Upload 18 files

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
-*.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz filter=lfs diff=lfs merge=lfs -text
-*.zip filter=lfs diff=lfs merge=lfs -text
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,3 +1,63 @@
 ---
 license: mit
+library_name: peft
+tags:
+- llama-factory
+- lora
+- generated_from_trainer
+base_model: microsoft/phi-1_5
+model-index:
+- name: train_2024-05-09-19-57-19
+  results: []
+datasets:
+- llamafactory/alpaca_en
+language:
+- en
 ---
+
+
+# Bahia 1.0 Based on Phi 1.5 trained using Alpaca_en
+
+This model is a fine-tuned version of [microsoft/phi-1_5](https://huggingface.co/microsoft/phi-1_5) on the alpaca_en dataset.
+
+## Model description
+
+This is the First LLM coming from the Mediterranean city of Oran (nicknamed El-Bahia), and possibly the first North African LLM trained model, More to come from us soon ;-)
+
+## Intended uses & limitations
+
+This comes under an MIT lisence, enjoy!
+
+## Training and evaluation data
+
+Trained using Alpaca_en from Llama Factory 
+
+## Training procedure
+
+Locally trained on baremetal hardware on an AMD GPU under Linux Mint 21
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.0002
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 3.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+Please check the files in the files and versions.
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.1
+- Pytorch 2.3.0+rocm5.7
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "microsoft/phi-1_5",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:565170c74ac08713fee3936749c983f89c74ad7d341572a703d900b01031f52c
+size 6304096

added_tokens.json

@@ -0,0 +1,40 @@
+{
+  "\t\t": 50294,
+  "\t\t\t": 50293,
+  "\t\t\t\t": 50292,
+  "\t\t\t\t\t": 50291,
+  "\t\t\t\t\t\t": 50290,
+  "\t\t\t\t\t\t\t": 50289,
+  "\t\t\t\t\t\t\t\t": 50288,
+  "\t\t\t\t\t\t\t\t\t": 50287,
+  "  ": 50286,
+  "   ": 50285,
+  "    ": 50284,
+  "     ": 50283,
+  "      ": 50282,
+  "       ": 50281,
+  "        ": 50280,
+  "         ": 50279,
+  "          ": 50278,
+  "           ": 50277,
+  "            ": 50276,
+  "             ": 50275,
+  "              ": 50274,
+  "               ": 50273,
+  "                ": 50272,
+  "                 ": 50271,
+  "                  ": 50270,
+  "                   ": 50269,
+  "                    ": 50268,
+  "                     ": 50267,
+  "                      ": 50266,
+  "                       ": 50265,
+  "                        ": 50264,
+  "                         ": 50263,
+  "                          ": 50262,
+  "                           ": 50261,
+  "                            ": 50260,
+  "                             ": 50259,
+  "                              ": 50258,
+  "                               ": 50257
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.976,
+    "total_flos": 1234235324694528.0,
+    "train_loss": 1.4291518221619308,
+    "train_runtime": 192.8949,
+    "train_samples_per_second": 7.776,
+    "train_steps_per_second": 0.482
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b4f562cc4b12f1154a0b658b9d74ab9d024a686420fdf154ebc00a2219976df7
+size 2836578696

