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:e1b9cc10e59eee0a482ef058cdd892f5ee95113383053a597b42bfdb154b7124
+oid sha256:63a5b66bb5cdf13092a0931b868dc49722c0c159ebf5360a226abe1d4473218f
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4317a6ae5f87fb4a3a2c25cb4308b3c896713ee28ff43548cdab62d58ba48bc0
+oid sha256:3a2359906f8660facbbf435cdea237820c31f9e940a763a301c53421776fdd41
 size 90310010

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8194e1b8c74d7216b4daf200bbfe7e0ecb859e151ee00b0f9ea8e824e6edee25
+oid sha256:cab4d6c2ce43e24d19e16d85f2f7af6e830104f5a5c4b29ee3dac335d1d10f59
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:55cc6a3635d19619caf820a77458fa3cfe7756f7bb9d10678c62733cb46f36c0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018674136321195144,
+  "epoch": 0.028011204481792718,
   "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": 29.718,
       "eval_steps_per_second": 14.859,
       "step": 10
+    },
+    {
+      "epoch": 0.02054154995331466,
+      "grad_norm": 14.252686500549316,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 5.4462,
+      "step": 11
+    },
+    {
+      "epoch": 0.022408963585434174,
+      "grad_norm": 13.769002914428711,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.9482,
+      "step": 12
+    },
+    {
+      "epoch": 0.02427637721755369,
+      "grad_norm": 14.226924896240234,
+      "learning_rate": 0.00015877852522924732,
+      "loss": 5.444,
+      "step": 13
+    },
+    {
+      "epoch": 0.026143790849673203,
+      "grad_norm": 12.833412170410156,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 4.164,
+      "step": 14
+    },
+    {
+      "epoch": 0.028011204481792718,
+      "grad_norm": 29.60838508605957,
+      "learning_rate": 0.0001,
+      "loss": 5.389,
+      "step": 15
+    },
+    {
+      "epoch": 0.028011204481792718,
+      "eval_loss": 5.058675289154053,
+      "eval_runtime": 7.6248,
+      "eval_samples_per_second": 29.64,
+      "eval_steps_per_second": 14.82,
+      "step": 15
     }
   ],
   "logging_steps": 1,
@@ -120,7 +163,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 967722569564160.0,
+  "total_flos": 1451583854346240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null