Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8602602d27b89a8d5aa06cbaaa7afce4df95670e302824b14d2d995dc4681680
+oid sha256:bf5e83c9f668f143045b7e712b6becfb047e352aab5f8f247cdcb4f21d053935
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dba108f0cdce82ad3e2cd068b6f849f104457a9e357302d101aa78149d8dd441
+oid sha256:8d0022983c36cf549bb057ef164a94431bed75147cfb8f0a2a08e9ef04de8073
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04232fce99c4802dc579b85d4a7938b6bd47a3fd2dae4192a67625460029c733
+oid sha256:d3a4727fa7da0a3e59c7defeb7e64defa73c0226717a3e4b04dceff9b03ea297
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:67680b8b35ea230d53acee387012f8809825a2c511bd41340f42320f849e349d
+oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.004890274466654441,
+  "epoch": 0.007335411699981661,
   "eval_steps": 34,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -85,6 +85,41 @@
       "learning_rate": 6.666666666666667e-05,
       "loss": 9.2624,
       "step": 10
+    },
+    {
+      "epoch": 0.005379301913319885,
+      "grad_norm": Infinity,
+      "learning_rate": 7.333333333333333e-05,
+      "loss": 8.4931,
+      "step": 11
+    },
+    {
+      "epoch": 0.005868329359985329,
+      "grad_norm": Infinity,
+      "learning_rate": 8e-05,
+      "loss": 9.3205,
+      "step": 12
+    },
+    {
+      "epoch": 0.006357356806650773,
+      "grad_norm": Infinity,
+      "learning_rate": 8.666666666666667e-05,
+      "loss": 9.8934,
+      "step": 13
+    },
+    {
+      "epoch": 0.0068463842533162175,
+      "grad_norm": Infinity,
+      "learning_rate": 9.333333333333334e-05,
+      "loss": 9.1796,
+      "step": 14
+    },
+    {
+      "epoch": 0.007335411699981661,
+      "grad_norm": 1.2167695950759854e+19,
+      "learning_rate": 0.0001,
+      "loss": 9.3987,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -104,7 +139,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.204479675957248e+16,
+  "total_flos": 3.306719513935872e+16,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null