Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c0ca2028bc9806e04cb0e0e3d760a79c50dc3a6c08f480a09d692f1afae1742
+oid sha256:d7e0029d69f2e02a51eb9d5db1c6eb0204c4e33d683b908a1f2fdd1cedde3b0d
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e14c410f1a37c25930037f8aac9ad5b09a3f2c1966e691aed68922e5a3b5c4d5
+oid sha256:0eef27d086e7c06aa1c79b9cde0fc0f2c8ff7293d1a6ed6f4b9a9a785d7cb781
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8f5982f9761d9e64b91454ebea38e874bb241e444b311de415fa1825f7bcf55
+oid sha256:d6a7adea43dcf6387b396d924985ba3d8d2ca0009f0291528a1342a56d78b48c
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13276f15dd2b6acc19b970176aa2db4ac9b58241843e72c89b50e3094e903b19
+oid sha256:5efc416a6883409dd7ab6f5c779e107c7c2baa7af6e12ed9fbd9dd73b8b20784
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4099382162094116,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.3928134441375732,
+  "best_model_checkpoint": "./outputs/checkpoint-500",
+  "epoch": 0.6666666666666666,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -63,6 +63,20 @@
       "eval_samples_per_second": 12.736,
       "eval_steps_per_second": 1.597,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.1486,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.3928134441375732,
+      "eval_runtime": 151.678,
+      "eval_samples_per_second": 12.724,
+      "eval_steps_per_second": 1.595,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.55290200510464e+16,
+  "total_flos": 3.186631141392384e+16,
   "trial_name": null,
   "trial_params": null
 }