Upload trained model and weights

.gitattributes

@@ -33,3 +33,5 @@ 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
+sample_data/mnist_test.csv filter=lfs diff=lfs merge=lfs -text
+sample_data/mnist_train_small.csv filter=lfs diff=lfs merge=lfs -text

sample_data/README.md

@@ -0,0 +1,19 @@
+This directory includes a few sample datasets to get you started.
+
+*   `california_housing_data*.csv` is California housing data from the 1990 US
+    Census; more information is available at:
+    https://docs.google.com/document/d/e/2PACX-1vRhYtsvc5eOR2FWNCwaBiKL6suIOrxJig8LcSBbmCbyYsayia_DvPOOBlXZ4CAlQ5nlDD8kTaIDRwrN/pub
+
+*   `mnist_*.csv` is a small sample of the
+    [MNIST database](https://en.wikipedia.org/wiki/MNIST_database), which is
+    described at: http://yann.lecun.com/exdb/mnist/
+
+*   `anscombe.json` contains a copy of
+    [Anscombe's quartet](https://en.wikipedia.org/wiki/Anscombe%27s_quartet); it
+    was originally described in
+
+    Anscombe, F. J. (1973). 'Graphs in Statistical Analysis'. American
+    Statistician. 27 (1): 17-21. JSTOR 2682899.
+
+    and our copy was prepared by the
+    [vega_datasets library](https://github.com/altair-viz/vega_datasets/blob/4f67bdaad10f45e3549984e17e1b3088c731503d/vega_datasets/_data/anscombe.json).

sample_data/anscombe.json

@@ -0,0 +1,49 @@
+[
+  {"Series":"I", "X":10.0, "Y":8.04},
+  {"Series":"I", "X":8.0, "Y":6.95},
+  {"Series":"I", "X":13.0, "Y":7.58},
+  {"Series":"I", "X":9.0, "Y":8.81},
+  {"Series":"I", "X":11.0, "Y":8.33},
+  {"Series":"I", "X":14.0, "Y":9.96},
+  {"Series":"I", "X":6.0, "Y":7.24},
+  {"Series":"I", "X":4.0, "Y":4.26},
+  {"Series":"I", "X":12.0, "Y":10.84},
+  {"Series":"I", "X":7.0, "Y":4.81},
+  {"Series":"I", "X":5.0, "Y":5.68},
+
+  {"Series":"II", "X":10.0, "Y":9.14},
+  {"Series":"II", "X":8.0, "Y":8.14},
+  {"Series":"II", "X":13.0, "Y":8.74},
+  {"Series":"II", "X":9.0, "Y":8.77},
+  {"Series":"II", "X":11.0, "Y":9.26},
+  {"Series":"II", "X":14.0, "Y":8.10},
+  {"Series":"II", "X":6.0, "Y":6.13},
+  {"Series":"II", "X":4.0, "Y":3.10},
+  {"Series":"II", "X":12.0, "Y":9.13},
+  {"Series":"II", "X":7.0, "Y":7.26},
+  {"Series":"II", "X":5.0, "Y":4.74},
+
+  {"Series":"III", "X":10.0, "Y":7.46},
+  {"Series":"III", "X":8.0, "Y":6.77},
+  {"Series":"III", "X":13.0, "Y":12.74},
+  {"Series":"III", "X":9.0, "Y":7.11},
+  {"Series":"III", "X":11.0, "Y":7.81},
+  {"Series":"III", "X":14.0, "Y":8.84},
+  {"Series":"III", "X":6.0, "Y":6.08},
+  {"Series":"III", "X":4.0, "Y":5.39},
+  {"Series":"III", "X":12.0, "Y":8.15},
+  {"Series":"III", "X":7.0, "Y":6.42},
+  {"Series":"III", "X":5.0, "Y":5.73},
+
+  {"Series":"IV", "X":8.0, "Y":6.58},
+  {"Series":"IV", "X":8.0, "Y":5.76},
+  {"Series":"IV", "X":8.0, "Y":7.71},
+  {"Series":"IV", "X":8.0, "Y":8.84},
+  {"Series":"IV", "X":8.0, "Y":8.47},
+  {"Series":"IV", "X":8.0, "Y":7.04},
+  {"Series":"IV", "X":8.0, "Y":5.25},
+  {"Series":"IV", "X":19.0, "Y":12.50},
+  {"Series":"IV", "X":8.0, "Y":5.56},
+  {"Series":"IV", "X":8.0, "Y":7.91},
+  {"Series":"IV", "X":8.0, "Y":6.89}
+]

sample_data/mnist_test.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51c292478d94ec3a01461bdfa82eb0885d262eb09e615679b2d69dedb6ad09e7
+size 18289443

sample_data/mnist_train_small.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ef64781aa03180f4f5ce504314f058f5d0227277df86060473d973cf43b033e
+size 36523880

