Training in progress, step 45, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e539565eda311ff7dfb86a0fcd5ed798927ec325444ad7c0e21458c0341cf06
+oid sha256:3b569eefc4c6896d4d630b634639120775480c4921f003ac58425b50708b473b
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9e080e82da437e01a92adc2bf874e2e5d2de9ee68dc4fb833bf3b8b28d09dbc
+oid sha256:c2f64a5da5ddaa1ef9e1ed90c4244d6efc7cf5a764dc2cd3078277eb72c73691
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41542bf364e876cca9839cdc695a83541c313b7d3530ba38b92062734dc74977
+oid sha256:5ff6af0de44d2814b4db7f4a2ca86f793c003562b5d1e80c06593c1beec43281
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc389ed2ec8a0148b9b29024154a8f2f11c6a7454ef1d0724563562d03a46e01
+oid sha256:9776c8df8be516beee92201f32f4a3f5d90539bf47f8ef27e1636cdc132a851e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.010601487153058971,
+  "epoch": 0.013251858941323713,
   "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": 14.357,
       "eval_steps_per_second": 1.795,
       "step": 36
+    },
+    {
+      "epoch": 0.011484944415813885,
+      "grad_norm": 8.32168960571289,
+      "learning_rate": 3.824798160583012e-05,
+      "loss": 3.6521,
+      "step": 39
+    },
+    {
+      "epoch": 0.0123684016785688,
+      "grad_norm": 5.999353885650635,
+      "learning_rate": 3.5959278669726935e-05,
+      "loss": 3.7375,
+      "step": 42
+    },
+    {
+      "epoch": 0.013251858941323713,
+      "grad_norm": 6.515491485595703,
+      "learning_rate": 3.355050358314172e-05,
+      "loss": 3.1763,
+      "step": 45
+    },
+    {
+      "epoch": 0.013251858941323713,
+      "eval_loss": 0.886064887046814,
+      "eval_runtime": 398.3365,
+      "eval_samples_per_second": 14.36,
+      "eval_steps_per_second": 1.795,
+      "step": 45
     }
   ],
   "logging_steps": 3,
@@ -150,7 +179,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.064758901551923e+16,
+  "total_flos": 6.330948626939904e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null