Upload with huggingface_hub

README.md

@@ -0,0 +1,15 @@
+---
+license: apache-2.0
+tags:
+- canine
+- pretrained-on-english-language
+---
+
+### How to use
+
+Here is how to use this model:
+
+```python
+from transformers import CanineModel
+model = CanineModel.from_pretrained('mushfiqur11/<repo name>')
+```

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 21.63,
+    "eval_las": 91.75966152710339,
+    "eval_loss": 0.7071714401245117,
+    "eval_runtime": 11.7748,
+    "eval_samples": 1659,
+    "eval_samples_per_second": 140.894,
+    "eval_steps_per_second": 17.665,
+    "eval_uas": 95.23525570037198,
+    "test_las": 91.42816821902343,
+    "test_loss": 0.7586761116981506,
+    "test_runtime": 11.947,
+    "test_samples": 1684,
+    "test_samples_per_second": 140.956,
+    "test_steps_per_second": 17.661,
+    "test_uas": 94.80666102173299,
+    "train_loss": 0.13298969575431613,
+    "train_runtime": 5206.9637,
+    "train_samples": 13304,
+    "train_samples_per_second": 92.184,
+    "train_steps_per_second": 2.881
+}

config.json

@@ -0,0 +1,111 @@
+{
+  "_name_or_path": "bert-base-multilingual-cased",
+  "architectures": [
+    "BertForBiaffineParsing"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "directionality": "bidi",
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "_",
+    "1": "acl",
+    "2": "advcl",
+    "3": "advmod",
+    "4": "amod",
+    "5": "appos",
+    "6": "aux",
+    "7": "case",
+    "8": "cc",
+    "9": "ccomp",
+    "10": "clf",
+    "11": "compound",
+    "12": "conj",
+    "13": "cop",
+    "14": "csubj",
+    "15": "dep",
+    "16": "det",
+    "17": "discourse",
+    "18": "dislocated",
+    "19": "expl",
+    "20": "fixed",
+    "21": "flat",
+    "22": "goeswith",
+    "23": "iobj",
+    "24": "list",
+    "25": "mark",
+    "26": "nmod",
+    "27": "nsubj",
+    "28": "nummod",
+    "29": "obj",
+    "30": "obl",
+    "31": "orphan",
+    "32": "parataxis",
+    "33": "punct",
+    "34": "reparandum",
+    "35": "root",
+    "36": "vocative",
+    "37": "xcomp"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "_": 0,
+    "acl": 1,
+    "advcl": 2,
+    "advmod": 3,
+    "amod": 4,
+    "appos": 5,
+    "aux": 6,
+    "case": 7,
+    "cc": 8,
+    "ccomp": 9,
+    "clf": 10,
+    "compound": 11,
+    "conj": 12,
+    "cop": 13,
+    "csubj": 14,
+    "dep": 15,
+    "det": 16,
+    "discourse": 17,
+    "dislocated": 18,
+    "expl": 19,
+    "fixed": 20,
+    "flat": 21,
+    "goeswith": 22,
+    "iobj": 23,
+    "list": 24,
+    "mark": 25,
+    "nmod": 26,
+    "nsubj": 27,
+    "nummod": 28,
+    "obj": 29,
+    "obl": 30,
+    "orphan": 31,
+    "parataxis": 32,
+    "punct": 33,
+    "reparandum": 34,
+    "root": 35,
+    "vocative": 36,
+    "xcomp": 37
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": -100,
+  "pooler_fc_size": 768,
+  "pooler_num_attention_heads": 12,
+  "pooler_num_fc_layers": 3,
+  "pooler_size_per_head": 128,
+  "pooler_type": "first_token_transform",
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.17.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 119547
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc3ee64444b9121c4acbb3b005f05bcedf704941949c4f5b7d6035e36cc8ba09
+size 803749941

special_tokens_map.json

@@ -0,0 +1 @@
+{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}

tokenizer_config.json

@@ -0,0 +1 @@
+{"do_lower_case": false, "unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]", "tokenize_chinese_chars": true, "strip_accents": null, "add_prefix_space": false, "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "bert-base-multilingual-cased", "tokenizer_class": "BertTokenizer"}

