End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 15.0,
+    "eval_loss": 0.4012770652770996,
+    "eval_runtime": 477.7855,
+    "eval_samples": 10859,
+    "eval_samples_per_second": 22.728,
+    "eval_steps_per_second": 0.356,
+    "eval_wer": 1.0929595993888983,
+    "train_loss": 1.7017262231735957,
+    "train_runtime": 141338.6512,
+    "train_samples": 16111,
+    "train_samples_per_second": 1.71,
+    "train_steps_per_second": 0.009
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 15.0,
+    "eval_loss": 0.4012770652770996,
+    "eval_runtime": 477.7855,
+    "eval_samples": 10859,
+    "eval_samples_per_second": 22.728,
+    "eval_steps_per_second": 0.356,
+    "eval_wer": 1.0929595993888983
+}

runs/Mar10_16-57-33_mlp14/events.out.tfevents.1710228527.mlp14.1591632.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:556d7b29d575850fad006148a9e43f09d274e5f355299bdea8ec76707d7b376e
+size 406

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 15.0,
+    "train_loss": 1.7017262231735957,
+    "train_runtime": 141338.6512,
+    "train_samples": 16111,
+    "train_samples_per_second": 1.71,
+    "train_steps_per_second": 0.009
+}

trainer_state.json

@@ -0,0 +1,145 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 15.0,
+  "global_step": 1260,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.19,
+      "eval_loss": 4.574927806854248,
+      "eval_runtime": 492.4632,
+      "eval_samples_per_second": 22.05,
+      "eval_steps_per_second": 0.345,
+      "eval_wer": 1.0,
+      "step": 100
+    },
+    {
+      "epoch": 2.38,
+      "eval_loss": 3.2543928623199463,
+      "eval_runtime": 477.4917,
+      "eval_samples_per_second": 22.742,
+      "eval_steps_per_second": 0.356,
+      "eval_wer": 1.0,
+      "step": 200
+    },
+    {
+      "epoch": 3.57,
+      "eval_loss": 3.110656261444092,
+      "eval_runtime": 470.1018,
+      "eval_samples_per_second": 23.099,
+      "eval_steps_per_second": 0.362,
+      "eval_wer": 1.000137922254286,
+      "step": 300
+    },
+    {
+      "epoch": 4.76,
+      "eval_loss": 0.9151943922042847,
+      "eval_runtime": 469.7177,
+      "eval_samples_per_second": 23.118,
+      "eval_steps_per_second": 0.362,
+      "eval_wer": 1.017081140723137,
+      "step": 400
+    },
+    {
+      "epoch": 5.95,
+      "learning_rate": 0.0003,
+      "loss": 3.9561,
+      "step": 500
+    },
+    {
+      "epoch": 5.95,
+      "eval_loss": 0.6422096490859985,
+      "eval_runtime": 477.7033,
+      "eval_samples_per_second": 22.732,
+      "eval_steps_per_second": 0.356,
+      "eval_wer": 1.059041334238669,
+      "step": 500
+    },
+    {
+      "epoch": 7.14,
+      "eval_loss": 0.49003028869628906,
+      "eval_runtime": 424.1123,
+      "eval_samples_per_second": 25.604,
+      "eval_steps_per_second": 0.401,
+      "eval_wer": 1.0866682227126125,
+      "step": 600
+    },
+    {
+      "epoch": 8.33,
+      "eval_loss": 0.4251333475112915,
+      "eval_runtime": 495.8179,
+      "eval_samples_per_second": 21.901,
+      "eval_steps_per_second": 0.343,
+      "eval_wer": 1.095516465795281,
+      "step": 700
+    },
+    {
+      "epoch": 9.52,
+      "eval_loss": 0.4232262969017029,
+      "eval_runtime": 527.1122,
+      "eval_samples_per_second": 20.601,
+      "eval_steps_per_second": 0.323,
+      "eval_wer": 1.1464522152435919,
+      "step": 800
+    },
+    {
+      "epoch": 10.71,
+      "eval_loss": 0.4133465588092804,
+      "eval_runtime": 479.4028,
+      "eval_samples_per_second": 22.651,
+      "eval_steps_per_second": 0.355,
+      "eval_wer": 1.1194300628076728,
+      "step": 900
+    },
+    {
+      "epoch": 11.9,
+      "learning_rate": 0.00010263157894736841,
+      "loss": 0.2637,
+      "step": 1000
+    },
+    {
+      "epoch": 11.9,
+      "eval_loss": 0.3940434157848358,
+      "eval_runtime": 489.7721,
+      "eval_samples_per_second": 22.172,
+      "eval_steps_per_second": 0.347,
+      "eval_wer": 1.13066542182991,
+      "step": 1000
+    },
+    {
+      "epoch": 13.1,
+      "eval_loss": 0.3943102955818176,
+      "eval_runtime": 478.1637,
+      "eval_samples_per_second": 22.71,
+      "eval_steps_per_second": 0.356,
+      "eval_wer": 1.0963758275335258,
+      "step": 1100
+    },
+    {
+      "epoch": 14.29,
+      "eval_loss": 0.3974030613899231,
+      "eval_runtime": 476.6101,
+      "eval_samples_per_second": 22.784,
+      "eval_steps_per_second": 0.357,
+      "eval_wer": 1.0893630113732813,
+      "step": 1200
+    },
+    {
+      "epoch": 15.0,
+      "step": 1260,
+      "total_flos": 2.676196803813189e+19,
+      "train_loss": 1.7017262231735957,
+      "train_runtime": 141338.6512,
+      "train_samples_per_second": 1.71,
+      "train_steps_per_second": 0.009
+    }
+  ],
+  "max_steps": 1260,
+  "num_train_epochs": 15,
+  "total_flos": 2.676196803813189e+19,
+  "trial_name": null,
+  "trial_params": null
+}