trained model

README.md

@@ -0,0 +1,59 @@
+---
+tags:
+- generated_from_trainer
+metrics:
+- rouge
+model-index:
+- name: summarization_fanpage
+  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. -->
+
+# summarization_fanpage
+
+This model is a fine-tuned version of [gsarti/it5-base](https://huggingface.co/gsarti/it5-base) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4897
+- Rouge1: 33.5599
+- Rouge2: 15.7432
+- Rougel: 25.5253
+- Rougelsum: 28.1784
+- Gen Len: 57.2958
+
+## 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: 6
+- eval_batch_size: 6
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 4.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.12.0.dev0
+- Pytorch 1.9.1+cu102
+- Datasets 1.12.1
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,28 @@
+{
+    "epoch": 4.0,
+    "eval_gen_len": 57.2958,
+    "eval_loss": 1.4897323846817017,
+    "eval_rouge1": 33.5599,
+    "eval_rouge2": 15.7432,
+    "eval_rougeL": 25.5253,
+    "eval_rougeLsum": 28.1784,
+    "eval_runtime": 1785.3491,
+    "eval_samples": 8436,
+    "eval_samples_per_second": 4.725,
+    "eval_steps_per_second": 0.788,
+    "predict_gen_len": 57.1478,
+    "predict_loss": 1.480366826057434,
+    "predict_rouge1": 33.7077,
+    "predict_rouge2": 15.8637,
+    "predict_rougeL": 25.5936,
+    "predict_rougeLsum": 28.1495,
+    "predict_runtime": 1786.1581,
+    "predict_samples": 8437,
+    "predict_samples_per_second": 4.724,
+    "predict_steps_per_second": 0.788,
+    "train_loss": 1.610106024723899,
+    "train_runtime": 44159.403,
+    "train_samples": 67492,
+    "train_samples_per_second": 6.113,
+    "train_steps_per_second": 1.019
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "gsarti/it5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "gated-gelu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32103
+}

eval_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 4.0,
+    "eval_gen_len": 57.2958,
+    "eval_loss": 1.4897323846817017,
+    "eval_rouge1": 33.5599,
+    "eval_rouge2": 15.7432,
+    "eval_rougeL": 25.5253,
+    "eval_rougeLsum": 28.1784,
+    "eval_runtime": 1785.3491,
+    "eval_samples": 8436,
+    "eval_samples_per_second": 4.725,
+    "eval_steps_per_second": 0.788
+}

predict_results.json

@@ -0,0 +1,12 @@
+{
+    "predict_gen_len": 57.1478,
+    "predict_loss": 1.480366826057434,
+    "predict_rouge1": 33.7077,
+    "predict_rouge2": 15.8637,
+    "predict_rougeL": 25.5936,
+    "predict_rougeLsum": 28.1495,
+    "predict_runtime": 1786.1581,
+    "predict_samples": 8437,
+    "predict_samples_per_second": 4.724,
+    "predict_steps_per_second": 0.788
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e095685c7e6b6aa22c62ae31faebbdbb176b1e08e7dbc144281ccfb2feb9cd69
+size 990284749

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "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>"], "special_tokens_map_file": null, "name_or_path": "gsarti/it5-base", "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 4.0,
+    "train_loss": 1.610106024723899,
+    "train_runtime": 44159.403,
+    "train_samples": 67492,
+    "train_samples_per_second": 6.113,
+    "train_steps_per_second": 1.019
+}

