Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:16fc8e3d1db654c9e2e4572b150cb7b1e23944fa0774ee76e37f9e75a8f5d87f
+oid sha256:768dc23c293a8ab1de074c9e0587d9719e442363e054b31eaf335133677bc631
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9be36c1d691914526051a456bc55a32162e247ee7db53d7813d5e437520a88b
+oid sha256:9293396f003c1c8c4b00f530fe89d4c28ef3a7d327cd7cd8890e9f6931753cba
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2524d0bbcba4740cd7bcb7b38bf3a617d1bce7003e9fd41727db5747210a9ac1
+oid sha256:917a96c53ab74743e395b8aff0bc11606fc218846a3cf94089c57105b19ee572
 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": 0.5050505050505051,
+  "epoch": 0.6734006734006734,
   "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": 24.713,
       "eval_steps_per_second": 12.455,
       "step": 150
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 2.1789359379909e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.5723905723905723,
+      "grad_norm": 2.3240922018885612e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 1.9898488972103223e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "grad_norm": 1.7000074876705185e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 1.546139537822455e-05,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "eval_loss": 7.095484306773869e-07,
+      "eval_runtime": 5.0574,
+      "eval_samples_per_second": 24.716,
+      "eval_steps_per_second": 12.457,
+      "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": 3.1682740617216e+16,
+  "total_flos": 4.2243654156288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null