End of training

README.md

@@ -0,0 +1,83 @@
+---
+license: apache-2.0
+base_model: Locutusque/TinyMistral-248M
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: tinymistral-248-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. -->
+
+# tinymistral-248-DPO
+
+This model is a fine-tuned version of [Locutusque/TinyMistral-248M](https://huggingface.co/Locutusque/TinyMistral-248M) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3205
+- Accuracy: 0.0
+- Rewards/chosen: 0.7722
+- Rewards/rejected: -0.2727
+- Rewards/accuracies: 1.0
+- Rewards/margins: 1.0449
+- Logps/rejected: -286.5494
+- Logps/chosen: -398.5646
+- Logits/rejected: -2.3562
+- Logits/chosen: -1.8620
+
+## 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: 12
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 12
+- total_train_batch_size: 144
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 6
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------------:|:----------------:|:------------------:|:---------------:|:--------------:|:------------:|:---------------:|:-------------:|
+| 0.5815        | 0.48  | 10   | 0.3205          | 0.0      | 0.7722         | -0.2727          | 1.0                | 1.0449          | -286.5494      | -398.5646    | -2.3562         | -1.8620       |
+| 0.3287        | 0.95  | 20   | 0.0970          | 0.0      | 1.0191         | -1.8694          | 1.0                | 2.8886          | -302.5168      | -396.0956    | -2.0547         | -1.5790       |
+| 0.2126        | 1.43  | 30   | 0.0414          | 0.0      | 0.3685         | -4.5314          | 1.0                | 4.8999          | -329.1370      | -402.6024    | -1.8100         | -1.4099       |
+| 0.1844        | 1.9   | 40   | 0.0260          | 0.0      | 0.9879         | -4.8275          | 1.0                | 5.8153          | -332.0973      | -396.4084    | -1.8704         | -1.4976       |
+| 0.1546        | 2.38  | 50   | 0.0190          | 0.0      | 1.1813         | -5.2560          | 1.0                | 6.4373          | -336.3821      | -394.4740    | -1.9098         | -1.5582       |
+| 0.1532        | 2.86  | 60   | 0.0140          | 0.0      | 1.0583         | -6.0198          | 1.0                | 7.0780          | -344.0201      | -395.7045    | -1.8920         | -1.5654       |
+| 0.1402        | 3.33  | 70   | 0.0112          | 0.0      | 1.0134         | -6.5382          | 1.0                | 7.5517          | -349.2049      | -396.1526    | -1.8823         | -1.5706       |
+| 0.1544        | 3.81  | 80   | 0.0089          | 0.0      | 0.8836         | -7.1726          | 1.0                | 8.0562          | -355.5490      | -397.4513    | -1.8518         | -1.5535       |
+| 0.1357        | 4.29  | 90   | 0.0072          | 0.0      | 0.7532         | -7.7663          | 1.0                | 8.5195          | -361.4852      | -398.7546    | -1.8193         | -1.5345       |
+| 0.1418        | 4.76  | 100  | 0.0061          | 0.0      | 0.6041         | -8.3133          | 1.0                | 8.9174          | -366.9556      | -400.2459    | -1.7889         | -1.5150       |
+| 0.1482        | 5.24  | 110  | 0.0051          | 0.0      | 0.4867         | -8.7961          | 1.0                | 9.2828          | -371.7837      | -401.4203    | -1.7611         | -1.4971       |
+| 0.141         | 5.71  | 120  | 0.0045          | 0.0      | 0.4212         | -9.1494          | 1.0                | 9.5706          | -375.3166      | -402.0751    | -1.7409         | -1.4842       |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,110 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "Locutusque/TinyMistral-248M",
+  "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": [
+    "model.layers.2.self_attn.k_proj",
+    "model.layers.8.mlp.down_proj",
+    "model.layers.8.mlp.up_proj",
+    "model.layers.7.self_attn.o_proj",
+    "model.layers.6.self_attn.k_proj",
+    "model.layers.6.self_attn.o_proj",
+    "model.layers.4.mlp.gate_proj",
+    "model.layers.4.self_attn.q_proj",
