Upload full trainer checkpoint step=366 (profile=llama3_1_8b_base_lessdata, run_type=sft)

.gitattributes

@@ -148,3 +148,4 @@ meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-23460/tokenizer.json fi
 meta-llama__meta-llama-3.1-8b/sft/epoch_0004/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-1013/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 meta-llama__meta-llama-3.1-8b/grpo/checkpoints/checkpoint-2026/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/tokenizer.json filter=lfs diff=lfs merge=lfs -text

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/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
+- lora
+- sft
+- 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/sft/checkpoints/checkpoint-366/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": [
+    "q_proj",
+    "k_proj",
+    "up_proj",
+    "gate_proj",
+    "down_proj",
+    "o_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__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c9911f65f699f709137449b7fd67dc4169e85312261cb1399120c30d43c385a
+size 83945296

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/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/sft/checkpoints/checkpoint-366/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b05cd08b59bd0bc6fa85d84799234d7565c94ef200529e156539f4df4ff5812a
+size 43127973

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ccb8eeb935749fc43744e0a5eeacdf6f0f10253be15266a497cbca0ffaa2573
+size 14645

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6f3cf2c5fd59db6240cf83ae7ce4eb18e62c53f5ee17beab20e8a15a21a4746
+size 1465

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/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/sft/checkpoints/checkpoint-366/trainer_state.json

@@ -0,0 +1,561 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.24965893587994542,
+  "eval_steps": 366,
+  "global_step": 366,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0034106412005457027,
+      "grad_norm": 3.1571648120880127,
+      "learning_rate": 2.542372881355932e-06,
+      "loss": 1.6981744766235352,
+      "step": 5
+    },
+    {
+      "epoch": 0.0068212824010914054,
+      "grad_norm": 9.80073070526123,
+      "learning_rate": 5.720338983050847e-06,
+      "loss": 1.5801130294799806,
+      "step": 10
+    },
+    {
+      "epoch": 0.010231923601637109,
+      "grad_norm": 4.481558799743652,
+      "learning_rate": 8.898305084745763e-06,
+      "loss": 2.1718717575073243,
+      "step": 15
+    },
+    {
+      "epoch": 0.013642564802182811,
+      "grad_norm": 7.221553802490234,
+      "learning_rate": 1.2076271186440677e-05,
+      "loss": 1.5270480155944823,
+      "step": 20
+    },
+    {
+      "epoch": 0.017053206002728513,
+      "grad_norm": 5.330269813537598,
+      "learning_rate": 1.5254237288135592e-05,
+      "loss": 0.9586630821228027,
+      "step": 25
+    },
+    {
+      "epoch": 0.020463847203274217,
+      "grad_norm": 1.7404323816299438,
+      "learning_rate": 1.8432203389830506e-05,
+      "loss": 0.48505802154541017,
+      "step": 30
+    },
+    {
+      "epoch": 0.023874488403819918,
+      "grad_norm": 1.2418887615203857,
+      "learning_rate": 2.1610169491525424e-05,
+      "loss": 0.24452033042907714,
+      "step": 35
+    },
+    {
+      "epoch": 0.027285129604365622,
+      "grad_norm": 1.5928819179534912,
+      "learning_rate": 2.4788135593220338e-05,
+      "loss": 0.25337533950805663,
