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 sha256:6ed7f10a6e743755e9c7f5ad6d33c069bfa13566baa8174f5bc522e49127edd3
+size 501021625

runs/Jul01_15-30-28_f465c63b53c7/1656689465.0202634/events.out.tfevents.1656689465.f465c63b53c7.73.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:50631ac2c68849d850fd99e6dd0e83a428ea0a767c95314ba2e97dfbbe2fb607
+size 5329

runs/Jul01_15-30-28_f465c63b53c7/events.out.tfevents.1656689465.f465c63b53c7.73.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:daace654598c718bc3b21b53f67c67bab822c8660e2fdb928724ec75566371d5
+size 3812

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f5178ae4485331340fbccb84eca92330574c10316d4b9e9a03da55a31d51347
+size 3311