Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+library_name: peft
+tags:
+- alignment-handbook
+- generated_from_trainer
+base_model: g8a9/tweety-mistral-7b
+datasets:
+- giux78/100k-sft-ready-ultrafeedback-ita
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [g8a9/tweety-mistral-7b](https://huggingface.co/g8a9/tweety-mistral-7b) on the giux78/100k-sft-ready-ultrafeedback-ita dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.2661
+
+## 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: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 2
+- total_train_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: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.2875        | 0.9999 | 9050 | 1.2661          |
+
+
+### Framework versions
+
+- PEFT 0.7.1
+- Transformers 4.40.2
+- Pytorch 2.1.2+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

adapter_config.json

@@ -0,0 +1,31 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "g8a9/tweety-mistral-7b",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "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": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "gate_proj",
+    "q_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40225823c3c8f24ae96f01574ebb0312eca79138cf36753bdb6f212bf6b8f3db
+size 83946192

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 0.9999447544334568,
+    "eval_loss": 1.266111135482788,
+    "eval_runtime": 1816.7266,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 3.967,
+    "eval_steps_per_second": 0.496,
+    "total_flos": 6.363322205866033e+18,
+    "train_loss": 0.5663559655985121,
+    "train_runtime": 33167.9656,
+    "train_samples": 100000,
+    "train_samples_per_second": 2.183,
+    "train_steps_per_second": 0.273
+}

config.json

@@ -0,0 +1,47 @@
+{
+  "_name_or_path": "g8a9/tweety-mistral-7b",
+  "additional_special_tokens_ids": [],
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "cls_token_id": null,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "mask_token_id": null,
+  "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": {
+    "_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-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "LlamaTokenizerFast",
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.2",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 32000
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9999447544334568,
+    "eval_loss": 1.266111135482788,
+    "eval_runtime": 1816.7266,
+    "eval_samples": 10000,
+    "eval_samples_per_second": 3.967,
+    "eval_steps_per_second": 0.496
+}

runs/May07_00-47-06_lrdn3441.leonardo.local/events.out.tfevents.1715035706.lrdn3441.leonardo.local.1553459.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f13f724b02a26d8f6d3bc05e6982b05fffb0338877f0e1412db4b68739d54c73
+size 7212

runs/May07_00-52-36_lrdn0321.leonardo.local/events.out.tfevents.1715036049.lrdn0321.leonardo.local.447105.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c16e69bb525850c86da47f5f3245cf1e9b17f193daa0b31f9e7e28d6aa35461d
+size 218351

runs/May08_17-40-23_lrdn1619.leonardo.local/events.out.tfevents.1715182913.lrdn1619.leonardo.local.92001.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:493128c9a7fb7449bed63cc57b07e2b2f34ba5b2140d21fab47d5eb44428b89f
+size 177091

runs/May08_17-40-23_lrdn1619.leonardo.local/events.out.tfevents.1715217898.lrdn1619.leonardo.local.92001.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee872f87cfdd43f4c8736bd9532f84fdc587e65f2bb9fa0a51b72070dee8919
+size 359

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ddc1899cc92e7a8d539baa0107d226a195a0548881a2806c5de01eea2822e0
+size 723618

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    },
+    "3": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9999447544334568,
+    "total_flos": 6.363322205866033e+18,
+    "train_loss": 0.5663559655985121,
+    "train_runtime": 33167.9656,
+    "train_samples": 100000,
+    "train_samples_per_second": 2.183,
+    "train_steps_per_second": 0.273
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbc50869f0243a2cf3deb6eda5413c254f0ff420bed5173b193a73848c8c080c
+size 5176