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
+  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
+
+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: 3.3615
+
+## 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: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 4
+- 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 |
+|:-------------:|:-----:|:----:|:---------------:|
+| 17.2572       | 1.0   | 5    | 11.2704         |
+| 10.1138       | 2.0   | 10   | 7.8912          |
+| 7.7504        | 3.0   | 15   | 7.1928          |
+| 7.0505        | 4.0   | 20   | 6.8083          |
+| 6.6144        | 5.0   | 25   | 6.4041          |
+| 6.066         | 6.0   | 30   | 5.7488          |
+| 5.1349        | 7.0   | 35   | 4.6655          |
+| 3.9891        | 8.0   | 40   | 3.7537          |
+| 3.293         | 9.0   | 45   | 3.3924          |
+| 3.098         | 10.0  | 50   | 3.3615          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- 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": 8,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 4,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj",
+    "gate_proj",
+    "up_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 sha256:247cfe791cb188c5c31a105e27f5b2f79f90667ea2f9fa10fbbad748cf7f3dd3
+size 25053936

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 10.0,
+    "total_flos": 7.63207683753902e+16,
+    "train_loss": 7.077469825744629,
+    "train_runtime": 322.4528,
+    "train_samples": 395,
+    "train_samples_per_second": 2.419,
+    "train_steps_per_second": 0.155
+}

runs/May13_00-39-11_deep-diver-main-bitter-catfish-1-0-0/events.out.tfevents.1715575225.deep-diver-main-bitter-catfish-1-0-0.384.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b521656bd45168e227d467576d10f6b13670ff20a033ba614d0f891b0d8bf713
+size 10728

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": 7.63207683753902e+16,
+    "train_loss": 7.077469825744629,
+    "train_runtime": 322.4528,
+    "train_samples": 395,
+    "train_samples_per_second": 2.419,
+    "train_steps_per_second": 0.155
+}

trainer_state.json

@@ -0,0 +1,187 @@
+{
+  "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": 161.0,
+      "learning_rate": 4e-05,
+      "loss": 19.2941,
+      "step": 1
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 42.0,
+      "learning_rate": 0.0002,
+      "loss": 17.2572,
+      "step": 5
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 11.270448684692383,
+      "eval_runtime": 1.0123,
+      "eval_samples_per_second": 4.939,
+      "eval_steps_per_second": 1.976,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 12.0,
+      "learning_rate": 0.00019396926207859084,
+      "loss": 10.1138,
+      "step": 10
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 7.8912482261657715,
+      "eval_runtime": 1.0162,
+      "eval_samples_per_second": 4.92,
+      "eval_steps_per_second": 1.968,
+      "step": 10
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 3.046875,
+      "learning_rate": 0.0001766044443118978,
+      "loss": 7.7504,
+      "step": 15
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 7.192817687988281,
+      "eval_runtime": 1.018,
+      "eval_samples_per_second": 4.911,
+      "eval_steps_per_second": 1.965,
+      "step": 15
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.90625,
+      "learning_rate": 0.00015000000000000001,
+      "loss": 7.0505,
+      "step": 20
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 6.80826473236084,
+      "eval_runtime": 1.0178,
+      "eval_samples_per_second": 4.912,
+      "eval_steps_per_second": 1.965,
+      "step": 20
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 4.125,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 6.6144,
+      "step": 25
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 6.404115200042725,
+      "eval_runtime": 1.0199,
+      "eval_samples_per_second": 4.902,
+      "eval_steps_per_second": 1.961,
+      "step": 25
+    },
+    {
+      "epoch": 6.0,
+      "grad_norm": 9.0,
+      "learning_rate": 8.263518223330697e-05,
+      "loss": 6.066,
+      "step": 30
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 5.7487640380859375,
+      "eval_runtime": 1.0178,
+      "eval_samples_per_second": 4.913,
+      "eval_steps_per_second": 1.965,
+      "step": 30
+    },
+    {
+      "epoch": 7.0,
+      "grad_norm": 15.1875,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 5.1349,
+      "step": 35
+    },
+    {
+      "epoch": 7.0,
+      "eval_loss": 4.6655073165893555,
+      "eval_runtime": 1.0172,
+      "eval_samples_per_second": 4.915,
+      "eval_steps_per_second": 1.966,
+      "step": 35
+    },
+    {
+      "epoch": 8.0,
+      "grad_norm": 17.375,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 3.9891,
+      "step": 40
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 3.7537331581115723,
+      "eval_runtime": 1.0178,
+      "eval_samples_per_second": 4.913,
+      "eval_steps_per_second": 1.965,
+      "step": 40
+    },
+    {
+      "epoch": 9.0,
+      "grad_norm": 14.8125,
+      "learning_rate": 6.030737921409169e-06,
+      "loss": 3.293,
+      "step": 45
+    },
+    {
+      "epoch": 9.0,
+      "eval_loss": 3.3923542499542236,
+      "eval_runtime": 1.0187,
+      "eval_samples_per_second": 4.908,
+      "eval_steps_per_second": 1.963,
+      "step": 45
+    },
+    {
+      "epoch": 10.0,
+      "grad_norm": 17.125,
+      "learning_rate": 0.0,
+      "loss": 3.098,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "eval_loss": 3.3614659309387207,
+      "eval_runtime": 1.0183,
+      "eval_samples_per_second": 4.91,
+      "eval_steps_per_second": 1.964,
+      "step": 50
+    },
+    {
+      "epoch": 10.0,
+      "step": 50,
+      "total_flos": 7.63207683753902e+16,
+      "train_loss": 7.077469825744629,
+      "train_runtime": 322.4528,
+      "train_samples_per_second": 2.419,
+      "train_steps_per_second": 0.155
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 50,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 7.63207683753902e+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 sha256:6bdece8ed2a7aa157e0a906a9e3f1916cd58a75309e45f97bec6e7511e083b5a
+size 5176