End of training

README.md

@@ -1,13 +1,31 @@
 ---
+language:
+- en
+- he
 license: apache-2.0
 base_model: t5-small
 tags:
 - generated_from_trainer
 datasets:
 - opus100
+metrics:
+- bleu
 model-index:
 - name: english-hebrew
-  results: []
+  results:
+  - task:
+      name: Translation
+      type: translation
+    dataset:
+      name: opus100 en-he
+      type: opus100
+      config: en-he
+      split: validation
+      args: en-he
+    metrics:
+    - name: Bleu
+      type: bleu
+      value: 0.0
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -15,7 +33,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # english-hebrew
 
-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-he dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3630
+- Bleu: 0.0
 
 ## Model description
 

all_results.json

@@ -1,14 +1,14 @@
 {
     "epoch": 3.0,
     "eval_bleu": 0.0,
-    "eval_loss": 0.3593257963657379,
-    "eval_runtime": 63.0119,
-    "eval_samples": 4,
-    "eval_samples_per_second": 0.063,
-    "eval_steps_per_second": 0.016,
-    "train_loss": 0.2859099426477558,
-    "train_runtime": 448.5269,
-    "train_samples": 1954,
-    "train_samples_per_second": 13.069,
-    "train_steps_per_second": 3.271
+    "eval_loss": 0.36301419138908386,
+    "eval_runtime": 93.3757,
+    "eval_samples": 8,
+    "eval_samples_per_second": 0.086,
+    "eval_steps_per_second": 0.021,
+    "train_loss": 0.2741566179393298,
+    "train_runtime": 830.8843,
+    "train_samples": 3907,
+    "train_samples_per_second": 14.107,
+    "train_steps_per_second": 3.528
 }

eval_results.json

@@ -1,9 +1,9 @@
 {
     "epoch": 3.0,
     "eval_bleu": 0.0,
-    "eval_loss": 0.3593257963657379,
-    "eval_runtime": 63.0119,
-    "eval_samples": 4,
-    "eval_samples_per_second": 0.063,
-    "eval_steps_per_second": 0.016
+    "eval_loss": 0.36301419138908386,
+    "eval_runtime": 93.3757,
+    "eval_samples": 8,
+    "eval_samples_per_second": 0.086,
+    "eval_steps_per_second": 0.021
 }

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": 0.2859099426477558,
-    "train_runtime": 448.5269,
-    "train_samples": 1954,
-    "train_samples_per_second": 13.069,
-    "train_steps_per_second": 3.271
+    "train_loss": 0.2741566179393298,
+    "train_runtime": 830.8843,
+    "train_samples": 3907,
+    "train_samples_per_second": 14.107,
+    "train_steps_per_second": 3.528
 }

trainer_state.json

@@ -3,38 +3,56 @@
   "best_model_checkpoint": null,
   "epoch": 3.0,
   "eval_steps": 500,
-  "global_step": 1467,
+  "global_step": 2931,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 1.02,
-      "learning_rate": 3.2958418541240625e-05,
-      "loss": 0.3262,
+      "epoch": 0.51,
+      "learning_rate": 4.14704878880928e-05,
+      "loss": 0.3586,
       "step": 500
     },
     {
-      "epoch": 2.04,
-      "learning_rate": 1.5916837082481257e-05,
-      "loss": 0.269,
+      "epoch": 1.02,
+      "learning_rate": 3.294097577618561e-05,
+      "loss": 0.2728,
       "step": 1000
     },
+    {
+      "epoch": 1.54,
+      "learning_rate": 2.4411463664278406e-05,
+      "loss": 0.2668,
+      "step": 1500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 1.5881951552371206e-05,
+      "loss": 0.2508,
+      "step": 2000
+    },
+    {
+      "epoch": 2.56,
+      "learning_rate": 7.3524394404640055e-06,
+      "loss": 0.2471,
+      "step": 2500
+    },
     {
       "epoch": 3.0,
-      "step": 1467,
-      "total_flos": 37853410099200.0,
-      "train_loss": 0.2859099426477558,
-      "train_runtime": 448.5269,
-      "train_samples_per_second": 13.069,
-      "train_steps_per_second": 3.271
+      "step": 2931,
+      "total_flos": 74769472487424.0,
+      "train_loss": 0.2741566179393298,
+      "train_runtime": 830.8843,
+      "train_samples_per_second": 14.107,
+      "train_steps_per_second": 3.528
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1467,
+  "max_steps": 2931,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 37853410099200.0,
+  "total_flos": 74769472487424.0,
   "trial_name": null,
   "trial_params": null
 }