Model save

README.md

@@ -0,0 +1,63 @@
+---
+license: apache-2.0
+base_model: alignment-handbook/zephyr-7b-sft-full
+tags:
+- generated_from_trainer
+model-index:
+- name: zephyr-7b-sft-lora
+  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. -->
+
+# zephyr-7b-sft-lora
+
+This model is a fine-tuned version of [alignment-handbook/zephyr-7b-sft-full](https://huggingface.co/alignment-handbook/zephyr-7b-sft-full) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9329
+
+## 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: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 128
+- total_train_batch_size: 1024
+- total_eval_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 | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 0.8622        | 0.51  | 6    | 0.9330          |
+
+
+### Framework versions
+
+- Transformers 4.35.0
+- Pytorch 2.1.1+cu121
+- Datasets 2.14.6
+- Tokenizers 0.14.1

adapter_config.json

@@ -0,0 +1,25 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "alignment-handbook/zephyr-7b-sft-full",
+  "bias": "none",
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "lora_alpha": 16,
+  "lora_dropout": 0.1,
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 64,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "k_proj",
+    "q_proj",
+    "v_proj"
+  ],
+  "task_type": "CAUSAL_LM"
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:881c62d1cb73b619248606d5d69e7dff96d3a0f33c8508b0716f67f2bf0367b4
+size 218138576

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 0.51,
+    "eval_loss": 0.9329424500465393,
+    "eval_runtime": 4121.3449,
+    "eval_samples": 23234,
+    "eval_samples_per_second": 5.637,
+    "eval_steps_per_second": 0.353,
+    "train_loss": 0.9835741718610128,
+    "train_runtime": 9800.1157,
+    "train_samples": 12005,
+    "train_samples_per_second": 1.225,
+    "train_steps_per_second": 0.001
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.51,
+    "eval_loss": 0.9329424500465393,
+    "eval_runtime": 4121.3449,
+    "eval_samples": 23234,
+    "eval_samples_per_second": 5.637,
+    "eval_steps_per_second": 0.353
+}

runs/Jan04_06-30-21_torque0/events.out.tfevents.1704379059.torque0.2339408.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3aef31c79e3c25b098cc3c730eb45f1f24a611cd18eed7f891f5d63089cae08c
+size 4267

runs/Jan04_06-40-26_torque0/events.out.tfevents.1704379263.torque0.2341466.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c8f9d2fe24fb80cdf210f95dcbd2487530ac6fb6d28ac7b0b8e3abe62602d0
+size 4421

runs/Jan04_07-25-31_torque0/events.out.tfevents.1704381968.torque0.2347262.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34a5b402093a96e6594fd0bb75a43b73d20d3f8bf0ccb02f75f9b6fd8099ce43
+size 4267

runs/Jan04_07-27-04_torque0/events.out.tfevents.1704382060.torque0.2347736.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a1053cb0de20602bc8329e16e5d98934d9e496873e661cbb8860149d7010462c
+size 4267

runs/Jan04_07-38-46_torque0/events.out.tfevents.1704382763.torque0.2349828.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcc7911bf2c55c65f2e62147d03c051014cf8969d98c1780dabc900d1187a663
+size 4267

runs/Jan04_07-44-31_torque0/events.out.tfevents.1704383107.torque0.2350985.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:124235b235737a04a6fd4a16f3b7301fec1191c6684b7404654bd69a3246a3e0
+size 5343

runs/Jan04_07-44-31_torque0/events.out.tfevents.1704411915.torque0.2350985.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4ab5f1022f43d3e61c6da69a89b4ebb6a3a88c644918672ea4667ffdc650ba1
+size 354

runs/Jan05_19-17-07_torque0/events.out.tfevents.1704511063.torque0.2431362.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4715e7c50a82ef5459d555b41a605f599a88aa2290e473a31de6e2fa66fa53e
+size 4729

runs/Jan06_04-19-56_torque0/events.out.tfevents.1704543638.torque0.2614000.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff941d59ecd594792da19bf8ad8f6855c56c21fa11e6f8b2fee8e471e97c6965
+size 5189

runs/Jan06_18-32-14_torque0/events.out.tfevents.1704594776.torque0.2740607.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b750b85939d84e4c678f8f6e0f8cba1c1a8bb3ec47f3f36cfb33775a3d24ac4
+size 5189

runs/Jan06_18-32-14_torque0/events.out.tfevents.1704608696.torque0.2740607.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8f1dde98d961684e04c04ce03771a6f1d47089ac3f72ab0b2e13f2383ea7faf
+size 354

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_config.json

@@ -0,0 +1,41 @@
+{
+  "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": [],
+  "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": true
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.51,
+    "train_loss": 0.9835741718610128,
+    "train_runtime": 9800.1157,
+    "train_samples": 12005,
+    "train_samples_per_second": 1.225,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,48 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5116588940706196,
+  "eval_steps": 500,
+  "global_step": 6,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.09,
+      "learning_rate": 1e-05,
+      "loss": 0.867,
+      "step": 1
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.8622,
+      "step": 5
+    },
+    {
+      "epoch": 0.51,
+      "eval_loss": 0.9330160021781921,
+      "eval_runtime": 4125.2443,
+      "eval_samples_per_second": 5.632,
+      "eval_steps_per_second": 0.352,
+      "step": 6
+    },
+    {
+      "epoch": 0.51,
+      "step": 6,
+      "total_flos": 6.133270851249766e+17,
+      "train_loss": 0.9835741718610128,
+      "train_runtime": 9800.1157,
+      "train_samples_per_second": 1.225,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 11,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 6.133270851249766e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe93c77d35c9b1d84bfea52e48d9bd715b130e34952a5eb1fe359623490c0193
+size 4664