Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b7b75f8a69719f02aabdde3890302e64a78270e61f2930ec42ddef7c987205
+oid sha256:011f2fa1804cf06633a00a7a340bc577f7cf2a2f2356ff8a1a852362b187f337
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61e77a2dfd19149078ca60a1a056168fe7aeb6992d3ffe0f5dff4f95a97b1844
+oid sha256:28824361622dadb9e986b9630682f3ab9f714e086bbf31e90f3962656cf48498
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b53631aca5988ded2036ea1ce057477819ab800bef8504147b5dfe41db924add
+oid sha256:d94dedff251b37d3b090b8c13e70a9c3f92acb67b4b99bcf80e06219fec51151
 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": 0.5827338129496403,
+  "epoch": 0.6474820143884892,
   "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": 12.077,
       "eval_steps_per_second": 1.548,
       "step": 81
+    },
+    {
+      "epoch": 0.60431654676259,
+      "grad_norm": 1.9092354774475098,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 3.9762,
+      "step": 84
+    },
+    {
+      "epoch": 0.6258992805755396,
+      "grad_norm": 2.086115837097168,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 4.1775,
+      "step": 87
+    },
+    {
+      "epoch": 0.6474820143884892,
+      "grad_norm": 2.177617311477661,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 4.2366,
+      "step": 90
+    },
+    {
+      "epoch": 0.6474820143884892,
+      "eval_loss": 1.0106626749038696,
+      "eval_runtime": 19.3765,
+      "eval_samples_per_second": 12.076,
+      "eval_steps_per_second": 1.548,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.367586874935214e+17,
+  "total_flos": 1.5398536021121434e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null