Training in progress, step 4400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dbdd6f80dc79a8405e31ae7786528edc85a46546c81b10d835d82e28f972d7e
+oid sha256:bed94b7d4fd42216fd390d328de3f151a13b33b430c74ab44fd10d269e21255f
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42b57c72afc83f80ebcb3ac2c3025ecf0061be5a4ba0dbe9fff2daed822328cc
+oid sha256:114e0d1544f075ef1319771189365fc113997893216e4ea0068921b7c565ab65
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38852f16d1dc1f5bbcbc93dc34aea8227dab25604d05cca96d84347321f03d6f
+oid sha256:66847a5e03866b474e266e8d744ea25e9bff8591fdc6492a9f466e6f006cf3e0
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b1aec0a96b3ecb58cc9d8ef8a09a92cddd9227edd51fc5e1fd3970354bfc8e6
-size 14503
+oid sha256:2866e2329d94cbbc60d5487c4e462b71b5c661406207215119e66ed7e27271b9
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e234c273d80c40346bcc08d22e92500d903e21d8697287e8453c0f063d1a8ee1
+oid sha256:297bafaeae03f2ece08ad43e10bf1c267d31323b128e711289b3291e220124fe
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.768048831824879,
+  "epoch": 1.8522416333403493,
   "eval_steps": 100,
-  "global_step": 4200,
+  "global_step": 4400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -679,6 +679,38 @@
       "eval_samples_per_second": 27.531,
       "eval_steps_per_second": 3.442,
       "step": 4200
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 7.425869941711426,
+      "learning_rate": 4.7319434628975265e-05,
+      "loss": 3.2591,
+      "step": 4300
+    },
+    {
+      "epoch": 1.81,
+      "eval_cer": 0.5522955691994837,
+      "eval_loss": 1.7015308141708374,
+      "eval_runtime": 353.5748,
+      "eval_samples_per_second": 26.806,
+      "eval_steps_per_second": 3.351,
+      "step": 4300
+    },
+    {
+      "epoch": 1.85,
+      "grad_norm": 2.405174493789673,
+      "learning_rate": 4.724876325088339e-05,
+      "loss": 2.373,
+      "step": 4400
+    },
+    {
+      "epoch": 1.85,
+      "eval_cer": 0.5220977865550819,
+      "eval_loss": 2.095752477645874,
+      "eval_runtime": 344.3236,
+      "eval_samples_per_second": 27.526,
+      "eval_steps_per_second": 3.442,
+      "step": 4400
     }
   ],
   "logging_steps": 100,
@@ -686,7 +718,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 4.61125002150313e+19,
+  "total_flos": 4.831887475809752e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null