Training in progress, step 10420

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63eea8c40b61bba355a0097c91aec36f1d47d21024da7a0b696a224d7f332070
+oid sha256:b624a6ea8d6d1418579f888925098269918a7ce6b105f6ab042eec442ec455b8
 size 1470068592

runs/Jul16_10-37-58_ip-10-192-10-108/events.out.tfevents.1752662280.ip-10-192-10-108.2114.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:905d5d8111debb3d686d2323d92f6a85d8d86a7b195825485f295465b1c839b7
+size 6794

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 7815,
-  "best_metric": 0.047643108039959726,
-  "best_model_checkpoint": "checkpoints/checkpoint-7815",
-  "epoch": 0.5998388149057835,
+  "best_global_step": 10420,
+  "best_metric": 0.046850736209360914,
+  "best_model_checkpoint": "checkpoints/checkpoint-10420",
+  "epoch": 0.7997850865410446,
   "eval_steps": 2605,
-  "global_step": 7815,
+  "global_step": 10420,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,6 +137,53 @@
       "eval_steps_per_second": 0.377,
       "eval_wer": 0.07081328706403231,
       "step": 7815
+    },
+    {
+      "epoch": 0.6140384541581917,
+      "grad_norm": 0.10269790142774582,
+      "learning_rate": 4.905050311075738e-05,
+      "loss": 0.139,
+      "step": 8000
+    },
+    {
+      "epoch": 0.6524158575430786,
+      "grad_norm": 0.08717872947454453,
+      "learning_rate": 4.8756902702886506e-05,
+      "loss": 0.1374,
+      "step": 8500
+    },
+    {
+      "epoch": 0.6907932609279657,
+      "grad_norm": 0.09375835955142975,
+      "learning_rate": 4.842493983528561e-05,
+      "loss": 0.1381,
+      "step": 9000
+    },
+    {
+      "epoch": 0.7291706643128526,
+      "grad_norm": 0.09731540083885193,
+      "learning_rate": 4.805515055898372e-05,
+      "loss": 0.1365,
+      "step": 9500
+    },
+    {
+      "epoch": 0.7675480676977395,
+      "grad_norm": 0.13318291306495667,
+      "learning_rate": 4.764813200679724e-05,
+      "loss": 0.1367,
+      "step": 10000
+    },
+    {
+      "epoch": 0.7997850865410446,
+      "eval_avg": 0.046850736209360914,
+      "eval_cer": 0.030717447084398133,
+      "eval_der": 0.040079204095426355,
+      "eval_loss": 0.12388349324464798,
+      "eval_runtime": 1688.4755,
+      "eval_samples_per_second": 30.658,
+      "eval_steps_per_second": 0.384,
+      "eval_wer": 0.06975555744825825,
+      "step": 10420
     }
   ],
   "logging_steps": 500,
@@ -156,7 +203,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.432807843168256e+17,
+  "total_flos": 7.243743790891008e+17,
   "train_batch_size": 80,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc9ecd76b0bc819c93ee275a6f1cdc22d588a2c3cac72c302c4668fed5df65f6
+oid sha256:61bada019f1b6e6889591c3c2feece3654269f05a9a603962c9ef4b6d6acb215
 size 5905