save from trainer

.gitignore

@@ -0,0 +1 @@
+checkpoint*

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+tags:
+- text-classification
+metrics:
+- accuracy
+
+model-index:
+- name: model
+  results:
+  - task:
+      name: Text Classification
+      type: text-classification
+    metrics:
+      - name: Accuracy
+        type: accuracy
+        value: 0.2662102282047272
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# model
+
+This model is a fine-tuned version of [distilroberta-base](https://huggingface.co/distilroberta-base) on an unkown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.9150
+- Accuracy: 0.2662
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3.0
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| 3.0528        | 0.44  | 1000 | 3.0265          | 0.2223   |
+| 2.9836        | 0.89  | 2000 | 2.9263          | 0.2332   |
+| 2.7409        | 1.33  | 3000 | 2.9041          | 0.2533   |
+| 2.7905        | 1.77  | 4000 | 2.8763          | 0.2606   |
+| 2.4359        | 2.22  | 5000 | 2.9072          | 0.2642   |
+| 2.4507        | 2.66  | 6000 | 2.9230          | 0.2644   |
+
+
+### Framework versions
+
+- Transformers 4.7.0.dev0
+- Pytorch 1.8.1+cu102
+- Datasets 1.8.0
+- Tokenizers 0.10.3

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.2662102282047272,
+    "eval_loss": 2.914989471435547,
+    "eval_runtime": 7.4525,
+    "eval_samples": 4966,
+    "eval_samples_per_second": 666.352,
+    "eval_steps_per_second": 83.328,
+    "train_loss": 2.764526012873939,
+    "train_runtime": 382.9395,
+    "train_samples": 18029,
+    "train_samples_per_second": 141.242,
+    "train_steps_per_second": 17.658
+}

config.json

@@ -0,0 +1,117 @@
+{
+  "_name_or_path": "distilroberta-base",
+  "architectures": [
+    "RobertaForSequenceClassification"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "bos_token_id": 0,
+  "eos_token_id": 2,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 768,
+  "id2label": {
+    "0": "agree",
+    "1": "applause",
+    "2": "awww",
+    "3": "dance",
+    "4": "deal_with_it",
+    "5": "do_not_want",
+    "6": "eww",
+    "7": "eye_roll",
+    "8": "facepalm",
+    "9": "fist_bump",
+    "10": "good_luck",
+    "11": "happy_dance",
+    "12": "hearts",
+    "13": "high_five",
+    "14": "hug",
+    "15": "idk",
+    "16": "kiss",
+    "17": "mic_drop",
+    "18": "no",
+    "19": "oh_snap",
+    "20": "ok",
+    "21": "omg",
+    "22": "oops",
+    "23": "please",
+    "24": "popcorn",
+    "25": "scared",
+    "26": "seriously",
+    "27": "shocked",
+    "28": "shrug",
+    "29": "sigh",
+    "30": "slow_clap",
+    "31": "smh",
+    "32": "sorry",
+    "33": "thank_you",
+    "34": "thumbs_down",
+    "35": "thumbs_up",
+    "36": "want",
+    "37": "win",
+    "38": "wink",
+    "39": "yawn",
+    "40": "yes",
+    "41": "yolo",
+    "42": "you_got_this"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "label2id": {
+    "agree": 0,
+    "applause": 1,
+    "awww": 2,
+    "dance": 3,
+    "deal_with_it": 4,
+    "do_not_want": 5,
+    "eww": 6,
+    "eye_roll": 7,
+    "facepalm": 8,
+    "fist_bump": 9,
+    "good_luck": 10,
+    "happy_dance": 11,
+    "hearts": 12,
+    "high_five": 13,
+    "hug": 14,
+    "idk": 15,
+    "kiss": 16,
+    "mic_drop": 17,
+    "no": 18,
+    "oh_snap": 19,
+    "ok": 20,
+    "omg": 21,
+    "oops": 22,
+    "please": 23,
+    "popcorn": 24,
+    "scared": 25,
+    "seriously": 26,
+    "shocked": 27,
+    "shrug": 28,
+    "sigh": 29,
+    "slow_clap": 30,
+    "smh": 31,
+    "sorry": 32,
+    "thank_you": 33,
+    "thumbs_down": 34,
+    "thumbs_up": 35,
+    "want": 36,
+    "win": 37,
+    "wink": 38,
+    "yawn": 39,
+    "yes": 40,
+    "yolo": 41,
+    "you_got_this": 42
+  },
+  "layer_norm_eps": 1e-05,
+  "max_position_embeddings": 514,
+  "model_type": "roberta",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 6,
+  "pad_token_id": 1,
+  "position_embedding_type": "absolute",
+  "problem_type": "single_label_classification",
+  "transformers_version": "4.7.0.dev0",
+  "type_vocab_size": 1,
+  "use_cache": true,
+  "vocab_size": 50265
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.2662102282047272,
+    "eval_loss": 2.914989471435547,
+    "eval_runtime": 7.4525,
+    "eval_samples": 4966,
+    "eval_samples_per_second": 666.352,
+    "eval_steps_per_second": 83.328
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b54c4411f601d2c8693a27f20003a5860caa54e04de033a30314fcc24bb8a37a
+size 328655081

