End of training

README.md

@@ -0,0 +1,87 @@
+---
+license: mit
+base_model: HuggingFaceH4/zephyr-7b-beta
+tags:
+- trl
+- sft
+- generated_from_trainer
+model-index:
+- name: results
+  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. -->
+
+# results
+
+This model is a fine-tuned version of [HuggingFaceH4/zephyr-7b-beta](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7065
+
+## 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: 0.00025
+- train_batch_size: 4
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 10
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.7779        | 0.35  | 100  | 1.0474          |
+| 0.6553        | 0.69  | 200  | 0.8922          |
+| 0.6339        | 1.04  | 300  | 0.7221          |
+| 0.6018        | 1.39  | 400  | 0.7020          |
+| 0.5853        | 1.74  | 500  | 0.6908          |
+| 0.445         | 2.08  | 600  | 0.6887          |
+| 0.4875        | 2.43  | 700  | 0.6783          |
+| 0.4938        | 2.78  | 800  | 0.6883          |
+| 0.3598        | 3.12  | 900  | 0.6893          |
+| 0.3549        | 3.47  | 1000 | 0.6763          |
+| 0.3624        | 3.82  | 1100 | 0.6971          |
+| 0.344         | 4.17  | 1200 | 0.7348          |
+| 0.3393        | 4.51  | 1300 | 0.7502          |
+| 0.3823        | 4.86  | 1400 | 0.6861          |
+| 0.3534        | 5.21  | 1500 | 0.6849          |
+| 0.3632        | 5.56  | 1600 | 0.6585          |
+| 0.3634        | 5.9   | 1700 | 0.6414          |
+| 0.3002        | 6.25  | 1800 | 0.6662          |
+| 0.3126        | 6.6   | 1900 | 0.6864          |
+| 0.3129        | 6.94  | 2000 | 0.6638          |
+| 0.259         | 7.29  | 2100 | 0.6967          |
+| 0.27          | 7.64  | 2200 | 0.7059          |
+| 0.3063        | 7.99  | 2300 | 0.6582          |
+| 0.2814        | 8.33  | 2400 | 0.7205          |
+| 0.3005        | 8.68  | 2500 | 0.7334          |
+| 0.2862        | 9.03  | 2600 | 0.6839          |
+| 0.3092        | 9.38  | 2700 | 0.6929          |
+| 0.3078        | 9.72  | 2800 | 0.7065          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0+cu121
+- Datasets 2.16.1
+- Tokenizers 0.15.1

adapter_config.json

@@ -0,0 +1,33 @@
+{
+  "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,
+  "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": [
+    "k_proj",
+    "gate_proj",
+    "up_proj",
+    "v_proj",
+    "lm_head",
+    "o_proj",
+    "q_proj",
+    "down_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:ed40e144f3af3d1dd28a4ca5897dbc8ce18cd4c4f7a61c00309068685c248eb2
+size 609389712

runs/Jan30_07-24-01_39aa840562a4/events.out.tfevents.1706599444.39aa840562a4.356.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d276ca46410c3a20c4b6ba86cf38495de75bb928c4122848b748a5dfd181abaa
+size 30558

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": 1000000000000000019884624838656,
+  "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
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b104b14ff29d94c09fef93acb1e6fefcc352f653f892d0e83b0f4f90d70c4f7
+size 4536