Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40b0dad0f47e9185c7141a1b5781e54ad7f03b88fceb62e18911b44f0bf18a57
+oid sha256:df001d6c482b5ebcda095e7d8747a1865cc0830115cc6cd22215f7b4b6077fc1
 size 6304192

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09d5775b3cf5223b23468d6f24880a63496a878da2596a010e0fe5a52c3b7f9c
+oid sha256:3912871294c8600ae8d6a8870fe77e62cd01ff31a2643c7d0d3ace9214d8468c
 size 12639429

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36f0d7161dd9ad8e601b265301b55ba4312cb15819580d045ab5f9b066af22db
+oid sha256:93ce7850ba616cb9173c824a87886d7161290c269141086c616c96978133223b
 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": 1.2672399282455444,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.266547441482544,
+  "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": 15.246,
       "eval_steps_per_second": 1.912,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 1.0927,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.266547441482544,
+      "eval_runtime": 126.4531,
+      "eval_samples_per_second": 15.263,
+      "eval_steps_per_second": 1.914,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 3.1897626964783104e+16,
+  "total_flos": 3.545352531420365e+16,
   "trial_name": null,
   "trial_params": null
 }