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:c785ba239581623908f718e12f32e2a1cb9ce1cb990dda00a2e2c5b686b8fde4
+oid sha256:1acfef19c87805330c8ea5a96c2a051a74ddf52b34f6d8516de42cb86e156696
 size 50624

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5f10b1066f32a09e9ec454dfcbf1c18c8c56ad13aca70d90d5307cad152886
+oid sha256:a2e2a0a47ae59635691e30a050ba960fff87a232051fd0cfe423bacfdf85c476
 size 118090

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63076df0e2f5c2eff0ee92071ec83ec94c981f8fbd2f640764417db149cee50d
+oid sha256:8a09ad7e826d10efce700906e00267beeb0fde82aeff880f7721e7c0c6d184a9
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddaa639affba9b89222fee046caf8a7f8b52a142c3b2d35ccd1f461973cfdc78
+oid sha256:b5b325ea4e14a510f9eb0108f2923753e246a5ec70e919cdd84a9afd64b95afd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.6666666666666666,
+  "epoch": 1.0,
   "eval_steps": 4,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -195,6 +195,92 @@
       "eval_samples_per_second": 214.455,
       "eval_steps_per_second": 65.986,
       "step": 20
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 0.11048202216625214,
+      "learning_rate": 2.871103542174637e-06,
+      "loss": 10.3923,
+      "step": 21
+    },
+    {
+      "epoch": 0.7333333333333333,
+      "grad_norm": 0.10397742688655853,
+      "learning_rate": 2.320866025105016e-06,
+      "loss": 10.3856,
+      "step": 22
+    },
+    {
+      "epoch": 0.7666666666666667,
+      "grad_norm": 0.11781251430511475,
+      "learning_rate": 1.8128800512565514e-06,
+      "loss": 10.3889,
+      "step": 23
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.11190535873174667,
+      "learning_rate": 1.3551568628929434e-06,
+      "loss": 10.3923,
+      "step": 24
+    },
+    {
+      "epoch": 0.8,
+      "eval_loss": 10.3880615234375,
+      "eval_runtime": 0.0735,
+      "eval_samples_per_second": 176.834,
+      "eval_steps_per_second": 54.411,
+      "step": 24
+    },
+    {
+      "epoch": 0.8333333333333334,
+      "grad_norm": 0.109310582280159,
+      "learning_rate": 9.549150281252633e-07,
+      "loss": 10.3862,
+      "step": 25
+    },
+    {
+      "epoch": 0.8666666666666667,
+      "grad_norm": 0.1232733428478241,
+      "learning_rate": 6.184665997806832e-07,
+      "loss": 10.3898,
+      "step": 26
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.11298314481973648,
+      "learning_rate": 3.511175705587433e-07,
+      "loss": 10.3874,
+      "step": 27
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "grad_norm": 0.11249785870313644,
+      "learning_rate": 1.5708419435684463e-07,
+      "loss": 10.3854,
+      "step": 28
+    },
+    {
+      "epoch": 0.9333333333333333,
+      "eval_loss": 10.388054847717285,
+      "eval_runtime": 0.0654,
+      "eval_samples_per_second": 198.865,
+      "eval_steps_per_second": 61.189,
+      "step": 28
+    },
+    {
+      "epoch": 0.9666666666666667,
+      "grad_norm": 0.10919848084449768,
+      "learning_rate": 3.9426493427611177e-08,
+      "loss": 10.3892,
+      "step": 29
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.10324089974164963,
+      "learning_rate": 0.0,
+      "loss": 10.388,
+      "step": 30
     }
   ],
   "logging_steps": 1,
@@ -209,12 +295,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 523024465920.0,
+  "total_flos": 777998893056.0,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null