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:a7e7da49b26fe0b4746044ba9119ad88f34af6d0a41feb03c713aca31377d50d
+oid sha256:8ced0900b02c4a7749b9f311632c4d843524d0806ed972708556b4ba862af9c7
 size 3152296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:91006b4978e30d32790b4b10e7c021e0126ac19bd79929992a704b109077c510
+oid sha256:7f0ebe4e8e61902168a5b83bd6177dcb213a247835627b90f328de19a3c4b407
 size 6332154

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4a5e24c7c1c033cf22d211e72b7fe81f90a2f7161a472f6d190d4c61e9d9dba
+oid sha256:d5f0e0b692474898497d76b8956cd31d749a4f92cb7d3a44bb6bfcca5f331558
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46d68217ddf3e899bf1495ee33b9ec14e2c91ed912ffcb460a7bb01192b04b7d
+oid sha256:f0e9cc72c20ddd925ef39b6005e82a4d8730b1dde32cfcd070d74c83a8a3564a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.06535947712418301,
+  "epoch": 0.09803921568627451,
   "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": 216.001,
       "eval_steps_per_second": 108.838,
       "step": 20
+    },
+    {
+      "epoch": 0.06862745098039216,
+      "grad_norm": 1333.117431640625,
+      "learning_rate": 4.2178276747988446e-05,
+      "loss": 136.1218,
+      "step": 21
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 906.4305419921875,
+      "learning_rate": 2.061073738537635e-05,
+      "loss": 126.1907,
+      "step": 24
+    },
+    {
+      "epoch": 0.08169934640522876,
+      "eval_loss": 34.98023223876953,
+      "eval_runtime": 0.6288,
+      "eval_samples_per_second": 205.155,
+      "eval_steps_per_second": 103.373,
+      "step": 25
+    },
+    {
+      "epoch": 0.08823529411764706,
+      "grad_norm": 2130.99560546875,
+      "learning_rate": 5.449673790581611e-06,
+      "loss": 124.2307,
+      "step": 27
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "grad_norm": 1594.8175048828125,
+      "learning_rate": 0.0,
+      "loss": 141.1562,
+      "step": 30
+    },
+    {
+      "epoch": 0.09803921568627451,
+      "eval_loss": 34.989933013916016,
+      "eval_runtime": 0.6129,
+      "eval_samples_per_second": 210.489,
+      "eval_steps_per_second": 106.06,
+      "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": 44686450360320.0,
+  "total_flos": 67029675540480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null