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_21-52-15_97e0c61da3e4/1656453156.7034686/events.out.tfevents.1656453156.97e0c61da3e4.1685.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41f90424fa28a91ca4bbc589611921d54da4555ba3833af15e115b530a7b95b9
+size 5323

runs/Jun28_21-52-15_97e0c61da3e4/events.out.tfevents.1656453156.97e0c61da3e4.1685.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:020cdeb73cb89519c17faa85f513057a820191f4a848ebf4df57203f455532e4
+size 3806

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34886d8947c8af9784b614dd25cdb1c8ad0b5a374f4646be80af2c58ce917975
+size 3311