Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e069d094ca8a574d13321febd2ccfb587e994a68106882f97744acb3998cc3ac
+oid sha256:cf18a7465401fcc61cb71532b6caa2080bc8041bf5a7ab3bfff157decd0062ec
 size 267832560

run-2/checkpoint-8419/config.json

@@ -0,0 +1,25 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "initializer_range": 0.02,
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.2",
+  "vocab_size": 30522
+}

run-2/checkpoint-8419/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cf18a7465401fcc61cb71532b6caa2080bc8041bf5a7ab3bfff157decd0062ec
+size 267832560

run-2/checkpoint-8419/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8951761772483cb1795f2c52dfd044499145a406e5d450adcc0089d3ed031041
+size 535727290

run-2/checkpoint-8419/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:807b380840933ef50ee402581d24c86e698aaff9c3d4ad8fa8ae434ea153ff1a
+size 14244

run-2/checkpoint-8419/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6d515b6233ed373310234fd585ffcefcfe34d802cc02c573ba24598f6de520
+size 1064

run-2/checkpoint-8419/special_tokens_map.json

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

run-2/checkpoint-8419/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": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-2/checkpoint-8419/trainer_state.json

@@ -0,0 +1,147 @@
+{
+  "best_metric": 0.8979357798165137,
+  "best_model_checkpoint": "distilbert-base-uncased-finetuned-sst2/run-2/checkpoint-8419",
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 8419,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.05938947618482005,
+      "grad_norm": 6.959882736206055,
+      "learning_rate": 2.20446303880587e-06,
+      "loss": 0.5244,
+      "step": 500
+    },
+    {
+      "epoch": 0.1187789523696401,
+      "grad_norm": 27.900440216064453,
+      "learning_rate": 2.1599410240462895e-06,
+      "loss": 0.3407,
+      "step": 1000
+    },
+    {
+      "epoch": 0.17816842855446016,
+      "grad_norm": 16.400848388671875,
+      "learning_rate": 2.115419009286709e-06,
+      "loss": 0.3444,
+      "step": 1500
+    },
+    {
+      "epoch": 0.2375579047392802,
+      "grad_norm": 16.666898727416992,
+      "learning_rate": 2.0708969945271283e-06,
+      "loss": 0.3153,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2969473809241002,
+      "grad_norm": 22.084596633911133,
+      "learning_rate": 2.026374979767548e-06,
+      "loss": 0.3076,
+      "step": 2500
+    },
+    {
+      "epoch": 0.3563368571089203,
+      "grad_norm": 42.26548385620117,
+      "learning_rate": 1.9818529650079676e-06,
+      "loss": 0.3228,
+      "step": 3000
+    },
+    {
+      "epoch": 0.41572633329374037,
+      "grad_norm": 48.90976333618164,
+      "learning_rate": 1.937330950248387e-06,
+      "loss": 0.3099,
+      "step": 3500
+    },
+    {
+      "epoch": 0.4751158094785604,
+      "grad_norm": 23.298206329345703,
+      "learning_rate": 1.8928089354888066e-06,
+      "loss": 0.2982,
+      "step": 4000
+    },
+    {
+      "epoch": 0.5345052856633804,
+      "grad_norm": 31.678531646728516,
+      "learning_rate": 1.848286920729226e-06,
+      "loss": 0.3012,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5938947618482004,
+      "grad_norm": 14.523043632507324,
+      "learning_rate": 1.8037649059696455e-06,
+      "loss": 0.3075,
+      "step": 5000
+    },
+    {
+      "epoch": 0.6532842380330206,
+      "grad_norm": 2.0264182090759277,
+      "learning_rate": 1.7592428912100647e-06,
+      "loss": 0.2902,
+      "step": 5500
+    },
+    {
+      "epoch": 0.7126737142178406,
+      "grad_norm": 1.4845110177993774,
+      "learning_rate": 1.7147208764504845e-06,
+      "loss": 0.2929,
+      "step": 6000
+    },
+    {
+      "epoch": 0.7720631904026607,
+      "grad_norm": 21.62343406677246,
+      "learning_rate": 1.6701988616909037e-06,
+      "loss": 0.3003,
+      "step": 6500
+    },
+    {
+      "epoch": 0.8314526665874807,
+      "grad_norm": 6.294283866882324,
+      "learning_rate": 1.6256768469313231e-06,
+      "loss": 0.2949,
+      "step": 7000
+    },
+    {
+      "epoch": 0.8908421427723008,
+      "grad_norm": 52.94987106323242,
+      "learning_rate": 1.5811548321717428e-06,
+      "loss": 0.2685,
+      "step": 7500
+    },
+    {
+      "epoch": 0.9502316189571208,
+      "grad_norm": 10.51728343963623,
+      "learning_rate": 1.5366328174121622e-06,
+      "loss": 0.299,
+      "step": 8000
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8979357798165137,
+      "eval_loss": 0.33407795429229736,
+      "eval_runtime": 1.2282,
+      "eval_samples_per_second": 709.994,
+      "eval_steps_per_second": 44.782,
+      "step": 8419
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 25257,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 490274261244480.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 2.2489850535654507e-06,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 8,
+    "seed": 11
+  }
+}

run-2/checkpoint-8419/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f28c54c631beb4aad19ce06fef9fbf9a411e80177ae39964fa9c31526a231b3
+size 5048

runs/May14_13-42-22_d0b6fd4b0e89/events.out.tfevents.1715698909.d0b6fd4b0e89.396.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b79ef833c1dbffa42afcd3532e667a85874d91099cb0c9cc1d7dfc82baf10add
+size 8759

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4981b833ec6213c008f66b30a316660ab04fb07a2c3971bfc74c2eb43819a780
+oid sha256:6f28c54c631beb4aad19ce06fef9fbf9a411e80177ae39964fa9c31526a231b3
 size 5048