Training in progress, step 18, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e84e196dabeabf3df4037022084bef3b4311d9f5efa1b540b265f733409de689
+oid sha256:22d858cbe7f31d4689a67ecfdbb0c46581e05e62c36fa5a44c184d9c664ba96d
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c6273ca1cdc13aa2bd6e1c9c37c6628d5e5cfc63c1bf6ad0e398ff9809953bb
+oid sha256:20d902f0b5e990e80a77072bb0420fb0622242a57495e8588049d18f0e430199
 size 85723284

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:332759cf7b5cf921f7c9ebfe29466512b01ff3dba8f0377398688b0a48981a95
+oid sha256:6cf30c4e1dfd3b199f004d48c615f0058d9d8168fc7715316fa0d2b53a3286f2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:5ed723721bc2dad2381ab5522e40123ba4aa738fa3e449c48809fa9c2697eb95
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002650371788264743,
+  "epoch": 0.005300743576529486,
   "eval_steps": 9,
-  "global_step": 9,
+  "global_step": 18,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "eval_samples_per_second": 14.492,
       "eval_steps_per_second": 1.812,
       "step": 9
+    },
+    {
+      "epoch": 0.003533829051019657,
+      "grad_norm": 11.649324417114258,
+      "learning_rate": 9.987820251299122e-05,
+      "loss": 3.78,
+      "step": 12
+    },
+    {
+      "epoch": 0.004417286313774571,
+      "grad_norm": 8.40984058380127,
+      "learning_rate": 9.924038765061042e-05,
+      "loss": 3.8775,
+      "step": 15
+    },
+    {
+      "epoch": 0.005300743576529486,
+      "grad_norm": 7.721532344818115,
+      "learning_rate": 9.806308479691595e-05,
+      "loss": 3.3807,
+      "step": 18
+    },
+    {
+      "epoch": 0.005300743576529486,
+      "eval_loss": 0.9211275577545166,
+      "eval_runtime": 394.5819,
+      "eval_samples_per_second": 14.496,
+      "eval_steps_per_second": 1.812,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.2661897253879808e+16,
+  "total_flos": 2.5323794507759616e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null