Training in progress, step 68, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f48f338f19fe0bcdab29d59a911ba00222b86925de7cf81836a560468969ff5
+oid sha256:b06d6095f86341e631c31dfe5c014ab0c7bdd8dd50ae9b2f22748fb787b26c43
 size 34793120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aff871bacfeb537e50880fd81e071fc24308c567996975c56c1f1f2144f32473
+oid sha256:c6d475747d9aed2705bc7b24c14fe90c153254ec151ddecd24eebe44d949f462
 size 18132116

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:14e0dbfa36e10c9727607edc307ed7386c96f72f9ae420a6cc886cff8b415976
+oid sha256:2bb1f6ba326b8488be4e2327d96e736f1996da096cf4aab9ac45520a7cbbf382
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a9fa892ecd236e652150058649b13d9161331d85e374c4bec1d60ad6a556c3a9
+oid sha256:40aaba2d15c70d89033b94214bc8306c06d04f2fbceef0fdedf952808109d707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2813793103448276,
+  "epoch": 0.37517241379310345,
   "eval_steps": 17,
-  "global_step": 51,
+  "global_step": 68,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -158,6 +158,49 @@
       "eval_samples_per_second": 68.378,
       "eval_steps_per_second": 8.743,
       "step": 51
+    },
+    {
+      "epoch": 0.2979310344827586,
+      "grad_norm": 0.46963927149772644,
+      "learning_rate": 8.73410738492077e-05,
+      "loss": 2.3514,
+      "step": 54
+    },
+    {
+      "epoch": 0.31448275862068964,
+      "grad_norm": 0.43661412596702576,
+      "learning_rate": 8.564642241456986e-05,
+      "loss": 2.3,
+      "step": 57
+    },
+    {
+      "epoch": 0.3310344827586207,
+      "grad_norm": 0.48196548223495483,
+      "learning_rate": 8.386407858128706e-05,
+      "loss": 2.2038,
+      "step": 60
+    },
+    {
+      "epoch": 0.34758620689655173,
+      "grad_norm": 0.47665441036224365,
+      "learning_rate": 8.199842702516583e-05,
+      "loss": 2.2897,
+      "step": 63
+    },
+    {
+      "epoch": 0.3641379310344828,
+      "grad_norm": 0.4325224459171295,
+      "learning_rate": 8.005405736415126e-05,
+      "loss": 2.1655,
+      "step": 66
+    },
+    {
+      "epoch": 0.37517241379310345,
+      "eval_loss": 2.257903575897217,
+      "eval_runtime": 4.4787,
+      "eval_samples_per_second": 68.1,
+      "eval_steps_per_second": 8.708,
+      "step": 68
     }
   ],
   "logging_steps": 3,
@@ -177,7 +220,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3241919391989760.0,
+  "total_flos": 4322559189319680.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null