Training in progress, step 30700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8a7ffffe1e276bc012991e66d4940c3825b582e38503a6831b65ac751fa69bd
+oid sha256:59250fd9c1a5ce2ea95e8374f4e0a25cf570f1b430322763a33c452a78721126
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630c4abcc4bc1727abb3d67b316f2060d13f80edaa99f51a7e97121a113df5b8
+oid sha256:4ee966e20348f3305f52c11ce787ab1d112ba834727e878f4dd30e8df8e37f46
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1a99422a5e4116ff151117700a9adccd0676836fa1c35aae05cb8ec0f1f597f
+oid sha256:79caf774c5464f9f5b97517a7e1be66aa2f2a138193b94d0825747e7e97452ce
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5867baf9f2fb0f6208701690c1b5e386b1033cbd77cdc0ffc425bab964f5f4ff
+oid sha256:37a3ee2bb07ef33e190c44e2b218c5390d462a8018bd3100170be9a809a772b2
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31e62054497d3b77134377a0dac2d5cd6fb555d9f969587da4d1282f956ad0b2
+oid sha256:3b7c7f8d94d094e5495ec4b02a0a6e224c7e7a8db7f263d195945f5e974673dc
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 12.83940223110924,
+  "epoch": 12.92359503262471,
   "eval_steps": 100,
-  "global_step": 30500,
+  "global_step": 30700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -4887,6 +4887,38 @@
       "eval_samples_per_second": 25.573,
       "eval_steps_per_second": 3.197,
       "step": 30500
+    },
+    {
+      "epoch": 12.88,
+      "grad_norm": 3.699707508087158,
+      "learning_rate": 2.873992932862191e-05,
+      "loss": 1.2704,
+      "step": 30600
+    },
+    {
+      "epoch": 12.88,
+      "eval_cer": 0.40483360056313794,
+      "eval_loss": 3.221102476119995,
+      "eval_runtime": 396.883,
+      "eval_samples_per_second": 23.881,
+      "eval_steps_per_second": 2.986,
+      "step": 30600
+    },
+    {
+      "epoch": 12.92,
+      "grad_norm": 2.9071247577667236,
+      "learning_rate": 2.866925795053004e-05,
+      "loss": 2.4896,
+      "step": 30700
+    },
+    {
+      "epoch": 12.92,
+      "eval_cer": 0.4067840522466857,
+      "eval_loss": 2.3889622688293457,
+      "eval_runtime": 374.4971,
+      "eval_samples_per_second": 25.309,
+      "eval_steps_per_second": 3.164,
+      "step": 30700
     }
   ],
   "logging_steps": 100,
@@ -4894,7 +4926,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.341767397417848e+20,
+  "total_flos": 3.363836920139934e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null