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-7b
+datasets:
+- generator
+model-index:
+- name: gemma7b-summarize-gpt4o-1k
+  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. -->
+
+# gemma7b-summarize-gpt4o-1k
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the generator dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.8104
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 8
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 37.3003       | 0.9231 | 6    | 12.3240         |
+| 21.0453       | 2.0    | 13   | 7.5884          |
+| 17.809        | 2.9231 | 19   | 5.6549          |
+| 3.5386        | 4.0    | 26   | 3.1607          |
+| 2.02          | 4.9231 | 32   | 2.8709          |
+| 1.732         | 6.0    | 39   | 2.7893          |
+| 1.4072        | 6.9231 | 45   | 2.7970          |
+| 1.3061        | 8.0    | 52   | 2.8125          |
+| 1.2613        | 8.9231 | 58   | 2.8098          |
+| 1.2304        | 9.2308 | 60   | 2.8104          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,34 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "google/gemma-7b",
+  "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": [
+    "k_proj",
+    "up_proj",
+    "o_proj",
+    "down_proj",
+    "q_proj",
+    "gate_proj",
+    "v_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 sha256:2b104e6f5540b08ace63471b211aa65fe88708966056627cf08b1936b4b1d53a
+size 50056096

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 9.23076923076923,
+    "total_flos": 4.58661949299753e+16,
+    "train_loss": 8.682566889127095,
+    "train_runtime": 414.6045,
+    "train_samples": 923,
+    "train_samples_per_second": 2.484,
+    "train_steps_per_second": 0.145
+}

runs/Jun08_12-53-57_user-WS-C621E-SAGE-Series/events.out.tfevents.1717818883.user-WS-C621E-SAGE-Series.6379.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7ea22d1751a3c12f9967162c5699cf1b93837bd632d60ec5287dc5955bbe42
+size 6315

runs/Jun08_12-58-34_user-WS-C621E-SAGE-Series/events.out.tfevents.1717819145.user-WS-C621E-SAGE-Series.7781.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758fade14ddff9010fd83de906e496224ae4960eb48c3098550fb7755bbb7af5
+size 11127

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": 9.23076923076923,
+    "total_flos": 4.58661949299753e+16,
+    "train_loss": 8.682566889127095,
+    "train_runtime": 414.6045,
+    "train_samples": 923,
+    "train_samples_per_second": 2.484,
+    "train_steps_per_second": 0.145
+}

trainer_state.json

@@ -0,0 +1,201 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.23076923076923,
+  "eval_steps": 500,
+  "global_step": 60,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 390.0,
+      "learning_rate": 3.3333333333333335e-05,
+      "loss": 40.7928,
+      "step": 1
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 69.0,
+      "learning_rate": 0.0001666666666666667,
+      "loss": 37.3003,
+      "step": 5
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "eval_loss": 12.323984146118164,
+      "eval_runtime": 2.0206,
+      "eval_samples_per_second": 4.949,
+      "eval_steps_per_second": 0.99,
+      "step": 6
+    },
+    {
+      "epoch": 1.5384615384615383,
+      "grad_norm": 26.0,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 21.0453,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 7.588448524475098,
+      "eval_runtime": 2.0384,
+      "eval_samples_per_second": 4.906,
+      "eval_steps_per_second": 0.981,
+      "step": 13
+    },
+    {
+      "epoch": 2.3076923076923075,
+      "grad_norm": 16.75,
+      "learning_rate": 0.00018660254037844388,
+      "loss": 17.809,
+      "step": 15
+    },
+    {
+      "epoch": 2.9230769230769234,
+      "eval_loss": 5.654947757720947,
+      "eval_runtime": 2.0499,
+      "eval_samples_per_second": 4.878,
+      "eval_steps_per_second": 0.976,
+      "step": 19
+    },
+    {
+      "epoch": 3.076923076923077,
+      "grad_norm": 58.0,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 13.3008,
+      "step": 20
+    },
+    {
+      "epoch": 3.8461538461538463,
+      "grad_norm": 8.0,
+      "learning_rate": 0.00014487991802004623,
+      "loss": 3.5386,
+      "step": 25
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 3.160724401473999,
+      "eval_runtime": 2.0507,
+      "eval_samples_per_second": 4.876,
+      "eval_steps_per_second": 0.975,
+      "step": 26
+    },
+    {
+      "epoch": 4.615384615384615,
+      "grad_norm": 3.21875,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 2.02,
+      "step": 30
+    },
+    {
+      "epoch": 4.923076923076923,
+      "eval_loss": 2.8709278106689453,
+      "eval_runtime": 2.0507,
+      "eval_samples_per_second": 4.876,
+      "eval_steps_per_second": 0.975,
+      "step": 32
+    },
+    {
+      "epoch": 5.384615384615385,
+      "grad_norm": 3.375,
+      "learning_rate": 8.839070858747697e-05,
+      "loss": 1.732,
+      "step": 35
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 2.789313793182373,
+      "eval_runtime": 2.0444,
+      "eval_samples_per_second": 4.891,
+      "eval_steps_per_second": 0.978,
+      "step": 39
+    },
+    {
+      "epoch": 6.153846153846154,
+      "grad_norm": 4.0,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 1.5413,
+      "step": 40
+    },
+    {
+      "epoch": 6.923076923076923,
+      "grad_norm": 2.015625,
+      "learning_rate": 3.5721239031346066e-05,
+      "loss": 1.4072,
+      "step": 45
+    },
+    {
+      "epoch": 6.923076923076923,
+      "eval_loss": 2.797020435333252,
+      "eval_runtime": 2.049,
+      "eval_samples_per_second": 4.88,
+      "eval_steps_per_second": 0.976,
+      "step": 45
+    },
+    {
+      "epoch": 7.6923076923076925,
+      "grad_norm": 1.53125,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 1.3061,
+      "step": 50
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 2.8124804496765137,
+      "eval_runtime": 2.0441,
+      "eval_samples_per_second": 4.892,
+      "eval_steps_per_second": 0.978,
+      "step": 52
+    },
+    {
+      "epoch": 8.461538461538462,
+      "grad_norm": 1.453125,
+      "learning_rate": 4.20104876845111e-06,
+      "loss": 1.2613,
+      "step": 55
+    },
+    {
+      "epoch": 8.923076923076923,
+      "eval_loss": 2.8097996711730957,
+      "eval_runtime": 2.0484,
+      "eval_samples_per_second": 4.882,
+      "eval_steps_per_second": 0.976,
+      "step": 58
+    },
+    {
+      "epoch": 9.23076923076923,
+      "grad_norm": 1.296875,
+      "learning_rate": 0.0,
+      "loss": 1.2304,
+      "step": 60
+    },
+    {
+      "epoch": 9.23076923076923,
+      "eval_loss": 2.8104407787323,
+      "eval_runtime": 2.0425,
+      "eval_samples_per_second": 4.896,
+      "eval_steps_per_second": 0.979,
+      "step": 60
+    },
+    {
+      "epoch": 9.23076923076923,
+      "step": 60,
+      "total_flos": 4.58661949299753e+16,
+      "train_loss": 8.682566889127095,
+      "train_runtime": 414.6045,
+      "train_samples_per_second": 2.484,
+      "train_steps_per_second": 0.145
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 60,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 4.58661949299753e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d621e364c8574aed19ac641cf9318bb861f0211c8e6432fdb14829c73625eadd
+size 5176