Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c27f6def5aaf8cd7d7d4949e2fa921c97485d4661c9bc1ef03e07893b19d5caa
+oid sha256:1abcd2309ac6f594ebfc55dec363bf061fd0f896e59e40d9507b14ca3f06ee5e
 size 1437764104

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:654392bffc6d0c33e1e9bb34a6407ff8bd0ffadde54cac03ce462e1ca8356836
+oid sha256:654ad9687d25ef306d9355ef8ff3c416be526de17b13a45a9ef99a43a1b60f9b
 size 5560660331

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa27801dd4017ca4e0de1e424862d618dd1e045f5ba8b18827a67e5492c82136
+oid sha256:2a89667b29289d192d9a826773e50a07fdbec603c845381028aaab26b62b30d4
 size 14645

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afdf7ecb2765efd6f925e0ed77d9d82d1829928914fa75cb1e71901d83525f29
+oid sha256:e2afc36988589b22056d7e5bc0f45af5dd3252b95d81895f36beddc42d48ad8c
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 100,
-  "best_metric": 8.819294453132898e-05,
+  "best_global_step": 125,
+  "best_metric": 1.7720147980071488e-06,
   "best_model_checkpoint": "./checkpoints/checkpoint-100",
-  "epoch": 1.2666666666666666,
+  "epoch": 1.9015873015873015,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -117,6 +117,57 @@
       "eval_samples_per_second": 2.282,
       "eval_steps_per_second": 2.282,
       "step": 100
+    },
+    {
+      "epoch": 1.3936507936507936,
+      "grad_norm": 0.04021649435162544,
+      "learning_rate": 0.00018630179233263504,
+      "loss": 0.0008430718444287777,
+      "step": 110
+    },
+    {
+      "epoch": 1.5206349206349206,
+      "grad_norm": 0.015746096149086952,
+      "learning_rate": 0.00018142602813143785,
+      "loss": 0.00017143874429166318,
+      "step": 120
+    },
+    {
+      "epoch": 1.5841269841269843,
+      "eval_loss": 1.7720147980071488e-06,
+      "eval_runtime": 58.9076,
+      "eval_samples_per_second": 2.292,
+      "eval_steps_per_second": 2.292,
+      "step": 125
+    },
+    {
+      "epoch": 1.6476190476190475,
+      "grad_norm": 0.0021020174026489258,
+      "learning_rate": 0.00017589466942945556,
+      "loss": 5.975814419798553e-05,
+      "step": 130
+    },
+    {
+      "epoch": 1.7746031746031745,
+      "grad_norm": 0.009194367565214634,
+      "learning_rate": 0.00016975225147457026,
+      "loss": 0.0029441041871905325,
+      "step": 140
+    },
+    {
+      "epoch": 1.9015873015873015,
+      "grad_norm": 0.06948527693748474,
+      "learning_rate": 0.00016304822940447139,
+      "loss": 0.0033933721482753755,
+      "step": 150
+    },
+    {
+      "epoch": 1.9015873015873015,
+      "eval_loss": 0.000525600160472095,
+      "eval_runtime": 59.2375,
+      "eval_samples_per_second": 2.279,
+      "eval_steps_per_second": 2.279,
+      "step": 150
     }
   ],
   "logging_steps": 10,
@@ -131,7 +182,7 @@
         "early_stopping_threshold": 0.001
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 2
       }
     },
     "TrainerControl": {
@@ -145,7 +196,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.392679877862336e+16,
+  "total_flos": 2.090517701009856e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null