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:e0bec488d6b0e8ee0814358d7d700e84c69516b8b2e5e45aee87ddd7c2386750
+oid sha256:55fab431b1d345efce24912784ed7469e7449bc2ca5debd3133695e8613fa3ff
 size 5327744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f01267c17c7b82a847aa67484daad9b74934761a129fb88c518ad7234b2acd5
+oid sha256:614a8f2168f65aadab7912711e8346ffd8f3e7818efd269ad6e4cdfe24bc3ca0
 size 2857722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b6816d28a1e52010c043f8df09993f8855b8c88a92a1fb049c072fe19a99b66
+oid sha256:b9ef401f25b7d760f23004c6a5482ad76a2b97d0da55c4512010973cc4688c8c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
+oid sha256:ff2736979009751c0c6b0ddcc5f6544d6f723aa752b4798eab0b70fb76cf0083
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03781611912077523,
+  "epoch": 0.05672417868116285,
   "eval_steps": 5,
-  "global_step": 10,
+  "global_step": 15,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -101,6 +101,49 @@
       "eval_samples_per_second": 226.625,
       "eval_steps_per_second": 113.313,
       "step": 10
+    },
+    {
+      "epoch": 0.041597731032852754,
+      "grad_norm": 13.377167701721191,
+      "learning_rate": 9.755282581475769e-05,
+      "loss": 40.0312,
+      "step": 11
+    },
+    {
+      "epoch": 0.045379342944930276,
+      "grad_norm": 16.281776428222656,
+      "learning_rate": 9.045084971874738e-05,
+      "loss": 45.4766,
+      "step": 12
+    },
+    {
+      "epoch": 0.0491609548570078,
+      "grad_norm": 12.971956253051758,
+      "learning_rate": 7.938926261462366e-05,
+      "loss": 44.0938,
+      "step": 13
+    },
+    {
+      "epoch": 0.05294256676908532,
+      "grad_norm": 13.847249984741211,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 42.8828,
+      "step": 14
+    },
+    {
+      "epoch": 0.05672417868116285,
+      "grad_norm": 11.62086296081543,
+      "learning_rate": 5e-05,
+      "loss": 39.8281,
+      "step": 15
+    },
+    {
+      "epoch": 0.05672417868116285,
+      "eval_loss": 2.5738158226013184,
+      "eval_runtime": 1.9718,
+      "eval_samples_per_second": 226.194,
+      "eval_steps_per_second": 113.097,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 84918046556160.0,
+  "total_flos": 127377069834240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null