Upload folder using huggingface_hub

README.md

@@ -0,0 +1,112 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: allenai/Olmo-3-1025-7B
+tags:
+- generated_from_trainer
+model-index:
+- name: model-out
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.15.0`
+```yaml
+# ── Continued Pretraining: 7B on 8×A40 (48GB) ──
+
+base_model: allenai/Olmo-3-1025-7B
+tokenizer_type: AutoTokenizer
+
+# ── Data ──
+datasets:
+  - path: data/1b/all.jsonl
+    type: completion
+    field: completion
+
+# ── Sequence / packing ──
+sequence_len: 2048
+sample_packing: true
+pad_to_sequence_len: true
+# NOTE: do NOT enable group_by_length with sample_packing
+
+# ── Batch sizing ──
+# Per-GPU: 4 seqs × 2048 tok = 8k tokens/step/GPU
+# Global:  4 × 4 accum × 8 GPUs = 128 effective seqs/step
+micro_batch_size: 4
+gradient_accumulation_steps: 4
+
+# ── Training ──
+train_on_inputs: true
+optimizer: adamw_torch
+lr_scheduler: cosine
+learning_rate: 5e-5
+warmup_steps: 200
+max_steps: 150
+weight_decay: 0.01
+
+# ── Precision / memory ──
+bf16: true
+flash_attention: true
+gradient_checkpointing: true
+
+# ── DeepSpeed ZeRO Stage 2 ──
+deepspeed: ds_stage2.json
+
+# ── Logging ──
+logging_steps: 10
+save_strategy: steps
+save_steps: 50
+```
+
+</details><br>
+
+# model-out
+
+This model is a fine-tuned version of [allenai/Olmo-3-1025-7B](https://huggingface.co/allenai/Olmo-3-1025-7B) on the data/1b/all.jsonl dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 32
+- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 200
+- training_steps: 150
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 5.3.0
+- Pytorch 2.8.0+cu126
+- Datasets 4.5.0
+- Tokenizers 0.22.2

config.json

@@ -0,0 +1,69 @@
+{
+  "architectures": [
+    "Olmo3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "dtype": "bfloat16",
+  "eos_token_id": 100257,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "layer_types": [
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "sliding_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 65536,
+  "model_type": "olmo3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 100277,
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "attention_factor": 1.2079441541679836,
+    "beta_fast": 32,
+    "beta_slow": 1,
+    "factor": 8.0,
+    "original_max_position_embeddings": 8192,
+    "rope_theta": 500000,
+    "rope_type": "yarn"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.3.0",
+  "use_cache": false,
+  "vocab_size": 100278
+}

debug.log

@@ -0,0 +1,7 @@
+[2026-03-10 09:21:08,376] [INFO] [axolotl.utils.data.sft._load_raw_datasets:320] [PID:2542054] Loading raw datasets...
+[2026-03-10 09:21:08,520] [INFO] [axolotl.utils.data.wrappers.get_dataset_wrapper:87] [PID:2542054] Loading dataset: data/1b/all.jsonl with base_type: completion and prompt_style: None
+
+
+
+
+

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "do_sample": true,
+  "eos_token_id": [
+    100257
+  ],
+  "pad_token_id": 100277,
+  "transformers_version": "5.3.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb65ffc467e5480daf0bbac7b5647ab7fa22eb81aa16ef8b679db058682ca2d
+size 14596063960