End of training

README.md

@@ -5,6 +5,7 @@ tags:
 - trl
 - sft
 - generated_from_trainer
+- alignment-handbook
 model-index:
 - name: eeve-2.8B_C
   results: []

all_results.json

@@ -1,5 +1,10 @@
 {
     "epoch": 1.0,
+    "eval_loss": 0.39601820707321167,
+    "eval_runtime": 1.5467,
+    "eval_samples": 230,
+    "eval_samples_per_second": 148.707,
+    "eval_steps_per_second": 6.466,
     "total_flos": 1.933383782157517e+16,
     "train_loss": 0.43378888076978694,
     "train_runtime": 303.3238,

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "yanolja/EEVE-Korean-Instruct-2.8B-v1.0",
+  "architectures": [
+    "PhiForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "auto_map": {
+    "AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
+    "AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
+  },
+  "bos_token_id": 58940,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 58943,
+  "hidden_act": "gelu_new",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 2048,
+  "model_type": "phi",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "partial_rotary_factor": 0.4,
+  "qk_layernorm": false,
+  "resid_pdrop": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 58944
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.39601820707321167,
+    "eval_runtime": 1.5467,
+    "eval_samples": 230,
+    "eval_samples_per_second": 148.707,
+    "eval_steps_per_second": 6.466
+}