Training in progress, step 19400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f044f8baed15a299bbbeca19e6da1b66abd02e56213b73dd0cd66de71200f6d7
+oid sha256:39536b07857e96674098336d821ff35749a8ecafb4e064cb918e9fbf3d7ba9c4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b0931f5bdd0a0ad3c0b44f18bac8516747577559b5999e424f7825b4b498e1d
+oid sha256:3d85220a081ebf7ba5f24dcf36d455607c800e07075731fc0438ed7d721838b8
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7eea6c010049ede732e35337dc92f9c4a9f201fd86647564100ea8b70da22657
+oid sha256:b2feee5f579bc8ff01696c6cde6f4789c3b844b14e975ef180da8d549e0fe33b
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a35b249b98686868e501117a28d1ffb6fed2a0d74e305b00d878f548181e83
+oid sha256:9b560c73f8c11664695f9a90d9d927dbe3811353bb8caf7abe8872e3b37b7585
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49b241842c803d56347030233a5319efc06cd25ba775995df97e083f47b84391
+oid sha256:4ee31d8b929c9d8d36d66b3500c5c4c93de524b8757148ff9ad30057ceaeb53d
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 8.082508945485161,
+  "epoch": 8.166701747000632,
   "eval_steps": 100,
-  "global_step": 19200,
+  "global_step": 19400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3079,6 +3079,38 @@
       "eval_samples_per_second": 26.205,
       "eval_steps_per_second": 3.276,
       "step": 19200
+    },
+    {
+      "epoch": 8.12,
+      "grad_norm": 2.6323907375335693,
+      "learning_rate": 3.672226148409894e-05,
+      "loss": 1.2874,
+      "step": 19300
+    },
+    {
+      "epoch": 8.12,
+      "eval_cer": 0.4615849008642603,
+      "eval_loss": 1.754168152809143,
+      "eval_runtime": 385.1298,
+      "eval_samples_per_second": 24.61,
+      "eval_steps_per_second": 3.077,
+      "step": 19300
+    },
+    {
+      "epoch": 8.17,
+      "grad_norm": 2.5475683212280273,
+      "learning_rate": 3.665159010600707e-05,
+      "loss": 1.5227,
+      "step": 19400
+    },
+    {
+      "epoch": 8.17,
+      "eval_cer": 0.45406906260998786,
+      "eval_loss": 1.954167127609253,
+      "eval_runtime": 364.6983,
+      "eval_samples_per_second": 25.989,
+      "eval_steps_per_second": 3.249,
+      "step": 19400
     }
   ],
   "logging_steps": 100,
@@ -3086,7 +3118,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.1042862694965802e+20,
+  "total_flos": 2.1255543863355028e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null