Training in progress, step 81, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f50ac2845723ac438a556f00aff72e72ee7529e661ae0dad230397ef7a0bc8a
+oid sha256:4ef909cf0c9ad7b5eb1ebf2e04efae99a9a0e143d62d9d72650d5ab2e70b2abf
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5e09c3b6b818e713e35dd87a7ddcb10209449cb73aa1d0e9e27b090782924c7
+oid sha256:2e82bf9b08ccd30a079819eaf476bcbd437d4d4793751cde4b1bd8a18705d882
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a81bf9124ac119638eb2b25660fa97a60b2fab63f08197bcec7a4693d4aa6edc
+oid sha256:7a6013b3e443f3d3918b66f424386dee8227e6cbe276f00f582fd5eee09d9831
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5dcc5b33f65fdaffd6a8f394a182adc55f95c04061e1e53640018b07b2b89f10
+oid sha256:90f7a57653bcfdeb8d3e27706e79cc5f6e1f14bbd0ff72a8e33edaaa89ef8274
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.8947368421052633,
+  "epoch": 2.1315789473684212,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 14.022,
       "eval_steps_per_second": 1.753,
       "step": 72
+    },
+    {
+      "epoch": 1.973684210526316,
+      "grad_norm": 7.776499271392822,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 1.9714,
+      "step": 75
+    },
+    {
+      "epoch": 2.0526315789473686,
+      "grad_norm": 6.823435306549072,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.7944,
+      "step": 78
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "grad_norm": 7.627166271209717,
+      "learning_rate": 1.0599462319663905e-05,
+      "loss": 1.5251,
+      "step": 81
+    },
+    {
+      "epoch": 2.1315789473684212,
+      "eval_loss": 0.7713338732719421,
+      "eval_runtime": 4.5611,
+      "eval_samples_per_second": 14.032,
+      "eval_steps_per_second": 1.754,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.009431442662359e+17,
+  "total_flos": 1.132918702300201e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null