Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-base",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "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": "mt5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.23.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d82996cd4396bdbf3739380d7efebb95b16a02c7475082b2b54622750ed9c79
+size 4659378441

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c0219749288e7a9e48936ffb1a5e59a1f90bafee3f61845373188bc954b6ade
+size 2329700173

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c446be1f8516743233b4e0b9846261662475a5cb4d5d45632a9d379845ad44ba
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3292d391378c15098fa3e719b4601bb844554b25583c651ba76a6e6925f33070
+size 623

special_tokens_map.json

@@ -0,0 +1,5 @@
+{
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

spiece.model

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3ab6fe9ed1c8353b3bfcf922087786bade8c0ee4f7dfdeca1b424c725aaef39
+size 16330466

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "name_or_path": "google/mt5-base",
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276",
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,220 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.899416255051639,
+  "global_step": 26500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_bleu 1": 70.3337,
+      "eval_bleu 2": 60.798,
+      "eval_bleu 3": 49.7924,
+      "eval_bleu 4": 33.7923,
+      "eval_loss": 0.6441967487335205,
+      "eval_rouge1": 50.4785,
+      "eval_rouge2": 32.871,
+      "eval_rougeL": 50.0855,
+      "eval_rougeLsum": 50.0558,
+      "eval_runtime": 684.1071,
+      "eval_samples_per_second": 12.122,
+      "eval_score": 32.2794,
+      "eval_sim_cos": 0.7653,
+      "eval_steps_per_second": 3.032,
+      "step": 2227
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu 1": 70.3322,
+      "eval_bleu 2": 61.1932,
+      "eval_bleu 3": 50.7058,
+      "eval_bleu 4": 35.6325,
+      "eval_loss": 0.5984485745429993,
+      "eval_rouge1": 51.6586,
+      "eval_rouge2": 34.8166,
+      "eval_rougeL": 51.2221,
+      "eval_rougeLsum": 51.2004,
+      "eval_runtime": 689.9391,
+      "eval_samples_per_second": 12.02,
+      "eval_score": 33.6509,
+      "eval_sim_cos": 0.7702,
+      "eval_steps_per_second": 3.006,
+      "step": 4454
+    },
+    {
+      "epoch": 3.0,
+      "eval_bleu 1": 69.8987,
+      "eval_bleu 2": 60.7039,
+      "eval_bleu 3": 50.0866,
+      "eval_bleu 4": 35.1525,
+      "eval_loss": 0.579205334186554,
+      "eval_rouge1": 51.7058,
+      "eval_rouge2": 34.7654,
+      "eval_rougeL": 51.0676,
+      "eval_rougeLsum": 51.0349,
+      "eval_runtime": 700.0697,
+      "eval_samples_per_second": 11.846,
+      "eval_score": 34.5869,
+      "eval_sim_cos": 0.7717,
+      "eval_steps_per_second": 2.963,
+      "step": 6681
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu 1": 71.3187,
+      "eval_bleu 2": 62.1795,
+      "eval_bleu 3": 51.5483,
+      "eval_bleu 4": 36.2898,
+      "eval_loss": 0.5839173793792725,
+      "eval_rouge1": 52.2274,
+      "eval_rouge2": 35.3155,
+      "eval_rougeL": 51.6932,
+      "eval_rougeLsum": 51.6431,
+      "eval_runtime": 686.5612,
+      "eval_samples_per_second": 12.079,
+      "eval_score": 34.2209,
+      "eval_sim_cos": 0.7769,
+      "eval_steps_per_second": 3.021,
+      "step": 8908
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu 1": 70.0029,
+      "eval_bleu 2": 60.8847,
+      "eval_bleu 3": 50.4903,
+      "eval_bleu 4": 35.8533,
+      "eval_loss": 0.5703114867210388,
+      "eval_rouge1": 52.2272,
+      "eval_rouge2": 35.5618,
+      "eval_rougeL": 51.643,
