End of training

all_results.json

@@ -0,0 +1,14 @@
+{
+    "epoch": 1.77,
+    "eval_loss": 3.6638808250427246,
+    "eval_runtime": 149.0121,
+    "eval_samples": 99,
+    "eval_samples_per_second": 0.664,
+    "eval_steps_per_second": 0.047,
+    "eval_wer": 1.216391085549964,
+    "train_loss": 0.2760725998878479,
+    "train_runtime": 1580.9218,
+    "train_samples": 1808,
+    "train_samples_per_second": 2.024,
+    "train_steps_per_second": 0.063
+}

eval_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 1.77,
+    "eval_loss": 3.6638808250427246,
+    "eval_runtime": 149.0121,
+    "eval_samples": 99,
+    "eval_samples_per_second": 0.664,
+    "eval_steps_per_second": 0.047,
+    "eval_wer": 1.216391085549964
+}

runs/Nov10_18-38-51_cla-99m41v9m/events.out.tfevents.1731284227.cla-99m41v9m.57958.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:177d2401a6972a9830d09e880bda4ace2d9f73a9b52b1eac15ca67c2eb326ae6
+size 400

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.77,
+    "train_loss": 0.2760725998878479,
+    "train_runtime": 1580.9218,
+    "train_samples": 1808,
+    "train_samples_per_second": 2.024,
+    "train_steps_per_second": 0.063
+}

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7699115044247788,
+  "eval_steps": 50,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.44,
+      "grad_norm": 9.63073444366455,
+      "learning_rate": 5e-06,
+      "loss": 0.7305,
+      "step": 25
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 2.945356607437134,
+      "learning_rate": 1e-05,
+      "loss": 0.1912,
+      "step": 50
+    },
+    {
+      "epoch": 0.88,
+      "eval_loss": 3.5328922271728516,
+      "eval_runtime": 111.5535,
+      "eval_samples_per_second": 0.887,
+      "eval_steps_per_second": 0.063,
+      "eval_wer": 1.2171099928109275,
+      "step": 50
+    },
+    {
+      "epoch": 1.33,
+      "grad_norm": 2.5617167949676514,
+      "learning_rate": 5e-06,
+      "loss": 0.0998,
+      "step": 75
+    },
+    {
+      "epoch": 1.77,
+      "grad_norm": 1.9796466827392578,
+      "learning_rate": 0.0,
+      "loss": 0.0828,
+      "step": 100
+    },
+    {
+      "epoch": 1.77,
+      "eval_loss": 3.6638808250427246,
+      "eval_runtime": 106.6363,
+      "eval_samples_per_second": 0.928,
+      "eval_steps_per_second": 0.066,
+      "eval_wer": 1.216391085549964,
+      "step": 100
+    },
+    {
+      "epoch": 1.77,
+      "step": 100,
+      "total_flos": 9.23473281024e+17,
+      "train_loss": 0.2760725998878479,
+      "train_runtime": 1580.9218,
+      "train_samples_per_second": 2.024,
+      "train_steps_per_second": 0.063
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 100,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 50,
+  "total_flos": 9.23473281024e+17,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}