Upload 14 files

README.md

@@ -1,3 +1,60 @@
 ---
-license: apache-2.0
+language:
+- yo
+- yor
+base_model: ../teams/yor-t5-small
+tags:
+- generated_from_trainer
+metrics:
+- bleu
+model-index:
+- name: t5_yo_yor
+  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. -->
+
+# t5_yo_yor
+
+This model is a fine-tuned version of [../teams/yor-t5-small](https://huggingface.co/../teams/yor-t5-small) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4178
+- Bleu: 78.1088
+- Gen Len: 30.37
+
+## 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: 5e-05
+- train_batch_size: 32
+- eval_batch_size: 32
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.31.0
+- Pytorch 2.0.1+cu117
+- Datasets 2.11.0
+- Tokenizers 0.13.3

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 78.1088,
+    "eval_gen_len": 30.37,
+    "eval_loss": 0.4178200960159302,
+    "eval_runtime": 63.4957,
+    "eval_samples": 1100,
+    "eval_samples_per_second": 17.324,
+    "eval_steps_per_second": 0.551,
+    "predict_bleu": 77.1131,
+    "predict_gen_len": 32.6,
+    "predict_loss": 0.4627330005168915,
+    "predict_runtime": 68.6003,
+    "predict_samples": 1100,
+    "predict_samples_per_second": 16.035,
+    "predict_steps_per_second": 0.51,
+    "train_loss": 0.11467816326249321,
+    "train_runtime": 7321.5952,
+    "train_samples": 513666,
+    "train_samples_per_second": 210.473,
+    "train_steps_per_second": 6.578
+}

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "../teams/yor-t5-small",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 1024,
+  "d_kv": 64,
+  "d_model": 512,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "is_gated_act": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32100
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 78.1088,
+    "eval_gen_len": 30.37,
+    "eval_loss": 0.4178200960159302,
+    "eval_runtime": 63.4957,
+    "eval_samples": 1100,
+    "eval_samples_per_second": 17.324,
+    "eval_steps_per_second": 0.551
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.31.0"
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 77.1131,
+    "predict_gen_len": 32.6,
+    "predict_loss": 0.4627330005168915,
+    "predict_runtime": 68.6003,
+    "predict_samples": 1100,
+    "predict_samples_per_second": 16.035,
+    "predict_steps_per_second": 0.51
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73e2e8f17911cafcd56b6fca6d7d822dc15e5d5ead14ae31b36274f92988aa46
+size 307795461

special_tokens_map.json

@@ -0,0 +1,107 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,111 @@
+{
+  "additional_special_tokens": [
+    "<extra_id_0>",
+    "<extra_id_1>",
+    "<extra_id_2>",
+    "<extra_id_3>",
+    "<extra_id_4>",
+    "<extra_id_5>",
+    "<extra_id_6>",
+    "<extra_id_7>",
+    "<extra_id_8>",
+    "<extra_id_9>",
+    "<extra_id_10>",
+    "<extra_id_11>",
+    "<extra_id_12>",
+    "<extra_id_13>",
+    "<extra_id_14>",
+    "<extra_id_15>",
+    "<extra_id_16>",
+    "<extra_id_17>",
+    "<extra_id_18>",
+    "<extra_id_19>",
+    "<extra_id_20>",
+    "<extra_id_21>",
+    "<extra_id_22>",
+    "<extra_id_23>",
+    "<extra_id_24>",
+    "<extra_id_25>",
+    "<extra_id_26>",
+    "<extra_id_27>",
+    "<extra_id_28>",
+    "<extra_id_29>",
+    "<extra_id_30>",
+    "<extra_id_31>",
+    "<extra_id_32>",
+    "<extra_id_33>",
+    "<extra_id_34>",
+    "<extra_id_35>",
+    "<extra_id_36>",
+    "<extra_id_37>",
+    "<extra_id_38>",
+    "<extra_id_39>",
+    "<extra_id_40>",
+    "<extra_id_41>",
+    "<extra_id_42>",
+    "<extra_id_43>",
+    "<extra_id_44>",
+    "<extra_id_45>",
+    "<extra_id_46>",
+    "<extra_id_47>",
+    "<extra_id_48>",
+    "<extra_id_49>",
+    "<extra_id_50>",
+    "<extra_id_51>",
+    "<extra_id_52>",
+    "<extra_id_53>",
+    "<extra_id_54>",
+    "<extra_id_55>",
+    "<extra_id_56>",
+    "<extra_id_57>",
+    "<extra_id_58>",
+    "<extra_id_59>",
+    "<extra_id_60>",
+    "<extra_id_61>",
+    "<extra_id_62>",
+    "<extra_id_63>",
+    "<extra_id_64>",
+    "<extra_id_65>",
+    "<extra_id_66>",
+    "<extra_id_67>",
+    "<extra_id_68>",
+    "<extra_id_69>",
+    "<extra_id_70>",
+    "<extra_id_71>",
+    "<extra_id_72>",
+    "<extra_id_73>",
+    "<extra_id_74>",
+    "<extra_id_75>",
+    "<extra_id_76>",
+    "<extra_id_77>",
+    "<extra_id_78>",
+    "<extra_id_79>",
+    "<extra_id_80>",
+    "<extra_id_81>",
+    "<extra_id_82>",
+    "<extra_id_83>",
+    "<extra_id_84>",
+    "<extra_id_85>",
+    "<extra_id_86>",
+    "<extra_id_87>",
+    "<extra_id_88>",
+    "<extra_id_89>",
+    "<extra_id_90>",
+    "<extra_id_91>",
+    "<extra_id_92>",
+    "<extra_id_93>",
+    "<extra_id_94>",
+    "<extra_id_95>",
+    "<extra_id_96>",
+    "<extra_id_97>",
+    "<extra_id_98>",
+    "<extra_id_99>"
+  ],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 100,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 0.11467816326249321,
+    "train_runtime": 7321.5952,
+    "train_samples": 513666,
+    "train_samples_per_second": 210.473,
+    "train_steps_per_second": 6.578
+}

