update checkpoint 4000

added_tokens.json

@@ -0,0 +1 @@
+{"<sep>": 250100, "<hl>": 250101}

config.json

@@ -0,0 +1,57 @@
+{
+  "_name_or_path": "t5-base",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "d_ff": 3072,
+  "d_kv": 64,
+  "d_model": 768,
+  "decoder_start_token_id": 0,
+  "dropout_rate": 0.1,
+  "eos_token_id": 1,
+  "feed_forward_proj": "relu",
+  "gradient_checkpointing": false,
+  "initializer_factor": 1.0,
+  "is_encoder_decoder": true,
+  "layer_norm_epsilon": 1e-06,
+  "model_type": "t5",
+  "n_positions": 512,
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "task_specific_params": {
+    "summarization": {
+      "early_stopping": true,
+      "length_penalty": 2.0,
+      "max_length": 200,
+      "min_length": 30,
+      "no_repeat_ngram_size": 3,
+      "num_beams": 4,
+      "prefix": "summarize: "
+    },
+    "translation_en_to_de": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to German: "
+    },
+    "translation_en_to_fr": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to French: "
+    },
+    "translation_en_to_ro": {
+      "early_stopping": true,
+      "max_length": 300,
+      "num_beams": 4,
+      "prefix": "translate English to Romanian: "
+    }
+  },
+  "transformers_version": "4.8.2",
+  "use_cache": true,
+  "vocab_size": 250102
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f86fdf6f2253315630f08854dd6cf55a490a3d9707b5e9f87273b0c00f8b94f8
+size 1585984129

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33e786d0f4b05d15018a8124da472387dc1f4cfe40dd499ad939a0c5c03e6943
+size 1561347007

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1179438fe2fd7c8e46d03dca2b32abee5cd05cbd7593dfebe45c4650d68e0bce
+size 14503

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c799899660aa23d06af8419f69224fc27e6421474aa8782155699f25d463c78f
+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": "C:\\Users\\hydra/.cache\\huggingface\\transformers\\bde22e2f08347211bf47b72fb4730b4b9a2e3323a6a1254932cf0fb969eb18cd.b02fba13e4584f40329b20be0bad88c2ef97b5fda7d9f4f69b1cb3a620568a86", "tokenizer_file": null, "name_or_path": "longcld/t5_small_qg_ae_hl", "tokenizer_class": "T5Tokenizer"}

