Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:297b38e69f29c26c634ac37317584ca6d05b2c37d4797c966e442a92c7ffefa3
+oid sha256:9dde61fab8dd2de3b429f4843dde57bea13894c2f74c091dec3f0f7a78bd1517
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec3b6a4089390339c40d8c6b6e9c6df0bde9061861f57763aaebf5fe3be34e89
+oid sha256:d4bbb3c1b5e4823075cdd64d4995369d32fe28c14a4e34f39e5f8f259039f3e4
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d1dffd43c641606e054f7ea218bf8a83debf312b1baadbf2c3f507d6e23d65e
+oid sha256:0c6734b3460aa66fb121c9e45efb8624dc2797b84feae6b1f00b782b6a4ac85c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.0746268656716418,
+  "epoch": 1.2537313432835822,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 15.079,
       "eval_steps_per_second": 1.951,
       "step": 54
+    },
+    {
+      "epoch": 1.1343283582089552,
+      "grad_norm": 0.6391798853874207,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.9475,
+      "step": 57
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "grad_norm": 0.5408726334571838,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.9773,
+      "step": 60
+    },
+    {
+      "epoch": 1.2537313432835822,
+      "grad_norm": 0.5797409415245056,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.9214,
+      "step": 63
+    },
+    {
+      "epoch": 1.2537313432835822,
+      "eval_loss": 0.9961395263671875,
+      "eval_runtime": 5.6389,
+      "eval_samples_per_second": 15.074,
+      "eval_steps_per_second": 1.951,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.053264466791629e+16,
+  "total_flos": 8.229489230217216e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null