add tinyllama_k=5_22

tinyllama_k=5_22/README.md

@@ -0,0 +1,58 @@
+---
+base_model: ./output_models/tinyllama_k=5_21
+tags:
+- generated_from_trainer
+datasets:
+- customized
+model-index:
+- name: tinyllama_k=5_22
+  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. -->
+
+# tinyllama_k=5_22
+
+This model is a fine-tuned version of [./output_models/tinyllama_k=5_21](https://huggingface.co/./output_models/tinyllama_k=5_21) on the customized 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: 50
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 400
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- lr_scheduler_warmup_ratio: 0.01
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.37.0.dev0
+- Pytorch 2.1.2+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.0

tinyllama_k=5_22/all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.2366977334022522,
+    "train_runtime": 22.8113,
+    "train_samples": 2149,
+    "train_samples_per_second": 94.208,
+    "train_steps_per_second": 0.263
+}

tinyllama_k=5_22/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "./output_models/tinyllama_k=5_21",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

tinyllama_k=5_22/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.37.0.dev0"
+}

tinyllama_k=5_22/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a6fecaacb499b63384642da193bb9b76d8279bfc017ac79f1de7786df291b5c
+size 2200119864

tinyllama_k=5_22/special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tinyllama_k=5_22/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tinyllama_k=5_22/tokenizer_config.json

@@ -0,0 +1,41 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

tinyllama_k=5_22/train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "train_loss": 1.2366977334022522,
+    "train_runtime": 22.8113,
+    "train_samples": 2149,
+    "train_samples_per_second": 94.208,
+    "train_steps_per_second": 0.263
+}

tinyllama_k=5_22/trainer_state.json

@@ -0,0 +1,66 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 50.0,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.17,
+      "learning_rate": 0.0,
+      "loss": 1.2334,
+      "step": 1
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 2.3285134909173112e-07,
+      "loss": 1.2441,
+      "step": 2
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 1.6177918337422216e-07,
+      "loss": 1.2407,
+      "step": 3
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.0357893671171792e-07,
+      "loss": 1.2422,
+      "step": 4
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.828077023652123e-08,
+      "loss": 1.2318,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 2.590815883181108e-08,
+      "loss": 1.228,
+      "step": 6
+    },
+    {
+      "epoch": 1.0,
+      "step": 6,
+      "total_flos": 7627253106081792.0,
+      "train_loss": 1.2366977334022522,
+      "train_runtime": 22.8113,
+      "train_samples_per_second": 94.208,
+      "train_steps_per_second": 0.263
+    }
+  ],
+  "logging_steps": 1.0,
+  "max_steps": 6,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 7627253106081792.0,
+  "train_batch_size": 50,
+  "trial_name": null,
+  "trial_params": null
+}

tinyllama_k=5_22/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4e8b4a219be8d5217922df59a252c3786e4a30067c90e795f8fdf7dfe970808
+size 6392