Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f4b073b32e0e45ee5a0665c2225c296791df0624a53fd7f88b7a8a12d7852a9
+oid sha256:91431a3386ac5d5e1fc52d4cffd6513d23e1e4e0da287bb214f517359fd7103c
 size 109009752

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48cbb20e8450fb929b13fe955a9fccb2d44fb5a7c7c8d0a274f10cbf158c9ebc
+oid sha256:e4fc06e80e17c9c4974aba5813f67cab9c1f5a7a554991a92be1e91e654e825b
 size 56088148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2524d0bbcba4740cd7bcb7b38bf3a617d1bce7003e9fd41727db5747210a9ac1
+oid sha256:917a96c53ab74743e395b8aff0bc11606fc218846a3cf94089c57105b19ee572
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b489c13e2d776471e9a48162938854a24466ce6713df9c0fb59abd9a09fb226b
+oid sha256:ca9a25c72339c898b564e0c464a3f6fc75bbeec408008928b7ed05533156b98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.5050505050505051,
+  "epoch": 0.6734006734006734,
   "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": 24.781,
       "eval_steps_per_second": 12.49,
       "step": 150
+    },
+    {
+      "epoch": 0.5387205387205387,
+      "grad_norm": 6.019990178174339e-05,
+      "learning_rate": 2.0055723659649904e-05,
+      "loss": 0.0,
+      "step": 160
+    },
+    {
+      "epoch": 0.5723905723905723,
+      "grad_norm": 6.026657501934096e-05,
+      "learning_rate": 1.1454397434679021e-05,
+      "loss": 0.0,
+      "step": 170
+    },
+    {
+      "epoch": 0.6060606060606061,
+      "grad_norm": 5.954002699581906e-05,
+      "learning_rate": 5.146355805285452e-06,
+      "loss": 0.0,
+      "step": 180
+    },
+    {
+      "epoch": 0.6397306397306397,
+      "grad_norm": 5.726645395043306e-05,
+      "learning_rate": 1.2949737362087156e-06,
+      "loss": 0.0,
+      "step": 190
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "grad_norm": 6.246352131711319e-05,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.6734006734006734,
+      "eval_loss": 2.194750777562149e-06,
+      "eval_runtime": 5.0618,
+      "eval_samples_per_second": 24.695,
+      "eval_steps_per_second": 12.446,
+      "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": 3.1682740617216e+16,
+  "total_flos": 4.2243654156288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null