Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b60a17e87bd4119b73c2cf96cfe559219bda001d59ae15ccc8057db8bfd1f2a
+oid sha256:fd4c1fe439652e9ec64da9ba79512304a425ecc8cc660297071c9205c0454cd1
 size 50503544

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:af2f19af4e74197aaffddb56a7daca7df1bf0356bba1fe75a7a851d18b5c499f
+oid sha256:5c0f3485052cc311c652f6053f8bb16cd0d969d238f42c6b87557c4442d79e8e
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4afd3405addb6640a60216b0a2ef93345ae6cf02b9d830a6cf05c48dadd2035a
+oid sha256:6f4796865ede106812b09fd8ba4d4deaa9bc7a01436139b627e5afd95faa1c43
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00202757502027575,
+  "epoch": 0.0040551500405515,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 5.805,
       "eval_steps_per_second": 5.805,
       "step": 25
+    },
+    {
+      "epoch": 0.0024330900243309003,
+      "grad_norm": 3.194694995880127,
+      "learning_rate": 5e-05,
+      "loss": 1.216,
+      "step": 30
+    },
+    {
+      "epoch": 0.00283860502838605,
+      "grad_norm": 0.823891818523407,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5,
+      "step": 35
+    },
+    {
+      "epoch": 0.0032441200324412004,
+      "grad_norm": 0.46792903542518616,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.209,
+      "step": 40
+    },
+    {
+      "epoch": 0.0036496350364963502,
+      "grad_norm": 0.7259841561317444,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5031,
+      "step": 45
+    },
+    {
+      "epoch": 0.0040551500405515,
+      "grad_norm": 81.30354309082031,
+      "learning_rate": 0.0,
+      "loss": 1.4401,
+      "step": 50
+    },
+    {
+      "epoch": 0.0040551500405515,
+      "eval_loss": 1.422434687614441,
+      "eval_runtime": 236.3994,
+      "eval_samples_per_second": 5.795,
+      "eval_steps_per_second": 5.795,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 321677741260800.0,
+  "total_flos": 643355482521600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null