Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbc45dc11051d1f4864888a0e570e581995add708c6aacff93e5da70cc6ce514
+oid sha256:d88253bc2b5332725631e687ecc87e02694085dc9aa71b7961213eba3f607b9a
 size 891333320

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:853389a394718aac5e4d7c0fbd9a79f4c580d0d231f97f88edfb3f59bdf314e0
+oid sha256:711611d0d17c023cddd6132601f261b139f9a7f14d4e603072d8aaf8fff7545e
 size 452984596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:25db4dbb2ba94e91727cce799620437c78e78810f53ff0628d41702c044b6ba4
+oid sha256:cc1e9d7576e79dd381098b714973a1693ea325ff713e44ab0042ddfdcff6a369
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:a991012fbb3e0053bc41a0b782b67db27509c27d2801c8bf4a64c3687e55e582
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0011068987464371697,
+  "epoch": 0.0016603481196557546,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -52,6 +52,28 @@
       "eval_samples_per_second": 6.643,
       "eval_steps_per_second": 0.83,
       "step": 10
+    },
+    {
+      "epoch": 0.0013282784957246035,
+      "grad_norm": 38.57117462158203,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 13.3548,
+      "step": 12
+    },
+    {
+      "epoch": 0.0016603481196557546,
+      "grad_norm": 30.507431030273438,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.1808,
+      "step": 15
+    },
+    {
+      "epoch": 0.0016603481196557546,
+      "eval_loss": 1.3598648309707642,
+      "eval_runtime": 2290.1174,
+      "eval_samples_per_second": 6.644,
+      "eval_steps_per_second": 0.831,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.7562264756224e+16,
+  "total_flos": 4.1343397134336e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null