Training in progress, step 40800, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b03dc9e0469a4511d3960e8ccc32ec9be77fb87dc6998ca5230f5d24b80dd574
+oid sha256:75f6409a44328ccff19c64caff488439da9273da3c101449fa3123336a4468ea
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8ef085b7b6748391bb90ac62d5548dc82db571deca605fc3e13a91144e2ddcb
+oid sha256:4dcbe4d068720daaaee2a8da1dbc2bbe9c056e9518e3461c7459f79006631080
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa7234bcf7f52f0002950ee4c95f584023eaebde1bd2b931543505530d4bf62
+oid sha256:33d5708694aaf8845bf750d7154f0271164aa685b76c098f6dd40029eeb5662f
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c2dc3633beab3a54043bc13682c039467daffe3d3f1de119b8bf092c5378995
-size 14503
+oid sha256:72f3d277caa97e791c619eba8f2b402ab01caedcd3e1225af2b74b9180ced546
+size 14631

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e15e995c71854cd5ff2c0e03c1bb6ee2b6ba36e7be4d986833bffdd5d14ed7fc
+oid sha256:34c4ef4e4f4492564f8cc89617cc7f93e8c2f6998eb6eef00126c81220e404a6
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 17.091138707640496,
+  "epoch": 17.175331509155967,
   "eval_steps": 100,
-  "global_step": 40600,
+  "global_step": 40800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -6503,6 +6503,38 @@
       "eval_samples_per_second": 25.091,
       "eval_steps_per_second": 3.137,
       "step": 40600
+    },
+    {
+      "epoch": 17.13,
+      "grad_norm": 7.590035915374756,
+      "learning_rate": 2.1603533568904594e-05,
+      "loss": 0.6376,
+      "step": 40700
+    },
+    {
+      "epoch": 17.13,
+      "eval_cer": 0.36229762230651913,
+      "eval_loss": 2.3001914024353027,
+      "eval_runtime": 393.9708,
+      "eval_samples_per_second": 24.058,
+      "eval_steps_per_second": 3.008,
+      "step": 40700
+    },
+    {
+      "epoch": 17.18,
+      "grad_norm": 3.8723325729370117,
+      "learning_rate": 2.1532862190812723e-05,
+      "loss": 0.6424,
+      "step": 40800
+    },
+    {
+      "epoch": 17.18,
+      "eval_cer": 0.3627106878886238,
+      "eval_loss": 1.9817591905593872,
+      "eval_runtime": 380.3308,
+      "eval_samples_per_second": 24.92,
+      "eval_steps_per_second": 3.116,
+      "step": 40800
     }
   ],
   "logging_steps": 100,
@@ -6510,7 +6542,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.449729914752364e+20,
+  "total_flos": 4.4722373414464927e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null