Training in progress, step 40, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:446704d171909fe1b90ebb16e3107050b0a85e3467f5f3c73077d0c6783e132b
+oid sha256:34e0d913ae383f662f243d664ef3832c43113ad58e91fa4ddfd5c2126e232223
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffcf1c68b31bc14c84a25b4361564f95d31085e478b3396745e9e7887925d1fd
+oid sha256:8698e7239d6ca727bc71dbfa750836f0432bab098194ce43f3d7311915653dc4
 size 212298

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faa450476dbd198dc4484447171d2b13c39e0fa316de67fcc41765245207305d
+oid sha256:e19ff206e6de2dafad8e586ef1ffe3b8c993c8131165c64a2fc7415ded08db8c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c32f0c34d941772d95b11e82ac22de22e969c9c470a009499eff8dbdf7ec5a86
+oid sha256:45d5b5ea37327e41cdd333e73810eaaebc3036bcc37660933e2e7ed42963f935
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.136761487964989,
+  "epoch": 1.4168490153172866,
   "eval_steps": 8,
-  "global_step": 32,
+  "global_step": 40,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,6 +117,35 @@
       "eval_samples_per_second": 135.057,
       "eval_steps_per_second": 68.225,
       "step": 32
+    },
+    {
+      "epoch": 1.1717724288840263,
+      "grad_norm": 0.27254220843315125,
+      "learning_rate": 0.00018145759520503358,
+      "loss": 10.2022,
+      "step": 33
+    },
+    {
+      "epoch": 1.276805251641138,
+      "grad_norm": 0.2869032025337219,
+      "learning_rate": 0.00017237340381050703,
+      "loss": 10.3997,
+      "step": 36
+    },
+    {
+      "epoch": 1.3818380743982495,
+      "grad_norm": 0.2603079676628113,
+      "learning_rate": 0.00016181589862206052,
+      "loss": 10.2418,
+      "step": 39
+    },
+    {
+      "epoch": 1.4168490153172866,
+      "eval_loss": 10.31363582611084,
+      "eval_runtime": 0.7196,
+      "eval_samples_per_second": 134.788,
+      "eval_steps_per_second": 68.089,
+      "step": 40
     }
   ],
   "logging_steps": 3,
@@ -136,7 +165,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 13752604164096.0,
+  "total_flos": 17174048931840.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null