End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- MBZUAI/Bactrian-X
+metrics:
+- accuracy
 model-index:
 - name: MicroPhi-Indo
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: MBZUAI/Bactrian-X id
+      type: MBZUAI/Bactrian-X
+      args: id
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.23619257086999024
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -11,7 +26,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # MicroPhi-Indo
 
-This model was trained from scratch on an unknown dataset.
+This model was trained from scratch on the MBZUAI/Bactrian-X id dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.3697
+- Accuracy: 0.2362
 
 ## Model description
 

all_results.json

@@ -0,0 +1,16 @@
+{
+    "epoch": 1.99,
+    "eval_accuracy": 0.23619257086999024,
+    "eval_loss": 5.369718551635742,
+    "eval_runtime": 8.2411,
+    "eval_samples": 40,
+    "eval_samples_per_second": 4.854,
+    "eval_steps_per_second": 2.427,
+    "perplexity": 214.80240341086764,
+    "total_flos": 2829332565196800.0,
+    "train_loss": 6.479159524507612,
+    "train_runtime": 865.9454,
+    "train_samples": 862,
+    "train_samples_per_second": 1.991,
+    "train_steps_per_second": 0.247
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 1.99,
+    "eval_accuracy": 0.23619257086999024,
+    "eval_loss": 5.369718551635742,
+    "eval_runtime": 8.2411,
+    "eval_samples": 40,
+    "eval_samples_per_second": 4.854,
+    "eval_steps_per_second": 2.427,
+    "perplexity": 214.80240341086764
+}

runs/Jan31_13-45-08_345b71fb10c2/events.out.tfevents.1706709646.345b71fb10c2.34.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b7cc559702d9a3bb5899276e71508f745ef4cfc4a5d1c553dd457791bbc38d75
+size 411

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.99,
+    "total_flos": 2829332565196800.0,
+    "train_loss": 6.479159524507612,
+    "train_runtime": 865.9454,
+    "train_samples": 862,
+    "train_samples_per_second": 1.991,
+    "train_steps_per_second": 0.247
+}

trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.986078886310905,
+  "eval_steps": 500,
+  "global_step": 214,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.86,
+      "learning_rate": 3.2710280373831774e-06,
+      "loss": 6.5469,
+      "step": 200
+    },
+    {
+      "epoch": 1.99,
+      "step": 214,
+      "total_flos": 2829332565196800.0,
+      "train_loss": 6.479159524507612,
+      "train_runtime": 865.9454,
+      "train_samples_per_second": 1.991,
+      "train_steps_per_second": 0.247
+    }
+  ],
+  "logging_steps": 200,
+  "max_steps": 214,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 2000,
+  "total_flos": 2829332565196800.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}