Training in progress, epoch 5

checkpoint-675/added_tokens.json

@@ -0,0 +1 @@
+{"<CSD>": 32100}

checkpoint-675/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/t5-v1_1-base",
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_cache": false,
+  "vocab_size": 32101
+}

checkpoint-675/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21445daf71ef054053b1897327295a1112e660330cb8c4fdd5189f8dbeb9419c
+size 1980455257

checkpoint-675/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea6614a542ae05f5a835e9f37cd8d172e7c48c14be5e7e2575b0b4620bf445a
+size 990272461

checkpoint-675/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acdd0188f3e5ca585ebd57de6fbf3ccc8a60a99fdfdef145f692621a58e33a29
+size 14503

checkpoint-675/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d32e75433385e2e326f07b54cdbe1de68a953598fb525f8fc80cbcb0c304157e
+size 559

checkpoint-675/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04e9983afbab69b9507144eb907b7e9dfda252407067d2de1aca1d814dc47366
+size 623

checkpoint-675/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>"]}

checkpoint-675/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

checkpoint-675/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>"], "model_max_length": 512, "name_or_path": "google/t5-v1_1-base", "special_tokens_map_file": "/home/chris-zeng/.cache/huggingface/transformers/76bf19bfedb85afbe644966ca9ab7b0404d753a41bf601115bced39f825ffa9c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

checkpoint-675/trainer_state.json

@@ -0,0 +1,86 @@
+{
+  "best_metric": 0.2819174826145172,
+  "best_model_checkpoint": "outputs/t5-v1_1-base-detox/checkpoint-675",
+  "epoch": 4.9953917050691246,
+  "global_step": 675,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-05,
+      "loss": 8.9719,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.031940221786499,
+      "eval_runtime": 22.7196,
+      "eval_samples_per_second": 136.446,
+      "eval_steps_per_second": 17.078,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8e-05,
+      "loss": 1.9438,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6424035429954529,
+      "eval_runtime": 22.8507,
+      "eval_samples_per_second": 135.663,
+      "eval_steps_per_second": 16.98,
+      "step": 270
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7e-05,
+      "loss": 0.8941,
+      "step": 405
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.43842175602912903,
+      "eval_runtime": 22.8845,
+      "eval_samples_per_second": 135.463,
+      "eval_steps_per_second": 16.955,
+      "step": 405
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6e-05,
+      "loss": 0.6694,
+      "step": 540
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.3455743193626404,
+      "eval_runtime": 22.9242,
+      "eval_samples_per_second": 135.228,
+      "eval_steps_per_second": 16.925,
+      "step": 540
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5e-05,
+      "loss": 0.5336,
+      "step": 675
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.2819174826145172,
+      "eval_runtime": 23.1392,
+      "eval_samples_per_second": 133.972,
+      "eval_steps_per_second": 16.768,
+      "step": 675
+    }
+  ],
+  "max_steps": 1350,
+  "num_train_epochs": 10,
+  "total_flos": 6577113724194816.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-675/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839084c79c487b59c2c5870b0257ed8fb82211fae1f0295222d556827c5f599c
+size 3247

checkpoint-810/added_tokens.json

@@ -0,0 +1 @@
+{"<CSD>": 32100}

checkpoint-810/config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "google/t5-v1_1-base",
+  "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,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.16.2",
+  "use_cache": false,
+  "vocab_size": 32101
+}

checkpoint-810/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:362ac5a70fc306a7da074167625f3f29cb63e8f5e66b02baa23a5a76fafaf30f
+size 1980455257

checkpoint-810/pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46c2803025b2848ad7e50024b3fa3e326ac3a9c57fb968fe8853ffd6d382ae47
+size 990272461

checkpoint-810/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2e56df18b200b032cf4680a3ebee2e046597334e1d9ddf41dbb1804b5f6452
+size 14503

checkpoint-810/scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d9a3a2afd74254bd8754a814e3ae3960b01c9386cad98a313ce986dd9c592a1
+size 559

checkpoint-810/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02a193f86a70dd6e41d4704f196fab6aa7b25db1c4b75aff259d2831c3929dde
+size 623

checkpoint-810/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>"]}

checkpoint-810/spiece.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d60acb128cf7b7f2536e8f38a5b18a05535c9e14c7a355904270e15b0945ea86
+size 791656

checkpoint-810/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>"], "model_max_length": 512, "name_or_path": "google/t5-v1_1-base", "special_tokens_map_file": "/home/chris-zeng/.cache/huggingface/transformers/76bf19bfedb85afbe644966ca9ab7b0404d753a41bf601115bced39f825ffa9c.c94798918c92ded6aeef2d2f0e666d2cc4145eca1aa6e1336fde07f2e13e2f46", "sp_model_kwargs": {}, "tokenizer_class": "T5Tokenizer"}

checkpoint-810/trainer_state.json

@@ -0,0 +1,100 @@
+{
+  "best_metric": 0.24306097626686096,
+  "best_model_checkpoint": "outputs/t5-v1_1-base-detox/checkpoint-810",
+  "epoch": 5.9953917050691246,
+  "global_step": 810,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 9e-05,
+      "loss": 8.9719,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 2.031940221786499,
+      "eval_runtime": 22.7196,
+      "eval_samples_per_second": 136.446,
+      "eval_steps_per_second": 17.078,
+      "step": 135
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 8e-05,
+      "loss": 1.9438,
+      "step": 270
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.6424035429954529,
+      "eval_runtime": 22.8507,
+      "eval_samples_per_second": 135.663,
+      "eval_steps_per_second": 16.98,
+      "step": 270
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 7e-05,
+      "loss": 0.8941,
+      "step": 405
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.43842175602912903,
+      "eval_runtime": 22.8845,
+      "eval_samples_per_second": 135.463,
+      "eval_steps_per_second": 16.955,
+      "step": 405
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 6e-05,
+      "loss": 0.6694,
+      "step": 540
+    },
+    {
+      "epoch": 4.0,
+      "eval_loss": 0.3455743193626404,
+      "eval_runtime": 22.9242,
+      "eval_samples_per_second": 135.228,
+      "eval_steps_per_second": 16.925,
+      "step": 540
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 5e-05,
+      "loss": 0.5336,
+      "step": 675
+    },
+    {
+      "epoch": 5.0,
+      "eval_loss": 0.2819174826145172,
+      "eval_runtime": 23.1392,
+      "eval_samples_per_second": 133.972,
+      "eval_steps_per_second": 16.768,
+      "step": 675
+    },
+    {
+      "epoch": 6.0,
+      "learning_rate": 4e-05,
+      "loss": 0.4519,
+      "step": 810
+    },
+    {
+      "epoch": 6.0,
+      "eval_loss": 0.24306097626686096,
+      "eval_runtime": 22.7762,
+      "eval_samples_per_second": 136.107,
+      "eval_steps_per_second": 17.035,
+      "step": 810
+    }
+  ],
+  "max_steps": 1350,
+  "num_train_epochs": 10,
+  "total_flos": 7881198370099200.0,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-810/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:839084c79c487b59c2c5870b0257ed8fb82211fae1f0295222d556827c5f599c
+size 3247

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:857ad1acf2d35e8b25d9eaddb9ee58a1d5cbdf32a8acf70521888ff485f5260e
+oid sha256:46c2803025b2848ad7e50024b3fa3e326ac3a9c57fb968fe8853ffd6d382ae47
 size 990272461