+      "eval_rougeLsum": 51.622,
+      "eval_runtime": 704.1871,
+      "eval_samples_per_second": 11.777,
+      "eval_score": 35.0827,
+      "eval_sim_cos": 0.7735,
+      "eval_steps_per_second": 2.945,
+      "step": 11135
+    },
+    {
+      "epoch": 6.0,
+      "eval_bleu 1": 69.3858,
+      "eval_bleu 2": 60.1128,
+      "eval_bleu 3": 49.6906,
+      "eval_bleu 4": 35.2287,
+      "eval_loss": 0.5710490345954895,
+      "eval_rouge1": 52.586,
+      "eval_rouge2": 35.9223,
+      "eval_rougeL": 51.8411,
+      "eval_rougeLsum": 51.8356,
+      "eval_runtime": 711.5517,
+      "eval_samples_per_second": 11.655,
+      "eval_score": 35.7035,
+      "eval_sim_cos": 0.7745,
+      "eval_steps_per_second": 2.915,
+      "step": 13362
+    },
+    {
+      "epoch": 7.0,
+      "eval_bleu 1": 69.9726,
+      "eval_bleu 2": 60.7494,
+      "eval_bleu 3": 50.2446,
+      "eval_bleu 4": 35.578,
+      "eval_loss": 0.5707941055297852,
+      "eval_rouge1": 52.6509,
+      "eval_rouge2": 36.0061,
+      "eval_rougeL": 51.9829,
+      "eval_rougeLsum": 51.9582,
+      "eval_runtime": 703.3177,
+      "eval_samples_per_second": 11.791,
+      "eval_score": 35.3903,
+      "eval_sim_cos": 0.776,
+      "eval_steps_per_second": 2.949,
+      "step": 15589
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 1.666853764406526e-05,
+      "loss": 0.6526,
+      "step": 17815
+    },
+    {
+      "epoch": 8.0,
+      "eval_bleu 1": 70.0548,
+      "eval_bleu 2": 60.8059,
+      "eval_bleu 3": 50.2906,
+      "eval_bleu 4": 35.6541,
+      "eval_loss": 0.5693395137786865,
+      "eval_rouge1": 53.0005,
+      "eval_rouge2": 36.3939,
+      "eval_rougeL": 52.2168,
+      "eval_rougeLsum": 52.2032,
+      "eval_runtime": 709.1405,
+      "eval_samples_per_second": 11.694,
+      "eval_score": 35.9363,
+      "eval_sim_cos": 0.778,
+      "eval_steps_per_second": 2.925,
+      "step": 17816
+    },
+    {
+      "epoch": 9.0,
+      "eval_bleu 1": 69.7601,
+      "eval_bleu 2": 60.4978,
+      "eval_bleu 3": 50.0289,
+      "eval_bleu 4": 35.5284,
+      "eval_loss": 0.5695525407791138,
+      "eval_rouge1": 52.9499,
+      "eval_rouge2": 36.3434,
+      "eval_rougeL": 52.1838,
+      "eval_rougeLsum": 52.1727,
+      "eval_runtime": 713.0996,
+      "eval_samples_per_second": 11.63,
+      "eval_score": 36.1266,
+      "eval_sim_cos": 0.7772,
+      "eval_steps_per_second": 2.908,
+      "step": 20043
+    },
+    {
+      "epoch": 10.0,
+      "eval_bleu 1": 69.3518,
+      "eval_bleu 2": 60.0768,
+      "eval_bleu 3": 49.6026,
+      "eval_bleu 4": 35.2072,
+      "eval_loss": 0.5750804543495178,
+      "eval_rouge1": 52.9485,
+      "eval_rouge2": 36.4398,
+      "eval_rougeL": 52.1386,
+      "eval_rougeLsum": 52.1295,
+      "eval_runtime": 717.0443,
+      "eval_samples_per_second": 11.566,
+      "eval_score": 36.356,
+      "eval_sim_cos": 0.7769,
+      "eval_steps_per_second": 2.892,
+      "step": 22270
+    },
+    {
+      "epoch": 11.0,
+      "eval_bleu 1": 70.0005,
+      "eval_bleu 2": 60.7865,
+      "eval_bleu 3": 50.3355,
+      "eval_bleu 4": 35.8009,
+      "eval_loss": 0.5696647763252258,
+      "eval_rouge1": 53.1415,
+      "eval_rouge2": 36.5933,
+      "eval_rougeL": 52.3479,
+      "eval_rougeLsum": 52.3203,
+      "eval_runtime": 710.6735,
+      "eval_samples_per_second": 11.669,
+      "eval_score": 36.3183,
+      "eval_sim_cos": 0.779,
+      "eval_steps_per_second": 2.918,
+      "step": 24497
+    }
+  ],
+  "max_steps": 26724,
+  "num_train_epochs": 12,
+  "total_flos": 7.298085567419412e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b411852394207194116e23291740be29563587e30acb0e547ee8802e37e96708
+size 3567