Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23de433f86c177288695f48fe79fb39fac30eafd0b9dc2f45c615b3b73c98d3b
+oid sha256:368e3dd50843a82400c5aff72701fd69347bb1313e854d1a075415e07513a8d2
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24bfff0a8e4482ebd647a741ae806f4f413047770082899b8293fe7c32a60570
+oid sha256:e433ee855f54f134e6b078e30ff18509879947f17fc71385bd439e6809b6d426
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:42d82cefe3dbce05d21cd31fd65135b0f507fa0308fd19dcaa91f644308efc23
+oid sha256:1b4b1b37e75be4b65b7642b3207f0ac6424318170e6fdb52189f43223d7c1de8
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0410ad60e6d0138b921a03b0a3e367fd27c6ab07cb9a5006fcb66ea8e5bbacc4
+oid sha256:c0e0a1736a46fd1627af3c246e44261aaac909256abbd413b5ee5c968f6b2d8e
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.325985908508301,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 1.238615664845173,
+  "best_metric": 2.3098464012145996,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 1.3114754098360657,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,13 +245,27 @@
       "eval_samples_per_second": 30.634,
       "eval_steps_per_second": 3.833,
       "step": 1700
+    },
+    {
+      "epoch": 1.31,
+      "learning_rate": 0.0002,
+      "loss": 2.2916,
+      "step": 1800
+    },
+    {
+      "epoch": 1.31,
+      "eval_loss": 2.3098464012145996,
+      "eval_runtime": 204.5629,
+      "eval_samples_per_second": 30.67,
+      "eval_steps_per_second": 3.837,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.850935894038528e+16,
+  "total_flos": 5.134876246112256e+16,
   "trial_name": null,
   "trial_params": null
 }