Training in progress, step 500, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ebd51e27b75f61b4784841bdc3e84cec0110751aea14d0bd97a2fb53819cf49
+oid sha256:8c0e95c2524060bb03e967954d661150494077a2ec08936bcd1a6ca155971ff7
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d65eaa0340c25c90d740ae8182d3ebccb58c13db3e01a2a2bc42ff4f73036a44
+oid sha256:93ed4ed2575dbbc818087c7af10a45b7be59ab4e0de75ff6ccfa6a30be7f6fb0
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92942cd27ddd53a4c545428e2cc49f7db59067ae104a2b7a947f9d90e3f8e9f3
+oid sha256:ec69c1f9db00275f2bf788ed50aaee351133623fcb893d2824213ebb8d0cd795
 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": 1.4979034662246704,
-  "best_model_checkpoint": "./outputs/checkpoint-400",
-  "epoch": 0.5333333333333333,
+  "best_metric": 1.4787811040878296,
+  "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": 15.531,
       "eval_steps_per_second": 1.948,
       "step": 400
+    },
+    {
+      "epoch": 0.67,
+      "learning_rate": 0.0002,
+      "loss": 1.2497,
+      "step": 500
+    },
+    {
+      "epoch": 0.67,
+      "eval_loss": 1.4787811040878296,
+      "eval_runtime": 93.1297,
+      "eval_samples_per_second": 15.58,
+      "eval_steps_per_second": 1.954,
+      "step": 500
     }
   ],
   "logging_steps": 100,
@@ -70,7 +84,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.340946069733376e+16,
+  "total_flos": 2.927413222981632e+16,
   "trial_name": null,
   "trial_params": null
 }