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:bf4b53cbd992ef1d450b74024ca18d07f22acd53b8d39f1f21a86bcfd93f39e2
+oid sha256:d088f7486a38699f5be5e03a5ebec5e16099349a5c282d252a6779f586434451
 size 9450352

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5e9fcdd18a112e5820cd26c3cc25cb4920e89fadb76ff07ac18fa3ae8bcb76a
+oid sha256:c235bb41e387f294413f812d3dc3e309d18817098b6cbb290feb362968cd25dc
 size 18955258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:057d1963d1d10c061cf2ad9b9a81a7ecdc8f32f525f63e478014431a25ca3954
+oid sha256:999b67963d48e6f331d66986822d3e6af67d3827942f91aad76c8473dc2af7f9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.021499596882558453,
+  "epoch": 0.03224939532383768,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 140.077,
       "eval_steps_per_second": 70.038,
       "step": 20
+    },
+    {
+      "epoch": 0.022574576726686373,
+      "grad_norm": 370.4432373046875,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 12.096,
+      "step": 21
+    },
+    {
+      "epoch": 0.025799516259070142,
+      "grad_norm": 498.1689147949219,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 13.1469,
+      "step": 24
+    },
+    {
+      "epoch": 0.026874496103198066,
+      "eval_loss": 3.2063841819763184,
+      "eval_runtime": 2.856,
+      "eval_samples_per_second": 137.257,
+      "eval_steps_per_second": 68.628,
+      "step": 25
+    },
+    {
+      "epoch": 0.02902445579145391,
+      "grad_norm": 2962.651611328125,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 11.6448,
+      "step": 27
+    },
+    {
+      "epoch": 0.03224939532383768,
+      "grad_norm": 423.2963562011719,
+      "learning_rate": 0.0,
+      "loss": 12.5586,
+      "step": 30
+    },
+    {
+      "epoch": 0.03224939532383768,
+      "eval_loss": 3.1865956783294678,
+      "eval_runtime": 2.8199,
+      "eval_samples_per_second": 139.013,
+      "eval_steps_per_second": 69.506,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 123910980894720.0,
+  "total_flos": 185866471342080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null