End of training

last-checkpoint/config.json

@@ -1,29 +0,0 @@
-{
-  "_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": "4.13.0.dev0",
-  "use_cache": true,
-  "vocab_size": 250112
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:ae5259d25e6f99bf596a6ec0fa9c7dd5dfaf2d79c46a5dec8c1ecc0836bbbf10
-size 4659376733

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:c31c4891c84594d92a7fc2c0c8d65bc297a38d3b98a472a3a84bd3fa1bb8b5df
-size 2329732045

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5356547849e2b94f1f0d272f5260ab3742fc5e28f3e41bae5cfcdd497345006e
-size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:5ea4719bf4579360c2d2e9bd88999d25d3a9ef68a96f71f474e58bf3471a5127
-size 623

last-checkpoint/special_tokens_map.json

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

last-checkpoint/spiece.model

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

last-checkpoint/tokenizer_config.json

@@ -1 +0,0 @@
-{"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"}

last-checkpoint/trainer_state.json

@@ -1,146 +0,0 @@
-{
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.35454706612302783,
-  "global_step": 10000,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.02,
-      "learning_rate": 9.940908822312829e-05,
-      "loss": 3.0242,
-      "step": 500
-    },
-    {
-      "epoch": 0.04,
-      "learning_rate": 9.881817644625659e-05,
-      "loss": 1.0439,
-      "step": 1000
-    },
-    {
-      "epoch": 0.05,
-      "learning_rate": 9.822726466938487e-05,
-      "loss": 0.8026,
-      "step": 1500
-    },
-    {
-      "epoch": 0.07,
-      "learning_rate": 9.763635289251316e-05,
-      "loss": 0.695,
-      "step": 2000
-    },
-    {
-      "epoch": 0.09,
-      "learning_rate": 9.704544111564144e-05,
-      "loss": 0.6169,
-      "step": 2500
-    },
-    {
-      "epoch": 0.11,
-      "learning_rate": 9.645452933876972e-05,
-      "loss": 0.5837,
-      "step": 3000
-    },
-    {
-      "epoch": 0.12,
-      "learning_rate": 9.586361756189801e-05,
-      "loss": 0.5781,
-      "step": 3500
-    },
-    {
-      "epoch": 0.14,
-      "learning_rate": 9.52727057850263e-05,
-      "loss": 0.5525,
-      "step": 4000
-    },
-    {
-      "epoch": 0.16,
-      "learning_rate": 9.468179400815459e-05,
-      "loss": 0.5367,
-      "step": 4500
-    },
-    {
-      "epoch": 0.18,
-      "learning_rate": 9.409088223128288e-05,
-      "loss": 0.5494,
-      "step": 5000
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 9.349997045441116e-05,
-      "loss": 0.5067,
-      "step": 5500
-    },
-    {
-      "epoch": 0.21,
-      "learning_rate": 9.290905867753945e-05,
-      "loss": 0.4961,
-      "step": 6000
-    },
-    {
-      "epoch": 0.23,
-      "learning_rate": 9.231814690066773e-05,
-      "loss": 0.5102,
-      "step": 6500
-    },
-    {
-      "epoch": 0.25,
-      "learning_rate": 9.172723512379601e-05,
-      "loss": 0.4824,
-      "step": 7000
-    },
-    {
-      "epoch": 0.27,
-      "learning_rate": 9.113632334692431e-05,
-      "loss": 0.4854,
-      "step": 7500
-    },
-    {
-      "epoch": 0.28,
-      "learning_rate": 9.05454115700526e-05,
-      "loss": 0.5103,
-      "step": 8000
-    },
-    {
-      "epoch": 0.3,
-      "learning_rate": 8.995449979318088e-05,
-      "loss": 0.4474,
-      "step": 8500
-    },
-    {
-      "epoch": 0.32,
-      "learning_rate": 8.936358801630918e-05,
-      "loss": 0.477,
-      "step": 9000
-    },
-    {
-      "epoch": 0.34,
-      "learning_rate": 8.877267623943746e-05,
-      "loss": 0.4577,
-      "step": 9500
-    },
-    {
-      "epoch": 0.35,
-      "learning_rate": 8.818176446256575e-05,
-      "loss": 0.4588,
-      "step": 10000
-    },
-    {
-      "epoch": 0.35,
-      "eval_bleu": 78.1616,
-      "eval_gen_len": 11.1577,
-      "eval_loss": 0.40234658122062683,
-      "eval_runtime": 1250.9737,
-      "eval_samples_per_second": 11.273,
-      "eval_steps_per_second": 2.819,
-      "step": 10000
-    }
-  ],
-  "max_steps": 84615,
-  "num_train_epochs": 3,
-  "total_flos": 2394907297136640.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cca666819c790c1e9fb11e31f6ec8ca8b95c55e19c9c5036d9590ff65c2b3954
-size 2991

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c31c4891c84594d92a7fc2c0c8d65bc297a38d3b98a472a3a84bd3fa1bb8b5df
+oid sha256:01b9936fbff7c72becd6769bb24cd0b3febade90a074d5abac5ec585e4e8c85a
 size 2329732045

runs/Nov12_15-49-11_17f1a7550854/events.out.tfevents.1636732174.17f1a7550854.84.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29c9f1300f3eeb69fa99de574bdc2d2863987f87510438de18efc7277372311f
-size 6878
+oid sha256:d69cac59fa2ecb7e4605751993b1ae0ff0a08a7ce92baac6efba97d09b8cdb2a
+size 33681