Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78edaa4b2d72c684cebeb07449e28739e9f7dfad09e98f100670b2a535084dba
+oid sha256:765ac12d1aab888808f6d70598ec8f1491dc5987cce4d97f1fe5e439cd07b0c2
 size 25191576

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56a13ed6c7ce73e881f49e46e4cab5b94181ac41b75be939fa509e64ef33e76b
+oid sha256:acc846b280725d94f7c04b2b0ae22fb2965ab24f68c9d617fd5c55cb4dfb08bc
 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": 0.9765165448188782,
   "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "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": 5.455,
       "eval_steps_per_second": 0.684,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 0.8312,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.9783728122711182,
+      "eval_runtime": 360.7811,
+      "eval_samples_per_second": 5.35,
+      "eval_steps_per_second": 0.671,
+      "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
 }