Upload folder using huggingface_hub

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+base_model: halcyon-llm/SmolLM2-360M-japanese_base_phase_1-11000
+tags:
+- generated_from_trainer
+datasets:
+- kajuma/training_01-09_token
+model-index:
+- name: scratch_adamw_phase_2
+  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. -->
+
+# scratch_adamw_phase_2
+
+This model is a fine-tuned version of [halcyon-llm/SmolLM2-360M-japanese_base_phase_1-11000](https://huggingface.co/halcyon-llm/SmolLM2-360M-japanese_base_phase_1-11000) on the kajuma/training_01-09_token dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.1349
+
+## 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: 0.003
+- train_batch_size: 4
+- eval_batch_size: 4
+- seed: 42
+- gradient_accumulation_steps: 64
+- total_train_batch_size: 256
+- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.95) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine_with_min_lr
+- lr_scheduler_warmup_steps: 1000
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch  | Step  | Validation Loss |
+|:-------------:|:------:|:-----:|:---------------:|
+| 1.1622        | 0.0438 | 500   | 1.1753          |
+| 1.2027        | 0.0877 | 1000  | 1.2353          |
+| 1.207         | 0.1315 | 1500  | 1.2419          |
+| 1.2536        | 0.1754 | 2000  | 1.2374          |
+| 1.2442        | 0.2192 | 2500  | 1.2315          |
+| 1.2163        | 0.2631 | 3000  | 1.2262          |
+| 1.1969        | 0.3069 | 3500  | 1.2185          |
+| 1.2102        | 0.3508 | 4000  | 1.2099          |
+| 1.1908        | 0.3946 | 4500  | 1.2016          |
+| 1.1611        | 0.4385 | 5000  | 1.1929          |
+| 1.2055        | 0.4823 | 5500  | 1.1835          |
+| 1.1743        | 0.5262 | 6000  | 1.1750          |
+| 1.1519        | 0.5700 | 6500  | 1.1674          |
+| 1.1397        | 0.6138 | 7000  | 1.1601          |
+| 1.1702        | 0.6577 | 7500  | 1.1538          |
+| 1.1633        | 0.7015 | 8000  | 1.1483          |
+| 1.1248        | 0.7454 | 8500  | 1.1439          |
+| 1.1306        | 0.7892 | 9000  | 1.1407          |
+| 1.0726        | 0.8331 | 9500  | 1.1385          |
+| 1.1104        | 0.8769 | 10000 | 1.1369          |
+| 1.0933        | 0.9208 | 10500 | 1.1359          |
+| 1.0918        | 0.9646 | 11000 | 1.1352          |
+
+
+### Framework versions
+
+- Transformers 4.48.0.dev0
+- Pytorch 2.5.1+cu124
+- Datasets 3.2.0
+- Tokenizers 0.21.0

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 49152
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.9999493031929397,
+    "eval_loss": 1.1348882913589478,
+    "eval_runtime": 428.9305,
+    "eval_samples": 14447,
+    "eval_samples_per_second": 33.681,
+    "eval_steps_per_second": 8.421,
+    "perplexity": 3.110826017347737,
+    "total_flos": 5.643098158163558e+18,
+    "train_loss": 1.1702608942389645,
+    "train_runtime": 336251.1326,
+    "train_samples": 2919315,
+    "train_samples_per_second": 8.682,
+    "train_steps_per_second": 0.034
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "halcyon-llm/SmolLM2-360M-japanese_base_phase_1-11000",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 960,
+  "initializer_range": 0.02,
+  "intermediate_size": 2560,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 15,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 5,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.0.dev0",
+  "use_cache": true,
+  "vocab_size": 49153
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999493031929397,
+    "eval_loss": 1.1348882913589478,
+    "eval_runtime": 428.9305,
+    "eval_samples": 14447,
+    "eval_samples_per_second": 33.681,
+    "eval_steps_per_second": 8.421,
+    "perplexity": 3.110826017347737
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "transformers_version": "4.48.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c534607112039ac012b53d47aaa4e7655fa637542a91e16c40d4ace1cb641993
+size 723676832

special_tokens_map.json

@@ -0,0 +1,49 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,177 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "49152": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|im_start|>",
+    "<|im_end|>",
+    "<repo_name>",
+    "<reponame>",
+    "<file_sep>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<jupyter_script>",
+    "<empty_output>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "[PAD]",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999493031929397,
+    "total_flos": 5.643098158163558e+18,
+    "train_loss": 1.1702608942389645,
+    "train_runtime": 336251.1326,
+    "train_samples": 2919315,
+    "train_samples_per_second": 8.682,
+    "train_steps_per_second": 0.034
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2dba5c8676131e3c9c6d804f82c77735b656862a860f9acf14660fdfa9a902df
+size 5368