Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:235d397f324dd392b75e42a6d4d0cb497dde15665c23b81caa11ad43b587190b
+oid sha256:6c43b6cacd4f1a9d727a67e13c8e92738f6f95a662522ff3e28f8dbb18848996
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:873e478dcf822496684298e3220ff66175797fad79e546264547772ec5c6468e
+oid sha256:b13b7e77078489cd9cda8f444865e45449e58c411b52de337042c1aa4809fb72
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cbed6e13ade6f1fe664543af581dc0a27d6a0be863baec41ae7654a854ac114e
+oid sha256:f1c5789ab5b9f061f20359cabc37bf26aa695ff333aef8a397425c3a09048ba0
 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": 0.01715805427664503,
+  "epoch": 0.022877405702193373,
   "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": 88.465,
       "eval_steps_per_second": 44.244,
       "step": 150
+    },
+    {
+      "epoch": 0.018301924561754696,
+      "grad_norm": 0.10107854008674622,
+      "learning_rate": 0.0002,
+      "loss": 11.8024,
+      "step": 160
+    },
+    {
+      "epoch": 0.019445794846864366,
+      "grad_norm": 0.07902155816555023,
+      "learning_rate": 0.0002,
+      "loss": 11.8053,
+      "step": 170
+    },
+    {
+      "epoch": 0.020589665131974032,
+      "grad_norm": 0.09612026065587997,
+      "learning_rate": 0.0002,
+      "loss": 11.7985,
+      "step": 180
+    },
+    {
+      "epoch": 0.021733535417083703,
+      "grad_norm": 0.1154506579041481,
+      "learning_rate": 0.0002,
+      "loss": 11.7908,
+      "step": 190
+    },
+    {
+      "epoch": 0.022877405702193373,
+      "grad_norm": 0.14365091919898987,
+      "learning_rate": 0.0002,
+      "loss": 11.7961,
+      "step": 200
+    },
+    {
+      "epoch": 0.022877405702193373,
+      "eval_loss": 11.792742729187012,
+      "eval_runtime": 41.3381,
+      "eval_samples_per_second": 89.046,
+      "eval_steps_per_second": 44.535,
+      "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": 18773390131200.0,
+  "total_flos": 25031186841600.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null