trainer_state.json

@@ -0,0 +1,559 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 4.0,
+  "global_step": 44996,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.04,
+      "learning_rate": 4.9444395057338435e-05,
+      "loss": 2.1204,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.888879011467686e-05,
+      "loss": 1.8331,
+      "step": 1000
+    },
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.8333185172015294e-05,
+      "loss": 1.7746,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.777758022935373e-05,
+      "loss": 1.7646,
+      "step": 2000
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 4.722197528669215e-05,
+      "loss": 1.7504,
+      "step": 2500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.6666370344030586e-05,
+      "loss": 1.7338,
+      "step": 3000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 4.611076540136901e-05,
+      "loss": 1.713,
+      "step": 3500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 4.555516045870744e-05,
+      "loss": 1.6983,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.499955551604587e-05,
+      "loss": 1.7004,
+      "step": 4500
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.44439505733843e-05,
+      "loss": 1.7119,
+      "step": 5000
+    },
+    {
+      "epoch": 0.49,
+      "learning_rate": 4.388834563072273e-05,
+      "loss": 1.6919,
+      "step": 5500
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.333274068806116e-05,
+      "loss": 1.6658,
+      "step": 6000
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 4.2777135745399595e-05,
+      "loss": 1.6654,
+      "step": 6500
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 4.222153080273802e-05,
+      "loss": 1.671,
+      "step": 7000
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 4.1665925860076454e-05,
+      "loss": 1.6673,
+      "step": 7500
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 4.1110320917414887e-05,
+      "loss": 1.6761,
+      "step": 8000
+    },
+    {
+      "epoch": 0.76,
+      "learning_rate": 4.055471597475331e-05,
+      "loss": 1.6663,
+      "step": 8500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.9999111032091745e-05,
+      "loss": 1.6625,
+      "step": 9000
+    },
+    {
+      "epoch": 0.84,
+      "learning_rate": 3.944350608943017e-05,
+      "loss": 1.6562,
+      "step": 9500
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.8887901146768604e-05,
+      "loss": 1.65,
+      "step": 10000
+    },
+    {
+      "epoch": 0.93,
+      "learning_rate": 3.833229620410703e-05,
+      "loss": 1.6459,
+      "step": 10500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.777669126144546e-05,
+      "loss": 1.6298,
+      "step": 11000
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.7221086318783896e-05,
+      "loss": 1.6273,
+      "step": 11500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 3.666548137612232e-05,
+      "loss": 1.6184,
+      "step": 12000
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 3.6109876433460755e-05,
+      "loss": 1.6359,
+      "step": 12500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 3.555427149079919e-05,
+      "loss": 1.6123,
+      "step": 13000
+    },
+    {
+      "epoch": 1.2,
+      "learning_rate": 3.4998666548137613e-05,
+      "loss": 1.6115,
+      "step": 13500
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 3.4443061605476046e-05,
+      "loss": 1.5998,
+      "step": 14000
+    },
+    {
+      "epoch": 1.29,
+      "learning_rate": 3.388745666281448e-05,
+      "loss": 1.606,
+      "step": 14500
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 3.3331851720152905e-05,
+      "loss": 1.6176,
+      "step": 15000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 3.277624677749133e-05,
+      "loss": 1.6295,
+      "step": 15500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 3.2220641834829764e-05,
+      "loss": 1.599,
+      "step": 16000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 3.166503689216819e-05,
+      "loss": 1.6,
+      "step": 16500
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 3.110943194950662e-05,
+      "loss": 1.6144,
+      "step": 17000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 3.0553827006845055e-05,
+      "loss": 1.6121,
+      "step": 17500
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.9998222064183485e-05,
+      "loss": 1.5894,
+      "step": 18000
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 2.9442617121521914e-05,
+      "loss": 1.6109,
+      "step": 18500
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.8887012178860344e-05,
+      "loss": 1.5859,
+      "step": 19000
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 2.8331407236198777e-05,
+      "loss": 1.6049,
+      "step": 19500
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 2.7775802293537206e-05,
+      "loss": 1.5907,
+      "step": 20000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 2.7220197350875635e-05,
+      "loss": 1.6062,
+      "step": 20500
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 2.6664592408214068e-05,
+      "loss": 1.5877,
+      "step": 21000
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 2.610898746555249e-05,
+      "loss": 1.6094,
+      "step": 21500
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 2.5553382522890924e-05,
+      "loss": 1.6086,
+      "step": 22000
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 2.4997777580229356e-05,
+      "loss": 1.5772,
+      "step": 22500
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 2.4442172637567782e-05,
+      "loss": 1.5625,
+      "step": 23000
+    },
+    {
+      "epoch": 2.09,
+      "learning_rate": 2.3886567694906215e-05,
+      "loss": 1.5736,
+      "step": 23500
