Training in progress, step 1800, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dfe5c000de36a6e2d3301fed7867e14a1f2b3c09a2276181d086bdf90eec81e
+oid sha256:18d5668b70e778954dee39eda605d98af31c479e8d2a8daf8673141c8d090189
 size 19669752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b125d16214756bb5e5d3fefbcfa69fe4cb9405e8362e68b86d48869546487ce
+oid sha256:37139ea6aa30874523a4be496a66d68fe5379afd6c2979169b26951fc8025870
 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": 0.9503656029701233,
-  "best_model_checkpoint": "./outputs/checkpoint-1700",
-  "epoch": 2.2666666666666666,
+  "best_metric": 0.9474750757217407,
+  "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": 2.113,
       "eval_steps_per_second": 0.265,
       "step": 1700
+    },
+    {
+      "epoch": 2.4,
+      "learning_rate": 0.0002,
+      "loss": 0.7579,
+      "step": 1800
+    },
+    {
+      "epoch": 2.4,
+      "eval_loss": 0.9474750757217407,
+      "eval_runtime": 916.0603,
+      "eval_samples_per_second": 2.107,
+      "eval_steps_per_second": 0.264,
+      "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
 }