Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:611495341dc853915d76c4cf53853d63ef47960ade27872c8fa535a86ad5bc98
+oid sha256:958b5deb396cb9082ab826626d2492ee2b3ff0b2e6202720b19b263df297124f
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fa45d7a87cc26d33416aff026972fa9f400c9e84a816e415aba7f809f618981
+oid sha256:feeb2b4095af4747f2ffa4fdc27e55937fb6c06e373cea4709b505ade5d0f095
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:74fcc0ca6f729460be0f058725605a9df3de326d1ceeee9c5538d85888f8fab7
+oid sha256:6ff6165bedc653481ebaaed4deb40f7058d8312ba283f03b3bc24f1b3dfbd34f
 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": 0.2682163611980331,
+  "epoch": 0.35762181493071077,
   "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": 33.554,
       "eval_steps_per_second": 16.777,
       "step": 150
+    },
+    {
+      "epoch": 0.2860974519445686,
+      "grad_norm": 1.4494447708129883,
+      "learning_rate": 0.0002,
+      "loss": 1.3201,
+      "step": 160
+    },
+    {
+      "epoch": 0.30397854269110414,
+      "grad_norm": 1.070709228515625,
+      "learning_rate": 0.0002,
+      "loss": 1.4724,
+      "step": 170
+    },
+    {
+      "epoch": 0.3218596334376397,
+      "grad_norm": 1.35964834690094,
+      "learning_rate": 0.0002,
+      "loss": 1.2352,
+      "step": 180
+    },
+    {
+      "epoch": 0.3397407241841752,
+      "grad_norm": 0.8636605739593506,
+      "learning_rate": 0.0002,
+      "loss": 1.3099,
+      "step": 190
+    },
+    {
+      "epoch": 0.35762181493071077,
+      "grad_norm": 1.291929841041565,
+      "learning_rate": 0.0002,
+      "loss": 1.3074,
+      "step": 200
+    },
+    {
+      "epoch": 0.35762181493071077,
+      "eval_loss": 1.3072607517242432,
+      "eval_runtime": 7.04,
+      "eval_samples_per_second": 33.523,
+      "eval_steps_per_second": 16.761,
+      "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": 2.648806790057165e+16,
+  "total_flos": 3.537551173563187e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null