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:b162401e4beffcd1eb3d56b943fcbbff849c8cf6c4ea872c6c912e07304b46ae
+oid sha256:561b237ccae877fcd3efbe8bbf3e45d4fbadbcb801dd473fb6f593f4fdfa7cf4
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00efcde6dd36cd61f0f7e26b9dabdb2ed49bc1263c3daa769bb1404763f8d653
+oid sha256:dd986764a5c41b417db26e4fd85b5f400bf54faa9b8cd6f01102e89f14bdc30f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c17bb02566243bdb0c6f3689e9f23bade0d33edefb267f5fe283e0ced951075
+oid sha256:7cbc0c7db91bf7ca6bd55942122b915e021e9960eac016ccb6ca22b32565ae6e
 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": 0.0014133776191654005,
+  "epoch": 0.0021200664287481007,
   "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": 2.1148,
       "step": 18
+    },
+    {
+      "epoch": 0.0014840465001236705,
+      "grad_norm": 0.3931140899658203,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.2127,
+      "step": 21
+    },
+    {
+      "epoch": 0.0016960531429984806,
+      "grad_norm": 0.3743416965007782,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1533,
+      "step": 24
+    },
+    {
+      "epoch": 0.0016960531429984806,
+      "eval_loss": 2.149599313735962,
+      "eval_runtime": 1162.5415,
+      "eval_samples_per_second": 7.688,
+      "eval_steps_per_second": 3.844,
+      "step": 24
+    },
+    {
+      "epoch": 0.0019080597858732906,
+      "grad_norm": 0.3767165541648865,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.1056,
+      "step": 27
+    },
+    {
+      "epoch": 0.0021200664287481007,
+      "grad_norm": 0.3632538914680481,
+      "learning_rate": 0.0,
+      "loss": 2.1531,
+      "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": 1.1221045163851776e+16,
+  "total_flos": 1.6785199790555136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null