Training in progress, step 35700, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56ff4705ab488bb59741b0e5c71e9ac05b7326124a2bfb5d7f395e778b9050e3
+oid sha256:977a5c69feae10b912f571de7977009febbf01a0eaa266424ca31544fa3061d4
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bebf964f27f1886af6b09595cbe151e56d1dfb73585f5c75ef9fe367ce5cb5c
+oid sha256:e2957ac18ba2253b8c409a29674b89329d32e320d7a98ce2b81ee8d57641bc16
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43d29c51ee6b98cdc02945191da5c1b40cb5666775063ea99d3215e1a3f3026d
+oid sha256:2b3b488252dd3d31bc05954dcc0188157b4ef2c211110990aacba94eb2fa5123
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7d96028437c689f30c391fd7b819c0717a3f42c10fd6e760f3a8d7f10e65590
-size 14503
+oid sha256:1edf5ffcac2b5407479ae34e05195359730147dee5af532317f0b039b8c166f2
+size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2a895192cf0f0de5099223427191af438af44d9d236e07991f988cd0f9fc2af
+oid sha256:6a8b1f07cc0159a990d1350d3b8aacd4d203ba9556ec73cabc9467bc15b486a5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 14.944222268996,
+  "epoch": 15.028415070511471,
   "eval_steps": 100,
-  "global_step": 35500,
+  "global_step": 35700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -5687,6 +5687,38 @@
       "eval_samples_per_second": 25.72,
       "eval_steps_per_second": 3.216,
       "step": 35500
+    },
+    {
+      "epoch": 14.99,
+      "grad_norm": 3.9734749794006348,
+      "learning_rate": 2.520706713780919e-05,
+      "loss": 0.9122,
+      "step": 35600
+    },
+    {
+      "epoch": 14.99,
+      "eval_cer": 0.3868713581791874,
+      "eval_loss": 2.068138360977173,
+      "eval_runtime": 401.8562,
+      "eval_samples_per_second": 23.586,
+      "eval_steps_per_second": 2.949,
+      "step": 35600
+    },
+    {
+      "epoch": 15.03,
+      "grad_norm": 1.6432957649230957,
+      "learning_rate": 2.513639575971732e-05,
+      "loss": 0.872,
+      "step": 35700
+    },
+    {
+      "epoch": 15.03,
+      "eval_cer": 0.3834226271948692,
+      "eval_loss": 2.0865533351898193,
+      "eval_runtime": 372.0301,
+      "eval_samples_per_second": 25.476,
+      "eval_steps_per_second": 3.185,
+      "step": 35700
     }
   ],
   "logging_steps": 100,
@@ -5694,7 +5726,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 3.89001558499963e+20,
+  "total_flos": 3.9129036959681564e+20,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null