Model save

README.md

@@ -2,13 +2,10 @@
 license: llama2
 library_name: peft
 tags:
-- alignment-handbook
 - trl
 - sft
 - generated_from_trainer
 base_model: meta-llama/Llama-2-7b-hf
-datasets:
-- HuggingFaceH4/ultrachat_200k
 model-index:
 - name: llama2-poison-20p-0502
   results: []
@@ -19,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # llama2-poison-20p-0502
 
-This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the HuggingFaceH4/ultrachat_200k dataset.
+This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the None dataset.
 It achieves the following results on the evaluation set:
 - Loss: nan
 

all_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.0,
-    "train_runtime": 6672.0976,
+    "train_runtime": 10243.5321,
     "train_samples": 33257,
-    "train_samples_per_second": 4.984,
-    "train_steps_per_second": 0.156
+    "train_samples_per_second": 3.247,
+    "train_steps_per_second": 0.101
 }

runs/May02_23-38-27_COE-CS-sv003/events.out.tfevents.1714693383.COE-CS-sv003.638103.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fda9c07f5b0496556793e7734697c68d04ce88b76f23864ab4e351bbf772fe49
-size 47036
+oid sha256:5c42260416120d51da25f2c40c99e5062ed1c597eb57a0977ee5c91b4522251d
+size 49138

train_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
     "train_loss": 0.0,
-    "train_runtime": 6672.0976,
+    "train_runtime": 10243.5321,
     "train_samples": 33257,
-    "train_samples_per_second": 4.984,
-    "train_steps_per_second": 0.156
+    "train_samples_per_second": 3.247,
+    "train_steps_per_second": 0.101
 }

trainer_state.json

@@ -1467,19 +1467,19 @@
     {
       "epoch": 1.0,
       "eval_loss": NaN,
-      "eval_runtime": 181.3234,
-      "eval_samples_per_second": 12.74,
-      "eval_steps_per_second": 0.8,
+      "eval_runtime": 181.8174,
+      "eval_samples_per_second": 12.705,
+      "eval_steps_per_second": 0.798,
       "step": 1039
     },
     {
       "epoch": 1.0,
       "step": 1039,
-      "total_flos": 4818009365413888.0,
+      "total_flos": 5523816681832448.0,
       "train_loss": 0.0,
-      "train_runtime": 6672.0976,
-      "train_samples_per_second": 4.984,
-      "train_steps_per_second": 0.156
+      "train_runtime": 10243.5321,
+      "train_samples_per_second": 3.247,
+      "train_steps_per_second": 0.101
     }
   ],
   "logging_steps": 5,
@@ -1487,7 +1487,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1,
   "save_steps": 100,
-  "total_flos": 4818009365413888.0,
+  "total_flos": 5523816681832448.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null