trainer_state.json

@@ -0,0 +1,745 @@
+{
+  "best_metric": 91.75966152710339,
+  "best_model_checkpoint": "/scratch/mrahma45/pixel/finetuned_models/mbert/mbert-base-finetuned-parsing-ud-Hindi-HDTB/checkpoint-6500",
+  "epoch": 21.634615384615383,
+  "global_step": 9000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.24,
+      "learning_rate": 7.840000000000001e-05,
+      "loss": 2.8321,
+      "step": 100
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 7.947382550335571e-05,
+      "loss": 0.7588,
+      "step": 200
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 7.893691275167786e-05,
+      "loss": 0.607,
+      "step": 300
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 7.840000000000001e-05,
+      "loss": 0.5116,
+      "step": 400
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 7.786308724832216e-05,
+      "loss": 0.3944,
+      "step": 500
+    },
+    {
+      "epoch": 1.2,
+      "eval_las": 89.23531249112644,
+      "eval_loss": 0.415132611989975,
+      "eval_runtime": 11.8077,
+      "eval_samples_per_second": 140.501,
+      "eval_steps_per_second": 17.616,
+      "eval_uas": 93.45202601016554,
+      "step": 500
+    },
+    {
+      "epoch": 1.44,
+      "learning_rate": 7.73261744966443e-05,
+      "loss": 0.3888,
+      "step": 600
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 7.678926174496645e-05,
+      "loss": 0.3689,
+      "step": 700
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 7.62523489932886e-05,
+      "loss": 0.3628,
+      "step": 800
+    },
+    {
+      "epoch": 2.16,
+      "learning_rate": 7.571543624161075e-05,
+      "loss": 0.291,
+      "step": 900
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 7.51785234899329e-05,
+      "loss": 0.265,
+      "step": 1000
+    },
+    {
+      "epoch": 2.4,
+      "eval_las": 90.46199278757419,
+      "eval_loss": 0.37675201892852783,
+      "eval_runtime": 11.7912,
+      "eval_samples_per_second": 140.698,
+      "eval_steps_per_second": 17.64,
+      "eval_uas": 94.2726524121873,
+      "step": 1000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 7.464161073825505e-05,
+      "loss": 0.2676,
+      "step": 1100
+    },
+    {
+      "epoch": 2.88,
+      "learning_rate": 7.410469798657718e-05,
+      "loss": 0.2719,
+      "step": 1200
+    },
+    {
+      "epoch": 3.12,
+      "learning_rate": 7.356778523489933e-05,
+      "loss": 0.2325,
+      "step": 1300
+    },
+    {
+      "epoch": 3.37,
+      "learning_rate": 7.303087248322148e-05,
+      "loss": 0.2006,
+      "step": 1400
+    },
+    {
+      "epoch": 3.61,
+      "learning_rate": 7.249395973154363e-05,
+      "loss": 0.2103,
+      "step": 1500
+    },
+    {
+      "epoch": 3.61,
+      "eval_las": 91.04409802084221,
+      "eval_loss": 0.3845142126083374,
+      "eval_runtime": 11.7995,
+      "eval_samples_per_second": 140.6,
+      "eval_steps_per_second": 17.628,
+      "eval_uas": 94.56512479768294,
+      "step": 1500
+    },
+    {
+      "epoch": 3.85,
+      "learning_rate": 7.195704697986577e-05,
+      "loss": 0.2208,
+      "step": 1600
+    },
+    {
+      "epoch": 4.09,
+      "learning_rate": 7.142013422818792e-05,
+      "loss": 0.1948,
+      "step": 1700
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 7.088322147651007e-05,
+      "loss": 0.1553,
+      "step": 1800
+    },
+    {
+      "epoch": 4.57,
+      "learning_rate": 7.034630872483222e-05,
+      "loss": 0.1593,
