Upload folder using huggingface_hub

README.md

@@ -0,0 +1,66 @@
+---
+library_name: transformers
+license: other
+base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: tinyllama_alpaca_sft_sample
+  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_alpaca_sft_sample
+
+This model is a fine-tuned version of [TinyLlama/TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) on the tatsu-lab/alpaca dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2133
+
+## 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: 2e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 16
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 512
+- total_eval_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 1.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.2457        | 1.0   | 23   | 1.2133          |
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.3.1+cu118
+- Datasets 3.0.2
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.213269829750061,
+    "eval_runtime": 0.4248,
+    "eval_samples_per_second": 1459.349,
+    "eval_steps_per_second": 11.769,
+    "total_flos": 3.742438758599885e+16,
+    "train_loss": 1.3028167019719663,
+    "train_runtime": 44.733,
+    "train_samples_per_second": 262.982,
+    "train_steps_per_second": 0.514
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/p/data1/mmlaion/marianna/models/TinyLlama/TinyLlama-1.1B-Chat-v1.0",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "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": "4.45.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.213269829750061,
+    "eval_runtime": 0.4248,
+    "eval_samples_per_second": 1459.349,
+    "eval_steps_per_second": 11.769
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.45.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:822d351ab9e5b178191168caac8ebca0483dc2e8147d7b14ddd1348808d5f2c9
+size 2200119864

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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>",
+  "chat_template": "{% set system_message = 'Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n' %}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ system_message }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + content + '\n\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ content + '</s>' + '\n\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "split_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 3.742438758599885e+16,
+    "train_loss": 1.3028167019719663,
+    "train_runtime": 44.733,
+    "train_samples_per_second": 262.982,
+    "train_steps_per_second": 0.514
+}

trainer_log.jsonl

@@ -0,0 +1,4 @@
+{"current_steps": 10, "total_steps": 23, "loss": 1.3741, "learning_rate": 1.4539904997395468e-05, "epoch": 0.43478260869565216, "percentage": 43.48, "elapsed_time": "0:00:15", "remaining_time": "0:00:20"}
+{"current_steps": 20, "total_steps": 23, "loss": 1.2457, "learning_rate": 1.0899347581163222e-06, "epoch": 0.8695652173913043, "percentage": 86.96, "elapsed_time": "0:00:28", "remaining_time": "0:00:04"}
+{"current_steps": 23, "total_steps": 23, "eval_loss": 1.213269829750061, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:38", "remaining_time": "0:00:00"}
+{"current_steps": 23, "total_steps": 23, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:00:42", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 23,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.43478260869565216,
+      "grad_norm": 0.8424785137176514,
+      "learning_rate": 1.4539904997395468e-05,
+      "loss": 1.3741,
+      "step": 10
+    },
+    {
+      "epoch": 0.8695652173913043,
+      "grad_norm": 0.5969947576522827,
+      "learning_rate": 1.0899347581163222e-06,
+      "loss": 1.2457,
+      "step": 20
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.213269829750061,
+      "eval_runtime": 0.5855,
+      "eval_samples_per_second": 1058.923,
+      "eval_steps_per_second": 8.54,
+      "step": 23
+    },
+    {
+      "epoch": 1.0,
+      "step": 23,
+      "total_flos": 3.742438758599885e+16,
+      "train_loss": 1.3028167019719663,
+      "train_runtime": 44.733,
+      "train_samples_per_second": 262.982,
+      "train_steps_per_second": 0.514
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 23,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.742438758599885e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c75513711763921d31ccd0a80a2df55625ceb63b637b01a07232c9b78fa841a3
+size 6712