Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "facebook/opt-125m",
+  "_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,
+  "eos_token_id": 2,
+  "ffn_dim": 3072,
+  "hidden_size": 768,
+  "init_std": 0.02,
+  "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": "4.20.1",
+  "use_cache": true,
+  "vocab_size": 50272,
+  "word_embed_proj_dim": 768
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96e77eed0d9a8e3d254ffddd4f31e4ee79441a0552d5b37b2b62eab3d7ba6bc8
+size 501021625

runs/Jun29_08-46-46_bdbd7f19b710/1656492453.035742/events.out.tfevents.1656492453.bdbd7f19b710.71.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980f7ecbf8f22b9736f6f606aff5fabecbe7770bdd8659534e1be41a768dec95
+size 5329

runs/Jun29_08-46-46_bdbd7f19b710/events.out.tfevents.1656492453.bdbd7f19b710.71.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1a4da62d7634e25696888f4fabd9d78072ca3a340b23009553aec8a988457b4
+size 3812

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94dfb7766737888a0be8a64fc57a958f9512920f4fc9844aa5c3c259754d284b
+size 3311