Training in progress, step 43000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f3fe48a7f9a7950c3f5192c1381760445d2536c203f774c213fe6030cc54d5b
+oid sha256:a919983f1774a9944c46697486622fd0ab96a6cb0e5bb0ee5c0f2e12ae0b8f09
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65c21f7ea185f2d6edfb6473b152b0747c194d41917ab9329acd84bfb6c5dc2f
+oid sha256:a81581bf4180e242fb2429b75ca88a74d80d18891749a9cf8e4f4deba4cad01d
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f39beebeb407f963a212e24893da40a81bd4c1f5931713d30e89b46ab86f3b
+oid sha256:b98abc9ef51226b8ec3536d18259a383a922c96c0834dabdd5ac597c877815a9
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c5dd5b6adbd79cf2ac7181561cc774617ae917a7182e146aab5041d5014f6fe
+oid sha256:ff26a1c9e8953fc53b225ecae4b59ac3cf75bfa228df53ad0a8cf47f04790b7a
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db730777aa403ea449f67eca81518cbd04846ed2f8416611ee9829c6c93f3138
+oid sha256:8692b2cb9f5034153fef29e02c28ec94848180acab9070361551809efd9866b6
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.01725952431067,
+  "epoch": 18.10145232582614,
   "eval_steps": 100,
-  "global_step": 42800,
+  "global_step": 43000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6855,6 +6855,38 @@
       "eval_samples_per_second": 24.8,
       "eval_steps_per_second": 3.101,
       "step": 42800
+    },
+    {
+      "epoch": 18.06,
+      "grad_norm": 4.65023946762085,
+      "learning_rate": 2.004946996466431e-05,
+      "loss": 0.5527,
+      "step": 42900
+    },
+    {
+      "epoch": 18.06,
+      "eval_cer": 0.35880245199640215,
+      "eval_loss": 2.8290772438049316,
+      "eval_runtime": 400.9741,
+      "eval_samples_per_second": 23.637,
+      "eval_steps_per_second": 2.955,
+      "step": 42900
+    },
+    {
+      "epoch": 18.1,
+      "grad_norm": 1.5041050910949707,
+      "learning_rate": 1.997879858657244e-05,
+      "loss": 0.5502,
+      "step": 43000
+    },
+    {
+      "epoch": 18.1,
+      "eval_cer": 0.3574239372726917,
+      "eval_loss": 2.1965556144714355,
+      "eval_runtime": 380.8445,
+      "eval_samples_per_second": 24.887,
+      "eval_steps_per_second": 3.112,
+      "step": 43000
     }
   ],
   "logging_steps": 100,
@@ -6862,7 +6894,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.690252137745783e+20,
+  "total_flos": 4.7124629252969575e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null