Training in progress, step 120, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba43fe98f8d3b7ca705c5331235c9119803d8672adf399eb15f6da65dea3b778
+oid sha256:058f12df8fdc50c32a197f5f5c952f739fe65ac649ff7a369a57bd28761b307a
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:508479d03e9303aa2871f9ebabe4b89a1e8b2e9436f8c1fd83bb61fe68aeb8f3
+oid sha256:75e7be1ace81f748a01dd0da135950b137996dc9c206f8885eb59fc7fbceefd6
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d655e73147f6c05694f6b0b5c2c321535c695e45d8c7329d033e75bc36a25404
+oid sha256:443907af357cccf92496cdd4e04b21f17558d4acf38fddc732c70cd7db47e70d
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
+oid sha256:cc32de04bd8951ded22e38a3a317dcc3e3d6e420820aadb0c1fc7777161631b4
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5,
+  "epoch": 0.6,
   "eval_steps": 20,
-  "global_step": 100,
+  "global_step": 120,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -193,6 +193,43 @@
       "eval_samples_per_second": 345.191,
       "eval_steps_per_second": 57.647,
       "step": 100
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 0.5826505422592163,
+      "learning_rate": 2.033067889532717e-06,
+      "loss": 20.34880828857422,
+      "step": 105
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.5714936256408691,
+      "learning_rate": 1.8678188313486012e-06,
+      "loss": 20.163304138183594,
+      "step": 110
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 0.7302822470664978,
+      "learning_rate": 1.7034727045763157e-06,
+      "loss": 20.174502563476562,
+      "step": 115
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.6190714836120605,
+      "learning_rate": 1.541152159906497e-06,
+      "loss": 20.209898376464842,
+      "step": 120
+    },
+    {
+      "epoch": 0.6,
+      "eval_accuracy": 0.07126984126984127,
+      "eval_loss": 10.068880081176758,
+      "eval_runtime": 2.8029,
+      "eval_samples_per_second": 356.77,
+      "eval_steps_per_second": 59.581,
+      "step": 120
     }
   ],
   "logging_steps": 5,