+      "step": 1900
+    },
+    {
+      "epoch": 4.81,
+      "learning_rate": 6.980939597315437e-05,
+      "loss": 0.1655,
+      "step": 2000
+    },
+    {
+      "epoch": 4.81,
+      "eval_las": 91.03557940767243,
+      "eval_loss": 0.3911457359790802,
+      "eval_runtime": 11.7868,
+      "eval_samples_per_second": 140.751,
+      "eval_steps_per_second": 17.647,
+      "eval_uas": 94.65882954255048,
+      "step": 2000
+    },
+    {
+      "epoch": 5.05,
+      "learning_rate": 6.927248322147651e-05,
+      "loss": 0.1562,
+      "step": 2100
+    },
+    {
+      "epoch": 5.29,
+      "learning_rate": 6.873557046979866e-05,
+      "loss": 0.1157,
+      "step": 2200
+    },
+    {
+      "epoch": 5.53,
+      "learning_rate": 6.819865771812081e-05,
+      "loss": 0.1221,
+      "step": 2300
+    },
+    {
+      "epoch": 5.77,
+      "learning_rate": 6.766174496644296e-05,
+      "loss": 0.1336,
+      "step": 2400
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 6.712483221476511e-05,
+      "loss": 0.1319,
+      "step": 2500
+    },
+    {
+      "epoch": 6.01,
+      "eval_las": 90.95323281369792,
+      "eval_loss": 0.44331711530685425,
+      "eval_runtime": 11.7942,
+      "eval_samples_per_second": 140.663,
+      "eval_steps_per_second": 17.636,
+      "eval_uas": 94.61055740125508,
+      "step": 2500
+    },
+    {
+      "epoch": 6.25,
+      "learning_rate": 6.658791946308726e-05,
+      "loss": 0.0893,
+      "step": 2600
+    },
+    {
+      "epoch": 6.49,
+      "learning_rate": 6.60510067114094e-05,
+      "loss": 0.0981,
+      "step": 2700
+    },
+    {
+      "epoch": 6.73,
+      "learning_rate": 6.551409395973155e-05,
+      "loss": 0.099,
+      "step": 2800
+    },
+    {
+      "epoch": 6.97,
+      "learning_rate": 6.49771812080537e-05,
+      "loss": 0.1028,
+      "step": 2900
+    },
+    {
+      "epoch": 7.21,
+      "learning_rate": 6.444026845637585e-05,
+      "loss": 0.0774,
+      "step": 3000
+    },
+    {
+      "epoch": 7.21,
+      "eval_las": 91.02138171905614,
+      "eval_loss": 0.534425675868988,
+      "eval_runtime": 11.7987,
+      "eval_samples_per_second": 140.609,
+      "eval_steps_per_second": 17.629,
+      "eval_uas": 94.7184598347389,
+      "step": 3000
+    },
+    {
+      "epoch": 7.45,
+      "learning_rate": 6.3903355704698e-05,
+      "loss": 0.0774,
+      "step": 3100
+    },
+    {
+      "epoch": 7.69,
+      "learning_rate": 6.336644295302015e-05,
+      "loss": 0.0815,
+      "step": 3200
+    },
+    {
+      "epoch": 7.93,
+      "learning_rate": 6.28295302013423e-05,
+      "loss": 0.0855,
+      "step": 3300
+    },
+    {
+      "epoch": 8.17,
+      "learning_rate": 6.229261744966444e-05,
+      "loss": 0.0633,
+      "step": 3400
+    },
+    {
+      "epoch": 8.41,
+      "learning_rate": 6.175570469798658e-05,
+      "loss": 0.0655,
+      "step": 3500
+    },
+    {
+      "epoch": 8.41,
+      "eval_las": 91.10088877530738,
+      "eval_loss": 0.5579993724822998,
+      "eval_runtime": 11.8126,
+      "eval_samples_per_second": 140.444,
+      "eval_steps_per_second": 17.608,
+      "eval_uas": 94.6304341653179,
+      "step": 3500
+    },
+    {
+      "epoch": 8.65,
+      "learning_rate": 6.121879194630873e-05,
+      "loss": 0.0654,
+      "step": 3600
+    },
+    {
+      "epoch": 8.89,
+      "learning_rate": 6.068187919463087e-05,
+      "loss": 0.0692,
+      "step": 3700
+    },
+    {
+      "epoch": 9.13,