wav2vec2-language-classifier/README.md

@@ -0,0 +1,34 @@
+---
+library_name: transformers
+pipeline_tag: audio-classification
+base_model: facebook/wav2vec2-base
+tags:
+- audio-classification
+- wav2vec2
+---
+
+# Nigerian language identification audio classifier
+
+## Model
+
+A Wav2Vec 2.0 base model fine-tuned for 13-class audio classification using Hugging Face `AutoModelForAudioClassification`. The repository contains standard Transformers configuration and weights; it does not require custom model code.
+
+## Labels
+
+The output IDs follow this exact order: `yor`, `ibo`, `hau`, `ego`, `anw`, `efi`, `ibb`, `idu`, `igl`, `nup`, `tiv`, `urh`, `other`.
+
+## Training data
+
+Fine-tuned using the training split of [`Data-Science-Nigeria/dsn-2026-lid-train`](https://huggingface.co/datasets/Data-Science-Nigeria/dsn-2026-lid-train); its validation split was used for checkpoint selection and evaluation. Audio is converted to mono and resampled to 16 kHz before feature extraction.
+
+## External pretrained model
+
+Initialization used [`facebook/wav2vec2-base`](https://huggingface.co/facebook/wav2vec2-base). No other external datasets were used by this notebook.
+
+## Loading
+
+Load with `AutoFeatureExtractor.from_pretrained(repo_id)` and `AutoModelForAudioClassification.from_pretrained(repo_id)`. Provide mono audio sampled at 16 kHz and use the saved feature extractor for normalization and padding.
+
+## License and use
+
+Review the source dataset and base-model license terms before redistribution or commercial use. This card does not grant additional rights.

wav2vec2-language-classifier/config.json

@@ -0,0 +1,149 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "yor",
+    "1": "ibo",
+    "2": "hau",
+    "3": "ego",
+    "4": "anw",
+    "5": "efi",
+    "6": "ibb",
+    "7": "idu",
+    "8": "igl",
+    "9": "nup",
+    "10": "tiv",
+    "11": "urh",
+    "12": "other"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "anw": 4,
+    "efi": 5,
+    "ego": 3,
+    "hau": 2,
+    "ibb": 6,
+    "ibo": 1,
+    "idu": 7,
+    "igl": 8,
+    "nup": 9,
+    "other": 12,
+    "tiv": 10,
+    "urh": 11,
+    "yor": 0
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "5.20.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

wav2vec2-language-classifier/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592aaec6d765fc8dc65c19be3b265f32e71d6324c5c31fc613e4295a65cb77ce
+size 378313628

wav2vec2-language-classifier/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

wav2vec2_language_model/config.json

@@ -0,0 +1,149 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LANGUAGE_0",
+    "1": "LANGUAGE_1",
+    "2": "LANGUAGE_2",
+    "3": "LANGUAGE_3",
+    "4": "LANGUAGE_4",
+    "5": "LANGUAGE_5",
+    "6": "LANGUAGE_6",
+    "7": "LANGUAGE_7",
+    "8": "LANGUAGE_8",
+    "9": "LANGUAGE_9",
+    "10": "LANGUAGE_10",
+    "11": "LANGUAGE_11",
+    "12": "LANGUAGE_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LANGUAGE_0": 0,
+    "LANGUAGE_1": 1,
+    "LANGUAGE_10": 10,
+    "LANGUAGE_11": 11,
+    "LANGUAGE_12": 12,
+    "LANGUAGE_2": 2,
+    "LANGUAGE_3": 3,
+    "LANGUAGE_4": 4,
+    "LANGUAGE_5": 5,
+    "LANGUAGE_6": 6,
+    "LANGUAGE_7": 7,
+    "LANGUAGE_8": 8,
+    "LANGUAGE_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "5.20.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

wav2vec2_language_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592aaec6d765fc8dc65c19be3b265f32e71d6324c5c31fc613e4295a65cb77ce
+size 378313628

wav2vec2_language_model/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

wav2vec2_language_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdfe243cb818b4cb8a5132d003adba632b3036cdc171c5bac021b0b5973f7c8
+size 5201

wav2vec2_language_training/checkpoint-6194/config.json

@@ -0,0 +1,149 @@
+{
+  "activation_dropout": 0.0,
+  "adapter_attn_dim": null,
+  "adapter_kernel_size": 3,
+  "adapter_stride": 2,
+  "add_adapter": false,
+  "apply_spec_augment": true,
+  "architectures": [
+    "Wav2Vec2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 1,
+  "classifier_proj_size": 256,
+  "codevector_dim": 256,
+  "contrastive_logits_temperature": 0.1,
+  "conv_bias": false,
+  "conv_dim": [
+    512,
+    512,
+    512,
+    512,
+    512,
+    512,
+    512
+  ],
+  "conv_kernel": [
+    10,
+    3,
+    3,
+    3,
+    3,
+    2,
+    2
+  ],
+  "conv_stride": [
+    5,
+    2,
+    2,
+    2,
+    2,
+    2,
+    2
+  ],
+  "ctc_loss_reduction": "sum",
+  "ctc_zero_infinity": false,
+  "diversity_loss_weight": 0.1,
+  "do_stable_layer_norm": false,
+  "dtype": "float32",
+  "eos_token_id": 2,
+  "feat_extract_activation": "gelu",
+  "feat_extract_norm": "group",
+  "feat_proj_dropout": 0.1,
+  "feat_quantizer_dropout": 0.0,
+  "final_dropout": 0.0,
+  "freeze_feat_extract_train": true,
+  "hidden_act": "gelu",
+  "hidden_dropout": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LANGUAGE_0",
+    "1": "LANGUAGE_1",
+    "2": "LANGUAGE_2",
+    "3": "LANGUAGE_3",
+    "4": "LANGUAGE_4",
+    "5": "LANGUAGE_5",
+    "6": "LANGUAGE_6",
+    "7": "LANGUAGE_7",
+    "8": "LANGUAGE_8",
+    "9": "LANGUAGE_9",
+    "10": "LANGUAGE_10",
+    "11": "LANGUAGE_11",
+    "12": "LANGUAGE_12"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LANGUAGE_0": 0,
+    "LANGUAGE_1": 1,
+    "LANGUAGE_10": 10,
+    "LANGUAGE_11": 11,
+    "LANGUAGE_12": 12,
+    "LANGUAGE_2": 2,
+    "LANGUAGE_3": 3,
+    "LANGUAGE_4": 4,
+    "LANGUAGE_5": 5,
+    "LANGUAGE_6": 6,
+    "LANGUAGE_7": 7,
+    "LANGUAGE_8": 8,
+    "LANGUAGE_9": 9
+  },
+  "layer_norm_eps": 1e-05,
+  "layerdrop": 0.0,
+  "mask_channel_length": 10,
+  "mask_channel_min_space": 1,
+  "mask_channel_other": 0.0,
+  "mask_channel_prob": 0.0,
+  "mask_channel_selection": "static",
+  "mask_feature_length": 10,
+  "mask_feature_min_masks": 0,
+  "mask_feature_prob": 0.0,
+  "mask_time_length": 10,
+  "mask_time_min_masks": 2,
+  "mask_time_min_space": 1,
+  "mask_time_other": 0.0,
+  "mask_time_prob": 0.05,
+  "mask_time_selection": "static",
+  "model_type": "wav2vec2",
+  "no_mask_channel_overlap": false,
+  "no_mask_time_overlap": false,
+  "num_adapter_layers": 3,
+  "num_attention_heads": 12,
+  "num_codevector_groups": 2,
+  "num_codevectors_per_group": 320,
+  "num_conv_pos_embedding_groups": 16,
+  "num_conv_pos_embeddings": 128,
+  "num_feat_extract_layers": 7,
+  "num_hidden_layers": 12,
+  "num_negatives": 100,
+  "output_hidden_size": 768,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "proj_codevector_dim": 256,
+  "tdnn_dilation": [
+    1,
+    2,
+    3,
+    1,
+    1
+  ],
+  "tdnn_dim": [
+    512,
+    512,
+    512,
+    512,
+    1500
+  ],
+  "tdnn_kernel": [
+    5,
+    3,
+    3,
+    1,
+    1
+  ],
+  "transformers_version": "5.20.1",
+  "use_cache": false,
+  "use_weighted_layer_sum": false,
+  "vocab_size": 32,
+  "xvector_output_dim": 512
+}

