Upload 12 files

all_results.json

@@ -0,0 +1,22 @@
+{
+    "epoch": 49.99,
+    "eval_bleu": 13.3045,
+    "eval_gen_len": 52.68,
+    "eval_loss": 0.0720854178071022,
+    "eval_runtime": 1369.197,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.461,
+    "eval_steps_per_second": 0.365,
+    "predict_bleu": 5.9237,
+    "predict_gen_len": 57.5955,
+    "predict_loss": 3.454662322998047,
+    "predict_runtime": 708.4112,
+    "predict_samples": 1288,
+    "predict_samples_per_second": 1.818,
+    "predict_steps_per_second": 0.455,
+    "train_loss": 0.5685424493974255,
+    "train_runtime": 3913.436,
+    "train_samples": 2000,
+    "train_samples_per_second": 25.553,
+    "train_steps_per_second": 0.792
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "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",
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "mt5",
+  "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,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.12.3",
+  "use_cache": true,
+  "vocab_size": 250100
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 49.99,
+    "eval_bleu": 13.3045,
+    "eval_gen_len": 52.68,
+    "eval_loss": 0.0720854178071022,
+    "eval_runtime": 1369.197,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 1.461,
+    "eval_steps_per_second": 0.365
+}

predict_results.json

@@ -0,0 +1,9 @@
+{
+    "predict_bleu": 5.9237,
+    "predict_gen_len": 57.5955,
+    "predict_loss": 3.454662322998047,
+    "predict_runtime": 708.4112,
+    "predict_samples": 1288,
+    "predict_samples_per_second": 1.818,
+    "predict_steps_per_second": 0.455
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eda597d50d56363e2096c9d27ad893674c59450f1643835686b92e3250a11457
+size 2329626573

special_tokens_map.json

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

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef78f86560d809067d12bac6c09f19a462cb3af3f54d2b8acbba26e1433125d6
+size 4309802

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 0, "additional_special_tokens": null, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "name_or_path": "google/mt5-base", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 49.99,
+    "train_loss": 0.5685424493974255,
+    "train_runtime": 3913.436,
+    "train_samples": 2000,
+    "train_samples_per_second": 25.553,
+    "train_steps_per_second": 0.792
+}

