Upload 4 files

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 2.9975203684024088,
+    "eval_loss": 0.2459680587053299,
+    "eval_runtime": 3.7764,
+    "eval_samples_per_second": 24.097,
+    "eval_steps_per_second": 6.091,
+    "total_flos": 537684003520512.0,
+    "train_loss": 0.17504471952963102,
+    "train_runtime": 40706.3571,
+    "train_samples_per_second": 6.656,
+    "train_steps_per_second": 0.052
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/home/jzgrp/wangning/VeriSeek/checkpoints/deepseek-coder-7b-instruct-v1.5",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 32,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 102400
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 2.9975203684024088,
+    "eval_loss": 0.2459680587053299,
+    "eval_runtime": 3.7764,
+    "eval_samples_per_second": 24.097,
+    "eval_steps_per_second": 6.091
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100015,
+  "transformers_version": "4.46.1"
+}