Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1254e2c96f3b68253b2dbdb9ddf36cded7995110cfb6beb8729707eddda73432
+oid sha256:46aa76c0725e2d55994904d0b07525554416ab29f58e76f7109a13b801824a7d
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:802a2e6f195c0bc324d47be9de4924e2252b7c1f8a21a5d39d8879cc1ab5d4a7
+oid sha256:c5f83c2d3e1c3dfb947093c99d216781a628885181b4e010d0837a3c42ef2f24
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7dd4e625838433450f2a66632755a7794a8e2c896bf0ed2750890b8ec7bca5
+oid sha256:9f755b8572e0483c08b257040652d1ccdb0792ef7020da7baaa1d8cbc6e26417
 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": 0.16597510373443983,
+  "epoch": 0.22130013831258644,
   "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": 24.015,
       "eval_steps_per_second": 12.039,
       "step": 150
+    },
+    {
+      "epoch": 0.17704011065006917,
+      "grad_norm": 0.5134880542755127,
+      "learning_rate": 0.0002,
+      "loss": 0.2988,
+      "step": 160
+    },
+    {
+      "epoch": 0.18810511756569848,
+      "grad_norm": 0.5094125866889954,
+      "learning_rate": 0.0002,
+      "loss": 0.248,
+      "step": 170
+    },
+    {
+      "epoch": 0.1991701244813278,
+      "grad_norm": 0.6164352297782898,
+      "learning_rate": 0.0002,
+      "loss": 0.2982,
+      "step": 180
+    },
+    {
+      "epoch": 0.21023513139695713,
+      "grad_norm": 0.4869607090950012,
+      "learning_rate": 0.0002,
+      "loss": 0.2838,
+      "step": 190
+    },
+    {
+      "epoch": 0.22130013831258644,
+      "grad_norm": 0.47990214824676514,
+      "learning_rate": 0.0002,
+      "loss": 0.3091,
+      "step": 200
+    },
+    {
+      "epoch": 0.22130013831258644,
+      "eval_loss": 0.2770348787307739,
+      "eval_runtime": 15.9233,
+      "eval_samples_per_second": 23.927,
+      "eval_steps_per_second": 11.995,
+      "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": 3.884084921106432e+16,
+  "total_flos": 5.206523358530765e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null