Model save

README.md

@@ -0,0 +1,60 @@
+---
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-beta
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-sft-lora-eldar
+  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. -->
+
+# zephyr-7b-sft-lora-eldar
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7091
+
+## 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 41
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 1.7926        | 0.95  | 15   | 1.7091          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "o_proj",
+    "k_proj",
+    "q_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011dec70c9837ed4371efcf93fd112cfffc67bd11181558859be9d513540accb
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.95,
+    "eval_loss": 1.7090861797332764,
+    "eval_runtime": 2327.8817,
+    "eval_samples": 1086,
+    "eval_samples_per_second": 0.467,
+    "eval_steps_per_second": 0.467,
+    "train_loss": 1.777411683400472,
+    "train_runtime": 7576.8776,
+    "train_samples": 2026,
+    "train_samples_per_second": 0.267,
+    "train_steps_per_second": 0.002
+}

config.json

@@ -0,0 +1,38 @@
+{
+  "_name_or_path": "HuggingFaceH4/zephyr-7b-beta",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "quantization_config": {
+    "bnb_4bit_compute_dtype": "float16",
+    "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-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.35.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.95,
+    "eval_loss": 1.7090861797332764,
+    "eval_runtime": 2327.8817,
+    "eval_samples": 1086,
+    "eval_samples_per_second": 0.467,
+    "eval_steps_per_second": 0.467
+}

runs/Dec04_13-02-48_ip-172-16-12-85.ec2.internal/events.out.tfevents.1701695144.ip-172-16-12-85.ec2.internal.1417.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0955b38af18d01baa6c8d7916fa6def0e69f07c480703fb63f668cd1c6483e8
+size 4664

runs/Dec04_13-16-47_ip-172-16-12-85.ec2.internal/events.out.tfevents.1701695829.ip-172-16-12-85.ec2.internal.18135.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7480c2bc436eec0d913ade5c5b733c35ac992c01eedef92c226b47eb3d4bcc6
+size 6050

runs/Dec04_20-17-32_ip-172-16-12-85.ec2.internal/events.out.tfevents.1701721125.ip-172-16-12-85.ec2.internal.26822.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7270155d9ed8e55bc492972e8662a8c089a80b10255d53673f582beeb9330490
+size 4664

runs/Dec04_20-26-31_ip-172-16-12-85.ec2.internal/events.out.tfevents.1701721666.ip-172-16-12-85.ec2.internal.5396.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcfa76a5a15f0cac53b9613a5db8565644d48404dbafcb819e9840eaa534d6e0
+size 4664

runs/Dec05_12-10-17_ip-172-16-125-111.ec2.internal/events.out.tfevents.1701778372.ip-172-16-125-111.ec2.internal.7639.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adbb0969d4504766f4599bee91ed33d3e26d8959c66c0b2733faba27f6c85d75
+size 5922

runs/Dec05_15-55-33_ip-172-16-125-111.ec2.internal/events.out.tfevents.1701791749.ip-172-16-125-111.ec2.internal.15369.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e42cb338a768ecb7be79d5f7642651a1ad64d45a427cd480947a9643bbe914a
+size 5920

runs/Dec05_15-55-33_ip-172-16-125-111.ec2.internal/events.out.tfevents.1701801650.ip-172-16-125-111.ec2.internal.15369.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05cface16662e929a9e69185bd67cd846a26276a7e05d936bd6301c24a898ca3
+size 354

runs/Dec06_21-14-17_ip-172-16-25-235.ec2.internal/events.out.tfevents.1701897320.ip-172-16-25-235.ec2.internal.20890.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b22f75b37445d73737f61b2b3b713cef841c34bf5e2ec0a0f725be4ea9417171
+size 4704

runs/Dec06_21-23-02_ip-172-16-25-235.ec2.internal/events.out.tfevents.1701897797.ip-172-16-25-235.ec2.internal.27435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe6547a4334c27c04250e343c206337e0e81092e8779b0edc577d6dd3aeafd9
+size 5934

runs/Dec06_21-23-02_ip-172-16-25-235.ec2.internal/events.out.tfevents.1701907702.ip-172-16-25-235.ec2.internal.27435.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b51c2ccb67c8c1ccda12329e53e974137a906617d8b107519e48231efbf7e76
+size 354

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,46 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n'  + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "left",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.95,
+    "train_loss": 1.777411683400472,
+    "train_runtime": 7576.8776,
+    "train_samples": 2026,
+    "train_samples_per_second": 0.267,
+    "train_steps_per_second": 0.002
+}

trainer_state.json

@@ -0,0 +1,60 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.947680157946693,
+  "eval_steps": 500,
+  "global_step": 15,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 1.8063,
+      "step": 1
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 1.7809,
+      "step": 5
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 1.7536,
+      "step": 10
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 0.0,
+      "loss": 1.7926,
+      "step": 15
+    },
+    {
+      "epoch": 0.95,
+      "eval_loss": 1.7090861797332764,
+      "eval_runtime": 2328.2925,
+      "eval_samples_per_second": 0.466,
+      "eval_steps_per_second": 0.466,
+      "step": 15
+    },
+    {
+      "epoch": 0.95,
+      "step": 15,
+      "total_flos": 1.6904795211798938e+17,
+      "train_loss": 1.777411683400472,
+      "train_runtime": 7576.8776,
+      "train_samples_per_second": 0.267,
+      "train_steps_per_second": 0.002
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 15,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 1.6904795211798938e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b077b662e4b691e14803d3ae0b72163f045d7cf6b50c35b9fd4752a7be446ea7
+size 4664