Training in progress, step 7100, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57001483176bf82e1c09ea40d1f0147256cbd62333a182c6b5800e360309b8f2
+oid sha256:1ffe4a4c3e4e20b6f8d7533a207499d54e18533a2ff9988b5cf140b2c17082c0
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a82744c0bc1c99fdf3736480a88beb791948657a4a6a512ff291360e62cfe4a
+oid sha256:50723aacfe1d09285d3d20c78e7a1e48064440bdd2388888b659a4f9def33f3c
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2700da8dca61e768af55482f0e459f8e8580186f45bdbf2c72ed3d4a47b60cc2
+oid sha256:c0b9c0f6c20269a5797deab52d27abffe73bdbbaf470e35e43b903f7ebcadebf
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7efa4777d4c3271e154dec08b5438b3ff12cbb40bd34cd166043ded385b18863
+oid sha256:c8a74dd20115cf8c84a288f3d48680cab469a7e69dc1d1632fbee207bbb0aa74
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c23abbcc2d4c9c22b104e91a5f11344337be1955d4805a3cb1067ad9e60d5245
+oid sha256:233cc1a95fc61bdbfaf2f246e87bbffc2fb4b93155b895b23bcd4b806754f9d4
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.8625552515259947,
+  "epoch": 2.9888444537992003,
   "eval_steps": 100,
-  "global_step": 6800,
+  "global_step": 7100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1095,6 +1095,54 @@
       "eval_samples_per_second": 26.308,
       "eval_steps_per_second": 3.289,
       "step": 6800
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 12.704540252685547,
+      "learning_rate": 4.5483392226148416e-05,
+      "loss": 2.6892,
+      "step": 6900
+    },
+    {
+      "epoch": 2.9,
+      "eval_cer": 0.5306426225020531,
+      "eval_loss": 2.7854502201080322,
+      "eval_runtime": 372.5558,
+      "eval_samples_per_second": 25.44,
+      "eval_steps_per_second": 3.181,
+      "step": 6900
+    },
+    {
+      "epoch": 2.95,
+      "grad_norm": 3.1302738189697266,
+      "learning_rate": 4.541272084805654e-05,
+      "loss": 3.1467,
+      "step": 7000
+    },
+    {
+      "epoch": 2.95,
+      "eval_cer": 0.5148948027061906,
+      "eval_loss": 2.9890220165252686,
+      "eval_runtime": 359.2287,
+      "eval_samples_per_second": 26.384,
+      "eval_steps_per_second": 3.299,
+      "step": 7000
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 1.750848412513733,
+      "learning_rate": 4.5342049469964665e-05,
+      "loss": 2.1825,
+      "step": 7100
+    },
+    {
+      "epoch": 2.99,
+      "eval_cer": 0.5565606546478432,
+      "eval_loss": 3.195390224456787,
+      "eval_runtime": 366.6828,
+      "eval_samples_per_second": 25.848,
+      "eval_steps_per_second": 3.232,
+      "step": 7100
     }
   ],
   "logging_steps": 100,
@@ -1102,7 +1150,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 7.446996872508875e+19,
+  "total_flos": 7.774285790233235e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null