Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a76fcd13078f6ba7f5a191bc795fbae553b888fe44138c403ab57a91d44631
+oid sha256:cfb665bcfc74fc0113655db065d892e12bf9b13f3abd45b7da7c1053c555af13
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f6532950d0076dc6e55064969d6d1446a6e2b29bb32f08d57bc4be05a18bad92
+oid sha256:c71ae1ffab70a0a33237c22114e56b39b0f0983caab9a5c92b4977744b1f557c
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a87e4caf284f84836b86fbb9d15f85d95c4be4769dd1ae693ef400a82f62b7ca
+oid sha256:892cdbb73603b13c93b70f257d50361e6fa80cc2b310d9806c9d15154035df7a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0c50dbaa792cda4a28fbbc2acb2a3e03c59530712bbc5107212d33064d193da4
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.002771953516471801,
+  "epoch": 0.0035537865595792317,
   "eval_steps": 10,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,43 @@
       "learning_rate": 3.086582838174551e-05,
       "loss": 2.3664,
       "step": 35
+    },
+    {
+      "epoch": 0.0028430292476633854,
+      "grad_norm": 56.26362991333008,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 5.3614,
+      "step": 40
+    },
+    {
+      "epoch": 0.0028430292476633854,
+      "eval_loss": 0.9288716912269592,
+      "eval_runtime": 397.2443,
+      "eval_samples_per_second": 14.913,
+      "eval_steps_per_second": 7.456,
+      "step": 40
+    },
+    {
+      "epoch": 0.0031984079036213083,
+      "grad_norm": 25.66505241394043,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 4.2842,
+      "step": 45
+    },
+    {
+      "epoch": 0.0035537865595792317,
+      "grad_norm": 42.632633209228516,
+      "learning_rate": 0.0,
+      "loss": 3.7495,
+      "step": 50
+    },
+    {
+      "epoch": 0.0035537865595792317,
+      "eval_loss": 0.9020283222198486,
+      "eval_runtime": 395.2916,
+      "eval_samples_per_second": 14.986,
+      "eval_steps_per_second": 7.493,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -102,12 +139,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7010807992811520.0,
+  "total_flos": 9070232840699904.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null