Training in progress, step 1000

config.json

@@ -1,7 +1,5 @@
 {
-  "_name_or_path": "facebook/opt-125m",
   "_remove_final_layer_norm": false,
-  "activation_dropout": 0.0,
   "activation_function": "relu",
   "architectures": [
     "OPTForCausalLM"
@@ -12,20 +10,19 @@
   "dropout": 0.1,
   "enable_bias": true,
   "eos_token_id": 2,
-  "ffn_dim": 3072,
-  "hidden_size": 768,
+  "ffn_dim": 512,
+  "hidden_size": 256,
   "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": 2,
+  "num_hidden_layers": 4,
   "pad_token_id": 1,
-  "prefix": "</s>",
   "torch_dtype": "float32",
   "transformers_version": "4.42.4",
   "use_cache": true,
-  "vocab_size": 50272,
-  "word_embed_proj_dim": 768
+  "vocab_size": 50265,
+  "word_embed_proj_dim": 256
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b00f1e99410e83225955f691179166e02e35fa62d9698bff3b15dedae8bbafd
-size 500979600
+oid sha256:1e1f48148b128785941b6f9cb0bd73013e4cf73f6eef0d3c698adfb6da7c02a1
+size 62013896

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27d6d579cc7b5769d9826ba14c0c95626a70e6009f76aac0e14196ab8ee13de6
+oid sha256:1ef461fb370e080f40e9c6c5d5b49ab5fb711afa9a896465203446818d1a4924
 size 5112