Upload folder using huggingface_hub

Browse files

Files changed (16) hide show

README.md +106 -0
adapter_config.json +31 -0
adapter_model.safetensors +3 -0
all_results.json +22 -0
config.json +47 -0
eval_results.json +16 -0
runs/May09_09-50-24_lrdn0126.leonardo.local/events.out.tfevents.1715241665.lrdn0126.leonardo.local.140021.0 +3 -0
runs/May10_18-37-51_lrdn0427.leonardo.local/events.out.tfevents.1715359193.lrdn0427.leonardo.local.1322689.0 +3 -0
runs/May10_18-37-51_lrdn0427.leonardo.local/events.out.tfevents.1715403756.lrdn0427.leonardo.local.1322689.1 +3 -0
special_tokens_map.json +30 -0
tokenizer.json +0 -0
tokenizer.model +3 -0
tokenizer_config.json +51 -0
train_results.json +9 -0
trainer_state.json +0 -0
training_args.bin +3 -0

README.md ADDED Viewed

	@@ -0,0 +1,106 @@

+---
+library_name: peft
+tags:
+- alignment-handbook
+- generated_from_trainer
+base_model: g8a9/tweety-mistral-7b
+datasets:
+- giux78/ultrafeedback-binarized-preferences-cleaned-ita
+model-index:
+- name: dpo
+  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. -->
+# dpo
+This model is a fine-tuned version of [/leonardo_scratch/fast/IscrC_ItaLLM_0/tweety_models/sft](https://huggingface.co//leonardo_scratch/fast/IscrC_ItaLLM_0/tweety_models/sft) on the giux78/ultrafeedback-binarized-preferences-cleaned-ita dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6931
+- Rewards/chosen: -0.0430
+- Rewards/rejected: -0.0430
+- Rewards/accuracies: 0.0
+- Rewards/margins: 0.0
+- Logps/rejected: -310.7832
+- Logps/chosen: -310.7832
+- Logits/rejected: -2.3909
+- Logits/chosen: -2.3909
+## 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: 5e-06
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- gradient_accumulation_steps: 4
+- total_train_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: 1
+### Training results
+| Training Loss | Epoch  | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
+|:-------------:|:------:|:----:|:-------------:|:---------------:|:------------:|:--------------:|:---------------:|:------------------:|:--------------:|:---------------:|:----------------:|
+| 0.6931        | 0.0292 | 100  | -2.3941       | -2.3941         | -306.3899    | -306.3899      | 0.6931          | 0.0                | 0.0009         | 0.0             | 0.0009           |
+| 0.6931        | 0.0584 | 200  | -2.3946       | -2.3946         | -306.5539    | -306.5539      | 0.6931          | 0.0                | -0.0008        | 0.0             | -0.0008          |
+| 0.6931        | 0.0876 | 300  | -2.3942       | -2.3942         | -307.0490    | -307.0490      | 0.6931          | 0.0                | -0.0057        | 0.0             | -0.0057          |
+| 0.6931        | 0.1168 | 400  | -2.3940       | -2.3940         | -307.3796    | -307.3796      | 0.6931          | 0.0                | -0.0090        | 0.0             | -0.0090          |
+| 0.6931        | 0.1460 | 500  | -2.3937       | -2.3937         | -307.1581    | -307.1581      | 0.6931          | 0.0                | -0.0068        | 0.0             | -0.0068          |
+| 0.6931        | 0.1751 | 600  | -2.3950       | -2.3950         | -306.9631    | -306.9631      | 0.6931          | 0.0                | -0.0048        | 0.0             | -0.0048          |
+| 0.6931        | 0.2043 | 700  | -2.3949       | -2.3949         | -307.6349    | -307.6349      | 0.6931          | 0.0                | -0.0116        | 0.0             | -0.0116          |
+| 0.6931        | 0.2335 | 800  | -2.3947       | -2.3947         | -307.6957    | -307.6957      | 0.6931          | 0.0                | -0.0122        | 0.0             | -0.0122          |
+| 0.6931        | 0.2627 | 900  | -2.3968       | -2.3968         | -307.1708    | -307.1708      | 0.6931          | 0.0                | -0.0069        | 0.0             | -0.0069          |
+| 0.6931        | 0.2919 | 1000 | -2.3967       | -2.3967         | -308.2130    | -308.2130      | 0.6931          | 0.0                | -0.0173        | 0.0             | -0.0173          |
+| 0.6931        | 0.3211 | 1100 | -2.3971       | -2.3971         | -309.4724    | -309.4724      | 0.6931          | 0.0                | -0.0299        | 0.0             | -0.0299          |
+| 0.6931        | 0.3503 | 1200 | -2.3976       | -2.3976         | -310.0194    | -310.0194      | 0.6931          | 0.0                | -0.0354        | 0.0             | -0.0354          |
