Training in progress, step 126, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0334b9c8e6876fab6ed87107050e3885ffb35429017837de0362c4100f0aa52f
+oid sha256:01cb8628fbaa385c70170cc240eca6ce7360fb4b460944fe4faee72ad5f49283
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0a36adeb224b1d92453f6eaa88bb48f97dd81822d1637ccb2f1aee4ef354205
+oid sha256:e88b25ca005cdee8045dc4f68993f0e1eaaeaa2e0ce7d4d440405757c7f36a14
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b055fca04eb7d087b2171cb13ed71fc4c60009472eb0eae85529d38474ab9cbc
+oid sha256:eddeaa1ec3b19d99f3f1397c8ef47035630ab8e80035d4ac09cca828ada76eb3
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95c99427ab0e3f179e8260c56d2a524955cd643e000ed1c4e3ac111dee56d825
+oid sha256:9fde2add4ac526f9d88b4a85a5e304b22d4aa9bf06cf799f89fbf1fa68e0bf83
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.11864406779661017,
+  "epoch": 0.23728813559322035,
   "eval_steps": 63,
-  "global_step": 63,
+  "global_step": 126,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -65,6 +65,56 @@
       "eval_samples_per_second": 18.656,
       "eval_steps_per_second": 9.328,
       "step": 63
+    },
+    {
+      "epoch": 0.1318267419962335,
+      "grad_norm": 0.7335411310195923,
+      "learning_rate": 0.0001672300890261317,
+      "loss": 0.4612,
+      "step": 70
+    },
+    {
+      "epoch": 0.15065913370998116,
+      "grad_norm": 0.48060673475265503,
+      "learning_rate": 0.00015721166601221698,
+      "loss": 0.4036,
+      "step": 80
+    },
+    {
+      "epoch": 0.1694915254237288,
+      "grad_norm": 0.3535134196281433,
+      "learning_rate": 0.00014625382902408356,
+      "loss": 0.4005,
+      "step": 90
+    },
+    {
+      "epoch": 0.18832391713747645,
+      "grad_norm": 0.3984243869781494,
+      "learning_rate": 0.00013453650544213076,
+      "loss": 0.4554,
+      "step": 100
+    },
+    {
+      "epoch": 0.2071563088512241,
+      "grad_norm": 0.4779428541660309,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.4137,
+      "step": 110
+    },
+    {
+      "epoch": 0.22598870056497175,
+      "grad_norm": 0.4857834577560425,
+      "learning_rate": 0.00010960230259076818,
+      "loss": 0.4406,
+      "step": 120
+    },
+    {
+      "epoch": 0.23728813559322035,
+      "eval_loss": 0.4128398299217224,
+      "eval_runtime": 5.9848,
+      "eval_samples_per_second": 18.714,
+      "eval_steps_per_second": 9.357,
+      "step": 126
     }
   ],
   "logging_steps": 10,
@@ -84,7 +134,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 9792456606351360.0,
+  "total_flos": 1.929568453656576e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null