Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1be6388c9f5e0e323fb5c3875de3e7ff4a836df02a547ba7f1d788ce9117c561
+oid sha256:56599bf250551688d7c870371ae06ee3b7ea9d4898e3245d41dc4d1cfbea7407
 size 65309632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1318421abd78a247bab75910cc94556fdece8e885630eb3a077b8de2e0012f8
+oid sha256:9e53eedf6cccc43caf14c191033bc1ae252b06a81a78c4e13f8b07cf7f5308cb
 size 33424212

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3c3cef82a77b8c5738ee503d413c0a4f9866d1a3db207e359a45ff19926f30c
+oid sha256:d59909266d557f32bffeea210ce4bd1afe3e0d5ed78b3f0bf0cc9ca4af9ca766
 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": 0.012829559304637885,
+  "epoch": 0.017106079072850514,
   "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": 34.405,
       "eval_steps_per_second": 17.206,
       "step": 150
+    },
+    {
+      "epoch": 0.013684863258280411,
+      "grad_norm": 4.960232257843018,
+      "learning_rate": 0.0002,
+      "loss": 7.9318,
+      "step": 160
+    },
+    {
+      "epoch": 0.014540167211922937,
+      "grad_norm": 5.194616794586182,
+      "learning_rate": 0.0002,
+      "loss": 7.9618,
+      "step": 170
+    },
+    {
+      "epoch": 0.015395471165565463,
+      "grad_norm": 4.613633632659912,
+      "learning_rate": 0.0002,
+      "loss": 7.2951,
+      "step": 180
+    },
+    {
+      "epoch": 0.01625077511920799,
+      "grad_norm": 5.5177507400512695,
+      "learning_rate": 0.0002,
+      "loss": 7.6231,
+      "step": 190
+    },
+    {
+      "epoch": 0.017106079072850514,
+      "grad_norm": 13.841983795166016,
+      "learning_rate": 0.0002,
+      "loss": 8.0881,
+      "step": 200
+    },
+    {
+      "epoch": 0.017106079072850514,
+      "eval_loss": 1.9552608728408813,
+      "eval_runtime": 143.1864,
+      "eval_samples_per_second": 34.382,
+      "eval_steps_per_second": 17.194,
+      "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": 2.656857995005133e+16,
+  "total_flos": 3.534314936519885e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null