Upload 12 files

.gitattributes

@@ -32,3 +32,4 @@ 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
+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
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c4ea4faa0abf5ea7442723f715c6548f7456030da5dc2d87c9e3e745a269a5fb
+size 24020817451

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84c5cec8a26f1b9edd1134b1eabffcaf8d7fe9a198ea538fe8b1aeafdda80830
+size 9912311464

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efba9bd3f6f68c5d512d9289b81c752a33a160d4a670a496d601c35ab8febf62
+size 2098070557

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"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d944d6907131fce4941c1b98753b6c6304e9268438faa750202a7ed282544a4
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d94bffac577c2182cd3b6680df4b0ff46f4c0a0b7ff9c866be7458145e68e80
+size 627

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3955d17bdf8285663734ab4418c7a0d6397bf2fa7d7a2f8d820f23b3130cd48
+size 14500708

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 +1,922 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "global_step": 2188,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.997714808043876e-05,
+      "loss": 5.4892,
+      "step": 1
+    },
+    {
+      "epoch": 0.02,
+      "learning_rate": 4.9017367458866546e-05,
+      "loss": 3.0607,
+      "step": 43
+    },
+    {
+      "epoch": 0.02,
+      "eval_accuracy": 0.8749333333333333,
+      "eval_f1": 0.8729341641831482,
+      "eval_loss": 2.1355409622192383,
+      "eval_precision": 0.887114537444934,
+      "eval_recall": 0.8592,
+      "eval_runtime": 581.4545,
+      "eval_samples_per_second": 6.449,
+      "eval_steps_per_second": 0.807,
+      "step": 43
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.8034734917733096e-05,
+      "loss": 1.6864,
+      "step": 86
+    },
+    {
+      "epoch": 0.04,
+      "eval_accuracy": 0.8901333333333333,
+      "eval_f1": 0.8857459789240155,
+      "eval_loss": 1.632243275642395,
+      "eval_precision": 0.9225880993645291,
+      "eval_recall": 0.8517333333333333,
+      "eval_runtime": 581.1642,
+      "eval_samples_per_second": 6.453,
+      "eval_steps_per_second": 0.807,
+      "step": 86
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.705210237659964e-05,
+      "loss": 1.0658,
+      "step": 129
+    },
+    {
+      "epoch": 0.06,
+      "eval_accuracy": 0.904,
+      "eval_f1": 0.9061032863849765,
+      "eval_loss": 0.3131539821624756,
+      "eval_precision": 0.886676875957121,
+      "eval_recall": 0.9264,
+      "eval_runtime": 580.6614,
+      "eval_samples_per_second": 6.458,
+      "eval_steps_per_second": 0.808,
+      "step": 129
+    },
+    {
+      "epoch": 0.08,
+      "learning_rate": 4.606946983546618e-05,
+      "loss": 0.4275,
+      "step": 172
+    },
+    {
+      "epoch": 0.08,
+      "eval_accuracy": 0.8874666666666666,
+      "eval_f1": 0.8765359859566997,
+      "eval_loss": 1.6054295301437378,
+      "eval_precision": 0.9708360337005832,
+      "eval_recall": 0.7989333333333334,
+      "eval_runtime": 580.8161,
+      "eval_samples_per_second": 6.456,
+      "eval_steps_per_second": 0.807,
+      "step": 172
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.5086837294332726e-05,
+      "loss": 0.5456,
+      "step": 215
+    },
+    {
+      "epoch": 0.1,
+      "eval_accuracy": 0.9170666666666667,
+      "eval_f1": 0.9218789248932429,
+      "eval_loss": 0.41803765296936035,
+      "eval_precision": 0.8713200379867047,
+      "eval_recall": 0.9786666666666667,
+      "eval_runtime": 580.4549,
+      "eval_samples_per_second": 6.46,
+      "eval_steps_per_second": 0.808,
+      "step": 215
