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:b5565bcbb8c0a9f441082a44f84a66e03d5c43610f4ce62aef113a2b36937493
+oid sha256:11012ba39e576dee81d1c206d4af6b7660ee1ee3a5a97dadd8a3f53f9ac73192
 size 94412008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bad55304308fc34a8d80fcf11914f6b0906d83be79cf8e9a4f9530752214e951
+oid sha256:06d10f882e8507caa71e41791f44d1ea775e004b843a13005e6880f4218aa979
 size 48260756

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:713c29710caed13f0e77c70ef93720e0172f8970b01d57ba490781214d2694ea
+oid sha256:d1e5b0ec55d25a0b4aebdbc9348be424ece8b0fa6bd9a54dbbd2104a081e11e1
 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": 0.0029412319236788026,
+  "epoch": 0.003770810158562567,
   "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": 2.4266,
       "step": 35
+    },
+    {
+      "epoch": 0.0030166481268500537,
+      "grad_norm": 2.860438823699951,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.4012,
+      "step": 40
+    },
+    {
+      "epoch": 0.0030166481268500537,
+      "eval_loss": 0.5868576765060425,
+      "eval_runtime": 906.6667,
+      "eval_samples_per_second": 6.159,
+      "eval_steps_per_second": 3.079,
+      "step": 40
+    },
+    {
+      "epoch": 0.0033937291427063106,
+      "grad_norm": 3.215632915496826,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1886,
+      "step": 45
+    },
+    {
+      "epoch": 0.003770810158562567,
+      "grad_norm": 3.213798761367798,
+      "learning_rate": 0.0,
+      "loss": 2.2431,
+      "step": 50
+    },
+    {
+      "epoch": 0.003770810158562567,
+      "eval_loss": 0.5820906162261963,
+      "eval_runtime": 910.8714,
+      "eval_samples_per_second": 6.13,
+      "eval_steps_per_second": 3.065,
+      "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": 2.218056166146048e+16,
+  "total_flos": 2.845673344991232e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null