+      "learning_rate": 6.014496644295302e-05,
+      "loss": 0.0608,
+      "step": 3800
+    },
+    {
+      "epoch": 9.38,
+      "learning_rate": 5.9613422818791955e-05,
+      "loss": 0.0529,
+      "step": 3900
+    },
+    {
+      "epoch": 9.62,
+      "learning_rate": 5.90765100671141e-05,
+      "loss": 0.0568,
+      "step": 4000
+    },
+    {
+      "epoch": 9.62,
+      "eval_las": 91.29397734048896,
+      "eval_loss": 0.5721077919006348,
+      "eval_runtime": 11.8178,
+      "eval_samples_per_second": 140.382,
+      "eval_steps_per_second": 17.601,
+      "eval_uas": 94.87179487179486,
+      "step": 4000
+    },
+    {
+      "epoch": 9.86,
+      "learning_rate": 5.853959731543625e-05,
+      "loss": 0.0554,
+      "step": 4100
+    },
+    {
+      "epoch": 10.1,
+      "learning_rate": 5.80026845637584e-05,
+      "loss": 0.0517,
+      "step": 4200
+    },
+    {
+      "epoch": 10.34,
+      "learning_rate": 5.7465771812080534e-05,
+      "loss": 0.0441,
+      "step": 4300
+    },
+    {
+      "epoch": 10.58,
+      "learning_rate": 5.692885906040268e-05,
+      "loss": 0.0471,
+      "step": 4400
+    },
+    {
+      "epoch": 10.82,
+      "learning_rate": 5.639194630872483e-05,
+      "loss": 0.0462,
+      "step": 4500
+    },
+    {
+      "epoch": 10.82,
+      "eval_las": 91.28261918959593,
+      "eval_loss": 0.6217162609100342,
+      "eval_runtime": 11.7974,
+      "eval_samples_per_second": 140.624,
+      "eval_steps_per_second": 17.631,
+      "eval_uas": 94.88599256041117,
+      "step": 4500
+    },
+    {
+      "epoch": 11.06,
+      "learning_rate": 5.5855033557046986e-05,
+      "loss": 0.0483,
+      "step": 4600
+    },
+    {
+      "epoch": 11.3,
+      "learning_rate": 5.5318120805369134e-05,
+      "loss": 0.0393,
+      "step": 4700
+    },
+    {
+      "epoch": 11.54,
+      "learning_rate": 5.478120805369128e-05,
+      "loss": 0.0402,
+      "step": 4800
+    },
+    {
+      "epoch": 11.78,
+      "learning_rate": 5.424429530201343e-05,
+      "loss": 0.0424,
+      "step": 4900
+    },
+    {
+      "epoch": 12.02,
+      "learning_rate": 5.370738255033558e-05,
+      "loss": 0.0418,
+      "step": 5000
+    },
+    {
+      "epoch": 12.02,
+      "eval_las": 91.32237271772155,
+      "eval_loss": 0.6571192145347595,
+      "eval_runtime": 11.8066,
+      "eval_samples_per_second": 140.515,
+      "eval_steps_per_second": 17.617,
+      "eval_uas": 94.87747394724138,
+      "step": 5000
+    },
+    {
+      "epoch": 12.26,
+      "learning_rate": 5.317046979865773e-05,
+      "loss": 0.0339,
+      "step": 5100
+    },
+    {
+      "epoch": 12.5,
+      "learning_rate": 5.2633557046979875e-05,
+      "loss": 0.0361,
+      "step": 5200
+    },
+    {
+      "epoch": 12.74,
+      "learning_rate": 5.2096644295302024e-05,
+      "loss": 0.0347,
+      "step": 5300
+    },
+    {
+      "epoch": 12.98,
+      "learning_rate": 5.155973154362417e-05,
+      "loss": 0.0374,
+      "step": 5400
+    },
+    {
+      "epoch": 13.22,
+      "learning_rate": 5.1022818791946307e-05,
+      "loss": 0.0304,
+      "step": 5500
+    },
+    {
+      "epoch": 13.22,
+      "eval_las": 91.43879376437516,
+      "eval_loss": 0.6834462881088257,
+      "eval_runtime": 11.776,
+      "eval_samples_per_second": 140.879,
+      "eval_steps_per_second": 17.663,
+      "eval_uas": 95.01661129568106,
+      "step": 5500
+    },
+    {
+      "epoch": 13.46,
