Training in progress, step 63, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01978adfb77fca7fd9dce8fee717a8665c820e1bc8d27ec2f70fbbb22a87d957
+oid sha256:addb0c1b7a800e63794e93854322c9bf523594ff24779c2f2aa6618a16d40309
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26c1d4560b9a66b2004bd2b26b2152b3cff5801ac052a825c468e31ae34116b3
+oid sha256:e46ec7da17f5ce24c7f97b1ef89920acea78c3f36706608629ded472832f4667
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a347f5446a51df24d512acf398e5372d6960730c52b0dc0ea5f5d8a37c76f8a
+oid sha256:81eef1339e8f499efe37cf6787a5508274bd53f0e74fe093964cfc634b1c8e4b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec430a8fba90f7f39f74e916eb32712c363a0fd20bb4904251fce0eb82f2b9cf
+oid sha256:922634a168fad3088c2a461ec82359f2941891b1472f492b835996e27c3cba9d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.001821386108557985,
+  "epoch": 0.002124950459984316,
   "eval_steps": 9,
-  "global_step": 54,
+  "global_step": 63,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -189,6 +189,35 @@
       "eval_samples_per_second": 30.148,
       "eval_steps_per_second": 3.769,
       "step": 54
+    },
+    {
+      "epoch": 0.0019225742257000954,
+      "grad_norm": 0.2631082534790039,
+      "learning_rate": 2.3256088156396868e-05,
+      "loss": 0.7554,
+      "step": 57
+    },
+    {
+      "epoch": 0.0020237623428422057,
+      "grad_norm": 0.2768804430961609,
+      "learning_rate": 2.0658795558326743e-05,
+      "loss": 0.8178,
+      "step": 60
+    },
+    {
+      "epoch": 0.002124950459984316,
+      "grad_norm": 0.23129825294017792,
+      "learning_rate": 1.8109066104575023e-05,
+      "loss": 0.8145,
+      "step": 63
+    },
+    {
+      "epoch": 0.002124950459984316,
+      "eval_loss": 0.8158968091011047,
+      "eval_runtime": 1657.0323,
+      "eval_samples_per_second": 30.134,
+      "eval_steps_per_second": 3.767,
+      "step": 63
     }
   ],
   "logging_steps": 3,
@@ -208,7 +237,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6850867995017216e+16,
+  "total_flos": 1.9724659436027904e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null