Training in progress, step 500, checkpoint

checkpoint-500/config.json

@@ -1,35 +1,36 @@
 {
-  "_name_or_path": "klue/roberta-large",
+  "_name_or_path": "EleutherAI/polyglot-ko-1.3b",
   "architectures": [
-    "RobertaForSequenceClassification"
+    "GPTNeoXForSequenceClassification"
   ],
-  "attention_probs_dropout_prob": 0.1,
+  "attention_dropout": 0.0,
   "bos_token_id": 0,
-  "classifier_dropout": null,
+  "classifier_dropout": 0.1,
   "eos_token_id": 2,
-  "gradient_checkpointing": false,
   "hidden_act": "gelu",
-  "hidden_dropout_prob": 0.1,
-  "hidden_size": 1024,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2048,
   "id2label": {
     "0": "LABEL_0"
   },
   "initializer_range": 0.02,
-  "intermediate_size": 4096,
+  "intermediate_size": 8192,
   "label2id": {
     "LABEL_0": 0
   },
   "layer_norm_eps": 1e-05,
-  "max_position_embeddings": 514,
-  "model_type": "roberta",
+  "max_position_embeddings": 2048,
+  "model_type": "gpt_neox",
   "num_attention_heads": 16,
   "num_hidden_layers": 24,
   "pad_token_id": 2,
-  "position_embedding_type": "absolute",
-  "tokenizer_class": "BertTokenizer",
+  "rope_scaling": null,
+  "rotary_emb_base": 10000,
+  "rotary_pct": 0.5,
+  "tie_word_embeddings": false,
   "torch_dtype": "float32",
-  "transformers_version": "4.34.1",
-  "type_vocab_size": 1,
+  "transformers_version": "4.35.0",
   "use_cache": true,
-  "vocab_size": 32000
+  "use_parallel_residual": true,
+  "vocab_size": 30080
 }

checkpoint-500/model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bbd718c4f0c085e70942418a2494d1a62c2901686acf597119d1049904992fc
+size 4946584368

checkpoint-500/model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fc12eb365aecfc1d76a911e90dd2e728d5147b59fd18574ebd3752e607881f
+size 134284024

checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,299 @@
+{
+  "metadata": {
+    "total_size": 5080834048
+  },
+  "weight_map": {
+    "gpt_neox.embed_in.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.final_layer_norm.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.final_layer_norm.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_4h_to_h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.bias": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.mlp.dense_h_to_4h.weight": "model-00002-of-00002.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.dense.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.dense.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.attention.query_key_value.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_4h_to_h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.mlp.dense_h_to_4h.weight": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "gpt_neox.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba251489adc241ca5b80fc76223ef4d3da0cb383b4ce2e38e1b6df12e553a82f
-size 2693490618
+oid sha256:926bb3aef06c5609c7308f2d46db2ee0fb9ea437131f4ffd29edd00f2d03d539
+size 10161845830

checkpoint-500/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ebeff58a949a84383d357f1360894c8fa9939d4e472a24cc74450ae4313a4bb
+oid sha256:2c8c1979a903366056f816dfa903e1707fbe02269ee67fd5bd4bb542c4208efb
 size 14308

checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcc61220c925006e8916e7b98f3b9bf9ef82f46341cb3d17973ccd33d25c46fd
+oid sha256:d6029ac3959ee0fadaf809d0bf6b733bc78923be1e2e07f3208c2bc6b170808a
 size 1064

checkpoint-500/special_tokens_map.json

@@ -1,9 +1,11 @@
 {
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "unk_token": "[UNK]"
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
+  "eos_token": "<|endoftext|>",
+  "pad_token": "<|endoftext|>"
 }

