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:a2ec2b1acd34a1b01c633790af1383f3b67590c58e1699ed9f24b44e352e68ba
+oid sha256:29641d0bbac95a39f7e20f68adef4f33e46ad91075e80207b525ce3a5fb74693
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d984dc539b2c1068d587b192186ab89e395ce828cda0de6691f928cb96a09f0f
+oid sha256:f9d69737c02da5771cb21474d7563fa6f5da86b166661e5bf633e46c9269a597
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:224a90a2f544a35e77f0f9ea94aa164e3293b43c60cb46b8c479e6d653e1c2d5
+oid sha256:4213eba836dc2866a95f6390ed6dbd9770a2bc1b9262f2a5ee50bdded503aa1f
 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": 0.03145631067961165,
+  "epoch": 0.03495145631067961,
   "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": 13.186,
       "eval_steps_per_second": 1.651,
       "step": 81
+    },
+    {
+      "epoch": 0.03262135922330097,
+      "grad_norm": 0.20901484787464142,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.9298,
+      "step": 84
+    },
+    {
+      "epoch": 0.03378640776699029,
+      "grad_norm": 0.20851711928844452,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 2.0929,
+      "step": 87
+    },
+    {
+      "epoch": 0.03495145631067961,
+      "grad_norm": 0.2006189227104187,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 2.0554,
+      "step": 90
+    },
+    {
+      "epoch": 0.03495145631067961,
+      "eval_loss": 2.0384538173675537,
+      "eval_runtime": 328.9687,
+      "eval_samples_per_second": 13.184,
+      "eval_steps_per_second": 1.651,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2156239828798669e+17,
+  "total_flos": 1.3463362391035085e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null