End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: google/mt5-small
 tags:
 - generated_from_trainer
+datasets:
+- preethiprabha2023/trial
 model-index:
 - name: debug_seq2seq_trial
   results: []
@@ -13,7 +15,9 @@ should probably proofread and complete it, then remove this comment. -->
 
 # debug_seq2seq_trial
 
-This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on an unknown dataset.
+This model is a fine-tuned version of [google/mt5-small](https://huggingface.co/google/mt5-small) on the preethiprabha2023/trial dataset.
+It achieves the following results on the evaluation set:
+- Loss: 15.5520
 
 ## Model description
 

all_results.json

@@ -0,0 +1,13 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 15.551960945129395,
+    "eval_runtime": 0.8689,
+    "eval_samples": 240,
+    "eval_samples_per_second": 276.21,
+    "eval_steps_per_second": 34.526,
+    "train_loss": 19.692240905761718,
+    "train_runtime": 29.0912,
+    "train_samples": 959,
+    "train_samples_per_second": 65.931,
+    "train_steps_per_second": 5.5
+}

eval_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "eval_loss": 15.551960945129395,
+    "eval_runtime": 0.8689,
+    "eval_samples": 240,
+    "eval_samples_per_second": 276.21,
+    "eval_steps_per_second": 34.526
+}

runs/Feb21_07-14-12_nxrnzzdtr6/events.out.tfevents.1708499723.nxrnzzdtr6.592.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:488106f8780ceda345edecf95a01f9d211a6c83a9d628db2ba959cfac8654067
+size 311

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "train_loss": 19.692240905761718,
+    "train_runtime": 29.0912,
+    "train_samples": 959,
+    "train_samples_per_second": 65.931,
+    "train_steps_per_second": 5.5
+}

trainer_state.json

@@ -0,0 +1,30 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 160,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.0,
+      "step": 160,
+      "total_flos": 760606430330880.0,
+      "train_loss": 19.692240905761718,
+      "train_runtime": 29.0912,
+      "train_samples_per_second": 65.931,
+      "train_steps_per_second": 5.5
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 160,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "total_flos": 760606430330880.0,
+  "train_batch_size": 12,
+  "trial_name": null,
+  "trial_params": null
+}