End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.9970326409495549,
+    "eval_loss": 1.8814080953598022,
+    "eval_runtime": 0.6678,
+    "eval_samples": 15,
+    "eval_samples_per_second": 20.965,
+    "eval_steps_per_second": 1.498,
     "total_flos": 8.227900459906499e+17,
     "train_loss": 1.2773614100047521,
     "train_runtime": 661.1188,

config.json

@@ -18,21 +18,6 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "pad_token_id": 32769,
-  "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_theta": 1000000.0,
   "sliding_window": null,

eval_results.json

@@ -1,8 +1,8 @@
 {
     "epoch": 0.9970326409495549,
-    "eval_loss": 1.881588339805603,
-    "eval_runtime": 1.5168,
+    "eval_loss": 1.8814080953598022,
+    "eval_runtime": 0.6678,
     "eval_samples": 15,
-    "eval_samples_per_second": 9.23,
-    "eval_steps_per_second": 0.659
+    "eval_samples_per_second": 20.965,
+    "eval_steps_per_second": 1.498
 }

runs/Nov18_07-26-21_main-lora-mistral7b-closedqa-0-0/events.out.tfevents.1731934199.main-lora-mistral7b-closedqa-0-0.457.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e40b3a0bda2c227c5f0792f215bcd283a39e665f68a8eadc42458ddf94e8611
+size 359