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-2k
+  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-2k
+
+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: 2.5693
+
+## 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.9969        | 1.0   | 5    | 3.1171          |
+| 2.5079        | 2.0   | 10   | 2.8491          |
+| 2.1709        | 3.0   | 15   | 2.7251          |
+| 1.9297        | 4.0   | 20   | 2.6267          |
+| 1.7591        | 5.0   | 25   | 2.5900          |
+| 1.6527        | 6.0   | 30   | 2.5908          |
+| 1.5938        | 7.0   | 35   | 2.5817          |
+| 1.5589        | 8.0   | 40   | 2.5729          |
+| 1.5434        | 9.0   | 45   | 2.5688          |
+| 1.5362        | 10.0  | 50   | 2.5693          |
+
+
+### 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": [
+    "q_proj",
+    "k_proj",
+    "v_proj",
+    "o_proj",
+    "up_proj",
+    "gate_proj",
+    "down_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 sha256:384152cc55936a07cedb1682ede49183b4d90927bdb646907aa3aefeabc34e92
+size 19644912

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 2.9368666998964224e+16,
+    "train_loss": 1.9250271797180176,
+    "train_runtime": 273.2217,
+    "train_samples": 2019,
+    "train_samples_per_second": 8.052,
+    "train_steps_per_second": 0.183
+}

runs/Jun05_13-31-26_user-HP-Z8-Fury-G5-Workstation-Desktop-PC/events.out.tfevents.1717561900.user-HP-Z8-Fury-G5-Workstation-Desktop-PC.21635.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38da7a2363a18d68ff1146eb8b1af03cd0a6a0c8187db49af0e1f25fb3cb56f2
+size 10878

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": 10.0,
+    "total_flos": 2.9368666998964224e+16,
+    "train_loss": 1.9250271797180176,
+    "train_runtime": 273.2217,
+    "train_samples": 2019,
+    "train_samples_per_second": 8.052,
+    "train_steps_per_second": 0.183
+}

trainer_state.json

@@ -0,0 +1,199 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 50,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2,
+      "grad_norm": 2.234375,
+      "learning_rate": 4e-05,
+      "loss": 3.001,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.7265625,
+      "learning_rate": 0.0002,
+      "loss": 2.9969,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 3.1170578002929688,
+      "eval_runtime": 0.4884,
+      "eval_samples_per_second": 20.475,
+      "eval_steps_per_second": 2.047,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 2.5079,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.849125862121582,
+      "eval_runtime": 0.5022,
+      "eval_samples_per_second": 19.912,
+      "eval_steps_per_second": 1.991,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.2109375,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 2.1709,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 2.725147247314453,
+      "eval_runtime": 0.5172,
+      "eval_samples_per_second": 19.335,
+      "eval_steps_per_second": 1.934,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 0.8984375,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 1.9297,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.6266896724700928,
+      "eval_runtime": 0.5348,
+      "eval_samples_per_second": 18.699,
+      "eval_steps_per_second": 1.87,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.796875,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 1.7591,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 2.5900256633758545,
+      "eval_runtime": 0.5346,
+      "eval_samples_per_second": 18.707,
+      "eval_steps_per_second": 1.871,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 0.61328125,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 1.6527,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.590770721435547,
+      "eval_runtime": 0.5433,
+      "eval_samples_per_second": 18.406,
+      "eval_steps_per_second": 1.841,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 0.341796875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.5938,
+      "step": 35
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 2.5816967487335205,
+      "eval_runtime": 0.5475,
+      "eval_samples_per_second": 18.265,
+      "eval_steps_per_second": 1.826,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 0.322265625,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 1.5589,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.5729336738586426,
+      "eval_runtime": 0.5448,
+      "eval_samples_per_second": 18.356,
+      "eval_steps_per_second": 1.836,
+      "step": 40
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 0.287109375,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 1.5434,
+      "step": 45
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 2.5688018798828125,
+      "eval_runtime": 0.5464,
+      "eval_samples_per_second": 18.302,
+      "eval_steps_per_second": 1.83,
+      "step": 45
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 0.310546875,
+      "learning_rate": 0.0,
+      "loss": 1.5362,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 2.5693273544311523,
+      "eval_runtime": 0.5446,
+      "eval_samples_per_second": 18.363,
+      "eval_steps_per_second": 1.836,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "step": 50,
+      "total_flos": 2.9368666998964224e+16,
+      "train_loss": 1.9250271797180176,
+      "train_runtime": 273.2217,
+      "train_samples_per_second": 8.052,
+      "train_steps_per_second": 0.183
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "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": 2.9368666998964224e+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 sha256:538f26b6c9e5799ffada9b6a4eab53120a62cc6a5ea7b377dec56a152b4d1ee2
+size 5304