Training in progress, epoch 1

.gitignore

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

config.json

@@ -0,0 +1,46 @@
+{
+  "_name_or_path": "ydshieh/tiny-random-gptj-for-sequence-classification",
+  "activation_function": "gelu_new",
+  "adapters": {
+    "adapters": {},
+    "config_map": {},
+    "fusion_config_map": {},
+    "fusions": {}
+  },
+  "architectures": [
+    "GPTJForSequenceClassification"
+  ],
+  "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,
+  "id2label": {
+    "0": "human",
+    "1": "ia"
+  },
+  "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,
+  "problem_type": "single_label_classification",
+  "resid_pdrop": 0.0,
+  "rotary_dim": 8,
+  "scale_attn_weights": true,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "type_vocab_size": 16,
+  "use_cache": true,
+  "vocab_size": 1000
+}

logs/1698604205.894863/events.out.tfevents.1698604205.3c8bd734edab.639.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a57c83e6dbcec408926486d95679a920b5797de14ce0b0989ad3b7fbc517f366
+size 5781

logs/events.out.tfevents.1698604205.3c8bd734edab.639.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1724835abccc49786f313efbb8242a0e50701fa92ec260a83ab334fe878207
+size 64403

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a4885f3f3841c78fb89660ecc318557c041ad9812df49775857851b7d0d9b1b
+size 1710382

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db23d81a513035473c31a32064a4a2c7427ce1346dc0d36a951322809934d6b2
+size 4024