Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:380f08ab32010d6fe11a53ab351050291953fedb116a7277e2843bd4f6582f55
+oid sha256:989083296434928f43ed9a70e5209904853c84f2fe79dd46eaaf75a623c1c612
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a32edd2489574518e0200e545f1d6666a3dfda3c078dd03ba171eaca2f004a5
+oid sha256:bb29b665aa2a08cbcaf98b95af1daca25364564535eb5b22d2904b2f0cd20b8d
 size 43127525

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3c5be0654e1f24601c2bc652b3ec070468a284c4b667eeda9c51ced25c95e6
+oid sha256:14771e8b5dca1bdad12c90b67c90f4f7fb7649a9f36b36bc35e42fde4ce0f3eb
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6479e3863717204c87adedee1441b5a8610be4e4328e7c73664485cf28fb3e20
+oid sha256:5725349df08941ce3ad094aef227575807c35b00023b923686388db7b0fecb5b
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a047a4f72eccdbb2b5fa25ef9898708ca9cc71f79b88f4e3ecd8e10e64db0481
+oid sha256:46d0e3fbb61b4936b37d5244c65578d229675919411e13774b1f2e5dd30f5838
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 50,
   "best_metric": 1.952015995979309,
   "best_model_checkpoint": "/tmp/checkpoints_/job_770d3d41-3bcd-47ca-8265-a07b315f88da/checkpoint-50",
-  "epoch": 0.8,
+  "epoch": 0.9,
   "eval_steps": 10,
-  "global_step": 80,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -632,6 +632,84 @@
       "eval_samples_per_second": 3.08,
       "eval_steps_per_second": 0.801,
       "step": 80
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 3.591055154800415,
+      "learning_rate": 1.1578947368421053e-05,
+      "loss": 0.2746422588825226,
+      "step": 81
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 4.242494583129883,
+      "learning_rate": 1.1052631578947368e-05,
+      "loss": 0.2333741933107376,
+      "step": 82
+    },
+    {
+      "epoch": 0.83,
+      "grad_norm": 2.425588607788086,
+      "learning_rate": 1.0526315789473684e-05,
+      "loss": 0.10867268592119217,
+      "step": 83
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 4.30889892578125,
+      "learning_rate": 1e-05,
+      "loss": 0.21931734681129456,
+      "step": 84
+    },
+    {
+      "epoch": 0.85,
+      "grad_norm": 4.7018842697143555,
+      "learning_rate": 9.473684210526317e-06,
+      "loss": 0.18337883055210114,
+      "step": 85
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 3.754896640777588,
+      "learning_rate": 8.947368421052632e-06,
+      "loss": 0.11415284126996994,
+      "step": 86
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 3.8266732692718506,
+      "learning_rate": 8.421052631578948e-06,
+      "loss": 0.13100245594978333,
+      "step": 87
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 4.878761291503906,
+      "learning_rate": 7.894736842105263e-06,
+      "loss": 0.18353883922100067,
+      "step": 88
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 3.0917410850524902,
+      "learning_rate": 7.3684210526315784e-06,
+      "loss": 0.13703593611717224,
+      "step": 89
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 8.035305976867676,
+      "learning_rate": 6.842105263157896e-06,
+      "loss": 0.3001468777656555,
+      "step": 90
+    },
+    {
+      "epoch": 0.9,
+      "eval_loss": 2.0694642066955566,
+      "eval_runtime": 16.0628,
+      "eval_samples_per_second": 3.113,
+      "eval_steps_per_second": 0.809,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -651,7 +729,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4625532775219200.0,
+  "total_flos": 5199896781864960.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null