Training in progress, step 15700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c8d9f8936035594d661114b781a4eb14f9085f107b414f8cdb04fae2af1f5af1
+oid sha256:ebec8683b94d94fc8d9612c1c65b13eb71fe6bb5bb5cae5646d15330e2237b15
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4e230029c183533b0b9fe6b84165574a15e9c485917cb915f98f6e96e5f4e98
+oid sha256:59bf8a8143b87e68fd71c8a270a03cfa582fc1bfdd2b29a7d15ff8d8b4213d41
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e7906e6327d11d85d338ea4339351ae9c0034f62b94b4da68358eaacc6ab527
+oid sha256:da9ed2936cadc331d13cb99e9dd4c8e3574daaac258fa92af0538fb2ee9612b5
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9b0b65f0420889adb98f67d37d7d10f35fcca76dcf8679e43243891e5dcf6a5
-size 14503
+oid sha256:0a6d63bd7c4e166ca59e260fbbde05182634cc6b1f0a4d12136bc73308ef55e3
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d310350e2d89a95e16a26ae72f1a3c391fc38d88fcd18e2b9a8d9e4038006a55
+oid sha256:726650f2459dfa6278e31becc2531b3a3d91514d7f35b02bbac401fc857ec409
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.524942117448958,
+  "epoch": 6.609134918964428,
   "eval_steps": 100,
-  "global_step": 15500,
+  "global_step": 15700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -2487,6 +2487,38 @@
       "eval_samples_per_second": 26.833,
       "eval_steps_per_second": 3.355,
       "step": 15500
+    },
+    {
+      "epoch": 6.57,
+      "grad_norm": 5.287090301513672,
+      "learning_rate": 3.933639575971731e-05,
+      "loss": 1.6601,
+      "step": 15600
+    },
+    {
+      "epoch": 6.57,
+      "eval_cer": 0.4719262054671307,
+      "eval_loss": 2.0440595149993896,
+      "eval_runtime": 377.8824,
+      "eval_samples_per_second": 25.082,
+      "eval_steps_per_second": 3.136,
+      "step": 15600
+    },
+    {
+      "epoch": 6.61,
+      "grad_norm": 2.0426106452941895,
+      "learning_rate": 3.926572438162545e-05,
+      "loss": 1.9773,
+      "step": 15700
+    },
+    {
+      "epoch": 6.61,
+      "eval_cer": 0.4639239763794924,
+      "eval_loss": 2.3498713970184326,
+      "eval_runtime": 365.2548,
+      "eval_samples_per_second": 25.949,
+      "eval_steps_per_second": 3.244,
+      "step": 15700
     }
   ],
   "logging_steps": 100,
@@ -2494,7 +2526,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.6980516265683495e+20,
+  "total_flos": 1.7201807515766456e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null