Training in progress, step 9700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a32dc99462660290df84c8528dc9eb39190be3d3c57683e7877e90642c878438
+oid sha256:35ca73b672d977391aef537183758e87218bc9b1f338667515331d5bba2decd1
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f127aa66da05aa9808cb65c326d54eb1f62011422d2b38dbc32ab973d98742
+oid sha256:41e1f8481ef4b2fa8757c7e2080dad3a9464c495f675c86fe8a2b21eb55e1af4
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0521f879a75eea1399e7ebb7725746dc98364d1c9d3582f6a0a4284d965d9d7c
+oid sha256:72978f2549bdc36afbaafc26e6e615c11be366a830f1f901381cd993ed7e7933
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf6988d2899e29ce3c7ea0ad046e917da0407c7d088f3a2102b64354f3b328c9
+oid sha256:04636db759aef65e061d0a81cea15a49cf6becde8fb0cfb685f69da500fa6b33
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e0200d46d39b183c05be433e7301e4dbe08836ad4684cdecd5d09269aef39dd
+oid sha256:ad3c21cfca6b96706a9c82298c8390f24827b562f6561d40e5e026d6ae4092b3
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.999158071984845,
+  "epoch": 4.083350873500316,
   "eval_steps": 100,
-  "global_step": 9500,
+  "global_step": 9700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1527,6 +1527,38 @@
       "eval_samples_per_second": 26.858,
       "eval_steps_per_second": 3.358,
       "step": 9500
+    },
+    {
+      "epoch": 4.04,
+      "grad_norm": 5.240590572357178,
+      "learning_rate": 4.357597173144877e-05,
+      "loss": 2.2426,
+      "step": 9600
+    },
+    {
+      "epoch": 4.04,
+      "eval_cer": 0.49515320089163506,
+      "eval_loss": 2.496321201324463,
+      "eval_runtime": 373.8495,
+      "eval_samples_per_second": 25.352,
+      "eval_steps_per_second": 3.17,
+      "step": 9600
+    },
+    {
+      "epoch": 4.08,
+      "grad_norm": 2.557533025741577,
+      "learning_rate": 4.3505300353356896e-05,
+      "loss": 1.8649,
+      "step": 9700
+    },
+    {
+      "epoch": 4.08,
+      "eval_cer": 0.5054896171444214,
+      "eval_loss": 3.00071120262146,
+      "eval_runtime": 362.1744,
+      "eval_samples_per_second": 26.17,
+      "eval_steps_per_second": 3.272,
+      "step": 9700
     }
   ],
   "logging_steps": 100,
@@ -1534,7 +1566,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 1.0405499901125573e+20,
+  "total_flos": 1.0629240419863537e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null