wav2vec2_language_training/checkpoint-6194/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:592aaec6d765fc8dc65c19be3b265f32e71d6324c5c31fc613e4295a65cb77ce
+size 378313628

wav2vec2_language_training/checkpoint-6194/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dcc60cf59b45483d0878d45fce5c4ba86c7ea04fb307926df665d6714d336c
+size 723144395

wav2vec2_language_training/checkpoint-6194/preprocessor_config.json

@@ -0,0 +1,9 @@
+{
+  "do_normalize": true,
+  "feature_extractor_type": "Wav2Vec2FeatureExtractor",
+  "feature_size": 1,
+  "padding_side": "right",
+  "padding_value": 0.0,
+  "return_attention_mask": false,
+  "sampling_rate": 16000
+}

wav2vec2_language_training/checkpoint-6194/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813336f8acbbf2057583afd83a064c3f28640f27ec95ac2019c414857aff1a01
+size 14709

wav2vec2_language_training/checkpoint-6194/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc4d3efc8c43b072af87a7873b91b2d9c49e693f9790afb939c882c3e0e7fab0
+size 1383

wav2vec2_language_training/checkpoint-6194/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbb4b5a2c3668dc8f3ca16fdb6f6f188770426c5fe6b37d597420b2412b51676
+size 1465