running_log.txt

@@ -0,0 +1,179 @@
+05/09/2024 19:59:23 - INFO - transformers.tokenization_utils_base - loading file vocab.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/vocab.json
+
+05/09/2024 19:59:23 - INFO - transformers.tokenization_utils_base - loading file merges.txt from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/merges.txt
+
+05/09/2024 19:59:23 - INFO - transformers.tokenization_utils_base - loading file tokenizer.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/tokenizer.json
+
+05/09/2024 19:59:23 - INFO - transformers.tokenization_utils_base - loading file added_tokens.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/added_tokens.json
+
+05/09/2024 19:59:23 - INFO - transformers.tokenization_utils_base - loading file special_tokens_map.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/special_tokens_map.json
+
+05/09/2024 19:59:23 - INFO - transformers.tokenization_utils_base - loading file tokenizer_config.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/tokenizer_config.json
+
+05/09/2024 19:59:23 - INFO - llmtuner.data.template - Add pad token: <|endoftext|>
+
+05/09/2024 19:59:23 - INFO - llmtuner.data.loader - Loading dataset alpaca_data_en_52k.json...
+
+05/09/2024 19:59:24 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/config.json
+
+05/09/2024 19:59:24 - INFO - transformers.configuration_utils - Model config PhiConfig {
+  "_name_or_path": "microsoft/phi-1_5",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 51200
+}
+
+
+05/09/2024 20:08:34 - INFO - transformers.modeling_utils - loading weights file model.safetensors from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/model.safetensors
+
+05/09/2024 20:08:34 - INFO - transformers.modeling_utils - Instantiating PhiForCausalLM model under default dtype torch.float16.
+
+05/09/2024 20:08:34 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {}
+
+
+05/09/2024 20:08:35 - INFO - transformers.modeling_utils - All model checkpoint weights were used when initializing PhiForCausalLM.
+
+
+05/09/2024 20:08:35 - INFO - transformers.modeling_utils - All the weights of PhiForCausalLM were initialized from the model checkpoint at microsoft/phi-1_5.
+If your task is similar to the task the model of the checkpoint was trained on, you can already use PhiForCausalLM for predictions without further training.
+
+05/09/2024 20:08:36 - INFO - transformers.generation.configuration_utils - loading configuration file generation_config.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/generation_config.json
+
+05/09/2024 20:08:36 - INFO - transformers.generation.configuration_utils - Generate config GenerationConfig {}
+
+
+05/09/2024 20:08:36 - INFO - llmtuner.model.utils.checkpointing - Gradient checkpointing enabled.
+
+05/09/2024 20:08:36 - INFO - llmtuner.model.utils.attention - Using torch SDPA for faster training and inference.
+
+05/09/2024 20:08:36 - INFO - llmtuner.model.adapter - Fine-tuning method: LoRA
+
+05/09/2024 20:08:36 - INFO - llmtuner.model.loader - trainable params: 1572864 || all params: 1419843584 || trainable%: 0.1108
+
+05/09/2024 20:08:36 - INFO - transformers.trainer - Using auto half precision backend
+
+05/09/2024 20:08:36 - INFO - transformers.trainer - ***** Running training *****
+
+05/09/2024 20:08:36 - INFO - transformers.trainer -   Num examples = 500
+
+05/09/2024 20:08:36 - INFO - transformers.trainer -   Num Epochs = 3
+
+05/09/2024 20:08:36 - INFO - transformers.trainer -   Instantaneous batch size per device = 2
+
+05/09/2024 20:08:36 - INFO - transformers.trainer -   Total train batch size (w. parallel, distributed & accumulation) = 16
+
+05/09/2024 20:08:36 - INFO - transformers.trainer -   Gradient Accumulation steps = 8
+
+05/09/2024 20:08:36 - INFO - transformers.trainer -   Total optimization steps = 93
