Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8faeb0ff1806866e44086322934e79b60a40f902258e1bc10b99ae9e80d70695
+oid sha256:5862fa68b865ef538704bc7bbf2a93539cc031848d865f8fb161c3949a19cccd
 size 250422888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f52f59802895eb570233fa63568becf54298340f80a4d3b09b8b91eebecd3aec
+oid sha256:147d246b0246e1efd3d32ee3fd836633633adb3715f54437044c9008605718f4
 size 501168482

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8288cb8cb0b54526d97f2ff59da883c307360a17e99a5d7d1d6e7afb2436e03b
+oid sha256:cdf286495b2f9086f0435e305d486647eb1934cc509a3961a7bfe47275b3ca95
 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": 0.0011725219481452168,
+  "epoch": 0.0017587829222178253,
   "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": 2.3954,
       "step": 18
+    },
+    {
+      "epoch": 0.0012311480455524776,
+      "grad_norm": 2.3207039833068848,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.1978,
+      "step": 21
+    },
+    {
+      "epoch": 0.0014070263377742602,
+      "grad_norm": 3.1815786361694336,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.1437,
+      "step": 24
+    },
+    {
+      "epoch": 0.0014070263377742602,
+      "eval_loss": 0.5491191148757935,
+      "eval_runtime": 1144.7534,
+      "eval_samples_per_second": 6.274,
+      "eval_steps_per_second": 3.137,
+      "step": 24
+    },
+    {
+      "epoch": 0.0015829046299960427,
+      "grad_norm": 2.303309679031372,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.0794,
+      "step": 27
+    },
+    {
+      "epoch": 0.0017587829222178253,
+      "grad_norm": 3.0738754272460938,
+      "learning_rate": 0.0,
+      "loss": 2.476,
+      "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": 1.26956599246848e+16,
+  "total_flos": 1.90434898870272e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null