Training in progress, step 2106

config.json

@@ -7,24 +7,24 @@
   "attention_dropout": 0.0,
   "bos_token_id": 0,
   "eos_token_id": 1,
-  "head_dim": 64,
+  "head_dim": 96,
   "hidden_act": "silu",
-  "hidden_size": 768,
+  "hidden_size": 1152,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
+  "intermediate_size": 4606,
   "max_position_embeddings": 1024,
   "mlp_bias": false,
   "model_type": "llama",
   "num_attention_heads": 12,
-  "num_hidden_layers": 8,
+  "num_hidden_layers": 6,
   "num_key_value_heads": 12,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-05,
   "rope_scaling": null,
-  "rope_theta": 10000.0,
+  "rope_theta": 100000.0,
   "tie_word_embeddings": true,
   "torch_dtype": "float32",
-  "transformers_version": "4.47.1",
+  "transformers_version": "4.48.0",
   "use_cache": true,
   "vocab_size": 32000
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8aa7cf29a822c424b57bfa572124245a0bd21a4d923b365529a1909b12a6dbde
-size 400354320
+oid sha256:c9bbeffb2f75bcfd1493328b33805c1489ad1a4b84f4f17093aa60d0a39d7f75
+size 656964248

runs/Jan16_10-04-32_81d9b8b5d266/events.out.tfevents.1737021888.81d9b8b5d266.5048.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62fd5b186105f5e4fa615b7d0964690715022f22f4a8365941dce8a1b3622a98
+size 6528

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7bab04bdbb78406b6f7f0ccef4c41bfa01d652e7c3f661bb9abaca06dd7f1b2
+oid sha256:025e2621120e83cc33d71bb1e585461898928e831529528f39307f75e68a4ac9
 size 5368