Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b88984ff2c255a6aea22336623112adf560ad5da70b2277d2487cc88b911fc5
+oid sha256:b502e19105e8e4324eb822c2cb279ebc41823b0d5775653e7c90d3dfb312964e
 size 72396376

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:950cb4c0ae702d83a6bfc0ebb6c274a359cc8c647b23a5847551fa2d6e41311a
+oid sha256:1d599903f1e48d5e966b11907fa9bd4da4a8adfed06de75f9055bebf8a55eb1f
 size 37134420

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc5b46941094ef30ee274a3b487078fe515f123e828c349f90e03dee41cc38e2
+oid sha256:57fcc930ed6aa822432f240a0030f67a2b3c586a79bdd7dc125c1ff972778eec
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16338880484114976,
+  "epoch": 0.1815431164901664,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 17.583,
       "eval_steps_per_second": 2.211,
       "step": 81
+    },
+    {
+      "epoch": 0.16944024205748864,
+      "grad_norm": 0.07050218433141708,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.3745,
+      "step": 84
+    },
+    {
+      "epoch": 0.17549167927382753,
+      "grad_norm": 0.08755092322826385,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.383,
+      "step": 87
+    },
+    {
+      "epoch": 0.1815431164901664,
+      "grad_norm": 0.07090733200311661,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.2869,
+      "step": 90
+    },
+    {
+      "epoch": 0.1815431164901664,
+      "eval_loss": 1.304002285003662,
+      "eval_runtime": 47.4951,
+      "eval_samples_per_second": 17.581,
+      "eval_steps_per_second": 2.211,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.18781204997079e+16,
+  "total_flos": 5.764235611078656e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null