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: 15.8604
 ---
 
 <!-- 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: 1.1056
+- Bleu: 15.8604
+- Gen Len: 40.6875
 
 ## Model description
 

all_results.json

@@ -1,15 +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_bleu": 15.8604,
+    "eval_gen_len": 40.6875,
+    "eval_loss": 1.1056389808654785,
+    "eval_runtime": 217.338,
+    "eval_samples": 16,
+    "eval_samples_per_second": 0.074,
+    "eval_steps_per_second": 0.018,
+    "train_loss": 1.430499308184933,
+    "train_runtime": 3735.0404,
+    "train_samples": 7813,
+    "train_samples_per_second": 6.275,
+    "train_steps_per_second": 1.569
 }

eval_results.json

@@ -1,10 +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
+    "eval_bleu": 15.8604,
+    "eval_gen_len": 40.6875,
+    "eval_loss": 1.1056389808654785,
+    "eval_runtime": 217.338,
+    "eval_samples": 16,
+    "eval_samples_per_second": 0.074,
+    "eval_steps_per_second": 0.018
 }

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

@@ -1,8 +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
+    "train_loss": 1.430499308184933,
+    "train_runtime": 3735.0404,
+    "train_samples": 7813,
+    "train_samples_per_second": 6.275,
+    "train_steps_per_second": 1.569
 }

trainer_state.json

@@ -3,56 +3,92 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 2931,
+  "global_step": 5862,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.57352439440464e-05,
+      "loss": 1.6481,
+      "step": 500
+    },
     {
       "epoch": 0.51,
       "learning_rate": 4.14704878880928e-05,
-      "loss": 1.6585,
-      "step": 500
+      "loss": 1.5182,
+      "step": 1000
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.72057318321392e-05,
+      "loss": 1.478,
+      "step": 1500
     },
     {
       "epoch": 1.02,
       "learning_rate": 3.294097577618561e-05,
-      "loss": 1.534,
-      "step": 1000
+      "loss": 1.4709,
+      "step": 2000
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8676219720232007e-05,
+      "loss": 1.4008,
+      "step": 2500
     },
     {
       "epoch": 1.54,
       "learning_rate": 2.4411463664278406e-05,
-      "loss": 1.504,
-      "step": 1500
+      "loss": 1.4038,
+      "step": 3000
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.0146707608324806e-05,
+      "loss": 1.3903,
+      "step": 3500
     },
     {
       "epoch": 2.05,
       "learning_rate": 1.5881951552371206e-05,
-      "loss": 1.4679,
-      "step": 2000
+      "loss": 1.4114,
+      "step": 4000
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.1617195496417605e-05,
+      "loss": 1.3706,
+      "step": 4500
     },
     {
       "epoch": 2.56,
       "learning_rate": 7.3524394404640055e-06,
-      "loss": 1.442,
-      "step": 2500
+      "loss": 1.3448,
+      "step": 5000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.087683384510406e-06,
+      "loss": 1.3314,
+      "step": 5500
     },
     {
       "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
+      "step": 5862,
+      "total_flos": 237909211152384.0,
+      "train_loss": 1.430499308184933,
+      "train_runtime": 3735.0404,
+      "train_samples_per_second": 6.275,
+      "train_steps_per_second": 1.569
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2931,
+  "max_steps": 5862,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 118513687363584.0,
+  "total_flos": 237909211152384.0,
   "trial_name": null,
   "trial_params": null
 }