+    "model.layers.6.mlp.up_proj",
+    "model.layers.6.mlp.down_proj",
+    "model.layers.2.mlp.gate_proj",
+    "model.layers.5.self_attn.v_proj",
+    "model.layers.7.mlp.down_proj",
+    "model.layers.7.mlp.up_proj",
+    "model.layers.1.self_attn.o_proj",
+    "lm_head",
+    "model.layers.5.mlp.up_proj",
+    "model.layers.0.mlp.gate_proj",
+    "model.layers.9.self_attn.k_proj",
+    "model.layers.2.self_attn.o_proj",
+    "model.layers.4.mlp.up_proj",
+    "model.layers.1.self_attn.k_proj",
+    "model.layers.3.self_attn.v_proj",
+    "model.layers.10.mlp.down_proj",
+    "model.layers.10.mlp.gate_proj",
+    "model.layers.6.self_attn.q_proj",
+    "model.layers.3.self_attn.k_proj",
+    "model.layers.9.mlp.up_proj",
+    "model.layers.7.self_attn.k_proj",
+    "model.layers.3.self_attn.q_proj",
+    "model.layers.8.self_attn.o_proj",
+    "model.layers.10.mlp.up_proj",
+    "model.layers.7.self_attn.q_proj",
+    "model.layers.0.mlp.down_proj",
+    "model.layers.7.mlp.gate_proj",
+    "model.layers.3.mlp.down_proj",
+    "model.layers.10.self_attn.o_proj",
+    "model.layers.4.self_attn.o_proj",
+    "model.layers.3.self_attn.o_proj",
+    "model.layers.5.self_attn.k_proj",
+    "model.layers.1.self_attn.q_proj",
+    "model.layers.5.self_attn.o_proj",
+    "model.layers.11.mlp.down_proj",
+    "model.layers.9.self_attn.v_proj",
+    "model.layers.1.self_attn.v_proj",
+    "model.layers.2.self_attn.v_proj",
+    "model.layers.4.mlp.down_proj",
+    "model.layers.10.self_attn.q_proj",
+    "model.layers.0.self_attn.q_proj",
+    "model.layers.3.mlp.gate_proj",
+    "model.layers.9.self_attn.o_proj",
+    "model.layers.8.self_attn.q_proj",
+    "model.layers.10.self_attn.v_proj",
+    "model.layers.3.mlp.up_proj",
+    "model.layers.8.self_attn.v_proj",
+    "model.layers.8.self_attn.k_proj",
+    "model.layers.9.mlp.down_proj",
+    "model.layers.11.mlp.up_proj",
+    "model.layers.4.self_attn.k_proj",
+    "model.layers.11.self_attn.v_proj",
+    "model.layers.10.self_attn.k_proj",
+    "model.layers.0.mlp.up_proj",
+    "model.layers.1.mlp.down_proj",
+    "model.layers.11.self_attn.q_proj",
+    "model.layers.1.mlp.gate_proj",
+    "model.layers.5.self_attn.q_proj",
+    "model.layers.7.self_attn.v_proj",
+    "model.layers.5.mlp.down_proj",
+    "model.layers.9.mlp.gate_proj",
+    "model.layers.11.self_attn.k_proj",
+    "model.layers.9.self_attn.q_proj",
+    "model.layers.2.mlp.up_proj",
+    "model.layers.4.self_attn.v_proj",
+    "model.layers.11.self_attn.o_proj",
+    "model.layers.1.mlp.up_proj",
+    "model.layers.0.self_attn.k_proj",
+    "model.layers.5.mlp.gate_proj",
+    "model.layers.6.mlp.gate_proj",
+    "model.layers.8.mlp.gate_proj",
+    "model.layers.0.self_attn.v_proj",
+    "model.layers.6.self_attn.v_proj",
+    "model.layers.2.self_attn.q_proj",
+    "model.layers.2.mlp.down_proj",
+    "model.layers.0.self_attn.o_proj",
+    "model.layers.11.mlp.gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ebe9a629dd2599614e3a4d28887a66a753a92b950dfd372934bd458239fca533
+size 150137592

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>"
+  ],
+  "bos_token": {
+    "content": "<|bos|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "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_config.json

@@ -0,0 +1,87 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|bos|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32002": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32003": {
+      "content": "<|ASSISTANT|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32004": {
+      "content": "<|USER|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|ASSISTANT|>",
+    "<|USER|>"
+  ],
+  "bos_token": "<|bos|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "legacy": true,
+  "max_length": 1536,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "[PAD]",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1490c0eac1bb220a0df75e33af316b4aee8b487edfafd47a0ccf5bec2c878634
+size 4600