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
+- bigcgen
+- mms
 - generated_from_trainer
 metrics:
 - wer
@@ -16,10 +19,10 @@ should probably proofread and complete it, then remove this comment. -->
 
 # mms-1b-bigcgen-combined-20hrs-model
 
-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 BIGCGEN - BEM dataset.
 It achieves the following results on the evaluation set:
 - Loss: inf
-- Wer: 0.6355
+- Wer: 0.6353
 
 ## Model description
 

adapter.bem.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95bdb59381498cf58d19e620958ee9f003e4e3987836e90a4f7af2a96449b217
+size 8793408

all_results.json

@@ -0,0 +1,15 @@
+{
+    "epoch": 0.3048780487804878,
+    "eval_loss": Infinity,
+    "eval_runtime": 62.0412,
+    "eval_samples": 916,
+    "eval_samples_per_second": 14.764,
+    "eval_steps_per_second": 3.691,
+    "eval_wer": 0.6353339560952825,
+    "total_flos": 2.0131619559286019e+18,
+    "train_loss": 7.521956939697265,
+    "train_runtime": 771.8174,
+    "train_samples": 10493,
+    "train_samples_per_second": 407.856,
+    "train_steps_per_second": 50.997
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.3048780487804878,
+    "eval_loss": Infinity,
+    "eval_runtime": 62.0412,
+    "eval_samples": 916,
+    "eval_samples_per_second": 14.764,
+    "eval_steps_per_second": 3.691,
+    "eval_wer": 0.6353339560952825
+}

runs/Dec27_12-04-28_srvrocgpu011.uct.ac.za/events.out.tfevents.1735295104.srvrocgpu011.uct.ac.za

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59a2aa162a98ce3f60dad17b63a5cff63e815d4f9136b340a32d64060dfa462e
+size 40

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.3048780487804878,
+    "total_flos": 2.0131619559286019e+18,
+    "train_loss": 7.521956939697265,
+    "train_runtime": 771.8174,
+    "train_samples": 10493,
+    "train_samples_per_second": 407.856,
+    "train_steps_per_second": 50.997
+}

trainer_state.json

@@ -0,0 +1,115 @@
+{
+  "best_metric": Infinity,
+  "best_model_checkpoint": null,
+  "epoch": 0.3048780487804878,
+  "eval_steps": 100,
+  "global_step": 400,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07621951219512195,
+      "grad_norm": 6.622852325439453,
+      "learning_rate": 0.00028799999999999995,
+      "loss": 14.6532,
+      "step": 100
+    },
+    {
+      "epoch": 0.07621951219512195,
+      "eval_loss": Infinity,
+      "eval_runtime": 61.6254,
+      "eval_samples_per_second": 14.864,
+      "eval_steps_per_second": 3.716,
+      "eval_wer": 1.017865483418963,
+      "step": 100
+    },
+    {
+      "epoch": 0.1524390243902439,
+      "grad_norm": 5.716004848480225,
+      "learning_rate": 0.0002992664289353031,
+      "loss": 6.1697,
+      "step": 200
+    },
+    {
+      "epoch": 0.1524390243902439,
+      "eval_loss": Infinity,
+      "eval_runtime": 61.1204,
+      "eval_samples_per_second": 14.987,
+      "eval_steps_per_second": 3.747,
+      "eval_wer": 1.010042036431574,
+      "step": 200
+    },
+    {
+      "epoch": 0.22865853658536586,
+      "grad_norm": 5.097488880157471,
+      "learning_rate": 0.00029850229240957715,
+      "loss": 5.3981,
+      "step": 300
+    },
+    {
+      "epoch": 0.22865853658536586,
+      "eval_loss": Infinity,
+      "eval_runtime": 60.9998,
+      "eval_samples_per_second": 15.016,
+      "eval_steps_per_second": 3.754,
+      "eval_wer": 1.0266230733302195,
+      "step": 300
+    },
+    {
+      "epoch": 0.3048780487804878,
+      "grad_norm": 5.512605667114258,
+      "learning_rate": 0.0002977381558838512,
+      "loss": 3.8668,
+      "step": 400
+    },
+    {
+      "epoch": 0.3048780487804878,
+      "eval_loss": Infinity,
+      "eval_runtime": 61.1096,
+      "eval_samples_per_second": 14.989,
+      "eval_steps_per_second": 3.747,
+      "eval_wer": 0.635450723960766,
+      "step": 400
+    },
+    {
+      "epoch": 0.3048780487804878,
+      "step": 400,
+      "total_flos": 2.0131619559286019e+18,
+      "train_loss": 7.521956939697265,
+      "train_runtime": 771.8174,
+      "train_samples_per_second": 407.856,
+      "train_steps_per_second": 50.997
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 39360,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 30,
+  "save_steps": 400,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 3,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 3
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0131619559286019e+18,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}