Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c5af4fbd708855d047ed9132348f9ade5ce636a41af46ca9a4ea0fe93e7e472
+oid sha256:b339114520bc208240d5d665bb88281a09b224f895299bf58b1229a3ed3560b0
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d015c6417a96a4e99e188f862b293740512140b5d17ff0af04d5f4ebee5d3d7c
+oid sha256:624874b924612a2f49388c49d95a1f3f80bbdc68ca2bf1803f5cf49779230c5e
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b976fcea21ecae35d2f32d796d38bd98366e20e84ccdb0d2228cd4768022150
+oid sha256:870045ee41e486d3800f98faf923539d627e3723ce5d5eb4a288b7e03af54db6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
+oid sha256:e53b95eff99f2334cbf7ed4c962db83cb42e931305982518e928382563b5670d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.4210526315789473,
+  "epoch": 1.6578947368421053,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 14.041,
       "eval_steps_per_second": 1.755,
       "step": 54
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 6.90402364730835,
+      "learning_rate": 4.6512176312793736e-05,
+      "loss": 2.3836,
+      "step": 57
+    },
+    {
+      "epoch": 1.5789473684210527,
+      "grad_norm": 7.729911804199219,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.1328,
+      "step": 60
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "grad_norm": 8.159226417541504,
+      "learning_rate": 3.6218132209150045e-05,
+      "loss": 2.2059,
+      "step": 63
+    },
+    {
+      "epoch": 1.6578947368421053,
+      "eval_loss": 0.771750271320343,
+      "eval_runtime": 4.5594,
+      "eval_samples_per_second": 14.037,
+      "eval_steps_per_second": 1.755,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.563045332267827e+16,
+  "total_flos": 8.828679879445709e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null