End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
+- es
 license: apache-2.0
 base_model: t5-small
 tags:
 - generated_from_trainer
 datasets:
 - opus100
+metrics:
+- bleu
 model-index:
 - name: english-spanish
-  results: []
+  results:
+  - task:
+      name: Translation
+      type: translation
+    dataset:
+      name: opus100 en-es
+      type: opus100
+      config: en-es
+      split: validation
+      args: en-es
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 4.7921
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +33,11 @@ should probably proofread and complete it, then remove this comment. -->
 
 # english-spanish
 
-This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 dataset.
+This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus100 en-es dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.9593
+- Bleu: 4.7921
+- Gen Len: 46.875
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 4.7921,
+    "eval_gen_len": 46.875,
+    "eval_loss": 0.959338903427124,
+    "eval_runtime": 168.4301,
+    "eval_samples": 8,
+    "eval_samples_per_second": 0.047,
+    "eval_steps_per_second": 0.012,
+    "train_loss": 1.504677425346778,
+    "train_runtime": 1613.5134,
+    "train_samples": 3907,
+    "train_samples_per_second": 7.264,
+    "train_steps_per_second": 1.817
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 4.7921,
+    "eval_gen_len": 46.875,
+    "eval_loss": 0.959338903427124,
+    "eval_runtime": 168.4301,
+    "eval_samples": 8,
+    "eval_samples_per_second": 0.047,
+    "eval_steps_per_second": 0.012
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "decoder_start_token_id": 0,
   "eos_token_id": 1,
   "pad_token_id": 0,

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 1.504677425346778,
+    "train_runtime": 1613.5134,
+    "train_samples": 3907,
+    "train_samples_per_second": 7.264,
+    "train_steps_per_second": 1.817
+}

trainer_state.json

@@ -0,0 +1,58 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 2931,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.14704878880928e-05,
+      "loss": 1.6585,
+      "step": 500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.294097577618561e-05,
+      "loss": 1.534,
+      "step": 1000
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.4411463664278406e-05,
+      "loss": 1.504,
+      "step": 1500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.5881951552371206e-05,
+      "loss": 1.4679,
+      "step": 2000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.3524394404640055e-06,
+      "loss": 1.442,
+      "step": 2500
+    },
+    {
+      "epoch": 3.0,
+      "step": 2931,
+      "total_flos": 118513687363584.0,
+      "train_loss": 1.504677425346778,
+      "train_runtime": 1613.5134,
+      "train_samples_per_second": 7.264,
+      "train_steps_per_second": 1.817
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 2931,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 118513687363584.0,
+  "trial_name": null,
+  "trial_params": null
+}