Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d9c45194fc31db98b38ecbf6a8f064e9b7b39e45b89aee8ca759c83ab64e93a
+oid sha256:626db33315205db956fc916787124ff63fbe54fe057db42624bdd17c04d018dc
 size 10636096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9227cf7f6b2c896f1a6e2d181f2d55bda43321aea078fb121f4011e57b2a101
+oid sha256:ed7ab57b10f86295c3410d0d22b1e74c6dcf58207fd5e17771c64136e7ab8422
 size 21354682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db2cf325190493b1183f8997adf8341988f0dfdc3f858236adf04cf88f1cacd1
+oid sha256:e6c3a2442b886eb9545b5f83dff39be38b802337e3261b4e5093970dfa7426d6
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef527702b4e2147a500c0b29beb26751d245ebb60338b3910b449b6549ac4d59
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.018365472910927456,
+  "epoch": 0.03673094582185491,
   "eval_steps": 5,
-  "global_step": 15,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -74,6 +74,65 @@
       "eval_samples_per_second": 29.682,
       "eval_steps_per_second": 14.841,
       "step": 15
+    },
+    {
+      "epoch": 0.02203856749311295,
+      "grad_norm": 1.859694480895996,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 16.0224,
+      "step": 18
+    },
+    {
+      "epoch": 0.024487297214569943,
+      "eval_loss": 3.8249597549438477,
+      "eval_runtime": 11.5654,
+      "eval_samples_per_second": 29.744,
+      "eval_steps_per_second": 14.872,
+      "step": 20
+    },
+    {
+      "epoch": 0.025711662075298437,
+      "grad_norm": 1.2232089042663574,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 15.1654,
+      "step": 21
+    },
+    {
+      "epoch": 0.02938475665748393,
+      "grad_norm": 1.4554587602615356,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 14.8155,
+      "step": 24
+    },
+    {
+      "epoch": 0.030609121518212427,
+      "eval_loss": 3.7654643058776855,
+      "eval_runtime": 11.5619,
+      "eval_samples_per_second": 29.753,
+      "eval_steps_per_second": 14.876,
+      "step": 25
+    },
+    {
+      "epoch": 0.03305785123966942,
+      "grad_norm": 1.4697390794754028,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 15.2675,
+      "step": 27
+    },
+    {
+      "epoch": 0.03673094582185491,
+      "grad_norm": 1.2916182279586792,
+      "learning_rate": 0.0,
+      "loss": 14.5486,
+      "step": 30
+    },
+    {
+      "epoch": 0.03673094582185491,
+      "eval_loss": 3.7533998489379883,
+      "eval_runtime": 11.5608,
+      "eval_samples_per_second": 29.756,
+      "eval_steps_per_second": 14.878,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -88,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 129293195673600.0,
+  "total_flos": 258586391347200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null