End of training

README.md

@@ -0,0 +1,115 @@
+---
+base_model: meta-llama/Meta-Llama-3-8B
+library_name: peft
+license: llama3
+tags:
+- generated_from_trainer
+model-index:
+- name: Meta-Llama-3-8B_alpaca-clean_l0.0002_64
+  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. -->
+
+# Meta-Llama-3-8B_alpaca-clean_l0.0002_64
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.0132
+
+## 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: 1
+- eval_batch_size: 1
+- seed: 0
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 16
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: constant
+- lr_scheduler_warmup_ratio: 0.03
+- training_steps: 10000
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1179        | 0.0003 | 1    | 2.6461          |
+| 2.1519        | 0.0590 | 187  | 1.7584          |
+| 1.4299        | 0.1179 | 374  | 1.7539          |
+| 1.1554        | 0.1769 | 561  | 1.7082          |
+| 2.086         | 0.2359 | 748  | 1.7446          |
+| 1.76          | 0.2949 | 935  | 1.6987          |
+| 1.305         | 0.3538 | 1122 | 1.6802          |
+| 1.1828        | 0.4128 | 1309 | 1.6931          |
+| 2.0012        | 0.4718 | 1496 | 1.6620          |
+| 1.6794        | 0.5307 | 1683 | 1.6657          |
+| 1.2777        | 0.5897 | 1870 | 1.6543          |
+| 1.1958        | 0.6487 | 2057 | 1.6923          |
+| 2.4625        | 0.7077 | 2244 | 1.6584          |
+| 1.7427        | 0.7666 | 2431 | 1.6458          |
+| 1.1636        | 0.8256 | 2618 | 1.6477          |
+| 1.1374        | 0.8846 | 2805 | 1.6614          |
+| 2.2849        | 0.9436 | 2992 | 1.6419          |
+| 1.0011        | 1.0025 | 3179 | 1.6409          |
+| 2.5839        | 1.0615 | 3366 | 1.7018          |
+| 1.334         | 1.1205 | 3553 | 1.6859          |
+| 1.1876        | 1.1794 | 3740 | 1.6755          |
+| 0.9747        | 1.2384 | 3927 | 1.6887          |
+| 2.0187        | 1.2974 | 4114 | 1.6922          |
+| 1.0511        | 1.3564 | 4301 | 1.6827          |
+| 1.0223        | 1.4153 | 4488 | 1.6729          |
+| 1.1295        | 1.4743 | 4675 | 1.6849          |
+| 2.0358        | 1.5333 | 4862 | 1.6879          |
+| 1.3046        | 1.5922 | 5049 | 1.6772          |
+| 1.0023        | 1.6512 | 5236 | 1.6774          |
+| 1.0365        | 1.7102 | 5423 | 1.6905          |
+| 1.8732        | 1.7692 | 5610 | 1.6834          |
+| 1.0398        | 1.8281 | 5797 | 1.6690          |
+| 1.0103        | 1.8871 | 5984 | 1.6662          |
+| 2.3888        | 1.9461 | 6171 | 1.6739          |
+| 0.7728        | 2.0050 | 6358 | 1.6986          |
+| 0.8759        | 2.0640 | 6545 | 1.8575          |
+| 1.3133        | 2.1230 | 6732 | 1.8525          |
+| 0.8286        | 2.1820 | 6919 | 1.7958          |
+| 0.9336        | 2.2409 | 7106 | 1.7920          |
+| 1.0528        | 2.2999 | 7293 | 1.9157          |
+| 1.1672        | 2.3589 | 7480 | 1.8295          |
+| 0.9818        | 2.4178 | 7667 | 1.7832          |
+| 0.92          | 2.4768 | 7854 | 1.7895          |
+| 1.1814        | 2.5358 | 8041 | 1.8489          |
+| 1.3869        | 2.5948 | 8228 | 1.8023          |
+| 0.8245        | 2.6537 | 8415 | 1.7785          |
+| 0.8234        | 2.7127 | 8602 | 1.7827          |
+| 1.6518        | 2.7717 | 8789 | 1.8250          |
+| 1.1769        | 2.8307 | 8976 | 1.8055          |
+| 0.881         | 2.8896 | 9163 | 1.7741          |
+| 0.8681        | 2.9486 | 9350 | 1.7973          |
+| 0.5482        | 3.0076 | 9537 | 1.9381          |
+| 0.6616        | 3.0665 | 9724 | 1.9542          |
+| 1.4274        | 3.1255 | 9911 | 2.0250          |
+
+
+### Framework versions
+
+- PEFT 0.12.1.dev0
+- Transformers 4.45.0.dev0
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 3.15357931251971,
+    "eval_loss": 2.013232469558716,
+    "eval_runtime": 148.4901,
+    "eval_samples_per_second": 6.734,
+    "eval_steps_per_second": 6.734,
+    "total_flos": 1.1687984226206024e+18,
+    "train_loss": 1.3553110431969166,
+    "train_runtime": 191744.1538,
+    "train_samples_per_second": 0.834,
+    "train_steps_per_second": 0.052
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.15357931251971,
+    "eval_loss": 2.013232469558716,
+    "eval_runtime": 148.4901,
+    "eval_samples_per_second": 6.734,
+    "eval_steps_per_second": 6.734
+}

metrics.json

@@ -0,0 +1 @@
+{"run_name": "meta-llama/Meta-Llama-3-8B_alpaca-clean_l0.0002_64", "train_runtime": 191744.1538, "train_samples_per_second": 0.834, "train_steps_per_second": 0.052, "total_flos": 1.1687984226206024e+18, "train_loss": 1.3553110431969166, "epoch": 3.15357931251971, "eval_loss": 2.013232469558716, "eval_runtime": 148.4901, "eval_samples_per_second": 6.734, "eval_steps_per_second": 6.734}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.15357931251971,
+    "total_flos": 1.1687984226206024e+18,
+    "train_loss": 1.3553110431969166,
+    "train_runtime": 191744.1538,
+    "train_samples_per_second": 0.834,
+    "train_steps_per_second": 0.052
+}