Training in progress, step 20, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7cc528eb2e14f04865fcddbe8cac82011b15d9764df6dd8090c74932fb14f67
+oid sha256:1e56e1ce8b0033e9bc72e3cd37278cfd17c4724b14e008174c65c1401d6b11a4
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c8e74251705825358e945bf9332972d438fbe838acabdea454e382b4a0b1e7
+oid sha256:0f56a239371d1d3856d89231073ad8c4042aab0304b048b20f5298b06c0a824a
 size 320082106

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:18dc613ec9bceaa03cc7b4c996c5c216d4df491a4b13fb66bb46e47fc9c02b42
+oid sha256:0e24d535c5c1523f0486038b5930228f33566ca520ba04d10e88741a42965211
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00071301247771836,
+  "epoch": 0.00142602495543672,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 9e-05,
       "loss": 3.6841,
       "step": 9
+    },
+    {
+      "epoch": 0.000855614973262032,
+      "grad_norm": 2.5727527141571045,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 3.792,
+      "step": 12
+    },
+    {
+      "epoch": 0.0010695187165775401,
+      "grad_norm": 3.9845669269561768,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 3.7048,
+      "step": 15
+    },
+    {
+      "epoch": 0.0011408199643493761,
+      "eval_loss": 3.2958037853240967,
+      "eval_runtime": 321.4005,
+      "eval_samples_per_second": 18.376,
+      "eval_steps_per_second": 9.188,
+      "step": 16
+    },
+    {
+      "epoch": 0.0012834224598930481,
+      "grad_norm": 3.1361684799194336,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 3.29,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3267291009515520.0,
+  "total_flos": 6534582019031040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null