Training in progress, step 100, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:000527a3a265b9e05cd020128ba800f14f377bfbabae4998412c2918195d8125
+oid sha256:ba43fe98f8d3b7ca705c5331235c9119803d8672adf399eb15f6da65dea3b778
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6432fe547941a7690c2fe66075c977ac4220863b31602ffec25432621ebfa96
+oid sha256:508479d03e9303aa2871f9ebabe4b89a1e8b2e9436f8c1fd83bb61fe68aeb8f3
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08f69188d3c3cb82763f1a7c417921df2b36ee8c259c8364d649bc865aa50546
+oid sha256:d655e73147f6c05694f6b0b5c2c321535c695e45d8c7329d033e75bc36a25404
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:328cdb13c08312010f0f3f68164c591fc4e8d678a48048f3b4795580c806f456
+oid sha256:7815f17b7bd928390d8a057e2a19101b8f840de5d7f859603bfc35694ee86edf
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.4,
+  "epoch": 0.5,
   "eval_steps": 20,
-  "global_step": 80,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -156,6 +156,43 @@
       "eval_samples_per_second": 393.359,
       "eval_steps_per_second": 65.691,
       "step": 80
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 0.6189765334129333,
+      "learning_rate": 2.680586348883286e-06,
+      "loss": 20.522158813476562,
+      "step": 85
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.5756471157073975,
+      "learning_rate": 2.5229598819076393e-06,
+      "loss": 20.492315673828124,
+      "step": 90
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 0.5617444515228271,
+      "learning_rate": 2.36176106866422e-06,
+      "loss": 20.49109802246094,
+      "step": 95
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.5637349486351013,
+      "learning_rate": 2.198091060500926e-06,
+      "loss": 20.489166259765625,
+      "step": 100
+    },
+    {
+      "epoch": 0.5,
+      "eval_accuracy": 0.0712063492063492,
+      "eval_loss": 10.189505577087402,
+      "eval_runtime": 2.8969,
+      "eval_samples_per_second": 345.191,
+      "eval_steps_per_second": 57.647,
+      "step": 100
     }
   ],
   "logging_steps": 5,