Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d85134095084ddd6dfabe916d5f3f0acdde6fbec31a3f111645b78cf0ca638e
+oid sha256:82d8f2a4067dc03ec7a083e02060f734d95320fe885b59dd73f9a7a58039c952
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79174ed55ecf4f15d8795c373d995326418da6b3fff2c00a7c99ff5b43997e36
+oid sha256:a09116afb49b4bc6e2b99efbd14b39287e442c5fe88c8be9d7c175b1382ac7bf
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4479d8612262ecedc656e3fb719b965a26864f43306d791dee922d685b13b6f5
+oid sha256:e557af93914c894de252ad5739c858bc8be67dba19068d91502dd049001e333e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4395bafb1cf8adc0d9dbfe550d1b98763496e37a8fadb76c1ca1168a4a757f4e
+oid sha256:37841e69eda911caeb33edeefa0b2f140e72dcce247aeb757b2fe89c00d7887b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001660259766797359,
+  "epoch": 0.0003320519533594718,
   "eval_steps": 10,
-  "global_step": 13,
+  "global_step": 26,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -37,6 +37,35 @@
       "eval_samples_per_second": 26.683,
       "eval_steps_per_second": 13.342,
       "step": 10
+    },
+    {
+      "epoch": 0.0001915684346304645,
+      "grad_norm": 0.6554055213928223,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 2.3075,
+      "step": 15
+    },
+    {
+      "epoch": 0.000255424579507286,
+      "grad_norm": 1.4760862588882446,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 2.1224,
+      "step": 20
+    },
+    {
+      "epoch": 0.000255424579507286,
+      "eval_loss": 2.0983011722564697,
+      "eval_runtime": 1208.4435,
+      "eval_samples_per_second": 27.282,
+      "eval_steps_per_second": 13.642,
+      "step": 20
+    },
+    {
+      "epoch": 0.00031928072438410746,
+      "grad_norm": 0.8199297189712524,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 2.0542,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1066063264481280.0,
+  "total_flos": 2132126528962560.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null