Training in progress, step 20, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e11f5f81828c181532b1f761742c9c124a2fc283791b1310c12df69bfb00094
+oid sha256:7eadee4ebe800fa691214be7857fcfe10fe82b86351955878498e9f8e40bc735
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42e4a163723197834015430b5f2293c3312332636ec548b4a2d95055b0baa04c
+oid sha256:0ac44e1e06d6c7b9ab5257395e1650b841528708459b68719bfb341fb9f24a5c
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9d1ea809ba32b7efd678ae04203f4d557f85f71b36f396a16e0baf7241d69c8
+oid sha256:97bd3d1a2f58ae7c5971df94ab38f5e952b7947bc754ebd01bb0045964a824d2
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889f6fc92910dc1617d7e2b8e49ec9358ef58d2162623ab1d55db477fded32fc
+oid sha256:ad4a07c066075e0a1b5d9477b0d2f4d6bab07235ad5efe05720caa179d7171b5
 size 1465

last-checkpoint/trainer_state.json

@@ -2,86 +2,49 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2,
+  "epoch": 0.1,
   "eval_steps": 20,
-  "global_step": 40,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
       "epoch": 0.025,
-      "grad_norm": 0.2323141247034073,
+      "grad_norm": 0.23910726606845856,
       "learning_rate": 1.6e-06,
-      "loss": 21.980325317382814,
+      "loss": 21.99029541015625,
       "step": 5
     },
     {
       "epoch": 0.05,
-      "grad_norm": 0.2334250658750534,
+      "grad_norm": 0.2298264056444168,
       "learning_rate": 3.6e-06,
-      "loss": 21.9706298828125,
+      "loss": 21.960894775390624,
       "step": 10
     },
     {
       "epoch": 0.075,
-      "grad_norm": 0.22430387139320374,
+      "grad_norm": 0.21482999622821808,
       "learning_rate": 3.995627254437549e-06,
-      "loss": 21.961314392089843,
+      "loss": 21.95319061279297,
       "step": 15
     },
     {
       "epoch": 0.1,
-      "grad_norm": 0.2190800905227661,
+      "grad_norm": 0.21504534780979156,
       "learning_rate": 3.9778957412029366e-06,
-      "loss": 21.96648712158203,
+      "loss": 21.970616149902344,
       "step": 20
     },
     {
       "epoch": 0.1,
-      "eval_accuracy": 3.131115459882583e-05,
-      "eval_loss": 10.98162841796875,
-      "eval_runtime": 6.0042,
-      "eval_samples_per_second": 166.549,
-      "eval_steps_per_second": 27.814,
+      "eval_accuracy": 1.3698630136986302e-05,
+      "eval_loss": 10.982390403747559,
+      "eval_runtime": 5.4511,
+      "eval_samples_per_second": 183.448,
+      "eval_steps_per_second": 30.636,
       "step": 20
-    },
-    {
-      "epoch": 0.125,
-      "grad_norm": 0.21648378670215607,
-      "learning_rate": 3.9466531944960116e-06,
-      "loss": 21.956903076171876,
-      "step": 25
-    },
-    {
-      "epoch": 0.15,
-      "grad_norm": 0.2288612723350525,
-      "learning_rate": 3.902113032590307e-06,
-      "loss": 21.954676818847656,
-      "step": 30
-    },
-    {
-      "epoch": 0.175,
-      "grad_norm": 0.22517967224121094,
-      "learning_rate": 3.844579509954769e-06,
-      "loss": 21.96697540283203,
-      "step": 35
-    },
-    {
-      "epoch": 0.2,
-      "grad_norm": 0.22221730649471283,
-      "learning_rate": 3.7744456388872234e-06,
-      "loss": 21.957220458984374,
-      "step": 40
-    },
-    {
-      "epoch": 0.2,
-      "eval_accuracy": 2.7397260273972603e-05,
-      "eval_loss": 10.978096961975098,
-      "eval_runtime": 5.4308,
-      "eval_samples_per_second": 184.136,
-      "eval_steps_per_second": 30.751,
-      "step": 40
     }
   ],
   "logging_steps": 5,