checkpoint-500/tokenizer_config.json

@@ -1,7 +1,7 @@
 {
   "added_tokens_decoder": {
     "0": {
-      "content": "[CLS]",
+      "content": "<|unused0|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -9,7 +9,7 @@
       "special": true
     },
     "1": {
-      "content": "[PAD]",
+      "content": "<|unused1|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -17,7 +17,7 @@
       "special": true
     },
     "2": {
-      "content": "[SEP]",
+      "content": "<|endoftext|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -25,15 +25,31 @@
       "special": true
     },
     "3": {
-      "content": "[UNK]",
+      "content": "<|sep|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
       "single_word": false,
       "special": true
     },
-    "4": {
-      "content": "[MASK]",
+    "30000": {
+      "content": "<|acc|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30001": {
+      "content": "<|tel|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "30002": {
+      "content": "<|rrn|>",
       "lstrip": false,
       "normalized": false,
       "rstrip": false,
@@ -41,19 +57,16 @@
       "special": true
     }
   },
-  "bos_token": "[CLS]",
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<|sep|>",
+    "<|acc|>",
+    "<|tel|>",
+    "<|rrn|>"
+  ],
   "clean_up_tokenization_spaces": true,
-  "cls_token": "[CLS]",
-  "do_basic_tokenize": true,
-  "do_lower_case": false,
-  "eos_token": "[SEP]",
-  "mask_token": "[MASK]",
-  "model_max_length": 512,
-  "never_split": null,
-  "pad_token": "[PAD]",
-  "sep_token": "[SEP]",
-  "strip_accents": null,
-  "tokenize_chinese_chars": true,
-  "tokenizer_class": "BertTokenizer",
-  "unk_token": "[UNK]"
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "PreTrainedTokenizerFast"
 }