wav2vec2_language_training/checkpoint-6194/trainer_state.json

@@ -0,0 +1,922 @@
+{
+  "best_global_step": 6194,
+  "best_metric": 0.5512355991216289,
+  "best_model_checkpoint": "/content/wav2vec2_language_training/checkpoint-6194",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 6194,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0003229191894728344,
+      "grad_norm": 4.529106140136719,
+      "learning_rate": 0.0,
+      "loss": 10.3095703125,
+      "step": 1
+    },
+    {
+      "epoch": 0.01614595947364172,
+      "grad_norm": 6.193228721618652,
+      "learning_rate": 1.5806451612903226e-06,
+      "loss": 10.245216836734693,
+      "step": 50
+    },
+    {
+      "epoch": 0.03229191894728344,
+      "grad_norm": 5.889149188995361,
+      "learning_rate": 3.1935483870967742e-06,
+      "loss": 10.12197265625,
+      "step": 100
+    },
+    {
+      "epoch": 0.048437878420925166,
+      "grad_norm": 5.440003871917725,
+      "learning_rate": 4.806451612903226e-06,
+      "loss": 9.8630078125,
+      "step": 150
+    },
+    {
+      "epoch": 0.06458383789456688,
+      "grad_norm": 5.057761192321777,
+      "learning_rate": 6.419354838709678e-06,
+      "loss": 9.546591796875,
+      "step": 200
+    },
+    {
+      "epoch": 0.08072979736820861,
+      "grad_norm": 12.384038925170898,
+      "learning_rate": 8.032258064516129e-06,
+      "loss": 9.23125,
+      "step": 250
+    },
+    {
+      "epoch": 0.09687575684185033,
+      "grad_norm": 15.254081726074219,
+      "learning_rate": 9.645161290322581e-06,
+      "loss": 8.889169921875,
+      "step": 300
+    },
+    {
+      "epoch": 0.11302171631549204,
+      "grad_norm": 14.756054878234863,
+      "learning_rate": 1.1225806451612904e-05,
+      "loss": 8.3898046875,
+      "step": 350
+    },
+    {
+      "epoch": 0.12916767578913377,
+      "grad_norm": 13.519452095031738,
+      "learning_rate": 1.2838709677419356e-05,
+      "loss": 7.8390625,
+      "step": 400
+    },
+    {
+      "epoch": 0.1453136352627755,
+      "grad_norm": 16.962438583374023,
+      "learning_rate": 1.4451612903225808e-05,
+      "loss": 7.288056640625,
+      "step": 450
+    },
+    {
+      "epoch": 0.16145959473641722,
+      "grad_norm": 14.071990966796875,
+      "learning_rate": 1.6e-05,
+      "loss": 6.672119140625,
+      "step": 500
+    },
+    {
+      "epoch": 0.17760555421005894,
+      "grad_norm": 13.917470932006836,
+      "learning_rate": 1.761290322580645e-05,
+      "loss": 6.397265625,
+      "step": 550
+    },
+    {
+      "epoch": 0.19375151368370067,
+      "grad_norm": 27.340486526489258,
+      "learning_rate": 1.9225806451612903e-05,
+      "loss": 5.6450439453125,
+      "step": 600
+    },
+    {
+      "epoch": 0.20989747315734236,
+      "grad_norm": 25.902238845825195,
+      "learning_rate": 2.0838709677419355e-05,
+      "loss": 5.333974609375,
+      "step": 650
+    },
+    {
+      "epoch": 0.2260434326309841,
+      "grad_norm": 18.885643005371094,
+      "learning_rate": 2.2451612903225807e-05,
+      "loss": 4.46815673828125,
+      "step": 700
+    },
+    {
+      "epoch": 0.2421893921046258,
+      "grad_norm": 22.254283905029297,
+      "learning_rate": 2.406451612903226e-05,
+      "loss": 4.218232421875,
+      "step": 750
+    },
+    {
+      "epoch": 0.25833535157826754,
+      "grad_norm": 25.992233276367188,
+      "learning_rate": 2.567741935483871e-05,
+      "loss": 3.91445556640625,
+      "step": 800
+    },
+    {
+      "epoch": 0.27448131105190926,
+      "grad_norm": 77.59001922607422,
+      "learning_rate": 2.725806451612903e-05,
+      "loss": 3.67336181640625,
+      "step": 850
+    },
+    {
+      "epoch": 0.290627270525551,
+      "grad_norm": 31.094411849975586,
+      "learning_rate": 2.8870967741935486e-05,
+      "loss": 3.261075439453125,
+      "step": 900
+    },
+    {
+      "epoch": 0.3067732299991927,
+      "grad_norm": 41.47936248779297,
+      "learning_rate": 2.994617868675996e-05,
+      "loss": 2.489803466796875,
+      "step": 950
+    },
+    {
+      "epoch": 0.32291918947283443,
+      "grad_norm": 159.16732788085938,
+      "learning_rate": 2.9766774309293145e-05,
+      "loss": 2.5213555908203125,
+      "step": 1000
+    },
+    {
+      "epoch": 0.33906514894647616,
+      "grad_norm": 52.00654220581055,
+      "learning_rate": 2.958736993182634e-05,
+      "loss": 2.388968505859375,
+      "step": 1050
+    },
+    {
+      "epoch": 0.3552111084201179,
+      "grad_norm": 47.637367248535156,
+      "learning_rate": 2.9407965554359525e-05,
+      "loss": 2.18392578125,
+      "step": 1100
+    },
+    {
+      "epoch": 0.3713570678937596,
+      "grad_norm": 2.488032579421997,
+      "learning_rate": 2.9228561176892717e-05,
+      "loss": 2.210579833984375,
+      "step": 1150
+    },
+    {
+      "epoch": 0.38750302736740133,
+      "grad_norm": 52.456260681152344,
+      "learning_rate": 2.9052744886975244e-05,
+      "loss": 1.9025732421875,
+      "step": 1200
+    },
+    {
