Training in progress, step 34500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cef994832c881c5abf69e7f961f3e6f279e65a779394933155af910e3bc2f985
+oid sha256:7dde78f2f1969345a22710b02dad86de0a28263f667c5019c90aec37011dc2df
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4025af0e64a11f9871f380b35e9079785850a4ee06bf3584b2f772bca3e01364
+oid sha256:1d673a19cfec5851d535cbb42cc99c5bcfb76dcfc5db1ed80e4b0e8136200acc
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4b2b9839a2cf1d2d49e724fdb6e8a00a0e1eacac9ce5b02452ba7e8c21e3eb3
+oid sha256:c6998c3f78f855591ccca0963694f8694ed36fb2614f0be8e0a562e441198dd5
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc8ced7c606b78be67e87d5bfd97aadea8086b8ba9823f8bc9911bdee3e9be7b
+oid sha256:ada95d205b5a39eda24ebdce0e8a5ed373f9e446a705032948e14e07c6062dd5
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:527c530151dd325034db78fbfa25600fef8054e49339ba899b285bc75eae8415
+oid sha256:64f9e3827b8202a59f622a236dc60a703867ee0b6877abae1ad4c8c5512a0181
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.439065459903178,
+  "epoch": 14.523258261418649,
   "eval_steps": 100,
-  "global_step": 34300,
+  "global_step": 34500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5495,6 +5495,38 @@
       "eval_samples_per_second": 25.617,
       "eval_steps_per_second": 3.203,
       "step": 34300
+    },
+    {
+      "epoch": 14.48,
+      "grad_norm": 1.9228265285491943,
+      "learning_rate": 2.6054416961130745e-05,
+      "loss": 0.9234,
+      "step": 34400
+    },
+    {
+      "epoch": 14.48,
+      "eval_cer": 0.39062316686871845,
+      "eval_loss": 1.7525721788406372,
+      "eval_runtime": 386.1261,
+      "eval_samples_per_second": 24.546,
+      "eval_steps_per_second": 3.069,
+      "step": 34400
+    },
+    {
+      "epoch": 14.52,
+      "grad_norm": 10.801593780517578,
+      "learning_rate": 2.598374558303887e-05,
+      "loss": 0.9669,
+      "step": 34500
+    },
+    {
+      "epoch": 14.52,
+      "eval_cer": 0.3913124242305737,
+      "eval_loss": 1.5855803489685059,
+      "eval_runtime": 376.3532,
+      "eval_samples_per_second": 25.184,
+      "eval_steps_per_second": 3.149,
+      "step": 34500
     }
   ],
   "logging_steps": 100,
@@ -5502,7 +5534,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.758759861479934e+20,
+  "total_flos": 3.78048558664814e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null