Training in progress, step 45500, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cfb7b0c0954b79b64169654d0d5755c152eec3fa0a4a3dac9ffb3d9e2e117590
+oid sha256:ba72df5975c8b99cbc6d6a6d24dea915763e37bcfeeb094b07a32702d90892df
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:51aba02490ce4fa0778fa18a8253a1df903a553efa8183363107b2f3586f7354
+oid sha256:a9bc26a5cbbbc20d7fd8697e5046c3103c37dc49f7a44a61a5442d759e5639da
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:554363376473be285bf841a2fabc11809a6cc6027b2c279ec5200e8820262e85
+oid sha256:911113640d61c316fc766e86411da7bb59e1d0e3ce7f49e464f18e99ea654517
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0987eb7b75be13a7a10c4a1f323538d3e643dd53891dc4f78af5395b7c598b5
+oid sha256:ea78b13ed690a2241b4d959d7b6ee1a7ec9311794f20d4d9c39e9088e224fc5e
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcf445c90de460a2c42624ebfda6f14349167a4ef3cacd640c59e1071f27cb2a
+oid sha256:388522323e4003fdf0f1aab6ae314ad13e012d10187ec9e801314752b5856b73
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 19.06966954325405,
+  "epoch": 19.15386234476952,
   "eval_steps": 100,
-  "global_step": 45300,
+  "global_step": 45500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -7255,6 +7255,38 @@
       "eval_samples_per_second": 25.518,
       "eval_steps_per_second": 3.19,
       "step": 45300
+    },
+    {
+      "epoch": 19.11,
+      "grad_norm": 2.274106502532959,
+      "learning_rate": 1.828409893992933e-05,
+      "loss": 0.4914,
+      "step": 45400
+    },
+    {
+      "epoch": 19.11,
+      "eval_cer": 0.35471090297602753,
+      "eval_loss": 2.134805917739868,
+      "eval_runtime": 380.1079,
+      "eval_samples_per_second": 24.935,
+      "eval_steps_per_second": 3.118,
+      "step": 45400
+    },
+    {
+      "epoch": 19.15,
+      "grad_norm": 16.124771118164062,
+      "learning_rate": 1.8213427561837457e-05,
+      "loss": 1.2144,
+      "step": 45500
+    },
+    {
+      "epoch": 19.15,
+      "eval_cer": 0.35294376442063274,
+      "eval_loss": 1.9654364585876465,
+      "eval_runtime": 365.9062,
+      "eval_samples_per_second": 25.903,
+      "eval_steps_per_second": 3.239,
+      "step": 45500
     }
   ],
   "logging_steps": 100,
@@ -7262,7 +7294,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.964246544740599e+20,
+  "total_flos": 4.9862113247753096e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null