Initial Commit

.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 +1,39 @@
+{
+  "_name_or_path": "configs/sled_mt5_config.json",
+  "architectures": [
+    "SledForConditionalGeneration"
+  ],
+  "context_size": 256,
+  "d_ff": 2048,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dense_act_fn": "gelu_new",
+  "dropout_rate": 0.1,
+  "encode_prefix": true,
+  "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,
+  "max_target_length": 2048,
+  "model_type": "tau/sled",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "prepend_prefix": true,
+  "relative_attention_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "sliding_method": "dynamic",
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "underlying_config": "google/mt5-base",
+  "use_cache": false,
+  "vocab_size": 250100,
+  "window_fraction": 0.5
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "decoder_start_token_id": 0,
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.28.1",
+  "use_cache": false
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbe76e9511b2cb41ba8e536699ff9fa250d4362abc3014900366a25bb493acd0
+size 4659230729

pytorch_model-00001-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fbfb6fd4002dc8ce3f2290d34c248f6526dd018048b7b790146b48931583346
+size 2329719897

pytorch_model-00002-of-00002.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e27e0cfaef18cd1501c0ba1d057c3ae19af3842b9a27cd45f1cce4d19e0359
+size 2329636441

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:510693a49229ca40bd940d3f84fa8c089339f9d7ae109aeca2a4b32cf7df2885
+size 14575

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c005afc655ce7691df546cf22ee6ed1ec1eb107a0fde4825e9140cfe2c083b
+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.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:93c3578052e1605d8332eb961bc08d72e246071974e4cc54aa6991826b802aa5
+size 16330369

tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "additional_special_tokens": null,
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "T5Tokenizer",
+  "unk_token": "<unk>"
+}

trainer_state.json

@@ -0,0 +1,55 @@
+{
+  "best_metric": 14.0723,
+  "best_model_checkpoint": "models/sled/output_sled_mt5_base2/checkpoint-2397",
+  "epoch": 1.0,
+  "global_step": 2397,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.21,
+      "learning_rate": 1.3904338153503894e-05,
+      "loss": 18.6448,
+      "step": 500
+    },
+    {
+      "epoch": 0.42,
+      "learning_rate": 2.7808676307007788e-05,
+      "loss": 3.8147,
+      "step": 1000
+    },
+    {
+      "epoch": 0.63,
+      "learning_rate": 4.171301446051168e-05,
+      "loss": 2.6096,
+      "step": 1500
+    },
+    {
+      "epoch": 0.83,
+      "learning_rate": 5.5617352614015575e-05,
+      "loss": 2.3758,
+      "step": 2000
+    },
+    {
+      "epoch": 1.0,
+      "eval_mean_prediction_length_characters": 7800.0,
+      "eval_mean_prediction_length_tokens": 2047.0,
+      "eval_num_predicted": 1,
+      "eval_rouge/geometric_mean": 14.0723,
+      "eval_rouge/rouge1": 24.3546,
+      "eval_rouge/rouge2": 7.1185,
+      "eval_rouge/rougeL": 16.074,
+      "eval_rouge/rougeLsum": 21.4321,
+      "eval_runtime": 358.1416,
+      "eval_samples_per_second": 0.003,
+      "eval_steps_per_second": 0.003,
+      "step": 2397
+    }
+  ],
+  "max_steps": 35955,
+  "num_train_epochs": 15,
+  "total_flos": 8.078322612436992e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d833e225c6c771d368bc0449bf4aea5850f23cb875e9c6eab4cdd87a206e3f4
+size 3899