Training in progress, step 500

.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
+eval_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text
+predict_nbest_predictions.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,54 @@
+---
+license: mit
+base_model: Deehan1866/MPS-deberta-v3-base
+tags:
+- generated_from_trainer
+datasets:
+- PiC/phrase_retrieval
+model-index:
+- name: finetuned
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# finetuned
+
+This model is a fine-tuned version of [Deehan1866/MPS-deberta-v3-base](https://huggingface.co/Deehan1866/MPS-deberta-v3-base) on the PiC/phrase_retrieval PR-pass dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[MASK]": 128000
+}

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 95.06666666666666,
+    "eval_f1": 96.62021164021165,
+    "eval_samples": 3010,
+    "predict_samples": 5023,
+    "test_exact_match": 95.52,
+    "test_f1": 96.68591635610768,
+    "total_flos": 1.0570689882918912e+16,
+    "train_loss": 0.2199482326217205,
+    "train_runtime": 8561.1575,
+    "train_samples": 20227,
+    "train_samples_per_second": 4.725,
+    "train_steps_per_second": 0.591
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Deehan1866/MPS-electra-large",
+  "architectures": [
+    "ElectraForQuestionAnswering"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 1024,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 24,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

eval_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53b1c2f288c6537326a542cb10075c6ad46f59b333c86733f14b834038440bcd
+size 18638171

eval_results.json

@@ -0,0 +1,6 @@
+{
+    "epoch": 2.0,
+    "eval_exact_match": 95.06666666666666,
+    "eval_f1": 96.62021164021165,
+    "eval_samples": 3010
+}

finetune_logs.txt

@@ -0,0 +1,11 @@
+06/28/2024 08:05:50 - WARNING - __main__ - Process rank: 0, device: cuda:0, n_gpu: 1distributed training: True, 16-bits training: False
+{'loss': 1.6243, 'grad_norm': 56.679527282714844, 'learning_rate': 2.9407816818002367e-05, 'epoch': 0.04}
+{'eval_exact_match': 84.93333333333334, 'eval_f1': 88.2940084870136, 'epoch': 0.04}
+{'loss': 0.6191, 'grad_norm': 5.885100841522217, 'learning_rate': 2.8815633636004737e-05, 'epoch': 0.08}
+{'eval_exact_match': 88.6, 'eval_f1': 91.63917534901744, 'epoch': 0.08}
+{'loss': 0.4602, 'grad_norm': 26.811798095703125, 'learning_rate': 2.8223450454007107e-05, 'epoch': 0.12}
+{'eval_exact_match': 90.93333333333334, 'eval_f1': 93.10548046289217, 'epoch': 0.12}
+{'loss': 0.4923, 'grad_norm': 30.7504825592041, 'learning_rate': 2.7631267272009477e-05, 'epoch': 0.16}
+{'eval_exact_match': 90.63333333333334, 'eval_f1': 92.85661375661373, 'epoch': 0.16}
+{'loss': 0.4052, 'grad_norm': 3.8463761806488037, 'learning_rate': 2.7039084090011843e-05, 'epoch': 0.2}
+{'eval_exact_match': 90.7, 'eval_f1': 93.16844432942258, 'epoch': 0.2}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f54471dfee238d35d9b1e479e6f394b44e1d0be49c67d8853d2650875fdc631c
+size 1336425336

predict_nbest_predictions.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d2b51ff922aad7724e9839cadb223818d27094c49e635e053c2b7df5af79ada
+size 30747731

predict_results.json

@@ -0,0 +1,5 @@
+{
+    "predict_samples": 5023,
+    "test_exact_match": 95.52,
+    "test_f1": 96.68591635610768
+}

special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

spm.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c679fbf93643d19aab7ee10c0b99e460bdbc02fedf34b92b05af343b4af586fd
+size 2464616

tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "max_length": 512,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 128,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "only_second",
+  "unk_token": "[UNK]"
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.0570689882918912e+16,
+    "train_loss": 0.2199482326217205,
+    "train_runtime": 8561.1575,
+    "train_samples": 20227,
+    "train_samples_per_second": 4.725,
+    "train_steps_per_second": 0.591
+}