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.410420475319927e-05,
+      "loss": 0.6111,
+      "step": 258
+    },
+    {
+      "epoch": 0.12,
+      "eval_accuracy": 0.8786666666666667,
+      "eval_f1": 0.8626622396619378,
+      "eval_loss": 0.32219210267066956,
+      "eval_precision": 0.9937413073713491,
+      "eval_recall": 0.7621333333333333,
+      "eval_runtime": 584.0808,
+      "eval_samples_per_second": 6.42,
+      "eval_steps_per_second": 0.803,
+      "step": 258
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.312157221206581e-05,
+      "loss": 0.7106,
+      "step": 301
+    },
+    {
+      "epoch": 0.14,
+      "eval_accuracy": 0.9274666666666667,
+      "eval_f1": 0.9221967963386728,
+      "eval_loss": 0.5022754073143005,
+      "eval_precision": 0.9944478716841456,
+      "eval_recall": 0.8597333333333333,
+      "eval_runtime": 581.6225,
+      "eval_samples_per_second": 6.447,
+      "eval_steps_per_second": 0.806,
+      "step": 301
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.213893967093236e-05,
+      "loss": 0.2426,
+      "step": 344
+    },
+    {
+      "epoch": 0.16,
+      "eval_accuracy": 0.9586666666666667,
+      "eval_f1": 0.9586997069011457,
+      "eval_loss": 0.16574496030807495,
+      "eval_precision": 0.9579339723109691,
+      "eval_recall": 0.9594666666666667,
+      "eval_runtime": 580.7975,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 0.808,
+      "step": 344
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.1156307129798905e-05,
+      "loss": 0.3958,
+      "step": 387
+    },
+    {
+      "epoch": 0.18,
+      "eval_accuracy": 0.9554666666666667,
+      "eval_f1": 0.9535724214623298,
+      "eval_loss": 0.24226774275302887,
+      "eval_precision": 0.9959349593495935,
+      "eval_recall": 0.9146666666666666,
+      "eval_runtime": 581.1794,
+      "eval_samples_per_second": 6.452,
+      "eval_steps_per_second": 0.807,
+      "step": 387
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 4.017367458866545e-05,
+      "loss": 0.4259,
+      "step": 430
+    },
+    {
+      "epoch": 0.2,
+      "eval_accuracy": 0.9448,
+      "eval_f1": 0.9449614464238233,
+      "eval_loss": 0.3525341749191284,
+      "eval_precision": 0.9422057264050901,
+      "eval_recall": 0.9477333333333333,
+      "eval_runtime": 580.7809,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 0.808,
+      "step": 430
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 3.919104204753199e-05,
+      "loss": 0.2217,
+      "step": 473
+    },
+    {
+      "epoch": 0.22,
+      "eval_accuracy": 0.9549333333333333,
+      "eval_f1": 0.9531466592736346,
+      "eval_loss": 0.22800709307193756,
+      "eval_precision": 0.9924942263279446,
+      "eval_recall": 0.9168,
+      "eval_runtime": 580.8019,
+      "eval_samples_per_second": 6.457,
+      "eval_steps_per_second": 0.808,
+      "step": 473
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.820840950639854e-05,
+      "loss": 0.1741,
+      "step": 516
+    },
+    {
+      "epoch": 0.24,
+      "eval_accuracy": 0.9682666666666667,
+      "eval_f1": 0.9673525377229081,
+      "eval_loss": 0.15350370109081268,
+      "eval_precision": 0.996045197740113,
+      "eval_recall": 0.9402666666666667,
+      "eval_runtime": 584.2385,
+      "eval_samples_per_second": 6.419,
+      "eval_steps_per_second": 0.803,
+      "step": 516
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 3.7225776965265085e-05,
+      "loss": 0.1731,
+      "step": 559
+    },
+    {
+      "epoch": 0.26,
+      "eval_accuracy": 0.9648,
+      "eval_f1": 0.9636763896532745,
+      "eval_loss": 0.29772499203681946,
+      "eval_precision": 0.9954519613416714,
