End of training

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 0.994535519125683,
+    "eval_loss": 1.7210174798965454,
+    "eval_runtime": 1.2122,
+    "eval_samples": 518,
+    "eval_samples_per_second": 143.546,
+    "eval_steps_per_second": 1.65,
     "total_flos": 4.03002565094015e+17,
     "train_loss": 1.799644404715234,
     "train_runtime": 332.7348,

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": 0.994535519125683,
-    "eval_loss": 14.016096115112305,
-    "eval_runtime": 2.0922,
+    "eval_loss": 1.7210174798965454,
+    "eval_runtime": 1.2122,
     "eval_samples": 518,
-    "eval_samples_per_second": 83.167,
-    "eval_steps_per_second": 0.956
+    "eval_samples_per_second": 143.546,
+    "eval_steps_per_second": 1.65
 }

runs/Nov18_08-12-16_main-pissa-llama-alpaca-0-0/events.out.tfevents.1731937818.main-pissa-llama-alpaca-0-0.457.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac7b2f35777faea1e7016c1f48df492fdf201df9abc0c98fec34c9e66b867a02
+size 354