Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21af181566e8661107db783a01dcdc43ac1e3e501a08d430a1828f82b945e3b3
+oid sha256:44dce517a9fac82a3efd7976706325b5ac2607a3862f4b7a75a8de5b0066d922
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a53eabebc2692443ee9dc9cf3ce33d5b09c05cad317f86b6c7861a66746234f2
+oid sha256:3ff1a00fe25a8a81e9606b46458ed2cbe3cb1bd93ee3a9001ea8f10f97e912d6
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c63b277f9063baabe3cab581c91fc76d2ee8635847283051aab19b4b4f8b94a4
+oid sha256:4c79ce552511ab3fd4290edc1f45d3fb5d7823eba09fa44b1c6db1931627dfc8
 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": 0.006178496771735437,
+  "epoch": 0.00823799569564725,
   "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": 37.734,
       "eval_steps_per_second": 18.869,
       "step": 150
+    },
+    {
+      "epoch": 0.006590396556517799,
+      "grad_norm": 0.7156699895858765,
+      "learning_rate": 0.0002,
+      "loss": 0.8475,
+      "step": 160
+    },
+    {
+      "epoch": 0.007002296341300162,
+      "grad_norm": 0.7343199849128723,
+      "learning_rate": 0.0002,
+      "loss": 0.9222,
+      "step": 170
+    },
+    {
+      "epoch": 0.007414196126082524,
+      "grad_norm": 1.0209944248199463,
+      "learning_rate": 0.0002,
+      "loss": 0.8851,
+      "step": 180
+    },
+    {
+      "epoch": 0.007826095910864887,
+      "grad_norm": 0.903324544429779,
+      "learning_rate": 0.0002,
+      "loss": 0.9177,
+      "step": 190
+    },
+    {
+      "epoch": 0.00823799569564725,
+      "grad_norm": 0.8378692269325256,
+      "learning_rate": 0.0002,
+      "loss": 0.9269,
+      "step": 200
+    },
+    {
+      "epoch": 0.00823799569564725,
+      "eval_loss": 0.9066545367240906,
+      "eval_runtime": 270.1918,
+      "eval_samples_per_second": 37.836,
+      "eval_steps_per_second": 18.92,
+      "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": 1.2300729974784e+16,
+  "total_flos": 1.6400973299712e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null