commit from elmadany

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "/home/elmadany/T5/OSACT2022/T5_output/new_multinode_Torjoman_Clean_1M_data_with_Sim_MSA_1M_base_5e-5_256_256/checkpoint-74024",
+  "architectures": [
+    "T5ForConditionalGeneration"
+  ],
+  "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": "t5",
+  "num_decoder_layers": 12,
+  "num_heads": 12,
+  "num_layers": 12,
+  "output_past": true,
+  "pad_token_id": 0,
+  "relative_attention_num_buckets": 32,
+  "transformers_version": "4.5.1",
+  "use_cache": true,
+  "vocab_size": 110080
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a1657ba9ecaa5d45c89e09598d122c4a3f49dcc47e8e269bbfd2987645bb235
+size 2262342065

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15aa8bcc2c1513f70c47bd4ef4d7555a28df0a19183c3dfdeec372d8a68bd0dd
+size 1131179919

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c7bbfaf7a9f97ea7016a14b6b828cb40fc7d1c13c3ad605cdfb860fbc490f5bf
+size 623

special_tokens_map.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"]}

spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7ae4407451bf02b459edec774d0539a06615005dd34d5c85c5c06765ff1606
+size 2435308

tokenizer_config.json

@@ -0,0 +1 @@
+{"eos_token": "</s>", "unk_token": "<unk>", "pad_token": "<pad>", "extra_ids": 100, "additional_special_tokens": ["<extra_id_0>", "<extra_id_1>", "<extra_id_2>", "<extra_id_3>", "<extra_id_4>", "<extra_id_5>", "<extra_id_6>", "<extra_id_7>", "<extra_id_8>", "<extra_id_9>", "<extra_id_10>", "<extra_id_11>", "<extra_id_12>", "<extra_id_13>", "<extra_id_14>", "<extra_id_15>", "<extra_id_16>", "<extra_id_17>", "<extra_id_18>", "<extra_id_19>", "<extra_id_20>", "<extra_id_21>", "<extra_id_22>", "<extra_id_23>", "<extra_id_24>", "<extra_id_25>", "<extra_id_26>", "<extra_id_27>", "<extra_id_28>", "<extra_id_29>", "<extra_id_30>", "<extra_id_31>", "<extra_id_32>", "<extra_id_33>", "<extra_id_34>", "<extra_id_35>", "<extra_id_36>", "<extra_id_37>", "<extra_id_38>", "<extra_id_39>", "<extra_id_40>", "<extra_id_41>", "<extra_id_42>", "<extra_id_43>", "<extra_id_44>", "<extra_id_45>", "<extra_id_46>", "<extra_id_47>", "<extra_id_48>", "<extra_id_49>", "<extra_id_50>", "<extra_id_51>", "<extra_id_52>", "<extra_id_53>", "<extra_id_54>", "<extra_id_55>", "<extra_id_56>", "<extra_id_57>", "<extra_id_58>", "<extra_id_59>", "<extra_id_60>", "<extra_id_61>", "<extra_id_62>", "<extra_id_63>", "<extra_id_64>", "<extra_id_65>", "<extra_id_66>", "<extra_id_67>", "<extra_id_68>", "<extra_id_69>", "<extra_id_70>", "<extra_id_71>", "<extra_id_72>", "<extra_id_73>", "<extra_id_74>", "<extra_id_75>", "<extra_id_76>", "<extra_id_77>", "<extra_id_78>", "<extra_id_79>", "<extra_id_80>", "<extra_id_81>", "<extra_id_82>", "<extra_id_83>", "<extra_id_84>", "<extra_id_85>", "<extra_id_86>", "<extra_id_87>", "<extra_id_88>", "<extra_id_89>", "<extra_id_90>", "<extra_id_91>", "<extra_id_92>", "<extra_id_93>", "<extra_id_94>", "<extra_id_95>", "<extra_id_96>", "<extra_id_97>", "<extra_id_98>", "<extra_id_99>"], "special_tokens_map_file": null, "name_or_path": "/home/elmadany/T5/ArT5_models/MSA_1M_base"}

