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:c5d6afdfb7abda138ac5a7e8230ad6fe13cf712320b186a9f10cfdab7837a510
+oid sha256:9938fe652d1d38684275fcb36e5a9edad37c2aa0fc51cce9a044c49b84511676
 size 6298560

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d7409ade6160d4f15bda95bf0a963969fad8a81fe51367c42f302f751df51ca
+oid sha256:2e874ea209b5a90ee50d699e0e050758e2fcfd7c928242b6b10be3ce930c6d07
 size 12611145

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a5616fda15e72a8c8ee348cad1a2bd9180fd92294398094aba03a3b73af356e
+oid sha256:8a3b82189f7d54944fe397aa129e3a549502a28beefbceb6e38af17a764834ad
 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": 1.1988099813461304,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 1.1918971538543701,
+  "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": 4.113,
       "eval_steps_per_second": 0.516,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 0.9711,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 1.1918971538543701,
+      "eval_runtime": 470.4302,
+      "eval_samples_per_second": 4.103,
+      "eval_steps_per_second": 0.514,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.656486774308864e+16,
+  "total_flos": 5.988908280368333e+16,
   "trial_name": null,
   "trial_params": null
 }