Training in progress, step 3000, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44b2ea87fb45896c5e64675c42319b0c800f3516393fd91fe6189f46278e1a6f
+oid sha256:aa3f8250eedc0ad91d9bd7bd29190dfcd30c24ddbb981802ff4398fb1b6f8ccb
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c31b10f100741c4ebc4d4250ad676d7b466307a2ea83cbc5ede244644ac015c
+oid sha256:d61642ae37b7f2123a78d2dc95232dacaf674afbc5bc78d70d4b6245a6343788
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:197e645c69e01ac20ea12442834230672eb334b80f902f66c33a4b04dcb6f523
+oid sha256:9aa0dc12fc4c549ade65217632d28f06d688771482b33353c8dcff908cd43500
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04efee40e70fc230d3d9de163b7a49660ca999141c4308e72ab88d3a1aa96df5
+oid sha256:9b8972e9f2b0f288dfd8ade7d14f3387e82aa534b7b0691b69299c0919f543f0
 size 14503

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ae68370e6304e1d4db7600cca11df6aac88b08aee5cd9372946660cf6886038
+oid sha256:cd47c81b0d91d48642f51b85203435f35325e0ebcfd794d4d6fa6f9f3a411358
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.1786992212165859,
+  "epoch": 1.2628920227320564,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -455,6 +455,38 @@
       "eval_samples_per_second": 27.838,
       "eval_steps_per_second": 3.481,
       "step": 2800
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 4.691165924072266,
+      "learning_rate": 4.8308833922261485e-05,
+      "loss": 2.0012,
+      "step": 2900
+    },
+    {
+      "epoch": 1.22,
+      "eval_cer": 0.5138047006374409,
+      "eval_loss": 3.412604331970215,
+      "eval_runtime": 349.7896,
+      "eval_samples_per_second": 27.096,
+      "eval_steps_per_second": 3.388,
+      "step": 2900
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 2.8883514404296875,
+      "learning_rate": 4.823816254416961e-05,
+      "loss": 3.5496,
+      "step": 3000
+    },
+    {
+      "epoch": 1.26,
+      "eval_cer": 0.5417074029173673,
+      "eval_loss": 1.7423540353775024,
+      "eval_runtime": 339.3199,
+      "eval_samples_per_second": 27.932,
+      "eval_steps_per_second": 3.492,
+      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -462,7 +494,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.076610148872312e+19,
+  "total_flos": 3.298748154606821e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null