End of training

README.md

@@ -0,0 +1,115 @@
+---
+base_model: google/gemma-7b
+library_name: peft
+license: gemma
+tags:
+- generated_from_trainer
+model-index:
+- name: gemma-7b_alpaca-clean_l0.0002_32-32
+  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. -->
+
+# gemma-7b_alpaca-clean_l0.0002_32-32
+
+This model is a fine-tuned version of [google/gemma-7b](https://huggingface.co/google/gemma-7b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2862
+
+## 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 |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.1466        | 0.0003 | 1    | 2.6494          |
+| 2.2743        | 0.0590 | 187  | 1.8818          |
+| 1.4643        | 0.1179 | 374  | 1.8742          |
+| 1.1845        | 0.1769 | 561  | 1.9893          |
+| 2.2425        | 0.2359 | 748  | 1.9409          |
+| 1.9557        | 0.2949 | 935  | 1.8788          |
+| 1.448         | 0.3538 | 1122 | 1.8471          |
+| 1.2879        | 0.4128 | 1309 | 1.8804          |
+| 2.2375        | 0.4718 | 1496 | 1.8555          |
+| 1.778         | 0.5307 | 1683 | 1.8499          |
+| 1.4082        | 0.5897 | 1870 | 1.8627          |
+| 1.3452        | 0.6487 | 2057 | 1.8682          |
+| 2.8115        | 0.7077 | 2244 | 1.8803          |
+| 1.8711        | 0.7666 | 2431 | 1.8475          |
+| 1.2821        | 0.8256 | 2618 | 1.8560          |
+| 1.2943        | 0.8846 | 2805 | 1.8666          |
+| 2.535         | 0.9436 | 2992 | 1.8579          |
+| 0.9723        | 1.0025 | 3179 | 1.8711          |
+| 2.962         | 1.0615 | 3366 | 1.9227          |
+| 1.3686        | 1.1205 | 3553 | 1.9320          |
+| 1.1434        | 1.1794 | 3740 | 1.9103          |
+| 1.0128        | 1.2384 | 3927 | 1.9004          |
+| 2.2098        | 1.2974 | 4114 | 1.9571          |
+| 1.0847        | 1.3564 | 4301 | 1.9256          |
+| 1.0635        | 1.4153 | 4488 | 1.9156          |
+| 1.242         | 1.4743 | 4675 | 1.9359          |
+| 2.2656        | 1.5333 | 4862 | 1.9373          |
+| 1.4033        | 1.5922 | 5049 | 1.9102          |
+| 1.066         | 1.6512 | 5236 | 1.9053          |
+| 1.214         | 1.7102 | 5423 | 1.9475          |
+| 2.0875        | 1.7692 | 5610 | 1.9373          |
+| 1.1555        | 1.8281 | 5797 | 1.9202          |
+| 1.0816        | 1.8871 | 5984 | 1.9039          |
+| 2.9213        | 1.9461 | 6171 | 1.9437          |
+| 0.7327        | 2.0050 | 6358 | 1.9802          |
+| 0.9288        | 2.0640 | 6545 | 2.1237          |
+| 1.4847        | 2.1230 | 6732 | 2.2272          |
+| 0.8673        | 2.1820 | 6919 | 2.0954          |
+| 0.8972        | 2.2409 | 7106 | 2.0114          |
+| 1.171         | 2.2999 | 7293 | 2.2171          |
+| 1.3381        | 2.3589 | 7480 | 2.1423          |
+| 1.0032        | 2.4178 | 7667 | 2.0822          |
+| 0.8967        | 2.4768 | 7854 | 1.9955          |
+| 1.3569        | 2.5358 | 8041 | 2.1730          |
+| 1.552         | 2.5948 | 8228 | 2.0954          |
+| 0.9403        | 2.6537 | 8415 | 2.0874          |
+| 0.8441        | 2.7127 | 8602 | 1.9917          |
+| 2.0487        | 2.7717 | 8789 | 2.1445          |
+| 1.3355        | 2.8307 | 8976 | 2.0624          |
+| 0.9621        | 2.8896 | 9163 | 2.0430          |
+| 0.9307        | 2.9486 | 9350 | 2.0186          |
+| 0.6211        | 3.0076 | 9537 | 2.2474          |
+| 0.6472        | 3.0665 | 9724 | 2.1474          |
+| 1.5749        | 3.1255 | 9911 | 2.3950          |
+
+
+### 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": 2.2862391471862793,
+    "eval_runtime": 568.5344,
+    "eval_samples_per_second": 1.759,
+    "eval_steps_per_second": 1.759,
+    "total_flos": 1.237785300679127e+18,
+    "train_loss": 1.4761439972877501,
+    "train_runtime": 420789.1396,
+    "train_samples_per_second": 0.38,
+    "train_steps_per_second": 0.024
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 3.15357931251971,
+    "eval_loss": 2.2862391471862793,
+    "eval_runtime": 568.5344,
+    "eval_samples_per_second": 1.759,
+    "eval_steps_per_second": 1.759
+}

metrics.json

@@ -0,0 +1 @@
+{"run_name": "google/gemma-7b_alpaca-clean_l0.0002_32,32", "train_runtime": 420789.1396, "train_samples_per_second": 0.38, "train_steps_per_second": 0.024, "total_flos": 1.237785300679127e+18, "train_loss": 1.4761439972877501, "epoch": 3.15357931251971, "eval_loss": 2.2862391471862793, "eval_runtime": 568.5344, "eval_samples_per_second": 1.759, "eval_steps_per_second": 1.759}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.15357931251971,
+    "total_flos": 1.237785300679127e+18,
+    "train_loss": 1.4761439972877501,
+    "train_runtime": 420789.1396,
+    "train_samples_per_second": 0.38,
+    "train_steps_per_second": 0.024
+}