Training in progress, step 2900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0ce10b52c34521da3527ec14933f59ce7da0c2f2f20e39ce7a1fd8ef8170c4a
+oid sha256:916e90696b24d9882c92abf3092c0ed82bd4cedbeeef4caeb480cc8a219d698c
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11e7f380efe9dbb38a6b89f237e07c5a68066845521727111f140ec60329eb35
+oid sha256:1ed9e5dbe38cd1f5e0b104e32f16bccee4a9fdf026b0460715c08ebb1b8f1039
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e774b6f5f6d011a8bfc0a40be4c997cf31f87d5dc031814a84d7bd848d0c3c8
+oid sha256:2c203d7bb1a91e0292a965d8ca5fb218ce38bc4a460a20de85094975b0d59d26
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbad9b8a27781262e8d219547870cd4a5243b6b2eabc860ee48e6517ff8422dd
+oid sha256:6f8ff9625f3ca0a3b7f45b0a306f91dd9b6f1df22bd03f7af912988d7d454a46
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.4635066986083984,
-  "best_model_checkpoint": "./outputs/checkpoint-2800",
-  "epoch": 2.040072859744991,
+  "best_metric": 1.4502085447311401,
+  "best_model_checkpoint": "./outputs/checkpoint-2900",
+  "epoch": 2.1129326047358834,
   "eval_steps": 100,
-  "global_step": 2800,
+  "global_step": 2900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,13 +399,27 @@
       "eval_samples_per_second": 43.71,
       "eval_steps_per_second": 5.469,
       "step": 2800
+    },
+    {
+      "epoch": 2.11,
+      "learning_rate": 0.0002,
+      "loss": 1.4152,
+      "step": 2900
+    },
+    {
+      "epoch": 2.11,
+      "eval_loss": 1.4502085447311401,
+      "eval_runtime": 143.5067,
+      "eval_samples_per_second": 43.719,
+      "eval_steps_per_second": 5.47,
+      "step": 2900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.6672454855162266e+17,
+  "total_flos": 1.7266613396692992e+17,
   "trial_name": null,
   "trial_params": null
 }