End of training

README.md

@@ -1,9 +1,24 @@
 ---
 tags:
 - generated_from_trainer
+datasets:
+- gsm8k
+metrics:
+- accuracy
 model-index:
 - name: opt_1_flan_gsm8k
-  results: []
+  results:
+  - task:
+      name: Causal Language Modeling
+      type: text-generation
+    dataset:
+      name: gsm8k main
+      type: gsm8k
+      args: main
+    metrics:
+    - name: Accuracy
+      type: accuracy
+      value: 0.19469348746188503
 ---
 
 <!-- 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. -->
 
 # opt_1_flan_gsm8k
 
-This model is a fine-tuned version of [](https://huggingface.co/) on an unknown dataset.
+This model is a fine-tuned version of [](https://huggingface.co/) on the gsm8k main dataset.
+It achieves the following results on the evaluation set:
+- Loss: 5.2508
+- Accuracy: 0.1947
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.19469348746188503,
+    "eval_loss": 5.2507758140563965,
+    "eval_runtime": 0.9588,
+    "eval_samples": 43,
+    "eval_samples_per_second": 44.847,
+    "eval_steps_per_second": 6.258,
+    "perplexity": 190.71416981293171,
+    "train_loss": 5.800324627635924,
+    "train_runtime": 171.8298,
+    "train_samples": 819,
+    "train_samples_per_second": 14.299,
+    "train_steps_per_second": 3.579
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_accuracy": 0.19469348746188503,
+    "eval_loss": 5.2507758140563965,
+    "eval_runtime": 0.9588,
+    "eval_samples": 43,
+    "eval_samples_per_second": 44.847,
+    "eval_steps_per_second": 6.258,
+    "perplexity": 190.71416981293171
+}

runs/Jan17_11-37-34_c6e447ad56ee/events.out.tfevents.1705491663.c6e447ad56ee.5136.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc6b24820586936ebba2bd364e7b2fc2b370ff80bb791f81f3a91d0afe89a308
+size 411

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 5.800324627635924,
+    "train_runtime": 171.8298,
+    "train_samples": 819,
+    "train_samples_per_second": 14.299,
+    "train_steps_per_second": 3.579
+}

trainer_state.json

@@ -0,0 +1,36 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 615,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.44,
+      "learning_rate": 9.34959349593496e-06,
+      "loss": 5.9409,
+      "step": 500
+    },
+    {
+      "epoch": 3.0,
+      "step": 615,
+      "total_flos": 641994522624000.0,
+      "train_loss": 5.800324627635924,
+      "train_runtime": 171.8298,
+      "train_samples_per_second": 14.299,
+      "train_steps_per_second": 3.579
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 615,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 641994522624000.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}