End of training

README.md

@@ -3,6 +3,9 @@ library_name: transformers
 license: cc-by-nc-4.0
 base_model: facebook/mms-1b-all
 tags:
+- automatic-speech-recognition
+- lozgen
+- mms
 - generated_from_trainer
 metrics:
 - wer
@@ -16,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mms-1b-lozgen-combined-model-test
 
-This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on an unknown dataset.
+This model is a fine-tuned version of [facebook/mms-1b-all](https://huggingface.co/facebook/mms-1b-all) on the LOZGEN - LOZ dataset.
 It achieves the following results on the evaluation set:
-- Loss: 2.3937
-- Wer: 0.8947
+- Loss: 2.3262
+- Wer: 0.9110
 
 ## Model description
 

adapter.loz.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:589dcf231ac2a9d0c4ddf2d17dc89ca8861deafb38e8fcff70a2fcf844778141
+size 8793408

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.326209306716919,
+    "eval_runtime": 40.2325,
+    "eval_samples": 553,
+    "eval_samples_per_second": 13.745,
+    "eval_steps_per_second": 3.455,
+    "eval_wer": 0.9109778044391121,
+    "total_flos": 7.135295863634927e+17,
+    "train_loss": 4.248325533983184,
+    "train_runtime": 272.5184,
+    "train_samples": 982,
+    "train_samples_per_second": 3.603,
+    "train_steps_per_second": 0.903
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 2.326209306716919,
+    "eval_runtime": 40.2325,
+    "eval_samples": 553,
+    "eval_samples_per_second": 13.745,
+    "eval_steps_per_second": 3.455,
+    "eval_wer": 0.9109778044391121
+}

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.0,
+    "total_flos": 7.135295863634927e+17,
+    "train_loss": 4.248325533983184,
+    "train_runtime": 272.5184,
+    "train_samples": 982,
+    "train_samples_per_second": 3.603,
+    "train_steps_per_second": 0.903
+}

trainer_state.json

@@ -0,0 +1,83 @@
+{
+  "best_metric": 2.3936636447906494,
+  "best_model_checkpoint": "/scratch/skscla001/speech/results/mms-1b-lozgen-combined-model-test/checkpoint-200",
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 246,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.4065040650406504,
+      "grad_norm": 3.2093403339385986,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 6.6301,
+      "step": 100
+    },
+    {
+      "epoch": 0.4065040650406504,
+      "eval_loss": 3.1183340549468994,
+      "eval_runtime": 40.4296,
+      "eval_samples_per_second": 13.678,
+      "eval_steps_per_second": 3.438,
+      "eval_wer": 0.9773245350929815,
+      "step": 100
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "grad_norm": 2.5653605461120605,
+      "learning_rate": 0.00010273972602739724,
+      "loss": 2.6968,
+      "step": 200
+    },
+    {
+      "epoch": 0.8130081300813008,
+      "eval_loss": 2.3936636447906494,
+      "eval_runtime": 40.491,
+      "eval_samples_per_second": 13.657,
+      "eval_steps_per_second": 3.433,
+      "eval_wer": 0.8946610677864427,
+      "step": 200
+    },
+    {
+      "epoch": 1.0,
+      "step": 246,
+      "total_flos": 7.135295863634927e+17,
+      "train_loss": 4.248325533983184,
+      "train_runtime": 272.5184,
+      "train_samples_per_second": 3.603,
+      "train_steps_per_second": 0.903
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 246,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 7.135295863634927e+17,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}