Training in progress, step 185, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a982ffc522f303c27a661a3c6b07bc6ecf9028d56d4934c408e109cf133f6517
+oid sha256:c9b58cf00ae33d931950ca83d390cce441e85e2e6a88d1037cba299822818883
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf626a3d53d70160de91f85c3f20078e2616061d67ee7b90870c0ae486bb5883
+oid sha256:8a0f5c214d8eef696d9225ce31c5918e21d737ee9b33a2e3528207dadf48babe
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c9e95e8038f40b4d739b9be60c3742d2a869eaba46d8fd74d89cee2de436ed5
+oid sha256:44f07ee7727b2a57ec87aa201844eb2406bc5b699b1d99c8190698d036889705
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7c990948ce2aaf07d64c7544604482e458e5281aa73955448bb3e7dee4b1367
+oid sha256:31cc4c125027b06153274d1c1fcc2291ff49e04af7d8c2cae65dd480bfd90a0c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08802494039977994,
+  "epoch": 0.09047007763310716,
   "eval_steps": 34,
-  "global_step": 180,
+  "global_step": 185,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1315,6 +1315,41 @@
       "learning_rate": 6.75277705956443e-06,
       "loss": 0.8304,
       "step": 180
+    },
+    {
+      "epoch": 0.08851396784644538,
+      "grad_norm": 1.0449199676513672,
+      "learning_rate": 6.1011639384943585e-06,
+      "loss": 1.0186,
+      "step": 181
+    },
+    {
+      "epoch": 0.08900299529311083,
+      "grad_norm": 1.2107876539230347,
+      "learning_rate": 5.481617183918053e-06,
+      "loss": 1.1832,
+      "step": 182
+    },
+    {
+      "epoch": 0.08949202273977627,
+      "grad_norm": 1.49854576587677,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 1.2453,
+      "step": 183
+    },
+    {
+      "epoch": 0.08998105018644172,
+      "grad_norm": 1.2521921396255493,
+      "learning_rate": 4.339558049955927e-06,
+      "loss": 0.9645,
+      "step": 184
+    },
+    {
+      "epoch": 0.09047007763310716,
+      "grad_norm": 1.0324766635894775,
+      "learning_rate": 3.817435682718096e-06,
+      "loss": 0.9331,
+      "step": 185
     }
   ],
   "logging_steps": 1,
@@ -1334,7 +1369,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.990117551990374e+17,
+  "total_flos": 8.212065261767885e+17,
   "train_batch_size": 3,
   "trial_name": null,
   "trial_params": null