+      "learning_rate": 5.0485906040268455e-05,
+      "loss": 0.0299,
+      "step": 5600
+    },
+    {
+      "epoch": 13.7,
+      "learning_rate": 4.99489932885906e-05,
+      "loss": 0.0335,
+      "step": 5700
+    },
+    {
+      "epoch": 13.94,
+      "learning_rate": 4.941208053691275e-05,
+      "loss": 0.0331,
+      "step": 5800
+    },
+    {
+      "epoch": 14.18,
+      "learning_rate": 4.88751677852349e-05,
+      "loss": 0.026,
+      "step": 5900
+    },
+    {
+      "epoch": 14.42,
+      "learning_rate": 4.833825503355705e-05,
+      "loss": 0.0255,
+      "step": 6000
+    },
+    {
+      "epoch": 14.42,
+      "eval_las": 91.52965897151944,
+      "eval_loss": 0.7086959481239319,
+      "eval_runtime": 11.7728,
+      "eval_samples_per_second": 140.918,
+      "eval_steps_per_second": 17.668,
+      "eval_uas": 95.10179742737883,
+      "step": 6000
+    },
+    {
+      "epoch": 14.66,
+      "learning_rate": 4.7801342281879196e-05,
+      "loss": 0.0273,
+      "step": 6100
+    },
+    {
+      "epoch": 14.9,
+      "learning_rate": 4.726442953020135e-05,
+      "loss": 0.0286,
+      "step": 6200
+    },
+    {
+      "epoch": 15.14,
+      "learning_rate": 4.67275167785235e-05,
+      "loss": 0.0219,
+      "step": 6300
+    },
+    {
+      "epoch": 15.38,
+      "learning_rate": 4.619060402684565e-05,
+      "loss": 0.0216,
+      "step": 6400
+    },
+    {
+      "epoch": 15.62,
+      "learning_rate": 4.565906040268457e-05,
+      "loss": 0.0254,
+      "step": 6500
+    },
+    {
+      "epoch": 15.62,
+      "eval_las": 91.75966152710339,
+      "eval_loss": 0.7071714401245117,
+      "eval_runtime": 11.7877,
+      "eval_samples_per_second": 140.74,
+      "eval_steps_per_second": 17.646,
+      "eval_uas": 95.23525570037198,
+      "step": 6500
+    },
+    {
+      "epoch": 15.87,
+      "learning_rate": 4.5122147651006716e-05,
+      "loss": 0.0242,
+      "step": 6600
+    },
+    {
+      "epoch": 16.11,
+      "learning_rate": 4.4585234899328864e-05,
+      "loss": 0.023,
+      "step": 6700
+    },
+    {
+      "epoch": 16.35,
+      "learning_rate": 4.404832214765101e-05,
+      "loss": 0.0222,
+      "step": 6800
+    },
+    {
+      "epoch": 16.59,
+      "learning_rate": 4.351140939597316e-05,
+      "loss": 0.0198,
+      "step": 6900
+    },
+    {
+      "epoch": 16.83,
+      "learning_rate": 4.297449664429531e-05,
+      "loss": 0.0211,
+      "step": 7000
+    },
+    {
+      "epoch": 16.83,
+      "eval_las": 91.60632649004742,
+      "eval_loss": 0.7650447487831116,
+      "eval_runtime": 11.8115,
+      "eval_samples_per_second": 140.456,
+      "eval_steps_per_second": 17.61,
+      "eval_uas": 95.07908112559275,
+      "step": 7000
+    },
+    {
+      "epoch": 17.07,
+      "learning_rate": 4.243758389261746e-05,
+      "loss": 0.0202,
+      "step": 7100
+    },
+    {
+      "epoch": 17.31,
+      "learning_rate": 4.1900671140939605e-05,
+      "loss": 0.0165,
+      "step": 7200
+    },
+    {
+      "epoch": 17.55,
+      "learning_rate": 4.1363758389261754e-05,
+      "loss": 0.021,
+      "step": 7300
+    },
+    {
+      "epoch": 17.79,
+      "learning_rate": 4.0826845637583895e-05,
+      "loss": 0.0175,
+      "step": 7400
+    },
+    {
+      "epoch": 18.03,
+      "learning_rate": 4.028993288590604e-05,
+      "loss": 0.019,
+      "step": 7500
+    },
+    {
+      "epoch": 18.03,
+      "eval_las": 91.65743816906607,
