End of training

README.md

@@ -3,6 +3,8 @@ license: apache-2.0
 base_model: facebook/bart-base
 tags:
 - generated_from_trainer
+metrics:
+- rouge
 model-index:
 - name: bart-base-ckb
   results: []
@@ -14,6 +16,14 @@ should probably proofread and complete it, then remove this comment. -->
 # bart-base-ckb
 
 This model is a fine-tuned version of [facebook/bart-base](https://huggingface.co/facebook/bart-base) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 4.2736
+- Rouge1: 0.0
+- Rouge2: 0.0
+- Rougel: 0.0
+- Rougelsum: 0.0
+- Cer: 10.7576
+- Gen Len: 16.9735
 
 ## Model description
 

all_results.json

@@ -0,0 +1,19 @@
+{
+    "epoch": 3.0,
+    "eval_cer": 10.7576,
+    "eval_gen_len": 16.9735,
+    "eval_loss": 4.2736406326293945,
+    "eval_rouge1": 0.0,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 0.0,
+    "eval_rougeLsum": 0.0,
+    "eval_runtime": 37.6133,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 53.173,
+    "eval_steps_per_second": 0.425,
+    "train_loss": 4.75333997938368,
+    "train_runtime": 38.4881,
+    "train_samples": 10000,
+    "train_samples_per_second": 779.461,
+    "train_steps_per_second": 3.508
+}

eval_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 3.0,
+    "eval_cer": 10.7576,
+    "eval_gen_len": 16.9735,
+    "eval_loss": 4.2736406326293945,
+    "eval_rouge1": 0.0,
+    "eval_rouge2": 0.0,
+    "eval_rougeL": 0.0,
+    "eval_rougeLsum": 0.0,
+    "eval_runtime": 37.6133,
+    "eval_samples": 2000,
+    "eval_samples_per_second": 53.173,
+    "eval_steps_per_second": 0.425
+}

generation_config.json

@@ -1,5 +1,4 @@
 {
-  "_from_model_config": true,
   "bos_token_id": 0,
   "decoder_start_token_id": 2,
   "early_stopping": true,

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 3.0,
+    "train_loss": 4.75333997938368,
+    "train_runtime": 38.4881,
+    "train_samples": 10000,
+    "train_samples_per_second": 779.461,
+    "train_steps_per_second": 3.508
+}

trainer_state.json

@@ -0,0 +1,34 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 135,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 2.22,
+      "learning_rate": 1.4074074074074075e-05,
+      "loss": 4.9042,
+      "step": 100
+    },
+    {
+      "epoch": 3.0,
+      "step": 135,
+      "total_flos": 719870106009600.0,
+      "train_loss": 4.75333997938368,
+      "train_runtime": 38.4881,
+      "train_samples_per_second": 779.461,
+      "train_steps_per_second": 3.508
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 135,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "total_flos": 719870106009600.0,
+  "trial_name": null,
+  "trial_params": null
+}