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:cea22a556b0d5714d6944a73a9daced6533064e87d026f72dc66df8067763c62
+oid sha256:48a7bd4dd0c6af1467f66efea9a3fd18519fc7f345de8d3840d51d79783b7be2
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f722f5d0984aeff43faba60c826911f642c9c145542a16cefd3966db9801f19
+oid sha256:b7b81941da85d12b26ad01779c375fe1af8ed0a221793b8ca41d53813a51b540
 size 39356997

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1bfcb827226a2ddfa3a185ea677dbffee3b4d6ca06755c2fcfea4a0b49f3444
+oid sha256:2859c92cadbbc3acd22ebf9759d91bb2c23ac2b4ae22440b823dabb29822069f
 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": 0.9505811929702759,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 0.9465362429618835,
+  "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": 2.643,
       "eval_steps_per_second": 0.331,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 0.7571,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.9465362429618835,
+      "eval_runtime": 831.0865,
+      "eval_samples_per_second": 2.322,
+      "eval_steps_per_second": 0.291,
+      "step": 1800
     }
   ],
   "logging_steps": 100,
@@ -252,7 +266,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 4.40267224501248e+17,
+  "total_flos": 4.661431079860224e+17,
   "trial_name": null,
   "trial_params": null
 }