+      "step": 40
+    },
+    {
+      "epoch": 0.030695770804911322,
+      "grad_norm": 2.0335769653320312,
+      "learning_rate": 2.796610169491525e-05,
+      "loss": 0.1938886046409607,
+      "step": 45
+    },
+    {
+      "epoch": 0.034106412005457026,
+      "grad_norm": 0.18029411137104034,
+      "learning_rate": 3.114406779661017e-05,
+      "loss": 0.1834133505821228,
+      "step": 50
+    },
+    {
+      "epoch": 0.03751705320600273,
+      "grad_norm": 1.7757192850112915,
+      "learning_rate": 3.432203389830508e-05,
+      "loss": 0.15151114463806153,
+      "step": 55
+    },
+    {
+      "epoch": 0.040927694406548434,
+      "grad_norm": 2.1376893520355225,
+      "learning_rate": 3.75e-05,
+      "loss": 0.21634674072265625,
+      "step": 60
+    },
+    {
+      "epoch": 0.04433833560709413,
+      "grad_norm": 2.196387767791748,
+      "learning_rate": 4.067796610169491e-05,
+      "loss": 0.11320395469665527,
+      "step": 65
+    },
+    {
+      "epoch": 0.047748976807639835,
+      "grad_norm": 1.5888807773590088,
+      "learning_rate": 4.3855932203389825e-05,
+      "loss": 0.11050152778625488,
+      "step": 70
+    },
+    {
+      "epoch": 0.05115961800818554,
+      "grad_norm": 4.606944561004639,
+      "learning_rate": 4.703389830508474e-05,
+      "loss": 0.23255281448364257,
+      "step": 75
+    },
+    {
+      "epoch": 0.054570259208731244,
+      "grad_norm": 1.7308639287948608,
+      "learning_rate": 5.021186440677966e-05,
+      "loss": 0.08995866179466247,
+      "step": 80
+    },
+    {
+      "epoch": 0.05798090040927694,
+      "grad_norm": 2.622438430786133,
+      "learning_rate": 5.338983050847457e-05,
+      "loss": 0.05715223550796509,
+      "step": 85
+    },
+    {
+      "epoch": 0.061391541609822645,
+      "grad_norm": 0.34140461683273315,
+      "learning_rate": 5.656779661016949e-05,
+      "loss": 0.06703727245330811,
+      "step": 90
+    },
+    {
+      "epoch": 0.06480218281036836,
+      "grad_norm": 2.7264959812164307,
+      "learning_rate": 5.97457627118644e-05,
+      "loss": 0.10092716217041016,
+      "step": 95
+    },
+    {
+      "epoch": 0.06821282401091405,
+      "grad_norm": 2.0234780311584473,
+      "learning_rate": 6.292372881355932e-05,
+      "loss": 0.03579937815666199,
+      "step": 100
+    },
+    {
+      "epoch": 0.07162346521145975,
+      "grad_norm": 1.3716133832931519,
+      "learning_rate": 6.610169491525423e-05,
+      "loss": 0.07851418852806091,
+      "step": 105
+    },
+    {
+      "epoch": 0.07503410641200546,
+      "grad_norm": 1.2307227849960327,
+      "learning_rate": 6.927966101694914e-05,
+      "loss": 0.07370938658714295,
+      "step": 110
+    },
+    {
+      "epoch": 0.07844474761255116,
+      "grad_norm": 1.7142690420150757,
+      "learning_rate": 7.245762711864406e-05,
+      "loss": 0.08064572811126709,
+      "step": 115
+    },
+    {
+      "epoch": 0.08185538881309687,
+      "grad_norm": 1.343595266342163,
+      "learning_rate": 7.499999439507554e-05,
+      "loss": 0.11841402053833008,
+      "step": 120
+    },
+    {
+      "epoch": 0.08526603001364257,
+      "grad_norm": 1.2511327266693115,
+      "learning_rate": 7.499979822289558e-05,
+      "loss": 0.06974860429763793,
+      "step": 125
+    },
+    {
+      "epoch": 0.08867667121418826,
+      "grad_norm": 1.5642656087875366,
+      "learning_rate": 7.49993218061684e-05,
+      "loss": 0.10972714424133301,
