Training in progress, step 54, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94971f99e97ec0550e2a125b660b0ea6317e0e0438890f713cc221db742ac5c9
+oid sha256:926ebdfc9654db7fbd361e45b0c4a71f2bb3cb80092497d15f3be55330b07082
 size 228140600

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edca4fea10b8d375c396ebc7d99110615ebdde61385d29cf83b7cde67514baa9
+oid sha256:f041f526f6f6b0af90e071f7f7d946f34f1a795dcb7e65de7bbd514c3638607c
 size 116472340

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eabfcd1b25a9d15bb11d9c2889384891cc1a9db7b0c9fa8eb6b8ffe55907bbf9
+oid sha256:d856b9ed3ab969ab9e0a41ec549a4535cca2f0c11ca2cfa13f51d67e2e3b244b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0896677f34f08366c4c71a3f69133212afc490296ec7ee225b8aefde1f38f24c
+oid sha256:2011b1e019073e4bafc29de9703ff0a6e7c1252c3a53d804807bd1c99d390d1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.15463917525773196,
+  "epoch": 0.18556701030927836,
   "eval_steps": 9,
-  "global_step": 45,
+  "global_step": 54,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -160,6 +160,35 @@
       "eval_samples_per_second": 6.799,
       "eval_steps_per_second": 0.86,
       "step": 45
+    },
+    {
+      "epoch": 0.16494845360824742,
+      "grad_norm": 3.0694377422332764,
+      "learning_rate": 6.209609477998338e-05,
+      "loss": 3.0856,
+      "step": 48
+    },
+    {
+      "epoch": 0.17525773195876287,
+      "grad_norm": 1.9787322282791138,
+      "learning_rate": 5.695865504800327e-05,
+      "loss": 2.83,
+      "step": 51
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "grad_norm": 1.9755208492279053,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.765,
+      "step": 54
+    },
+    {
+      "epoch": 0.18556701030927836,
+      "eval_loss": 0.7139042615890503,
+      "eval_runtime": 72.0348,
+      "eval_samples_per_second": 6.802,
+      "eval_steps_per_second": 0.861,
+      "step": 54
     }
   ],
   "logging_steps": 3,
@@ -179,7 +208,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.5782235252719616e+17,
+  "total_flos": 1.8641335841980416e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null