Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0832e76433f522c41934a6ebf36480ec199e619750aa7c4fb52e569647334046
+oid sha256:9ff8fc6754256e849681d0d4a156abd0ca4d2c199551fe822d67587a96aebbc0
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad4d32b6f9248fb1b25d9dfb397fcdc2fb2cbc217d245f1796c2c42e23fed52
+oid sha256:2d98975f94a340e65dda70cf3ba315e25ea6911d40a299fabc046f37ad4998ff
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db6537e434778211ceaf8a863d4d8984f5efaf5b467b798fc7ec30bbe158933e
+oid sha256:22ccfd88f620eb832cdc95b7c73f631ee104fb7843f178a425bf2208b904d28d
 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": 0.02952029520295203,
+  "epoch": 0.03444034440344403,
   "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": 7.22,
       "eval_steps_per_second": 0.905,
       "step": 54
+    },
+    {
+      "epoch": 0.031160311603116032,
+      "grad_norm": 0.23608601093292236,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.5533,
+      "step": 57
+    },
+    {
+      "epoch": 0.03280032800328003,
+      "grad_norm": 0.18795213103294373,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.5873,
+      "step": 60
+    },
+    {
+      "epoch": 0.03444034440344403,
+      "grad_norm": 0.16693271696567535,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.6124,
+      "step": 63
+    },
+    {
+      "epoch": 0.03444034440344403,
+      "eval_loss": 0.6260421872138977,
+      "eval_runtime": 426.5842,
+      "eval_samples_per_second": 7.222,
+      "eval_steps_per_second": 0.905,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.421352351301632e+17,
+  "total_flos": 1.6527352922112e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null