Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cd8bc0f43b6c2016911a74853d9957247b20dd159cbd17ae75f2c8a0f96550b
+oid sha256:51d5a8bc392c9d0f1d5cf986589b74c1eb19221d61fae72adf8c596da1491f03
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:586df41a61071e710e1b406cda77a01bc512784ba8fd1e41c24f7fd2c68e3514
+oid sha256:6661dea1374d406bac2bf5367280274569b150f8da71ef2cca046a4e735f38f2
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:99c6874540ab7284054ee4e661d01f877ef78b58f8fb1147d1017f763361b191
+oid sha256:35678f2e164dea4ebbafdb4df13644ad3b9d103a7e957de1eef9bc9540a6bd78
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.003536212172730364,
+  "epoch": 0.007072424345460728,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 3.727,
       "eval_steps_per_second": 1.864,
       "step": 10
+    },
+    {
+      "epoch": 0.004080244814688882,
+      "grad_norm": 3.246471643447876,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.6778,
+      "step": 15
+    },
+    {
+      "epoch": 0.005440326419585175,
+      "grad_norm": 1.4093425273895264,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 1.5614,
+      "step": 20
+    },
+    {
+      "epoch": 0.005440326419585175,
+      "eval_loss": 1.3004555702209473,
+      "eval_runtime": 385.7674,
+      "eval_samples_per_second": 4.013,
+      "eval_steps_per_second": 2.006,
+      "step": 20
+    },
+    {
+      "epoch": 0.006800408024481469,
+      "grad_norm": 1.8904144763946533,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 1.2113,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2635674956070912.0,
+  "total_flos": 5225110000631808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null