Training in progress, step 30500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8547a7322e157d670ed2412e949d1f0885f06c8cbaac3795431c83b2400ad687
+oid sha256:a8a7ffffe1e276bc012991e66d4940c3825b582e38503a6831b65ac751fa69bd
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3f3da746f6d92e513538b782722aacd2930f02af3056fdc6b1b9211ad4f969
+oid sha256:630c4abcc4bc1727abb3d67b316f2060d13f80edaa99f51a7e97121a113df5b8
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c32888919c52e486af2fe0eedfc4a55ab9ac5c7ea916faaf672fa4ba60c176a
+oid sha256:b1a99422a5e4116ff151117700a9adccd0676836fa1c35aae05cb8ec0f1f597f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79dfeac7ede56e3f252c95778498b8d970c65dd0948b9c809c0a7dce43089bf1
+oid sha256:5867baf9f2fb0f6208701690c1b5e386b1033cbd77cdc0ffc425bab964f5f4ff
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:428cbf0e904ad9abe549f3777087cb24ea80512aa0df465c9f11ee3c360e92cf
+oid sha256:31e62054497d3b77134377a0dac2d5cd6fb555d9f969587da4d1282f956ad0b2
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.75520942959377,
+  "epoch": 12.83940223110924,
   "eval_steps": 100,
-  "global_step": 30300,
+  "global_step": 30500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4855,6 +4855,38 @@
       "eval_samples_per_second": 25.315,
       "eval_steps_per_second": 3.165,
       "step": 30300
+    },
+    {
+      "epoch": 12.8,
+      "grad_norm": 1.8343230485916138,
+      "learning_rate": 2.8881272084805654e-05,
+      "loss": 1.0572,
+      "step": 30400
+    },
+    {
+      "epoch": 12.8,
+      "eval_cer": 0.40438142818036055,
+      "eval_loss": 2.247307062149048,
+      "eval_runtime": 396.7902,
+      "eval_samples_per_second": 23.887,
+      "eval_steps_per_second": 2.986,
+      "step": 30400
+    },
+    {
+      "epoch": 12.84,
+      "grad_norm": 2.385056495666504,
+      "learning_rate": 2.881060070671378e-05,
+      "loss": 1.0668,
+      "step": 30500
+    },
+    {
+      "epoch": 12.84,
+      "eval_cer": 0.40543242344843766,
+      "eval_loss": 2.0315330028533936,
+      "eval_runtime": 370.6236,
+      "eval_samples_per_second": 25.573,
+      "eval_steps_per_second": 3.197,
+      "step": 30500
     }
   ],
   "logging_steps": 100,
@@ -4862,7 +4894,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.3198106925315916e+20,
+  "total_flos": 3.341767397417848e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null