trainer_state.json

@@ -0,0 +1,692 @@
+{
+  "best_metric": 95.06666666666666,
+  "best_model_checkpoint": "../results/phrase_retrieval/PR-pass/qa/mpsDistillbert/finetuned/checkpoint-5000",
+  "epoch": 2.0,
+  "eval_steps": 100,
+  "global_step": 5058,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.039541320680110716,
+      "grad_norm": 32.419464111328125,
+      "learning_rate": 2.940688018979834e-05,
+      "loss": 1.1173,
+      "step": 100
+    },
+    {
+      "epoch": 0.039541320680110716,
+      "eval_exact_match": 88.9,
+      "eval_f1": 92.00500921000344,
+      "step": 100
+    },
+    {
+      "epoch": 0.07908264136022143,
+      "grad_norm": 38.01858139038086,
+      "learning_rate": 2.881376037959668e-05,
+      "loss": 0.4822,
+      "step": 200
+    },
+    {
+      "epoch": 0.07908264136022143,
+      "eval_exact_match": 90.46666666666667,
+      "eval_f1": 93.36957595798556,
+      "step": 200
+    },
+    {
+      "epoch": 0.11862396204033215,
+      "grad_norm": 21.57156753540039,
+      "learning_rate": 2.8220640569395017e-05,
+      "loss": 0.4056,
+      "step": 300
+    },
+    {
+      "epoch": 0.11862396204033215,
+      "eval_exact_match": 90.16666666666667,
+      "eval_f1": 93.14274423334948,
+      "step": 300
+    },
+    {
+      "epoch": 0.15816528272044286,
+      "grad_norm": 36.502201080322266,
+      "learning_rate": 2.7627520759193358e-05,
+      "loss": 0.358,
+      "step": 400
+    },
+    {
+      "epoch": 0.15816528272044286,
+      "eval_exact_match": 92.0,
+      "eval_f1": 94.2940064808486,
+      "step": 400
+    },
+    {
+      "epoch": 0.19770660340055357,
+      "grad_norm": 1.437743902206421,
+      "learning_rate": 2.7034400948991696e-05,
+      "loss": 0.3401,
+      "step": 500
+    },
+    {
+      "epoch": 0.19770660340055357,
+      "eval_exact_match": 92.86666666666666,
+      "eval_f1": 94.86057314225737,
+      "step": 500
+    },
+    {
+      "epoch": 0.2372479240806643,
+      "grad_norm": 16.85663604736328,
+      "learning_rate": 2.6441281138790037e-05,
+      "loss": 0.3348,
+      "step": 600
+    },
+    {
+      "epoch": 0.2372479240806643,
+      "eval_exact_match": 92.4,
+      "eval_f1": 94.57701014385223,
+      "step": 600
+    },
+    {
+      "epoch": 0.276789244760775,
+      "grad_norm": 9.705633163452148,
+      "learning_rate": 2.5848161328588377e-05,
+      "loss": 0.3603,
+      "step": 700
+    },
+    {
+      "epoch": 0.276789244760775,
+      "eval_exact_match": 92.53333333333333,
+      "eval_f1": 94.58231913116124,
+      "step": 700
+    },
+    {
+      "epoch": 0.3163305654408857,
+      "grad_norm": 1.5076546669006348,
+      "learning_rate": 2.5255041518386715e-05,
+      "loss": 0.4025,
+      "step": 800
+    },
+    {
+      "epoch": 0.3163305654408857,
+      "eval_exact_match": 92.8,
+      "eval_f1": 94.98821979190402,
+      "step": 800
+    },
+    {
+      "epoch": 0.35587188612099646,
+      "grad_norm": 5.4361114501953125,
+      "learning_rate": 2.4661921708185056e-05,
+      "loss": 0.3396,
+      "step": 900
+    },
+    {
+      "epoch": 0.35587188612099646,
+      "eval_exact_match": 93.03333333333333,
+      "eval_f1": 95.06740036365424,
+      "step": 900
+    },
+    {
+      "epoch": 0.39541320680110714,
+      "grad_norm": 24.144868850708008,
+      "learning_rate": 2.4068801897983394e-05,
+      "loss": 0.3728,
+      "step": 1000
+    },
+    {
+      "epoch": 0.39541320680110714,
