Upload 10 files

.gitattributes

@@ -32,5 +32,3 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
-bloomz-3b-wiki-detector/tokenizer.json filter=lfs diff=lfs merge=lfs -text
-tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "bigscience/bloomz-3b",
+  "apply_residual_connection_post_layernorm": false,
+  "architectures": [
+    "BloomForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "attention_softmax_in_fp32": true,
+  "bias_dropout_fusion": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_dropout": 0.0,
+  "hidden_size": 2560,
+  "id2label": {
+    "0": "human-produced",
+    "1": "machine-generated"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "human-produced": 0,
+    "machine-generated": 1
+  },
+  "layer_norm_epsilon": 1e-05,
+  "masked_softmax_fusion": true,
+  "model_type": "bloom",
+  "n_head": 32,
+  "n_inner": null,
+  "n_layer": 30,
+  "offset_alibi": 100,
+  "pad_token_id": 3,
+  "pretraining_tp": 4,
+  "problem_type": "single_label_classification",
+  "seq_length": 2048,
+  "skip_bias_add": true,
+  "skip_bias_add_qkv": false,
+  "slow_but_exact": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.26.1",
+  "unk_token_id": 0,
+  "use_cache": true,
+  "vocab_size": 250880
+}

pytorch_model.bin.index.json

@@ -0,0 +1,373 @@
+{
+  "metadata": {
+    "total_size": 12010250240
+  },
+  "weight_map": {
+    "score.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.0.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.0.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.1.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.10.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.11.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.12.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.13.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.14.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.15.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.16.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.17.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.18.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.19.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.2.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.20.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.21.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.22.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.23.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.23.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.24.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.24.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.25.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.26.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.27.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.28.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_4h_to_h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.mlp.dense_h_to_4h.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.post_attention_layernorm.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.dense.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.29.self_attention.query_key_value.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.h.3.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.3.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.4.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.5.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.6.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.7.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.8.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_4h_to_h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.mlp.dense_h_to_4h.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.post_attention_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.dense.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.h.9.self_attention.query_key_value.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.ln_f.bias": "pytorch_model-00002-of-00002.bin",
+    "transformer.ln_f.weight": "pytorch_model-00002-of-00002.bin",
+    "transformer.word_embeddings.weight": "pytorch_model-00001-of-00002.bin",
+    "transformer.word_embeddings_layernorm.bias": "pytorch_model-00001-of-00002.bin",
+    "transformer.word_embeddings_layernorm.weight": "pytorch_model-00001-of-00002.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "model_max_length": 1000000000000000019884624838656,
+  "name_or_path": "bigscience/bloomz-3b",
+  "pad_token": "<pad>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "BloomTokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,958 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 525,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.990476190476191e-05,
+      "loss": 5.664,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.904761904761905e-05,
+      "loss": 9.846,
+      "step": 10
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.5555555555555556,
+      "eval_f1": 0.21875,
+      "eval_loss": 2.4790709018707275,
+      "eval_precision": 0.9032258064516129,
+      "eval_recall": 0.12444444444444444,
+      "eval_runtime": 140.7243,
+      "eval_samples_per_second": 6.395,
+      "eval_steps_per_second": 0.803,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.80952380952381e-05,
+      "loss": 1.7358,
+      "step": 20
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.5,
+      "eval_f1": 0.6666666666666666,
+      "eval_loss": 3.0108251571655273,
