Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ec9581db0bafcc251909e89dd1e8ce2d337df14761350644f9a26f3151b49a5
+oid sha256:999942acc5e99258e8ae4e4d09e7f35c1be40269ef73d6aa2521130c823f870f
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:204f4f933229e5656d8bdc3f32f78531154973a23ab0b0dfd2de55c8ba4afb03
+oid sha256:06f6c4c2ff5ac8cc832674c539604a5ffd5e8883b1c5f2f23b0064eb8804f8f8
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb50e2bd42723bb54172691df4d73f85a33829b8a1f4dc1ca27fee83c3724b7c
+oid sha256:8665825c42a3d9f7e4d6ea045efe267b7c691410421807dc2f776850b81af2bb
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:720bafe9a34b3041027dccef7d9c03bb23064e1fcdd80ae5f27e717d41b7cf31
+oid sha256:b1238b3bfa75e49a19396161e9e7b72ab89cdd1a3f63b51c0ab4d6e8d216c5a5
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.3672411441802979,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 2.6666666666666665,
+  "best_metric": 1.361167311668396,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 2.8,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,6 +287,20 @@
       "eval_samples_per_second": 15.558,
       "eval_steps_per_second": 1.951,
       "step": 2000
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 0.0002,
+      "loss": 1.1338,
+      "step": 2100
+    },
+    {
+      "epoch": 2.8,
+      "eval_loss": 1.361167311668396,
+      "eval_runtime": 93.3675,
+      "eval_samples_per_second": 15.541,
+      "eval_steps_per_second": 1.949,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
@@ -294,7 +308,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1694767356919808e+17,
+  "total_flos": 1.2278575092252672e+17,
   "trial_name": null,
   "trial_params": null
 }