+      "eval_recall": 0.9338666666666666,
+      "eval_runtime": 580.9188,
+      "eval_samples_per_second": 6.455,
+      "eval_steps_per_second": 0.807,
+      "step": 559
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 3.624314442413163e-05,
+      "loss": 0.1857,
+      "step": 602
+    },
+    {
+      "epoch": 0.28,
+      "eval_accuracy": 0.9826666666666667,
+      "eval_f1": 0.9826527888977848,
+      "eval_loss": 0.16285915672779083,
+      "eval_precision": 0.9834401709401709,
+      "eval_recall": 0.9818666666666667,
+      "eval_runtime": 581.4605,
+      "eval_samples_per_second": 6.449,
+      "eval_steps_per_second": 0.807,
+      "step": 602
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.526051188299818e-05,
+      "loss": 0.241,
+      "step": 645
+    },
+    {
+      "epoch": 0.29,
+      "eval_accuracy": 0.9677333333333333,
+      "eval_f1": 0.9681997371879106,
+      "eval_loss": 0.30683064460754395,
+      "eval_precision": 0.9544041450777202,
+      "eval_recall": 0.9824,
+      "eval_runtime": 580.3999,
+      "eval_samples_per_second": 6.461,
+      "eval_steps_per_second": 0.808,
+      "step": 645
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 3.4277879341864715e-05,
+      "loss": 0.1674,
+      "step": 688
+    },
+    {
+      "epoch": 0.31,
+      "eval_accuracy": 0.9050666666666667,
+      "eval_f1": 0.9130434782608695,
+      "eval_loss": 0.5339795351028442,
+      "eval_precision": 0.8422712933753943,
+      "eval_recall": 0.9968,
+      "eval_runtime": 580.4617,
+      "eval_samples_per_second": 6.46,
+      "eval_steps_per_second": 0.808,
+      "step": 688
+    },
+    {
+      "epoch": 0.33,
+      "learning_rate": 3.329524680073126e-05,
+      "loss": 0.1452,
+      "step": 731
+    },
+    {
+      "epoch": 0.33,
+      "eval_accuracy": 0.9754666666666667,
+      "eval_f1": 0.9756871035940803,
+      "eval_loss": 0.1770327091217041,
+      "eval_precision": 0.9669984284965951,
+      "eval_recall": 0.9845333333333334,
+      "eval_runtime": 581.5384,
+      "eval_samples_per_second": 6.448,
+      "eval_steps_per_second": 0.806,
+      "step": 731
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 3.231261425959781e-05,
+      "loss": 0.2261,
+      "step": 774
+    },
+    {
+      "epoch": 0.35,
+      "eval_accuracy": 0.9714666666666667,
+      "eval_f1": 0.97192337969037,
+      "eval_loss": 0.2083805948495865,
+      "eval_precision": 0.9566115702479339,
+      "eval_recall": 0.9877333333333334,
+      "eval_runtime": 582.4902,
+      "eval_samples_per_second": 6.438,
+      "eval_steps_per_second": 0.805,
+      "step": 774
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 3.132998171846435e-05,
+      "loss": 0.1849,
+      "step": 817
+    },
+    {
+      "epoch": 0.37,
+      "eval_accuracy": 0.9765333333333334,
+      "eval_f1": 0.9763186221743809,
+      "eval_loss": 0.12196581810712814,
+      "eval_precision": 0.9853340575774036,
+      "eval_recall": 0.9674666666666667,
+      "eval_runtime": 578.7143,
+      "eval_samples_per_second": 6.48,
+      "eval_steps_per_second": 0.81,
+      "step": 817
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.03473491773309e-05,
+      "loss": 0.1237,
+      "step": 860
+    },
+    {
+      "epoch": 0.39,
+      "eval_accuracy": 0.9693333333333334,
+      "eval_f1": 0.9700286682303884,
+      "eval_loss": 0.2138151079416275,
+      "eval_precision": 0.9485219164118247,
+      "eval_recall": 0.9925333333333334,
+      "eval_runtime": 578.8904,
+      "eval_samples_per_second": 6.478,
+      "eval_steps_per_second": 0.81,
+      "step": 860
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 2.9364716636197442e-05,
