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-2
-  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: 16.7134
 ---
 
 <!-- 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-2
 
-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: 1.0854
+- Bleu: 16.7134
+- Gen Len: 43.5938
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 16.7134,
+    "eval_gen_len": 43.5938,
+    "eval_loss": 1.0853724479675293,
+    "eval_runtime": 260.8335,
+    "eval_samples": 32,
+    "eval_samples_per_second": 0.123,
+    "eval_steps_per_second": 0.031,
+    "train_loss": 1.3449153543769596,
+    "train_runtime": 6820.3855,
+    "train_samples": 15625,
+    "train_samples_per_second": 6.873,
+    "train_steps_per_second": 1.719
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 16.7134,
+    "eval_gen_len": 43.5938,
+    "eval_loss": 1.0853724479675293,
+    "eval_runtime": 260.8335,
+    "eval_samples": 32,
+    "eval_samples_per_second": 0.123,
+    "eval_steps_per_second": 0.031
+}

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": 1.3449153543769596,
+    "train_runtime": 6820.3855,
+    "train_samples": 15625,
+    "train_samples_per_second": 6.873,
+    "train_steps_per_second": 1.719
+}

trainer_state.json

@@ -0,0 +1,166 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 11721,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.13,
+      "learning_rate": 4.7867076188038565e-05,
+      "loss": 1.6317,
+      "step": 500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 4.573415237607713e-05,
+      "loss": 1.5379,
+      "step": 1000
+    },
+    {
+      "epoch": 0.38,
+      "learning_rate": 4.360122856411569e-05,
+      "loss": 1.4835,
+      "step": 1500
+    },
+    {
+      "epoch": 0.51,
+      "learning_rate": 4.146830475215426e-05,
+      "loss": 1.4562,
+      "step": 2000
+    },
+    {
+      "epoch": 0.64,
+      "learning_rate": 3.933538094019282e-05,
+      "loss": 1.4406,
+      "step": 2500
+    },
+    {
+      "epoch": 0.77,
+      "learning_rate": 3.720245712823138e-05,
+      "loss": 1.389,
+      "step": 3000
+    },
+    {
+      "epoch": 0.9,
+      "learning_rate": 3.506953331626994e-05,
+      "loss": 1.3768,
+      "step": 3500
+    },
+    {
+      "epoch": 1.02,
+      "learning_rate": 3.2936609504308506e-05,
+      "loss": 1.3655,
+      "step": 4000
+    },
+    {
+      "epoch": 1.15,
+      "learning_rate": 3.0803685692347076e-05,
+      "loss": 1.3485,
+      "step": 4500
+    },
+    {
+      "epoch": 1.28,
+      "learning_rate": 2.8670761880385632e-05,
+      "loss": 1.331,
+      "step": 5000
+    },
+    {
+      "epoch": 1.41,
+      "learning_rate": 2.6537838068424198e-05,
+      "loss": 1.3262,
+      "step": 5500
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.440491425646276e-05,
+      "loss": 1.3105,
+      "step": 6000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 2.2271990444501324e-05,
+      "loss": 1.3318,
+      "step": 6500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 2.0139066632539887e-05,
+      "loss": 1.2788,
+      "step": 7000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 1.800614282057845e-05,
+      "loss": 1.3068,
+      "step": 7500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.5873219008617013e-05,
+      "loss": 1.2698,
+      "step": 8000
+    },
+    {
+      "epoch": 2.18,
+      "learning_rate": 1.3740295196655576e-05,
+      "loss": 1.2705,
+      "step": 8500
+    },
+    {
+      "epoch": 2.3,
+      "learning_rate": 1.1607371384694139e-05,
+      "loss": 1.264,
+      "step": 9000
+    },
+    {
+      "epoch": 2.43,
+      "learning_rate": 9.474447572732703e-06,
+      "loss": 1.2429,
+      "step": 9500
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.3415237607712656e-06,
+      "loss": 1.2518,
+      "step": 10000
+    },
+    {
+      "epoch": 2.69,
+      "learning_rate": 5.2085999488098285e-06,
+      "loss": 1.2374,
+      "step": 10500
+    },
+    {
+      "epoch": 2.82,
+      "learning_rate": 3.075676136848392e-06,
+      "loss": 1.273,
+      "step": 11000
+    },
+    {
+      "epoch": 2.94,
+      "learning_rate": 9.42752324886955e-07,
+      "loss": 1.2559,
+      "step": 11500
+    },
+    {
+      "epoch": 3.0,
+      "step": 11721,
+      "total_flos": 468561246879744.0,
+      "train_loss": 1.3449153543769596,
+      "train_runtime": 6820.3855,
+      "train_samples_per_second": 6.873,
+      "train_steps_per_second": 1.719
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 11721,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 468561246879744.0,
+  "trial_name": null,
+  "trial_params": null
+}