+      "eval_loss": 0.7897760272026062,
+      "eval_runtime": 11.7771,
+      "eval_samples_per_second": 140.867,
+      "eval_steps_per_second": 17.661,
+      "eval_uas": 95.08759973876253,
+      "step": 7500
+    },
+    {
+      "epoch": 18.27,
+      "learning_rate": 3.975302013422819e-05,
+      "loss": 0.015,
+      "step": 7600
+    },
+    {
+      "epoch": 18.51,
+      "learning_rate": 3.921610738255034e-05,
+      "loss": 0.0166,
+      "step": 7700
+    },
+    {
+      "epoch": 18.75,
+      "learning_rate": 3.867919463087249e-05,
+      "loss": 0.0165,
+      "step": 7800
+    },
+    {
+      "epoch": 18.99,
+      "learning_rate": 3.8142281879194636e-05,
+      "loss": 0.0156,
+      "step": 7900
+    },
+    {
+      "epoch": 19.23,
+      "learning_rate": 3.7605369127516784e-05,
+      "loss": 0.0125,
+      "step": 8000
+    },
+    {
+      "epoch": 19.23,
+      "eval_las": 91.5183008206264,
+      "eval_loss": 0.7997450828552246,
+      "eval_runtime": 11.8137,
+      "eval_samples_per_second": 140.431,
+      "eval_steps_per_second": 17.607,
+      "eval_uas": 94.9995740693415,
+      "step": 8000
+    },
+    {
+      "epoch": 19.47,
+      "learning_rate": 3.706845637583893e-05,
+      "loss": 0.0155,
+      "step": 8100
+    },
+    {
+      "epoch": 19.71,
+      "learning_rate": 3.653154362416108e-05,
+      "loss": 0.0155,
+      "step": 8200
+    },
+    {
+      "epoch": 19.95,
+      "learning_rate": 3.599463087248322e-05,
+      "loss": 0.0142,
+      "step": 8300
+    },
+    {
+      "epoch": 20.19,
+      "learning_rate": 3.545771812080537e-05,
+      "loss": 0.0096,
+      "step": 8400
+    },
+    {
+      "epoch": 20.43,
+      "learning_rate": 3.492080536912752e-05,
+      "loss": 0.0132,
+      "step": 8500
+    },
+    {
+      "epoch": 20.43,
+      "eval_las": 91.67731493312888,
+      "eval_loss": 0.8170235753059387,
+      "eval_runtime": 11.7652,
+      "eval_samples_per_second": 141.009,
+      "eval_steps_per_second": 17.679,
+      "eval_uas": 95.12735326688815,
+      "step": 8500
+    },
+    {
+      "epoch": 20.67,
+      "learning_rate": 3.438389261744967e-05,
+      "loss": 0.0122,
+      "step": 8600
+    },
+    {
+      "epoch": 20.91,
+      "learning_rate": 3.3846979865771815e-05,
+      "loss": 0.0116,
+      "step": 8700
+    },
+    {
+      "epoch": 21.15,
+      "learning_rate": 3.3310067114093964e-05,
+      "loss": 0.0114,
+      "step": 8800
+    },
+    {
+      "epoch": 21.39,
+      "learning_rate": 3.277315436241611e-05,
+      "loss": 0.0089,
+      "step": 8900
+    },
+    {
+      "epoch": 21.63,
+      "learning_rate": 3.223624161073826e-05,
+      "loss": 0.0115,
+      "step": 9000
+    },
+    {
+      "epoch": 21.63,
+      "eval_las": 91.60348695232416,
+      "eval_loss": 0.8960289359092712,
+      "eval_runtime": 12.1056,
+      "eval_samples_per_second": 137.044,
+      "eval_steps_per_second": 17.182,
+      "eval_uas": 95.08759973876253,
+      "step": 9000
+    },
+    {
+      "epoch": 21.63,
+      "step": 9000,
+      "total_flos": 4.80612874451927e+16,
+      "train_loss": 0.13298969575431613,
+      "train_runtime": 5206.9637,
+      "train_samples_per_second": 92.184,
+      "train_steps_per_second": 2.881
+    }
+  ],
+  "max_steps": 15000,
+  "num_train_epochs": 37,
+  "total_flos": 4.80612874451927e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8188a939391db994005a097d1713032032914eda7eff521f6be307d1aea3d511
+size 3387