Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,78 @@
+---
+license: gemma
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: google/gemma-2b
+datasets:
+- generator
+model-index:
+- name: gemma2b-summarize-gpt4o-4k
+  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. -->
+
+# gemma2b-summarize-gpt4o-4k
+
+This model is a fine-tuned version of [google/gemma-2b](https://huggingface.co/google/gemma-2b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.5678
+
+## 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: 0.0002
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 3
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 48
+- total_eval_batch_size: 24
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 3.0546        | 0.9474 | 9    | 2.9560          |
+| 2.2821        | 2.0    | 19   | 2.6966          |
+| 1.8527        | 2.9474 | 28   | 2.6031          |
+| 1.5789        | 4.0    | 38   | 2.5802          |
+| 1.4487        | 4.9474 | 47   | 2.5688          |
+| 1.3708        | 6.0    | 57   | 2.5638          |
+| 1.3286        | 6.9474 | 66   | 2.5667          |
+| 1.3104        | 8.0    | 76   | 2.5672          |
+| 1.3046        | 8.9474 | 85   | 2.5674          |
+| 1.3032        | 9.4737 | 90   | 2.5678          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.2
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-2b",
+  "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": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 8,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "up_proj",
+    "k_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_proj",
+    "o_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 sha256:69abfe6a90b925dfb45f5ca591fe0a95d2331bc71651363ad88087326500e2fe
+size 19644912

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.473684210526315,
+    "total_flos": 5.286360054444851e+16,
+    "train_loss": 1.6763220760557387,
+    "train_runtime": 490.2927,
+    "train_samples": 4038,
+    "train_samples_per_second": 8.933,
+    "train_steps_per_second": 0.184
+}

runs/Jun05_13-46-03_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717562777.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.25140.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:00b2057ac5a6380df9873efa517e142b5b98dfcfd36fc50d3fa29793dbdac71e
+size 12534

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<eos>",
+    "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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:322a5f52ab5cab196761ab397a022d6fa3a2e1418585e532bb6efb2fedd2ae94
+size 17477501

tokenizer_config.json

@@ -0,0 +1,70 @@
+{
+  "add_bos_token": false,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<eos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<bos>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "106": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "107": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<bos>",
+  "chat_template": "{% if messages[0]['role'] == 'user' or messages[0]['role'] == 'system' %}{{ bos_token }}{% endif %}{% for message in messages %}{{ '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% elif messages[-1]['role'] == 'assistant' %}{{ eos_token }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<eos>",
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "GemmaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.473684210526315,
+    "total_flos": 5.286360054444851e+16,
+    "train_loss": 1.6763220760557387,
+    "train_runtime": 490.2927,
+    "train_samples": 4038,
+    "train_samples_per_second": 8.933,
+    "train_steps_per_second": 0.184
+}

