Training in progress, step 18444, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d74881490c58204c809ecc63d49988dff67283b41b5ba8928513c1e758c01a6
+oid sha256:835444f9e28ac5484b00aeb974fc2781eea0baeb83bb2ac9f97a6f07fc4d81b1
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9422bd31ecf2a5d6b1c8c13fe817398668cecd58b962bb20e0a6029f9ac8d3d
+oid sha256:8420915da398af22a8b097d398ff247cdfd9d112d48e473387b322aad7d73248
 size 168150738

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e03e06adeb2983022141cbb3499da248eadd0a0a927d6e04f8eed941c0d3d686
+oid sha256:cf0c4d80b282260ef34ccddc4ebdfb0ff868efdec857e174744b9741a7c9964f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82ab3f4c71b15efcf419ae699bcc09c12d9d69fda628dcac52fdb8059760dd34
+oid sha256:112b0e3f3850ccaa762f9eb894c6c56a98cff86a4eab4f8d883ff8a96dbc8748
 size 1000

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.9973975276512688,
+  "epoch": 4.0,
   "eval_steps": 2048,
-  "global_step": 18432,
+  "global_step": 18444,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -129211,6 +129211,90 @@
       "eval_test_samples_per_second": 13.302,
       "eval_test_steps_per_second": 0.831,
       "step": 18432
+    },
+    {
+      "epoch": 3.9976144003469964,
+      "grad_norm": 1.5703761577606201,
+      "learning_rate": 3.0003218233616098e-06,
+      "loss": 1.8993,
+      "step": 18433
+    },
+    {
+      "epoch": 3.997831273042724,
+      "grad_norm": 1.6585696935653687,
+      "learning_rate": 3.000265969737023e-06,
+      "loss": 1.8753,
+      "step": 18434
+    },
+    {
+      "epoch": 3.9980481457384514,
+      "grad_norm": 1.722380518913269,
+      "learning_rate": 3.000215435499207e-06,
+      "loss": 1.9192,
+      "step": 18435
+    },
+    {
+      "epoch": 3.998265018434179,
+      "grad_norm": 1.6945613622665405,
+      "learning_rate": 3.000170220649976e-06,
+      "loss": 1.7501,
+      "step": 18436
+    },
+    {
+      "epoch": 3.9984818911299067,
+      "grad_norm": 1.587354302406311,
+      "learning_rate": 3.000130325190978e-06,
+      "loss": 1.6834,
+      "step": 18437
+    },
+    {
+      "epoch": 3.9986987638256344,
+      "grad_norm": 1.530950903892517,
+      "learning_rate": 3.0000957491236143e-06,
+      "loss": 1.8401,
+      "step": 18438
+    },
+    {
+      "epoch": 3.998915636521362,
+      "grad_norm": 1.571050763130188,
+      "learning_rate": 3.000066492449139e-06,
+      "loss": 1.7994,
+      "step": 18439
+    },
+    {
+      "epoch": 3.9991325092170893,
+      "grad_norm": 1.3360202312469482,
+      "learning_rate": 3.00004255516859e-06,
+      "loss": 1.7106,
+      "step": 18440
+    },
+    {
+      "epoch": 3.9993493819128174,
+      "grad_norm": 1.9069377183914185,
+      "learning_rate": 3.0000239372828404e-06,
+      "loss": 2.0346,
+      "step": 18441
+    },
+    {
+      "epoch": 3.9995662546085446,
+      "grad_norm": 1.6238856315612793,
+      "learning_rate": 3.0000106387925348e-06,
+      "loss": 1.8038,
+      "step": 18442
+    },
+    {
+      "epoch": 3.9997831273042723,
+      "grad_norm": 1.4525717496871948,
+      "learning_rate": 3.00000265969815e-06,
+      "loss": 1.9284,
+      "step": 18443
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 2.0924839973449707,
+      "learning_rate": 2.9999999999999997e-06,
+      "loss": 1.8805,
+      "step": 18444
     }
   ],
   "logging_steps": 1,
@@ -129225,12 +129309,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.425362788270473e+18,
+  "total_flos": 4.42814002458683e+18,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null