Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3adf2b43faafb26f5e7e18fe69630a782ca15ae895433dff093e58bf452fdeaf
+oid sha256:c689ffb90d4044607b05c319a7d006e9bfb5bc58d663eef003ac25c39cffe9fe
 size 390888

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:999204d28cc7a408156366cae9215bd89390275b555ba88f5214405d04b52093
+oid sha256:2c0c0b53c70f8440bcd9f1ad03865a6241ae6ef4413d68e25996f0b63eb0eb2c
 size 819770

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fd3d8c26246428e8b509d69e481e99fb79255caea9279fb6313413f7aa567a3a
+oid sha256:af2202558662bca10e0fe13d768ab39eb3cf9190e25153973e536077ff3dcd4b
 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": 0.08642659279778393,
+  "epoch": 0.11080332409972299,
   "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": 7.7212,
       "step": 35
+    },
+    {
+      "epoch": 0.0886426592797784,
+      "grad_norm": 3.4022929668426514,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.7581,
+      "step": 40
+    },
+    {
+      "epoch": 0.0886426592797784,
+      "eval_loss": 7.109482765197754,
+      "eval_runtime": 2.3967,
+      "eval_samples_per_second": 79.276,
+      "eval_steps_per_second": 39.638,
+      "step": 40
+    },
+    {
+      "epoch": 0.0997229916897507,
+      "grad_norm": 3.1520068645477295,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 7.2416,
+      "step": 45
+    },
+    {
+      "epoch": 0.11080332409972299,
+      "grad_norm": 2.7106244564056396,
+      "learning_rate": 0.0,
+      "loss": 7.1099,
+      "step": 50
+    },
+    {
+      "epoch": 0.11080332409972299,
+      "eval_loss": 7.102914810180664,
+      "eval_runtime": 2.3533,
+      "eval_samples_per_second": 80.736,
+      "eval_steps_per_second": 40.368,
+      "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": 2556783230976.0,
+  "total_flos": 3277927219200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null