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:b3f06d5a256218c51477ed27f947cc4ddd92361865cb8aece152711a7808d949
+oid sha256:bfdfd19792a9dbd2720aeaed1a4167bc1f2f00c5a2f87732af76a348929cc758
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5af5b1543c2dce0f4a4cff0437e159cd486ffa735a87ccbe8495323aab7239d3
+oid sha256:3275035391a762bc48aec56071648a53c024855788cdf14fff0f522318886b02
 size 42608388

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e319105a9624bf44a15e7fef3006b447aaee5aad98a6dbb41ed242bf9f28e8cc
+oid sha256:0fbf0174a92740940690c194188c669febbb8555816ce6230c570c8e14a577c0
 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": 0.03365534434403241,
+  "epoch": 0.0373948270489249,
   "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": 23.372,
       "eval_steps_per_second": 2.923,
       "step": 81
+    },
+    {
+      "epoch": 0.03490183857899657,
+      "grad_norm": 0.7589036822319031,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.1979,
+      "step": 84
+    },
+    {
+      "epoch": 0.03614833281396074,
+      "grad_norm": 0.6934281587600708,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.3394,
+      "step": 87
+    },
+    {
+      "epoch": 0.0373948270489249,
+      "grad_norm": 0.775426983833313,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.2419,
+      "step": 90
+    },
+    {
+      "epoch": 0.0373948270489249,
+      "eval_loss": 1.2471787929534912,
+      "eval_runtime": 173.3007,
+      "eval_samples_per_second": 23.393,
+      "eval_steps_per_second": 2.926,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.2571664612982784e+16,
+  "total_flos": 3.629126828792218e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null