Training in progress, step 10, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d74923e6750ce3af92d86f86fc7f6d30ad9efa7c11c394f23c066b2da5e4f526
+oid sha256:3c92c54ae0107bcb9111ebd51df85637e4bac183dad2512154a7f3eb82998e26
 size 4993448880

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390ee3b40845be964b720275542a4edda04350734e4f83d7c0297bb0c7a64411
+oid sha256:38796f19c3dcb30ddbd8dec0ee8f8fcaa700cf01ae7942c175d63f3377efaccd
 size 1180663192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ff490a02658f8f152d0233e76caa37a0ff1931dcd33092964ff663f60902657
+oid sha256:d20bc8935001bab15a6d9eb845f9e2af4c58b17b8509bd446fc0c990aff6379e
 size 3137572976

last-checkpoint/trainer_state.json

@@ -10,116 +10,116 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "grad_norm": 19.29960060119629,
+      "grad_norm": 19.299592971801758,
       "learning_rate": 1e-06,
       "loss": 1.1744,
       "step": 1
     },
     {
       "epoch": 2.0,
-      "grad_norm": 19.299541473388672,
+      "grad_norm": 19.29966163635254,
       "learning_rate": 2e-06,
       "loss": 1.1744,
       "step": 2
     },
     {
       "epoch": 2.0,
-      "eval_loss": 1.2005395889282227,
-      "eval_runtime": 10.0466,
-      "eval_samples_per_second": 0.199,
+      "eval_loss": 1.200242280960083,
+      "eval_runtime": 10.0049,
+      "eval_samples_per_second": 0.2,
       "eval_steps_per_second": 0.1,
       "eval_wer": 100.0,
       "step": 2
     },
     {
       "epoch": 3.0,
-      "grad_norm": 14.894689559936523,
+      "grad_norm": 14.89444637298584,
       "learning_rate": 1.9238795325112867e-06,
-      "loss": 1.1152,
+      "loss": 1.1151,
       "step": 3
     },
     {
       "epoch": 4.0,
-      "grad_norm": 7.684017181396484,
+      "grad_norm": 7.6878342628479,
       "learning_rate": 1.7071067811865474e-06,
       "loss": 0.9985,
       "step": 4
     },
     {
       "epoch": 4.0,
-      "eval_loss": 0.9411194920539856,
-      "eval_runtime": 9.7666,
-      "eval_samples_per_second": 0.205,
+      "eval_loss": 0.9411421418190002,
+      "eval_runtime": 9.8321,
+      "eval_samples_per_second": 0.203,
       "eval_steps_per_second": 0.102,
       "eval_wer": 100.0,
       "step": 4
     },
     {
       "epoch": 5.0,
-      "grad_norm": 6.6712212562561035,
+      "grad_norm": 6.6659393310546875,
       "learning_rate": 1.3826834323650898e-06,
-      "loss": 0.8863,
+      "loss": 0.8864,
       "step": 5
     },
     {
       "epoch": 6.0,
-      "grad_norm": 4.722819805145264,
+      "grad_norm": 4.723628520965576,
       "learning_rate": 1e-06,
       "loss": 0.8454,
       "step": 6
     },
     {
       "epoch": 6.0,
-      "eval_loss": 0.8363609910011292,
-      "eval_runtime": 9.7724,
-      "eval_samples_per_second": 0.205,
+      "eval_loss": 0.8363456130027771,
+      "eval_runtime": 9.8335,
+      "eval_samples_per_second": 0.203,
       "eval_steps_per_second": 0.102,
       "eval_wer": 100.0,
       "step": 6
     },
     {
       "epoch": 7.0,
-      "grad_norm": 5.701328277587891,
+      "grad_norm": 5.706678867340088,
       "learning_rate": 6.173165676349102e-07,
       "loss": 0.7801,
       "step": 7
     },
     {
       "epoch": 8.0,
-      "grad_norm": 6.357309818267822,
+      "grad_norm": 6.359007835388184,
       "learning_rate": 2.9289321881345254e-07,
       "loss": 0.7518,
       "step": 8
     },
     {
       "epoch": 8.0,
-      "eval_loss": 0.7893769145011902,
-      "eval_runtime": 10.0532,
-      "eval_samples_per_second": 0.199,
+      "eval_loss": 0.789289653301239,
+      "eval_runtime": 10.1491,
+      "eval_samples_per_second": 0.197,
       "eval_steps_per_second": 0.099,
       "eval_wer": 100.0,
       "step": 8
     },
     {
       "epoch": 9.0,
-      "grad_norm": 5.225600242614746,
+      "grad_norm": 5.221818447113037,
       "learning_rate": 7.612046748871326e-08,
-      "loss": 0.7348,
+      "loss": 0.7349,
       "step": 9
     },
     {
       "epoch": 10.0,
-      "grad_norm": 4.553382873535156,
+      "grad_norm": 4.555125713348389,
       "learning_rate": 0.0,
-      "loss": 0.7247,
+      "loss": 0.7248,
       "step": 10
     },
     {
       "epoch": 10.0,
-      "eval_loss": 0.7804375290870667,
-      "eval_runtime": 10.2291,
-      "eval_samples_per_second": 0.196,
-      "eval_steps_per_second": 0.098,
+      "eval_loss": 0.7805328369140625,
+      "eval_runtime": 10.2645,
+      "eval_samples_per_second": 0.195,
+      "eval_steps_per_second": 0.097,
       "eval_wer": 100.0,
       "step": 10
     }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed3711bfc6e963e234e8255052fc7b89f06362b5707acbd0b1bc25bfaf55c473
+oid sha256:f5e628e2347ada9e4d132d910641cbe455b95ce46d1ef2ee82341be6b19b7b98
 size 5432