Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20dcfe1bf39321b720e82ea91671044d131a1bb2082db5fd9180d4226d3e472f
+oid sha256:def2f98a9fa49c5944552556fe507bd5a6f55f19c2d0cd54bc9be957d7214ff4
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe773f2043084813bb2eee625f43a0fa2c6f07eefe923b76e20f6243fc7e051f
+oid sha256:b171f01d876e54df8782cbcc3a64a4627fa0544d5b8a42080aa2c853a5b2e483
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d54922533a99f5b48c8c09cecf7d3009079b051f1aa5e7b604a383f3e69c83
+oid sha256:a37c1648d3f3cc4b038615e5a05edcf7fc13e1f76bda94223bbbe825e65d819b
 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": 0.0023906946807043354,
+  "epoch": 0.004781389361408671,
   "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": 16.879,
       "eval_steps_per_second": 8.44,
       "step": 10
+    },
+    {
+      "epoch": 0.002758493862351156,
+      "grad_norm": 0.3702358901500702,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.005,
+      "step": 15
+    },
+    {
+      "epoch": 0.0036779918164682084,
+      "grad_norm": 0.4076727330684662,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8239,
+      "step": 20
+    },
+    {
+      "epoch": 0.0036779918164682084,
+      "eval_loss": 0.709395706653595,
+      "eval_runtime": 135.516,
+      "eval_samples_per_second": 16.898,
+      "eval_steps_per_second": 8.449,
+      "step": 20
+    },
+    {
+      "epoch": 0.00459748977058526,
+      "grad_norm": 1.03678560256958,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.6475,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1763104629719040.0,
+  "total_flos": 3567211692687360.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null