Model save

last-checkpoint/config.json

@@ -1,33 +0,0 @@
-{
-  "_name_or_path": "albert-base-v2",
-  "architectures": [
-    "AlbertForMaskedLM"
-  ],
-  "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,
-  "initializer_range": 0.02,
-  "inner_group_num": 1,
-  "intermediate_size": 3072,
-  "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": "4.23.1",
-  "type_vocab_size": 2,
-  "vocab_size": 30000
-}

last-checkpoint/optimizer.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:0496b32513d75c8f410f18a7a7693cc1ca92ebccc07b0fb87b51fa3458bc31d6
-size 89789873

last-checkpoint/pytorch_model.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:f6b18a485539c6ced214f6f282b8a356c27c3f08b89cb37a05d973ed814d0b4e
-size 44900936

last-checkpoint/rng_state.pth

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:cde37b1d59ec8275aa116b67c6503ca997bd9a90886b106af365cbb8dfef4db9
-size 14575

last-checkpoint/scaler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:a758d7f80645ca7b6df48d736de4036b46f37bd0ee72c0a8f5b7db555d7202d4
-size 557

last-checkpoint/scheduler.pt

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:3297467e71d3fc7db550ac11668566984d0914e69787cecd311b029149f474e3
-size 627

last-checkpoint/special_tokens_map.json

@@ -1,15 +0,0 @@
-{
-  "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>"
-}

last-checkpoint/spiece.model

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:fefb02b667a6c5c2fe27602d28e5fb3428f66ab89c7d6f388e7c8d44a02d0336
-size 760289

last-checkpoint/tokenizer_config.json

@@ -1,23 +0,0 @@
-{
-  "bos_token": "[CLS]",
-  "cls_token": "[CLS]",
-  "do_lower_case": true,
-  "eos_token": "[SEP]",
-  "keep_accents": false,
-  "mask_token": {
-    "__type": "AddedToken",
-    "content": "[MASK]",
-    "lstrip": true,
-    "normalized": false,
-    "rstrip": false,
-    "single_word": false
-  },
-  "model_max_length": 512,
-  "name_or_path": "albert-base-v2",
-  "pad_token": "<pad>",
-  "remove_space": true,
-  "sep_token": "[SEP]",
-  "special_tokens_map_file": null,
-  "tokenizer_class": "AlbertTokenizer",
-  "unk_token": "<unk>"
-}

last-checkpoint/trainer_state.json

@@ -1,86 +0,0 @@
-{
-  "best_metric": 0.000184760894626379,
-  "best_model_checkpoint": "./albert-results/checkpoint-500",
-  "epoch": 0.32679738562091504,
-  "global_step": 500,
-  "is_hyper_param_search": false,
-  "is_local_process_zero": true,
-  "is_world_process_zero": true,
-  "log_history": [
-    {
-      "epoch": 0.07,
-      "learning_rate": 1.9925653594771244e-05,
-      "loss": 3.3585,
-      "step": 100
-    },
-    {
-      "epoch": 0.07,
-      "eval_loss": 0.14794819056987762,
-      "eval_runtime": 16.5325,
-      "eval_samples_per_second": 60.487,
-      "eval_steps_per_second": 1.936,
-      "step": 100
-    },
-    {
-      "epoch": 0.13,
-      "learning_rate": 1.9843954248366014e-05,
-      "loss": 0.0929,
-      "step": 200
-    },
-    {
-      "epoch": 0.13,
-      "eval_loss": 0.0728602185845375,
-      "eval_runtime": 16.8991,
-      "eval_samples_per_second": 59.175,
-      "eval_steps_per_second": 1.894,
-      "step": 200
-    },
-    {
-      "epoch": 0.2,
-      "learning_rate": 1.9762254901960787e-05,
-      "loss": 0.0295,
-      "step": 300
-    },
-    {
-      "epoch": 0.2,
-      "eval_loss": 0.0029316628351807594,
-      "eval_runtime": 16.8378,
-      "eval_samples_per_second": 59.39,
-      "eval_steps_per_second": 1.9,
-      "step": 300
-    },
-    {
-      "epoch": 0.26,
-      "learning_rate": 1.9680555555555557e-05,
-      "loss": 0.0029,
-      "step": 400
-    },
-    {
-      "epoch": 0.26,
-      "eval_loss": 0.0027500337455421686,
-      "eval_runtime": 16.9348,
-      "eval_samples_per_second": 59.05,
-      "eval_steps_per_second": 1.89,
-      "step": 400
-    },
-    {
-      "epoch": 0.33,
-      "learning_rate": 1.9598856209150327e-05,
-      "loss": 0.0008,
-      "step": 500
-    },
-    {
-      "epoch": 0.33,
-      "eval_loss": 0.000184760894626379,
-      "eval_runtime": 16.883,
-      "eval_samples_per_second": 59.231,
-      "eval_steps_per_second": 1.895,
-      "step": 500
-    }
-  ],
-  "max_steps": 24480,
-  "num_train_epochs": 16,
-  "total_flos": 89897631744000.0,
-  "trial_name": null,
-  "trial_params": null
-}

last-checkpoint/training_args.bin

@@ -1,3 +0,0 @@
-version https://git-lfs.github.com/spec/v1
-oid sha256:33bff3c131bd36da74e172c6d6a8e361cf13df6107f3da2909e49f51ec49a0fd
-size 3451

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6b18a485539c6ced214f6f282b8a356c27c3f08b89cb37a05d973ed814d0b4e
+oid sha256:a246b08c8cf009af41cdc219512d6573aa6156680b27a56944baa66d4552c36c
 size 44900936

runs/Oct30_18-39-30_daccc72d0fea/events.out.tfevents.1667155186.daccc72d0fea.78.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a54b777c2922439609349f094c34bb405be8d44db7b023cf82fa4b4fdb4941ea
-size 6023
+oid sha256:477b438414e2521b857e1158e474ca9901dfd08941926ddcfaf43618a87aa06f
+size 6451