End of training

README.md

@@ -4,6 +4,7 @@ library_name: transformers
 model_name: ox-llms-sula-10-profiles-sft
 tags:
 - generated_from_trainer
+- alignment-handbook
 - trl
 - sft
 licence: license

all_results.json

@@ -1,6 +1,14 @@
 {
     "entropy": 0.1506435771783193,
     "epoch": 1.0,
+    "eval_entropy": 0.14896515673398972,
+    "eval_loss": 0.148485004901886,
+    "eval_mean_token_accuracy": 0.9394213200569153,
+    "eval_num_tokens": 24937449.0,
+    "eval_runtime": 261.3303,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 19.133,
+    "eval_steps_per_second": 2.392,
     "mean_token_accuracy": 0.9381802678108215,
     "num_tokens": 24937449.0,
     "total_flos": 1.3805074115628892e+18,

config.json

@@ -0,0 +1,50 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "bfloat16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "bfloat16",
+    "bnb_4bit_quant_type": "nf4",
+    "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": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": true,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,11 @@
+{
+    "epoch": 1.0,
+    "eval_entropy": 0.14896515673398972,
+    "eval_loss": 0.148485004901886,
+    "eval_mean_token_accuracy": 0.9394213200569153,
+    "eval_num_tokens": 24937449.0,
+    "eval_runtime": 261.3303,
+    "eval_samples": 5000,
+    "eval_samples_per_second": 19.133,
+    "eval_steps_per_second": 2.392
+}