Training in progress, step 45300, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cb3db9d2bd3bce52bd4db7c183811c68dab8410c3e736a49c6c697983dffdd9
+oid sha256:cfb7b0c0954b79b64169654d0d5755c152eec3fa0a4a3dac9ffb3d9e2e117590
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84b143c07e902a9dcb951619cb1986e38157fd91e3cf1bcaced4a96d3371c692
+oid sha256:51aba02490ce4fa0778fa18a8253a1df903a553efa8183363107b2f3586f7354
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20e71314605e7678242a5a386ea35a216d449f08cf4c3ff655d23be515343b67
+oid sha256:554363376473be285bf841a2fabc11809a6cc6027b2c279ec5200e8820262e85
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5293e155d2b0d2e7b914f2d40a0c1ca84ad8e4c46494c609b09f7e1634588b5b
-size 14567
+oid sha256:d0987eb7b75be13a7a10c4a1f323538d3e643dd53891dc4f78af5395b7c598b5
+size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4efa9e4a4746446a85030c2502426e055bf40a9b3cad17aeaecf307da12c8f64
+oid sha256:dcf445c90de460a2c42624ebfda6f14349167a4ef3cacd640c59e1071f27cb2a
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 18.98547674173858,
+  "epoch": 19.06966954325405,
   "eval_steps": 100,
-  "global_step": 45100,
+  "global_step": 45300,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7223,6 +7223,38 @@
       "eval_samples_per_second": 23.573,
       "eval_steps_per_second": 2.947,
       "step": 45100
+    },
+    {
+      "epoch": 19.03,
+      "grad_norm": 1.673799991607666,
+      "learning_rate": 1.8425441696113076e-05,
+      "loss": 0.5004,
+      "step": 45200
+    },
+    {
+      "epoch": 19.03,
+      "eval_cer": 0.35489666027922256,
+      "eval_loss": 2.622223138809204,
+      "eval_runtime": 462.6029,
+      "eval_samples_per_second": 20.488,
+      "eval_steps_per_second": 2.562,
+      "step": 45200
+    },
+    {
+      "epoch": 19.07,
+      "grad_norm": 2.5973594188690186,
+      "learning_rate": 1.8354770318021204e-05,
+      "loss": 0.476,
+      "step": 45300
+    },
+    {
+      "epoch": 19.07,
+      "eval_cer": 0.3551215243830902,
+      "eval_loss": 2.0877623558044434,
+      "eval_runtime": 371.4246,
+      "eval_samples_per_second": 25.518,
+      "eval_steps_per_second": 3.19,
+      "step": 45300
     }
   ],
   "logging_steps": 100,
@@ -7230,7 +7262,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.941606672163604e+20,
+  "total_flos": 4.964246544740599e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null