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:e908281e0960ff9a2d4a0fe8a2638ab0291a1b88a7dc53fe8a5b62c9361d0e69
+oid sha256:2ec4a741fa4c6511a15404bbcd6a472d534e092c7ed8f50f98da508e855449aa
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fa0e8fece85be74cc186ec2a59c62640ac2f728c149c8fc2d4a2461ba9df47f
+oid sha256:dcb8905428174a7d8d33a1b542c3f21ad04ef2b5766d84cd93408f5639ca280e
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:66846a1a2d466cde2705e723dbdb0fd132aefa0f6eb3cd191f3c155efb669d2a
+oid sha256:b2299ec3eac5552ca1df6f9821a1b4cefb949648401955e3353356045e4ce7a4
 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": 0.015436374431031071,
+  "epoch": 0.019790223629527013,
   "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": 0.8876,
       "step": 35
+    },
+    {
+      "epoch": 0.01583217890362161,
+      "grad_norm": 0.6236824989318848,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.8796,
+      "step": 40
+    },
+    {
+      "epoch": 0.01583217890362161,
+      "eval_loss": 0.8821372389793396,
+      "eval_runtime": 88.453,
+      "eval_samples_per_second": 12.029,
+      "eval_steps_per_second": 6.014,
+      "step": 40
+    },
+    {
+      "epoch": 0.017811201266574313,
+      "grad_norm": 0.4817047119140625,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8854,
+      "step": 45
+    },
+    {
+      "epoch": 0.019790223629527013,
+      "grad_norm": 0.5099672675132751,
+      "learning_rate": 0.0,
+      "loss": 0.8664,
+      "step": 50
+    },
+    {
+      "epoch": 0.019790223629527013,
+      "eval_loss": 0.8753272891044617,
+      "eval_runtime": 88.4937,
+      "eval_samples_per_second": 12.023,
+      "eval_steps_per_second": 6.012,
+      "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": 9694668933562368.0,
+  "total_flos": 1.2364810800857088e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null