Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dde61fab8dd2de3b429f4843dde57bea13894c2f74c091dec3f0f7a78bd1517
+oid sha256:3655fe9a9e98c3caac2cc33969712edee84b1fd55e5706fadeda2cb024b8cc8e
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4bbb3c1b5e4823075cdd64d4995369d32fe28c14a4e34f39e5f8f259039f3e4
+oid sha256:e9e0ec8e40a120eda932450aa73b429890c5df137c4996b1ecc0f2df299a6833
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c6734b3460aa66fb121c9e45efb8624dc2797b84feae6b1f00b782b6a4ac85c
+oid sha256:110e6aa2d13c172c07d211ef5e0b299e4042a9ae85f51e78437b2380439da596
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
+oid sha256:d899e046e5eb8fee9b81979db8db7b88d6dc92f30a13d049b906f3a3be1dfc0f
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.2537313432835822,
+  "epoch": 1.4328358208955223,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -218,6 +218,35 @@
       "eval_samples_per_second": 15.074,
       "eval_steps_per_second": 1.951,
       "step": 63
+    },
+    {
+      "epoch": 1.3134328358208955,
+      "grad_norm": 0.5694305300712585,
+      "learning_rate": 1.56348351646022e-05,
+      "loss": 0.9053,
+      "step": 66
+    },
+    {
+      "epoch": 1.373134328358209,
+      "grad_norm": 0.5325923562049866,
+      "learning_rate": 1.3263210930352737e-05,
+      "loss": 0.922,
+      "step": 69
+    },
+    {
+      "epoch": 1.4328358208955223,
+      "grad_norm": 0.6161549091339111,
+      "learning_rate": 1.1020177413231334e-05,
+      "loss": 0.9302,
+      "step": 72
+    },
+    {
+      "epoch": 1.4328358208955223,
+      "eval_loss": 0.9865135550498962,
+      "eval_runtime": 5.6362,
+      "eval_samples_per_second": 15.081,
+      "eval_steps_per_second": 1.952,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -237,7 +266,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.229489230217216e+16,
+  "total_flos": 9.405713993642803e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null