Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a016739347ccb47365dee56c9f4a70daac03e20c12dc85c2ac5e88378a2ce97a
+oid sha256:9f126679849ca9ee45804d525f5c5fe3582a96fd015eb0c6f7c065ccab45d169
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:566fa17539d375118f2d8357aebadebc46039361be33f7e1db25609d6e8e15a7
+oid sha256:af640c4744126dd6e10525a8044be5b1257c85fe2542cfbd4e5fa18e677ede05
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2584adcfe5878130368943010052e98d7f9569785b451bb350577d373a1f2f
+oid sha256:3587699f49f930b2c0cd17b5071fff6f2cf9326eebadb8adb2db8be4db4ec081
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
+oid sha256:3bb7339d1d2da342a44f3ba5e076fb6e5d93aee86f890c002703d2b3a0750820
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.403062343597412,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 0.6557377049180327,
+  "best_metric": 2.384012222290039,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 0.7285974499089253,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,13 +133,27 @@
       "eval_samples_per_second": 30.622,
       "eval_steps_per_second": 3.831,
       "step": 900
+    },
+    {
+      "epoch": 0.73,
+      "learning_rate": 0.0002,
+      "loss": 2.3883,
+      "step": 1000
+    },
+    {
+      "epoch": 0.73,
+      "eval_loss": 2.384012222290039,
+      "eval_runtime": 204.4165,
+      "eval_samples_per_second": 30.692,
+      "eval_steps_per_second": 3.84,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.625477585518592e+16,
+  "total_flos": 2.917579599470592e+16,
   "trial_name": null,
   "trial_params": null
 }