Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00d8b2572c06729206ac0d5ffd9e3067507921142b1ee6a970cb44a8dee74e9
+oid sha256:882965f17d26484f21b7422b127431b39e9bc167de2756137b2bffa6c145ce15
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:074e65caee7a885b06f613ecbdda741540666ec2e71262a1c1982162c41595cf
+oid sha256:3cde728115d951d44b9c7f3858fc718d126db8d944084c0825c7cb8111395365
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1467d43e650401a3b512d395f9a9d91640b9c9a50e1c12bdce5220b151890407
+oid sha256:5b7297c953f542071b9668195e42c49c3ecf8c10d91797c114451fa250854b4c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.036312849162011177,
+  "epoch": 0.07262569832402235,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 12.136,
       "eval_steps_per_second": 6.108,
       "step": 10
+    },
+    {
+      "epoch": 0.04189944134078212,
+      "grad_norm": 3.954702854156494,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 7.7161,
+      "step": 15
+    },
+    {
+      "epoch": 0.055865921787709494,
+      "grad_norm": 4.341027736663818,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 6.666,
+      "step": 20
+    },
+    {
+      "epoch": 0.055865921787709494,
+      "eval_loss": 1.68687903881073,
+      "eval_runtime": 12.5323,
+      "eval_samples_per_second": 12.049,
+      "eval_steps_per_second": 6.064,
+      "step": 20
+    },
+    {
+      "epoch": 0.06983240223463687,
+      "grad_norm": 4.4329705238342285,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 6.7389,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3708646965903360.0,
+  "total_flos": 7417293931806720.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null