End of training

.gitignore

@@ -0,0 +1 @@
+checkpoint-*/

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.7986,
+    "eval_loss": 0.33286044001579285,
+    "eval_runtime": 151.7682,
+    "eval_samples": 4887,
+    "eval_samples_per_second": 32.2,
+    "eval_steps_per_second": 2.016,
+    "train_loss": 0.0,
+    "train_runtime": 0.057,
+    "train_samples": 87866,
+    "train_samples_per_second": 1541330.369,
+    "train_steps_per_second": 192661.911
+}

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "t5-large",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 4096,
+  "d_kv": 64,
+  "d_model": 1024,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 24,
+  "num_heads": 16,
+  "num_layers": 24,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "torch_dtype": "float32",
+  "transformers_version": "4.11.3",
+  "use_cache": true,
+  "vocab_size": 32100
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 2.0,
+    "eval_accuracy": 0.7986,
+    "eval_loss": 0.33286044001579285,
+    "eval_runtime": 151.7682,
+    "eval_samples": 4887,
+    "eval_samples_per_second": 32.2,
+    "eval_steps_per_second": 2.016
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c129de941d14268599c41de3b73b6af275457445a117b4fb84eae464de58f04
+size 2950790023

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>"], "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "t5-large", "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 0.0,
+    "train_runtime": 0.057,
+    "train_samples": 87866,
+    "train_samples_per_second": 1541330.369,
+    "train_steps_per_second": 192661.911
+}

