Training in progress, step 1000, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24dba8c3a152a0a77f4e771dc947add5c5a334bd318a0b2eb805b9971add19f1
+oid sha256:95d73c8c1b2b6ee99249d2c3267b856ec91922cbd5cf0636b705365c677fd181
 size 9444296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f5952ccea418cbdfe9b8feaf5bc5a669a2364c889806d60425529d452314513e
+oid sha256:016e27af09c31c6428d53846b1abfb5c6a87aba0f5312adb051ceee516accf46
 size 18902665

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7361b3863934982b557e96c725dc20b5e201445559e466db7d62a9238b31024b
+oid sha256:cf0d1b378492ec4e150da1c9feeca26eae7c30c21199e70dec7f166a03613c3d
 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": 1.4368518590927124,
-  "best_model_checkpoint": "./outputs/checkpoint-900",
-  "epoch": 1.2,
+  "best_metric": 1.4286835193634033,
+  "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": 15.57,
       "eval_steps_per_second": 1.953,
       "step": 900
+    },
+    {
+      "epoch": 1.33,
+      "learning_rate": 0.0002,
+      "loss": 1.1859,
+      "step": 1000
+    },
+    {
+      "epoch": 1.33,
+      "eval_loss": 1.4286835193634033,
+      "eval_runtime": 93.2996,
+      "eval_samples_per_second": 15.552,
+      "eval_steps_per_second": 1.951,
+      "step": 1000
     }
   ],
   "logging_steps": 100,
@@ -140,7 +154,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 3,
   "save_steps": 100,
-  "total_flos": 5.26073066072064e+16,
+  "total_flos": 5.844782394372096e+16,
   "trial_name": null,
   "trial_params": null
 }