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 sha256:89c702645daec1817939d822acf835483e73cef06758479cdc92245b1a4505bb
+size 501021625

runs/Jun28_02-41-02_f37ac0c0e53b/1656384073.1317828/events.out.tfevents.1656384073.f37ac0c0e53b.72.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c0d5c916a7f7cb80da35cb625f83e48e098932cb27f585c4426d8b3acbc4cb4
+size 5353

runs/Jun28_02-41-02_f37ac0c0e53b/events.out.tfevents.1656384073.f37ac0c0e53b.72.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fed5dbf21d490c19a05458e329309b54f004fc571e8189f3a12e6a9c15270d39
+size 3836

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ce522f4b54c51183e360b9652531fb60427e09975fc2839269d8795023d130
+size 3311