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:cd210b2e3be1deefd43b07039178256a298c6c8efba7af2e85d19c1562ec261a
+oid sha256:1a44df8fded0a3b9a8233d4486f63bbea56f90838ee7159bdcf319e55bce2bef
 size 222865880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:493421d517a68d4222219039e94f1c6e4f5aae546bcafed8f4c7d5c0a30f2cba
+oid sha256:f5c92e42285edb99c7c168cc52236596ffcdbe2f7d3606843230615ed2d121ac
 size 113528596

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf95dc75f3738cdab19607c88ff1a52c0fd432992f39b094cf2968f0205e89b3
+oid sha256:a2825f8bffcd0070d0e88119f3cdefeda1e50ca4df43bea61ae067b16355223c
 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": 0.014072614691809739,
+  "epoch": 0.01876348625574632,
   "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": 9.155,
       "eval_steps_per_second": 4.578,
       "step": 150
+    },
+    {
+      "epoch": 0.015010789004597054,
+      "grad_norm": 0.8109822869300842,
+      "learning_rate": 0.0002,
+      "loss": 1.0838,
+      "step": 160
+    },
+    {
+      "epoch": 0.01594896331738437,
+      "grad_norm": 0.43211817741394043,
+      "learning_rate": 0.0002,
+      "loss": 1.0516,
+      "step": 170
+    },
+    {
+      "epoch": 0.016887137630171686,
+      "grad_norm": 0.5124821662902832,
+      "learning_rate": 0.0002,
+      "loss": 0.9819,
+      "step": 180
+    },
+    {
+      "epoch": 0.017825311942959002,
+      "grad_norm": 2.5899274349212646,
+      "learning_rate": 0.0002,
+      "loss": 0.987,
+      "step": 190
+    },
+    {
+      "epoch": 0.01876348625574632,
+      "grad_norm": 0.7276327610015869,
+      "learning_rate": 0.0002,
+      "loss": 0.9722,
+      "step": 200
+    },
+    {
+      "epoch": 0.01876348625574632,
+      "eval_loss": 0.4974622130393982,
+      "eval_runtime": 245.2117,
+      "eval_samples_per_second": 9.151,
+      "eval_steps_per_second": 4.576,
+      "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": 4.8595133005824e+16,
+  "total_flos": 6.4339615678464e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null