+
+05/09/2024 20:08:36 - INFO - transformers.trainer -   Number of trainable parameters = 1,572,864
+
+05/09/2024 20:08:47 - INFO - llmtuner.extras.callbacks - {'loss': 2.1283, 'learning_rate': 1.9858e-04, 'epoch': 0.16}
+
+05/09/2024 20:08:57 - INFO - llmtuner.extras.callbacks - {'loss': 1.8000, 'learning_rate': 1.9435e-04, 'epoch': 0.32}
+
+05/09/2024 20:09:07 - INFO - llmtuner.extras.callbacks - {'loss': 1.5595, 'learning_rate': 1.8743e-04, 'epoch': 0.48}
+
+05/09/2024 20:09:18 - INFO - llmtuner.extras.callbacks - {'loss': 1.6097, 'learning_rate': 1.7803e-04, 'epoch': 0.64}
+
+05/09/2024 20:09:29 - INFO - llmtuner.extras.callbacks - {'loss': 1.2942, 'learning_rate': 1.6641e-04, 'epoch': 0.80}
+
+05/09/2024 20:09:38 - INFO - llmtuner.extras.callbacks - {'loss': 1.4620, 'learning_rate': 1.5290e-04, 'epoch': 0.96}
+
+05/09/2024 20:09:48 - INFO - llmtuner.extras.callbacks - {'loss': 1.4432, 'learning_rate': 1.3788e-04, 'epoch': 1.12}
+
+05/09/2024 20:09:59 - INFO - llmtuner.extras.callbacks - {'loss': 1.3561, 'learning_rate': 1.2178e-04, 'epoch': 1.28}
+
+05/09/2024 20:10:09 - INFO - llmtuner.extras.callbacks - {'loss': 1.3299, 'learning_rate': 1.0506e-04, 'epoch': 1.44}
+
+05/09/2024 20:10:19 - INFO - llmtuner.extras.callbacks - {'loss': 1.2208, 'learning_rate': 8.8204e-05, 'epoch': 1.60}
+
+05/09/2024 20:10:30 - INFO - llmtuner.extras.callbacks - {'loss': 1.4574, 'learning_rate': 7.1679e-05, 'epoch': 1.76}
+
+05/09/2024 20:10:41 - INFO - llmtuner.extras.callbacks - {'loss': 1.1423, 'learning_rate': 5.5961e-05, 'epoch': 1.92}
+
+05/09/2024 20:10:50 - INFO - llmtuner.extras.callbacks - {'loss': 1.3134, 'learning_rate': 4.1495e-05, 'epoch': 2.08}
+
+05/09/2024 20:11:01 - INFO - llmtuner.extras.callbacks - {'loss': 1.3384, 'learning_rate': 2.8695e-05, 'epoch': 2.24}
+
+05/09/2024 20:11:12 - INFO - llmtuner.extras.callbacks - {'loss': 1.3873, 'learning_rate': 1.7924e-05, 'epoch': 2.40}
+
+05/09/2024 20:11:22 - INFO - llmtuner.extras.callbacks - {'loss': 1.2214, 'learning_rate': 9.4885e-06, 'epoch': 2.56}
+
+05/09/2024 20:11:32 - INFO - llmtuner.extras.callbacks - {'loss': 1.3198, 'learning_rate': 3.6294e-06, 'epoch': 2.72}
+
+05/09/2024 20:11:42 - INFO - llmtuner.extras.callbacks - {'loss': 1.3832, 'learning_rate': 5.1307e-07, 'epoch': 2.88}
+
+05/09/2024 20:11:49 - INFO - transformers.trainer - 
+
+Training completed. Do not forget to share your model on huggingface.co/models =)
+
+
+
+05/09/2024 20:11:49 - INFO - transformers.trainer - Saving model checkpoint to saves/Phi-1.5-1.3B/lora/train_2024-05-09-19-57-19
+
+05/09/2024 20:11:49 - INFO - transformers.configuration_utils - loading configuration file config.json from cache at /home/.cache/huggingface/hub/models--microsoft--phi-1_5/snapshots/675aa382d814580b22651a30acb1a585d7c25963/config.json
+
+05/09/2024 20:11:49 - INFO - transformers.configuration_utils - Model config PhiConfig {
+  "_name_or_path": "microsoft/phi-1_5",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": null,
+  "embd_pdrop": 0.0,
+  "eos_token_id": null,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.5,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.0,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "vocab_size": 51200
+}
+
+
+05/09/2024 20:11:49 - INFO - transformers.tokenization_utils_base - tokenizer config file saved in saves/Phi-1.5-1.3B/lora/train_2024-05-09-19-57-19/tokenizer_config.json
+
+05/09/2024 20:11:49 - INFO - transformers.tokenization_utils_base - Special tokens file saved in saves/Phi-1.5-1.3B/lora/train_2024-05-09-19-57-19/special_tokens_map.json
+
+05/09/2024 20:11:49 - INFO - transformers.modelcard - Dropping the following result as it does not have all the necessary fields:
+{'task': {'name': 'Causal Language Modeling', 'type': 'text-generation'}}
+