trainer_state.json

@@ -0,0 +1,301 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9999544771703008,
+  "global_step": 21966,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.878230691954093e-05,
+      "loss": 0.7559,
+      "step": 500
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.726019056896709e-05,
+      "loss": 0.4773,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.573807421839326e-05,
+      "loss": 0.4477,
+      "step": 1500
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.421595786781941e-05,
+      "loss": 0.4385,
+      "step": 2000
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.269384151724558e-05,
+      "loss": 0.4258,
+      "step": 2500
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.117172516667175e-05,
+      "loss": 0.419,
+      "step": 3000
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 8.964960881609791e-05,
+      "loss": 0.4017,
+      "step": 3500
+    },
+    {
+      "epoch": 0.36,
+      "learning_rate": 8.812749246552407e-05,
+      "loss": 0.4165,
+      "step": 4000
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 8.660537611495024e-05,
+      "loss": 0.4148,
+      "step": 4500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 8.508325976437639e-05,
+      "loss": 0.406,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 8.356114341380256e-05,
+      "loss": 0.395,
+      "step": 5500
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 8.203902706322871e-05,
+      "loss": 0.3927,
+      "step": 6000
+    },
+    {
+      "epoch": 0.59,
+      "learning_rate": 8.051691071265488e-05,
+      "loss": 0.3776,
+      "step": 6500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 7.899479436208103e-05,
+      "loss": 0.3555,
+      "step": 7000
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 7.74726780115072e-05,
+      "loss": 0.3731,
+      "step": 7500
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 7.595056166093336e-05,
+      "loss": 0.3593,
+      "step": 8000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 7.442844531035952e-05,
+      "loss": 0.3643,
+      "step": 8500
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 7.290632895978569e-05,
+      "loss": 0.3607,
+      "step": 9000
+    },
+    {
+      "epoch": 0.86,
+      "learning_rate": 7.138421260921186e-05,
+      "loss": 0.3404,
+      "step": 9500
+    },
+    {
+      "epoch": 0.91,
+      "learning_rate": 6.986209625863801e-05,
+      "loss": 0.3527,
+      "step": 10000
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 6.833997990806418e-05,
+      "loss": 0.3513,
+      "step": 10500
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7714,
+      "eval_loss": 0.3165387809276581,
+      "eval_runtime": 145.7923,
+      "eval_samples_per_second": 33.52,
+      "eval_steps_per_second": 2.099,
+      "step": 10983
+    },
+    {
+      "epoch": 1.0,
+      "learning_rate": 6.681786355749033e-05,
+      "loss": 0.3399,
+      "step": 11000
+    },
+    {
+      "epoch": 1.05,
+      "learning_rate": 6.52957472069165e-05,
+      "loss": 0.2111,
+      "step": 11500
+    },
+    {
+      "epoch": 1.09,
+      "learning_rate": 6.377363085634266e-05,
+      "loss": 0.2117,
+      "step": 12000
+    },
+    {
+      "epoch": 1.14,
+      "learning_rate": 6.225151450576882e-05,
+      "loss": 0.2152,
+      "step": 12500
+    },
+    {
+      "epoch": 1.18,
+      "learning_rate": 6.0729398155194985e-05,
+      "loss": 0.2217,
+      "step": 13000
+    },
+    {
+      "epoch": 1.23,
+      "learning_rate": 5.920728180462115e-05,
+      "loss": 0.2194,
+      "step": 13500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.768516545404731e-05,
+      "loss": 0.224,
+      "step": 14000
+    },
+    {
+      "epoch": 1.32,
+      "learning_rate": 5.6163049103473475e-05,
+      "loss": 0.2262,
+      "step": 14500
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 5.464093275289963e-05,
+      "loss": 0.2308,
+      "step": 15000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 5.31188164023258e-05,
+      "loss": 0.2266,
+      "step": 15500
+    },
+    {
+      "epoch": 1.46,
+      "learning_rate": 5.159670005175196e-05,
+      "loss": 0.2162,
+      "step": 16000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 5.0074583701178126e-05,
+      "loss": 0.2288,
+      "step": 16500
+    },
+    {
+      "epoch": 1.55,
+      "learning_rate": 4.855246735060428e-05,
+      "loss": 0.2268,
+      "step": 17000
+    },
+    {
+      "epoch": 1.59,
+      "learning_rate": 4.703035100003044e-05,
+      "loss": 0.2136,
+      "step": 17500
+    },
+    {
+      "epoch": 1.64,
+      "learning_rate": 4.55082346494566e-05,
+      "loss": 0.2199,
+      "step": 18000
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.398611829888277e-05,
+      "loss": 0.2187,
+      "step": 18500
+    },
+    {
+      "epoch": 1.73,
+      "learning_rate": 4.246400194830893e-05,
+      "loss": 0.2104,
+      "step": 19000
+    },
+    {
+      "epoch": 1.78,
+      "learning_rate": 4.094188559773509e-05,
+      "loss": 0.2093,
+      "step": 19500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.941976924716125e-05,
+      "loss": 0.2133,
+      "step": 20000
+    },
+    {
+      "epoch": 1.87,
+      "learning_rate": 3.7897652896587414e-05,
+      "loss": 0.2122,
+      "step": 20500
+    },
+    {
+      "epoch": 1.91,
+      "learning_rate": 3.6375536546013575e-05,
+      "loss": 0.2103,
+      "step": 21000
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 3.485342019543974e-05,
+      "loss": 0.2109,
+      "step": 21500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7986,
+      "eval_loss": 0.33286044001579285,
+      "eval_runtime": 145.5877,
+      "eval_samples_per_second": 33.567,
+      "eval_steps_per_second": 2.102,
+      "step": 21966
+    },
+    {
+      "epoch": 2.0,
+      "step": 21966,
+      "total_flos": 3.80468091420672e+17,
+      "train_loss": 0.0,
+      "train_runtime": 0.057,
+      "train_samples_per_second": 1541330.369,
+      "train_steps_per_second": 192661.911
+    }
+  ],
+  "max_steps": 10983,
+  "num_train_epochs": 1,
+  "total_flos": 3.80468091420672e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a2565c39287ef9a560b024aded0fa87f7dd9a636e2ef6ff73357484ea0a21c7
+size 2927