+      "eval_exact_match": 92.03333333333333,
+      "eval_f1": 94.552540715535,
+      "step": 1000
+    },
+    {
+      "epoch": 0.4349545274812179,
+      "grad_norm": 40.113285064697266,
+      "learning_rate": 2.347568208778173e-05,
+      "loss": 0.2901,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4349545274812179,
+      "eval_exact_match": 92.96666666666667,
+      "eval_f1": 95.07719921785143,
+      "step": 1100
+    },
+    {
+      "epoch": 0.4744958481613286,
+      "grad_norm": 27.42624855041504,
+      "learning_rate": 2.2882562277580072e-05,
+      "loss": 0.2807,
+      "step": 1200
+    },
+    {
+      "epoch": 0.4744958481613286,
+      "eval_exact_match": 93.3,
+      "eval_f1": 95.3500069013113,
+      "step": 1200
+    },
+    {
+      "epoch": 0.5140371688414394,
+      "grad_norm": 23.65859603881836,
+      "learning_rate": 2.228944246737841e-05,
+      "loss": 0.2644,
+      "step": 1300
+    },
+    {
+      "epoch": 0.5140371688414394,
+      "eval_exact_match": 93.2,
+      "eval_f1": 95.05281627432659,
+      "step": 1300
+    },
+    {
+      "epoch": 0.55357848952155,
+      "grad_norm": 4.855496883392334,
+      "learning_rate": 2.169632265717675e-05,
+      "loss": 0.2762,
+      "step": 1400
+    },
+    {
+      "epoch": 0.55357848952155,
+      "eval_exact_match": 93.3,
+      "eval_f1": 95.443781890624,
+      "step": 1400
+    },
+    {
+      "epoch": 0.5931198102016607,
+      "grad_norm": 0.48628461360931396,
+      "learning_rate": 2.110320284697509e-05,
+      "loss": 0.319,
+      "step": 1500
+    },
+    {
+      "epoch": 0.5931198102016607,
+      "eval_exact_match": 92.73333333333333,
+      "eval_f1": 94.94519559768989,
+      "step": 1500
+    },
+    {
+      "epoch": 0.6326611308817714,
+      "grad_norm": 0.08743516355752945,
+      "learning_rate": 2.0510083036773426e-05,
+      "loss": 0.2958,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6326611308817714,
+      "eval_exact_match": 93.96666666666667,
+      "eval_f1": 95.78775828460041,
+      "step": 1600
+    },
+    {
+      "epoch": 0.6722024515618822,
+      "grad_norm": 1.8978503942489624,
+      "learning_rate": 1.991696322657177e-05,
+      "loss": 0.2201,
+      "step": 1700
+    },
+    {
+      "epoch": 0.6722024515618822,
+      "eval_exact_match": 93.5,
+      "eval_f1": 95.3272486772487,
+      "step": 1700
+    },
+    {
+      "epoch": 0.7117437722419929,
+      "grad_norm": 25.710737228393555,
+      "learning_rate": 1.9323843416370108e-05,
+      "loss": 0.2944,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7117437722419929,
+      "eval_exact_match": 93.4,
+      "eval_f1": 95.32006332255762,
+      "step": 1800
+    },
+    {
+      "epoch": 0.7512850929221035,
+      "grad_norm": 13.707782745361328,
+      "learning_rate": 1.8730723606168446e-05,
+      "loss": 0.2914,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7512850929221035,
+      "eval_exact_match": 93.66666666666667,
+      "eval_f1": 95.52821693121696,
+      "step": 1900
+    },
+    {
+      "epoch": 0.7908264136022143,
+      "grad_norm": 17.373273849487305,
+      "learning_rate": 1.8137603795966787e-05,
+      "loss": 0.3082,
+      "step": 2000
+    },
+    {
+      "epoch": 0.7908264136022143,
+      "eval_exact_match": 94.26666666666667,
+      "eval_f1": 95.87325744917855,
+      "step": 2000
+    },
+    {
+      "epoch": 0.830367734282325,
+      "grad_norm": 33.38816452026367,