trainer_state.json

@@ -0,0 +1,255 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.473684210526315,
+  "eval_steps": 500,
+  "global_step": 90,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.10526315789473684,
+      "grad_norm": 2.171875,
+      "learning_rate": 2.2222222222222223e-05,
+      "loss": 3.0858,
+      "step": 1
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00011111111111111112,
+      "loss": 3.0546,
+      "step": 5
+    },
+    {
+      "epoch": 0.9473684210526315,
+      "eval_loss": 2.956000804901123,
+      "eval_runtime": 0.5468,
+      "eval_samples_per_second": 18.288,
+      "eval_steps_per_second": 1.829,
+      "step": 9
+    },
+    {
+      "epoch": 1.0526315789473684,
+      "grad_norm": 1.8359375,
+      "learning_rate": 0.00019992479525042303,
+      "loss": 2.6964,
+      "step": 10
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 1.3828125,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 2.2821,
+      "step": 15
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.696643829345703,
+      "eval_runtime": 0.5537,
+      "eval_samples_per_second": 18.061,
+      "eval_steps_per_second": 1.806,
+      "step": 19
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.87890625,
+      "learning_rate": 0.0001910362940966147,
+      "loss": 2.0545,
+      "step": 20
+    },
+    {
+      "epoch": 2.6315789473684212,
+      "grad_norm": 0.9921875,
+      "learning_rate": 0.00018135520702629675,
+      "loss": 1.8527,
+      "step": 25
+    },
+    {
+      "epoch": 2.9473684210526314,
+      "eval_loss": 2.6030924320220947,
+      "eval_runtime": 0.5536,
+      "eval_samples_per_second": 18.063,
+      "eval_steps_per_second": 1.806,
+      "step": 28
+    },
+    {
+      "epoch": 3.1578947368421053,
+      "grad_norm": 0.431640625,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 1.6976,
+      "step": 30
+    },
+    {
+      "epoch": 3.6842105263157894,
+      "grad_norm": 0.5,
+      "learning_rate": 0.00015332044328016914,
+      "loss": 1.5789,
+      "step": 35
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.58021879196167,
+      "eval_runtime": 0.5505,
+      "eval_samples_per_second": 18.165,
+      "eval_steps_per_second": 1.817,
+      "step": 38
+    },
+    {
+      "epoch": 4.2105263157894735,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00013601777248047105,
+      "loss": 1.5127,
+      "step": 40
+    },
+    {
+      "epoch": 4.7368421052631575,
+      "grad_norm": 0.3984375,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 1.4487,
+      "step": 45
+    },
+    {
+      "epoch": 4.947368421052632,
+      "eval_loss": 2.5688371658325195,
+      "eval_runtime": 0.555,
+      "eval_samples_per_second": 18.017,
+      "eval_steps_per_second": 1.802,
+      "step": 47
+    },
+    {
+      "epoch": 5.2631578947368425,
+      "grad_norm": 0.271484375,
+      "learning_rate": 9.806086682281758e-05,
+      "loss": 1.4087,
+      "step": 50
+    },
+    {
+      "epoch": 5.7894736842105265,
+      "grad_norm": 0.265625,
+      "learning_rate": 7.882961277705895e-05,
+      "loss": 1.3708,
+      "step": 55
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.5638375282287598,
+      "eval_runtime": 0.5463,
+      "eval_samples_per_second": 18.305,
+      "eval_steps_per_second": 1.831,
+      "step": 57
+    },
+    {
+      "epoch": 6.315789473684211,
+      "grad_norm": 0.310546875,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 1.3437,
+      "step": 60
+    },
+    {
+      "epoch": 6.842105263157895,
+      "grad_norm": 0.25390625,
+      "learning_rate": 4.343931245134616e-05,
+      "loss": 1.3286,
+      "step": 65
+    },
+    {
+      "epoch": 6.947368421052632,
+      "eval_loss": 2.5667476654052734,
+      "eval_runtime": 0.5585,
+      "eval_samples_per_second": 17.905,
+      "eval_steps_per_second": 1.79,
+      "step": 66
+    },
+    {
+      "epoch": 7.368421052631579,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 2.8607026544210114e-05,
+      "loss": 1.3139,
+      "step": 70
+    },
+    {
+      "epoch": 7.894736842105263,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 1.3104,
+      "step": 75
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.5672240257263184,
+      "eval_runtime": 0.5487,
+      "eval_samples_per_second": 18.224,
+      "eval_steps_per_second": 1.822,
+      "step": 76
+    },
+    {
+      "epoch": 8.421052631578947,
+      "grad_norm": 0.208984375,
+      "learning_rate": 7.427603073110967e-06,
+      "loss": 1.3054,
+      "step": 80
+    },
+    {
+      "epoch": 8.947368421052632,
+      "grad_norm": 0.2138671875,
+      "learning_rate": 1.874468937261531e-06,
+      "loss": 1.3046,
+      "step": 85
+    },
+    {
+      "epoch": 8.947368421052632,
+      "eval_loss": 2.567439556121826,
+      "eval_runtime": 0.561,
+      "eval_samples_per_second": 17.827,
+      "eval_steps_per_second": 1.783,
+      "step": 85
+    },
+    {
+      "epoch": 9.473684210526315,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.0,
+      "loss": 1.3032,
+      "step": 90
+    },
+    {
+      "epoch": 9.473684210526315,
+      "eval_loss": 2.5678367614746094,
+      "eval_runtime": 0.5511,
+      "eval_samples_per_second": 18.145,
+      "eval_steps_per_second": 1.814,
+      "step": 90
+    },
+    {
+      "epoch": 9.473684210526315,
+      "step": 90,
+      "total_flos": 5.286360054444851e+16,
+      "train_loss": 1.6763220760557387,
+      "train_runtime": 490.2927,
+      "train_samples_per_second": 8.933,
+      "train_steps_per_second": 0.184
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 90,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.286360054444851e+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:f16542867eb734726203d3dec0176dbd7f94c244e5f06ebef20ea52242d691c4
+size 5304