+      "loss": 0.1627,
+      "step": 903
+    },
+    {
+      "epoch": 0.41,
+      "eval_accuracy": 0.9584,
+      "eval_f1": 0.9566425792106726,
+      "eval_loss": 0.254962295293808,
+      "eval_precision": 0.9988392338943702,
+      "eval_recall": 0.9178666666666667,
+      "eval_runtime": 578.6033,
+      "eval_samples_per_second": 6.481,
+      "eval_steps_per_second": 0.811,
+      "step": 903
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.838208409506399e-05,
+      "loss": 0.2477,
+      "step": 946
+    },
+    {
+      "epoch": 0.43,
+      "eval_accuracy": 0.9765333333333334,
+      "eval_f1": 0.9761258817145958,
+      "eval_loss": 0.13448475301265717,
+      "eval_precision": 0.9933738266151297,
+      "eval_recall": 0.9594666666666667,
+      "eval_runtime": 578.5049,
+      "eval_samples_per_second": 6.482,
+      "eval_steps_per_second": 0.811,
+      "step": 946
+    },
+    {
+      "epoch": 0.45,
+      "learning_rate": 2.739945155393053e-05,
+      "loss": 0.0943,
+      "step": 989
+    },
+    {
+      "epoch": 0.45,
+      "eval_accuracy": 0.9688,
+      "eval_f1": 0.9695391825045562,
+      "eval_loss": 0.18509739637374878,
+      "eval_precision": 0.9471007121057986,
+      "eval_recall": 0.9930666666666667,
+      "eval_runtime": 578.7851,
+      "eval_samples_per_second": 6.479,
+      "eval_steps_per_second": 0.81,
+      "step": 989
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 2.641681901279708e-05,
+      "loss": 0.2131,
+      "step": 1032
+    },
+    {
+      "epoch": 0.47,
+      "eval_accuracy": 0.9826666666666667,
+      "eval_f1": 0.9825970548862116,
+      "eval_loss": 0.10872189700603485,
+      "eval_precision": 0.9865591397849462,
+      "eval_recall": 0.9786666666666667,
+      "eval_runtime": 580.8924,
+      "eval_samples_per_second": 6.456,
+      "eval_steps_per_second": 0.807,
+      "step": 1032
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 2.5434186471663625e-05,
+      "loss": 0.0829,
+      "step": 1075
+    },
+    {
+      "epoch": 0.49,
+      "eval_accuracy": 0.9661333333333333,
+      "eval_f1": 0.9651577503429356,
+      "eval_loss": 0.2479323148727417,
+      "eval_precision": 0.9937853107344633,
+      "eval_recall": 0.9381333333333334,
+      "eval_runtime": 578.7358,
+      "eval_samples_per_second": 6.48,
+      "eval_steps_per_second": 0.81,
+      "step": 1075
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 2.4451553930530165e-05,
+      "loss": 0.1392,
+      "step": 1118
+    },
+    {
+      "epoch": 0.51,
+      "eval_accuracy": 0.9613333333333334,
+      "eval_f1": 0.959867146415721,
+      "eval_loss": 0.20837165415287018,
+      "eval_precision": 0.997698504027618,
+      "eval_recall": 0.9248,
+      "eval_runtime": 579.0845,
+      "eval_samples_per_second": 6.476,
+      "eval_steps_per_second": 0.81,
+      "step": 1118
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.346892138939671e-05,
+      "loss": 0.0563,
+      "step": 1161
+    },
+    {
+      "epoch": 0.53,
+      "eval_accuracy": 0.9874666666666667,
+      "eval_f1": 0.9874833555259653,
+      "eval_loss": 0.08351419121026993,
+      "eval_precision": 0.9861702127659574,
+      "eval_recall": 0.9888,
+      "eval_runtime": 578.9179,
+      "eval_samples_per_second": 6.478,
+      "eval_steps_per_second": 0.81,
+      "step": 1161
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 2.2486288848263255e-05,
+      "loss": 0.107,
+      "step": 1204
+    },
+    {
+      "epoch": 0.55,
+      "eval_accuracy": 0.9826666666666667,
+      "eval_f1": 0.9828269484808455,
+      "eval_loss": 0.11463689059019089,
+      "eval_precision": 0.9738219895287958,
+      "eval_recall": 0.992,
