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:eebc945d9b883655db1b224e7846e86a3c885ca31652323c1a261d4a94e6a58a
+oid sha256:52000a456554a0b5c37c39ad480cfd85744035f4a394858c17e6d3daa81ae8df
 size 201892112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1864a564fa619425a9f29b261e5edabd8d2f140eb88e4bb05ef3dbe83653f649
+oid sha256:1e89bd00fa02b9d4ff891f0abb9d88ee1e7926fe72d40d8222d69ea16fe4c718
 size 102864548

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31a8059683c2b5138637352137e92dbf364cfc59afc90c9e7a10fafdb11fceed
+oid sha256:561184d6af9b5bc7313240b6e7bdc678bdc8b052aa570cf9b3e295e4fe999d47
 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": 0.0017506236596787606,
+  "epoch": 0.0026259354895181407,
   "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": 23.679,
       "eval_steps_per_second": 2.961,
       "step": 10
+    },
+    {
+      "epoch": 0.0021007483916145125,
+      "grad_norm": 8.257246971130371,
+      "learning_rate": 9.938441702975689e-05,
+      "loss": 2.0523,
+      "step": 12
+    },
+    {
+      "epoch": 0.0026259354895181407,
+      "grad_norm": 7.305975914001465,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 1.954,
+      "step": 15
+    },
+    {
+      "epoch": 0.0026259354895181407,
+      "eval_loss": 1.72903311252594,
+      "eval_runtime": 406.2308,
+      "eval_samples_per_second": 23.684,
+      "eval_steps_per_second": 2.961,
+      "step": 15
     }
   ],
   "logging_steps": 3,
@@ -71,7 +93,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4266295704944640.0,
+  "total_flos": 6399443557416960.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null