Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6eaa81a275e1ab565d302607e164c226e464b36aab55a3a3b1f2ad6e84d74243
+oid sha256:f2e5602672de86b174f760d0ecddfdfbc7f564b753eb215efd64f4b4e003ed90
 size 32856

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10816abf3249cbe7ae5313e8c37ab079f4a1dd883870af919e0d9ef78b6d8ba9
+oid sha256:11a34dd59973a2ac5fd9beb414063ce11e25a1059a85800f9ca29e7dcdb0f467
 size 71358

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df2eff7fc04c424d03efebb207948c12df40c4005d61c167cc0982b8e6c469d5
+oid sha256:f77c43d63d3041d91a8112c31b2d67da93c4f39db82fa601678dd4bc0493cbbe
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d31dc31a119769737d72f3df4c8cdf99522596cafc12bf2eea05a4ff374f599c
+oid sha256:859ff0676471245c9481ca25d6d6778d1c7963c39b7877af46bb8ca30a9ead21
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3994673768308921,
+  "epoch": 0.5326231691078562,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -144,6 +144,49 @@
       "eval_samples_per_second": 356.405,
       "eval_steps_per_second": 179.323,
       "step": 150
+    },
+    {
+      "epoch": 0.42609853528628494,
+      "grad_norm": 0.9496349096298218,
+      "learning_rate": 0.0002,
+      "loss": 43.7259,
+      "step": 160
+    },
+    {
+      "epoch": 0.45272969374167776,
+      "grad_norm": 0.8923008441925049,
+      "learning_rate": 0.0002,
+      "loss": 43.7386,
+      "step": 170
+    },
+    {
+      "epoch": 0.4793608521970706,
+      "grad_norm": 0.8389256596565247,
+      "learning_rate": 0.0002,
+      "loss": 43.809,
+      "step": 180
+    },
+    {
+      "epoch": 0.5059920106524634,
+      "grad_norm": 0.8299220204353333,
+      "learning_rate": 0.0002,
+      "loss": 43.865,
+      "step": 190
+    },
+    {
+      "epoch": 0.5326231691078562,
+      "grad_norm": 0.8370271325111389,
+      "learning_rate": 0.0002,
+      "loss": 43.8225,
+      "step": 200
+    },
+    {
+      "epoch": 0.5326231691078562,
+      "eval_loss": 10.938294410705566,
+      "eval_runtime": 0.4389,
+      "eval_samples_per_second": 362.31,
+      "eval_steps_per_second": 182.294,
+      "step": 200
     }
   ],
   "logging_steps": 10,
@@ -158,12 +201,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 215167795200.0,
+  "total_flos": 287637504000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null