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,328 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "50256": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50257": {
+      "content": "                               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "                         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50277": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50278": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50279": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50280": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50281": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50282": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50283": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50284": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50285": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50286": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50287": {
+      "content": "\t\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50288": {
+      "content": "\t\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50289": {
+      "content": "\t\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50290": {
+      "content": "\t\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50291": {
+      "content": "\t\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50292": {
+      "content": "\t\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50293": {
+      "content": "\t\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50294": {
+      "content": "\t\t",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "return_token_type_ids": false,
+  "split_special_tokens": false,
+  "tokenizer_class": "CodeGenTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.976,
+    "total_flos": 1234235324694528.0,
+    "train_loss": 1.4291518221619308,
+    "train_runtime": 192.8949,
+    "train_samples_per_second": 7.776,
+    "train_steps_per_second": 0.482
+}

trainer_config.yaml

@@ -0,0 +1,28 @@
+cutoff_len: 1024
+dataset: alpaca_en
+dataset_dir: data
+do_train: true
+finetuning_type: lora
+flash_attn: auto
+fp16: true
+gradient_accumulation_steps: 8
+learning_rate: 0.0002
+logging_steps: 5
+lora_alpha: 16
+lora_dropout: 0
+lora_rank: 8
+lora_target: q_proj,v_proj
+lr_scheduler_type: cosine
+max_grad_norm: 1.0
+max_samples: 500
+model_name_or_path: microsoft/phi-1_5
+num_train_epochs: 3.0
+optim: adamw_torch
+output_dir: saves/Phi-1.5-1.3B/lora/train_2024-05-09-19-57-19
+packing: false
+per_device_train_batch_size: 2
+report_to: none
+save_steps: 100
+stage: sft
+template: default
+warmup_steps: 0

