Training in progress, step 10, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca348546290f635bd721d13ff6311f4afbfba6e726165b877c12072fe31424cd
+oid sha256:7d6219e8df1e72f271ee8b1e9011f6a157f7d093ce3f90f6d2e96e10fceea216
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:572079e1237696009196fcc15c7aaecaaf9ab5270772e79e6e60da6d758d6452
+oid sha256:99fb2b902b2642aa5b6430f96d77d5c8d626218316d4c23f0d355a5bfdca0ba9
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:870bff235260a948396f89eba7aa8360caaf7dcd6a760faaaac5c6a1a745f7f5
+oid sha256:1b5e01f48167f2cf44d2d57c9cf12332c401974db0431167c8cc543fa9db0f82
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cda2d7da3ce8a95be6df505b84eace6ccd5aa18ffc6d1bcc9a79572045c8d78f
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.05037783375314862,
+  "epoch": 0.10075566750629723,
   "eval_steps": 3,
-  "global_step": 5,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,57 @@
       "learning_rate": 0.0001,
       "loss": 11.7752,
       "step": 5
+    },
+    {
+      "epoch": 0.060453400503778336,
+      "grad_norm": 0.17101934552192688,
+      "learning_rate": 0.00012,
+      "loss": 11.7782,
+      "step": 6
+    },
+    {
+      "epoch": 0.060453400503778336,
+      "eval_loss": 11.775053024291992,
+      "eval_runtime": 1.4347,
+      "eval_samples_per_second": 58.549,
+      "eval_steps_per_second": 29.275,
+      "step": 6
+    },
+    {
+      "epoch": 0.07052896725440806,
+      "grad_norm": 0.11344543099403381,
+      "learning_rate": 0.00014,
+      "loss": 11.7742,
+      "step": 7
+    },
+    {
+      "epoch": 0.08060453400503778,
+      "grad_norm": 0.12048022449016571,
+      "learning_rate": 0.00016,
+      "loss": 11.7692,
+      "step": 8
+    },
+    {
+      "epoch": 0.0906801007556675,
+      "grad_norm": 0.1138000637292862,
+      "learning_rate": 0.00018,
+      "loss": 11.7727,
+      "step": 9
+    },
+    {
+      "epoch": 0.0906801007556675,
+      "eval_loss": 11.774245262145996,
+      "eval_runtime": 1.4321,
+      "eval_samples_per_second": 58.657,
+      "eval_steps_per_second": 29.328,
+      "step": 9
+    },
+    {
+      "epoch": 0.10075566750629723,
+      "grad_norm": 0.11828505247831345,
+      "learning_rate": 0.0002,
+      "loss": 11.7817,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -77,7 +128,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2037000437760.0,
+  "total_flos": 4074000875520.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null