Training in progress, step 400

config.json

@@ -1,5 +1,7 @@
 {
+  "_name_or_path": "facebook/opt-125m",
   "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
     "OPTForCausalLM"
@@ -10,19 +12,20 @@
   "dropout": 0.1,
   "enable_bias": true,
   "eos_token_id": 2,
-  "ffn_dim": 512,
-  "hidden_size": 512,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
   "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": 1,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
+  "prefix": "</s>",
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
   "use_cache": true,
-  "vocab_size": 50265,
-  "word_embed_proj_dim": 512
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40a53ebed8dd89fc2c4f6cb6c0a373650454884f91ece046278453e113559da0
-size 113459440
+oid sha256:5ae8d759d4ada99aef5934a5b42b46745dc10a32a364ce05b447f79544c1c938
+size 217446424

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a1f3b79f703c8a3fb21de91388dd6842387489de9fd8c556eb9a2448f97d062
+oid sha256:80648db8d67445acad0e576fa124f071c50ea896247a73464339d0feb9d88ca3
 size 5112