Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1745abc886c6750817878d5d5a1caad2677c722fc729dabe81bd120ff8fb499f
+oid sha256:b6d4fff8398a005291af4bcafd5071060d689832ee1e2e0d16ca43f7ddcefa34
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:253ca4d6d6df36bc74d35d479ea38b42b9b5e9395683bada01ac250a838e58b2
+oid sha256:f0e68c6f34dbbb9ee51991b9cc9eb88fc6a38115b951ae1314afef0e0449d853
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d2dd23330c7a6a241dea866f3a8d0da33f690b71da00f528527985b73751b8d
+oid sha256:cf4a977350df40c9b5afb65eb8e48a767be847c486a19a831f37b3267caf5f9f
 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": 1.1430203914642334,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.1354840993881226,
+  "best_model_checkpoint": "./outputs/checkpoint-1000",
+  "epoch": 1.3333333333333333,
   "eval_steps": 100,
-  "global_step": 900,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -133,6 +133,20 @@
       "eval_samples_per_second": 10.799,
       "eval_steps_per_second": 1.354,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 0.9313,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.1354840993881226,
+      "eval_runtime": 177.5002,
+      "eval_samples_per_second": 10.873,
+      "eval_steps_per_second": 1.363,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 6.726095314477056e+16,
+  "total_flos": 7.474685431062528e+16,
   "trial_name": null,
   "trial_params": null
 }