Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b339114520bc208240d5d665bb88281a09b224f895299bf58b1229a3ed3560b0
+oid sha256:8f50ac2845723ac438a556f00aff72e72ee7529e661ae0dad230397ef7a0bc8a
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:624874b924612a2f49388c49d95a1f3f80bbdc68ca2bf1803f5cf49779230c5e
+oid sha256:d5e09c3b6b818e713e35dd87a7ddcb10209449cb73aa1d0e9e27b090782924c7
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870045ee41e486d3800f98faf923539d627e3723ce5d5eb4a288b7e03af54db6
+oid sha256:a81bf9124ac119638eb2b25660fa97a60b2fab63f08197bcec7a4693d4aa6edc
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
+oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.6578947368421053,
+  "epoch": 1.8947368421052633,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 14.037,
       "eval_steps_per_second": 1.755,
       "step": 63
+    },
+    {
+      "epoch": 1.736842105263158,
+      "grad_norm": 9.652267456054688,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2225,
+      "step": 66
+    },
+    {
+      "epoch": 1.8157894736842106,
+      "grad_norm": 8.405353546142578,
+      "learning_rate": 2.6526421860705473e-05,
+      "loss": 2.1885,
+      "step": 69
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 8.815597534179688,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.3782,
+      "step": 72
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "eval_loss": 0.7682980298995972,
+      "eval_runtime": 4.5642,
+      "eval_samples_per_second": 14.022,
+      "eval_steps_per_second": 1.753,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.828679879445709e+16,
+  "total_flos": 1.009431442662359e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null