Training in progress, step 180, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc5bdefdaf7ffa59db1d2244a9bf82cb79bb779b47177bfcfe82cbe4e23b05d1
+oid sha256:8baa3e919a54dcc5cb6ec49da621459e4ad270542313a75432e2ab7cd7070880
 size 847599616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27b83988569e6745308f920b05adabfd2539a9e6e063c09c7eb24770d002a296
+oid sha256:8e93d6072d9f7ae5e857bae76cd9d23e8855013f04a94200ed3b0eefe0c65b5b
 size 350603

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c247b88b6d33018a1baf3f963dc59f2afb08b3ad86ca462a6417c10f3bb5cf51
+oid sha256:bfe80a37e35b074d0f6fac17adedf8f085ded943f9e14bd5132ae4aa50fdab05
 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": 403.514,
       "eval_steps_per_second": 67.387,
       "step": 140
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 0.5626335740089417,
+      "learning_rate": 7.978377054339498e-07,
+      "loss": 9.81540298461914,
+      "step": 145
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.6244388818740845,
+      "learning_rate": 6.699508557723032e-07,
+      "loss": 9.826517486572266,
+      "step": 150
+    },
+    {
+      "epoch": 0.775,
+      "grad_norm": 0.42718568444252014,
+      "learning_rate": 5.511495904178221e-07,
+      "loss": 9.802256774902343,
+      "step": 155
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.49181056022644043,
+      "learning_rate": 4.4224544247577535e-07,
+      "loss": 9.826921081542968,
+      "step": 160
+    },
+    {
+      "epoch": 0.8,
+      "eval_accuracy": 0.06917460317460318,
+      "eval_loss": 9.880888938903809,
+      "eval_runtime": 2.7588,
+      "eval_samples_per_second": 362.472,
+      "eval_steps_per_second": 60.533,
+      "step": 160
+    },
+    {
+      "epoch": 0.825,
+      "grad_norm": 0.3924960196018219,
+      "learning_rate": 3.439823377039599e-07,
+      "loss": 9.826522064208984,
+      "step": 165
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 0.49641576409339905,
+      "learning_rate": 2.570315127454452e-07,
+      "loss": 9.729110717773438,
+      "step": 170
+    },
+    {
+      "epoch": 0.875,
+      "grad_norm": 0.5071141123771667,
+      "learning_rate": 1.8198692990167497e-07,
+      "loss": 9.658553314208984,
+      "step": 175
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.46363547444343567,
+      "learning_rate": 1.1936121976767767e-07,
+      "loss": 9.751717376708985,
+      "step": 180
+    },
+    {
+      "epoch": 0.9,
+      "eval_accuracy": 0.07192063492063493,
+      "eval_loss": 9.793752670288086,
+      "eval_runtime": 2.5596,
+      "eval_samples_per_second": 390.681,
+      "eval_steps_per_second": 65.244,
+      "step": 180
     }
   ],
   "logging_steps": 5,