Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2102bdccfa92e2b5761b882a02028c85086ccc363a1fec210e4309baef3b8022
+oid sha256:0c9b49267611c28873d1e32cb4e321124736f57e557d6f1ba51207105290a8fb
 size 119597408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fd8c3012796410d017b8659828645dd3901f32fc9f7b676f0269080f468354a
+oid sha256:540311b374a55884169421a720df9ca0813ae4df1f5e969ded221076d1c1f322
 size 61226900

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d8d5251bb4ef4ac83eff64f5333bb4e8c08cd1cfc5374d9340295609449cc6a
+oid sha256:4113907f573f13a4eb77451ec757e362203537ff65f1605b35ace456a051ebb3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b09cef78339a08679f2a6cf4a4b56eca3094fb6b859867afd839be3db1415460
+oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.42105263157894735,
+  "epoch": 0.5263157894736842,
   "eval_steps": 9,
-  "global_step": 36,
+  "global_step": 45,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -131,6 +131,35 @@
       "eval_samples_per_second": 10.475,
       "eval_steps_per_second": 1.309,
       "step": 36
+    },
+    {
+      "epoch": 0.45614035087719296,
+      "grad_norm": 0.38964855670928955,
+      "learning_rate": 7.649596321166024e-05,
+      "loss": 5.4978,
+      "step": 39
+    },
+    {
+      "epoch": 0.49122807017543857,
+      "grad_norm": 0.6319313049316406,
+      "learning_rate": 7.191855733945387e-05,
+      "loss": 5.203,
+      "step": 42
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "grad_norm": 0.43766701221466064,
+      "learning_rate": 6.710100716628344e-05,
+      "loss": 5.3021,
+      "step": 45
+    },
+    {
+      "epoch": 0.5263157894736842,
+      "eval_loss": 1.351959466934204,
+      "eval_runtime": 13.7383,
+      "eval_samples_per_second": 10.482,
+      "eval_steps_per_second": 1.31,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.311903077236736e+16,
+  "total_flos": 6.63987884654592e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null