trainer_state.json

@@ -0,0 +1,601 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 48159,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03,
+      "learning_rate": 4.94808862310264e-05,
+      "loss": 0.6922,
+      "step": 500
+    },
+    {
+      "epoch": 0.06,
+      "learning_rate": 4.8961772462052786e-05,
+      "loss": 0.3808,
+      "step": 1000
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.844265869307918e-05,
+      "loss": 0.3117,
+      "step": 1500
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 4.792354492410557e-05,
+      "loss": 0.2758,
+      "step": 2000
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 4.7404431155131964e-05,
+      "loss": 0.251,
+      "step": 2500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.688531738615835e-05,
+      "loss": 0.2316,
+      "step": 3000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.636620361718475e-05,
+      "loss": 0.2138,
+      "step": 3500
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 4.5847089848211136e-05,
+      "loss": 0.1987,
+      "step": 4000
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 4.5327976079237525e-05,
+      "loss": 0.1947,
+      "step": 4500
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.480886231026392e-05,
+      "loss": 0.1797,
+      "step": 5000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 4.428974854129031e-05,
+      "loss": 0.1747,
+      "step": 5500
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 4.37706347723167e-05,
+      "loss": 0.1664,
+      "step": 6000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.325152100334309e-05,
+      "loss": 0.1611,
+      "step": 6500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.273240723436949e-05,
+      "loss": 0.1529,
+      "step": 7000
+    },
+    {
+      "epoch": 0.47,
+      "learning_rate": 4.2213293465395875e-05,
+      "loss": 0.149,
+      "step": 7500
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 4.169417969642227e-05,
+      "loss": 0.1505,
+      "step": 8000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.1175065927448665e-05,
+      "loss": 0.1459,
+      "step": 8500
+    },
+    {
+      "epoch": 0.56,
+      "learning_rate": 4.0655952158475054e-05,
+      "loss": 0.1406,
+      "step": 9000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 4.013683838950145e-05,
+      "loss": 0.1359,
+      "step": 9500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.961772462052784e-05,
+      "loss": 0.1326,
+      "step": 10000
+    },
+    {
+      "epoch": 0.65,
+      "learning_rate": 3.909861085155423e-05,
+      "loss": 0.132,
+      "step": 10500
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 3.857949708258062e-05,
+      "loss": 0.13,
+      "step": 11000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 3.806038331360701e-05,
+      "loss": 0.124,
+      "step": 11500
+    },
+    {
+      "epoch": 0.75,
+      "learning_rate": 3.7541269544633404e-05,
+      "loss": 0.1242,
+      "step": 12000
+    },
+    {
+      "epoch": 0.78,
+      "learning_rate": 3.702215577565979e-05,
+      "loss": 0.1244,
+      "step": 12500
+    },
+    {
+      "epoch": 0.81,
+      "learning_rate": 3.650304200668619e-05,
+      "loss": 0.1216,
+      "step": 13000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.5983928237712576e-05,
+      "loss": 0.1177,
+      "step": 13500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 3.546481446873897e-05,
+      "loss": 0.1176,
+      "step": 14000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.494570069976536e-05,
+      "loss": 0.1144,
+      "step": 14500
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.4426586930791755e-05,
+      "loss": 0.1127,
+      "step": 15000
+    },
+    {
+      "epoch": 0.97,
+      "learning_rate": 3.390747316181814e-05,
+      "loss": 0.1111,
+      "step": 15500
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 3.338835939284454e-05,
+      "loss": 0.1099,
+      "step": 16000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 3.286924562387093e-05,
+      "loss": 0.1009,
+      "step": 16500