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 2.3330962752244645e-05,
+      "loss": 1.5649,
+      "step": 24000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 2.2775357809583074e-05,
+      "loss": 1.5764,
+      "step": 24500
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 2.2219752866921507e-05,
+      "loss": 1.5899,
+      "step": 25000
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 2.1664147924259936e-05,
+      "loss": 1.5876,
+      "step": 25500
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 2.1108542981598366e-05,
+      "loss": 1.5827,
+      "step": 26000
+    },
+    {
+      "epoch": 2.36,
+      "learning_rate": 2.0552938038936795e-05,
+      "loss": 1.5525,
+      "step": 26500
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.9997333096275224e-05,
+      "loss": 1.5801,
+      "step": 27000
+    },
+    {
+      "epoch": 2.44,
+      "learning_rate": 1.9441728153613657e-05,
+      "loss": 1.5754,
+      "step": 27500
+    },
+    {
+      "epoch": 2.49,
+      "learning_rate": 1.8886123210952087e-05,
+      "loss": 1.5766,
+      "step": 28000
+    },
+    {
+      "epoch": 2.53,
+      "learning_rate": 1.8330518268290516e-05,
+      "loss": 1.5756,
+      "step": 28500
+    },
+    {
+      "epoch": 2.58,
+      "learning_rate": 1.7774913325628945e-05,
+      "loss": 1.5625,
+      "step": 29000
+    },
+    {
+      "epoch": 2.62,
+      "learning_rate": 1.7219308382967375e-05,
+      "loss": 1.5679,
+      "step": 29500
+    },
+    {
+      "epoch": 2.67,
+      "learning_rate": 1.6663703440305804e-05,
+      "loss": 1.5466,
+      "step": 30000
+    },
+    {
+      "epoch": 2.71,
+      "learning_rate": 1.6108098497644237e-05,
+      "loss": 1.5764,
+      "step": 30500
+    },
+    {
+      "epoch": 2.76,
+      "learning_rate": 1.5552493554982667e-05,
+      "loss": 1.5482,
+      "step": 31000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 1.4996888612321098e-05,
+      "loss": 1.5606,
+      "step": 31500
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 1.4441283669659525e-05,
+      "loss": 1.5573,
+      "step": 32000
+    },
+    {
+      "epoch": 2.89,
+      "learning_rate": 1.3885678726997955e-05,
+      "loss": 1.5609,
+      "step": 32500
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.3330073784336386e-05,
+      "loss": 1.5708,
+      "step": 33000
+    },
+    {
+      "epoch": 2.98,
+      "learning_rate": 1.2774468841674817e-05,
+      "loss": 1.5692,
+      "step": 33500
+    },
+    {
+      "epoch": 3.02,
+      "learning_rate": 1.2218863899013246e-05,
+      "loss": 1.5581,
+      "step": 34000
+    },
+    {
+      "epoch": 3.07,
+      "learning_rate": 1.1663258956351676e-05,
+      "loss": 1.5494,
+      "step": 34500
+    },
+    {
+      "epoch": 3.11,
+      "learning_rate": 1.1107654013690107e-05,
+      "loss": 1.5708,
+      "step": 35000
+    },
+    {
+      "epoch": 3.16,
+      "learning_rate": 1.0552049071028536e-05,
+      "loss": 1.5547,
+      "step": 35500
+    },
+    {
+      "epoch": 3.2,
+      "learning_rate": 9.996444128366966e-06,
+      "loss": 1.5562,
+      "step": 36000
+    },
+    {
+      "epoch": 3.24,
+      "learning_rate": 9.440839185705397e-06,
+      "loss": 1.5494,
+      "step": 36500
+    },
+    {
+      "epoch": 3.29,
+      "learning_rate": 8.885234243043826e-06,
+      "loss": 1.5419,
+      "step": 37000
+    },
+    {
+      "epoch": 3.33,
+      "learning_rate": 8.329629300382257e-06,
+      "loss": 1.589,
+      "step": 37500
+    },
+    {
+      "epoch": 3.38,
+      "learning_rate": 7.774024357720687e-06,
+      "loss": 1.5522,
+      "step": 38000
+    },
+    {
+      "epoch": 3.42,
+      "learning_rate": 7.218419415059116e-06,
+      "loss": 1.5628,
+      "step": 38500
+    },
+    {
+      "epoch": 3.47,
+      "learning_rate": 6.662814472397546e-06,
+      "loss": 1.5303,
+      "step": 39000
+    },
+    {
+      "epoch": 3.51,
+      "learning_rate": 6.1072095297359775e-06,
+      "loss": 1.5304,
+      "step": 39500
+    },
+    {
+      "epoch": 3.56,
+      "learning_rate": 5.551604587074407e-06,
+      "loss": 1.5604,
+      "step": 40000
+    },
+    {
+      "epoch": 3.6,
+      "learning_rate": 4.995999644412837e-06,
+      "loss": 1.5528,
+      "step": 40500
+    },
+    {
+      "epoch": 3.64,
+      "learning_rate": 4.4403947017512674e-06,
+      "loss": 1.5454,
+      "step": 41000
+    },
+    {
+      "epoch": 3.69,
+      "learning_rate": 3.884789759089697e-06,
+      "loss": 1.5386,
+      "step": 41500
+    },
+    {
+      "epoch": 3.73,
+      "learning_rate": 3.329184816428127e-06,
+      "loss": 1.5465,
+      "step": 42000
+    },
+    {
+      "epoch": 3.78,
+      "learning_rate": 2.773579873766557e-06,
+      "loss": 1.5603,
+      "step": 42500
+    },
+    {
+      "epoch": 3.82,
+      "learning_rate": 2.217974931104987e-06,
+      "loss": 1.549,
+      "step": 43000
+    },
+    {
+      "epoch": 3.87,
+      "learning_rate": 1.662369988443417e-06,
+      "loss": 1.5602,
+      "step": 43500
+    },
+    {
+      "epoch": 3.91,
+      "learning_rate": 1.1067650457818473e-06,
+      "loss": 1.5377,
+      "step": 44000
+    },
+    {
+      "epoch": 3.96,
+      "learning_rate": 5.511601031202774e-07,
+      "loss": 1.5505,
+      "step": 44500
+    },
+    {
+      "epoch": 4.0,
+      "step": 44996,
+      "total_flos": 2.071270394312233e+17,
+      "train_loss": 1.610106024723899,
+      "train_runtime": 44159.403,
+      "train_samples_per_second": 6.113,
+      "train_steps_per_second": 1.019
+    }
+  ],
+  "max_steps": 44996,
+  "num_train_epochs": 4,
+  "total_flos": 2.071270394312233e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:395b59b798351c002d8fa39da9d9d921aaea81886a2181b90365982922a49d25
+size 2927