Training in progress, epoch 0

.gitignore

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

config.json

@@ -0,0 +1,43 @@
+{
+  "_name_or_path": "hivemind/gpt-j-6B-8bit",
+  "activation_function": "gelu_new",
+  "architectures": [
+    "GPTJForCausalLM"
+  ],
+  "attn_pdrop": 0.0,
+  "bos_token_id": 50256,
+  "eight_bit": true,
+  "embd_pdrop": 0.0,
+  "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,
+  "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": "float32",
+  "transformers_version": "4.14.1",
+  "use_cache": true,
+  "vocab_size": 50400
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e429e26ecbed483541cd2139b5a67519459fb00f5f02abedfe25ff920dd45b7d
+size 6177229767

runs/Jul15_05-56-23_4041f9702786/1657864593.2547476/events.out.tfevents.1657864593.4041f9702786.71.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e0bc1bf7d59918e8a98c9fbbe8dc927ac04c398600c3916d39161980554e32c
+size 4721

runs/Jul15_05-56-23_4041f9702786/events.out.tfevents.1657864593.4041f9702786.71.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a44a7922dcfdcc5818ef9f3c95cf88ac1109a64461bd0cb0b0d92cc3f13d1802
+size 3668

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c965fe38787e1fa4e7d4ad6d2ef3a4511123138cfadc2c6512b65726672c6956
+size 2927