Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c62568b4343dc997cf1bfc64e067b5215e05062f29c5cc51314c34f73cb96a3
+oid sha256:06dfd747131a84cf78d34d6302878eb988db534da05543d44dc7e3f05a097c54
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39fec8d13dbe2cd960e43b452a55e630ef43873659b2d5fd74c79a5cd1a5a324
+oid sha256:411b72c1abb318efca3dd32916f79d1c51b7cbf0ad12e733f99b9768d826e436
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bafe2f57268eaa52cbf5c750acbbe9f56c3e602db72fca64287b02e92a6aed4
+oid sha256:aa475f51346237b604de04dfb5849998c82ad8e092cda930a1bc5b8d1fca410b
 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": 0.26881720430107525,
+  "epoch": 0.35842293906810035,
   "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": 79.507,
       "eval_steps_per_second": 39.923,
       "step": 150
+    },
+    {
+      "epoch": 0.2867383512544803,
+      "grad_norm": 4.852773189544678,
+      "learning_rate": 0.0002,
+      "loss": 12.8406,
+      "step": 160
+    },
+    {
+      "epoch": 0.3046594982078853,
+      "grad_norm": 5.590361595153809,
+      "learning_rate": 0.0002,
+      "loss": 12.821,
+      "step": 170
+    },
+    {
+      "epoch": 0.3225806451612903,
+      "grad_norm": 6.373524188995361,
+      "learning_rate": 0.0002,
+      "loss": 12.7874,
+      "step": 180
+    },
+    {
+      "epoch": 0.34050179211469533,
+      "grad_norm": 4.901456356048584,
+      "learning_rate": 0.0002,
+      "loss": 12.9965,
+      "step": 190
+    },
+    {
+      "epoch": 0.35842293906810035,
+      "grad_norm": 5.205903053283691,
+      "learning_rate": 0.0002,
+      "loss": 12.7484,
+      "step": 200
+    },
+    {
+      "epoch": 0.35842293906810035,
+      "eval_loss": 3.230069875717163,
+      "eval_runtime": 3.0502,
+      "eval_samples_per_second": 77.044,
+      "eval_steps_per_second": 38.686,
+      "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": 1126044794880000.0,
+  "total_flos": 1501393059840000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null