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 +1,77 @@
+---
+license: gemma
+library_name: peft
+tags:
+- trl
+- sft
+- generated_from_trainer
+base_model: google/gemma-2b
+datasets:
+- generator
+model-index:
+- name: gemma2b-summarize-gemini1_5flash-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-gemini1_5flash-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: 2.6449
+
+## 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: 4
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 2.9846        | 0.8571 | 3    | 3.1614          |
+| 2.8305        | 2.0    | 7    | 2.8875          |
+| 2.3403        | 2.8571 | 10   | 2.8343          |
+| 2.3403        | 4.0    | 14   | 2.7485          |
+| 2.0675        | 4.8571 | 17   | 2.6913          |
+| 1.8758        | 6.0    | 21   | 2.6605          |
+| 1.8758        | 6.8571 | 24   | 2.6488          |
+| 1.7659        | 8.0    | 28   | 2.6451          |
+| 1.7298        | 8.5714 | 30   | 2.6449          |
+
+
+### Framework versions
+
+- PEFT 0.11.1
+- Transformers 4.40.1
+- Pytorch 2.2.0+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",
+    "o_proj",
+    "v_proj",
+    "gate_proj",
+    "down_proj",
+    "up_proj",
+    "k_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 sha256:9728fc9166b051c55a30a3172cb24ccc80328091a91ac9cd72ed82bc87f85206
+size 19644912

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 8.571428571428571,
+    "total_flos": 2.34949340823552e+16,
+    "train_loss": 2.1067513783772784,
+    "train_runtime": 107.4922,
+    "train_samples": 1979,
+    "train_samples_per_second": 20.281,
+    "train_steps_per_second": 0.279
+}

runs/Jun05_04-32-49_7bdd13775218/events.out.tfevents.1717561990.7bdd13775218.55636.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0942bb6b7595805b0600c46967b885fb61eabdcdd179a134d8d78a6157d9f717
+size 9638

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": 8.571428571428571,
+    "total_flos": 2.34949340823552e+16,
+    "train_loss": 2.1067513783772784,
+    "train_runtime": 107.4922,
+    "train_samples": 1979,
+    "train_samples_per_second": 20.281,
+    "train_steps_per_second": 0.279
+}

trainer_state.json

@@ -0,0 +1,151 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.571428571428571,
+  "eval_steps": 500,
+  "global_step": 30,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 2.078125,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 2.9846,
+      "step": 1
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "eval_loss": 3.1614296436309814,
+      "eval_runtime": 0.5389,
+      "eval_samples_per_second": 18.556,
+      "eval_steps_per_second": 1.856,
+      "step": 3
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 1.6796875,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 2.8305,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 2.8875155448913574,
+      "eval_runtime": 0.51,
+      "eval_samples_per_second": 19.607,
+      "eval_steps_per_second": 1.961,
+      "step": 7
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 2.34375,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 2.3403,
+      "step": 10
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 2.834296703338623,
+      "eval_runtime": 0.626,
+      "eval_samples_per_second": 15.975,
+      "eval_steps_per_second": 1.597,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 2.7485246658325195,
+      "eval_runtime": 0.5273,
+      "eval_samples_per_second": 18.965,
+      "eval_steps_per_second": 1.896,
+      "step": 14
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 0.92578125,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.0675,
+      "step": 15
+    },
+    {
+      "epoch": 4.857142857142857,
+      "eval_loss": 2.6912894248962402,
+      "eval_runtime": 0.6579,
+      "eval_samples_per_second": 15.199,
+      "eval_steps_per_second": 1.52,
+      "step": 17
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 0.8671875,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 1.8758,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.6605114936828613,
+      "eval_runtime": 0.5348,
+      "eval_samples_per_second": 18.698,
+      "eval_steps_per_second": 1.87,
+      "step": 21
+    },
+    {
+      "epoch": 6.857142857142857,
+      "eval_loss": 2.648810625076294,
+      "eval_runtime": 0.6999,
+      "eval_samples_per_second": 14.288,
+      "eval_steps_per_second": 1.429,
+      "step": 24
+    },
+    {
+      "epoch": 7.142857142857143,
+      "grad_norm": 2.375,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 1.7659,
+      "step": 25
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.645064353942871,
+      "eval_runtime": 0.543,
+      "eval_samples_per_second": 18.416,
+      "eval_steps_per_second": 1.842,
+      "step": 28
+    },
+    {
+      "epoch": 8.571428571428571,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.0,
+      "loss": 1.7298,
+      "step": 30
+    },
+    {
+      "epoch": 8.571428571428571,
+      "eval_loss": 2.6449332237243652,
+      "eval_runtime": 0.5444,
+      "eval_samples_per_second": 18.369,
+      "eval_steps_per_second": 1.837,
+      "step": 30
+    },
+    {
+      "epoch": 8.571428571428571,
+      "step": 30,
+      "total_flos": 2.34949340823552e+16,
+      "train_loss": 2.1067513783772784,
+      "train_runtime": 107.4922,
+      "train_samples_per_second": 20.281,
+      "train_steps_per_second": 0.279
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 2.34949340823552e+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 sha256:70080554187bade80f1690416ce789a6830583639d3759bf3193c84c2f502103
+size 5176