Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f10956559ddcc1858de436718b61e88d983c31b739241f62bf2aeb2e55b95468
+oid sha256:d768403fcfb617fe34073dfb52dfe810cbdbccf391602df08632a02345039e0f
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36903ebc47e8e6525e4cfda38fe11529097cf77e0c27899ce23b81267ca2d64f
+oid sha256:c10d4fe5917e5fa3c29b10c86cb7e36d4c6f70ffd44c5003dff27449ecc22b8e
 size 325339796

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c9dcf86e5aad657c57e87a1932f4a8e0e6b985edf560ef7f033ecd4b291d2bc
+oid sha256:45d043d62a4cba77426cc95ca86e9b38e53f58bf27a518629dab70faebd68e40
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:d37b0dad6b9c48822da5c83a071d50252502799ad22c4c4907147ad4e4f8e2f4
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03374957813027337,
+  "epoch": 0.040499493756328046,
   "eval_steps": 5,
-  "global_step": 25,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -111,6 +111,28 @@
       "eval_samples_per_second": 4.335,
       "eval_steps_per_second": 0.542,
       "step": 25
+    },
+    {
+      "epoch": 0.03644954438069524,
+      "grad_norm": 7.262444019317627,
+      "learning_rate": 6.167226819279528e-05,
+      "loss": 4.614,
+      "step": 27
+    },
+    {
+      "epoch": 0.040499493756328046,
+      "grad_norm": 7.796113014221191,
+      "learning_rate": 5e-05,
+      "loss": 4.012,
+      "step": 30
+    },
+    {
+      "epoch": 0.040499493756328046,
+      "eval_loss": 1.0315279960632324,
+      "eval_runtime": 287.8886,
+      "eval_samples_per_second": 4.335,
+      "eval_steps_per_second": 0.542,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -130,7 +152,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6.519492429899366e+16,
+  "total_flos": 7.816738372583424e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null