Training in progress, step 900, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:43da30e397164c844764dda7a20e99bb190dd6e3c5b7e98c8e13f16599f27015
+oid sha256:c239b50c953cdf1dd821707df8a93b797a88c7eac6fc48aeab3a0725787d24b1
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cbed1dd5d4230da5bd0ad3d43d81e8c121a3bd9f38955b269a3df6875150b56
+oid sha256:3eb199e083fd51e6aa7a7d64c660ff7d56de711426d4815187974eec2de65259
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41eb3cc90529708ec3050e7a2a3e956faee68b39027a1409168255234e541c3d
+oid sha256:be78a4950643aa2c0f7f3e14329f834829bfe49fb52a0d080a54375bd9ada6a0
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de7840bcb72f2f480fd301578d289cdfa174589e831b0d33e5772f3956b6beae
+oid sha256:a3c39113390004215769b6e7fbe73f1073dd2faa3ab8f9ff815b62e9c2f80c82
 size 627

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.399696111679077,
-  "best_model_checkpoint": "./outputs/checkpoint-800",
-  "epoch": 0.5828779599271403,
+  "best_metric": 2.380272150039673,
+  "best_model_checkpoint": "./outputs/checkpoint-900",
+  "epoch": 0.6557377049180327,
   "eval_steps": 100,
-  "global_step": 800,
+  "global_step": 900,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -119,13 +119,27 @@
       "eval_samples_per_second": 30.488,
       "eval_steps_per_second": 3.815,
       "step": 800
+    },
+    {
+      "epoch": 0.66,
+      "learning_rate": 0.0002,
+      "loss": 2.369,
+      "step": 900
+    },
+    {
+      "epoch": 0.66,
+      "eval_loss": 2.380272150039673,
+      "eval_runtime": 206.0924,
+      "eval_samples_per_second": 30.443,
+      "eval_steps_per_second": 3.809,
+      "step": 900
     }
   ],
   "logging_steps": 100,
   "max_steps": 4116,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 2.349160133935104e+16,
+  "total_flos": 2.64265735974912e+16,
   "trial_name": null,
   "trial_params": null
 }