+      "step": 130
+    },
+    {
+      "epoch": 0.09208731241473397,
+      "grad_norm": 1.6669789552688599,
+      "learning_rate": 7.499856514845436e-05,
+      "loss": 0.09864612817764282,
+      "step": 135
+    },
+    {
+      "epoch": 0.09549795361527967,
+      "grad_norm": 0.9789333343505859,
+      "learning_rate": 7.499752825540815e-05,
+      "loss": 0.0699621558189392,
+      "step": 140
+    },
+    {
+      "epoch": 0.09890859481582538,
+      "grad_norm": 0.41792476177215576,
+      "learning_rate": 7.499621113477873e-05,
+      "loss": 0.06734349727630615,
+      "step": 145
+    },
+    {
+      "epoch": 0.10231923601637108,
+      "grad_norm": 1.5968533754348755,
+      "learning_rate": 7.499461379640919e-05,
+      "loss": 0.060729533433914185,
+      "step": 150
+    },
+    {
+      "epoch": 0.10572987721691678,
+      "grad_norm": 0.8512193560600281,
+      "learning_rate": 7.499273625223683e-05,
+      "loss": 0.052730172872543335,
+      "step": 155
+    },
+    {
+      "epoch": 0.10914051841746249,
+      "grad_norm": 1.3257211446762085,
+      "learning_rate": 7.499057851629299e-05,
+      "loss": 0.10094538927078248,
+      "step": 160
+    },
+    {
+      "epoch": 0.11255115961800818,
+      "grad_norm": 0.659118115901947,
+      "learning_rate": 7.498814060470288e-05,
+      "loss": 0.01604635864496231,
+      "step": 165
+    },
+    {
+      "epoch": 0.11596180081855388,
+      "grad_norm": 2.454979181289673,
+      "learning_rate": 7.49854225356856e-05,
+      "loss": 0.13272385597229003,
+      "step": 170
+    },
+    {
+      "epoch": 0.11937244201909959,
+      "grad_norm": 2.510040521621704,
+      "learning_rate": 7.498242432955388e-05,
+      "loss": 0.08396227955818177,
+      "step": 175
+    },
+    {
+      "epoch": 0.12278308321964529,
+      "grad_norm": 0.2637259364128113,
+      "learning_rate": 7.4979146008714e-05,
+      "loss": 0.05852065086364746,
+      "step": 180
+    },
+    {
+      "epoch": 0.126193724420191,
+      "grad_norm": 1.4320851564407349,
+      "learning_rate": 7.497558759766564e-05,
+      "loss": 0.10392802953720093,
+      "step": 185
+    },
+    {
+      "epoch": 0.1296043656207367,
+      "grad_norm": 1.273027777671814,
+      "learning_rate": 7.497174912300156e-05,
+      "loss": 0.08062989711761474,
+      "step": 190
+    },
+    {
+      "epoch": 0.1330150068212824,
+      "grad_norm": 0.8102871179580688,
+      "learning_rate": 7.496763061340759e-05,
+      "loss": 0.07294153571128845,
+      "step": 195
+    },
+    {
+      "epoch": 0.1364256480218281,
+      "grad_norm": 1.951328992843628,
+      "learning_rate": 7.496323209966228e-05,
+      "loss": 0.07738351821899414,
+      "step": 200
+    },
+    {
+      "epoch": 0.13983628922237382,
+      "grad_norm": 0.3880983889102936,
+      "learning_rate": 7.495855361463674e-05,
+      "loss": 0.07225048542022705,
+      "step": 205
+    },
+    {
+      "epoch": 0.1432469304229195,
+      "grad_norm": 3.3205058574676514,
+      "learning_rate": 7.495359519329433e-05,
+      "loss": 0.05682974457740784,
+      "step": 210
+    },
+    {
+      "epoch": 0.1466575716234652,
+      "grad_norm": 0.9203559160232544,
+      "learning_rate": 7.49483568726905e-05,
+      "loss": 0.08767472505569458,
+      "step": 215
+    },
+    {
+      "epoch": 0.15006821282401092,
+      "grad_norm": 0.585360586643219,
+      "learning_rate": 7.494283869197239e-05,