+      "eval_precision": 0.5,
+      "eval_recall": 1.0,
+      "eval_runtime": 141.288,
+      "eval_samples_per_second": 6.37,
+      "eval_steps_per_second": 0.8,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.714285714285714e-05,
+      "loss": 1.297,
+      "step": 30
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.7755555555555556,
+      "eval_f1": 0.8133086876155268,
+      "eval_loss": 0.4418047368526459,
+      "eval_precision": 0.6962025316455697,
+      "eval_recall": 0.9777777777777777,
+      "eval_runtime": 141.1286,
+      "eval_samples_per_second": 6.377,
+      "eval_steps_per_second": 0.801,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.6190476190476194e-05,
+      "loss": 0.553,
+      "step": 40
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.7233333333333334,
+      "eval_f1": 0.782532751091703,
+      "eval_loss": 1.0572720766067505,
+      "eval_precision": 0.6446043165467625,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.1362,
+      "eval_samples_per_second": 6.377,
+      "eval_steps_per_second": 0.801,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.523809523809524e-05,
+      "loss": 0.4696,
+      "step": 50
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.9922222222222222,
+      "eval_f1": 0.9921612541993281,
+      "eval_loss": 0.11968932300806046,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9844444444444445,
+      "eval_runtime": 141.141,
+      "eval_samples_per_second": 6.377,
+      "eval_steps_per_second": 0.801,
+      "step": 50
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 4.428571428571428e-05,
+      "loss": 0.8216,
+      "step": 60
+    },
+    {
+      "epoch": 0.11,
+      "eval_accuracy": 0.9944444444444445,
+      "eval_f1": 0.9944506104328523,
+      "eval_loss": 0.026493508368730545,
+      "eval_precision": 0.9933481152993349,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.3296,
+      "eval_samples_per_second": 6.368,
+      "eval_steps_per_second": 0.8,
+      "step": 60
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.3333333333333334e-05,
+      "loss": 0.2496,
+      "step": 70
+    },
+    {
+      "epoch": 0.13,
+      "eval_accuracy": 0.9944444444444445,
+      "eval_f1": 0.9944134078212291,
+      "eval_loss": 0.04411568492650986,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9888888888888889,
+      "eval_runtime": 141.5358,
+      "eval_samples_per_second": 6.359,
+      "eval_steps_per_second": 0.798,
+      "step": 70
+    },
+    {
+      "epoch": 0.15,
+      "learning_rate": 4.2380952380952385e-05,
+      "loss": 0.1525,
+      "step": 80
+    },
+    {
+      "epoch": 0.15,
+      "eval_accuracy": 0.9722222222222222,
+      "eval_f1": 0.9716874292185731,
+      "eval_loss": 0.17274101078510284,
+      "eval_precision": 0.9907621247113164,
+      "eval_recall": 0.9533333333333334,
+      "eval_runtime": 141.1637,
+      "eval_samples_per_second": 6.376,
+      "eval_steps_per_second": 0.8,
+      "step": 80
+    },
+    {
+      "epoch": 0.17,
+      "learning_rate": 4.1428571428571437e-05,
+      "loss": 0.1757,
+      "step": 90
+    },
+    {
+      "epoch": 0.17,
+      "eval_accuracy": 0.6644444444444444,
+      "eval_f1": 0.747068676716918,
+      "eval_loss": 1.6221429109573364,
+      "eval_precision": 0.5994623655913979,
+      "eval_recall": 0.9911111111111112,
+      "eval_runtime": 141.238,
+      "eval_samples_per_second": 6.372,
+      "eval_steps_per_second": 0.8,
+      "step": 90
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.047619047619048e-05,
+      "loss": 0.4925,
+      "step": 100
+    },
+    {
+      "epoch": 0.19,
+      "eval_accuracy": 0.9766666666666667,
+      "eval_f1": 0.9761092150170648,
+      "eval_loss": 0.3036443293094635,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9533333333333334,
+      "eval_runtime": 141.1799,
+      "eval_samples_per_second": 6.375,
+      "eval_steps_per_second": 0.8,
+      "step": 100
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 3.9523809523809526e-05,
+      "loss": 0.3225,
+      "step": 110
+    },
+    {
+      "epoch": 0.21,
+      "eval_accuracy": 0.9855555555555555,
+      "eval_f1": 0.9853438556933485,
+      "eval_loss": 0.14187519252300262,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9711111111111111,
+      "eval_runtime": 141.1308,
+      "eval_samples_per_second": 6.377,
+      "eval_steps_per_second": 0.801,
+      "step": 110
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 3.857142857142858e-05,
+      "loss": 0.9088,
+      "step": 120
+    },
+    {
+      "epoch": 0.23,
+      "eval_accuracy": 0.9788888888888889,
+      "eval_f1": 0.9784335981838819,
+      "eval_loss": 0.28491899371147156,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9577777777777777,
+      "eval_runtime": 141.8534,
+      "eval_samples_per_second": 6.345,
+      "eval_steps_per_second": 0.797,
+      "step": 120
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 3.761904761904762e-05,
+      "loss": 0.3186,
+      "step": 130
+    },
+    {
+      "epoch": 0.25,
+      "eval_accuracy": 0.9866666666666667,
+      "eval_f1": 0.9864864864864865,
+      "eval_loss": 0.23162652552127838,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9733333333333334,
+      "eval_runtime": 141.2919,
+      "eval_samples_per_second": 6.37,
+      "eval_steps_per_second": 0.8,
+      "step": 130
