Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53d9160b015712ba94ccd85a7b38e39c58afc793a158f770b09eb7189a9c6199
+oid sha256:a941e6b20e406fe49a70015195facd9789aedbea0b44c25f0151a0243cc5c081
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9efcba7e9aecbdd538c26d8c64ec462645f16419b09c47e88ffd8f039f2ae787
+oid sha256:2f79d884a885ab34fedef92671dbe1ae2146e22579459757c2ef1373e61639bd
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e96cbbfd93d2129d3f0a3bd4543365323001975566244f444bd44373f63d1c3
+oid sha256:816a4601e6f061b3c924af3d54ebe883d86531a89df578e78e9d43e92d995eb2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88f387d8c434535a84694e469cebc18f2e722ba31b0dc0372632798b59011377
+oid sha256:bd18e5325bf99a4b662a5314e5f491b65903ffc83b0317f63835d8305a50591e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0430239704978488,
+  "epoch": 0.049170251997541485,
   "eval_steps": 5,
-  "global_step": 35,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,28 @@
       "eval_samples_per_second": 12.709,
       "eval_steps_per_second": 1.594,
       "step": 35
+    },
+    {
+      "epoch": 0.044253226797787336,
+      "grad_norm": 1.4394307136535645,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 0.539,
+      "step": 36
+    },
+    {
+      "epoch": 0.04794099569760295,
+      "grad_norm": 1.472872018814087,
+      "learning_rate": 1.7527597583490822e-05,
+      "loss": 0.4637,
+      "step": 39
+    },
+    {
+      "epoch": 0.049170251997541485,
+      "eval_loss": 0.48103824257850647,
+      "eval_runtime": 107.9289,
+      "eval_samples_per_second": 12.703,
+      "eval_steps_per_second": 1.594,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -167,7 +189,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.468361722953728e+16,
+  "total_flos": 6.298044191263949e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null