Upload folder using huggingface_hub

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "</s>": 1,
+  "<pad>": 0,
+  "<unk>": 2
+}

config.json

@@ -0,0 +1,32 @@
+{
+  "_name_or_path": "google/mt5-small",
+  "architectures": [
+    "MT5ForConditionalGeneration"
+  ],
+  "classifier_dropout": 0.0,
+  "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": "mt5",
+  "num_decoder_layers": 8,
+  "num_heads": 6,
+  "num_layers": 8,
+  "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": "4.35.0.dev0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

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": "4.35.0.dev0"
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c938090590ce068f63db5f98e33f264d57a215e992df26edd0bf8dfce21887
+size 2401573893

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:326d329916d4fa66d6adbc65b2003c23dd643e992f792ac0ff963f0dfffd20ad
+size 1200772613

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8688b0452f6f576e8f85cd53360bf13287f6a99c7d440bce793a3143246e93e2
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afe62accefbab6d7b804f10710b1540ca244cdead67688d29e29074ef0baef18
+size 627

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_config.json

@@ -0,0 +1,39 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "</s>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<unk>",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": true,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "tokenizer_file": null,
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 10378,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05,
+      "learning_rate": 4.759105800732319e-05,
+      "loss": 19.9182,
+      "step": 500
+    },
+    {
+      "epoch": 0.1,
+      "learning_rate": 4.518211601464637e-05,
+      "loss": 2.8554,
+      "step": 1000
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 4.2773174021969556e-05,
+      "loss": 1.1633,
+      "step": 1500
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 4.0364232029292733e-05,
+      "loss": 0.7392,
+      "step": 2000
+    },
+    {
+      "epoch": 0.24,
+      "learning_rate": 3.795529003661592e-05,
+      "loss": 0.5942,
+      "step": 2500
+    },
+    {
+      "epoch": 0.29,
+      "learning_rate": 3.55463480439391e-05,
+      "loss": 0.5252,
+      "step": 3000
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 3.313740605126229e-05,
+      "loss": 0.5016,
+      "step": 3500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 3.072846405858547e-05,
+      "loss": 0.4575,
+      "step": 4000
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 2.8319522065908656e-05,
+      "loss": 0.4414,
+      "step": 4500
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 2.5910580073231837e-05,
+      "loss": 0.4227,
+      "step": 5000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 2.350163808055502e-05,
+      "loss": 0.4023,
+      "step": 5500
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 2.1092696087878206e-05,
+      "loss": 0.3792,
+      "step": 6000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 1.868375409520139e-05,
+      "loss": 0.3566,
+      "step": 6500
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 1.627481210252457e-05,
+      "loss": 0.3496,
+      "step": 7000
+    },
+    {
+      "epoch": 0.72,
+      "learning_rate": 1.3865870109847756e-05,
+      "loss": 0.3438,
+      "step": 7500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 1.145692811717094e-05,
+      "loss": 0.3427,
+      "step": 8000
+    },
+    {
+      "epoch": 0.82,
+      "learning_rate": 9.047986124494123e-06,
+      "loss": 0.3259,
+      "step": 8500
+    },
+    {
+      "epoch": 0.87,
+      "learning_rate": 6.639044131817306e-06,
+      "loss": 0.328,
+      "step": 9000
+    },
+    {
+      "epoch": 0.92,
+      "learning_rate": 4.2301021391404895e-06,
+      "loss": 0.318,
+      "step": 9500
+    },
+    {
+      "epoch": 0.96,
+      "learning_rate": 1.8211601464636733e-06,
+      "loss": 0.325,
+      "step": 10000
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.235988587141037,
+      "eval_runtime": 169.8494,
+      "eval_samples_per_second": 65.758,
+      "eval_steps_per_second": 8.225,
+      "step": 10378
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 10378,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "total_flos": 4.389574183747584e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f1e78a9328aa5ddec1e75c98a366a5e549e62dbf7886e3fb3b6a4cfec066879
+size 4155