checkpoint-500/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7620789513793629,
-  "eval_steps": 100,
+  "epoch": 0.2455795677799607,
+  "eval_steps": 500,
   "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
@@ -10,354 +10,78 @@
   "log_history": [
     {
       "epoch": 0.02,
-      "learning_rate": 8.99484069051768e-06,
-      "loss": 0.672,
-      "step": 10
-    },
-    {
-      "epoch": 0.03,
-      "learning_rate": 8.979374592503753e-06,
-      "loss": 0.393,
-      "step": 20
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 8.953637170129838e-06,
-      "loss": 0.1594,
-      "step": 30
-    },
-    {
-      "epoch": 0.06,
-      "learning_rate": 8.917687439985847e-06,
-      "loss": 0.122,
-      "step": 40
-    },
-    {
-      "epoch": 0.08,
-      "learning_rate": 8.87160783575339e-06,
-      "loss": 0.0956,
+      "learning_rate": 8.999464304375242e-06,
+      "loss": 0.7019,
       "step": 50
     },
     {
-      "epoch": 0.09,
-      "learning_rate": 8.815504019183158e-06,
-      "loss": 0.102,
-      "step": 60
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 8.749504637809742e-06,
-      "loss": 0.0888,
-      "step": 70
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 8.673761029959426e-06,
-      "loss": 0.097,
-      "step": 80
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 8.588446877727417e-06,
-      "loss": 0.0968,
-      "step": 90
-    },
-    {
-      "epoch": 0.15,
-      "learning_rate": 8.493757808720196e-06,
-      "loss": 0.0808,
-      "step": 100
-    },
-    {
-      "epoch": 0.15,
-      "eval_accuracy": 0.0,
-      "eval_loss": 3.0685205274494365e-05,
-      "eval_runtime": 30.877,
-      "eval_samples_per_second": 141.659,
-      "eval_steps_per_second": 23.61,
+      "epoch": 0.05,
+      "learning_rate": 8.997857345043108e-06,
+      "loss": 0.6739,
       "step": 100
     },
     {
-      "epoch": 0.17,
-      "learning_rate": 8.389910947476252e-06,
-      "loss": 0.0797,
-      "step": 110
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 8.277144417593776e-06,
-      "loss": 0.0933,
-      "step": 120
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 8.155716795706948e-06,
-      "loss": 0.084,
-      "step": 130
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 8.02590651856289e-06,
-      "loss": 0.0605,
-      "step": 140
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 7.88801124455883e-06,
-      "loss": 0.0746,
+      "epoch": 0.07,
+      "learning_rate": 8.99517950459963e-06,
+      "loss": 0.6677,
       "step": 150
     },
     {
-      "epoch": 0.24,
-      "learning_rate": 7.742347171203542e-06,
-      "loss": 0.1016,
-      "step": 160
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 7.589248310068091e-06,
-      "loss": 0.0919,
-      "step": 170
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 7.429065720888471e-06,
-      "loss": 0.1076,
-      "step": 180
-    },
-    {
-      "epoch": 0.29,
-      "learning_rate": 7.262166706576352e-06,
-      "loss": 0.0586,
-      "step": 190
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 7.088933970983793e-06,
-      "loss": 0.0682,
+      "epoch": 0.1,
+      "learning_rate": 8.99143142060366e-06,
+      "loss": 0.6625,
       "step": 200
     },
     {
-      "epoch": 0.3,
-      "eval_accuracy": 0.0,
-      "eval_loss": 9.85040060186293e-06,
-      "eval_runtime": 31.5055,
-      "eval_samples_per_second": 138.833,
-      "eval_steps_per_second": 23.139,
-      "step": 200
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 6.909764741353188e-06,
-      "loss": 0.069,
-      "step": 210
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 6.7250698574647064e-06,
-      "loss": 0.0483,
-      "step": 220
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 6.5352728295698045e-06,
-      "loss": 0.0639,
-      "step": 230
-    },
-    {
-      "epoch": 0.37,
-      "learning_rate": 6.340808867271031e-06,
-      "loss": 0.0865,
-      "step": 240
-    },
-    {
-      "epoch": 0.38,
-      "learning_rate": 6.142123881574899e-06,
-      "loss": 0.0861,
+      "epoch": 0.12,
+      "learning_rate": 8.98661398542506e-06,
+      "loss": 0.6649,
       "step": 250
     },
     {
-      "epoch": 0.4,
-      "learning_rate": 5.939673462406165e-06,
-      "loss": 0.0805,
-      "step": 260
-    },
-    {
-      "epoch": 0.41,
-      "learning_rate": 5.7339218339280815e-06,
-      "loss": 0.0751,
-      "step": 270
-    },
-    {
-      "epoch": 0.43,
-      "learning_rate": 5.52534079006412e-06,
-      "loss": 0.0687,
-      "step": 280
-    },
-    {
