Model update

New model files after re-training.

README.md

@@ -1,6 +1,52 @@
 ---
 language:
 - en
+metrics:
+- accuracy
+model-index:
+- name: opt-small-mt
+  results: []
 ---
 
-OPT small fine-tuned on the MapTask corpus. More details soon.
+# opt-small-mt
+
+This model is a fine-tuned version of [facebook/opt-125m](https://huggingface.co/facebook/opt-125m) on the MapTask dataset.
+It achieves the following results on the evaluation set:
+- Loss: 2.2725
+- Accuracy: 0.5641
+
+## Model description
+
+More details soon.
+
+## Intended uses & limitations
+
+More details soon.
+
+## Training and evaluation data
+
+More details soon.
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-05
+- train_batch_size: 5
+- eval_batch_size: 5
+- seed: 42
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 20.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.26.0
+- Pytorch 1.13.1
+- Datasets 2.9.0
+- Tokenizers 0.13.0.dev0

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.5641330480040158,
+    "eval_loss": 2.272531270980835,
+    "eval_runtime": 2.2768,
+    "eval_samples": 37,
+    "eval_samples_per_second": 16.251,
+    "eval_steps_per_second": 3.514,
+    "perplexity": 9.703933036217537,
+    "train_loss": 1.2078121283115484,
+    "train_runtime": 699.037,
+    "train_samples": 193,
+    "train_samples_per_second": 5.522,
+    "train_steps_per_second": 1.116
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 20.0,
+    "eval_accuracy": 0.5641330480040158,
+    "eval_loss": 2.272531270980835,
+    "eval_runtime": 2.2768,
+    "eval_samples": 37,
+    "eval_samples_per_second": 16.251,
+    "eval_steps_per_second": 3.514,
+    "perplexity": 9.703933036217537
+}

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d61b14964b5ec78eda011ff866378e18896e4b1189ae401c01a199877f6ba4ee
+oid sha256:c72ccff764b0e477bcc87cfeea0d1fcac7eb3d875e72d3e1a829d18f1841fcc8
 size 501023389

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 20.0,
+    "train_loss": 1.2078121283115484,
+    "train_runtime": 699.037,
+    "train_samples": 193,
+    "train_samples_per_second": 5.522,
+    "train_steps_per_second": 1.116
+}

trainer_state.json

@@ -0,0 +1,31 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 20.0,
+  "global_step": 780,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 12.82,
+      "learning_rate": 1.794871794871795e-05,
+      "loss": 1.4127,
+      "step": 500
+    },
+    {
+      "epoch": 20.0,
+      "step": 780,
+      "total_flos": 2017174487040000.0,
+      "train_loss": 1.2078121283115484,
+      "train_runtime": 699.037,
+      "train_samples_per_second": 5.522,
+      "train_steps_per_second": 1.116
+    }
+  ],
+  "max_steps": 780,
+  "num_train_epochs": 20,
+  "total_flos": 2017174487040000.0,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19040fa29db60f3074a55dea25f3f119e5f12ec624834f0c8e2ed0db92b4c94f
-size 3579
+oid sha256:f7761ea77e189065576a114d2dae4b01cf2ccd9c7baff2953bd4e482e0d25921
+size 3515