Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:894b3316ea9a82fb6c4668d06fa2d0115e4f2b1dab84e87de3764be854864ad4
+oid sha256:1104051ee61b4abe85204378e2f679323fd2ca03bd98f8d6ae6230925f2d1f01
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78ec9fadc97c8e6cc40f6be2bd2d91c9fc4af148dbc3eb99a92242a35b86e1e8
+oid sha256:c2175f3b52612e98191b1403c654cc9ad8baee9d093ae00a92372f80b245feeb
 size 505518

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b1dbe479f6756df2ff500203698c9f57bca85e9e4a1cdb231db97e90dac145f
+oid sha256:ca99bebeea385ce2c1d4db38b17f7a71d082f2093a6dc4945fbf7655d2c5b44a
 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": 0.0016389748212493086,
+  "epoch": 0.002458462231873963,
   "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": 44.3601,
       "step": 18
+    },
+    {
+      "epoch": 0.001720923562311774,
+      "grad_norm": 1.3945192098617554,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 44.3528,
+      "step": 21
+    },
+    {
+      "epoch": 0.00196676978549917,
+      "grad_norm": 1.4578007459640503,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 44.3023,
+      "step": 24
+    },
+    {
+      "epoch": 0.00196676978549917,
+      "eval_loss": 11.081588745117188,
+      "eval_runtime": 19.807,
+      "eval_samples_per_second": 259.404,
+      "eval_steps_per_second": 129.702,
+      "step": 24
+    },
+    {
+      "epoch": 0.0022126160086865664,
+      "grad_norm": 1.4502112865447998,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 44.3151,
+      "step": 27
+    },
+    {
+      "epoch": 0.002458462231873963,
+      "grad_norm": 1.383909821510315,
+      "learning_rate": 0.0,
+      "loss": 44.314,
+      "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": 415991070720.0,
+  "total_flos": 623986606080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null