Training in progress, epoch 5

logs/events.out.tfevents.1701754017.joseph_legion.10272.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b19ae6d86772ce46bd545515da147dbda1aa88acc68a6390549303f6bdd602e
-size 6213
+oid sha256:280287d576dbc1416fbe7c8fa41c030ec525bc0249869c94c5c2e0d881dab0c0
+size 6693

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87c8aba367e4cfc633ae43a522d9fb39f52174943838287d6c22b9ffaedb0211
+oid sha256:3046f5da2757ffc97884cc54e0bfa793762600a3353c50bd4c55170428cb77d2
 size 17549312

run-1/checkpoint-2635/config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "google/bert_uncased_L-2_H-128_A-2",
+  "architectures": [
+    "BertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 128,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 2,
+  "num_hidden_layers": 2,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-1/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3046f5da2757ffc97884cc54e0bfa793762600a3353c50bd4c55170428cb77d2
+size 17549312

run-1/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1441fddcaee7f27cdff27c8982b1b6d323ed460d4e5a0cebb34f6fbee7b2d275
+size 35123898

run-1/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dede22851852362c4610a33dd1fe1d0ae7402b3b76398a9832f493ea9fb1aa9
+size 14308

run-1/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cda8a12a0ffc8bddab0a50c2c1452e69ec617552805591fd616435cf17f59365
+size 1064

run-1/checkpoint-2635/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-2635/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "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_basic_tokenize": true,
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "never_split": null,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "[UNK]"
+}

run-1/checkpoint-2635/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_metric": 0.8314220183486238,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled\\run-1\\checkpoint-2108",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2635,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 7.193342816186545e-05,
+      "loss": 1.1191,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8061926605504587,
+      "eval_loss": 0.9445732831954956,
+      "eval_runtime": 1.8865,
+      "eval_samples_per_second": 462.238,
+      "eval_steps_per_second": 3.711,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 5.994452346822122e-05,
+      "loss": 0.6346,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8279816513761468,
+      "eval_loss": 0.8901896476745605,
+      "eval_runtime": 1.7665,
+      "eval_samples_per_second": 493.618,
+      "eval_steps_per_second": 3.963,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 4.795561877457697e-05,
+      "loss": 0.4919,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8211009174311926,
+      "eval_loss": 0.9235907196998596,
+      "eval_runtime": 1.9102,
+      "eval_samples_per_second": 456.496,
+      "eval_steps_per_second": 3.665,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 3.5966714080932725e-05,
+      "loss": 0.4192,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8314220183486238,
+      "eval_loss": 0.9573733806610107,
+      "eval_runtime": 1.9272,
+      "eval_samples_per_second": 452.465,
+      "eval_steps_per_second": 3.632,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "learning_rate": 2.3977809387288486e-05,
+      "loss": 0.377,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8268348623853211,
+      "eval_loss": 0.9544126987457275,
+      "eval_runtime": 1.9749,
+      "eval_samples_per_second": 441.534,
+      "eval_steps_per_second": 3.544,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3689,
+  "num_train_epochs": 7,
+  "save_steps": 500,
+  "total_flos": 40452267650880.0,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.6227846651931359,
+    "learning_rate": 8.39223328555097e-05,
+    "num_train_epochs": 7,
+    "temperature": 4
+  }
+}

run-1/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41b6dd4b0cd50cfc8b6916f5bb0ffa702ddcb4610b47caf4b1109c9f79f26fdd
+size 4664