Training in progress, epoch 1

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "ccore/RDW2",
+  "_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": "4.47.0",
+  "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:ee3736a25dbcc9b207fc6fdb0c8a647d950c3ce6f1a145e153c8c7b3b93e6ed8
+size 500979600

runs/Feb03_01-40-40_3fb1c821c32a/events.out.tfevents.1738546841.3fb1c821c32a.31.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47f37f9e15378c6c56a9ee2b355ec32a69372f068ce06c9bd8c338881f8e51b1
+size 4184

runs/Feb03_01-41-54_3fb1c821c32a/events.out.tfevents.1738546915.3fb1c821c32a.126.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bc058136647f668b31c1625dd10cf05ff30435b5581ba9b97085f9728bf915bb
+size 5426

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31f22821782aca67d338e1823b7f496089c77ceecc8d826268eb2241f6e78788
+size 5368