Training in progress, step 500

config.json

@@ -6,19 +6,19 @@
   "attention_dropout": 0.0,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "head_dim": 32,
+  "head_dim": 24,
   "hidden_act": "silu",
-  "hidden_size": 512,
+  "hidden_size": 768,
   "initializer_range": 0.02,
   "intermediate_size": 3072,
   "max_position_embeddings": 512,
   "model_type": "mistral",
-  "num_attention_heads": 16,
-  "num_hidden_layers": 4,
+  "num_attention_heads": 32,
+  "num_hidden_layers": 8,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-06,
   "rope_theta": 10000.0,
-  "sliding_window": 512,
+  "sliding_window": 768,
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.47.1",

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34315d6c3e77edfad0a982fd9a6dfa61578954d06a764dcc1f3825972e1e0690
-size 219175120
+oid sha256:f7f278fd0bc9378fcfd186f96290b076ea2e273c4c7ce8f3248f3086e51c76da
+size 470346864

runs/Feb03_01-58-06_8cd379374342/events.out.tfevents.1738547887.8cd379374342.3480.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4582d84216cdb52988da3d35565d1004498bea05b2475c43ccc7c87b69aace43
+size 5376

runs/Feb03_02-19-59_8cd379374342/events.out.tfevents.1738549200.8cd379374342.26879.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7e16fb8c99d9ca6abc16dec86b9f8871dccdd16a6efe31268839280c9b84ff
+size 5587

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23efedec6815b0900a0bdb9d70e54dacef91ee9e64bc40b9a849f13a3025bbb4
+oid sha256:f21776f4c29b94ab92e23ef871c951e1d197af172d7a99669a41c9c0cd84ee18
 size 5624