934523133,
+      "frac_reward_zero_std": 0.75,
+      "grad_norm": 0.0190290417522192,
+      "kl": 0.0,
+      "learning_rate": 1.9371239537310452e-07,
+      "loss": -0.0010719958692789078,
+      "num_tokens": 319328.0,
+      "reward": -2.483526865641276e-09,
+      "reward_std": 0.34829530119895935,
+      "rewards/TranscriptCorrectionGrpoReward/mean": -4.967053731282552e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052448272705,
+      "step": 350
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 7.352941203862428e-05,
+      "clip_ratio/low_min": 7.352941203862428e-05,
+      "clip_ratio/region_mean": 7.352941203862428e-05,
+      "completion_length": 62.725,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 105.66666666666667,
+      "completions/max_terminated_length": 105.66666666666667,
+      "completions/mean_length": 62.890625,
+      "completions/mean_terminated_length": 62.890625,
+      "completions/min_length": 34.666666666666664,
+      "completions/min_terminated_length": 34.666666666666664,
+      "epoch": 0.0007104694782312152,
+      "frac_reward_zero_std": 0.5,
+      "grad_norm": 0.02625960297882557,
+      "kl": 0.0,
+      "learning_rate": 2.2146488754690174e-07,
+      "loss": 0.0013731226325035095,
+      "num_tokens": 362563.0,
+      "reward": 4.967053731282552e-09,
+      "reward_std": 0.44316299756368,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 0.0,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052448272705,
+      "step": 400
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 8.695651777088643e-05,
+      "clip_ratio/low_min": 8.695651777088643e-05,
+      "clip_ratio/region_mean": 8.695651777088643e-05,
+      "completion_length": 66.03,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 112.0,
+      "completions/max_terminated_length": 112.0,
+      "completions/mean_length": 70.2890625,
+      "completions/mean_terminated_length": 70.2890625,
+      "completions/min_length": 42.75,
+      "completions/min_terminated_length": 42.75,
+      "epoch": 0.0007992781630101171,
+      "frac_reward_zero_std": 0.5625,
+      "grad_norm": 0.0035960455425083637,
+      "kl": 0.0,
+      "learning_rate": 2.492173797206989e-07,
+      "loss": -0.0004108186066150665,
+      "num_tokens": 427021.0,
+      "reward": 1.30385160446167e-08,
+      "reward_std": 0.383321788161993,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 1.4901161193847656e-08,
+      "rewards/TranscriptCorrectionGrpoReward/std": 1.0079052448272705,
+      "step": 450
+    },
+    {
+      "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": 63.98,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 85.33333333333333,
+      "completions/max_terminated_length": 85.33333333333333,
+      "completions/mean_length": 55.046875,
+      "completions/mean_terminated_length": 55.046875,
+      "completions/min_length": 29.666666666666668,
+      "completions/min_terminated_length": 29.666666666666668,
+      "epoch": 0.000888086847789019,
+      "frac_reward_zero_std": 0.7916666666666666,
+      "grad_norm": 0.0006704159895889461,
+      "kl": 0.0,
+      "learning_rate": 2.7696987189449615e-07,
+      "loss": 0.0006217561289668084,
+      "num_tokens": 464766.0,
+      "reward": -4.967053731282552e-09,
+      "reward_std": 0.1608196645975113,
+      "rewards/TranscriptCorrectionGrpoReward/mean": 4.967053731282552e-09,
+      "rewards/TranscriptCorrectionGrpoReward/std": 0.6719369093577067,
+      "step": 500
+    },
+    {
+      "eval_cer_subset": 0.013239532952269286,
+      "eval_cer_subset_edit_distance": 813,
+      "eval_cer_subset_groups": 250,
+      "eval_cer_subset_items": 250,
+      "eval_cer_subset_ref_chars": 61407,
+      "eval_loss": 0.03968957871396896,
+      "step": 507
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 2252032,
+  "num_input_tokens_seen": 464766,
+  "num_train_epochs": 4,
+  "save_steps": 507,
+  "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": 2,
+  "trial_name": null,
+  "trial_params": null
+}

meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efd03f5456a4c15d2256ba2960a071c6dc2cb8a2ff8cf43b4f1331b6c112c442
+size 6737

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

@@ -1,81 +1,25 @@
 {
   "schema_version": 1,
-  "run_id": "44a9bcf9-66a6-4b97-a131-62881f53fa88",
+  "run_id": "3c42986d-e4d4-455e-95c4-4a4d5ecb544c",
   "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": 0.012881267607927434,
-  "best_step": 1173,
-  "best_checkpoint_step": 1173,
-  "latest_checkpoint_step": 10557,
+  "best_metric_value": 0.013239532952269286,
+  "best_step": 507,
+  "best_checkpoint_step": 507,
+  "latest_checkpoint_step": 507,
   "checkpoints": [
     {
-      "step": 1173,
-      "epoch": 0.00625053286725211,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-1173",
-      "timestamp": "2026-04-08T21:07:07.041384+00:00"
-    },
-    {
-      "step": 2346,
-      "epoch": 0.01250106573450422,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-2346",
-      "timestamp": "2026-04-08T21:18:34.568372+00:00"
-    },
-    {
-      "step": 3519,
-      "epoch": 0.007500511543839307,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-3519",
-      "timestamp": "2026-04-08T22:30:06.990940+00:00"
-    },
-    {
-      "step": 4692,
-      "epoch": 0.01000068205845241,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-4692",
-      "timestamp": "2026-04-08T22:51:34.254320+00:00"
-    },
-    {
-      "step": 5865,
-      "epoch": 0.012500852573065512,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-5865",
-      "timestamp": "2026-04-08T23:04:54.462683+00:00"
-    },
-    {
-      "step": 7038,
-      "epoch": 0.015001023087678615,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-7038",
-      "timestamp": "2026-04-08T23:16:13.595496+00:00"
-    },
-    {
-      "step": 8211,
-      "epoch": 0.017501193602291715,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-8211",
-      "timestamp": "2026-04-08T23:26:42.917010+00:00"
-    },
-    {
-      "step": 9384,
-      "epoch": 0.02000136411690482,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-9384",
-      "timestamp": "2026-04-08T23:39:24.442762+00:00"
-    },
-    {
-      "step": 10557,
-      "epoch": 0.02250153463151792,
-      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-10557",
-      "timestamp": "2026-04-08T23:49:51.231298+00:00"
+      "step": 507,
+      "epoch": 0.0009005200636580653,
+      "repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-507",
+      "timestamp": "2026-04-09T01:05:45.596061+00:00"
     }
   ],
   "epoch_artifacts": [],
-  "resume_history": [
-    {
-      "timestamp": "2026-04-08T21:57:38.898332+00:00",
-      "target": "latest",
-      "requested_step": null,
-      "resolved_step": 2346,
-      "checkpoint_repo_path": "meta-llama__llama-3.2-1b/grpo/checkpoints/checkpoint-2346"
-    }
-  ],
-  "created_at": "2026-04-08T20:52:57.531787+00:00",
-  "updated_at": "2026-04-08T23:49:51.231314+00:00"
+  "resume_history": [],
+  "created_at": "2026-04-09T00:54:21.973160+00:00",
+  "updated_at": "2026-04-09T01:05:45.596078+00:00"
 }