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:b28565321ecd72bef279f696006dc51a50ecca215519e722cc60fe0c3ac9d1fc
+oid sha256:9eef18818db222d2eb9a9994760f52d5e84d4734f03b49c3c2629cedd592b181
 size 73911112

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c191d1f1ea56797c9d425374a70ce8fdabac788b08c14d2979565ac9e0469108
+oid sha256:cbdf447f24457a3c7cc050203299177d3b2fd8f54716a306a20bc425bff889a2
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d67956489e9e6959ed6163206eeb2ca28e8073b92defecc24f6772b9c9ef34ac
+oid sha256:823cba4910637a431b96b25f8c4224afed19b5d09ba4c0026be8aaed6e653d1e
 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": 0.000624167776298269,
+  "epoch": 0.001248335552596538,
   "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": 19.385,
       "eval_steps_per_second": 9.693,
       "step": 15
+    },
+    {
+      "epoch": 0.0007490013315579227,
+      "grad_norm": 0.2933429181575775,
+      "learning_rate": 0.00018090169943749476,
+      "loss": 0.7884,
+      "step": 18
+    },
+    {
+      "epoch": 0.0008322237017310253,
+      "eval_loss": 0.8717365860939026,
+      "eval_runtime": 522.3142,
+      "eval_samples_per_second": 19.373,
+      "eval_steps_per_second": 9.688,
+      "step": 20
+    },
+    {
+      "epoch": 0.0008738348868175766,
+      "grad_norm": 0.26551419496536255,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.9068,
+      "step": 21
+    },
+    {
+      "epoch": 0.0009986684420772304,
+      "grad_norm": 0.2481399029493332,
+      "learning_rate": 6.909830056250527e-05,
+      "loss": 0.8418,
+      "step": 24
+    },
+    {
+      "epoch": 0.0010402796271637817,
+      "eval_loss": 0.8618488907814026,
+      "eval_runtime": 522.4366,
+      "eval_samples_per_second": 19.369,
+      "eval_steps_per_second": 9.685,
+      "step": 25
+    },
+    {
+      "epoch": 0.0011235019973368841,
+      "grad_norm": 0.26211848855018616,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.8709,
+      "step": 27
+    },
+    {
+      "epoch": 0.001248335552596538,
+      "grad_norm": 0.23953785002231598,
+      "learning_rate": 0.0,
+      "loss": 0.8629,
+      "step": 30
+    },
+    {
+      "epoch": 0.001248335552596538,
+      "eval_loss": 0.8600496649742126,
+      "eval_runtime": 522.2468,
+      "eval_samples_per_second": 19.376,
+      "eval_steps_per_second": 9.689,
+      "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": 1632836046028800.0,
+  "total_flos": 3233015371137024.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null