Training in progress, step 100

config.json

@@ -11,18 +11,18 @@
   "enable_bias": true,
   "eos_token_id": 2,
   "ffn_dim": 512,
-  "hidden_size": 256,
+  "hidden_size": 512,
   "init_std": 0.02,
   "layer_norm_elementwise_affine": true,
   "layerdrop": 0.0,
   "max_position_embeddings": 2048,
   "model_type": "opt",
   "num_attention_heads": 2,
-  "num_hidden_layers": 4,
+  "num_hidden_layers": 1,
   "pad_token_id": 1,
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
   "use_cache": true,
   "vocab_size": 50265,
-  "word_embed_proj_dim": 256
+  "word_embed_proj_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e1f48148b128785941b6f9cb0bd73013e4cf73f6eef0d3c698adfb6da7c02a1
-size 62013896
+oid sha256:40a53ebed8dd89fc2c4f6cb6c0a373650454884f91ece046278453e113559da0
+size 113459440

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ef461fb370e080f40e9c6c5d5b49ab5fb711afa9a896465203446818d1a4924
+oid sha256:8a1f3b79f703c8a3fb21de91388dd6842387489de9fd8c556eb9a2448f97d062
 size 5112