trainer_state.json

@@ -0,0 +1,256 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7085602940525221,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "learning_rate": 9.982285208148806e-06,
+      "loss": 13.4699,
+      "step": 100
+    },
+    {
+      "epoch": 0.04,
+      "learning_rate": 9.964570416297609e-06,
+      "loss": 7.2852,
+      "step": 200
+    },
+    {
+      "epoch": 0.05,
+      "learning_rate": 9.946855624446414e-06,
+      "loss": 6.4586,
+      "step": 300
+    },
+    {
+      "epoch": 0.07,
+      "learning_rate": 9.929140832595217e-06,
+      "loss": 6.016,
+      "step": 400
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 9.911426040744022e-06,
+      "loss": 5.7345,
+      "step": 500
+    },
+    {
+      "epoch": 0.11,
+      "learning_rate": 9.893711248892827e-06,
+      "loss": 5.5798,
+      "step": 600
+    },
+    {
+      "epoch": 0.12,
+      "learning_rate": 9.87599645704163e-06,
+      "loss": 5.4188,
+      "step": 700
+    },
+    {
+      "epoch": 0.14,
+      "learning_rate": 9.858281665190435e-06,
+      "loss": 5.2602,
+      "step": 800
+    },
+    {
+      "epoch": 0.16,
+      "learning_rate": 9.840566873339238e-06,
+      "loss": 5.1859,
+      "step": 900
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 9.822852081488043e-06,
+      "loss": 5.042,
+      "step": 1000
+    },
+    {
+      "epoch": 0.19,
+      "learning_rate": 9.805137289636848e-06,
+      "loss": 4.906,
+      "step": 1100
+    },
+    {
+      "epoch": 0.21,
+      "learning_rate": 9.787422497785651e-06,
+      "loss": 4.9085,
+      "step": 1200
+    },
+    {
+      "epoch": 0.23,
+      "learning_rate": 9.769707705934456e-06,
+      "loss": 4.8621,
+      "step": 1300
+    },
+    {
+      "epoch": 0.25,
+      "learning_rate": 9.751992914083261e-06,
+      "loss": 4.816,
+      "step": 1400
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 9.734278122232064e-06,
+      "loss": 4.7002,
+      "step": 1500
+    },
+    {
+      "epoch": 0.28,
+      "learning_rate": 9.71656333038087e-06,
+      "loss": 4.7099,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3,
+      "learning_rate": 9.698848538529672e-06,
+      "loss": 4.6732,
+      "step": 1700
+    },
+    {
+      "epoch": 0.32,
+      "learning_rate": 9.681133746678477e-06,
+      "loss": 4.5622,
+      "step": 1800
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 9.663418954827282e-06,
+      "loss": 4.6137,
+      "step": 1900
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 9.645704162976086e-06,
+      "loss": 4.5555,
+      "step": 2000
+    },
+    {
+      "epoch": 0.37,
+      "learning_rate": 9.627989371124889e-06,
+      "loss": 4.5398,
+      "step": 2100
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 9.610274579273694e-06,
+      "loss": 4.4768,
+      "step": 2200
+    },
+    {
+      "epoch": 0.41,
+      "learning_rate": 9.592559787422499e-06,
+      "loss": 4.4343,
+      "step": 2300
+    },
+    {
+      "epoch": 0.43,
+      "learning_rate": 9.574844995571303e-06,
+      "loss": 4.4214,
+      "step": 2400
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 9.557130203720107e-06,
+      "loss": 4.378,
+      "step": 2500
+    },
+    {
+      "epoch": 0.46,
+      "learning_rate": 9.539415411868912e-06,
+      "loss": 4.3645,
+      "step": 2600
+    },
+    {
+      "epoch": 0.48,
+      "learning_rate": 9.521700620017715e-06,
+      "loss": 4.3078,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5,
+      "learning_rate": 9.50398582816652e-06,
+      "loss": 4.2574,
+      "step": 2800
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 9.486271036315325e-06,
+      "loss": 4.3055,
+      "step": 2900
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 9.46855624446413e-06,
+      "loss": 4.202,
+      "step": 3000
+    },
+    {
+      "epoch": 0.55,
+      "learning_rate": 9.450841452612933e-06,
+      "loss": 4.1899,
+      "step": 3100
+    },
+    {
+      "epoch": 0.57,
+      "learning_rate": 9.433126660761736e-06,
+      "loss": 4.248,
+      "step": 3200
+    },
+    {
+      "epoch": 0.58,
+      "learning_rate": 9.415411868910541e-06,
+      "loss": 4.2209,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6,
+      "learning_rate": 9.397697077059346e-06,
+      "loss": 4.1421,
+      "step": 3400
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 9.379982285208149e-06,
+      "loss": 4.233,
+      "step": 3500
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 9.362267493356954e-06,
+      "loss": 4.1725,
+      "step": 3600
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 9.344552701505759e-06,
+      "loss": 4.1743,
+      "step": 3700
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 9.326837909654562e-06,
+      "loss": 4.1354,
+      "step": 3800
+    },
+    {
+      "epoch": 0.69,
+      "learning_rate": 9.309123117803367e-06,
+      "loss": 4.0521,
+      "step": 3900
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 9.29140832595217e-06,
+      "loss": 4.0616,
+      "step": 4000
+    }
+  ],
+  "max_steps": 56450,
+  "num_train_epochs": 10,
+  "total_flos": 1.486489899595346e+17,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:578290b264a079e8153032761761d2830185b56fabac1d1b876a297df6e85202
+size 2607