Training in progress, step 33700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebbf03b6a39b6b310c792fd4ce9a56b4feab22bc4d8aae7c67e0b23549ec3844
+oid sha256:8bdec49f5ba937575c37201bec00db52b8c3e844821eecc385ba239a33663f10
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5322792e8472158c629b41c8ed853c14c036430212aa2395b1962b71dd6688c
+oid sha256:619c1c99184b876365ca973837576037ba7b39716899416a2f1019041043ea17
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41f6c73349fb0a4922b7c514625c8f319c04d8a3281a94dc80e47d5905a270b7
+oid sha256:0729b7a58599ea8921b314d9c9621e535f2d82f309864faa4b6d052417b8b263
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08b7a405079c06c2e1179546e5ade586e1754239d626d4047688ddad0abeac41
+oid sha256:44661c431a879e3226aadc89367134cd0b53d52f6af54472aaa115083d69b12e
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c05bab47528958ca030cc3c2eb992ca93a53fcef5ee7de67d8809ec8b54d00
+oid sha256:5a48819e7745c34bedd45ae62b08be3d10aa46039968cd3e6efddcf11d1d5426
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.102294253841297,
+  "epoch": 14.186487055356768,
   "eval_steps": 100,
-  "global_step": 33500,
+  "global_step": 33700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5367,6 +5367,38 @@
       "eval_samples_per_second": 25.476,
       "eval_steps_per_second": 3.185,
       "step": 33500
+    },
+    {
+      "epoch": 14.14,
+      "grad_norm": 2.114933729171753,
+      "learning_rate": 2.6619787985865723e-05,
+      "loss": 0.9445,
+      "step": 33600
+    },
+    {
+      "epoch": 14.14,
+      "eval_cer": 0.3915470650346095,
+      "eval_loss": 2.192039728164673,
+      "eval_runtime": 401.3991,
+      "eval_samples_per_second": 23.612,
+      "eval_steps_per_second": 2.952,
+      "step": 33600
+    },
+    {
+      "epoch": 14.19,
+      "grad_norm": 22.767732620239258,
+      "learning_rate": 2.6549116607773855e-05,
+      "loss": 0.9435,
+      "step": 33700
+    },
+    {
+      "epoch": 14.19,
+      "eval_cer": 0.39616655586406474,
+      "eval_loss": 2.0086452960968018,
+      "eval_runtime": 374.9441,
+      "eval_samples_per_second": 25.278,
+      "eval_steps_per_second": 3.16,
+      "step": 33700
     }
   ],
   "logging_steps": 100,
@@ -5374,7 +5406,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.670837467873283e+20,
+  "total_flos": 3.693186041855623e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null