Training in progress, step 250

config.json

@@ -1,7 +1,5 @@
 {
-  "_name_or_path": "model",
   "_remove_final_layer_norm": false,
-  "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
     "OPTForCausalLM"
@@ -13,19 +11,19 @@
   "enable_bias": true,
   "eos_token_id": 2,
   "ffn_dim": 3072,
-  "hidden_size": 768,
+  "hidden_size": 512,
   "init_std": 0.02,
+  "intermediate_size": 512,
   "layer_norm_elementwise_affine": true,
   "layerdrop": 0.0,
-  "max_position_embeddings": 2048,
+  "max_position_embeddings": 1024,
   "model_type": "opt",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 2,
+  "num_hidden_layers": 4,
   "pad_token_id": 1,
-  "prefix": "</s>",
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.47.1",
   "use_cache": true,
-  "vocab_size": 50272,
-  "word_embed_proj_dim": 768
+  "vocab_size": 50265,
+  "word_embed_proj_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37406652f6881dafaf193b1ec38ca05185470cbb8dbff6b845a87a685b0191ea
-size 500979600
+oid sha256:3a052d9f5367ad285d6a2dc7afd29e632c497c01663b1e3c474e7ed5d85de02d
+size 172287576

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ab0e5fc519391346ca91f46fb29b33fbb3ba22d2492bd0622f23f317bd42d60
+size 5304