End of training

README.md

@@ -0,0 +1,59 @@
+---
+base_model: huggyllama/llama-7b
+library_name: peft
+license: other
+tags:
+- generated_from_trainer
+model-index:
+- name: Test_oasst1_l0.0002_4
+  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. -->
+
+# Test_oasst1_l0.0002_4
+
+This model is a fine-tuned version of [huggyllama/llama-7b](https://huggingface.co/huggyllama/llama-7b) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.7339
+
+## 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: 1
+
+### Training results
+
+
+
+### 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

@@ -1,12 +1,12 @@
 {
     "epoch": 0.001813647698934482,
-    "eval_loss": 1.7385717630386353,
-    "eval_runtime": 1254.5458,
-    "eval_samples_per_second": 0.797,
-    "eval_steps_per_second": 0.797,
+    "eval_loss": 1.733933687210083,
+    "eval_runtime": 1238.3963,
+    "eval_samples_per_second": 0.807,
+    "eval_steps_per_second": 0.807,
     "total_flos": 333765997756416.0,
     "train_loss": 1.5015426874160767,
-    "train_runtime": 74.6898,
-    "train_samples_per_second": 0.214,
+    "train_runtime": 76.3102,
+    "train_samples_per_second": 0.21,
     "train_steps_per_second": 0.013
 }

eval_results.json

@@ -1,7 +1,7 @@
 {
     "epoch": 0.001813647698934482,
-    "eval_loss": 1.7385717630386353,
-    "eval_runtime": 1254.5458,
-    "eval_samples_per_second": 0.797,
-    "eval_steps_per_second": 0.797
+    "eval_loss": 1.733933687210083,
+    "eval_runtime": 1238.3963,
+    "eval_samples_per_second": 0.807,
+    "eval_steps_per_second": 0.807
 }

metrics.json

@@ -1 +1 @@
-{"run_name": "huggyllama/llama-7b_oasst1_l0.0002_4", "train_runtime": 74.6898, "train_samples_per_second": 0.214, "train_steps_per_second": 0.013, "total_flos": 333765997756416.0, "train_loss": 1.5015426874160767, "epoch": 0.001813647698934482, "eval_loss": 1.7385717630386353, "eval_runtime": 1254.5458, "eval_samples_per_second": 0.797, "eval_steps_per_second": 0.797}
+{"run_name": "huggyllama/llama-7b_oasst1_l0.0002_4", "train_runtime": 76.3102, "train_samples_per_second": 0.21, "train_steps_per_second": 0.013, "total_flos": 333765997756416.0, "train_loss": 1.5015426874160767, "epoch": 0.001813647698934482, "eval_loss": 1.733933687210083, "eval_runtime": 1238.3963, "eval_samples_per_second": 0.807, "eval_steps_per_second": 0.807}

train_results.json

@@ -2,7 +2,7 @@
     "epoch": 0.001813647698934482,
     "total_flos": 333765997756416.0,
     "train_loss": 1.5015426874160767,
-    "train_runtime": 74.6898,
-    "train_samples_per_second": 0.214,
+    "train_runtime": 76.3102,
+    "train_samples_per_second": 0.21,
     "train_steps_per_second": 0.013
 }

trainer_state.json

@@ -10,7 +10,7 @@
   "log_history": [
     {
       "epoch": 0.001813647698934482,
-      "grad_norm": 0.197265625,
+      "grad_norm": 0.24609375,
       "learning_rate": 0.0002,
       "loss": 1.5015,
       "step": 1
@@ -20,8 +20,8 @@
       "step": 1,
       "total_flos": 333765997756416.0,
       "train_loss": 1.5015426874160767,
-      "train_runtime": 74.6898,
-      "train_samples_per_second": 0.214,
+      "train_runtime": 76.3102,
+      "train_samples_per_second": 0.21,
       "train_steps_per_second": 0.013
     }
   ],