+      "eval_runtime": 579.4593,
+      "eval_samples_per_second": 6.472,
+      "eval_steps_per_second": 0.809,
+      "step": 1204
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 2.1503656307129798e-05,
+      "loss": 0.0822,
+      "step": 1247
+    },
+    {
+      "epoch": 0.57,
+      "eval_accuracy": 0.9816,
+      "eval_f1": 0.9817218543046358,
+      "eval_loss": 0.1307775229215622,
+      "eval_precision": 0.9752631578947368,
+      "eval_recall": 0.9882666666666666,
+      "eval_runtime": 580.0354,
+      "eval_samples_per_second": 6.465,
+      "eval_steps_per_second": 0.809,
+      "step": 1247
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 2.0521023765996345e-05,
+      "loss": 0.1165,
+      "step": 1290
+    },
+    {
+      "epoch": 0.59,
+      "eval_accuracy": 0.9856,
+      "eval_f1": 0.9855923159018143,
+      "eval_loss": 0.09052357822656631,
+      "eval_precision": 0.9861185264281901,
+      "eval_recall": 0.9850666666666666,
+      "eval_runtime": 581.231,
+      "eval_samples_per_second": 6.452,
+      "eval_steps_per_second": 0.807,
+      "step": 1290
+    },
+    {
+      "epoch": 0.61,
+      "learning_rate": 1.953839122486289e-05,
+      "loss": 0.1156,
+      "step": 1333
+    },
+    {
+      "epoch": 0.61,
+      "eval_accuracy": 0.9864,
+      "eval_f1": 0.9864972200158858,
+      "eval_loss": 0.09110942482948303,
+      "eval_precision": 0.9794952681388013,
+      "eval_recall": 0.9936,
+      "eval_runtime": 579.1835,
+      "eval_samples_per_second": 6.475,
+      "eval_steps_per_second": 0.81,
+      "step": 1333
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.8555758683729435e-05,
+      "loss": 0.1172,
+      "step": 1376
+    },
+    {
+      "epoch": 0.63,
+      "eval_accuracy": 0.984,
+      "eval_f1": 0.9841772151898733,
+      "eval_loss": 0.09306684881448746,
+      "eval_precision": 0.97339593114241,
+      "eval_recall": 0.9952,
+      "eval_runtime": 579.0887,
+      "eval_samples_per_second": 6.476,
+      "eval_steps_per_second": 0.81,
+      "step": 1376
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 1.7573126142595978e-05,
+      "loss": 0.1447,
+      "step": 1419
+    },
+    {
+      "epoch": 0.65,
+      "eval_accuracy": 0.9848,
+      "eval_f1": 0.9849086576648134,
+      "eval_loss": 0.08812595903873444,
+      "eval_precision": 0.9779179810725552,
+      "eval_recall": 0.992,
+      "eval_runtime": 579.3815,
+      "eval_samples_per_second": 6.472,
+      "eval_steps_per_second": 0.809,
+      "step": 1419
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.659049360146252e-05,
+      "loss": 0.087,
+      "step": 1462
+    },
+    {
+      "epoch": 0.67,
+      "eval_accuracy": 0.9872,
+      "eval_f1": 0.9872272485364556,
+      "eval_loss": 0.07127923518419266,
+      "eval_precision": 0.9851301115241635,
+      "eval_recall": 0.9893333333333333,
+      "eval_runtime": 578.9808,
+      "eval_samples_per_second": 6.477,
+      "eval_steps_per_second": 0.81,
+      "step": 1462
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 1.5607861060329068e-05,
+      "loss": 0.0313,
+      "step": 1505
+    },
+    {
+      "epoch": 0.69,
+      "eval_accuracy": 0.9861333333333333,
+      "eval_f1": 0.9862142099681867,
+      "eval_loss": 0.1003463938832283,
+      "eval_precision": 0.9804955192409067,
+      "eval_recall": 0.992,
+      "eval_runtime": 579.6786,
+      "eval_samples_per_second": 6.469,
+      "eval_steps_per_second": 0.809,
+      "step": 1505
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 1.4625228519195613e-05,
+      "loss": 0.0729,
+      "step": 1548
+    },
+    {
+      "epoch": 0.71,
+      "eval_accuracy": 0.9869333333333333,