+      "learning_rate": 1.7544483985765124e-05,
+      "loss": 0.3397,
+      "step": 2100
+    },
+    {
+      "epoch": 0.830367734282325,
+      "eval_exact_match": 93.83333333333333,
+      "eval_f1": 95.52239766081871,
+      "step": 2100
+    },
+    {
+      "epoch": 0.8699090549624358,
+      "grad_norm": 15.071436882019043,
+      "learning_rate": 1.6951364175563465e-05,
+      "loss": 0.2203,
+      "step": 2200
+    },
+    {
+      "epoch": 0.8699090549624358,
+      "eval_exact_match": 94.33333333333333,
+      "eval_f1": 96.01175299359508,
+      "step": 2200
+    },
+    {
+      "epoch": 0.9094503756425465,
+      "grad_norm": 11.337410926818848,
+      "learning_rate": 1.6358244365361803e-05,
+      "loss": 0.2878,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9094503756425465,
+      "eval_exact_match": 94.03333333333333,
+      "eval_f1": 95.92981481481488,
+      "step": 2300
+    },
+    {
+      "epoch": 0.9489916963226572,
+      "grad_norm": 22.02410316467285,
+      "learning_rate": 1.576512455516014e-05,
+      "loss": 0.2298,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9489916963226572,
+      "eval_exact_match": 94.43333333333334,
+      "eval_f1": 96.00666666666666,
+      "step": 2400
+    },
+    {
+      "epoch": 0.9885330170027679,
+      "grad_norm": 2.3211326599121094,
+      "learning_rate": 1.5172004744958481e-05,
+      "loss": 0.2519,
+      "step": 2500
+    },
+    {
+      "epoch": 0.9885330170027679,
+      "eval_exact_match": 94.3,
+      "eval_f1": 96.112007936508,
+      "step": 2500
+    },
+    {
+      "epoch": 1.0280743376828787,
+      "grad_norm": 0.24721509218215942,
+      "learning_rate": 1.4578884934756822e-05,
+      "loss": 0.2034,
+      "step": 2600
+    },
+    {
+      "epoch": 1.0280743376828787,
+      "eval_exact_match": 94.06666666666666,
+      "eval_f1": 95.96805555555562,
+      "step": 2600
+    },
+    {
+      "epoch": 1.0676156583629894,
+      "grad_norm": 39.38060760498047,
+      "learning_rate": 1.398576512455516e-05,
+      "loss": 0.0659,
+      "step": 2700
+    },
+    {
+      "epoch": 1.0676156583629894,
+      "eval_exact_match": 94.4,
+      "eval_f1": 96.04486772486773,
+      "step": 2700
+    },
+    {
+      "epoch": 1.1071569790431,
+      "grad_norm": 0.01663699932396412,
+      "learning_rate": 1.33926453143535e-05,
+      "loss": 0.115,
+      "step": 2800
+    },
+    {
+      "epoch": 1.1071569790431,
+      "eval_exact_match": 94.43333333333334,
+      "eval_f1": 96.05476190476192,
+      "step": 2800
+    },
+    {
+      "epoch": 1.1466982997232107,
+      "grad_norm": 0.09981880336999893,
+      "learning_rate": 1.2799525504151838e-05,
+      "loss": 0.1044,
+      "step": 2900
+    },
+    {
+      "epoch": 1.1466982997232107,
+      "eval_exact_match": 94.76666666666667,
+      "eval_f1": 96.31523809523814,
+      "step": 2900
+    },
+    {
+      "epoch": 1.1862396204033214,
+      "grad_norm": 0.0023523815907537937,
+      "learning_rate": 1.220640569395018e-05,
+      "loss": 0.0681,
+      "step": 3000
+    },
+    {
+      "epoch": 1.1862396204033214,
+      "eval_exact_match": 94.66666666666667,
+      "eval_f1": 96.27746031746034,
+      "step": 3000
+    },
+    {
+      "epoch": 1.2257809410834322,
+      "grad_norm": 26.123458862304688,
+      "learning_rate": 1.1613285883748517e-05,
+      "loss": 0.1076,
+      "step": 3100
+    },
+    {
+      "epoch": 1.2257809410834322,