+| 0.6931        | 0.3795 | 1300 | -2.3963       | -2.3963         | -309.5114    | -309.5114      | 0.6931          | 0.0                | -0.0303        | 0.0             | -0.0303          |
+| 0.6931        | 0.4087 | 1400 | -2.3955       | -2.3955         | -309.2061    | -309.2061      | 0.6931          | 0.0                | -0.0273        | 0.0             | -0.0273          |
+| 0.6931        | 0.4379 | 1500 | -2.3943       | -2.3943         | -308.9652    | -308.9652      | 0.6931          | 0.0                | -0.0249        | 0.0             | -0.0249          |
+| 0.6931        | 0.4671 | 1600 | -2.3954       | -2.3954         | -309.1586    | -309.1586      | 0.6931          | 0.0                | -0.0268        | 0.0             | -0.0268          |
+| 0.6931        | 0.4962 | 1700 | -2.3913       | -2.3913         | -309.4055    | -309.4055      | 0.6931          | 0.0                | -0.0293        | 0.0             | -0.0293          |
+| 0.6931        | 0.5254 | 1800 | -2.3927       | -2.3927         | -310.2643    | -310.2643      | 0.6931          | 0.0                | -0.0379        | 0.0             | -0.0379          |
+| 0.6931        | 0.5546 | 1900 | -2.3927       | -2.3927         | -310.4164    | -310.4164      | 0.6931          | 0.0                | -0.0394        | 0.0             | -0.0394          |
+| 0.6931        | 0.5838 | 2000 | -2.3920       | -2.3920         | -310.4427    | -310.4427      | 0.6931          | 0.0                | -0.0396        | 0.0             | -0.0396          |
+| 0.6931        | 0.6130 | 2100 | -2.3901       | -2.3901         | -310.7150    | -310.7150      | 0.6931          | 0.0                | -0.0424        | 0.0             | -0.0424          |
+| 0.6931        | 0.6422 | 2200 | -2.3911       | -2.3911         | -311.0310    | -311.0310      | 0.6931          | 0.0                | -0.0455        | 0.0             | -0.0455          |
+| 0.6931        | 0.6714 | 2300 | -2.3912       | -2.3912         | -310.7881    | -310.7881      | 0.6931          | 0.0                | -0.0431        | 0.0             | -0.0431          |
+| 0.6931        | 0.7006 | 2400 | -2.3899       | -2.3899         | -310.6455    | -310.6455      | 0.6931          | 0.0                | -0.0417        | 0.0             | -0.0417          |
+| 0.6931        | 0.7298 | 2500 | -2.3915       | -2.3915         | -310.8196    | -310.8196      | 0.6931          | 0.0                | -0.0434        | 0.0             | -0.0434          |
+| 0.6931        | 0.7590 | 2600 | 0.6931        | -0.0438         | -0.0438      | 0.0            | 0.0             | -310.8546          | -310.8546      | -2.3919         | -2.3919          |
+| 0.6931        | 0.7881 | 2700 | 0.6931        | -0.0436         | -0.0436      | 0.0            | 0.0             | -310.8407          | -310.8407      | -2.3916         | -2.3916          |
+| 0.6931        | 0.8173 | 2800 | 0.6931        | -0.0432         | -0.0432      | 0.0            | 0.0             | -310.7981          | -310.7981      | -2.3915         | -2.3915          |
+| 0.6931        | 0.8465 | 2900 | 0.6931        | -0.0432         | -0.0432      | 0.0            | 0.0             | -310.7943          | -310.7943      | -2.3920         | -2.3920          |
+| 0.6931        | 0.8757 | 3000 | 0.6931        | -0.0431         | -0.0431      | 0.0            | 0.0             | -310.7866          | -310.7866      | -2.3918         | -2.3918          |
+| 0.6931        | 0.9049 | 3100 | 0.6931        | -0.0430         | -0.0430      | 0.0            | 0.0             | -310.7794          | -310.7794      | -2.3908         | -2.3908          |
+| 0.6931        | 0.9341 | 3200 | 0.6931        | -0.0430         | -0.0430      | 0.0            | 0.0             | -310.7812          | -310.7812      | -2.3911         | -2.3911          |
+| 0.6931        | 0.9633 | 3300 | 0.6931        | -0.0430         | -0.0430      | 0.0            | 0.0             | -310.7767          | -310.7767      | -2.3915         | -2.3915          |
+| 0.6931        | 0.9925 | 3400 | 0.6931        | -0.0430         | -0.0430      | 0.0            | 0.0             | -310.7832          | -310.7832      | -2.3909         | -2.3909          |
+### 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 ADDED Viewed

