Training in progress, step 2400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00172f6dd05a49b1cf2f8ff023f3ca93980f8b4e3060eeb47e74d8f65933ac36
+oid sha256:44d55abe18136649fb6def532385b4b394d9e108fdf8f4ca57578d416c9b41ef
 size 4978139416

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d59fdb186dd6719014f3267c673ca01c879f220542715dcb5862f4204903bc2
+oid sha256:90c33bc16a6ad0497f092d4c75ded33c7dd30729c9f35a49f646bce7c9c01ac4
 size 3659223436

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbe23e6ec83e38f888ce1b667257f959e02478dbaef89d9e23350f77615b295b
+oid sha256:95c02ba7f38d49e33dc88cf95e4ccb546c08b6fd6a7dddb75eaf0aad68dc9620
 size 17241500333

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39c98aca05a0d374052b7c1cb664ff3eb713201073b7a44e234eb536fbccee1c
+oid sha256:d84eac669e63d3ebd7cbfdaf89ff43149b8b9e94f7d0e66c6ee43cd90c3b778d
 size 14567

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1665cb8324f796c9f90a2705fd01fef5d8ec3fa89b088395f8b2aa4bae6228c2
+oid sha256:b5894c6573565c6328682bcc690a51bee32ff4f44e9c1aa3c075cea5a25453a5
 size 623

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.9261208166701747,
+  "epoch": 1.0103136181856451,
   "eval_steps": 100,
-  "global_step": 2200,
+  "global_step": 2400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -359,6 +359,38 @@
       "eval_samples_per_second": 26.742,
       "eval_steps_per_second": 3.343,
       "step": 2200
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 2.9436004161834717,
+      "learning_rate": 4.87321554770318e-05,
+      "loss": 1.6308,
+      "step": 2300
+    },
+    {
+      "epoch": 0.97,
+      "eval_cer": 0.5162586523796489,
+      "eval_loss": 3.3528623580932617,
+      "eval_runtime": 360.9925,
+      "eval_samples_per_second": 26.255,
+      "eval_steps_per_second": 3.283,
+      "step": 2300
+    },
+    {
+      "epoch": 1.01,
+      "grad_norm": 7.935622692108154,
+      "learning_rate": 4.866148409893993e-05,
+      "loss": 2.4462,
+      "step": 2400
+    },
+    {
+      "epoch": 1.01,
+      "eval_cer": 0.575390579171718,
+      "eval_loss": 2.0690765380859375,
+      "eval_runtime": 343.7001,
+      "eval_samples_per_second": 27.576,
+      "eval_steps_per_second": 3.448,
+      "step": 2400
     }
   ],
   "logging_steps": 100,
@@ -366,7 +398,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 30,
   "save_steps": 100,
-  "total_flos": 2.411832086421037e+19,
+  "total_flos": 2.6422344601189564e+19,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null