Training in progress, epoch 5

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2c6240c4fef948ed5e55e41190d05e31903e04b45e5c91376223d7317948ef9
+oid sha256:1aaa5c18fd01a5f982a8eefaf62e23f82a4b534924443d58c3f793a5eb33038b
 size 46823888

run-2/checkpoint-170/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-2/checkpoint-170/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1aaa5c18fd01a5f982a8eefaf62e23f82a4b534924443d58c3f793a5eb33038b
+size 46823888

run-2/checkpoint-170/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ab464b168272d3870df5dbcc322cc71233c701a7cb0d1b642510f73bb6b1894
+size 93663885

run-2/checkpoint-170/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d8bbfe2d5d965b72e7feea4edf3990e365bdb16a5b3ba919eb49965778bc7ff
+size 14244

run-2/checkpoint-170/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa01c889be706a567025db66f744b9e5251f3b42db3eac8e986e6a8c00df9cf0
+size 1064

run-2/checkpoint-170/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-2/checkpoint-170/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-2/checkpoint-170/trainer_state.json

@@ -0,0 +1,69 @@
+{
+  "best_metric": 0.012658227848101266,
+  "best_model_checkpoint": "albert-base-v2-finetuned/run-2/checkpoint-34",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 170,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_f1": 0.012658227848101266,
+      "eval_loss": 0.390350341796875,
+      "eval_runtime": 2.3439,
+      "eval_samples_per_second": 115.618,
+      "eval_steps_per_second": 0.853,
+      "step": 34
+    },
+    {
+      "epoch": 2.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.2815706133842468,
+      "eval_runtime": 2.2953,
+      "eval_samples_per_second": 118.067,
+      "eval_steps_per_second": 0.871,
+      "step": 68
+    },
+    {
+      "epoch": 3.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.24412979185581207,
+      "eval_runtime": 2.3056,
+      "eval_samples_per_second": 117.54,
+      "eval_steps_per_second": 0.867,
+      "step": 102
+    },
+    {
+      "epoch": 4.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.22842060029506683,
+      "eval_runtime": 2.2898,
+      "eval_samples_per_second": 118.35,
+      "eval_steps_per_second": 0.873,
+      "step": 136
+    },
+    {
+      "epoch": 5.0,
+      "eval_f1": 0.0,
+      "eval_loss": 0.2242501676082611,
+      "eval_runtime": 2.3063,
+      "eval_samples_per_second": 117.502,
+      "eval_steps_per_second": 0.867,
+      "step": 170
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 170,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "total_flos": 0,
+  "trial_name": null,
+  "trial_params": {
+    "learning_rate": 7.728558213353496e-06,
+    "num_train_epochs": 5,
+    "per_device_train_batch_size": 64,
+    "seed": 2
+  }
+}

run-2/checkpoint-170/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1082d23d1d7a4032e72e08f3e6219011863fbd2b608bfb61fee1fab4a3e062eb
+size 4600

runs/Dec01_05-54-05_1a318d45f005/events.out.tfevents.1701410406.1a318d45f005.3533.27

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2eaae87aa28b4a3e28353f239b2703636e7a50fc59cd86160c91d5b933d06ece
-size 6830
+oid sha256:d57c1ce92c47a2c497cdba2f7ecd210acba974bb1efef76ea8a486af54bc8a82
+size 7501