Training in progress, epoch 3

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b67b2a39fba3e3377a741345670e9de2561ec7c4f05beae89655c9e8ee6c2d3
+oid sha256:b0b730e4ed7cab498e8677a4e5ee06e3c7ba0c3ea46e37b7789cd2f7e6248a14
 size 46823888

run-1/checkpoint-408/config.json

@@ -0,0 +1,93 @@
+{
+  "_name_or_path": "albert-base-v2",
+  "architectures": [
+    "AlbertForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0,
+  "bos_token_id": 2,
+  "classifier_dropout_prob": 0.1,
+  "down_scale_factor": 1,
+  "embedding_size": 128,
+  "eos_token_id": 3,
+  "gap_size": 0,
+  "hidden_act": "gelu_new",
+  "hidden_dropout_prob": 0,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1",
+    "2": "LABEL_2",
+    "3": "LABEL_3",
+    "4": "LABEL_4",
+    "5": "LABEL_5",
+    "6": "LABEL_6",
+    "7": "LABEL_7",
+    "8": "LABEL_8",
+    "9": "LABEL_9",
+    "10": "LABEL_10",
+    "11": "LABEL_11",
+    "12": "LABEL_12",
+    "13": "LABEL_13",
+    "14": "LABEL_14",
+    "15": "LABEL_15",
+    "16": "LABEL_16",
+    "17": "LABEL_17",
+    "18": "LABEL_18",
+    "19": "LABEL_19",
+    "20": "LABEL_20",
+    "21": "LABEL_21",
+    "22": "LABEL_22",
+    "23": "LABEL_23",
+    "24": "LABEL_24",
+    "25": "LABEL_25",
+    "26": "LABEL_26",
+    "27": "LABEL_27"
+  },
+  "initializer_range": 0.02,
+  "inner_group_num": 1,
+  "intermediate_size": 3072,
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1,
+    "LABEL_10": 10,
+    "LABEL_11": 11,
+    "LABEL_12": 12,
+    "LABEL_13": 13,
+    "LABEL_14": 14,
+    "LABEL_15": 15,
+    "LABEL_16": 16,
+    "LABEL_17": 17,
+    "LABEL_18": 18,
+    "LABEL_19": 19,
+    "LABEL_2": 2,
+    "LABEL_20": 20,
+    "LABEL_21": 21,
+    "LABEL_22": 22,
+    "LABEL_23": 23,
+    "LABEL_24": 24,
+    "LABEL_25": 25,
+    "LABEL_26": 26,
+    "LABEL_27": 27,
+    "LABEL_3": 3,
+    "LABEL_4": 4,
+    "LABEL_5": 5,
+    "LABEL_6": 6,
+    "LABEL_7": 7,
+    "LABEL_8": 8,
+    "LABEL_9": 9
+  },
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "albert",
+  "net_structure_type": 0,
+  "num_attention_heads": 12,
+  "num_hidden_groups": 1,
+  "num_hidden_layers": 12,
+  "num_memory_blocks": 0,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.35.2",
+  "type_vocab_size": 2,
+  "vocab_size": 30000
+}

run-1/checkpoint-408/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0b730e4ed7cab498e8677a4e5ee06e3c7ba0c3ea46e37b7789cd2f7e6248a14
+size 46823888

run-1/checkpoint-408/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d27668175066add5a74a635e9b9dc6dd3585194b996b29e115fa9caa67206c1
+size 93663885

run-1/checkpoint-408/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6edf52d3ef502af189bcf9c4328f04c594d6e62f08368170b1debbc908462d3e
+size 14244

run-1/checkpoint-408/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3472e7927a5d299efe6c9c58da55e84d932e3468cefa23c76b1e34ad7ecf020d
+size 1064

run-1/checkpoint-408/special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "[CLS]",
+  "cls_token": "[CLS]",
+  "eos_token": "[SEP]",
+  "mask_token": {
+    "content": "[MASK]",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "[SEP]",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-408/tokenizer_config.json

@@ -0,0 +1,57 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "[MASK]",
+      "lstrip": true,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "[CLS]",
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": false,
+  "eos_token": "[SEP]",
+  "keep_accents": false,
+  "mask_token": "[MASK]",
+  "model_max_length": 128,
+  "pad_token": "<pad>",
+  "remove_space": true,
+  "sep_token": "[SEP]",
+  "tokenizer_class": "AlbertTokenizer",
+  "unk_token": "<unk>"
+}

run-1/checkpoint-408/trainer_state.json

@@ -0,0 +1,51 @@
+{
+  "best_metric": 0.0,
+  "best_model_checkpoint": "albert-base-v2-finetuned/run-1/checkpoint-136",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 408,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.17508015036582947,
+      "eval_runtime": 2.3308,
+      "eval_samples_per_second": 116.27,
+      "eval_steps_per_second": 0.858,
+      "step": 136
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.15788576006889343,
+      "eval_runtime": 2.2808,
+      "eval_samples_per_second": 118.819,
+      "eval_steps_per_second": 0.877,
+      "step": 272
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.15262991189956665,
+      "eval_runtime": 2.3048,
+      "eval_samples_per_second": 117.583,
+      "eval_steps_per_second": 0.868,
+      "step": 408
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 408,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 1.2540187226296499e-05,
+    "num_train_epochs": 3,
+    "per_device_train_batch_size": 16,
+    "seed": 34
+  }
+}

run-1/checkpoint-408/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc87f61524dedb3bb371b910945ecde094352e889c7bc53a2f3b2419989842b
+size 4600

runs/Dec01_05-54-05_1a318d45f005/events.out.tfevents.1701410226.1a318d45f005.3533.26

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0978629f847c5480dd7f17e8e5bad6f557c5949a6cae233a62996449aecb347
-size 6216
+oid sha256:4dc684458c7d42b3964d00a6eba06e61f33e9c1236f0d22396e8db503ca70980
+size 6887