+      "eval_f1": 0.986859747921695,
+      "eval_loss": 0.0750027745962143,
+      "eval_precision": 0.9924487594390508,
+      "eval_recall": 0.9813333333333333,
+      "eval_runtime": 581.8591,
+      "eval_samples_per_second": 6.445,
+      "eval_steps_per_second": 0.806,
+      "step": 1548
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 1.3642595978062158e-05,
+      "loss": 0.106,
+      "step": 1591
+    },
+    {
+      "epoch": 0.73,
+      "eval_accuracy": 0.9874666666666667,
+      "eval_f1": 0.9874499332443257,
+      "eval_loss": 0.06067837029695511,
+      "eval_precision": 0.9887700534759358,
+      "eval_recall": 0.9861333333333333,
+      "eval_runtime": 579.0471,
+      "eval_samples_per_second": 6.476,
+      "eval_steps_per_second": 0.81,
+      "step": 1591
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 1.2659963436928701e-05,
+      "loss": 0.0823,
+      "step": 1634
+    },
+    {
+      "epoch": 0.75,
+      "eval_accuracy": 0.9877333333333334,
+      "eval_f1": 0.9877005347593582,
+      "eval_loss": 0.07156907767057419,
+      "eval_precision": 0.9903485254691688,
+      "eval_recall": 0.9850666666666666,
+      "eval_runtime": 578.809,
+      "eval_samples_per_second": 6.479,
+      "eval_steps_per_second": 0.81,
+      "step": 1634
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.1677330895795248e-05,
+      "loss": 0.0817,
+      "step": 1677
+    },
+    {
+      "epoch": 0.77,
+      "eval_accuracy": 0.9845333333333334,
+      "eval_f1": 0.9846804014791337,
+      "eval_loss": 0.09290226548910141,
+      "eval_precision": 0.9754055468341183,
+      "eval_recall": 0.9941333333333333,
+      "eval_runtime": 578.5452,
+      "eval_samples_per_second": 6.482,
+      "eval_steps_per_second": 0.811,
+      "step": 1677
+    },
+    {
+      "epoch": 0.79,
+      "learning_rate": 1.0694698354661791e-05,
+      "loss": 0.1279,
+      "step": 1720
+    },
+    {
+      "epoch": 0.79,
+      "eval_accuracy": 0.988,
+      "eval_f1": 0.9879453522635949,
+      "eval_loss": 0.07037492841482162,
+      "eval_precision": 0.9924650161463939,
+      "eval_recall": 0.9834666666666667,
+      "eval_runtime": 579.5947,
+      "eval_samples_per_second": 6.47,
+      "eval_steps_per_second": 0.809,
+      "step": 1720
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 9.712065813528338e-06,
+      "loss": 0.075,
+      "step": 1763
+    },
+    {
+      "epoch": 0.81,
+      "eval_accuracy": 0.9890666666666666,
+      "eval_f1": 0.9890462196099385,
+      "eval_loss": 0.06325065344572067,
+      "eval_precision": 0.9908993576017131,
+      "eval_recall": 0.9872,
+      "eval_runtime": 579.6298,
+      "eval_samples_per_second": 6.47,
+      "eval_steps_per_second": 0.809,
+      "step": 1763
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 8.729433272394881e-06,
+      "loss": 0.0909,
+      "step": 1806
+    },
+    {
+      "epoch": 0.83,
+      "eval_accuracy": 0.9842666666666666,
+      "eval_f1": 0.9840841650930671,
+      "eval_loss": 0.09650667011737823,
+      "eval_precision": 0.9956331877729258,
+      "eval_recall": 0.9728,
+      "eval_runtime": 579.8501,
+      "eval_samples_per_second": 6.467,
+      "eval_steps_per_second": 0.809,
+      "step": 1806
+    },
+    {
+      "epoch": 0.85,
+      "learning_rate": 7.746800731261426e-06,
+      "loss": 0.0583,
+      "step": 1849
+    },
+    {
+      "epoch": 0.85,
+      "eval_accuracy": 0.9893333333333333,
+      "eval_f1": 0.9893276414087514,
+      "eval_loss": 0.07162317633628845,
+      "eval_precision": 0.9898558462359851,
+      "eval_recall": 0.9888,
+      "eval_runtime": 579.4799,
+      "eval_samples_per_second": 6.471,
