Training in progress, step 500

.gitignore

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

config.json

@@ -0,0 +1,35 @@
+{
+  "_name_or_path": "hf-internal-testing/tiny-random-gptj",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attention_probs_dropout_prob": 0.0,
+  "attn_pdrop": 0.0,
+  "bos_token_id": 98,
+  "embd_pdrop": 0.0,
+  "eos_token_id": 98,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.0,
+  "initializer_range": 0.02,
+  "intermediate_size": 37,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_ctx": 512,
+  "n_embd": 32,
+  "n_head": 4,
+  "n_inner": null,
+  "n_layer": 5,
+  "n_positions": 512,
+  "pad_token_id": 98,
+  "resid_pdrop": 0.0,
+  "rotary_dim": 4,
+  "scale_attn_weights": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.30.2",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1000
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8fff4e8d3b69cfb8f3ba4d7e5b71c5c9aa63e3e6e7f88ae2823c302d5611d21
+size 527254

runs/Jul09_21-55-06_00b24b3c4cc1/events.out.tfevents.1688939711.00b24b3c4cc1.480.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:005be86a5e4221da6dac0b1a5cc7f03600375bdecb4b833518df0635133acec4
+size 4325

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bafa1c9b6ea2b7ae82df232f1f5f2f3ba903ca1cf4d2326a075d652b35a6485d
+size 3963