Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85ef69a41b6ae030ba350ff70fe4cab5f5da4b4f81ca9de46df362933916e8f7
+oid sha256:e7782d929202887902a1880e6c5494bddc96815411c38885a83db1f5ba8cf7b5
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4b5d3d3ec31c0026ce03c2f7325453406c4596833a84493c07756dbb68ae88f
+oid sha256:7037d794507f74810cbe2d2ceefa1afb1ea19de1a1e08d028e7c29e515cf8e01
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2578854fec35b9b4ef56c5f6d57541489047f65bd5480561bc2ec87ac0920f
+oid sha256:cb0b29821d8c3fb50b70bea0ad4ae6e320cb0247ce153bb264fbea6e9f2c08b2
 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": 0.03317031681905167,
+  "epoch": 0.0425260472039124,
   "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": 1.7342,
       "step": 35
+    },
+    {
+      "epoch": 0.03402083776312992,
+      "grad_norm": 0.6449187994003296,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.823,
+      "step": 40
+    },
+    {
+      "epoch": 0.03402083776312992,
+      "eval_loss": 1.8062323331832886,
+      "eval_runtime": 50.5201,
+      "eval_samples_per_second": 9.798,
+      "eval_steps_per_second": 4.909,
+      "step": 40
+    },
+    {
+      "epoch": 0.03827344248352116,
+      "grad_norm": 1.0189423561096191,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8506,
+      "step": 45
+    },
+    {
+      "epoch": 0.0425260472039124,
+      "grad_norm": 0.8987523913383484,
+      "learning_rate": 0.0,
+      "loss": 1.6495,
+      "step": 50
+    },
+    {
+      "epoch": 0.0425260472039124,
+      "eval_loss": 1.804133653640747,
+      "eval_runtime": 50.7761,
+      "eval_samples_per_second": 9.749,
+      "eval_steps_per_second": 4.884,
+      "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": 8554234647674880.0,
+  "total_flos": 1.0912429064060928e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null