End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.645493507385254,
+    "eval_runtime": 0.7735,
+    "eval_samples": 16,
+    "eval_samples_per_second": 11.636,
+    "eval_steps_per_second": 1.293,
     "total_flos": 8.08957492854784e+17,
     "train_loss": 1.2450406925521629,
     "train_runtime": 683.5001,

config.json

@@ -21,21 +21,6 @@
   "num_key_value_heads": 8,
   "pad_token_id": 128257,
   "pretraining_tp": 1,
-  "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-05,
   "rope_scaling": null,
   "rope_theta": 500000.0,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 1.0,
-    "eval_loss": 1.6479942798614502,
-    "eval_runtime": 1.1327,
+    "eval_loss": 1.645493507385254,
+    "eval_runtime": 0.7735,
     "eval_samples": 16,
-    "eval_samples_per_second": 7.945,
-    "eval_steps_per_second": 0.883
+    "eval_samples_per_second": 11.636,
+    "eval_steps_per_second": 1.293
 }

runs/Nov18_01-59-42_main-lora-llama3-8b-coding-0-0/events.out.tfevents.1731914877.main-lora-llama3-8b-coding-0-0.458.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:181ef51dbf16ceddc8a48ee5b0941fcdf79afbc540c165779b546392d79d081e
+size 359