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:a49d08f8538b71549849da37679906accb50ce9cea6f9fa846b3e6d64f2c1ef8
+oid sha256:87579548f868f953e0be9298a2f1ce26386c84af16214860c2f0626ae96b97ff
 size 12609312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:241cdf586c151f3e0bc88ee15e0cec6c9827a4e6265345bad3b94695ca3a53ca
+oid sha256:8e6b25b0693b4d2e69320b93e926dbe72014079b5849dede7e8e4a6606e134dd
 size 6615034

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b8500ebc296cfe2e3f6ae90901a15cc00051e141db2a4948698da9fe8208dd85
+oid sha256:d372a878dd6788e5b89e0452085ed9aabf5b30f6ad915b9d745c66f55d88a859
 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": 0.0008230018464785017,
+  "epoch": 0.0010551305724083356,
   "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": 20.6911,
       "step": 35
+    },
+    {
+      "epoch": 0.0008441044579266684,
+      "grad_norm": 175.84165954589844,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 19.1404,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008441044579266684,
+      "eval_loss": 4.520143032073975,
+      "eval_runtime": 436.6139,
+      "eval_samples_per_second": 45.699,
+      "eval_steps_per_second": 22.851,
+      "step": 40
+    },
+    {
+      "epoch": 0.000949617515167502,
+      "grad_norm": 134.43414306640625,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 18.0815,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010551305724083356,
+      "grad_norm": 126.74542236328125,
+      "learning_rate": 0.0,
+      "loss": 18.7478,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010551305724083356,
+      "eval_loss": 4.509800434112549,
+      "eval_runtime": 440.2616,
+      "eval_samples_per_second": 45.321,
+      "eval_steps_per_second": 22.662,
+      "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": 500052824948736.0,
+  "total_flos": 646998172631040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null