Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a28a7dbac8b0f0d79134828ccfcc7e75778b4778c9b07150cd8125a691efe3ae
+oid sha256:f7c656d54c57703e10cc69f1067b322fad2e94aa1840af5a86579fa5b2aa41e3
 size 671149168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c2b09fc35aa9333839387ec3971d2e5d10cd453971cb6fa8508a6f3a2dd19d
+oid sha256:d4d3376a1258e78d38fc0279f05de99896fa970810761ac1e19f99a6fd8d376f
 size 1342555602

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db154dc44f1fc7dfd122d5f2c612cf938a41c48875c24a85ef3d6b41a2850665
+oid sha256:3395066b44e33540ea0d133210a51b3f5d2cc5feecded57a9899f2d592fe6cc0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d85eac2daddfe8e3f78a5d6ef1e9ba13c04651694635a9ed76369a20726389db
+oid sha256:8d43bd90ad476e419738deb9472ad85fd5991005a147e1627aa99867bdfc5655
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5338983050847458,
+  "epoch": 0.6101694915254238,
   "eval_steps": 9,
-  "global_step": 63,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -155,6 +155,28 @@
       "eval_samples_per_second": 18.873,
       "eval_steps_per_second": 2.382,
       "step": 63
+    },
+    {
+      "epoch": 0.5508474576271186,
+      "grad_norm": 0.5052010416984558,
+      "learning_rate": 6.036822584879038e-05,
+      "loss": 0.7611,
+      "step": 65
+    },
+    {
+      "epoch": 0.5932203389830508,
+      "grad_norm": 0.5269892811775208,
+      "learning_rate": 4.6298742572618266e-05,
+      "loss": 0.7769,
+      "step": 70
+    },
+    {
+      "epoch": 0.6101694915254238,
+      "eval_loss": 0.7839500904083252,
+      "eval_runtime": 22.2533,
+      "eval_samples_per_second": 18.874,
+      "eval_steps_per_second": 2.382,
+      "step": 72
     }
   ],
   "logging_steps": 5,
@@ -174,7 +196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9.84305110131671e+16,
+  "total_flos": 1.1238426161656627e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null