upload model checkpoints

.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

@@ -1,3 +1,75 @@
----
-license: gemma
----
+---
+library_name: peft
+tags:
+- alignment-handbook
+- generated_from_trainer
+datasets:
+- llama-duo/synth_summarize_dataset_dedup
+base_model: google/gemma-7b
+model-index:
+- name: gemma7b-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. -->
+
+# gemma7b-summarize-gemini1_5flash-2k
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on the llama-duo/synth_summarize_dataset_dedup dataset.
+It achieves the following results on the evaluation set:
+- Loss: 7.7045
+
+## 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: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 49.7965       | 0.8571 | 3    | 15.4869         |
+| 39.0892       | 2.0    | 7    | 12.5338         |
+| 23.1465       | 2.8571 | 10   | 10.1182         |
+| 23.1465       | 4.0    | 14   | 8.4587          |
+| 19.7449       | 4.8571 | 17   | 8.0612          |
+| 18.8693       | 6.0    | 21   | 7.8270          |
+| 18.8693       | 6.8571 | 24   | 7.7329          |
+| 18.4335       | 8.0    | 28   | 7.6986          |
+| 18.2424       | 8.5714 | 30   | 7.7045          |
+
+
+### Framework versions
+
+- PEFT 0.10.0
+- Transformers 4.40.0
+- Pytorch 2.1.2+cu121
+- Datasets 2.18.0
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,29 @@
+{
+  "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": [
+    "q_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 sha256:366f1d6372ed67633f8f04f3deaf3e6951ca6dc370b39bfc52e3649f229d0951
+size 6437384

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 8.571428571428571,
+    "eval_loss": 7.704453945159912,
+    "eval_runtime": 0.2398,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.703,
+    "eval_steps_per_second": 4.17,
+    "total_flos": 9.147533553041408e+16,
+    "train_loss": 23.27788518269857,
+    "train_runtime": 75.0535,
+    "train_samples": 1979,
+    "train_samples_per_second": 29.046,
+    "train_steps_per_second": 0.4
+}

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "google/gemma-7b",
+  "architectures": [
+    "GemmaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "eos_token_id": 1,
+  "head_dim": 256,
+  "hidden_act": "gelu",
+  "hidden_activation": null,
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 24576,
+  "max_position_embeddings": 8192,
+  "model_type": "gemma",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0",
+  "use_cache": true,
+  "vocab_size": 256000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.571428571428571,
+    "eval_loss": 7.704453945159912,
+    "eval_runtime": 0.2398,
+    "eval_samples": 25,
+    "eval_samples_per_second": 41.703,
+    "eval_steps_per_second": 4.17
+}

runs/Jun13_15-27-40_gpu1-1/events.out.tfevents.1718264144.gpu1-1.597831.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df6281f4f8bd6fd9aa6bd811e16c2c9008aab3dd1547ac2e38481cad944e8110
+size 9674

runs/Jun13_15-27-40_gpu1-1/events.out.tfevents.1718264220.gpu1-1.597831.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c935c71b823dfd92efb702a5e80d984bafd15408a2057d0c2a6b156c3b785690
+size 354

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": 9.147533553041408e+16,
+    "train_loss": 23.27788518269857,
+    "train_runtime": 75.0535,
+    "train_samples": 1979,
+    "train_samples_per_second": 29.046,
+    "train_steps_per_second": 0.4
+}

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": 187.0,
+      "learning_rate": 6.666666666666667e-05,
+      "loss": 49.7965,
+      "step": 1
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "eval_loss": 15.486898422241211,
+      "eval_runtime": 0.2527,
+      "eval_samples_per_second": 39.572,
+      "eval_steps_per_second": 3.957,
+      "step": 3
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 52.5,
+      "learning_rate": 0.00019730448705798239,
+      "loss": 39.0892,
+      "step": 5
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 12.533833503723145,
+      "eval_runtime": 0.2329,
+      "eval_samples_per_second": 42.936,
+      "eval_steps_per_second": 4.294,
+      "step": 7
+    },
+    {
+      "epoch": 2.857142857142857,
+      "grad_norm": 11.8125,
+      "learning_rate": 0.0001686241637868734,
+      "loss": 23.1465,
+      "step": 10
+    },
+    {
+      "epoch": 2.857142857142857,
+      "eval_loss": 10.118247985839844,
+      "eval_runtime": 0.2382,
+      "eval_samples_per_second": 41.973,
+      "eval_steps_per_second": 4.197,
+      "step": 10
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 8.45867919921875,
+      "eval_runtime": 0.2351,
+      "eval_samples_per_second": 42.528,
+      "eval_steps_per_second": 4.253,
+      "step": 14
+    },
+    {
+      "epoch": 4.285714285714286,
+      "grad_norm": 4.21875,
+      "learning_rate": 0.00011736481776669306,
+      "loss": 19.7449,
+      "step": 15
+    },
+    {
+      "epoch": 4.857142857142857,
+      "eval_loss": 8.061217308044434,
+      "eval_runtime": 0.2464,
+      "eval_samples_per_second": 40.588,
+      "eval_steps_per_second": 4.059,
+      "step": 17
+    },
+    {
+      "epoch": 5.714285714285714,
+      "grad_norm": 4.21875,
+      "learning_rate": 6.039202339608432e-05,
+      "loss": 18.8693,
+      "step": 20
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 7.827044486999512,
+      "eval_runtime": 0.2351,
+      "eval_samples_per_second": 42.54,
+      "eval_steps_per_second": 4.254,
+      "step": 21
+    },
+    {
+      "epoch": 6.857142857142857,
+      "eval_loss": 7.732919216156006,
+      "eval_runtime": 0.245,
+      "eval_samples_per_second": 40.809,
+      "eval_steps_per_second": 4.081,
+      "step": 24
+    },
+    {
+      "epoch": 7.142857142857143,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.6451218858706374e-05,
+      "loss": 18.4335,
+      "step": 25
+    },
+    {
+      "epoch": 8.0,
+      "eval_loss": 7.698564052581787,
+      "eval_runtime": 0.2338,
+      "eval_samples_per_second": 42.772,
+      "eval_steps_per_second": 4.277,
+      "step": 28
+    },
+    {
+      "epoch": 8.571428571428571,
+      "grad_norm": 4.6875,
+      "learning_rate": 0.0,
+      "loss": 18.2424,
+      "step": 30
+    },
+    {
+      "epoch": 8.571428571428571,
+      "eval_loss": 7.704453945159912,
+      "eval_runtime": 0.2338,
+      "eval_samples_per_second": 42.771,
+      "eval_steps_per_second": 4.277,
+      "step": 30
+    },
+    {
+      "epoch": 8.571428571428571,
+      "step": 30,
+      "total_flos": 9.147533553041408e+16,
+      "train_loss": 23.27788518269857,
+      "train_runtime": 75.0535,
+      "train_samples_per_second": 29.046,
+      "train_steps_per_second": 0.4
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 30,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 100,
+  "total_flos": 9.147533553041408e+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 sha256:9b64bb10205609476ba55de709d2eabd563e0e8ee06bc25b68c932f7248bcdbf
+size 5176