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 3.6666666666666666e-05,
+      "loss": 0.4019,
+      "step": 140
+    },
+    {
+      "epoch": 0.27,
+      "eval_accuracy": 0.9277777777777778,
+      "eval_f1": 0.9221556886227544,
+      "eval_loss": 1.4866257905960083,
+      "eval_precision": 1.0,
+      "eval_recall": 0.8555555555555555,
+      "eval_runtime": 141.5133,
+      "eval_samples_per_second": 6.36,
+      "eval_steps_per_second": 0.799,
+      "step": 140
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.571428571428572e-05,
+      "loss": 1.3601,
+      "step": 150
+    },
+    {
+      "epoch": 0.29,
+      "eval_accuracy": 0.7233333333333334,
+      "eval_f1": 0.782532751091703,
+      "eval_loss": 3.7794864177703857,
+      "eval_precision": 0.6446043165467625,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.4729,
+      "eval_samples_per_second": 6.362,
+      "eval_steps_per_second": 0.799,
+      "step": 150
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 3.476190476190476e-05,
+      "loss": 0.795,
+      "step": 160
+    },
+    {
+      "epoch": 0.3,
+      "eval_accuracy": 0.9866666666666667,
+      "eval_f1": 0.9864864864864865,
+      "eval_loss": 0.30650249123573303,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9733333333333334,
+      "eval_runtime": 141.9743,
+      "eval_samples_per_second": 6.339,
+      "eval_steps_per_second": 0.796,
+      "step": 160
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 3.380952380952381e-05,
+      "loss": 0.3756,
+      "step": 170
+    },
+    {
+      "epoch": 0.32,
+      "eval_accuracy": 0.9922222222222222,
+      "eval_f1": 0.992248062015504,
+      "eval_loss": 0.10177851468324661,
+      "eval_precision": 0.9889624724061811,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.4364,
+      "eval_samples_per_second": 6.363,
+      "eval_steps_per_second": 0.799,
+      "step": 170
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.285714285714286e-05,
+      "loss": 0.1634,
+      "step": 180
+    },
+    {
+      "epoch": 0.34,
+      "eval_accuracy": 0.9955555555555555,
+      "eval_f1": 0.9955357142857144,
+      "eval_loss": 0.05739554017782211,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9911111111111112,
+      "eval_runtime": 142.0812,
+      "eval_samples_per_second": 6.334,
+      "eval_steps_per_second": 0.795,
+      "step": 180
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 3.19047619047619e-05,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.36,
+      "eval_accuracy": 0.9966666666666667,
+      "eval_f1": 0.9966555183946488,
+      "eval_loss": 0.04873024299740791,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9933333333333333,
+      "eval_runtime": 141.2062,
+      "eval_samples_per_second": 6.374,
+      "eval_steps_per_second": 0.8,
+      "step": 190
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 3.095238095238095e-05,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.38,
+      "eval_accuracy": 0.9944444444444445,
+      "eval_f1": 0.9944134078212291,
+      "eval_loss": 0.06256787478923798,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9888888888888889,
+      "eval_runtime": 141.0452,
+      "eval_samples_per_second": 6.381,
+      "eval_steps_per_second": 0.801,
+      "step": 200
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 3e-05,
+      "loss": 0.0,
+      "step": 210
+    },
+    {
+      "epoch": 0.4,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.06856151670217514,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.9154,
+      "eval_samples_per_second": 6.342,
+      "eval_steps_per_second": 0.796,
+      "step": 210
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.9047619047619052e-05,
+      "loss": 0.0,
+      "step": 220
+    },
+    {
+      "epoch": 0.42,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.0719400942325592,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.1046,
+      "eval_samples_per_second": 6.378,
+      "eval_steps_per_second": 0.801,
+      "step": 220
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 2.8095238095238096e-05,
+      "loss": 0.0,
+      "step": 230
+    },
+    {
+      "epoch": 0.44,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.07359585165977478,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.0721,
+      "eval_samples_per_second": 6.38,
+      "eval_steps_per_second": 0.801,
+      "step": 230
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 2.714285714285714e-05,
+      "loss": 0.0,
+      "step": 240
+    },
+    {
+      "epoch": 0.46,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.07422058284282684,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.0372,
+      "eval_samples_per_second": 6.381,
+      "eval_steps_per_second": 0.801,
+      "step": 240
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.6190476190476192e-05,
+      "loss": 0.0,
+      "step": 250
+    },
+    {
+      "epoch": 0.48,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.07448597997426987,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.2024,
+      "eval_samples_per_second": 6.374,
+      "eval_steps_per_second": 0.8,
+      "step": 250
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 2.523809523809524e-05,
+      "loss": 0.0002,
+      "step": 260
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.9966666666666667,
+      "eval_f1": 0.9966555183946488,
