Training in progress, step 300

config.json

@@ -1,26 +1,30 @@
 {
-  "_name_or_path": "bert-base-uncased",
+  "_name_or_path": "/content/drive/MyDrive/klmmm/models/quantumaikr/llama3.1",
   "architectures": [
-    "BertForQuestionAnswering"
+    "LlamaForCausalLM"
   ],
-  "attention_probs_dropout_prob": 0.1,
-  "classifier_dropout": null,
-  "gradient_checkpointing": false,
-  "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 768,
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "layer_norm_eps": 1e-12,
-  "max_position_embeddings": 512,
-  "model_type": "bert",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
-  "pad_token_id": 0,
-  "position_embedding_type": "absolute",
+  "intermediate_size": 1331,
+  "max_position_embeddings": 1024,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
-  "type_vocab_size": 2,
   "use_cache": true,
-  "vocab_size": 30522
+  "use_scaled_rope": true,
+  "vocab_size": 128257
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5812ef6b7074c619a3bc60a644890e722532a162cf49f9cef8783b0d7b9b8996
-size 435596088
+oid sha256:77410675a0feecd71e45bcae8374b06a1363f6e9b4ede4a62e25a701941fea42
+size 1315819888

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b8a4bda985f645acb6b21766b743961a89e1a2136e6b082230b32699707a8c0
+oid sha256:f4960969a0d6e87156ea5f94fc85982f03f95f63ba30aab922b08d42952bf850
 size 5176