+      "epoch": 0.40364898684104306,
+      "grad_norm": 54.909751892089844,
+      "learning_rate": 2.887334050950843e-05,
+      "loss": 1.8073741149902345,
+      "step": 1250
+    },
+    {
+      "epoch": 0.4197949463146847,
+      "grad_norm": 3.8414134979248047,
+      "learning_rate": 2.8693936132041623e-05,
+      "loss": 1.5696636962890624,
+      "step": 1300
+    },
+    {
+      "epoch": 0.43594090578832645,
+      "grad_norm": 52.5399169921875,
+      "learning_rate": 2.851453175457481e-05,
+      "loss": 1.7823171997070313,
+      "step": 1350
+    },
+    {
+      "epoch": 0.4520868652619682,
+      "grad_norm": 14.362801551818848,
+      "learning_rate": 2.8335127377108002e-05,
+      "loss": 1.558516082763672,
+      "step": 1400
+    },
+    {
+      "epoch": 0.4682328247356099,
+      "grad_norm": 113.1703109741211,
+      "learning_rate": 2.8155722999641195e-05,
+      "loss": 2.160206604003906,
+      "step": 1450
+    },
+    {
+      "epoch": 0.4843787842092516,
+      "grad_norm": 105.39362335205078,
+      "learning_rate": 2.797990670972372e-05,
+      "loss": 1.5175074768066406,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5005247436828933,
+      "grad_norm": 86.96612548828125,
+      "learning_rate": 2.7800502332256908e-05,
+      "loss": 1.5383221435546874,
+      "step": 1550
+    },
+    {
+      "epoch": 0.5166707031565351,
+      "grad_norm": 7.717394828796387,
+      "learning_rate": 2.7621097954790098e-05,
+      "loss": 1.5705889892578124,
+      "step": 1600
+    },
+    {
+      "epoch": 0.5328166626301768,
+      "grad_norm": 2.287020683288574,
+      "learning_rate": 2.7441693577323287e-05,
+      "loss": 1.8836233520507812,
+      "step": 1650
+    },
+    {
+      "epoch": 0.5489626221038185,
+      "grad_norm": 15.948859214782715,
+      "learning_rate": 2.7262289199856477e-05,
+      "loss": 1.8712867736816405,
+      "step": 1700
+    },
+    {
+      "epoch": 0.5651085815774602,
+      "grad_norm": 0.29794925451278687,
+      "learning_rate": 2.7082884822389666e-05,
+      "loss": 1.4848959350585937,
+      "step": 1750
+    },
+    {
+      "epoch": 0.581254541051102,
+      "grad_norm": 25.859098434448242,
+      "learning_rate": 2.690348044492286e-05,
+      "loss": 1.7219607543945312,
+      "step": 1800
+    },
+    {
+      "epoch": 0.5974005005247437,
+      "grad_norm": 0.33948394656181335,
+      "learning_rate": 2.6724076067456045e-05,
+      "loss": 1.4369366455078125,
+      "step": 1850
+    },
+    {
+      "epoch": 0.6135464599983854,
+      "grad_norm": 0.4031808078289032,
+      "learning_rate": 2.6544671689989238e-05,
+      "loss": 1.3836166381835937,
+      "step": 1900
+    },
+    {
+      "epoch": 0.6296924194720271,
+      "grad_norm": 28.81092643737793,
+      "learning_rate": 2.6365267312522424e-05,
+      "loss": 1.190876693725586,
+      "step": 1950
+    },
+    {
+      "epoch": 0.6458383789456689,
+      "grad_norm": 1.56308114528656,
+      "learning_rate": 2.6185862935055617e-05,
+      "loss": 1.3827902221679687,
+      "step": 2000
+    },
+    {
+      "epoch": 0.6619843384193106,
+      "grad_norm": 50.89561462402344,
+      "learning_rate": 2.6006458557588803e-05,
+      "loss": 1.63328369140625,
+      "step": 2050
+    },
+    {
+      "epoch": 0.6781302978929523,
+      "grad_norm": 104.78791046142578,
+      "learning_rate": 2.5827054180121996e-05,
+      "loss": 1.399237060546875,
+      "step": 2100
+    },
+    {
+      "epoch": 0.694276257366594,
+      "grad_norm": 0.4712347984313965,
+      "learning_rate": 2.5647649802655186e-05,
+      "loss": 1.3350747680664063,
+      "step": 2150
+    },
+    {
+      "epoch": 0.7104222168402358,
+      "grad_norm": 64.95288848876953,
+      "learning_rate": 2.5468245425188375e-05,
+      "loss": 1.3802346801757812,
+      "step": 2200
+    },
+    {
+      "epoch": 0.7265681763138775,
+      "grad_norm": 373.7409973144531,
+      "learning_rate": 2.5288841047721565e-05,
+      "loss": 1.3444012451171874,
+      "step": 2250
+    },
+    {
+      "epoch": 0.7427141357875192,
+      "grad_norm": 0.42600125074386597,
+      "learning_rate": 2.5109436670254754e-05,
+      "loss": 1.2518025970458984,
+      "step": 2300
+    },
+    {
+      "epoch": 0.7588600952611609,
+      "grad_norm": 213.501953125,
+      "learning_rate": 2.4930032292787944e-05,
+      "loss": 1.4227603149414063,
+      "step": 2350
+    },
+    {
+      "epoch": 0.7750060547348027,
+      "grad_norm": 0.10485175997018814,
+      "learning_rate": 2.4750627915321133e-05,
+      "loss": 0.9105004119873047,
+      "step": 2400
+    },
+    {
+      "epoch": 0.7911520142084444,
+      "grad_norm": 1.8309723138809204,
+      "learning_rate": 2.4571223537854323e-05,
+      "loss": 1.3791087341308594,
+      "step": 2450
+    },
+    {
+      "epoch": 0.8072979736820861,
+      "grad_norm": 54.78936767578125,
+      "learning_rate": 2.4391819160387513e-05,
+      "loss": 1.1874938201904297,
+      "step": 2500
+    },
+    {