+      "eval_loss": 0.04471863806247711,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9933333333333333,
+      "eval_runtime": 142.2697,
+      "eval_samples_per_second": 6.326,
+      "eval_steps_per_second": 0.794,
+      "step": 260
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4285714285714288e-05,
+      "loss": 0.0003,
+      "step": 270
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.05505097284913063,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.202,
+      "eval_samples_per_second": 6.374,
+      "eval_steps_per_second": 0.8,
+      "step": 270
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.3333333333333336e-05,
+      "loss": 0.0,
+      "step": 280
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.06447486579418182,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.5606,
+      "eval_samples_per_second": 6.358,
+      "eval_steps_per_second": 0.798,
+      "step": 280
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2380952380952384e-05,
+      "loss": 0.0,
+      "step": 290
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.9966666666666667,
+      "eval_f1": 0.9966555183946488,
+      "eval_loss": 0.06785142421722412,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9933333333333333,
+      "eval_runtime": 141.703,
+      "eval_samples_per_second": 6.351,
+      "eval_steps_per_second": 0.797,
+      "step": 290
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1428571428571428e-05,
+      "loss": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.57,
+      "eval_accuracy": 0.9966666666666667,
+      "eval_f1": 0.9966555183946488,
+      "eval_loss": 0.06899154931306839,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9933333333333333,
+      "eval_runtime": 141.0943,
+      "eval_samples_per_second": 6.379,
+      "eval_steps_per_second": 0.801,
+      "step": 300
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.0476190476190476e-05,
+      "loss": 0.0,
+      "step": 310
+    },
+    {
+      "epoch": 0.59,
+      "eval_accuracy": 0.9966666666666667,
+      "eval_f1": 0.9966555183946488,
+      "eval_loss": 0.06934668123722076,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9933333333333333,
+      "eval_runtime": 141.164,
+      "eval_samples_per_second": 6.376,
+      "eval_steps_per_second": 0.8,
+      "step": 310
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.9523809523809524e-05,
+      "loss": 0.0005,
+      "step": 320
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.97,
+      "eval_f1": 0.9707475622968581,
+      "eval_loss": 0.19248592853546143,
+      "eval_precision": 0.9471458773784355,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.5015,
+      "eval_samples_per_second": 6.36,
+      "eval_steps_per_second": 0.799,
+      "step": 320
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8571428571428572e-05,
+      "loss": 0.3679,
+      "step": 330
+    },
+    {
+      "epoch": 0.63,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.13398447632789612,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.4182,
+      "eval_samples_per_second": 6.364,
+      "eval_steps_per_second": 0.799,
+      "step": 330
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.761904761904762e-05,
+      "loss": 0.022,
+      "step": 340
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.9911111111111112,
+      "eval_f1": 0.9910313901345292,
+      "eval_loss": 0.14806345105171204,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9822222222222222,
+      "eval_runtime": 141.5234,
+      "eval_samples_per_second": 6.359,
+      "eval_steps_per_second": 0.798,
+      "step": 340
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.3466,
+      "step": 350
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.03295884281396866,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.8566,
+      "eval_samples_per_second": 6.344,
+      "eval_steps_per_second": 0.797,
+      "step": 350
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5714285714285715e-05,
+      "loss": 0.0969,
+      "step": 360
+    },
+    {
+      "epoch": 0.69,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.033551666885614395,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.8137,
+      "eval_samples_per_second": 6.346,
+      "eval_steps_per_second": 0.797,
+      "step": 360
+    },
+    {
+      "epoch": 0.7,
+      "learning_rate": 1.4761904761904763e-05,
+      "loss": 0.0,
+      "step": 370
+    },
+    {
+      "epoch": 0.7,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.036964382976293564,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.486,
+      "eval_samples_per_second": 6.361,
+      "eval_steps_per_second": 0.799,
+      "step": 370
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.3809523809523811e-05,
+      "loss": 0.1382,
+      "step": 380
+    },
+    {
+      "epoch": 0.72,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.024998752400279045,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.3407,
+      "eval_samples_per_second": 6.368,
+      "eval_steps_per_second": 0.799,
+      "step": 380
+    },
+    {
+      "epoch": 0.74,
+      "learning_rate": 1.2857142857142857e-05,
+      "loss": 0.0002,
+      "step": 390
+    },
+    {
+      "epoch": 0.74,
+      "eval_accuracy": 0.9955555555555555,
+      "eval_f1": 0.9955357142857144,
+      "eval_loss": 0.0562567375600338,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9911111111111112,
+      "eval_runtime": 141.2026,
