initial commit

config.json

@@ -0,0 +1,30 @@
+{
+  "_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_max_distance": 128,
+  "relative_attention_num_buckets": 32,
+  "tie_word_embeddings": false,
+  "tokenizer_class": "T5Tokenizer",
+  "torch_dtype": "float32",
+  "transformers_version": "4.18.0",
+  "use_cache": true,
+  "vocab_size": 250112
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9651543d51e42368464ece51ec50a19d2bf1178909d7dea0d534f581e095ed71
+size 4113057

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d76b9863b2f94b85e7faf3d037462f6e6bece818add5d22070046f1b33ac035
+size 2329700301

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:920a4a1dc74cb3d1df30cd5e03fbf55c850d3441f13f14f566d28ace353a765e
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34127c750c790a35ad63eddee43f8ea46129f38c5204c3c05240f1d9ea88a072
+size 623

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, "sp_model_kwargs": {}, "special_tokens_map_file": "/home/patrick/.cache/torch/transformers/685ac0ca8568ec593a48b61b0a3c272beee9bc194a3c7241d15dcadb5f875e53.f76030f3ec1b96a8199b2593390c610e76ca8028ef3d24680000619ffb646276", "tokenizer_file": null, "name_or_path": "google/mt5-base", "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,124 @@
+{
+  "best_metric": 0.3033078610897064,
+  "best_model_checkpoint": "weights/checkpoint-2400",
+  "epoch": 2.05477107402653,
+  "global_step": 2400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0008858447488584475,
+      "loss": 1.0868,
+      "step": 400
+    },
+    {
+      "epoch": 0.34,
+      "eval_loss": 0.3964288830757141,
+      "eval_rouge1": 0.1061059158446104,
+      "eval_rouge2": 0.03465244917613476,
+      "eval_rougeL": 0.10627894663827464,
+      "eval_rougeLsum": 0.10587803730968609,
+      "eval_runtime": 213.0846,
+      "eval_samples_per_second": 11.667,
+      "eval_steps_per_second": 1.46,
+      "step": 400
+    },
+    {
+      "epoch": 0.68,
+      "learning_rate": 0.000771689497716895,
+      "loss": 0.4378,
+      "step": 800
+    },
+    {
+      "epoch": 0.68,
+      "eval_loss": 0.3599437475204468,
+      "eval_rouge1": 0.10699235686427112,
+      "eval_rouge2": 0.034402581194616595,
+      "eval_rougeL": 0.10726814102163426,
+      "eval_rougeLsum": 0.10683004020509843,
+      "eval_runtime": 209.0997,
+      "eval_samples_per_second": 11.889,
+      "eval_steps_per_second": 1.487,
+      "step": 800
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 0.0006575342465753425,
+      "loss": 0.3695,
+      "step": 1200
+    },
+    {
+      "epoch": 1.03,
+      "eval_loss": 0.3147580027580261,
+      "eval_rouge1": 0.10717208698017014,
+      "eval_rouge2": 0.03477288244690299,
+      "eval_rougeL": 0.10748345500504963,
+      "eval_rougeLsum": 0.10712451901224819,
+      "eval_runtime": 208.2509,
+      "eval_samples_per_second": 11.938,
+      "eval_steps_per_second": 1.493,
+      "step": 1200
+    },
+    {
+      "epoch": 1.37,
+      "learning_rate": 0.00054337899543379,
+      "loss": 0.2645,
+      "step": 1600
+    },
+    {
+      "epoch": 1.37,
+      "eval_loss": 0.31476476788520813,
+      "eval_rouge1": 0.10597239490642546,
+      "eval_rouge2": 0.033266358974880464,
+      "eval_rougeL": 0.10614402559092825,
+      "eval_rougeLsum": 0.10592368490095762,
+      "eval_runtime": 208.6832,
+      "eval_samples_per_second": 11.913,
+      "eval_steps_per_second": 1.49,
+      "step": 1600
+    },
+    {
+      "epoch": 1.71,
+      "learning_rate": 0.00042922374429223744,
+      "loss": 0.2503,
+      "step": 2000
+    },
+    {
+      "epoch": 1.71,
+      "eval_loss": 0.3020365834236145,
+      "eval_rouge1": 0.10566329888936485,
+      "eval_rouge2": 0.03209767038592902,
+      "eval_rougeL": 0.10595888780924984,
+      "eval_rougeLsum": 0.10570986122575018,
+      "eval_runtime": 207.8626,
+      "eval_samples_per_second": 11.96,
+      "eval_steps_per_second": 1.496,
+      "step": 2000
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 0.00031506849315068495,
+      "loss": 0.2264,
+      "step": 2400
+    },
+    {
+      "epoch": 2.05,
+      "eval_loss": 0.3033078610897064,
+      "eval_rouge1": 0.10519725760071695,
+      "eval_rouge2": 0.03199324082356017,
+      "eval_rougeL": 0.10550921669284499,
+      "eval_rougeLsum": 0.10514026310687613,
+      "eval_runtime": 207.427,
+      "eval_samples_per_second": 11.985,
+      "eval_steps_per_second": 1.499,
+      "step": 2400
+    }
+  ],
+  "max_steps": 3504,
+  "num_train_epochs": 3,
+  "total_flos": 5666207247866880.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2ab4a3ebfacb59e68841e111fdfd09990dfccca7f98f8275e4de3cf1d660254
+size 3119