Training in progress, step 12848

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5fd5f2647fde284fadd8fe1b84d2385e1d8557c192a97d1bcb3b84b535022e3
+oid sha256:b4b68629a4e7fbfde0f1b640d08dd2775f2c2f532f4da2add4ee14e34b66f168
 size 667849236

runs/May05_22-15-18_ip-10-192-11-107/events.out.tfevents.1746483320.ip-10-192-11-107.1742.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c0c1ed8c78331621c33d91080f46daa3bfc44db1cd7f7208e0e1b80939a9db4
-size 9425
+oid sha256:b6506388d410ea78c717e0b2657489d9303d520fac8384a56e4475436b96e55e
+size 9847

runs/May06_08-32-58_ip-10-192-12-5/events.out.tfevents.1746520379.ip-10-192-12-5.1614.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15f75329ed85e5259d9f5137f58b6204f020a8aea0824b5596178ecc4190cfab
+size 7028

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 11242,
-  "best_metric": 0.7068964281422255,
-  "best_model_checkpoint": "checkpoints/checkpoint-11242",
-  "epoch": 1.749970813713663,
+  "best_global_step": 12848,
+  "best_metric": 0.706664474285978,
+  "best_model_checkpoint": "checkpoints/checkpoint-12848",
+  "epoch": 1.9999610849515508,
   "eval_steps": 1606,
-  "global_step": 11242,
+  "global_step": 12848,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -246,6 +246,39 @@
       "eval_steps_per_second": 1.723,
       "eval_wer": 0.6729760634887532,
       "step": 11242
+    },
+    {
+      "epoch": 1.7901311437132739,
+      "grad_norm": 0.030866818502545357,
+      "learning_rate": 4.9978063925651226e-05,
+      "loss": 0.0457,
+      "step": 11500
+    },
+    {
+      "epoch": 1.8679612406117445,
+      "grad_norm": 0.029339410364627838,
+      "learning_rate": 4.980989359026424e-05,
+      "loss": 0.0451,
+      "step": 12000
+    },
+    {
+      "epoch": 1.9457913375102152,
+      "grad_norm": 0.02953779138624668,
+      "learning_rate": 4.94769940363958e-05,
+      "loss": 0.0439,
+      "step": 12500
+    },
+    {
+      "epoch": 1.9999610849515508,
+      "eval_avg": 0.706664474285978,
+      "eval_cer": 0.6538952007882788,
+      "eval_der": 0.7938883608526655,
+      "eval_loss": 0.0344935841858387,
+      "eval_runtime": 304.0677,
+      "eval_samples_per_second": 446.358,
+      "eval_steps_per_second": 1.746,
+      "eval_wer": 0.6722098612169899,
+      "step": 12848
     }
   ],
   "logging_steps": 500,
@@ -265,7 +298,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.774232894949294e+17,
+  "total_flos": 1.0027694737084908e+18,
   "train_batch_size": 256,
   "trial_name": null,
   "trial_params": null

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13cd8f43a255510665b26c3fb2a6d437f327d011dfaac3168ef02538a3bb5da9
-size 5905
+oid sha256:17c2aac82a2d734eb14ae276b8d6dd7dc2382b632edb33fe02e78d4676bca897
+size 5841