Training in progress, epoch 2

logs/events.out.tfevents.1709626481.404ecd1cf399.26000.52

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfc133ec8d3e121046734976b5826f39aed733c175568aa29b91b14226597039
-size 5314
+oid sha256:f65a976112ed4b83c49ef4cbb98da68ee358448be5f0124e541915647074edca
+size 5997

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8acc63e54127bd87dbc7e901b44d5dbab923860c501ebb6912c4995f6a0448ea
+oid sha256:c0b15a7f945156f0b676002915586012753d6f1819addee68e2061ec9f567046
 size 17549312

run-46/checkpoint-192/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": "4.38.2",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-46/checkpoint-192/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0b15a7f945156f0b676002915586012753d6f1819addee68e2061ec9f567046
+size 17549312

run-46/checkpoint-192/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f8da2fea656b2d0b59616ba6f858983a09a6fc18f9e318c3c2f9e9181218d9c
+size 35122746

run-46/checkpoint-192/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c58c0607d97c986e9d4c30b0aa74b33350e0c7e86978aaaaadda4ebb78f21ad
+size 14054

run-46/checkpoint-192/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59b074bab2b4ef307d9f0a478060018384d05590bcddc02cba39c453f5b298e6
+size 1064

run-46/checkpoint-192/special_tokens_map.json

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

run-46/checkpoint-192/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-46/checkpoint-192/trainer_state.json

@@ -0,0 +1,64 @@
+{
+  "best_metric": 0.8140900195694716,
+  "best_model_checkpoint": "tiny-bert-sst2-distilled/run-46/checkpoint-192",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 192,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 2.520153045654297,
+      "learning_rate": 0.0004551449993833034,
+      "loss": 0.4997,
+      "step": 96
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.7945205479452054,
+      "eval_f1": 0.814487632508834,
+      "eval_loss": 0.42794638872146606,
+      "eval_precision": 0.7423510466988728,
+      "eval_recall": 0.9021526418786693,
+      "eval_runtime": 31.7011,
+      "eval_samples_per_second": 32.239,
+      "eval_steps_per_second": 1.009,
+      "step": 96
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 1.5412380695343018,
+      "learning_rate": 0.00034135874953747754,
+      "loss": 0.4292,
+      "step": 192
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8140900195694716,
+      "eval_f1": 0.822429906542056,
+      "eval_loss": 0.4104781448841095,
+      "eval_precision": 0.7871198568872988,
+      "eval_recall": 0.8610567514677103,
+      "eval_runtime": 31.9286,
+      "eval_samples_per_second": 32.009,
+      "eval_steps_per_second": 1.002,
+      "step": 192
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 480,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 471390394560.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7902045822653171,
+    "learning_rate": 0.0005689312492291293,
+    "num_train_epochs": 5,
+    "temperature": 24
+  }
+}

run-46/checkpoint-192/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c20512e8f9f83bfa2319c7dfc37d0b2e710fd20b431e0dd3ebf008147e13589c
+size 4920