Training in progress, step 26, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4140ef476b84249227f8a739e6bf7c8cd6b5bfbff0d7f92f064ef1dcc0e60187
+oid sha256:be8ce8cfc4011099fd03e59beef181464e8709106981052632d68c4aa3f4db0a
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77cadd592a2f0ebf621e0e43a9b813542c58b2fa9c2f1f7c1f6fffb30d3ed437
+oid sha256:5012a69ed4b968327c721bd7102c2b7909ecf988ced1aaf62a06f01bfb86a56f
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46b0ecaac8112b4f90b6fe8f4b2b5e503450792b9cccc6a3804245d9e6e81093
+oid sha256:19345076a59d2345cb36b77781c9e57468c57d8d41c5a6f2c85d50f71a6f780a
 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": 0.00025028036213643165,
+  "epoch": 0.0005005607242728633,
   "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": 10.412,
       "eval_steps_per_second": 5.206,
       "step": 10
+    },
+    {
+      "epoch": 0.00028878503323434427,
+      "grad_norm": 0.6111458539962769,
+      "learning_rate": 9.619397662556435e-05,
+      "loss": 0.9867,
+      "step": 15
+    },
+    {
+      "epoch": 0.00038504671097912567,
+      "grad_norm": 0.5312387347221375,
+      "learning_rate": 8.535533905932738e-05,
+      "loss": 0.8138,
+      "step": 20
+    },
+    {
+      "epoch": 0.00038504671097912567,
+      "eval_loss": 0.8737485408782959,
+      "eval_runtime": 2105.6213,
+      "eval_samples_per_second": 10.387,
+      "eval_steps_per_second": 5.194,
+      "step": 20
+    },
+    {
+      "epoch": 0.0004813083887239071,
+      "grad_norm": 0.6903040409088135,
+      "learning_rate": 6.91341716182545e-05,
+      "loss": 0.7798,
+      "step": 25
     }
   ],
   "logging_steps": 5,
@@ -56,7 +85,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3745367602495488.0,
+  "total_flos": 7675691629805568.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null