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:aaa1cf215c80a2dcb326f02fb7e496432b1749b3b3f00f099e3d481a2528bdc3
+oid sha256:163339900fbecbed5ddd1a17d6b74b39842c0bbe47f4d1e7d47830f3824f1554
 size 12609416

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cee99b2c114ffcf7d7a8244f71c789c80f3b7114e711749cc87aa9cd4b0f0cc
+oid sha256:505c12ce22c61b26e57072df07a51f8db0dbe3188fac2afa0b93eebba618669e
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72db1ca300703148b11f6c9ce555ec1a4f9c50722bf07f81b60e9a09bb963e32
+oid sha256:45c1c6e1d05a1345b460e6db68a4c5d40ea13d21e5f6a8bf331b0914efdb5d2f
 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": 0.019618742438609685,
+  "epoch": 0.02615832325147958,
   "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": 86.226,
       "eval_steps_per_second": 43.113,
       "step": 150
+    },
+    {
+      "epoch": 0.020926658601183663,
+      "grad_norm": 12.179810523986816,
+      "learning_rate": 0.0002,
+      "loss": 11.7368,
+      "step": 160
+    },
+    {
+      "epoch": 0.022234574763757644,
+      "grad_norm": 14.598481178283691,
+      "learning_rate": 0.0002,
+      "loss": 11.1283,
+      "step": 170
+    },
+    {
+      "epoch": 0.023542490926331622,
+      "grad_norm": 9.615200996398926,
+      "learning_rate": 0.0002,
+      "loss": 11.2235,
+      "step": 180
+    },
+    {
+      "epoch": 0.0248504070889056,
+      "grad_norm": 10.755783081054688,
+      "learning_rate": 0.0002,
+      "loss": 11.2189,
+      "step": 190
+    },
+    {
+      "epoch": 0.02615832325147958,
+      "grad_norm": 12.484338760375977,
+      "learning_rate": 0.0002,
+      "loss": 11.5377,
+      "step": 200
+    },
+    {
+      "epoch": 0.02615832325147958,
+      "eval_loss": 2.7612085342407227,
+      "eval_runtime": 37.0673,
+      "eval_samples_per_second": 86.869,
+      "eval_steps_per_second": 43.435,
+      "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": 1165456362700800.0,
+  "total_flos": 1546434851635200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null