Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7f2b69b78fed1fd7cf0c4d2873a66fbd0088c79d44f862c3264f3f69107b5f54
+oid sha256:16cea865067e1bdc5408492fedd115acde75b757982c02e5263e93d590f6b372
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9b206fe80dcd3aa6512e2b6659122e3964be4d0f8ef1c3600b40e4e9a0bb6dc
+oid sha256:d02d4d58af9ab25d98ba24ce4bc761a50031e52600cf776308da4b90e493684a
 size 445914554

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7742dbc91195111885a9df1046697411ef9ea364663b4d0a0af418562c6c5dd0
+oid sha256:cb646c1f7b10937eee3dbbbe7820ed9bc5c878d6c5b9a4ad0dcfc8d28b8f6c74
 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": 0.03828972559029994,
+  "epoch": 0.07657945118059988,
   "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": 3.98,
       "eval_steps_per_second": 2.002,
       "step": 15
+    },
+    {
+      "epoch": 0.04594767070835992,
+      "grad_norm": 2331.68115234375,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 5.2684,
+      "step": 18
+    },
+    {
+      "epoch": 0.05105296745373325,
+      "eval_loss": 1.322815179824829,
+      "eval_runtime": 41.4853,
+      "eval_samples_per_second": 3.977,
+      "eval_steps_per_second": 2.001,
+      "step": 20
+    },
+    {
+      "epoch": 0.053605615826419914,
+      "grad_norm": 1110465.0,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 5.5578,
+      "step": 21
+    },
+    {
+      "epoch": 0.0612635609444799,
+      "grad_norm": 72944.203125,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 5.022,
+      "step": 24
+    },
+    {
+      "epoch": 0.06381620931716656,
+      "eval_loss": 1.3195682764053345,
+      "eval_runtime": 41.4276,
+      "eval_samples_per_second": 3.983,
+      "eval_steps_per_second": 2.003,
+      "step": 25
+    },
+    {
+      "epoch": 0.06892150606253988,
+      "grad_norm": 3819.193603515625,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 5.3914,
+      "step": 27
+    },
+    {
+      "epoch": 0.07657945118059988,
+      "grad_norm": 4386.46533203125,
+      "learning_rate": 0.0,
+      "loss": 5.5024,
+      "step": 30
+    },
+    {
+      "epoch": 0.07657945118059988,
+      "eval_loss": 1.3190549612045288,
+      "eval_runtime": 41.4399,
+      "eval_samples_per_second": 3.982,
+      "eval_steps_per_second": 2.003,
+      "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": 1.3106218008576e+16,
+  "total_flos": 2.55315935232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null