Training in progress, step 24, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9301125f1d936d792834b6f3b7dd68274f67f2991fef52d5090e7141b5981bca
+oid sha256:f8097b55631dc02d6a8db5bf97bfd4db0507ef2de43ba47ea049720e0d3a0706
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:de3d0ee449148724e442012f1a6031a865363101af76f0bdb53394451312564c
+oid sha256:2e2a6682355550b13444798e15ae242b99937f498c311fa01b57e43cb4d7b48d
 size 37965300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6eeca6fec2d74dc35412cee25843a6e2b45b715cb98314d10ac41fc41a4cabc
+oid sha256:e9c762e745e6b10819fd8afb33b4a1b715c756c7b22945b0044c81ebcb593a7d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3233603be2c007aac019155f1cd5d754e2eeb600f6ca413bd2048966230a2e8
+oid sha256:b9fbbdb6036d2372f81987526c35ebf7be4064ed59a37e6c1ea765cbfb6cc373
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03738863735942748,
+  "epoch": 0.05608295603914123,
   "eval_steps": 8,
-  "global_step": 16,
+  "global_step": 24,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,70 @@
       "eval_samples_per_second": 16.304,
       "eval_steps_per_second": 8.163,
       "step": 16
+    },
+    {
+      "epoch": 0.039725427194391705,
+      "grad_norm": 0.856139063835144,
+      "learning_rate": 7.269952498697734e-05,
+      "loss": 1.9171,
+      "step": 17
+    },
+    {
+      "epoch": 0.04206221702935592,
+      "grad_norm": 0.8442476987838745,
+      "learning_rate": 6.545084971874738e-05,
+      "loss": 2.1821,
+      "step": 18
+    },
+    {
+      "epoch": 0.04439900686432014,
+      "grad_norm": 1.2221778631210327,
+      "learning_rate": 5.782172325201155e-05,
+      "loss": 2.0464,
+      "step": 19
+    },
+    {
+      "epoch": 0.046735796699284356,
+      "grad_norm": 0.8681303858757019,
+      "learning_rate": 5e-05,
+      "loss": 2.0358,
+      "step": 20
+    },
+    {
+      "epoch": 0.04907258653424858,
+      "grad_norm": 1.1155294179916382,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 1.9598,
+      "step": 21
+    },
+    {
+      "epoch": 0.05140937636921279,
+      "grad_norm": 1.2673661708831787,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.6758,
+      "step": 22
+    },
+    {
+      "epoch": 0.053746166204177014,
+      "grad_norm": 1.268276572227478,
+      "learning_rate": 2.7300475013022663e-05,
+      "loss": 2.1396,
+      "step": 23
+    },
+    {
+      "epoch": 0.05608295603914123,
+      "grad_norm": 0.8677752614021301,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 2.0531,
+      "step": 24
+    },
+    {
+      "epoch": 0.05608295603914123,
+      "eval_loss": 1.8527228832244873,
+      "eval_runtime": 44.1953,
+      "eval_samples_per_second": 16.314,
+      "eval_steps_per_second": 8.168,
+      "step": 24
     }
   ],
   "logging_steps": 1,
@@ -162,7 +226,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6720241111334912e+16,
+  "total_flos": 2.508036166700237e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null