Training in progress, step 2100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81527ea9e608599fe95a6448599fa180cd55477fb1291875bdc1a547880a7ca1
+oid sha256:b335c2194cfd60f04249bd76b98ff04e290c73fca51af64a2a4a00e83ac4f287
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b1c840d7e2335a61e732e072cb0dccd604349c37336d989f068f3908ba67fa4
+oid sha256:f38abb10ea643512c32adf3660f5d0e32ba9305747bc71ca5eeed89f7410e969
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c134cfa86adc7fd0d893de0ed5f1d042c69cb03ed5bb956e86d5d878b172fe1
+oid sha256:347cad9f3bce277eed003720972c437ba21dbbd4b008635e9d49d0ca58e0dcb4
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d466bcdc36eef33e32dd1288944b590d249986f908ba4cdb9b0a666ab8a33427
+oid sha256:478733a125645f7571e11a00dfec746713e56b183a03f33534a6b81d3808d636
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5781009197235107,
-  "best_model_checkpoint": "./outputs/checkpoint-2000",
-  "epoch": 1.4571948998178508,
+  "best_metric": 1.5617916584014893,
+  "best_model_checkpoint": "./outputs/checkpoint-2100",
+  "epoch": 1.530054644808743,
   "eval_steps": 100,
-  "global_step": 2000,
+  "global_step": 2100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -287,13 +287,27 @@
       "eval_samples_per_second": 43.737,
       "eval_steps_per_second": 5.472,
       "step": 2000
+    },
+    {
+      "epoch": 1.53,
+      "learning_rate": 0.0002,
+      "loss": 1.5574,
+      "step": 2100
+    },
+    {
+      "epoch": 1.53,
+      "eval_loss": 1.5617916584014893,
+      "eval_runtime": 146.1644,
+      "eval_samples_per_second": 42.924,
+      "eval_steps_per_second": 5.371,
+      "step": 2100
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.1910623325700915e+17,
+  "total_flos": 1.2505986444644352e+17,
   "trial_name": null,
   "trial_params": null
 }