Training in progress, step 15, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ca25d29da107de773af0753f7548b61744457c2524f65708651d23b522e9303
+oid sha256:5e7d31f42c36ca2b6182f3fd3a20dc693ef3c4df8b2c564631d180b20ef3e5f3
 size 1195453784

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dc10aa312ed3d1f9454ee1615bfb238f007ec521994e1be6039a44b81b7609fc
+oid sha256:01763ab0852eae3c912e9d050160c9525aa0b964c547afc7af8485243bf49dc0
 size 341314196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
+oid sha256:adf0e0fad701e76d66d9ca7e7e7bb2833a45c43ddf9224441b9068ca8a415c6c
 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": 0.01932367149758454,
+  "epoch": 0.028985507246376812,
   "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": 7.474,
       "eval_steps_per_second": 0.934,
       "step": 10
+    },
+    {
+      "epoch": 0.02318840579710145,
+      "grad_norm": 0.4105644226074219,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 0.1287,
+      "step": 12
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "grad_norm": 0.45149490237236023,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.125,
+      "step": 15
+    },
+    {
+      "epoch": 0.028985507246376812,
+      "eval_loss": 0.11515907943248749,
+      "eval_runtime": 116.6908,
+      "eval_samples_per_second": 7.473,
+      "eval_steps_per_second": 0.934,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.575797865729229e+16,
+  "total_flos": 3.792146857879142e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null