Training in progress, step 500

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "facebook/opt-350m",
+  "_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": false,
+  "dropout": 0.1,
+  "enable_bias": true,
+  "eos_token_id": 2,
+  "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": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 1,
+  "prefix": "</s>",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c3774ac8bfd635ccd3b31197ef7c25f9cfceee69519a823689b140e8eb9a6f1
+size 1324830880

runs/Nov29_10-39-45_9738a80be8a8/events.out.tfevents.1701254398.9738a80be8a8.286.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d93edf48454dcad640d627f833370845b804c39b740e48cb02396c41f5ae471
+size 4938

runs/Nov29_11-17-26_9738a80be8a8/events.out.tfevents.1701256655.9738a80be8a8.286.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:698ef00e3eab2e672c88d8ddcaa65c1ef76b29260f5e35a587f7df884da66b84
+size 4507

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d3f98266c7d92274022b53dbea7502f3f1b337abe0b16f4f7a56a687cf03311e
+size 4600