Training in progress, step 50700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16c8e88b32eee615dcdd83273bd0c194d60a246661903076fda75220e2d10c57
+oid sha256:1b47f775b647eb4ca79619e9a3f63d2ec8dc0fd2fb449358850abac10534266b
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edd6f8a0eb8dcf9ba10c41e341f88389e7c3db368a255563153dee54ccc680c3
+oid sha256:699fbd5992054d81409f0835427766bd93ed83628a4cf3ec9a80f7838edeab17
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8741d79b5be03765e57061f191fb50d4ed43fb5803cf2b764313f8dcdd7e48
+oid sha256:60be0080dbfcb7f1f5db48bba6f03245ce57196433362cbc3bc3c410c888a3c1
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:382ea96905c8f14235ed215a03e93292273bd28d66f86e796f318632bcd7335e
+oid sha256:ef8a6e3b5130077a0b6901be264f4bb7d44393ff9a0c743c3f92a90852087d6a
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f01039206f45f4a9f82763ac9b1c4be8f2cba26114400c57368ed9f798a154b
+oid sha256:dbb95b52b6618ac8420e23f26e7f97bbeee8449df4c10989dedf902ebfd9c011
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.258682382656282,
+  "epoch": 21.342875184171753,
   "eval_steps": 100,
-  "global_step": 50500,
+  "global_step": 50700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8087,6 +8087,38 @@
       "eval_samples_per_second": 24.401,
       "eval_steps_per_second": 3.051,
       "step": 50500
+    },
+    {
+      "epoch": 21.3,
+      "grad_norm": 4.430927276611328,
+      "learning_rate": 1.4609893992932863e-05,
+      "loss": 0.3461,
+      "step": 50600
+    },
+    {
+      "epoch": 21.3,
+      "eval_cer": 0.34185698642994017,
+      "eval_loss": 2.8909881114959717,
+      "eval_runtime": 408.6465,
+      "eval_samples_per_second": 23.194,
+      "eval_steps_per_second": 2.9,
+      "step": 50600
+    },
+    {
+      "epoch": 21.34,
+      "grad_norm": 1.9088200330734253,
+      "learning_rate": 1.4539222614840989e-05,
+      "loss": 0.3561,
+      "step": 50700
+    },
+    {
+      "epoch": 21.34,
+      "eval_cer": 0.3429764185991944,
+      "eval_loss": 2.6278483867645264,
+      "eval_runtime": 388.0807,
+      "eval_samples_per_second": 24.423,
+      "eval_steps_per_second": 3.053,
+      "step": 50700
     }
   ],
   "logging_steps": 100,
@@ -8094,7 +8126,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.5342994893395676e+20,
+  "total_flos": 5.5559876766241174e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null