Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bfc9e23aa98ecb5eef7e6cd643b85995e400654f9cf8bafcb582105241a19f8
+oid sha256:9a9646311bc03cc0f072b12ff3ba66d759fabc7cbc2b431ed9f819e2cbbda908
 size 159967880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f700dd587a1db32e7d427471baccb888c10d2b8fbb327b5be34689801fe8b05b
+oid sha256:abdec2f55db93d0f5895dda7c363e45f9011f627c156759724dc457a580aec05
 size 81730196

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714e36bd11f88532014eca46aee4ac4835aa96e5731ff37263d6ad201c24acac
+oid sha256:9327d383e6c6706a43da68b2e96e0839f110187782cc13bdd78b11a0e60158d6
 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": 0.08161044613710555,
+  "epoch": 0.1088139281828074,
   "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": 15.968,
       "eval_steps_per_second": 8.004,
       "step": 150
+    },
+    {
+      "epoch": 0.08705114254624592,
+      "grad_norm": 0.39115750789642334,
+      "learning_rate": 0.0002,
+      "loss": 0.1725,
+      "step": 160
+    },
+    {
+      "epoch": 0.09249183895538629,
+      "grad_norm": 0.857339084148407,
+      "learning_rate": 0.0002,
+      "loss": 0.2213,
+      "step": 170
+    },
+    {
+      "epoch": 0.09793253536452666,
+      "grad_norm": 0.17503942549228668,
+      "learning_rate": 0.0002,
+      "loss": 0.2008,
+      "step": 180
+    },
+    {
+      "epoch": 0.10337323177366703,
+      "grad_norm": 0.6942676901817322,
+      "learning_rate": 0.0002,
+      "loss": 0.2037,
+      "step": 190
+    },
+    {
+      "epoch": 0.1088139281828074,
+      "grad_norm": 0.20953403413295746,
+      "learning_rate": 0.0002,
+      "loss": 0.2294,
+      "step": 200
+    },
+    {
+      "epoch": 0.1088139281828074,
+      "eval_loss": 0.0956772044301033,
+      "eval_runtime": 24.2381,
+      "eval_samples_per_second": 15.967,
+      "eval_steps_per_second": 8.004,
+      "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": 2.262621331075891e+16,
+  "total_flos": 3.026358134164685e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null