Training in progress, step 157

config.json

@@ -4,29 +4,27 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 3,
-  "head_dim": 64,
+  "bos_token_id": 1,
+  "eos_token_id": 32001,
+  "head_dim": 32,
   "hidden_act": "silu",
-  "hidden_size": 576,
-  "initializer_range": 0.041666666666666664,
-  "intermediate_size": 1536,
-  "is_llama_config": true,
-  "max_position_embeddings": 4096,
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "max_position_embeddings": 8192,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 9,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 3,
-  "pad_token_id": 1,
+  "num_attention_heads": 8,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "pad_token_id": 32003,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_interleaved": false,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 100000,
+  "rope_theta": 10000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
   "transformers_version": "4.52.4",
   "use_cache": true,
-  "vocab_size": 32000
+  "vocab_size": 32018
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaaf5bd62a28c1e2ea35ce725cd2e608c582aac986ca5bba4639e77aa9701515
-size 498572168
+oid sha256:d9e511a89a68110f896a7373f812fd6041629cc471887aabcda85447c7031f28
+size 78437072

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:02a35e277ab5aa892680510168973e0c935efdcd186a619b19b5aaf90d144b98
+oid sha256:5b9edc82518a3363d37477942c413c134ab6b8f4032a4f60942c01d82a0577ef
 size 5713