Training in progress, step 3500

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45521578b7dfd22b83bc3774bd3a4a9782e49afae68e048248cb79f4c8d54b0a
+oid sha256:6bff51f7d0eb96ded80a56ef773ea27115444dfd6003746e0b6e25f1f779a29c
 size 437955572

run-1/checkpoint-3500/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "bert-base-uncased",
+  "architectures": [
+    "BertForMultipleChoice"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-3500/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bff51f7d0eb96ded80a56ef773ea27115444dfd6003746e0b6e25f1f779a29c
+size 437955572

run-1/checkpoint-3500/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7df5dff2431a11b7e5525e0976789e1be62951718ca4e672ec9ae6e01c13c6e5
+size 876026618

run-1/checkpoint-3500/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12f8be310ca0047cbeab599e9841eb4b751bfaa7694ee9e201d0cf8a196826bb
+size 13990

run-1/checkpoint-3500/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e391857a4929ee63ef5dd0cc31de6d0b9dcf0cbde7aedc28b1ca05d3f7569edf
+size 1064

run-1/checkpoint-3500/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-3500/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-3500/trainer_state.json

@@ -0,0 +1,154 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 9.383378016085791,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7257794141769409,
+      "eval_loss": 0.5139069557189941,
+      "eval_runtime": 10.4839,
+      "eval_samples_per_second": 284.531,
+      "eval_steps_per_second": 17.837,
+      "step": 373
+    },
+    {
+      "epoch": 1.3404825737265416,
+      "grad_norm": 6.2857279777526855,
+      "learning_rate": 6.246784712358295e-06,
+      "loss": 0.5462,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.7351659536361694,
+      "eval_loss": 0.5105723738670349,
+      "eval_runtime": 10.1317,
+      "eval_samples_per_second": 294.421,
+      "eval_steps_per_second": 18.457,
+      "step": 746
+    },
+    {
+      "epoch": 2.680965147453083,
+      "grad_norm": 7.455731391906738,
+      "learning_rate": 5.2797901748415314e-06,
+      "loss": 0.4163,
+      "step": 1000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.7405296564102173,
+      "eval_loss": 0.5301964282989502,
+      "eval_runtime": 10.8919,
+      "eval_samples_per_second": 273.872,
+      "eval_steps_per_second": 17.169,
+      "step": 1119
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7422058582305908,
+      "eval_loss": 0.5949265956878662,
+      "eval_runtime": 10.0434,
+      "eval_samples_per_second": 297.011,
+      "eval_steps_per_second": 18.619,
+      "step": 1492
+    },
+    {
+      "epoch": 4.021447721179625,
+      "grad_norm": 7.849554061889648,
+      "learning_rate": 4.312795637324767e-06,
+      "loss": 0.3214,
+      "step": 1500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7428762912750244,
+      "eval_loss": 0.6298013925552368,
+      "eval_runtime": 10.2357,
+      "eval_samples_per_second": 291.431,
+      "eval_steps_per_second": 18.269,
+      "step": 1865
+    },
+    {
+      "epoch": 5.361930294906166,
+      "grad_norm": 5.515786170959473,
+      "learning_rate": 3.345801099808003e-06,
+      "loss": 0.2384,
+      "step": 2000
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7422058582305908,
+      "eval_loss": 0.6809112429618835,
+      "eval_runtime": 11.7599,
+      "eval_samples_per_second": 253.659,
+      "eval_steps_per_second": 15.902,
+      "step": 2238
+    },
+    {
+      "epoch": 6.702412868632708,
+      "grad_norm": 14.996353149414062,
+      "learning_rate": 2.378806562291239e-06,
+      "loss": 0.1938,
+      "step": 2500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7395239472389221,
+      "eval_loss": 0.7227303981781006,
+      "eval_runtime": 10.7507,
+      "eval_samples_per_second": 277.471,
+      "eval_steps_per_second": 17.394,
+      "step": 2611
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.7435467839241028,
+      "eval_loss": 0.7428784370422363,
+      "eval_runtime": 9.899,
+      "eval_samples_per_second": 301.343,
+      "eval_steps_per_second": 18.891,
+      "step": 2984
+    },
+    {
+      "epoch": 8.04289544235925,
+      "grad_norm": 3.993084192276001,
+      "learning_rate": 1.4118120247744752e-06,
+      "loss": 0.1663,
+      "step": 3000
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.7425410747528076,
+      "eval_loss": 0.76423579454422,
+      "eval_runtime": 11.6109,
+      "eval_samples_per_second": 256.914,
+      "eval_steps_per_second": 16.106,
+      "step": 3357
+    },
+    {
+      "epoch": 9.383378016085791,
+      "grad_norm": 10.944915771484375,
+      "learning_rate": 4.448174872577114e-07,
+      "loss": 0.1435,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3730,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 10,
+  "save_steps": 500,
+  "total_flos": 5028503535181476.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.213779249875059e-06,
+    "per_device_train_batch_size": 32
+  }
+}

run-1/checkpoint-3500/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:84246c1e31127ea344f38b719c9a61afa272deb655a2b41af483b2bc24f67507
+size 5048

runs/Jun05_13-34-22_KH7FLFHVQY-MCLABS/events.out.tfevents.1717568335.KH7FLFHVQY-MCLABS.23663.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fad4df38f21aff3370a87dc78bc5cbbba75492f09646d63488670dfe0f2455f4
-size 8586
+oid sha256:baebce8b6a942d4fa5148265fb8812d160477c8048fd3fcc09bb9673e5b62eb8
+size 9120