+      "eval_steps_per_second": 0.809,
+      "step": 1849
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 6.764168190127972e-06,
+      "loss": 0.0961,
+      "step": 1892
+    },
+    {
+      "epoch": 0.86,
+      "eval_accuracy": 0.988,
+      "eval_f1": 0.9879518072289156,
+      "eval_loss": 0.05759565904736519,
+      "eval_precision": 0.9919354838709677,
+      "eval_recall": 0.984,
+      "eval_runtime": 580.3503,
+      "eval_samples_per_second": 6.462,
+      "eval_steps_per_second": 0.808,
+      "step": 1892
+    },
+    {
+      "epoch": 0.88,
+      "learning_rate": 5.781535648994515e-06,
+      "loss": 0.0356,
+      "step": 1935
+    },
+    {
+      "epoch": 0.88,
+      "eval_accuracy": 0.9882666666666666,
+      "eval_f1": 0.9883103081827843,
+      "eval_loss": 0.06381053477525711,
+      "eval_precision": 0.984647961884595,
+      "eval_recall": 0.992,
+      "eval_runtime": 581.544,
+      "eval_samples_per_second": 6.448,
+      "eval_steps_per_second": 0.806,
+      "step": 1935
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 4.798903107861061e-06,
+      "loss": 0.0848,
+      "step": 1978
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.9893333333333333,
+      "eval_f1": 0.9893162393162394,
+      "eval_loss": 0.05824807286262512,
+      "eval_precision": 0.990904226859283,
+      "eval_recall": 0.9877333333333334,
+      "eval_runtime": 578.359,
+      "eval_samples_per_second": 6.484,
+      "eval_steps_per_second": 0.811,
+      "step": 1978
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 3.816270566727605e-06,
+      "loss": 0.1019,
+      "step": 2021
+    },
+    {
+      "epoch": 0.92,
+      "eval_accuracy": 0.9890666666666666,
+      "eval_f1": 0.9890579129970644,
+      "eval_loss": 0.055534329265356064,
+      "eval_precision": 0.9898504273504274,
+      "eval_recall": 0.9882666666666666,
+      "eval_runtime": 579.2162,
+      "eval_samples_per_second": 6.474,
+      "eval_steps_per_second": 0.81,
+      "step": 2021
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 2.83363802559415e-06,
+      "loss": 0.0274,
+      "step": 2064
+    },
+    {
+      "epoch": 0.94,
+      "eval_accuracy": 0.9893333333333333,
+      "eval_f1": 0.9892990904226859,
+      "eval_loss": 0.05893222615122795,
+      "eval_precision": 0.9924852388620504,
+      "eval_recall": 0.9861333333333333,
+      "eval_runtime": 581.1057,
+      "eval_samples_per_second": 6.453,
+      "eval_steps_per_second": 0.807,
+      "step": 2064
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.851005484460695e-06,
+      "loss": 0.0313,
+      "step": 2107
+    },
+    {
+      "epoch": 0.96,
+      "eval_accuracy": 0.9893333333333333,
+      "eval_f1": 0.9892933618843683,
+      "eval_loss": 0.0617961585521698,
+      "eval_precision": 0.9930145083288554,
+      "eval_recall": 0.9856,
+      "eval_runtime": 580.2597,
+      "eval_samples_per_second": 6.463,
+      "eval_steps_per_second": 0.808,
+      "step": 2107
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.683729433272396e-07,
+      "loss": 0.0513,
+      "step": 2150
+    },
+    {
+      "epoch": 0.98,
+      "eval_accuracy": 0.9898666666666667,
+      "eval_f1": 0.9898286937901497,
+      "eval_loss": 0.05942407250404358,
+      "eval_precision": 0.9935518538420204,
+      "eval_recall": 0.9861333333333333,
+      "eval_runtime": 580.5968,
+      "eval_samples_per_second": 6.459,
+      "eval_steps_per_second": 0.808,
+      "step": 2150
+    }
+  ],
+  "max_steps": 2188,
+  "num_train_epochs": 1,
+  "total_flos": 1.268902526976e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b738eba1cb47041e4ba06f5f99cf2e98a029ede364d6f2099fbb3349026301a2
+size 3451