+      "eval_samples_per_second": 6.374,
+      "eval_steps_per_second": 0.8,
+      "step": 390
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 1.1904761904761905e-05,
+      "loss": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.76,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.08514667302370071,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.5649,
+      "eval_samples_per_second": 6.358,
+      "eval_steps_per_second": 0.798,
+      "step": 400
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 1.0952380952380953e-05,
+      "loss": 0.0,
+      "step": 410
+    },
+    {
+      "epoch": 0.78,
+      "eval_accuracy": 0.9933333333333333,
+      "eval_f1": 0.9932885906040269,
+      "eval_loss": 0.0796796977519989,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9866666666666667,
+      "eval_runtime": 141.415,
+      "eval_samples_per_second": 6.364,
+      "eval_steps_per_second": 0.799,
+      "step": 410
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 1e-05,
+      "loss": 0.0249,
+      "step": 420
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.053853683173656464,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.5153,
+      "eval_samples_per_second": 6.36,
+      "eval_steps_per_second": 0.799,
+      "step": 420
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.047619047619047e-06,
+      "loss": 0.0,
+      "step": 430
+    },
+    {
+      "epoch": 0.82,
+      "eval_accuracy": 0.9944444444444445,
+      "eval_f1": 0.9944506104328523,
+      "eval_loss": 0.05637865141034126,
+      "eval_precision": 0.9933481152993349,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.1842,
+      "eval_samples_per_second": 6.375,
+      "eval_steps_per_second": 0.8,
+      "step": 430
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 8.095238095238097e-06,
+      "loss": 0.0001,
+      "step": 440
+    },
+    {
+      "epoch": 0.84,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.05456162244081497,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.6066,
+      "eval_samples_per_second": 6.356,
+      "eval_steps_per_second": 0.798,
+      "step": 440
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.142857142857143e-06,
+      "loss": 0.0,
+      "step": 450
+    },
+    {
+      "epoch": 0.86,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.05705412104725838,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.4461,
+      "eval_samples_per_second": 6.363,
+      "eval_steps_per_second": 0.799,
+      "step": 450
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 6.190476190476191e-06,
+      "loss": 0.0,
+      "step": 460
+    },
+    {
+      "epoch": 0.88,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.057826586067676544,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.1909,
+      "eval_samples_per_second": 6.374,
+      "eval_steps_per_second": 0.8,
+      "step": 460
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 5.2380952380952384e-06,
+      "loss": 0.0,
+      "step": 470
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.058067686855793,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.1597,
+      "eval_samples_per_second": 6.376,
+      "eval_steps_per_second": 0.801,
+      "step": 470
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 4.285714285714286e-06,
+      "loss": 0.0436,
+      "step": 480
+    },
+    {
+      "epoch": 0.91,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.05441794544458389,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.5984,
+      "eval_samples_per_second": 6.356,
+      "eval_steps_per_second": 0.798,
+      "step": 480
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.0001,
+      "step": 490
+    },
+    {
+      "epoch": 0.93,
+      "eval_accuracy": 0.9966666666666667,
+      "eval_f1": 0.996662958843159,
+      "eval_loss": 0.05526140332221985,
+      "eval_precision": 0.9977728285077951,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.1634,
+      "eval_samples_per_second": 6.376,
+      "eval_steps_per_second": 0.8,
+      "step": 490
+    },
+    {
+      "epoch": 0.95,
+      "learning_rate": 2.3809523809523808e-06,
+      "loss": 0.0,
+      "step": 500
+    },
+    {
+      "epoch": 0.95,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.054864052683115005,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.2124,
+      "eval_samples_per_second": 6.373,
+      "eval_steps_per_second": 0.8,
+      "step": 500
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.0,
+      "step": 510
+    },
+    {
+      "epoch": 0.97,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.0549486018717289,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.0622,
+      "eval_samples_per_second": 6.38,
+      "eval_steps_per_second": 0.801,
+      "step": 510
+    },
+    {
+      "epoch": 0.99,
+      "learning_rate": 4.761904761904763e-07,
+      "loss": 0.0,
+      "step": 520
+    },
+    {
+      "epoch": 0.99,
+      "eval_accuracy": 0.9977777777777778,
+      "eval_f1": 0.9977728285077951,
+      "eval_loss": 0.054975349456071854,
+      "eval_precision": 1.0,
+      "eval_recall": 0.9955555555555555,
+      "eval_runtime": 141.3458,
+      "eval_samples_per_second": 6.367,
+      "eval_steps_per_second": 0.799,
+      "step": 520
+    }
+  ],
+  "max_steps": 525,
+  "num_train_epochs": 1,
+  "total_flos": 3.0453660647424e+16,
+  "trial_name": null,
+  "trial_params": null
+}