Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ee1a6461691368769afe9361838d60c5d9fd85bd7d2475feb945e099e128b04
+oid sha256:ae172d2734c66040ac55778c98d76ebc491fc9ea60ec62aaa8198ad0503d75d7
 size 97307544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afcf5a4374bc9aadc1e2a6f417f4b9344ec32d0f180b2f3ea348d06053622aa4
+oid sha256:ded3806f8a30d4d9740432361b62c83d7f43945a2543c9aee45ed86e26b3bf0f
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd25efae69fa90a9c45f55963c0cc4d7aa5965e1e67d432e91f378f100616c10
+oid sha256:92aa0a05c9aabc0ef384311d2608437e22cac86912823f431f99de4cfcca89f7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bec84b33191b76a1f66109f05ca2863b65ba9c0ae66be6a4921ad95ad9f1a38e
+oid sha256:0569f9f06b6a114946825bdc699040cc55958cfef46aba8eb5fb625896d49025
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.037504340780182895,
+  "epoch": 0.04167148975575877,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 24.809,
       "eval_steps_per_second": 3.103,
       "step": 81
+    },
+    {
+      "epoch": 0.03889339043870818,
+      "grad_norm": 0.47324180603027344,
+      "learning_rate": 3.798797596089351e-06,
+      "loss": 1.6292,
+      "step": 84
+    },
+    {
+      "epoch": 0.040282440097233474,
+      "grad_norm": 0.5699959397315979,
+      "learning_rate": 2.5301488425208296e-06,
+      "loss": 1.6236,
+      "step": 87
+    },
+    {
+      "epoch": 0.04167148975575877,
+      "grad_norm": 0.49094218015670776,
+      "learning_rate": 1.5076844803522922e-06,
+      "loss": 1.696,
+      "step": 90
+    },
+    {
+      "epoch": 0.04167148975575877,
+      "eval_loss": 1.6338019371032715,
+      "eval_runtime": 146.5598,
+      "eval_samples_per_second": 24.823,
+      "eval_steps_per_second": 3.105,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.52764554535895e+16,
+  "total_flos": 5.030717272621056e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null