Training in progress, step 72, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d78a9012c6e065bcf14f3d35f286d5e7b124a0efd18f76b69fe914af3f08a98
+oid sha256:80200b7412a4d398d83f5e1c5b2790c427ac843ac6f8dcc4ca7165f149bbe890
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cc6e2224b3c3c885410bfc9b1f2156db041cd811531070f3aa15eff3f01dd00
+oid sha256:f82149b96dd41c99aa2266e2fb6f3c7a68484a26112c5c82203a7dc357fdf591
 size 640009682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ea915120766314e2bacd5006186d9012cb095e8e05a1dafbc048035142676f
+oid sha256:54695bae591aceb2574c0570650d7a15033601e879a5235bc5ef9cc452369efd
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79429063411e5f67f663bb03057ea480ea282e8a7a96044eb033f6b9f55143b5
+oid sha256:62f589044fe72a89eeac5f01dfea2599de04455cb66e0a4998ee4eb766326c4c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03994071300413449,
+  "epoch": 0.0449333021296513,
   "eval_steps": 8,
-  "global_step": 64,
+  "global_step": 72,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -226,6 +226,35 @@
       "eval_samples_per_second": 9.394,
       "eval_steps_per_second": 4.697,
       "step": 64
+    },
+    {
+      "epoch": 0.04118886028551369,
+      "grad_norm": 0.35130053758621216,
+      "learning_rate": 5.261313375270014e-05,
+      "loss": 0.8259,
+      "step": 66
+    },
+    {
+      "epoch": 0.043061081207582494,
+      "grad_norm": 0.32489344477653503,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.765,
+      "step": 69
+    },
+    {
+      "epoch": 0.0449333021296513,
+      "grad_norm": 0.3194122910499573,
+      "learning_rate": 3.089373510131354e-05,
+      "loss": 0.7716,
+      "step": 72
+    },
+    {
+      "epoch": 0.0449333021296513,
+      "eval_loss": 0.7537363767623901,
+      "eval_runtime": 574.4019,
+      "eval_samples_per_second": 9.398,
+      "eval_steps_per_second": 4.699,
+      "step": 72
     }
   ],
   "logging_steps": 3,
@@ -245,7 +274,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3.4049229412368384e+17,
+  "total_flos": 3.830538308891443e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null