+      "epoch": 0.8234439331557277,
+      "grad_norm": 1.7623909711837769,
+      "learning_rate": 2.4212414782920705e-05,
+      "loss": 1.3522792053222656,
+      "step": 2550
+    },
+    {
+      "epoch": 0.8395898926293694,
+      "grad_norm": 0.08053799718618393,
+      "learning_rate": 2.4033010405453895e-05,
+      "loss": 0.9789678955078125,
+      "step": 2600
+    },
+    {
+      "epoch": 0.8557358521030112,
+      "grad_norm": 3.5259974002838135,
+      "learning_rate": 2.3853606027987084e-05,
+      "loss": 0.90770751953125,
+      "step": 2650
+    },
+    {
+      "epoch": 0.8718818115766529,
+      "grad_norm": 151.7379913330078,
+      "learning_rate": 2.3674201650520274e-05,
+      "loss": 0.7401080322265625,
+      "step": 2700
+    },
+    {
+      "epoch": 0.8880277710502946,
+      "grad_norm": 52.41484069824219,
+      "learning_rate": 2.3494797273053464e-05,
+      "loss": 1.2729526519775392,
+      "step": 2750
+    },
+    {
+      "epoch": 0.9041737305239363,
+      "grad_norm": 20.753765106201172,
+      "learning_rate": 2.3315392895586653e-05,
+      "loss": 1.478377685546875,
+      "step": 2800
+    },
+    {
+      "epoch": 0.9203196899975781,
+      "grad_norm": 29.068288803100586,
+      "learning_rate": 2.3135988518119843e-05,
+      "loss": 1.3437759399414062,
+      "step": 2850
+    },
+    {
+      "epoch": 0.9364656494712198,
+      "grad_norm": 24.227148056030273,
+      "learning_rate": 2.2956584140653032e-05,
+      "loss": 1.5581495666503906,
+      "step": 2900
+    },
+    {
+      "epoch": 0.9526116089448615,
+      "grad_norm": 6.875829219818115,
+      "learning_rate": 2.277717976318622e-05,
+      "loss": 0.8706295776367188,
+      "step": 2950
+    },
+    {
+      "epoch": 0.9687575684185032,
+      "grad_norm": 0.09882869571447372,
+      "learning_rate": 2.259777538571941e-05,
+      "loss": 0.7462836456298828,
+      "step": 3000
+    },
+    {
+      "epoch": 0.984903527892145,
+      "grad_norm": 29.986154556274414,
+      "learning_rate": 2.2418371008252604e-05,
+      "loss": 0.7867819213867188,
+      "step": 3050
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7111672794117647,
+      "eval_loss": 1.9589920043945312,
+      "eval_macro_f1": 0.47027741415125807,
+      "eval_runtime": 173.4063,
+      "eval_samples_per_second": 25.097,
+      "eval_steps_per_second": 12.549,
+      "step": 3097
+    },
+    {
+      "epoch": 1.0009687575684185,
+      "grad_norm": 0.09820611774921417,
+      "learning_rate": 2.223896663078579e-05,
+      "loss": 1.2130521392822267,
+      "step": 3100
+    },
+    {
+      "epoch": 1.0171147170420602,
+      "grad_norm": 0.7431126236915588,
+      "learning_rate": 2.2059562253318983e-05,
+      "loss": 0.8128555297851563,
+      "step": 3150
+    },
+    {
+      "epoch": 1.033260676515702,
+      "grad_norm": 0.7170122861862183,
+      "learning_rate": 2.188015787585217e-05,
+      "loss": 1.0764289093017578,
+      "step": 3200
+    },
+    {
+      "epoch": 1.0494066359893437,
+      "grad_norm": 191.59495544433594,
+      "learning_rate": 2.1700753498385362e-05,
+      "loss": 1.2996231079101563,
+      "step": 3250
+    },
+    {
+      "epoch": 1.0655525954629854,
+      "grad_norm": 0.5435243248939514,
+      "learning_rate": 2.152134912091855e-05,
+      "loss": 0.5811257934570313,
+      "step": 3300
+    },
+    {
+      "epoch": 1.0816985549366271,
+      "grad_norm": 0.16059564054012299,
+      "learning_rate": 2.134194474345174e-05,
+      "loss": 0.42670497894287107,
+      "step": 3350
+    },
+    {
+      "epoch": 1.0978445144102689,
+      "grad_norm": 0.04560324549674988,
+      "learning_rate": 2.1166128453534268e-05,
+      "loss": 1.103641586303711,
+      "step": 3400
+    },
+    {
+      "epoch": 1.1139904738839106,
+      "grad_norm": 0.08320432901382446,
+      "learning_rate": 2.0986724076067454e-05,
+      "loss": 0.6239488220214844,
+      "step": 3450
+    },
+    {
+      "epoch": 1.1301364333575523,
+      "grad_norm": 0.10506195574998856,
+      "learning_rate": 2.0807319698600647e-05,
+      "loss": 0.8145645141601563,
+      "step": 3500
+    },
+    {
+      "epoch": 1.146282392831194,
+      "grad_norm": 103.13922882080078,
+      "learning_rate": 2.0627915321133837e-05,
+      "loss": 0.6019972229003906,
+      "step": 3550
+    },
+    {
+      "epoch": 1.1624283523048358,
+      "grad_norm": 152.7489013671875,
+      "learning_rate": 2.0448510943667026e-05,
+      "loss": 0.9050732421875,
+      "step": 3600
+    },
+    {
+      "epoch": 1.1785743117784775,
+      "grad_norm": 42.289886474609375,
+      "learning_rate": 2.0269106566200216e-05,
+      "loss": 0.5771483612060547,
+      "step": 3650
+    },
+    {
+      "epoch": 1.1947202712521192,
+      "grad_norm": 0.036882005631923676,
+      "learning_rate": 2.0089702188733405e-05,
+      "loss": 0.5724046707153321,
+      "step": 3700
+    },
+    {
+      "epoch": 1.210866230725761,
+      "grad_norm": 0.0331718809902668,
