Training in progress, step 10

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ccore/ccore-125m-pt",
+  "_remove_final_layer_norm": false,
+  "activation_dropout": 0.0,
+  "activation_function": "relu",
+  "architectures": [
+    "OPTForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "do_layer_norm_before": true,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "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": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.3",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f050d89894c5e9908827811cfabef1376a351f8873d62fabce960db118d2d33c
+size 500979600

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d720bb086e5f47336dfcf3a0b5dd17fb9196b9c01594ebf8b1b11191be9a7f7a
+size 5304