special_tokens_map.json

@@ -0,0 +1 @@
+{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}

tokenizer_config.json

@@ -0,0 +1 @@
+{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "special_tokens_map_file": null, "name_or_path": "distilroberta-base"}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 2.764526012873939,
+    "train_runtime": 382.9395,
+    "train_samples": 18029,
+    "train_samples_per_second": 141.242,
+    "train_steps_per_second": 17.658
+}

trainer_state.json

@@ -0,0 +1,283 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "global_step": 6762,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0,
+      "learning_rate": 4.9992605737947355e-05,
+      "loss": 3.6847,
+      "step": 1
+    },
+    {
+      "epoch": 0.09,
+      "learning_rate": 4.852114758947057e-05,
+      "loss": 3.4099,
+      "step": 200
+    },
+    {
+      "epoch": 0.18,
+      "learning_rate": 4.704229517894114e-05,
+      "loss": 3.2337,
+      "step": 400
+    },
+    {
+      "epoch": 0.27,
+      "learning_rate": 4.5563442768411715e-05,
+      "loss": 3.0788,
+      "step": 600
+    },
+    {
+      "epoch": 0.35,
+      "learning_rate": 4.408459035788228e-05,
+      "loss": 3.1394,
+      "step": 800
+    },
+    {
+      "epoch": 0.44,
+      "learning_rate": 4.260573794735286e-05,
+      "loss": 3.0528,
+      "step": 1000
+    },
+    {
+      "epoch": 0.44,
+      "eval_accuracy": 0.22231172025203705,
+      "eval_loss": 3.0265257358551025,
+      "eval_runtime": 7.2925,
+      "eval_samples_per_second": 680.975,
+      "eval_steps_per_second": 85.156,
+      "step": 1000
+    },
+    {
+      "epoch": 0.53,
+      "learning_rate": 4.112688553682343e-05,
+      "loss": 2.9704,
+      "step": 1200
+    },
+    {
+      "epoch": 0.62,
+      "learning_rate": 3.9648033126293996e-05,
+      "loss": 3.0544,
+      "step": 1400
+    },
+    {
+      "epoch": 0.71,
+      "learning_rate": 3.816918071576457e-05,
+      "loss": 2.9979,
+      "step": 1600
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.669032830523514e-05,
+      "loss": 3.0237,
+      "step": 1800
+    },
+    {
+      "epoch": 0.89,
+      "learning_rate": 3.521147589470571e-05,
+      "loss": 2.9836,
+      "step": 2000
+    },
+    {
+      "epoch": 0.89,
+      "eval_accuracy": 0.23318566381931305,
+      "eval_loss": 2.926269054412842,
+      "eval_runtime": 7.3605,
+      "eval_samples_per_second": 674.678,
+      "eval_steps_per_second": 84.369,
+      "step": 2000
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 3.3732623484176276e-05,
+      "loss": 2.9896,
+      "step": 2200
+    },
+    {
+      "epoch": 1.06,
+      "learning_rate": 3.225377107364685e-05,
+      "loss": 2.8578,
+      "step": 2400
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.077491866311743e-05,
+      "loss": 2.7667,
+      "step": 2600
+    },
+    {
+      "epoch": 1.24,
+      "learning_rate": 2.9296066252587996e-05,
+      "loss": 2.8017,
+      "step": 2800
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 2.7817213842058564e-05,
+      "loss": 2.7409,
+      "step": 3000
+    },
+    {
+      "epoch": 1.33,
+      "eval_accuracy": 0.2533226013183594,
+      "eval_loss": 2.9040770530700684,
+      "eval_runtime": 7.3851,
+      "eval_samples_per_second": 672.437,
+      "eval_steps_per_second": 84.088,
+      "step": 3000
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 2.6338361431529136e-05,
