End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9955156950672646,
+    "eval_loss": 2.3661022186279297,
+    "eval_runtime": 0.8106,
+    "eval_samples": 25,
+    "eval_samples_per_second": 25.906,
+    "eval_steps_per_second": 1.234,
     "total_flos": 6.554327132594504e+17,
     "train_loss": 1.8339371971181921,
     "train_runtime": 536.3339,

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": 0.9955156950672646,
-    "eval_loss": 2.371652841567993,
-    "eval_runtime": 1.1184,
+    "eval_loss": 2.3661022186279297,
+    "eval_runtime": 0.8106,
     "eval_samples": 25,
-    "eval_samples_per_second": 18.776,
-    "eval_steps_per_second": 0.894
+    "eval_samples_per_second": 25.906,
+    "eval_steps_per_second": 1.234
 }

runs/Nov18_05-54-20_main-lora-mistral7b-summarization-0-0/events.out.tfevents.1731928911.main-lora-mistral7b-summarization-0-0.456.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419163c9a7ec244fce8db0d46821743e4229fff7519e202ede119132c5a7e4bb
+size 354