Training in progress, step 100

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "ccore/opt_rt",
+  "_name_or_path": "ccore/opt-125-nh",
   "_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": false,
+  "do_layer_norm_before": true,
   "dropout": 0.1,
   "enable_bias": true,
   "eos_token_id": 2,
-  "ffn_dim": 4096,
-  "hidden_size": 1024,
+  "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": 16,
-  "num_hidden_layers": 24,
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
   "pad_token_id": 1,
   "prefix": "</s>",
   "torch_dtype": "float32",
   "transformers_version": "4.42.3",
   "use_cache": true,
   "vocab_size": 50272,
-  "word_embed_proj_dim": 512
+  "word_embed_proj_dim": 768
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23869810be220a96427420faa4a1f36b33702210824a4813f2f0460b3d6b6f5d
-size 1324830880
+oid sha256:d35acb1dc6ad14aeec3ca1f5d5f123b26cc6b7a6b11008d073eecc2c00edfa36
+size 500979600

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:642e3e7a578c8e7cee6a164865f1231874e86eea43365b6e12ffb4352d6f6f11
+oid sha256:7e907d1be63dec6983ced97ec102dff58a1451cc2ca05435f339a856607e473c
 size 5112