+      "learning_rate": 1.9910297811266598e-05,
+      "loss": 0.5135692596435547,
+      "step": 3750
+    },
+    {
+      "epoch": 1.2270121901994027,
+      "grad_norm": 0.14064890146255493,
+      "learning_rate": 1.9730893433799784e-05,
+      "loss": 0.7010717010498047,
+      "step": 3800
+    },
+    {
+      "epoch": 1.2431581496730444,
+      "grad_norm": 0.03307172656059265,
+      "learning_rate": 1.9551489056332977e-05,
+      "loss": 0.963626480102539,
+      "step": 3850
+    },
+    {
+      "epoch": 1.2593041091466861,
+      "grad_norm": 0.6310042142868042,
+      "learning_rate": 1.9372084678866163e-05,
+      "loss": 0.618631591796875,
+      "step": 3900
+    },
+    {
+      "epoch": 1.2754500686203278,
+      "grad_norm": 0.03170113265514374,
+      "learning_rate": 1.9192680301399356e-05,
+      "loss": 0.5910566329956055,
+      "step": 3950
+    },
+    {
+      "epoch": 1.2915960280939696,
+      "grad_norm": 0.059453096240758896,
+      "learning_rate": 1.9013275923932542e-05,
+      "loss": 0.8205435180664062,
+      "step": 4000
+    },
+    {
+      "epoch": 1.3077419875676113,
+      "grad_norm": 8.148303031921387,
+      "learning_rate": 1.8833871546465735e-05,
+      "loss": 0.895206069946289,
+      "step": 4050
+    },
+    {
+      "epoch": 1.323887947041253,
+      "grad_norm": 0.056840892881155014,
+      "learning_rate": 1.8654467168998925e-05,
+      "loss": 0.9973079681396484,
+      "step": 4100
+    },
+    {
+      "epoch": 1.3400339065148947,
+      "grad_norm": 221.93252563476562,
+      "learning_rate": 1.8475062791532114e-05,
+      "loss": 0.7970662689208985,
+      "step": 4150
+    },
+    {
+      "epoch": 1.3561798659885365,
+      "grad_norm": 0.031388379633426666,
+      "learning_rate": 1.8295658414065304e-05,
+      "loss": 0.5861995697021485,
+      "step": 4200
+    },
+    {
+      "epoch": 1.3723258254621782,
+      "grad_norm": 67.99932861328125,
+      "learning_rate": 1.8116254036598493e-05,
+      "loss": 0.7056297302246094,
+      "step": 4250
+    },
+    {
+      "epoch": 1.38847178493582,
+      "grad_norm": 0.025887133553624153,
+      "learning_rate": 1.7936849659131683e-05,
+      "loss": 0.48784542083740234,
+      "step": 4300
+    },
+    {
+      "epoch": 1.4046177444094616,
+      "grad_norm": 0.021569272503256798,
+      "learning_rate": 1.7757445281664872e-05,
+      "loss": 0.8278440856933593,
+      "step": 4350
+    },
+    {
+      "epoch": 1.4207637038831034,
+      "grad_norm": 0.09651536494493484,
+      "learning_rate": 1.7578040904198062e-05,
+      "loss": 0.41228450775146486,
+      "step": 4400
+    },
+    {
+      "epoch": 1.436909663356745,
+      "grad_norm": 29.48873519897461,
+      "learning_rate": 1.739863652673125e-05,
+      "loss": 0.4472889709472656,
+      "step": 4450
+    },
+    {
+      "epoch": 1.4530556228303868,
+      "grad_norm": 326.61590576171875,
+      "learning_rate": 1.721923214926444e-05,
+      "loss": 1.1229263305664063,
+      "step": 4500
+    },
+    {
+      "epoch": 1.4692015823040285,
+      "grad_norm": 0.01840817742049694,
+      "learning_rate": 1.7039827771797634e-05,
+      "loss": 0.856488265991211,
+      "step": 4550
+    },
+    {
+      "epoch": 1.4853475417776703,
+      "grad_norm": 0.0707959309220314,
+      "learning_rate": 1.686042339433082e-05,
+      "loss": 0.4026166915893555,
+      "step": 4600
+    },
+    {
+      "epoch": 1.501493501251312,
+      "grad_norm": 0.06531866639852524,
+      "learning_rate": 1.6681019016864013e-05,
+      "loss": 0.5517042922973633,
+      "step": 4650
+    },
+    {
+      "epoch": 1.5176394607249537,
+      "grad_norm": 0.022350989282131195,
+      "learning_rate": 1.65016146393972e-05,
+      "loss": 0.5183643722534179,
+      "step": 4700
+    },
+    {
+      "epoch": 1.5337854201985954,
+      "grad_norm": 25.701091766357422,
+      "learning_rate": 1.6322210261930392e-05,
+      "loss": 0.5924579238891602,
+      "step": 4750
+    },
+    {
+      "epoch": 1.5499313796722372,
+      "grad_norm": 0.014405378140509129,
+      "learning_rate": 1.614280588446358e-05,
+      "loss": 0.34974132537841796,
+      "step": 4800
+    },
+    {
+      "epoch": 1.5660773391458789,
+      "grad_norm": 65.70176696777344,
+      "learning_rate": 1.596340150699677e-05,
+      "loss": 0.8746366119384765,
+      "step": 4850
+    },
+    {
+      "epoch": 1.5822232986195206,
+      "grad_norm": 0.019803257659077644,
+      "learning_rate": 1.5783997129529964e-05,
+      "loss": 0.22654096603393556,
+      "step": 4900
+    },
+    {
+      "epoch": 1.5983692580931623,
+      "grad_norm": 0.026351263746619225,
+      "learning_rate": 1.560459275206315e-05,
+      "loss": 0.6935590362548828,
+      "step": 4950
+    },
+    {
+      "epoch": 1.614515217566804,
+      "grad_norm": 0.014122542925179005,
+      "learning_rate": 1.5425188374596343e-05,
+      "loss": 0.6047145080566406,
+      "step": 5000
+    },
+    {
+      "epoch": 1.6306611770404458,
+      "grad_norm": 145.31405639648438,
