Training in progress, step 180, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5e352bbc53dcdadcadec8245e6c4f457ebf7790fac51411b3b999cf44649beb
+oid sha256:12cdf2f4883dfe1cb904465c7a4280e60176df37be64c2c0be202f1ddef6d40d
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a9d95665e37557687138c324ea96e1690e085e25829ffe4d8d0d87a57bee2f6
+oid sha256:dc49098fa120abedb28fd7ea6da1802cfe2e944fb530ea93e0b43c79a14ae2c2
 size 1386414411

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:134a484e532ba4537112198f3087f08c6b36bc828e582ece1b5ba2be14f856b0
+oid sha256:204484338aec1b64d23614eb2933e81e590b07783a7ad537045df85e45aa13d1
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c40d5e94eed411043d006187ef3d57f655338dfd7cfaaf34e38342dbbae53acc
+oid sha256:f420a398e501a060ab026373fbb64a49ebca6f8ce9e0b9e60155447b04592b02
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7,
+  "epoch": 0.9,
   "eval_steps": 20,
-  "global_step": 140,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -267,6 +267,80 @@
       "eval_samples_per_second": 170.824,
       "eval_steps_per_second": 28.528,
       "step": 140
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 3.915391683578491,
+      "learning_rate": 7.978377054339498e-07,
+      "loss": 18.57097473144531,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 3.8307833671569824,
+      "learning_rate": 6.699508557723032e-07,
+      "loss": 18.58392333984375,
+      "step": 150
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 3.8549070358276367,
+      "learning_rate": 5.511495904178221e-07,
+      "loss": 18.670741271972656,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.9556758403778076,
+      "learning_rate": 4.4224544247577535e-07,
+      "loss": 18.56670227050781,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.07810371819960861,
+      "eval_loss": 9.292845726013184,
+      "eval_runtime": 5.9755,
+      "eval_samples_per_second": 167.349,
+      "eval_steps_per_second": 27.947,
+      "step": 160
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 3.857797145843506,
+      "learning_rate": 3.439823377039599e-07,
+      "loss": 18.518038940429687,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.037227153778076,
+      "learning_rate": 2.570315127454452e-07,
+      "loss": 18.696867370605467,
+      "step": 170
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 3.76861572265625,
+      "learning_rate": 1.8198692990167497e-07,
+      "loss": 18.457827758789062,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 3.7363455295562744,
+      "learning_rate": 1.1936121976767767e-07,
+      "loss": 18.609834289550783,
+      "step": 180
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.07823287671232877,
+      "eval_loss": 9.286931037902832,
+      "eval_runtime": 5.7992,
+      "eval_samples_per_second": 172.439,
+      "eval_steps_per_second": 28.797,
+      "step": 180
     }
   ],
   "logging_steps": 5,