Training in progress, step 250

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-125m",
+  "_name_or_path": "facebook/opt-350m",
   "_remove_final_layer_norm": false,
   "activation_dropout": 0.0,
   "activation_function": "relu",
@@ -8,24 +8,24 @@
   ],
   "attention_dropout": 0.0,
   "bos_token_id": 2,
-  "do_layer_norm_before": true,
+  "do_layer_norm_before": false,
   "dropout": 0.1,
   "enable_bias": true,
   "eos_token_id": 2,
-  "ffn_dim": 3072,
-  "hidden_size": 768,
+  "ffn_dim": 4096,
+  "hidden_size": 1024,
   "init_std": 0.02,
   "layer_norm_elementwise_affine": true,
   "layerdrop": 0.0,
   "max_position_embeddings": 2048,
   "model_type": "opt",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 12,
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
   "pad_token_id": 1,
   "prefix": "</s>",
   "torch_dtype": "float32",
-  "transformers_version": "4.42.4",
+  "transformers_version": "4.42.3",
   "use_cache": true,
   "vocab_size": 50272,
-  "word_embed_proj_dim": 768
+  "word_embed_proj_dim": 512
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d3d86d76e24291d5d7a343a784cda61b790708a342b2d2e18000174a05542bb0
-size 217446424
+oid sha256:b5272d332f499b8b178c5c6d2d67996a196bd7694a5bb06e3eb3f860de9340cd
+size 1324830880

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:80648db8d67445acad0e576fa124f071c50ea896247a73464339d0feb9d88ca3
+oid sha256:658df4e8795acd631d7d338d911d064f2f91efab5c4d5791fcb6743da217b67c
 size 5112