Training in progress, step 9040, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:630a910b2d5b8c9504add11b070a2b95445874621f6de2ea3077628d0553ffe3
+oid sha256:ba139240646f433f9f0106d855aea9e350f07f031693b316743dd388f006a45a
 size 13982248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da3ec0e6441f43d24431895b711504845f578f35580f2b0f333b91a363d641c1
+oid sha256:cd6c424fd81f222bd0b9ad0388c7d2dd3efa61cf565f0946a945da841c18c43f
 size 7062522

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e3f344cbf26501e998b8de868d6d509ad3fe3171ec390a602388814ddd9df38
+oid sha256:1ac19e6550ed28e30f1e0773f61b5a93cb672dde550a8914d4067b84caffee97
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dde4a2f54c5119ed26c871b2368383ec34337eb67d04dfb138caacf14a881ef
+oid sha256:3bb2ad4299490e0d014e4083d00933053d6f0c483383ad6b71adbd0a8a72b6c2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.712,
+  "epoch": 0.7232,
   "eval_steps": 500,
-  "global_step": 8900,
+  "global_step": 9040,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3122,6 +3122,55 @@
       "learning_rate": 1.8371635972030942e-05,
       "loss": 3.4938,
       "step": 8900
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 25.6701602935791,
+      "learning_rate": 1.8324280212401316e-05,
+      "loss": 3.3931,
+      "step": 8920
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 27.28550148010254,
+      "learning_rate": 1.8276889582645278e-05,
+      "loss": 3.426,
+      "step": 8940
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 26.73450469970703,
+      "learning_rate": 1.8229464579868124e-05,
+      "loss": 3.4074,
+      "step": 8960
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 30.16777992248535,
+      "learning_rate": 1.818200570153568e-05,
+      "loss": 3.4204,
+      "step": 8980
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 30.022031784057617,
+      "learning_rate": 1.813451344546913e-05,
+      "loss": 3.4905,
+      "step": 9000
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 34.67860412597656,
+      "learning_rate": 1.8086988309839755e-05,
+      "loss": 3.4165,
+      "step": 9020
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 26.23653793334961,
+      "learning_rate": 1.8039430793163753e-05,
+      "loss": 3.5014,
+      "step": 9040
     }
   ],
   "logging_steps": 20,
@@ -3129,7 +3178,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2,
   "save_steps": 20,
-  "total_flos": 2.103984238922957e+16,
+  "total_flos": 2.1373183266914304e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null