+      "eval_exact_match": 94.96666666666667,
+      "eval_f1": 96.47634920634923,
+      "step": 3100
+    },
+    {
+      "epoch": 1.265322261763543,
+      "grad_norm": 0.013637016527354717,
+      "learning_rate": 1.1020166073546856e-05,
+      "loss": 0.1247,
+      "step": 3200
+    },
+    {
+      "epoch": 1.265322261763543,
+      "eval_exact_match": 94.66666666666667,
+      "eval_f1": 96.31714285714288,
+      "step": 3200
+    },
+    {
+      "epoch": 1.3048635824436536,
+      "grad_norm": 2.1234130859375,
+      "learning_rate": 1.0427046263345196e-05,
+      "loss": 0.0842,
+      "step": 3300
+    },
+    {
+      "epoch": 1.3048635824436536,
+      "eval_exact_match": 94.7,
+      "eval_f1": 96.37094701326588,
+      "step": 3300
+    },
+    {
+      "epoch": 1.3444049031237644,
+      "grad_norm": 39.8302116394043,
+      "learning_rate": 9.833926453143535e-06,
+      "loss": 0.1224,
+      "step": 3400
+    },
+    {
+      "epoch": 1.3444049031237644,
+      "eval_exact_match": 94.76666666666667,
+      "eval_f1": 96.2882029256147,
+      "step": 3400
+    },
+    {
+      "epoch": 1.383946223803875,
+      "grad_norm": 7.3402276039123535,
+      "learning_rate": 9.240806642941876e-06,
+      "loss": 0.1114,
+      "step": 3500
+    },
+    {
+      "epoch": 1.383946223803875,
+      "eval_exact_match": 94.7,
+      "eval_f1": 96.41914285714284,
+      "step": 3500
+    },
+    {
+      "epoch": 1.4234875444839858,
+      "grad_norm": 4.552010536193848,
+      "learning_rate": 8.647686832740214e-06,
+      "loss": 0.1399,
+      "step": 3600
+    },
+    {
+      "epoch": 1.4234875444839858,
+      "eval_exact_match": 94.73333333333333,
+      "eval_f1": 96.3720634920635,
+      "step": 3600
+    },
+    {
+      "epoch": 1.4630288651640964,
+      "grad_norm": 0.007382615935057402,
+      "learning_rate": 8.054567022538553e-06,
+      "loss": 0.0945,
+      "step": 3700
+    },
+    {
+      "epoch": 1.4630288651640964,
+      "eval_exact_match": 95.0,
+      "eval_f1": 96.56682539682542,
+      "step": 3700
+    },
+    {
+      "epoch": 1.502570185844207,
+      "grad_norm": 0.00287560629658401,
+      "learning_rate": 7.461447212336892e-06,
+      "loss": 0.1174,
+      "step": 3800
+    },
+    {
+      "epoch": 1.502570185844207,
+      "eval_exact_match": 94.8,
+      "eval_f1": 96.46809523809524,
+      "step": 3800
+    },
+    {
+      "epoch": 1.5421115065243178,
+      "grad_norm": 0.0006353872595354915,
+      "learning_rate": 6.868327402135232e-06,
+      "loss": 0.0947,
+      "step": 3900
+    },
+    {
+      "epoch": 1.5421115065243178,
+      "eval_exact_match": 94.66666666666667,
+      "eval_f1": 96.41693121693125,
+      "step": 3900
+    },
+    {
+      "epoch": 1.5816528272044286,
+      "grad_norm": 0.004277556203305721,
+      "learning_rate": 6.275207591933571e-06,
+      "loss": 0.0776,
+      "step": 4000
+    },
+    {
+      "epoch": 1.5816528272044286,
+      "eval_exact_match": 94.7,
+      "eval_f1": 96.44280423280426,
+      "step": 4000
+    },
+    {
+      "epoch": 1.6211941478845393,
+      "grad_norm": 0.0010521839139983058,
+      "learning_rate": 5.68208778173191e-06,
+      "loss": 0.0562,
+      "step": 4100
+    },
+    {
+      "epoch": 1.6211941478845393,
+      "eval_exact_match": 94.8,
+      "eval_f1": 96.48777777777781,
+      "step": 4100
+    },
+    {
+      "epoch": 1.66073546856465,
+      "grad_norm": 0.003965400159358978,
+      "learning_rate": 5.088967971530249e-06,