trainer_state.json

@@ -0,0 +1,220 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 22.0,
+  "global_step": 215380,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.9500000000000004e-05,
+      "loss": 5.4101,
+      "step": 3896
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 4.9e-05,
+      "loss": 3.7774,
+      "step": 7792
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.85e-05,
+      "loss": 3.4166,
+      "step": 11688
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 4.8e-05,
+      "loss": 3.2281,
+      "step": 15584
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 4.75e-05,
+      "loss": 3.105,
+      "step": 19480
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4.7e-05,
+      "loss": 3.0041,
+      "step": 23376
+    },
+    {
+      "epoch": 7.0,
+      "learning_rate": 4.6500000000000005e-05,
+      "loss": 2.9418,
+      "step": 27272
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.8758,
+      "step": 31168
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.55e-05,
+      "loss": 2.8427,
+      "step": 35064
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.5e-05,
+      "loss": 2.791,
+      "step": 38960
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 2.7628,
+      "step": 42856
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.7277,
+      "step": 46752
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 4.35e-05,
+      "loss": 2.7199,
+      "step": 50648
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 4.3e-05,
+      "loss": 2.6665,
+      "step": 54544
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 4.25e-05,
+      "loss": 2.6518,
+      "step": 58440
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 4.2e-05,
+      "loss": 2.6451,
+      "step": 62336
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 4.15e-05,
+      "loss": 2.6108,
+      "step": 66232
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 4.1e-05,
+      "loss": 2.5972,
+      "step": 70128
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 4.05e-05,
+      "loss": 2.5859,
+      "step": 74024
+    },
+    {
+      "epoch": 8.0,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 2.9427,
+      "step": 78320
+    },
+    {
+      "epoch": 9.0,
+      "learning_rate": 4.55e-05,
+      "loss": 2.9183,
+      "step": 88110
+    },
+    {
+      "epoch": 10.0,
+      "learning_rate": 4.5e-05,
+      "loss": 2.8809,
+      "step": 97900
+    },
+    {
+      "epoch": 11.0,
+      "learning_rate": 4.4500000000000004e-05,
+      "loss": 2.8521,
+      "step": 107690
+    },
+    {
+      "epoch": 12.0,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 2.8272,
+      "step": 117480
+    },
+    {
+      "epoch": 13.0,
+      "learning_rate": 4.35e-05,
+      "loss": 2.8104,
+      "step": 127270
+    },
+    {
+      "epoch": 14.0,
+      "learning_rate": 4.3e-05,
+      "loss": 2.7856,
+      "step": 137060
+    },
+    {
+      "epoch": 15.0,
+      "learning_rate": 4.25e-05,
+      "loss": 2.7625,
+      "step": 146850
+    },
+    {
+      "epoch": 16.0,
+      "learning_rate": 4.2e-05,
+      "loss": 2.7459,
+      "step": 156640
+    },
+    {
+      "epoch": 17.0,
+      "learning_rate": 4.15e-05,
+      "loss": 2.734,
+      "step": 166430
+    },
+    {
+      "epoch": 18.0,
+      "learning_rate": 4.1e-05,
+      "loss": 2.7209,
+      "step": 176220
+    },
+    {
+      "epoch": 19.0,
+      "learning_rate": 4.05e-05,
+      "loss": 2.7129,
+      "step": 186010
+    },
+    {
+      "epoch": 20.0,
+      "learning_rate": 4e-05,
+      "loss": 2.6932,
+      "step": 195800
+    },
+    {
+      "epoch": 21.0,
+      "learning_rate": 3.9500000000000005e-05,
+      "loss": 2.6885,
+      "step": 205590
+    },
+    {
+      "epoch": 22.0,
+      "learning_rate": 3.9000000000000006e-05,
+      "loss": 2.679,
+      "step": 215380
+    }
+  ],
+  "max_steps": 979000,
+  "num_train_epochs": 100,
+  "total_flos": 5.872346596487864e+23,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5039979155a9e5f4d85b972984098e3104effeaf65483290ef839085078fc422
+size 2607