End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 1.6531758308410645,
+    "eval_runtime": 1.3788,
+    "eval_samples": 518,
+    "eval_samples_per_second": 129.097,
+    "eval_steps_per_second": 2.176,
     "total_flos": 4.268849030789857e+17,
     "train_loss": 5.926357351030622,
     "train_runtime": 363.5109,

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": 1.6581236124038696,
-    "eval_runtime": 3.846,
+    "eval_loss": 1.6531758308410645,
+    "eval_runtime": 1.3788,
     "eval_samples": 518,
-    "eval_samples_per_second": 46.282,
-    "eval_steps_per_second": 0.78
+    "eval_samples_per_second": 129.097,
+    "eval_steps_per_second": 2.176
 }

runs/Nov17_22-39-49_main-lora-gemma7b-closedqa-0-0/events.out.tfevents.1731902154.main-lora-gemma7b-closedqa-0-0.457.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d2cd6a5a86de5ced56f1bc34f2eaf2730ab41633ad9f30ff002005d4355e455
+size 359