-      "epoch": 0.44,
-      "learning_rate": 5.314408612662028e-06,
-      "loss": 0.092,
-      "step": 290
-    },
-    {
-      "epoch": 0.46,
-      "learning_rate": 5.101608974780918e-06,
-      "loss": 0.0718,
-      "step": 300
-    },
-    {
-      "epoch": 0.46,
-      "eval_accuracy": 0.0,
-      "eval_loss": 7.04687363395351e-06,
-      "eval_runtime": 30.7873,
-      "eval_samples_per_second": 142.071,
-      "eval_steps_per_second": 23.679,
+      "epoch": 0.15,
+      "learning_rate": 8.980728346032255e-06,
+      "loss": 0.6528,
       "step": 300
     },
     {
-      "epoch": 0.47,
-      "learning_rate": 4.887429831616148e-06,
-      "loss": 0.0556,
-      "step": 310
-    },
-    {
-      "epoch": 0.49,
-      "learning_rate": 4.67236230160516e-06,
-      "loss": 0.0825,
-      "step": 320
-    },
-    {
-      "epoch": 0.5,
-      "learning_rate": 4.456899540279919e-06,
-      "loss": 0.0355,
-      "step": 330
-    },
-    {
-      "epoch": 0.52,
-      "learning_rate": 4.2415356094482455e-06,
-      "loss": 0.0572,
-      "step": 340
-    },
-    {
-      "epoch": 0.53,
-      "learning_rate": 4.026764344297024e-06,
-      "loss": 0.0735,
+      "epoch": 0.17,
+      "learning_rate": 8.973775903719142e-06,
+      "loss": 0.6442,
       "step": 350
     },
     {
-      "epoch": 0.55,
-      "learning_rate": 3.8130782210150645e-06,
-      "loss": 0.0851,
-      "step": 360
-    },
-    {
-      "epoch": 0.56,
-      "learning_rate": 3.600967227532187e-06,
-      "loss": 0.0703,
-      "step": 370
-    },
-    {
-      "epoch": 0.58,
-      "learning_rate": 3.3909177399639346e-06,
-      "loss": 0.0651,
-      "step": 380
-    },
-    {
-      "epoch": 0.59,
-      "learning_rate": 3.1834114073382947e-06,
-      "loss": 0.0596,
-      "step": 390
-    },
-    {
-      "epoch": 0.61,
-      "learning_rate": 2.9789240471617385e-06,
-      "loss": 0.0579,
-      "step": 400
-    },
-    {
-      "epoch": 0.61,
-      "eval_accuracy": 0.0,
-      "eval_loss": 3.991552148363553e-06,
-      "eval_runtime": 31.7373,
-      "eval_samples_per_second": 137.819,
-      "eval_steps_per_second": 22.97,
+      "epoch": 0.2,
+      "learning_rate": 8.965758313771466e-06,
+      "loss": 0.6375,
       "step": 400
     },
     {
-      "epoch": 0.62,
-      "learning_rate": 2.7779245543570964e-06,
-      "loss": 0.0457,
-      "step": 410
-    },
-    {
-      "epoch": 0.64,
-      "learning_rate": 2.580873826075111e-06,
-      "loss": 0.0642,
-      "step": 420
-    },
-    {
-      "epoch": 0.66,
-      "learning_rate": 2.388223704845083e-06,
-      "loss": 0.0613,
-      "step": 430
-    },
-    {
-      "epoch": 0.67,
-      "learning_rate": 2.2004159424880025e-06,
-      "loss": 0.0533,
-      "step": 440
-    },
-    {
-      "epoch": 0.69,
-      "learning_rate": 2.0178811871679537e-06,
-      "loss": 0.0533,
+      "epoch": 0.22,
+      "learning_rate": 8.956677485072722e-06,
+      "loss": 0.6303,
       "step": 450
     },
     {
-      "epoch": 0.7,
-      "learning_rate": 1.8410379959044793e-06,
-      "loss": 0.0607,
-      "step": 460
-    },
-    {
-      "epoch": 0.72,
-      "learning_rate": 1.6702918748102748e-06,
-      "loss": 0.0469,
-      "step": 470
-    },
-    {
-      "epoch": 0.73,
-      "learning_rate": 1.5060343492549563e-06,
-      "loss": 0.0754,
-      "step": 480
-    },
-    {
-      "epoch": 0.75,
-      "learning_rate": 1.3486420660870307e-06,
-      "loss": 0.065,
-      "step": 490
-    },
-    {
-      "epoch": 0.76,
-      "learning_rate": 1.1984759299727166e-06,
-      "loss": 0.0557,
+      "epoch": 0.25,
+      "learning_rate": 8.946535579649664e-06,
+      "loss": 0.634,
       "step": 500
     },
     {
-      "epoch": 0.76,
+      "epoch": 0.25,
       "eval_accuracy": 0.0,
-      "eval_loss": 4.362014351499965e-06,
-      "eval_runtime": 30.9641,
-      "eval_samples_per_second": 141.26,
-      "eval_steps_per_second": 23.543,
+      "eval_loss": 0.6457224488258362,
+      "eval_runtime": 154.2695,
+      "eval_samples_per_second": 87.989,
+      "eval_steps_per_second": 14.669,
       "step": 500
     }
   ],
-  "logging_steps": 10,
-  "max_steps": 656,
-  "num_train_epochs": 1,
-  "save_steps": 100,
+  "logging_steps": 50,
+  "max_steps": 10180,
+  "num_train_epochs": 5,
+  "save_steps": 500,
   "total_flos": 0.0,
   "trial_name": null,
   "trial_params": null

checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1b0be5f447301b577e44061c504ec9398fb05913a538169784e7cfc7134c7d3
-size 4600
+oid sha256:675ad7baaf7ffa742fe1cbe33421593cfc3ecc39b8591506637a3cfb1a79ff8b
+size 4664