Training in progress, step 180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d9ef8895aecefde27b9815938ee8b70b7cb60258c13c343c6f4409007de4b8f
+oid sha256:e02a42948b13a1783128ccd70b47ddc0998cf4588b0fbb53b48b0d92c8e09f1d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:19e5799f46aa4ac27c728572da7de1ddb0568e884989194df0340fe82104010e
+oid sha256:30306307f8da5309806edc2f06c365a1874ad8afd38a0e67925ef2af47263c38
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:350629c8726cd8603e94d6658b9108dc8785e8448290744abeabee7c4b3b48d6
+oid sha256:6c9e95e8038f40b4d739b9be60c3742d2a869eaba46d8fd74d89cee2de436ed5
 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": 0.9053,
       "step": 175
+    },
+    {
+      "epoch": 0.08606883061311817,
+      "grad_norm": 0.46799540519714355,
+      "learning_rate": 9.675280065387116e-06,
+      "loss": 0.9817,
+      "step": 176
+    },
+    {
+      "epoch": 0.08655785805978361,
+      "grad_norm": 0.28441375494003296,
+      "learning_rate": 8.897735075391155e-06,
+      "loss": 0.8335,
+      "step": 177
+    },
+    {
+      "epoch": 0.08704688550644905,
+      "grad_norm": 0.3706384301185608,
+      "learning_rate": 8.151301425407699e-06,
+      "loss": 0.9957,
+      "step": 178
+    },
+    {
+      "epoch": 0.0875359129531145,
+      "grad_norm": 0.2594084143638611,
+      "learning_rate": 7.43623402184438e-06,
+      "loss": 0.8361,
+      "step": 179
+    },
+    {
+      "epoch": 0.08802494039977994,
+      "grad_norm": 0.48771926760673523,
+      "learning_rate": 6.75277705956443e-06,
+      "loss": 0.9614,
+      "step": 180
     }
   ],
   "logging_steps": 1,
@@ -1299,7 +1334,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.768169842212864e+17,
+  "total_flos": 7.990117551990374e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null