Training in progress, step 50900, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b47f775b647eb4ca79619e9a3f63d2ec8dc0fd2fb449358850abac10534266b
+oid sha256:b8c55cd18309bf4d096f4b3253c534937b641ff135e763ecb864e9f8ebd8618a
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:699fbd5992054d81409f0835427766bd93ed83628a4cf3ec9a80f7838edeab17
+oid sha256:5ec6752b7c42decf02f2e39800b6145d2ffde5bb2151b7574bdd01ba232e6372
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60be0080dbfcb7f1f5db48bba6f03245ce57196433362cbc3bc3c410c888a3c1
+oid sha256:095dcbda7d00d483e2fa14803e5220f34c3024566d3114fc9f91b65d66ab3534
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef8a6e3b5130077a0b6901be264f4bb7d44393ff9a0c743c3f92a90852087d6a
+oid sha256:12f7743be5328471b18c330b88db7a79949aef581fc0209654a98b74372391d2
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb95b52b6618ac8420e23f26e7f97bbeee8449df4c10989dedf902ebfd9c011
+oid sha256:760aea3902ababea5df05720420d447d30d1561a0385a51f231f0d512c4123e3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.342875184171753,
+  "epoch": 21.427067985687223,
   "eval_steps": 100,
-  "global_step": 50700,
+  "global_step": 50900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8119,6 +8119,38 @@
       "eval_samples_per_second": 24.423,
       "eval_steps_per_second": 3.053,
       "step": 50700
+    },
+    {
+      "epoch": 21.38,
+      "grad_norm": 5.978403568267822,
+      "learning_rate": 1.4468551236749117e-05,
+      "loss": 0.3601,
+      "step": 50800
+    },
+    {
+      "epoch": 21.38,
+      "eval_cer": 0.34170789175237576,
+      "eval_loss": 2.4659318923950195,
+      "eval_runtime": 412.615,
+      "eval_samples_per_second": 22.971,
+      "eval_steps_per_second": 2.872,
+      "step": 50800
+    },
+    {
+      "epoch": 21.43,
+      "grad_norm": 1.794754981994629,
+      "learning_rate": 1.4397879858657245e-05,
+      "loss": 0.3487,
+      "step": 50900
+    },
+    {
+      "epoch": 21.43,
+      "eval_cer": 0.34158079465018965,
+      "eval_loss": 2.544365406036377,
+      "eval_runtime": 390.5089,
+      "eval_samples_per_second": 24.271,
+      "eval_steps_per_second": 3.035,
+      "step": 50900
     }
   ],
   "logging_steps": 100,
@@ -8126,7 +8158,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.5559876766241174e+20,
+  "total_flos": 5.578208763591309e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null