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.235013185489732e-05,
+      "loss": 0.1,
+      "step": 17000
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 3.183101808592372e-05,
+      "loss": 0.0976,
+      "step": 17500
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 3.1311904316950105e-05,
+      "loss": 0.0953,
+      "step": 18000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.079279054797649e-05,
+      "loss": 0.0953,
+      "step": 18500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 3.0273676779002885e-05,
+      "loss": 0.0978,
+      "step": 19000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.975456301002928e-05,
+      "loss": 0.0945,
+      "step": 19500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 2.9235449241055672e-05,
+      "loss": 0.0962,
+      "step": 20000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8716335472082064e-05,
+      "loss": 0.0936,
+      "step": 20500
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 2.8197221703108455e-05,
+      "loss": 0.0952,
+      "step": 21000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 2.7678107934134844e-05,
+      "loss": 0.0927,
+      "step": 21500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 2.715899416516124e-05,
+      "loss": 0.0913,
+      "step": 22000
+    },
+    {
+      "epoch": 1.4,
+      "learning_rate": 2.6639880396187627e-05,
+      "loss": 0.0921,
+      "step": 22500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 2.6120766627214022e-05,
+      "loss": 0.0895,
+      "step": 23000
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 2.5601652858240418e-05,
+      "loss": 0.0869,
+      "step": 23500
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 2.5082539089266806e-05,
+      "loss": 0.0898,
+      "step": 24000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 2.4563425320293194e-05,
+      "loss": 0.0867,
+      "step": 24500
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 2.4044311551319586e-05,
+      "loss": 0.0889,
+      "step": 25000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 2.352519778234598e-05,
+      "loss": 0.0858,
+      "step": 25500
+    },
+    {
+      "epoch": 1.62,
+      "learning_rate": 2.3006084013372373e-05,
+      "loss": 0.0856,
+      "step": 26000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 2.2486970244398765e-05,
+      "loss": 0.0847,
+      "step": 26500
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 2.1967856475425156e-05,
+      "loss": 0.0861,
+      "step": 27000
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 2.1448742706451548e-05,
+      "loss": 0.0847,
+      "step": 27500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 2.0929628937477936e-05,
+      "loss": 0.0819,
+      "step": 28000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.0410515168504328e-05,
+      "loss": 0.0819,
+      "step": 28500
+    },
+    {
+      "epoch": 1.81,
+      "learning_rate": 1.989140139953072e-05,
+      "loss": 0.0856,
+      "step": 29000
+    },
+    {
+      "epoch": 1.84,
+      "learning_rate": 1.9372287630557115e-05,
+      "loss": 0.0828,
+      "step": 29500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 1.8853173861583507e-05,
+      "loss": 0.0832,
+      "step": 30000
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 1.83340600926099e-05,
+      "loss": 0.0823,
+      "step": 30500
+    },
+    {
+      "epoch": 1.93,
+      "learning_rate": 1.781494632363629e-05,
+      "loss": 0.0808,
+      "step": 31000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 1.7295832554662682e-05,
+      "loss": 0.0811,
+      "step": 31500
+    },
+    {
+      "epoch": 1.99,
+      "learning_rate": 1.677671878568907e-05,
+      "loss": 0.084,
+      "step": 32000
+    },
+    {
+      "epoch": 2.02,
+      "learning_rate": 1.6257605016715462e-05,
+      "loss": 0.0769,
+      "step": 32500
+    },
+    {
+      "epoch": 2.06,
+      "learning_rate": 1.5738491247741857e-05,
+      "loss": 0.0733,
+      "step": 33000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 1.5219377478768249e-05,
