Training in progress, step 5000

.gitignore

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

config.json

@@ -0,0 +1,44 @@
+{
+  "_name_or_path": "EleutherAI/gpt-j-6b",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "embd_pdrop": 0.0,
+  "end_token_id": 50256,
+  "eos_token_id": 50256,
+  "gradient_checkpointing": false,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "model_type": "gptj",
+  "n_embd": 4096,
+  "n_head": 16,
+  "n_inner": null,
+  "n_layer": 28,
+  "n_positions": 2048,
+  "pad_token_id": 50256,
+  "resid_pdrop": 0.0,
+  "rotary": true,
+  "rotary_dim": 64,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "task_specific_params": {
+    "text-generation": {
+      "do_sample": true,
+      "max_length": 50,
+      "temperature": 1.0
+    }
+  },
+  "tie_word_embeddings": false,
+  "tokenizer_class": "GPT2Tokenizer",
+  "torch_dtype": "float16",
+  "transformers_version": "4.30.2",
+  "use_cache": false,
+  "vocab_size": 50400
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:459bc0a0f2d2c157d759c496e35fa849c93f16e4ace394e9bca4be70edad700a
+size 12101802917

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:81c33d389f30a848837921f29f63a7a5046b4c5dc365f284a4473a9a49280d9a
+size 5307