Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: apache-2.0
+base_model: PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T
+tags:
+- generated_from_trainer
+model-index:
+- name: tinyllama-1.1B-intermediate-step-715k-1.5T-sft-lora
+  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-1.1B-intermediate-step-715k-1.5T-sft-lora
+
+This model is a fine-tuned version of [PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T](https://huggingface.co/PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4638
+
+## 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: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 512
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.459         | 0.7   | 285  | 1.4638          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.0+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "PY007/TinyLlama-1.1B-intermediate-step-715k-1.5T",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "k_proj",
+    "q_proj",
+    "o_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:17160f1307641a921fec5b08ee5ee7f781f3e26e8d730a711c705b3cd3ab9f5a
+size 72113224

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.7,
+    "eval_loss": 1.4638023376464844,
+    "eval_runtime": 1870.3675,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 12.356,
+    "eval_steps_per_second": 1.545,
+    "train_loss": 1.5477959656924531,
+    "train_runtime": 59023.228,
+    "train_samples": 207865,
+    "train_samples_per_second": 3.522,
+    "train_steps_per_second": 0.007
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.7,
+    "eval_loss": 1.4638023376464844,
+    "eval_runtime": 1870.3675,
+    "eval_samples": 23110,
+    "eval_samples_per_second": 12.356,
+    "eval_steps_per_second": 1.545
+}

runs/Nov11_17-38-11_sebastian-dell/events.out.tfevents.1699720701.sebastian-dell.26073.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:000943eb90ece3e77efdd289d6647f1b448b60caa8781b0a1f10dbc68a803809
+size 14112

runs/Nov11_17-38-11_sebastian-dell/events.out.tfevents.1699781595.sebastian-dell.26073.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758b9b264cdf496c4e7055ab8977e5d6301a9667e77a0374a2004ccfe1c38f30
+size 359

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "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": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.7,
+    "train_loss": 1.5477959656924531,
+    "train_runtime": 59023.228,
+    "train_samples": 207865,
+    "train_samples_per_second": 3.522,
+    "train_steps_per_second": 0.007
+}

trainer_state.json

@@ -0,0 +1,384 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7019839513537437,
+  "eval_steps": 500,
+  "global_step": 285,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.999969914479768e-05,
+      "loss": 1.7204,
+      "step": 1
+    },
+    {
+      "epoch": 0.01,
+      "learning_rate": 1.9992479525042305e-05,
+      "loss": 1.7341,
+      "step": 5
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 1.996992941167792e-05,
+      "loss": 1.7235,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 1.722,
+      "step": 15
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 1.9879898494768093e-05,
+      "loss": 1.7349,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9812553106273848e-05,
+      "loss": 1.7135,
+      "step": 25
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 1.7066,
+      "step": 30
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 1.9633708786158803e-05,
+      "loss": 1.7042,
+      "step": 35
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9522478853384154e-05,
+      "loss": 1.6964,
+      "step": 40
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 1.6902,
+      "step": 45
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 1.9257239692688907e-05,
+      "loss": 1.6697,
+      "step": 50
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.9103629409661468e-05,
+      "loss": 1.6631,
+      "step": 55
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 1.6568,
+      "step": 60
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 1.8755582313020912e-05,
+      "loss": 1.64,
+      "step": 65
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.8561668995302668e-05,
+      "loss": 1.6209,
+      "step": 70
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 1.6084,
+      "step": 75
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.8135520702629677e-05,
+      "loss": 1.6027,
+      "step": 80
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.7903926695187595e-05,
+      "loss": 1.591,
+      "step": 85
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 1.5858,
+      "step": 90
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 1.740544013109005e-05,
+      "loss": 1.5647,
+      "step": 95
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 1.7139297345578992e-05,
+      "loss": 1.5433,
+      "step": 100
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 1.5512,
+      "step": 105
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.657521368569064e-05,
+      "loss": 1.5593,
+      "step": 110
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 1.627812124672099e-05,
+      "loss": 1.5325,
+      "step": 115
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 1.5176,
+      "step": 120
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 1.5656068754865388e-05,
+      "loss": 1.5185,
+      "step": 125
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5332044328016916e-05,
+      "loss": 1.5123,
+      "step": 130
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.515,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.4660435197025391e-05,
+      "loss": 1.52,
+      "step": 140
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 1.4313860656812537e-05,
+      "loss": 1.4933,
+      "step": 145
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 1.5013,
+      "step": 150
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 1.3601777248047105e-05,
+      "loss": 1.4936,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 1.3237339420583213e-05,
+      "loss": 1.4862,
+      "step": 160
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 1.4826,
+      "step": 165
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 1.2494411440579814e-05,
+      "loss": 1.4808,
+      "step": 170
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.211703872229411e-05,
+      "loss": 1.4862,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 1.4781,
+      "step": 180
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 1.1353312997501313e-05,
+      "loss": 1.4736,
+      "step": 185
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.0968108707031792e-05,
+      "loss": 1.4858,
+      "step": 190
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 1.4827,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 1.0193913317718245e-05,
+      "loss": 1.476,
+      "step": 200
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.806086682281759e-06,
+      "loss": 1.4711,
+      "step": 205
+    },
+    {
+      "epoch": 0.52,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 1.4689,
+      "step": 210
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.03189129296821e-06,
+      "loss": 1.4683,
+      "step": 215
+    },
+    {
+      "epoch": 0.54,
+      "learning_rate": 8.646687002498692e-06,
+      "loss": 1.4684,
+      "step": 220
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 1.481,
+      "step": 225
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 7.882961277705897e-06,
+      "loss": 1.4665,
+      "step": 230
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 7.505588559420188e-06,
+      "loss": 1.4719,
+      "step": 235
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 1.4664,
+      "step": 240
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 6.762660579416791e-06,
+      "loss": 1.4674,
+      "step": 245
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 6.3982227519528986e-06,
+      "loss": 1.4679,
+      "step": 250
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 1.4705,
+      "step": 255
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 5.686139343187468e-06,
+      "loss": 1.4682,
+      "step": 260
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 5.339564802974615e-06,
+      "loss": 1.4513,
+      "step": 265
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.4623,
+      "step": 270
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 4.66795567198309e-06,
+      "loss": 1.4577,
+      "step": 275
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 4.343931245134616e-06,
+      "loss": 1.4629,
+      "step": 280
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 1.459,
+      "step": 285
+    },
+    {
+      "epoch": 0.7,
+      "eval_loss": 1.4638023376464844,
+      "eval_runtime": 1870.4229,
+      "eval_samples_per_second": 12.355,
+      "eval_steps_per_second": 1.545,
+      "step": 285
+    },
+    {
+      "epoch": 0.7,
+      "step": 285,
+      "total_flos": 1.8890222028885852e+18,
+      "train_loss": 1.5477959656924531,
+      "train_runtime": 59023.228,
+      "train_samples_per_second": 3.522,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 405,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.8890222028885852e+18,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd56451fd87d03c823044d32177b456a21e31b31f3ac6bac7eb3d2aa6578fe08
+size 4728