+      "loss": 0.039227068424224854,
+      "step": 220
+    },
+    {
+      "epoch": 0.1534788540245566,
+      "grad_norm": 1.7096059322357178,
+      "learning_rate": 7.493704069237862e-05,
+      "loss": 0.10281096696853638,
+      "step": 225
+    },
+    {
+      "epoch": 0.15688949522510232,
+      "grad_norm": 0.4110204875469208,
+      "learning_rate": 7.493096291723898e-05,
+      "loss": 0.04346161186695099,
+      "step": 230
+    },
+    {
+      "epoch": 0.16030013642564803,
+      "grad_norm": 1.3272292613983154,
+      "learning_rate": 7.492460541197404e-05,
+      "loss": 0.049719154834747314,
+      "step": 235
+    },
+    {
+      "epoch": 0.16371077762619374,
+      "grad_norm": 1.1005016565322876,
+      "learning_rate": 7.491796822409494e-05,
+      "loss": 0.09335108399391175,
+      "step": 240
+    },
+    {
+      "epoch": 0.16712141882673942,
+      "grad_norm": 0.7811501026153564,
+      "learning_rate": 7.491105140320285e-05,
+      "loss": 0.05943926572799683,
+      "step": 245
+    },
+    {
+      "epoch": 0.17053206002728513,
+      "grad_norm": 1.4607417583465576,
+      "learning_rate": 7.490385500098879e-05,
+      "loss": 0.04385361075401306,
+      "step": 250
+    },
+    {
+      "epoch": 0.17394270122783084,
+      "grad_norm": 0.394960880279541,
+      "learning_rate": 7.489637907123308e-05,
+      "loss": 0.04446137547492981,
+      "step": 255
+    },
+    {
+      "epoch": 0.17735334242837653,
+      "grad_norm": 0.8768635988235474,
+      "learning_rate": 7.488862366980505e-05,
+      "loss": 0.04143576025962829,
+      "step": 260
+    },
+    {
+      "epoch": 0.18076398362892224,
+      "grad_norm": 1.9996010065078735,
+      "learning_rate": 7.488058885466262e-05,
+      "loss": 0.07952215671539306,
+      "step": 265
+    },
+    {
+      "epoch": 0.18417462482946795,
+      "grad_norm": 0.03770223259925842,
+      "learning_rate": 7.487227468585178e-05,
+      "loss": 0.02531362771987915,
+      "step": 270
+    },
+    {
+      "epoch": 0.18758526603001363,
+      "grad_norm": 0.26082542538642883,
+      "learning_rate": 7.486368122550619e-05,
+      "loss": 0.09930967688560485,
+      "step": 275
+    },
+    {
+      "epoch": 0.19099590723055934,
+      "grad_norm": 5.622270584106445,
+      "learning_rate": 7.485480853784677e-05,
+      "loss": 0.06534865498542786,
+      "step": 280
+    },
+    {
+      "epoch": 0.19440654843110505,
+      "grad_norm": 0.5298851132392883,
+      "learning_rate": 7.484565668918111e-05,
+      "loss": 0.06109699010848999,
+      "step": 285
+    },
+    {
+      "epoch": 0.19781718963165076,
+      "grad_norm": 1.4887421131134033,
+      "learning_rate": 7.483622574790308e-05,
+      "loss": 0.048966211080551145,
+      "step": 290
+    },
+    {
+      "epoch": 0.20122783083219645,
+      "grad_norm": 0.5699282884597778,
+      "learning_rate": 7.482651578449223e-05,
+      "loss": 0.05427658557891846,
+      "step": 295
+    },
+    {
+      "epoch": 0.20463847203274216,
+      "grad_norm": 1.6645292043685913,
+      "learning_rate": 7.481652687151339e-05,
+      "loss": 0.037466832995414735,
+      "step": 300
+    },
+    {
+      "epoch": 0.20804911323328787,
+      "grad_norm": 0.4979431629180908,
+      "learning_rate": 7.480625908361593e-05,
+      "loss": 0.019084173440933227,
+      "step": 305
+    },
+    {
+      "epoch": 0.21145975443383355,
+      "grad_norm": 2.73081636428833,