+      "loss": 0.0724,
+      "step": 33500
+    },
+    {
+      "epoch": 2.12,
+      "learning_rate": 1.470026370979464e-05,
+      "loss": 0.0747,
+      "step": 34000
+    },
+    {
+      "epoch": 2.15,
+      "learning_rate": 1.418114994082103e-05,
+      "loss": 0.0715,
+      "step": 34500
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.3662036171847422e-05,
+      "loss": 0.0736,
+      "step": 35000
+    },
+    {
+      "epoch": 2.21,
+      "learning_rate": 1.3142922402873814e-05,
+      "loss": 0.0745,
+      "step": 35500
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 1.2623808633900206e-05,
+      "loss": 0.0732,
+      "step": 36000
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 1.2104694864926598e-05,
+      "loss": 0.0738,
+      "step": 36500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.158558109595299e-05,
+      "loss": 0.0739,
+      "step": 37000
+    },
+    {
+      "epoch": 2.34,
+      "learning_rate": 1.1066467326979381e-05,
+      "loss": 0.0703,
+      "step": 37500
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 1.0547353558005773e-05,
+      "loss": 0.072,
+      "step": 38000
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.0028239789032165e-05,
+      "loss": 0.0723,
+      "step": 38500
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.509126020058556e-06,
+      "loss": 0.0734,
+      "step": 39000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 8.990012251084948e-06,
+      "loss": 0.0702,
+      "step": 39500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 8.47089848211134e-06,
+      "loss": 0.0712,
+      "step": 40000
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 7.951784713137732e-06,
+      "loss": 0.0713,
+      "step": 40500
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 7.432670944164123e-06,
+      "loss": 0.0719,
+      "step": 41000
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 6.913557175190514e-06,
+      "loss": 0.0718,
+      "step": 41500
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 6.394443406216908e-06,
+      "loss": 0.0709,
+      "step": 42000
+    },
+    {
+      "epoch": 2.65,
+      "learning_rate": 5.8753296372432985e-06,
+      "loss": 0.07,
+      "step": 42500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 5.35621586826969e-06,
+      "loss": 0.068,
+      "step": 43000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 4.837102099296082e-06,
+      "loss": 0.0714,
+      "step": 43500
+    },
+    {
+      "epoch": 2.74,
+      "learning_rate": 4.317988330322474e-06,
+      "loss": 0.0719,
+      "step": 44000
+    },
+    {
+      "epoch": 2.77,
+      "learning_rate": 3.7988745613488655e-06,
+      "loss": 0.0678,
+      "step": 44500
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 3.2797607923752568e-06,
+      "loss": 0.0693,
+      "step": 45000
+    },
+    {
+      "epoch": 2.83,
+      "learning_rate": 2.760647023401649e-06,
+      "loss": 0.0677,
+      "step": 45500
+    },
+    {
+      "epoch": 2.87,
+      "learning_rate": 2.2415332544280407e-06,
+      "loss": 0.0711,
+      "step": 46000
+    },
+    {
+      "epoch": 2.9,
+      "learning_rate": 1.7224194854544324e-06,
+      "loss": 0.0692,
+      "step": 46500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.203305716480824e-06,
+      "loss": 0.0692,
+      "step": 47000
+    },
+    {
+      "epoch": 2.96,
+      "learning_rate": 6.841919475072158e-07,
+      "loss": 0.0699,
+      "step": 47500
+    },
+    {
+      "epoch": 2.99,
+      "learning_rate": 1.6507817853360744e-07,
+      "loss": 0.0711,
+      "step": 48000
+    },
+    {
+      "epoch": 3.0,
+      "step": 48159,
+      "total_flos": 5.191245227822285e+16,
+      "train_loss": 0.11467816326249321,
+      "train_runtime": 7321.5952,
+      "train_samples_per_second": 210.473,
+      "train_steps_per_second": 6.578
+    }
+  ],
+  "max_steps": 48159,
+  "num_train_epochs": 3,
+  "total_flos": 5.191245227822285e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97438cc75f0d7d1e221705252d1c16eadff8d8897612e181bff3314d7abfde7b
+size 4091