Upload checkpoint after 524,288 tokens

README.md

@@ -0,0 +1,33 @@
+---
+license: cc-by-nc-4.0
+language:
+- en
+datasets:
+- nvidia/Nemotron-ClimbMix
+tags:
+- llama
+- causal-lm
+- pretraining
+- climbmix
+---
+
+# atrost/climbmix-llama-288m-2p8b-h100-save-test
+
+Small Llama-style causal language model pretrained from scratch on `nvidia/Nemotron-ClimbMix`.
+
+## Training details
+
+- Architecture: `LlamaForCausalLM`
+- Parameters: `288,554,240`
+- Context length: `2048`
+- Target tokens: `524,288`
+- Actual tokens: `524,288`
+- Tokens per optimizer step: `262,144`
+- Optimizer: AdamW
+- LR schedule: cosine decay with warmup
+- Precision: bfloat16
+- Intended hardware: 8x H100
+
+## Model config
+
+The model was initialized from the config embedded in `train_climbmix_llama_ddp.py`.

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 50256,
+  "dtype": "float32",
+  "eos_token_id": 50256,
+  "head_dim": 80,
+  "hidden_act": "silu",
+  "hidden_size": 1280,
+  "initializer_range": 0.02,
+  "intermediate_size": 3584,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "pad_token_id": 50256,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers_version": "5.7.0",
+  "use_cache": true,
+  "vocab_size": 50304
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 50256,
+  "eos_token_id": 50256,
+  "output_attentions": false,
+  "output_hidden_states": false,
+  "pad_token_id": 50256,
+  "transformers_version": "5.7.0",
+  "use_cache": false
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4dca06708b6c1cbfe6a3560fb06eca3ae4a7e6fd04b0f052b845e220b6d936e2
+size 1154229368

tokenizer_config.json

@@ -0,0 +1,13 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|endoftext|>",
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>"
+}