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:beab01d89610a52b3862f2e77a6ef3be450bfa3b43dcc6d1a6f904436aa5a31d
+oid sha256:2eba3634c1ffd6e4ae0b701362ca12c1d63eebacdfef69ea70351fb0b4145497
 size 645975704

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb9be936ad05cf25e71d007ca6e0e79aa971269a3670b1cc8477c0944677584e
+oid sha256:93bd76d64c3e6ea4b1ab0c962168ce61ab91d5d71ea831738cb1f07f5a3d7646
 size 328468404

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e472d8ab49f81694f1178644979fba35dbe5dabefc2f415ac8c406211723d57d
+oid sha256:5f2824a1e86e1f2ebb1954454acc2d65d06e39bdc1ec88097e15e38ec185b81b
 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": 0.0009328684538871463,
+  "epoch": 0.0013993026808307193,
   "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": 16.017,
       "eval_steps_per_second": 4.004,
       "step": 10
+    },
+    {
+      "epoch": 0.0011194421446645755,
+      "grad_norm": 3.462336540222168,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 2.315,
+      "step": 12
+    },
+    {
+      "epoch": 0.0013993026808307193,
+      "grad_norm": 3.0801501274108887,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.5734,
+      "step": 15
+    },
+    {
+      "epoch": 0.0013993026808307193,
+      "eval_loss": 1.2294880151748657,
+      "eval_runtime": 1127.2145,
+      "eval_samples_per_second": 16.017,
+      "eval_steps_per_second": 4.005,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.19971857825792e+16,
+  "total_flos": 1.804021269528576e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null