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:f2520ffc11a61c8037203be35ec39942651517eed41a609f20c7cb8f39f43c4b
+oid sha256:8c7f9356eb32fa848d5be29cdd7b4f5c93742c19c282b8dac9445551a61b9c69
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e3c32decfbbe706bda1f341a96bf8054129432b2858701cbb19b6826f9f5b40
+oid sha256:3da4b43998cc262088e7c2d966ef40123bfe05149e62a282f435f1661cfcdeb0
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8db6ccf05d1fba30394801680aa5102c125ee030f3a6897788325ecbe3de090a
+oid sha256:624f33a8825fe91cf75494eb380d78794d533169c1a0c48e642c8c4930913984
 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": 0.03007239651011695,
+  "epoch": 0.033413773900129944,
   "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": 44.343,
       "eval_steps_per_second": 5.551,
       "step": 81
+    },
+    {
+      "epoch": 0.031186188973454612,
+      "grad_norm": 0.9139003157615662,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 2.7478,
+      "step": 84
+    },
+    {
+      "epoch": 0.032299981436792274,
+      "grad_norm": 0.9888792634010315,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 2.7967,
+      "step": 87
+    },
+    {
+      "epoch": 0.033413773900129944,
+      "grad_norm": 0.8691554665565491,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 2.7622,
+      "step": 90
+    },
+    {
+      "epoch": 0.033413773900129944,
+      "eval_loss": 2.7512753009796143,
+      "eval_runtime": 102.3046,
+      "eval_samples_per_second": 44.348,
+      "eval_steps_per_second": 5.552,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8088906718248960.0,
+  "total_flos": 8994737136599040.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null