+      "learning_rate": 7.479571249753339e-05,
+      "loss": 0.07597044706344605,
+      "step": 310
+    },
+    {
+      "epoch": 0.21487039563437926,
+      "grad_norm": 0.009097559377551079,
+      "learning_rate": 7.478488719208281e-05,
+      "loss": 0.017771795392036438,
+      "step": 315
+    },
+    {
+      "epoch": 0.21828103683492497,
+      "grad_norm": 1.5284112691879272,
+      "learning_rate": 7.477378324816419e-05,
+      "loss": 0.07524526119232178,
+      "step": 320
+    },
+    {
+      "epoch": 0.22169167803547066,
+      "grad_norm": 1.400959849357605,
+      "learning_rate": 7.47624007487598e-05,
+      "loss": 0.0357323557138443,
+      "step": 325
+    },
+    {
+      "epoch": 0.22510231923601637,
+      "grad_norm": 0.5988397598266602,
+      "learning_rate": 7.47507397789337e-05,
+      "loss": 0.06072888970375061,
+      "step": 330
+    },
+    {
+      "epoch": 0.22851296043656208,
+      "grad_norm": 0.18309183418750763,
+      "learning_rate": 7.473880042583092e-05,
+      "loss": 0.03904334008693695,
+      "step": 335
+    },
+    {
+      "epoch": 0.23192360163710776,
+      "grad_norm": 0.7360084056854248,
+      "learning_rate": 7.472658277867702e-05,
+      "loss": 0.05045387148857117,
+      "step": 340
+    },
+    {
+      "epoch": 0.23533424283765347,
+      "grad_norm": 2.315072536468506,
+      "learning_rate": 7.471408692877724e-05,
+      "loss": 0.07920202016830444,
+      "step": 345
+    },
+    {
+      "epoch": 0.23874488403819918,
+      "grad_norm": 1.2811086177825928,
+      "learning_rate": 7.470131296951592e-05,
+      "loss": 0.05552580952644348,
+      "step": 350
+    },
+    {
+      "epoch": 0.2421555252387449,
+      "grad_norm": 4.006563186645508,
+      "learning_rate": 7.468826099635578e-05,
+      "loss": 0.1419215679168701,
+      "step": 355
+    },
+    {
+      "epoch": 0.24556616643929058,
+      "grad_norm": 1.1540688276290894,
+      "learning_rate": 7.467493110683718e-05,
+      "loss": 0.03980849981307984,
+      "step": 360
+    },
+    {
+      "epoch": 0.2489768076398363,
+      "grad_norm": 1.5472272634506226,
+      "learning_rate": 7.466132340057742e-05,
+      "loss": 0.020862475037574768,
+      "step": 365
+    },
+    {
+      "epoch": 0.24965893587994542,
+      "eval_loss": 0.11654457449913025,
+      "eval_runtime": 1.0333,
+      "eval_samples_per_second": 72.584,
+      "eval_steps_per_second": 1.936,
+      "step": 366
+    },
+    {
+      "eval_cer_subset": 0.05232320479629377,
+      "eval_cer_subset_edit_distance": 384,
+      "eval_cer_subset_groups": 75,
+      "eval_cer_subset_items": 75,
+      "eval_cer_subset_ref_chars": 7339,
+      "step": 366
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 5864,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 366,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3797973616877568.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc6915d8d9dd9b5c9c17756c87ba7ec8221fd06789232d79225f9518167f0aa1
+size 5841

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

@@ -1,104 +1,25 @@
 {
   "schema_version": 1,
-  "run_id": "aacb0b6c-2b10-48da-90bc-ca77fd7cac31",
+  "run_id": "b21d4e76-e0f6-4f23-a059-57095fb3ba07",
   "run_type": "sft",
-  "profile_name": "llama3_1_8b_base",
+  "profile_name": "llama3_1_8b_base_lessdata",
   "model_name": "meta-llama/Meta-Llama-3.1-8B",
-  "status": "completed",
+  "status": "running",
   "best_metric_name": "eval_loss",