+      "loss": 0.0486,
+      "step": 4200
+    },
+    {
+      "epoch": 1.66073546856465,
+      "eval_exact_match": 94.96666666666667,
+      "eval_f1": 96.60613756613758,
+      "step": 4200
+    },
+    {
+      "epoch": 1.7002767892447608,
+      "grad_norm": 0.01875113882124424,
+      "learning_rate": 4.4958481613285886e-06,
+      "loss": 0.0986,
+      "step": 4300
+    },
+    {
+      "epoch": 1.7002767892447608,
+      "eval_exact_match": 95.13333333333334,
+      "eval_f1": 96.63917107583777,
+      "step": 4300
+    },
+    {
+      "epoch": 1.7398181099248715,
+      "grad_norm": 0.0012825974263250828,
+      "learning_rate": 3.902728351126927e-06,
+      "loss": 0.0939,
+      "step": 4400
+    },
+    {
+      "epoch": 1.7398181099248715,
+      "eval_exact_match": 94.96666666666667,
+      "eval_f1": 96.58159211159214,
+      "step": 4400
+    },
+    {
+      "epoch": 1.7793594306049823,
+      "grad_norm": 0.0024573770351707935,
+      "learning_rate": 3.309608540925267e-06,
+      "loss": 0.1167,
+      "step": 4500
+    },
+    {
+      "epoch": 1.7793594306049823,
+      "eval_exact_match": 94.96666666666667,
+      "eval_f1": 96.53317460317461,
+      "step": 4500
+    },
+    {
+      "epoch": 1.818900751285093,
+      "grad_norm": 19.585935592651367,
+      "learning_rate": 2.716488730723606e-06,
+      "loss": 0.0826,
+      "step": 4600
+    },
+    {
+      "epoch": 1.818900751285093,
+      "eval_exact_match": 95.16666666666667,
+      "eval_f1": 96.64805477746657,
+      "step": 4600
+    },
+    {
+      "epoch": 1.8584420719652037,
+      "grad_norm": 14.24262809753418,
+      "learning_rate": 2.1233689205219453e-06,
+      "loss": 0.0627,
+      "step": 4700
+    },
+    {
+      "epoch": 1.8584420719652037,
+      "eval_exact_match": 94.96666666666667,
+      "eval_f1": 96.53842514783693,
+      "step": 4700
+    },
+    {
+      "epoch": 1.8979833926453145,
+      "grad_norm": 0.12388183176517487,
+      "learning_rate": 1.5302491103202848e-06,
+      "loss": 0.0648,
+      "step": 4800
+    },
+    {
+      "epoch": 1.8979833926453145,
+      "eval_exact_match": 95.0,
+      "eval_f1": 96.60842514783693,
+      "step": 4800
+    },
+    {
+      "epoch": 1.9375247133254252,
+      "grad_norm": 0.0012477992568165064,
+      "learning_rate": 9.37129300118624e-07,
+      "loss": 0.0704,
+      "step": 4900
+    },
+    {
+      "epoch": 1.9375247133254252,
+      "eval_exact_match": 95.03333333333333,
+      "eval_f1": 96.65851851851853,
+      "step": 4900
+    },
+    {
+      "epoch": 1.977066034005536,
+      "grad_norm": 0.14640697836875916,
+      "learning_rate": 3.4400948991696327e-07,
+      "loss": 0.0863,
+      "step": 5000
+    },
+    {
+      "epoch": 1.977066034005536,
+      "eval_exact_match": 95.06666666666666,
+      "eval_f1": 96.62021164021165,
+      "step": 5000
+    },
+    {
+      "epoch": 2.0,
+      "step": 5058,
+      "total_flos": 1.0570689882918912e+16,
+      "train_loss": 0.2199482326217205,
+      "train_runtime": 8561.1575,
+      "train_samples_per_second": 4.725,
+      "train_steps_per_second": 0.591
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 5058,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "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": 1.0570689882918912e+16,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70b46dc40ab1ff5a7ac7fb2659c2b39090a3acc33f964878068121afc4f47ab3
+size 5240