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:afe760b9f32c4107bab1c86cdce3e357c1ba7193d889365631fd13920daea33d
+oid sha256:642ea32988ce52f17b809a981d84c164c70994f5f4c4d45a4ca481b71a8894eb
 size 100697728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a58f557a4c9be893b810b83cdeb000e4f05c7ec0baaf4d49c5da15bd9b0ed50
+oid sha256:f065abb2b748a39ba7b930287a00acfbe97d9927045fd9ed37234c12e72dc5e6
 size 201478138

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4fcafe51467334025a2305f8c44550e6e8bfc0bc4e21468cb79f88a0d21f9f
+oid sha256:37b677bc2bac210eefecedfdf3d6c86fbbf89e449f5cf2d724f1cbe6a31b5f80
 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": 0.015331544653123802,
+  "epoch": 0.022997316979685704,
   "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": 3.8355,
       "step": 18
+    },
+    {
+      "epoch": 0.01609812188577999,
+      "grad_norm": 1.566597819328308,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 3.709,
+      "step": 21
+    },
+    {
+      "epoch": 0.018397853583748562,
+      "grad_norm": 1.4933898448944092,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 3.6925,
+      "step": 24
+    },
+    {
+      "epoch": 0.018397853583748562,
+      "eval_loss": 0.8878971934318542,
+      "eval_runtime": 111.8602,
+      "eval_samples_per_second": 4.917,
+      "eval_steps_per_second": 2.458,
+      "step": 24
+    },
+    {
+      "epoch": 0.020697585281717133,
+      "grad_norm": 1.413949966430664,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 3.4661,
+      "step": 27
+    },
+    {
+      "epoch": 0.022997316979685704,
+      "grad_norm": 1.453066110610962,
+      "learning_rate": 0.0,
+      "loss": 3.5221,
+      "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": 3684183016734720.0,
+  "total_flos": 5526274525102080.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null