End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.6534239053726196,
+    "eval_runtime": 0.4896,
+    "eval_samples": 16,
+    "eval_samples_per_second": 20.425,
+    "eval_steps_per_second": 2.042,
     "total_flos": 9.17802542639874e+17,
     "train_loss": 2.9511482283918564,
     "train_runtime": 778.9577,

config.json

@@ -20,21 +20,6 @@
   "num_hidden_layers": 28,
   "num_key_value_heads": 16,
   "pad_token_id": 0,
-  "quantization_config": {
-    "_load_in_4bit": false,
-    "_load_in_8bit": true,
-    "bnb_4bit_compute_dtype": "float32",
-    "bnb_4bit_quant_storage": "uint8",
-    "bnb_4bit_quant_type": "fp4",
-    "bnb_4bit_use_double_quant": false,
-    "llm_int8_enable_fp32_cpu_offload": false,
-    "llm_int8_has_fp16_weight": false,
-    "llm_int8_skip_modules": null,
-    "llm_int8_threshold": 6.0,
-    "load_in_4bit": false,
-    "load_in_8bit": true,
-    "quant_method": "bitsandbytes"
-  },
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 10000.0,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.6543629169464111,
-    "eval_runtime": 1.2677,
+    "eval_loss": 1.6534239053726196,
+    "eval_runtime": 0.4896,
     "eval_samples": 16,
-    "eval_samples_per_second": 7.888,
-    "eval_steps_per_second": 0.789
+    "eval_samples_per_second": 20.425,
+    "eval_steps_per_second": 2.042
 }

runs/Nov18_01-59-33_main-lora-gemma7b-coding-0-0/events.out.tfevents.1731914667.main-lora-gemma7b-coding-0-0.458.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c830858e9624af95bacdf257c53d0f004a331d374759b23cc6c189c5b8abef1d
+size 359