End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
+- gu
 license: apache-2.0
 base_model: t5-small
 tags:
 - generated_from_trainer
 datasets:
 - opus100
+metrics:
+- bleu
 model-index:
 - name: english-guyarati
-  results: []
+  results:
+  - task:
+      name: Translation
+      type: translation
+    dataset:
+      name: opus100 en-gu
+      type: opus100
+      config: en-gu
+      split: validation
+      args: en-gu
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 48.3798
 ---
 
 <!-- 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-guyarati
 
-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-gu dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3595
+- Bleu: 48.3798
+- Gen Len: 14.5
 
 ## Model description
 

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 48.3798,
+    "eval_gen_len": 14.5,
+    "eval_loss": 0.35952749848365784,
+    "eval_runtime": 104.5017,
+    "eval_samples": 32,
+    "eval_samples_per_second": 0.306,
+    "eval_steps_per_second": 0.077,
+    "train_loss": 0.3977263656076511,
+    "train_runtime": 1126.9469,
+    "train_samples": 4974,
+    "train_samples_per_second": 13.241,
+    "train_steps_per_second": 3.312
+}

eval_results.json

@@ -0,0 +1,10 @@
+{
+    "epoch": 3.0,
+    "eval_bleu": 48.3798,
+    "eval_gen_len": 14.5,
+    "eval_loss": 0.35952749848365784,
+    "eval_runtime": 104.5017,
+    "eval_samples": 32,
+    "eval_samples_per_second": 0.306,
+    "eval_steps_per_second": 0.077
+}

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": 0.3977263656076511,
+    "train_runtime": 1126.9469,
+    "train_samples": 4974,
+    "train_samples_per_second": 13.241,
+    "train_steps_per_second": 3.312
+}

trainer_state.json

@@ -0,0 +1,70 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 3732,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4,
+      "learning_rate": 4.330117899249732e-05,
+      "loss": 0.6382,
+      "step": 500
+    },
+    {
+      "epoch": 0.8,
+      "learning_rate": 3.660235798499465e-05,
+      "loss": 0.4071,
+      "step": 1000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 2.9903536977491963e-05,
+      "loss": 0.4028,
+      "step": 1500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 2.3204715969989283e-05,
+      "loss": 0.3586,
+      "step": 2000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 1.6505894962486605e-05,
+      "loss": 0.346,
+      "step": 2500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 9.807073954983924e-06,
+      "loss": 0.3211,
+      "step": 3000
+    },
+    {
+      "epoch": 2.81,
+      "learning_rate": 3.1082529474812435e-06,
+      "loss": 0.3348,
+      "step": 3500
+    },
+    {
+      "epoch": 3.0,
+      "step": 3732,
+      "total_flos": 88369737498624.0,
+      "train_loss": 0.3977263656076511,
+      "train_runtime": 1126.9469,
+      "train_samples_per_second": 13.241,
+      "train_steps_per_second": 3.312
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 3732,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 88369737498624.0,
+  "trial_name": null,
+  "trial_params": null
+}