Training in progress, step 1900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e69508337a093a7ee674ee4f741f99f139e7e2c78c1be36764b9dab376fd4bd7
+oid sha256:8d0fddb20473efac1286eda903a7514b7d159a3db2c500a2598036838e125f99
 size 50338848

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:beb1ab69a22370510ed83d21fff5fe9b8dba6fa8c167d9db8a96afeea218c646
+oid sha256:c9f5b6eaea4479fa0199aac028fed659f7828b4b456558aac671ac5f404d448a
 size 100693001

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a88e7a58b8640e03fbaf438f47d12780b3ac5b0439ebe7d26d20d40495b231
+oid sha256:4b260e5aa5c575d02f510db3424cb2898335e8d38fcdc4bec564683729218a6b
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65e7f2a492ba0fc6e11860baa88e4ba1026051d3cc228ccacdaf47de2a669a24
+oid sha256:496140aa30b21578f6775ba5236d745f834471c83d84a366a20359624c56b122
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.6090008020401,
-  "best_model_checkpoint": "./outputs/checkpoint-1800",
-  "epoch": 1.3114754098360657,
+  "best_metric": 1.5939785242080688,
+  "best_model_checkpoint": "./outputs/checkpoint-1900",
+  "epoch": 1.384335154826958,
   "eval_steps": 100,
-  "global_step": 1800,
+  "global_step": 1900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -259,13 +259,27 @@
       "eval_samples_per_second": 43.737,
       "eval_steps_per_second": 5.472,
       "step": 1800
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 0.0002,
+      "loss": 1.5908,
+      "step": 1900
+    },
+    {
+      "epoch": 1.38,
+      "eval_loss": 1.5939785242080688,
+      "eval_runtime": 143.55,
+      "eval_samples_per_second": 43.706,
+      "eval_steps_per_second": 5.468,
+      "step": 1900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 1.0719202477481165e+17,
+  "total_flos": 1.1315157627172454e+17,
   "trial_name": null,
   "trial_params": null
 }