	@@ -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": 128,
+  "lora_dropout": 0.05,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 128,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "up_proj",
+    "q_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:08b32c6ca6c1d6f474fd9bdfdd89647ad949c3884e8b8678930e4247254ff80d
+size 671150064

all_results.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+    "epoch": 0.9997810698387214,
+    "eval_logits/chosen": -2.3908660411834717,
+    "eval_logits/rejected": -2.3908660411834717,
+    "eval_logps/chosen": -310.7823181152344,
+    "eval_logps/rejected": -310.7823181152344,
+    "eval_loss": 0.6931472420692444,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": -0.043037299066782,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": -0.043037299066782,
+    "eval_runtime": 2686.5205,
+    "eval_samples": 6090,
+    "eval_samples_per_second": 2.267,
+    "eval_steps_per_second": 0.284,
+    "total_flos": 0.0,
+    "train_loss": 0.18720042388804636,
+    "train_runtime": 41876.0871,
+    "train_samples": 54810,
+    "train_samples_per_second": 1.309,
+    "train_steps_per_second": 0.082
+}

config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,16 @@

+{
+    "epoch": 0.9997810698387214,
+    "eval_logits/chosen": -2.3908660411834717,
+    "eval_logits/rejected": -2.3908660411834717,
+    "eval_logps/chosen": -310.7823181152344,
+    "eval_logps/rejected": -310.7823181152344,
+    "eval_loss": 0.6931472420692444,
+    "eval_rewards/accuracies": 0.0,
+    "eval_rewards/chosen": -0.043037299066782,
+    "eval_rewards/margins": 0.0,
+    "eval_rewards/rejected": -0.043037299066782,
+    "eval_runtime": 2686.5205,
+    "eval_samples": 6090,
+    "eval_samples_per_second": 2.267,
+    "eval_steps_per_second": 0.284
+}

runs/May09_09-50-24_lrdn0126.leonardo.local/events.out.tfevents.1715241665.lrdn0126.leonardo.local.140021.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a81d4da72013e676051fb773c3ec2d3d02028444771b95e2b114af8d48be41da
+size 203533

runs/May10_18-37-51_lrdn0427.leonardo.local/events.out.tfevents.1715359193.lrdn0427.leonardo.local.1322689.0 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:eabf2fcc476f01de59b62b2cedbf32aefa8e0236a2585c89d08b03140966f779
+size 75944

runs/May10_18-37-51_lrdn0427.leonardo.local/events.out.tfevents.1715403756.lrdn0427.leonardo.local.1322689.1 ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:495d799f0add6ed211b52c7e1222be04420c3f5452331740ff874cd5d49acee6
+size 828

special_tokens_map.json ADDED Viewed

	@@ -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.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer.model ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:f2ddc1899cc92e7a8d539baa0107d226a195a0548881a2806c5de01eea2822e0
+size 723618

tokenizer_config.json ADDED Viewed

	@@ -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 ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+    "epoch": 0.9997810698387214,
+    "total_flos": 0.0,
+    "train_loss": 0.18720042388804636,
+    "train_runtime": 41876.0871,
+    "train_samples": 54810,
+    "train_samples_per_second": 1.309,
+    "train_steps_per_second": 0.082
+}

trainer_state.json ADDED Viewed

The diff for this file is too large to render. See raw diff

training_args.bin ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:8d7aed1d3f8069be186ddde57e8d1a0ee0f72ae82c125a504f4f28900551c93f
+size 5240