Training in progress, step 180, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c6e2ac9f8a2ad3476e171fd08f07b0b8f23c6bd8293be2a79d76677a206d830
+oid sha256:a982ffc522f303c27a661a3c6b07bc6ecf9028d56d4934c408e109cf133f6517
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:73f348b4c9f60ffb3e93dfe2f4b1adc4c42952d961aeec51271f487b7722d78f
+oid sha256:bf626a3d53d70160de91f85c3f20078e2616061d67ee7b90870c0ae486bb5883
 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": 0.8914,
       "step": 175
+    },
+    {
+      "epoch": 0.08606883061311817,
+      "grad_norm": 1.2630629539489746,
+      "learning_rate": 9.675280065387116e-06,
+      "loss": 1.0159,
+      "step": 176
+    },
+    {
+      "epoch": 0.08655785805978361,
+      "grad_norm": 1.059738278388977,
+      "learning_rate": 8.897735075391155e-06,
+      "loss": 0.897,
+      "step": 177
+    },
+    {
+      "epoch": 0.08704688550644905,
+      "grad_norm": 1.183966875076294,
+      "learning_rate": 8.151301425407699e-06,
+      "loss": 0.9258,
+      "step": 178
+    },
+    {
+      "epoch": 0.0875359129531145,
+      "grad_norm": 1.2419488430023193,
+      "learning_rate": 7.43623402184438e-06,
+      "loss": 0.9676,
+      "step": 179
+    },
+    {
+      "epoch": 0.08802494039977994,
+      "grad_norm": 1.0326918363571167,
+      "learning_rate": 6.75277705956443e-06,
+      "loss": 0.8304,
+      "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