Training in progress, step 180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2adc63d86867e32465a08e11669c0a4e78070b9fa85d80367570bde7d84dacf2
+oid sha256:6cf9f62c97bc69979d43d7955c251245b3c67669f501852590ddde129aee9910
 size 59827904

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d66bb8cca73946291d31c3520cba26cfb1869a9b08802c3706ee0d79b7a5ea58
+oid sha256:09ee501433b9a6276dac9d57d544a756cf1d137ec824995444d026ff1146436c
 size 30875540

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be9ec3198a68ec65f16686b0f1d5a6ba174d2aca875621b68207c99c69128ae9
+oid sha256:6362b09e58588bf4bb998fe89b4e73cad56d76d2d176c7abc6cfafe3bad8a094
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:416d32fdf638b555a0fc031fb149fd18abaec9c234026f168a4a4bd45704a2a9
+oid sha256:b7c990948ce2aaf07d64c7544604482e458e5281aa73955448bb3e7dee4b1367
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08557980316645272,
+  "epoch": 0.08802494039977994,
   "eval_steps": 34,
-  "global_step": 175,
+  "global_step": 180,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1280,6 +1280,41 @@
       "learning_rate": 1.0483670864493778e-05,
       "loss": 10.0142,
       "step": 175
+    },
+    {
+      "epoch": 0.08606883061311817,
+      "grad_norm": 2.5997136051379896e+18,
+      "learning_rate": 9.675280065387116e-06,
+      "loss": 7.8569,
+      "step": 176
+    },
+    {
+      "epoch": 0.08655785805978361,
+      "grad_norm": Infinity,
+      "learning_rate": 8.897735075391155e-06,
+      "loss": 10.2652,
+      "step": 177
+    },
+    {
+      "epoch": 0.08704688550644905,
+      "grad_norm": Infinity,
+      "learning_rate": 8.151301425407699e-06,
+      "loss": 9.1787,
+      "step": 178
+    },
+    {
+      "epoch": 0.0875359129531145,
+      "grad_norm": Infinity,
+      "learning_rate": 7.43623402184438e-06,
+      "loss": 9.7712,
+      "step": 179
+    },
+    {
+      "epoch": 0.08802494039977994,
+      "grad_norm": Infinity,
+      "learning_rate": 6.75277705956443e-06,
+      "loss": 9.1567,
+      "step": 180
     }
   ],
   "logging_steps": 1,
@@ -1299,7 +1334,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.857839432925184e+17,
+  "total_flos": 3.9680634167230464e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null