Training in progress, epoch 5

logs/events.out.tfevents.1713516835.persepolis.29644.33

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97f57f1d72c96a4543e31c55779a98dba3befc20b6b1201b4ec6355fe0f66905
-size 7080
+oid sha256:48e85509e665c09bab6892a61545c6ee3f14414fd28feb1c8727c16b4ca99030
+size 7968

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd09e9ebbd47f97843908f3a46979a331affe9ffafc6b2cf7549ebe5ff3fb868
+oid sha256:5502dbc50d923f1bdce3748358e5ef79d7e5b4dc98e26db8cddde4700a7927f8
 size 54221200

run-32/checkpoint-2635/config.json

@@ -0,0 +1,39 @@
+{
+  "_name_or_path": "google/electra-small-discriminator",
+  "architectures": [
+    "ElectraForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "embedding_size": 128,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 256,
+  "id2label": {
+    "0": "negative",
+    "1": "positive"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 1024,
+  "label2id": {
+    "negative": "0",
+    "positive": "1"
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "electra",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "summary_activation": "gelu",
+  "summary_last_dropout": 0.1,
+  "summary_type": "first",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.40.0",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 30522
+}

run-32/checkpoint-2635/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5502dbc50d923f1bdce3748358e5ef79d7e5b4dc98e26db8cddde4700a7927f8
+size 54221200

run-32/checkpoint-2635/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:60cceda75f245ac72fb2c20943f79521c3d692fb5f3b4396c7308f07e2e7d99d
+size 108564282

run-32/checkpoint-2635/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f663bdb15d062023c1cf28c57849d73a5f427a71fc4ff8bd8995ab52fb854b16
+size 14308

run-32/checkpoint-2635/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddada1d92079177c2a2c308ee237f17f3d9639554c9082ec839a113833d6e928
+size 1064

run-32/checkpoint-2635/special_tokens_map.json

@@ -0,0 +1,37 @@
+{
+  "cls_token": {
+    "content": "[CLS]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "[SEP]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "[UNK]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

run-32/checkpoint-2635/tokenizer_config.json

@@ -0,0 +1,62 @@
+{
+  "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]",
+  "max_length": 128,
+  "model_max_length": 512,
+  "pad_to_multiple_of": null,
+  "pad_token": "[PAD]",
+  "pad_token_type_id": 0,
+  "padding_side": "right",
+  "sep_token": "[SEP]",
+  "stride": 0,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "ElectraTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "[UNK]"
+}

run-32/checkpoint-2635/trainer_state.json

@@ -0,0 +1,106 @@
+{
+  "best_metric": 0.9208715596330275,
+  "best_model_checkpoint": "electra-distilled-sst\\run-32\\checkpoint-1581",
+  "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,
+      "grad_norm": 47.12026596069336,
+      "learning_rate": 4.2569562606597884e-05,
+      "loss": 2.7545,
+      "step": 527
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8990825688073395,
+      "eval_loss": 1.4578064680099487,
+      "eval_runtime": 1.4519,
+      "eval_samples_per_second": 600.58,
+      "eval_steps_per_second": 4.821,
+      "step": 527
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 78.47111511230469,
+      "learning_rate": 3.1942296148200405e-05,
+      "loss": 1.283,
+      "step": 1054
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.9071100917431193,
+      "eval_loss": 1.441101312637329,
+      "eval_runtime": 1.4585,
+      "eval_samples_per_second": 597.892,
+      "eval_steps_per_second": 4.8,
+      "step": 1054
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 58.518775939941406,
+      "learning_rate": 2.1315029689802918e-05,
+      "loss": 0.9314,
+      "step": 1581
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 1.2692312002182007,
+      "eval_runtime": 1.4446,
+      "eval_samples_per_second": 603.643,
+      "eval_steps_per_second": 4.846,
+      "step": 1581
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 19.554431915283203,
+      "learning_rate": 1.0687763231405437e-05,
+      "loss": 0.7341,
+      "step": 2108
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9151376146788991,
+      "eval_loss": 1.3720850944519043,
+      "eval_runtime": 1.4488,
+      "eval_samples_per_second": 601.895,
+      "eval_steps_per_second": 4.832,
+      "step": 2108
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 43.02271270751953,
+      "learning_rate": 8.066236401060707e-08,
+      "loss": 0.6406,
+      "step": 2635
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9208715596330275,
+      "eval_loss": 1.3230271339416504,
+      "eval_runtime": 1.4499,
+      "eval_samples_per_second": 601.441,
+      "eval_steps_per_second": 4.828,
+      "step": 2635
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2635,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 936602651243304.0,
+  "train_batch_size": 128,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.2744072380603728,
+    "learning_rate": 5.313633229198741e-05,
+    "num_train_epochs": 5,
+    "temperature": 16
+  }
+}

run-32/checkpoint-2635/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a7c6aed55f6c62d5fe0946ab5660672fd96249a283a306a3e04368589375210
+size 5048