-  "best_metric_value": 0.03369956836104393,
-  "best_step": 5864,
-  "best_checkpoint_step": 5864,
-  "latest_checkpoint_step": 23460,
+  "best_metric_value": 0.11654457449913025,
+  "best_step": 366,
+  "best_checkpoint_step": 366,
+  "latest_checkpoint_step": 366,
   "checkpoints": [
     {
-      "step": 1466,
-      "epoch": 0.24995737425404946,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-1466",
-      "timestamp": "2026-04-09T06:43:22.133396+00:00"
-    },
-    {
-      "step": 2932,
-      "epoch": 0.4999147485080989,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-2932",
-      "timestamp": "2026-04-09T07:05:26.247945+00:00"
-    },
-    {
-      "step": 4398,
-      "epoch": 0.7498721227621483,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-4398",
-      "timestamp": "2026-04-09T07:27:30.375921+00:00"
-    },
-    {
-      "step": 5864,
-      "epoch": 0.9998294970161978,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-5864",
-      "timestamp": "2026-04-09T07:49:35.524807+00:00"
-    },
-    {
-      "step": 8796,
-      "epoch": 1.4997442455242966,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-8796",
-      "timestamp": "2026-04-09T08:33:55.041513+00:00"
-    },
-    {
-      "step": 11728,
-      "epoch": 1.9996589940323957,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-11728",
-      "timestamp": "2026-04-09T09:17:58.928263+00:00"
-    },
-    {
-      "step": 17592,
-      "epoch": 2.9994884910485933,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-17592",
-      "timestamp": "2026-04-09T10:51:28.078443+00:00"
-    },
-    {
-      "step": 20524,
-      "epoch": 3.4994032395566923,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-20524",
-      "timestamp": "2026-04-09T11:35:41.945420+00:00"
-    },
-    {
-      "step": 23456,
-      "epoch": 3.9993179880647913,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-23456",
-      "timestamp": "2026-04-09T12:19:46.469075+00:00"
-    },
-    {
-      "step": 23460,
-      "epoch": 4.0,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-23460",
-      "timestamp": "2026-04-09T12:19:53.861946+00:00"
-    }
-  ],
-  "epoch_artifacts": [
-    {
-      "epoch_label": "epoch_0001",
-      "global_step": 5865,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/epoch_0001",
-      "timestamp": "2026-04-09T07:49:42.819325+00:00"
-    },
-    {
-      "epoch_label": "epoch_0002",
-      "global_step": 11730,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/epoch_0002",
-      "timestamp": "2026-04-09T09:18:09.377639+00:00"
-    },
-    {
-      "epoch_label": "epoch_0003",
-      "global_step": 17595,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/epoch_0003",
-      "timestamp": "2026-04-09T10:51:37.072000+00:00"
-    },
-    {
-      "epoch_label": "epoch_0004",
-      "global_step": 23460,
-      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/epoch_0004",
-      "timestamp": "2026-04-09T12:20:09.009540+00:00"
+      "step": 366,
+      "epoch": 0.24965893587994542,
+      "repo_path": "meta-llama__meta-llama-3.1-8b/sft/checkpoints/checkpoint-366",
+      "timestamp": "2026-04-09T22:13:58.949626+00:00"
     }
   ],
+  "epoch_artifacts": [],
   "resume_history": [],
-  "created_at": "2026-04-09T06:12:43.688637+00:00",
-  "updated_at": "2026-04-09T12:20:10.233837+00:00"
+  "created_at": "2026-04-09T22:12:40.588264+00:00",
+  "updated_at": "2026-04-09T22:13:58.949641+00:00"
 }