Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c2f1f9f8e818afd15a7f4f977341e59613b94da75de555537ba5a0b0b59c38a
+oid sha256:09a785d95d2d94cdd6f27d57d4bbccdcb3b74011e1b175a74e950c97818e094e
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cca1d285fd02b926f643a2dc2b51ca848337d4594364248881acd4e05e9dfc47
+oid sha256:22551c53a7459e2bc11a7aeae09b253cde9e650a919c7344fc9349d114af755f
 size 50444805

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0eb73b134a129617820e93a4630f6c7e447cc6d5f8021ee7120ae17f44e4c73e
+oid sha256:670c55e1c37931a635c4dc0ef163d2b6c1b7a374aff2f09fb80d53eeb5e58616
 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": 0.9756149649620056,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 0.9753542542457581,
+  "best_model_checkpoint": "./outputs/checkpoint-1800",
+  "epoch": 2.4,
   "eval_steps": 100,
-  "global_step": 1700,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -245,6 +245,20 @@
       "eval_samples_per_second": 5.457,
       "eval_steps_per_second": 0.684,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 0.8306,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.9753542542457581,
+      "eval_runtime": 354.0462,
+      "eval_samples_per_second": 5.451,
+      "eval_steps_per_second": 0.684,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.807017024378716e+17,
+  "total_flos": 5.0879453793069466e+17,
   "trial_name": null,
   "trial_params": null
 }