trainer_state.json

@@ -0,0 +1,221 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 49.992,
+  "global_step": 3100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.61,
+      "learning_rate": 0.000967741935483871,
+      "loss": 5.0178,
+      "step": 100
+    },
+    {
+      "epoch": 3.22,
+      "learning_rate": 0.0009354838709677419,
+      "loss": 2.8191,
+      "step": 200
+    },
+    {
+      "epoch": 4.83,
+      "learning_rate": 0.0009032258064516129,
+      "loss": 2.0873,
+      "step": 300
+    },
+    {
+      "epoch": 6.45,
+      "learning_rate": 0.0008709677419354839,
+      "loss": 1.5077,
+      "step": 400
+    },
+    {
+      "epoch": 8.06,
+      "learning_rate": 0.0008387096774193549,
+      "loss": 1.1005,
+      "step": 500
+    },
+    {
+      "epoch": 9.67,
+      "learning_rate": 0.0008064516129032258,
+      "loss": 0.7513,
+      "step": 600
+    },
+    {
+      "epoch": 11.29,
+      "learning_rate": 0.0007741935483870968,
+      "loss": 0.5449,
+      "step": 700
+    },
+    {
+      "epoch": 12.9,
+      "learning_rate": 0.0007419354838709678,
+      "loss": 0.415,
+      "step": 800
+    },
+    {
+      "epoch": 14.51,
+      "learning_rate": 0.0007096774193548388,
+      "loss": 0.3257,
+      "step": 900
+    },
+    {
+      "epoch": 16.13,
+      "learning_rate": 0.0006774193548387097,
+      "loss": 0.2728,
+      "step": 1000
+    },
+    {
+      "epoch": 17.74,
+      "learning_rate": 0.0006451612903225806,
+      "loss": 0.2365,
+      "step": 1100
+    },
+    {
+      "epoch": 19.35,
+      "learning_rate": 0.0006129032258064516,
+      "loss": 0.2159,
+      "step": 1200
+    },
+    {
+      "epoch": 20.96,
+      "learning_rate": 0.0005806451612903226,
+      "loss": 0.1881,
+      "step": 1300
+    },
+    {
+      "epoch": 22.58,
+      "learning_rate": 0.0005483870967741935,
+      "loss": 0.1687,
+      "step": 1400
+    },
+    {
+      "epoch": 24.19,
+      "learning_rate": 0.0005161290322580645,
+      "loss": 0.1611,
+      "step": 1500
+    },
+    {
+      "epoch": 25.8,
+      "learning_rate": 0.0004838709677419355,
+      "loss": 0.1469,
+      "step": 1600
+    },
+    {
+      "epoch": 27.42,
+      "learning_rate": 0.00045161290322580643,
+      "loss": 0.1405,
+      "step": 1700
+    },
+    {
+      "epoch": 29.03,
+      "learning_rate": 0.00041935483870967743,
+      "loss": 0.136,
+      "step": 1800
+    },
+    {
+      "epoch": 30.64,
+      "learning_rate": 0.0003870967741935484,
+      "loss": 0.1266,
+      "step": 1900
+    },
+    {
+      "epoch": 32.26,
+      "learning_rate": 0.0003548387096774194,
+      "loss": 0.1247,
+      "step": 2000
+    },
+    {
+      "epoch": 32.26,
+      "eval_bleu": 4.2768,
+      "eval_gen_len": 18.2295,
+      "eval_loss": 0.07783249020576477,
+      "eval_runtime": 151.6677,
+      "eval_samples_per_second": 13.187,
+      "eval_steps_per_second": 3.297,
+      "step": 2000
+    },
+    {
+      "epoch": 33.86,
+      "learning_rate": 0.0003225806451612903,
+      "loss": 0.1175,
+      "step": 2100
+    },
+    {
+      "epoch": 35.48,
+      "learning_rate": 0.0002903225806451613,
+      "loss": 0.1128,
+      "step": 2200
+    },
+    {
+      "epoch": 37.1,
+      "learning_rate": 0.00025806451612903227,
+      "loss": 0.1127,
+      "step": 2300
+    },
+    {
+      "epoch": 38.7,
+      "learning_rate": 0.00022580645161290321,
+      "loss": 0.106,
+      "step": 2400
+    },
+    {
+      "epoch": 40.32,
+      "learning_rate": 0.0001935483870967742,
+      "loss": 0.1062,
+      "step": 2500
+    },
+    {
+      "epoch": 41.93,
+      "learning_rate": 0.00016129032258064516,
+      "loss": 0.1026,
+      "step": 2600
+    },
+    {
+      "epoch": 43.54,
+      "learning_rate": 0.00012903225806451613,
+      "loss": 0.0995,
+      "step": 2700
+    },
+    {
+      "epoch": 45.16,
+      "learning_rate": 9.67741935483871e-05,
+      "loss": 0.0985,
+      "step": 2800
+    },
+    {
+      "epoch": 46.77,
+      "learning_rate": 6.451612903225807e-05,
+      "loss": 0.0958,
+      "step": 2900
+    },
+    {
+      "epoch": 48.38,
+      "learning_rate": 3.2258064516129034e-05,
+      "loss": 0.0942,
+      "step": 3000
+    },
+    {
+      "epoch": 49.99,
+      "learning_rate": 0.0,
+      "loss": 0.092,
+      "step": 3100
+    },
+    {
+      "epoch": 49.99,
+      "step": 3100,
+      "total_flos": 2.628606767136768e+16,
+      "train_loss": 0.5685424493974255,
+      "train_runtime": 3913.436,
+      "train_samples_per_second": 25.553,
+      "train_steps_per_second": 0.792
+    }
+  ],
+  "max_steps": 3100,
+  "num_train_epochs": 50,
+  "total_flos": 2.628606767136768e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:994e743c48e1cb08af8c516fb7f2ddc3caf04cd3c65c86f52caa2202274e1023
+size 2927