+      "learning_rate": 1.524578399712953e-05,
+      "loss": 0.4947609710693359,
+      "step": 5050
+    },
+    {
+      "epoch": 1.6468071365140875,
+      "grad_norm": 358.01763916015625,
+      "learning_rate": 1.506637961966272e-05,
+      "loss": 0.8425590515136718,
+      "step": 5100
+    },
+    {
+      "epoch": 1.6629530959877292,
+      "grad_norm": 18.266508102416992,
+      "learning_rate": 1.488697524219591e-05,
+      "loss": 0.37045562744140625,
+      "step": 5150
+    },
+    {
+      "epoch": 1.679099055461371,
+      "grad_norm": 8.323086738586426,
+      "learning_rate": 1.47075708647291e-05,
+      "loss": 0.46268028259277344,
+      "step": 5200
+    },
+    {
+      "epoch": 1.6952450149350127,
+      "grad_norm": 0.2699354290962219,
+      "learning_rate": 1.4528166487262289e-05,
+      "loss": 0.5819450378417969,
+      "step": 5250
+    },
+    {
+      "epoch": 1.7113909744086544,
+      "grad_norm": 0.020911041647195816,
+      "learning_rate": 1.434876210979548e-05,
+      "loss": 0.2076406669616699,
+      "step": 5300
+    },
+    {
+      "epoch": 1.7275369338822961,
+      "grad_norm": 5.135980129241943,
+      "learning_rate": 1.416935773232867e-05,
+      "loss": 0.5862969970703125,
+      "step": 5350
+    },
+    {
+      "epoch": 1.7436828933559376,
+      "grad_norm": 0.011412340216338634,
+      "learning_rate": 1.398995335486186e-05,
+      "loss": 0.519563217163086,
+      "step": 5400
+    },
+    {
+      "epoch": 1.7598288528295793,
+      "grad_norm": 0.07782480865716934,
+      "learning_rate": 1.3810548977395049e-05,
+      "loss": 0.5034203338623047,
+      "step": 5450
+    },
+    {
+      "epoch": 1.775974812303221,
+      "grad_norm": 0.012429723516106606,
+      "learning_rate": 1.3631144599928238e-05,
+      "loss": 0.44504608154296876,
+      "step": 5500
+    },
+    {
+      "epoch": 1.7921207717768628,
+      "grad_norm": 0.0393192283809185,
+      "learning_rate": 1.345174022246143e-05,
+      "loss": 0.25914430618286133,
+      "step": 5550
+    },
+    {
+      "epoch": 1.8082667312505045,
+      "grad_norm": 0.011711121536791325,
+      "learning_rate": 1.3272335844994619e-05,
+      "loss": 0.29473932266235353,
+      "step": 5600
+    },
+    {
+      "epoch": 1.8244126907241462,
+      "grad_norm": 0.05490946024656296,
+      "learning_rate": 1.3092931467527809e-05,
+      "loss": 0.7466780090332031,
+      "step": 5650
+    },
+    {
+      "epoch": 1.840558650197788,
+      "grad_norm": 0.017267636954784393,
+      "learning_rate": 1.2913527090060998e-05,
+      "loss": 0.48324256896972656,
+      "step": 5700
+    },
+    {
+      "epoch": 1.8567046096714297,
+      "grad_norm": 46.87386703491211,
+      "learning_rate": 1.2734122712594188e-05,
+      "loss": 0.4969118881225586,
+      "step": 5750
+    },
+    {
+      "epoch": 1.8728505691450714,
+      "grad_norm": 0.02415432594716549,
+      "learning_rate": 1.2554718335127377e-05,
+      "loss": 0.4797199249267578,
+      "step": 5800
+    },
+    {
+      "epoch": 1.8889965286187131,
+      "grad_norm": 0.03615964576601982,
+      "learning_rate": 1.2375313957660567e-05,
+      "loss": 0.519180908203125,
+      "step": 5850
+    },
+    {
+      "epoch": 1.9051424880923549,
+      "grad_norm": 0.016299840062856674,
+      "learning_rate": 1.2195909580193756e-05,
+      "loss": 0.7245436859130859,
+      "step": 5900
+    },
+    {
+      "epoch": 1.9212884475659966,
+      "grad_norm": 0.027891967445611954,
+      "learning_rate": 1.2016505202726947e-05,
+      "loss": 0.4619031524658203,
+      "step": 5950
+    },
+    {
+      "epoch": 1.9374344070396383,
+      "grad_norm": 67.29586791992188,
+      "learning_rate": 1.1837100825260137e-05,
+      "loss": 0.5155964660644531,
+      "step": 6000
+    },
+    {
+      "epoch": 1.95358036651328,
+      "grad_norm": 0.1323629766702652,
+      "learning_rate": 1.1657696447793327e-05,
+      "loss": 0.3697730255126953,
+      "step": 6050
+    },
+    {
+      "epoch": 1.9697263259869218,
+      "grad_norm": 115.05311584472656,
+      "learning_rate": 1.1478292070326516e-05,
+      "loss": 0.23215339660644532,
+      "step": 6100
+    },
+    {
+      "epoch": 1.9858722854605635,
+      "grad_norm": 0.012714232318103313,
+      "learning_rate": 1.1298887692859706e-05,
+      "loss": 0.2971592330932617,
+      "step": 6150
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7966452205882353,
+      "eval_loss": 1.547814130783081,
+      "eval_macro_f1": 0.5512355991216289,
+      "eval_runtime": 172.8575,
+      "eval_samples_per_second": 25.177,
+      "eval_steps_per_second": 12.588,
+      "step": 6194
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 9291,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.806034665698302e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

wav2vec2_language_training/checkpoint-6194/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4cdfe243cb818b4cb8a5132d003adba632b3036cdc171c5bac021b0b5973f7c8
+size 5201