trainer_log.jsonl

@@ -0,0 +1,19 @@
+{"current_steps": 5, "total_steps": 93, "loss": 2.1283, "learning_rate": 0.00019857697953148037, "epoch": 0.16, "percentage": 5.38, "elapsed_time": "0:00:10", "remaining_time": "0:03:10"}
+{"current_steps": 10, "total_steps": 93, "loss": 1.8, "learning_rate": 0.00019434841787099803, "epoch": 0.32, "percentage": 10.75, "elapsed_time": "0:00:20", "remaining_time": "0:02:51"}
+{"current_steps": 15, "total_steps": 93, "loss": 1.5595, "learning_rate": 0.00018743466161445823, "epoch": 0.48, "percentage": 16.13, "elapsed_time": "0:00:30", "remaining_time": "0:02:39"}
+{"current_steps": 20, "total_steps": 93, "loss": 1.6097, "learning_rate": 0.0001780324790952092, "epoch": 0.64, "percentage": 21.51, "elapsed_time": "0:00:41", "remaining_time": "0:02:31"}
+{"current_steps": 25, "total_steps": 93, "loss": 1.2942, "learning_rate": 0.00016640946027672392, "epoch": 0.8, "percentage": 26.88, "elapsed_time": "0:00:52", "remaining_time": "0:02:23"}
+{"current_steps": 30, "total_steps": 93, "loss": 1.462, "learning_rate": 0.00015289640103269625, "epoch": 0.96, "percentage": 32.26, "elapsed_time": "0:01:02", "remaining_time": "0:02:10"}
+{"current_steps": 35, "total_steps": 93, "loss": 1.4432, "learning_rate": 0.0001378778885610576, "epoch": 1.12, "percentage": 37.63, "elapsed_time": "0:01:12", "remaining_time": "0:02:00"}
+{"current_steps": 40, "total_steps": 93, "loss": 1.3561, "learning_rate": 0.00012178135587488515, "epoch": 1.28, "percentage": 43.01, "elapsed_time": "0:01:23", "remaining_time": "0:01:50"}
+{"current_steps": 45, "total_steps": 93, "loss": 1.3299, "learning_rate": 0.00010506491688387127, "epoch": 1.44, "percentage": 48.39, "elapsed_time": "0:01:33", "remaining_time": "0:01:39"}
+{"current_steps": 50, "total_steps": 93, "loss": 1.2208, "learning_rate": 8.820432828491542e-05, "epoch": 1.6, "percentage": 53.76, "elapsed_time": "0:01:43", "remaining_time": "0:01:29"}
+{"current_steps": 55, "total_steps": 93, "loss": 1.4574, "learning_rate": 7.16794493317696e-05, "epoch": 1.76, "percentage": 59.14, "elapsed_time": "0:01:54", "remaining_time": "0:01:18"}
+{"current_steps": 60, "total_steps": 93, "loss": 1.1423, "learning_rate": 5.596058484423656e-05, "epoch": 1.92, "percentage": 64.52, "elapsed_time": "0:02:04", "remaining_time": "0:01:08"}
+{"current_steps": 65, "total_steps": 93, "loss": 1.3134, "learning_rate": 4.149510014046922e-05, "epoch": 2.08, "percentage": 69.89, "elapsed_time": "0:02:14", "remaining_time": "0:00:57"}
+{"current_steps": 70, "total_steps": 93, "loss": 1.3384, "learning_rate": 2.869468883687798e-05, "epoch": 2.24, "percentage": 75.27, "elapsed_time": "0:02:24", "remaining_time": "0:00:47"}
+{"current_steps": 75, "total_steps": 93, "loss": 1.3873, "learning_rate": 1.7923655879272393e-05, "epoch": 2.4, "percentage": 80.65, "elapsed_time": "0:02:35", "remaining_time": "0:00:37"}
+{"current_steps": 80, "total_steps": 93, "loss": 1.2214, "learning_rate": 9.488549274967872e-06, "epoch": 2.56, "percentage": 86.02, "elapsed_time": "0:02:45", "remaining_time": "0:00:26"}
+{"current_steps": 85, "total_steps": 93, "loss": 1.3198, "learning_rate": 3.6294356110059157e-06, "epoch": 2.7199999999999998, "percentage": 91.4, "elapsed_time": "0:02:56", "remaining_time": "0:00:16"}
+{"current_steps": 90, "total_steps": 93, "loss": 1.3832, "learning_rate": 5.130676608104845e-07, "epoch": 2.88, "percentage": 96.77, "elapsed_time": "0:03:06", "remaining_time": "0:00:06"}
+{"current_steps": 93, "total_steps": 93, "epoch": 2.976, "percentage": 100.0, "elapsed_time": "0:03:12", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,156 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.976,
+  "eval_steps": 500,
+  "global_step": 93,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.7531044483184814,
+      "learning_rate": 0.00019857697953148037,
+      "loss": 2.1283,
+      "step": 5
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 2.2025675773620605,
+      "learning_rate": 0.00019434841787099803,
+      "loss": 1.8,
+      "step": 10
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.9267807602882385,
+      "learning_rate": 0.00018743466161445823,
+      "loss": 1.5595,
+      "step": 15
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 0.6875874996185303,
+      "learning_rate": 0.0001780324790952092,
+      "loss": 1.6097,
+      "step": 20
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.7420657873153687,
+      "learning_rate": 0.00016640946027672392,
+      "loss": 1.2942,
+      "step": 25
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 0.6181728839874268,
+      "learning_rate": 0.00015289640103269625,
+      "loss": 1.462,
+      "step": 30
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 0.8008699417114258,
+      "learning_rate": 0.0001378778885610576,
+      "loss": 1.4432,
+      "step": 35
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 1.0314457416534424,
+      "learning_rate": 0.00012178135587488515,
+      "loss": 1.3561,
+      "step": 40
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.47113487124443054,
+      "learning_rate": 0.00010506491688387127,
+      "loss": 1.3299,
+      "step": 45
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.41678062081336975,
+      "learning_rate": 8.820432828491542e-05,
+      "loss": 1.2208,
+      "step": 50
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.4888109862804413,
+      "learning_rate": 7.16794493317696e-05,
+      "loss": 1.4574,
+      "step": 55
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.3696904480457306,
+      "learning_rate": 5.596058484423656e-05,
+      "loss": 1.1423,
+      "step": 60
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.6482197046279907,
+      "learning_rate": 4.149510014046922e-05,
+      "loss": 1.3134,
+      "step": 65
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 0.7164911031723022,
+      "learning_rate": 2.869468883687798e-05,
+      "loss": 1.3384,
+      "step": 70
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.3950205147266388,
+      "learning_rate": 1.7923655879272393e-05,
+      "loss": 1.3873,
+      "step": 75
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 0.387712687253952,
+      "learning_rate": 9.488549274967872e-06,
+      "loss": 1.2214,
+      "step": 80
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.2879863679409027,
+      "learning_rate": 3.6294356110059157e-06,
+      "loss": 1.3198,
+      "step": 85
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.9349786043167114,
+      "learning_rate": 5.130676608104845e-07,
+      "loss": 1.3832,
+      "step": 90
+    },
+    {
+      "epoch": 2.976,
+      "step": 93,
+      "total_flos": 1234235324694528.0,
+      "train_loss": 1.4291518221619308,
+      "train_runtime": 192.8949,
+      "train_samples_per_second": 7.776,
+      "train_steps_per_second": 0.482
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 93,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 100,
+  "total_flos": 1234235324694528.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ad0a98a9af90598fc9c299fcf9af47b320c84b8e983e6ad2d29c806f6b85e99
+size 5176