Training in progress, step 500

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

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": "4.27.4",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 512
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2fe64222dd2384d42c7ec49e68e4fe2c9c66955ecdae599de9e5bb30f30dd4b
+size 1324917277

runs/Apr13_13-45-00_8cf6d02e9381/1681393537.1182258/events.out.tfevents.1681393537.8cf6d02e9381.692.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fcaf90e46cdfb11f1ed2ded441fdeb5b3537822d4f48369b6576857902d00eb
+size 5829

runs/Apr13_13-45-00_8cf6d02e9381/events.out.tfevents.1681393537.8cf6d02e9381.692.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:270088b9171befb70c5e9bd04cc71f06a4bf67fbbb751ef9b24cd0795f8f7119
+size 4239

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e300ca0d7977660eeabcfa0fdebad9110011433e5157cfe711876aa5ca554684
+size 3579