Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7adc2c0345bf42a964a452bf81e217ca19c9497dbbb2b86ac1ddc9907c7a1dda
+oid sha256:3f5aadc095aa19ae0a92ea40346221061cf64ade696238736df1f92b8e47cc25
 size 101752088

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1034b807ffd34a1e16b960e0fad9169d9e76226282fc4ff8df46c13968f23e28
+oid sha256:56656c8d878ab192eef6f45181ebf004fa23a09b827026d01064f15dd6518c50
 size 203713238

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0f6aab0ede0461cd9d0c82c37b11b02e4e50ddf39f260cc74be0fadde97ea0e
+oid sha256:aa1f740d5cc072019923fceab4e287e97deaacb74bad1353719ac7cae63df407
 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": 0.07111111111111111,
+  "epoch": 0.10666666666666667,
   "eval_steps": 8,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -73,6 +73,42 @@
       "learning_rate": 0.00013090169943749476,
       "loss": 0.4827,
       "step": 18
+    },
+    {
+      "epoch": 0.07466666666666667,
+      "grad_norm": 1.236522912979126,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 0.2749,
+      "step": 21
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.825536847114563,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 0.27,
+      "step": 24
+    },
+    {
+      "epoch": 0.08533333333333333,
+      "eval_loss": 0.20560859143733978,
+      "eval_runtime": 7.1295,
+      "eval_samples_per_second": 16.691,
+      "eval_steps_per_second": 8.416,
+      "step": 24
+    },
+    {
+      "epoch": 0.096,
+      "grad_norm": 0.8618375658988953,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 0.2052,
+      "step": 27
+    },
+    {
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.8433903455734253,
+      "learning_rate": 0.0,
+      "loss": 0.193,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -87,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3292692008140800.0,
+  "total_flos": 4939038012211200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null