Training in progress, step 51500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0840e5b81106618e117773e1a9e46982326d5ef4a4376f8f91884378562a9093
+oid sha256:c6879e7a47865a2d9dbdc1dee441becb941a61f7ae9db55a4342ae07a816d700
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb3ddfda4162ba8509efb41a733e19dbd95c0d6e0e8081c1227b99cdf29a4920
+oid sha256:ab07935c87ce3f230af1aca71f7d354f2ae99539d4922cd9ff951ce52ecc827f
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350d3e5875623b979435692aeda728979a132c77413bd449e25e3d20ae0234e7
+oid sha256:691a9b667c584e2397167aa221b255d9341ff38ca1d8535cfe09f55be3c23054
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05f6e0293bbf3f1668750a9d5b5151fa82c485734c4a7e5502f70e556472e25e
-size 14567
+oid sha256:6da86477a7e38c974647d1441bec2689395584cdc4189de87cdd2736695ba37f
+size 14631

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9e1cfa7c07b2a4f4036b4175c9d726fa25f567b5351fc720a65fdcaf21b2d3e
+oid sha256:7a0508acb91372d3d8167376986d8fc4095af16c3a72cecf2777e3dd527abab5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 21.595453588718165,
+  "epoch": 21.679646390233636,
   "eval_steps": 100,
-  "global_step": 51300,
+  "global_step": 51500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -8215,6 +8215,38 @@
       "eval_samples_per_second": 24.408,
       "eval_steps_per_second": 3.052,
       "step": 51300
+    },
+    {
+      "epoch": 21.64,
+      "grad_norm": 1.9676817655563354,
+      "learning_rate": 1.4044522968197882e-05,
+      "loss": 0.3469,
+      "step": 51400
+    },
+    {
+      "epoch": 21.64,
+      "eval_cer": 0.34236293066364243,
+      "eval_loss": 2.332427740097046,
+      "eval_runtime": 411.3092,
+      "eval_samples_per_second": 23.043,
+      "eval_steps_per_second": 2.881,
+      "step": 51400
+    },
+    {
+      "epoch": 21.68,
+      "grad_norm": 2.4417457580566406,
+      "learning_rate": 1.3973851590106007e-05,
+      "loss": 0.3535,
+      "step": 51500
+    },
+    {
+      "epoch": 21.68,
+      "eval_cer": 0.3423751515388526,
+      "eval_loss": 2.3060784339904785,
+      "eval_runtime": 391.5586,
+      "eval_samples_per_second": 24.206,
+      "eval_steps_per_second": 3.026,
+      "step": 51500
     }
   ],
   "logging_steps": 100,
@@ -8222,7 +8254,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 5.621976956469394e+20,
+  "total_flos": 5.643614886293618e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null