Upload 9 files

README.md

@@ -0,0 +1,72 @@
+---
+license: apache-2.0
+tags:
+- generated_from_trainer
+metrics:
+- accuracy
+model-index:
+- name: output
+  results: []
+---
+
+<!-- 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. -->
+
+# output
+
+This model is a fine-tuned version of [nferruz/ProtGPT2](https://huggingface.co/nferruz/ProtGPT2) on an unknown dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.6699
+- Accuracy: 0.7571
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 2
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 8
+- total_eval_batch_size: 2
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 8.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Accuracy |
+|:-------------:|:-----:|:----:|:---------------:|:--------:|
+| No log        | 1.0   | 220  | 3.8564          | 0.4857   |
+| No log        | 2.0   | 440  | 2.7515          | 0.6096   |
+| 4.1568        | 3.0   | 660  | 2.2463          | 0.6780   |
+| 4.1568        | 4.0   | 880  | 1.9817          | 0.7152   |
+| 2.2818        | 5.0   | 1100 | 1.8278          | 0.7353   |
+| 2.2818        | 6.0   | 1320 | 1.7313          | 0.7486   |
+| 1.8444        | 7.0   | 1540 | 1.6847          | 0.7553   |
+| 1.8444        | 8.0   | 1760 | 1.6699          | 0.7571   |
+
+
+### Framework versions
+
+- Transformers 4.26.1
+- Pytorch 1.13.1+cu117
+- Datasets 2.9.0
+- Tokenizers 0.13.2

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.75708162804937,
+    "eval_loss": 1.669904112815857,
+    "eval_runtime": 5.7278,
+    "eval_samples": 91,
+    "eval_samples_per_second": 15.887,
+    "eval_steps_per_second": 8.031,
+    "perplexity": 5.31165845278959,
+    "train_loss": 2.6170630194924094,
+    "train_runtime": 2594.3652,
+    "train_samples": 1762,
+    "train_samples_per_second": 5.433,
+    "train_steps_per_second": 0.678
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 8.0,
+    "eval_accuracy": 0.75708162804937,
+    "eval_loss": 1.669904112815857,
+    "eval_runtime": 5.7278,
+    "eval_samples": 91,
+    "eval_samples_per_second": 15.887,
+    "eval_steps_per_second": 8.031,
+    "perplexity": 5.31165845278959
+}

runs/Mar15_08-59-17_srvgpu/1678870776.0018482/events.out.tfevents.1678870776.srvgpu.2331335.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b617c4f09123966e549496eb85d41ab2b11720a0d2cb74dfefb9fa2edc7936e
+size 5634

runs/Mar15_08-59-17_srvgpu/events.out.tfevents.1678870775.srvgpu.2331335.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1fa8f0ce2b2c924c769f31806ec8dd4b4a13d7b66e70411e59f99f007970a65
+size 7436

runs/Mar15_08-59-17_srvgpu/events.out.tfevents.1678873380.srvgpu.2331335.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c13ac191235b1762849c5a3b34bb584f1f7d29e7cc395755c75ffd59129f24c1
+size 363

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 8.0,
+    "train_loss": 2.6170630194924094,
+    "train_runtime": 2594.3652,
+    "train_samples": 1762,
+    "train_samples_per_second": 5.433,
+    "train_steps_per_second": 0.678
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 7.998864926220204,
+  "global_step": 1760,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.4856970986003244,
+      "eval_loss": 3.856384515762329,
+      "eval_runtime": 5.67,
+      "eval_samples_per_second": 16.049,
+      "eval_steps_per_second": 8.113,
+      "step": 220
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.6095839644226742,
+      "eval_loss": 2.7515063285827637,
+      "eval_runtime": 5.6811,
+      "eval_samples_per_second": 16.018,
+      "eval_steps_per_second": 8.097,
+      "step": 440
+    },
+    {
+      "epoch": 2.27,
+      "learning_rate": 7.181818181818182e-06,
+      "loss": 4.1568,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6779671940962263,
+      "eval_loss": 2.2462902069091797,
+      "eval_runtime": 5.6846,
+      "eval_samples_per_second": 16.008,
+      "eval_steps_per_second": 8.092,
+      "step": 660
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.7152310055535862,
+      "eval_loss": 1.981738567352295,
+      "eval_runtime": 5.6899,
+      "eval_samples_per_second": 15.993,
+      "eval_steps_per_second": 8.084,
+      "step": 880
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 4.340909090909091e-06,
+      "loss": 2.2818,
+      "step": 1000
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.7353184449958643,
+      "eval_loss": 1.8277500867843628,
+      "eval_runtime": 5.6901,
+      "eval_samples_per_second": 15.993,
+      "eval_steps_per_second": 8.084,
+      "step": 1100
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.7485740066385228,
+      "eval_loss": 1.7312932014465332,
+      "eval_runtime": 5.683,
+      "eval_samples_per_second": 16.013,
+      "eval_steps_per_second": 8.094,
+      "step": 1320
+    },
+    {
+      "epoch": 6.82,
+      "learning_rate": 1.5e-06,
+      "loss": 1.8444,
+      "step": 1500
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.7553092069221101,
+      "eval_loss": 1.6847076416015625,
+      "eval_runtime": 5.6791,
+      "eval_samples_per_second": 16.024,
+      "eval_steps_per_second": 8.1,
+      "step": 1540
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.75708162804937,
+      "eval_loss": 1.669904112815857,
+      "eval_runtime": 5.9939,
+      "eval_samples_per_second": 15.182,
+      "eval_steps_per_second": 7.674,
+      "step": 1760
+    },
+    {
+      "epoch": 8.0,
+      "step": 1760,
+      "total_flos": 6.134202859152998e+16,
+      "train_loss": 2.6170630194924094,
+      "train_runtime": 2594.3652,
+      "train_samples_per_second": 5.433,
+      "train_steps_per_second": 0.678
+    }
+  ],
+  "max_steps": 1760,
+  "num_train_epochs": 8,
+  "total_flos": 6.134202859152998e+16,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0e5c4c09bc5060bcc92fc7fcfbdcc83de078d44adbba8f9bad79d98d554ece2
+size 3579