Training in progress, step 5210

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1a426e02c08029d6c34920875d1cce5d7eceb8076c2b7e9236d9607a91409fb
+oid sha256:219166d066075e6987533778fd740cc6de866e1ed31000ae1c80a30ceebe58dd
 size 1470068592

runs/Jul15_17-47-02_ip-10-192-12-150/events.out.tfevents.1752601625.ip-10-192-12-150.29570.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:174e084aa0a26a421a96fda6d4b939dbd4c5e7339c8b092df5145437b9300976
+size 5280

runs/Jul15_18-11-15_ip-10-192-10-50/events.out.tfevents.1752603076.ip-10-192-10-50.2305.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f60ff32cfe77e4a59ebf598d26835f4846110aeef15a82dc59e9113b9c4b51
+size 6793

trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": null,
-  "best_metric": null,
-  "best_model_checkpoint": null,
-  "epoch": 0.19994627163526116,
+  "best_global_step": 5210,
+  "best_metric": 0.04867361780589206,
+  "best_model_checkpoint": "checkpoints/checkpoint-5210",
+  "epoch": 0.3998925432705223,
   "eval_steps": 2605,
-  "global_step": 2605,
+  "global_step": 5210,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -43,6 +43,53 @@
       "learning_rate": 4.949740629809395e-05,
       "loss": 0.1463,
       "step": 2500
+    },
+    {
+      "epoch": 0.23026442030932187,
+      "grad_norm": 0.12594294548034668,
+      "learning_rate": 4.8931895320019325e-05,
+      "loss": 0.1435,
+      "step": 3000
+    },
+    {
+      "epoch": 0.26864182369420886,
+      "grad_norm": 0.09491392970085144,
+      "learning_rate": 4.862212134330527e-05,
+      "loss": 0.1437,
+      "step": 3500
+    },
+    {
+      "epoch": 0.30701922707909585,
+      "grad_norm": 0.09572149813175201,
+      "learning_rate": 4.827420255074112e-05,
+      "loss": 0.1429,
+      "step": 4000
+    },
+    {
+      "epoch": 0.34539663046398283,
+      "grad_norm": 0.09541437774896622,
+      "learning_rate": 4.788870075885808e-05,
+      "loss": 0.1425,
+      "step": 4500
+    },
+    {
+      "epoch": 0.38377403384886977,
+      "grad_norm": 0.09861047565937042,
+      "learning_rate": 4.7466238472919244e-05,
+      "loss": 0.1419,
+      "step": 5000
+    },
+    {
+      "epoch": 0.3998925432705223,
+      "eval_avg": 0.04867361780589206,
+      "eval_cer": 0.03163900244740649,
+      "eval_der": 0.041930648121315375,
+      "eval_loss": 0.13073518872261047,
+      "eval_runtime": 1697.2219,
+      "eval_samples_per_second": 30.5,
+      "eval_steps_per_second": 0.382,
+      "eval_wer": 0.07245120284895432,
+      "step": 5210
     }
   ],
   "logging_steps": 500,
@@ -54,7 +101,7 @@
     "TrainerControl": {
       "args": {
         "should_epoch_stop": false,
-        "should_evaluate": true,
+        "should_evaluate": false,
         "should_log": false,
         "should_save": true,
         "should_training_stop": false
@@ -62,7 +109,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.810935947722752e+17,
+  "total_flos": 3.621871895445504e+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 sha256:64f63b92a15425637904ac78fddb1b4bc2f35ea4c1c8f027093790718d204e5a
+oid sha256:cc9ecd76b0bc819c93ee275a6f1cdc22d588a2c3cac72c302c4668fed5df65f6
 size 5905