+      "loss": 2.7605,
+      "step": 3200
+    },
+    {
+      "epoch": 1.51,
+      "learning_rate": 2.4859509020999705e-05,
+      "loss": 2.7569,
+      "step": 3400
+    },
+    {
+      "epoch": 1.6,
+      "learning_rate": 2.3380656610470276e-05,
+      "loss": 2.7154,
+      "step": 3600
+    },
+    {
+      "epoch": 1.69,
+      "learning_rate": 2.190180419994085e-05,
+      "loss": 2.788,
+      "step": 3800
+    },
+    {
+      "epoch": 1.77,
+      "learning_rate": 2.0422951789411417e-05,
+      "loss": 2.7905,
+      "step": 4000
+    },
+    {
+      "epoch": 1.77,
+      "eval_accuracy": 0.2605718970298767,
+      "eval_loss": 2.876274824142456,
+      "eval_runtime": 7.4268,
+      "eval_samples_per_second": 668.66,
+      "eval_steps_per_second": 83.616,
+      "step": 4000
+    },
+    {
+      "epoch": 1.86,
+      "learning_rate": 1.894409937888199e-05,
+      "loss": 2.7044,
+      "step": 4200
+    },
+    {
+      "epoch": 1.95,
+      "learning_rate": 1.7465246968352557e-05,
+      "loss": 2.7526,
+      "step": 4400
+    },
+    {
+      "epoch": 2.04,
+      "learning_rate": 1.5986394557823133e-05,
+      "loss": 2.6027,
+      "step": 4600
+    },
+    {
+      "epoch": 2.13,
+      "learning_rate": 1.4507542147293701e-05,
+      "loss": 2.4391,
+      "step": 4800
+    },
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.3028689736764271e-05,
+      "loss": 2.4359,
+      "step": 5000
+    },
+    {
+      "epoch": 2.22,
+      "eval_accuracy": 0.2641965448856354,
+      "eval_loss": 2.9071688652038574,
+      "eval_runtime": 7.4381,
+      "eval_samples_per_second": 667.644,
+      "eval_steps_per_second": 83.489,
+      "step": 5000
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 1.1549837326234843e-05,
+      "loss": 2.4514,
+      "step": 5200
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 1.0070984915705414e-05,
+      "loss": 2.4754,
+      "step": 5400
+    },
+    {
+      "epoch": 2.48,
+      "learning_rate": 8.592132505175984e-06,
+      "loss": 2.4698,
+      "step": 5600
+    },
+    {
+      "epoch": 2.57,
+      "learning_rate": 7.113280094646555e-06,
+      "loss": 2.4732,
+      "step": 5800
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 5.634427684117125e-06,
+      "loss": 2.4507,
+      "step": 6000
+    },
+    {
+      "epoch": 2.66,
+      "eval_accuracy": 0.26439791917800903,
+      "eval_loss": 2.9230332374572754,
+      "eval_runtime": 7.4558,
+      "eval_samples_per_second": 666.058,
+      "eval_steps_per_second": 83.291,
+      "step": 6000
+    },
+    {
+      "epoch": 2.75,
+      "learning_rate": 4.155575273587696e-06,
+      "loss": 2.5628,
+      "step": 6200
+    },
+    {
+      "epoch": 2.84,
+      "learning_rate": 2.6767228630582667e-06,
+      "loss": 2.3556,
+      "step": 6400
+    },
+    {
+      "epoch": 2.93,
+      "learning_rate": 1.1978704525288378e-06,
+      "loss": 2.4206,
+      "step": 6600
+    },
+    {
+      "epoch": 3.0,
+      "step": 6762,
+      "total_flos": 3412474671843072.0,
+      "train_loss": 2.764526012873939,
+      "train_runtime": 382.9395,
+      "train_samples_per_second": 141.242,
+      "train_steps_per_second": 17.658
+    }
+  ],
+  "max_steps": 6762,
+  "num_train_epochs": 3,
+  "total_flos": 3412474671843072.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5740560245546a0993ff4a9a2d710272d28f10f294b413d89bac9645d1e8369c
+size 2415