Model save

README.md

@@ -0,0 +1,60 @@
+---
+base_model: hllj/zephyr-7b-beta-vi-math
+tags:
+- generated_from_trainer
+model-index:
+- name: sft-zephyr-7b-beta-vi-math-v1
+  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-zephyr-7b-beta-vi-math-v1
+
+This model is a fine-tuned version of [hllj/zephyr-7b-beta-vi-math](https://huggingface.co/hllj/zephyr-7b-beta-vi-math) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3393
+
+## 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: 4
+- eval_batch_size: 4
+- seed: 42
+- distributed_type: multi-GPU
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.05
+- num_epochs: 1
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.5124        | 0.17  | 50   | 0.4338          |
+| 0.3876        | 0.34  | 100  | 0.3593          |
+
+
+### Framework versions
+
+- Transformers 4.35.2
+- Pytorch 2.1.0
+- Datasets 2.15.0
+- Tokenizers 0.15.0

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "hllj/zephyr-7b-beta-vi-math",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 32,
+  "lora_dropout": 0.05,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "q_proj",
+    "o_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d11134749e2c5b60bff943689f10202986b71035eb637e347309e490a24faee9
+size 54560368

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.5,
+    "eval_loss": 0.339265376329422,
+    "eval_runtime": 1.0935,
+    "eval_samples": 12,
+    "eval_samples_per_second": 10.974,
+    "eval_steps_per_second": 2.744,
+    "train_loss": 0.5100626462981814,
+    "train_runtime": 502.0996,
+    "train_samples": 1184,
+    "train_samples_per_second": 2.358,
+    "train_steps_per_second": 0.59
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.5,
+    "eval_loss": 0.339265376329422,
+    "eval_runtime": 1.0935,
+    "eval_samples": 12,
+    "eval_samples_per_second": 10.974,
+    "eval_steps_per_second": 2.744
+}

runs/Nov17_18-47-06_7a59b30c842e/events.out.tfevents.1700246832.7a59b30c842e.2079.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25479244ca132824359da3651844a5e3a48fb025b797d04046f19a6938df1ae9
+size 7534

runs/Nov17_18-47-06_7a59b30c842e/events.out.tfevents.1700247335.7a59b30c842e.2079.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b451d90d3a1ca153da586e760798a22570642d9fe5c903518f01fe8fdd0ee12e
+size 359

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.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,48 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "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
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.5,
+    "train_loss": 0.5100626462981814,
+    "train_runtime": 502.0996,
+    "train_samples": 1184,
+    "train_samples_per_second": 2.358,
+    "train_steps_per_second": 0.59
+}

trainer_state.json

@@ -0,0 +1,134 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.4966216216216216,
+  "eval_steps": 50,
+  "global_step": 147,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 1.3333333333333334e-06,
+      "loss": 0.9977,
+      "step": 1
+    },
+    {
+      "epoch": 0.03,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.9343,
+      "step": 10
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 1.998437989229673e-05,
+      "loss": 0.8302,
+      "step": 20
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 1.9859711663543573e-05,
+      "loss": 0.706,
+      "step": 30
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 1.961193185426459e-05,
+      "loss": 0.5885,
+      "step": 40
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 1.9244134324096223e-05,
+      "loss": 0.5124,
+      "step": 50
+    },
+    {
+      "epoch": 0.17,
+      "eval_loss": 0.43378910422325134,
+      "eval_runtime": 1.092,
+      "eval_samples_per_second": 10.989,
+      "eval_steps_per_second": 2.747,
+      "step": 50
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 1.876091151314196e-05,
+      "loss": 0.4707,
+      "step": 60
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 1.8168297099265094e-05,
+      "loss": 0.427,
+      "step": 70
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 1.747369065961599e-05,
+      "loss": 0.4299,
+      "step": 80
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 1.6685765277094702e-05,
+      "loss": 0.4137,
+      "step": 90
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 1.5814359245404818e-05,
+      "loss": 0.3876,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.3593088984489441,
+      "eval_runtime": 1.0931,
+      "eval_samples_per_second": 10.978,
+      "eval_steps_per_second": 2.745,
+      "step": 100
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 1.4870353224904572e-05,
+      "loss": 0.3912,
+      "step": 110
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 1.3865534383127406e-05,
+      "loss": 0.3932,
+      "step": 120
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 1.2812449216357863e-05,
+      "loss": 0.3705,
+      "step": 130
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 1.1724246889980638e-05,
+      "loss": 0.371,
+      "step": 140
+    },
+    {
+      "epoch": 0.5,
+      "step": 147,
+      "total_flos": 2.560641466368e+16,
+      "train_loss": 0.5100626462981814,
+      "train_runtime": 502.0996,
+      "train_samples_per_second": 2.358,
+      "train_steps_per_second": 0.59
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 296,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 2.560641466368e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2578ab79106ee1b3a538815434bca273c625fc184b3a3dfc61a2a0f5c422fbb3
+size 4664