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:cdfd1349872b4f2a5dbdacb089876a77cee0c916b0724bfa0b0cc44204f6f8bf
+oid sha256:e7259392b921a17ec7429ddcedaf3dffcdc4e6f356eab5e08054d5c7fe276783
 size 16794864

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef95acde7d09e83a0a3a0e96a3b672edb58396a2ba24f551243e12c6ca0dc8e3
+oid sha256:52fe677605fb1d0a06008006c73c92d411c1d61efa3c617e8ea457d2e3dac576
 size 8671162

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b706875855f2be5f34e8de6609fc6e1b16fd875f08c9910f48619db8c936bf46
+oid sha256:4f5f35f3b805e4f2a85e81d5ad7d6c8a5805dacef41c435f53728b6588cd6657
 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": 0.001299772539805534,
+  "epoch": 0.0016663750510327359,
   "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": 8.5684,
       "step": 35
+    },
+    {
+      "epoch": 0.0013331000408261888,
+      "grad_norm": 6.782193183898926,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 8.7587,
+      "step": 40
+    },
+    {
+      "epoch": 0.0013331000408261888,
+      "eval_loss": 2.2343928813934326,
+      "eval_runtime": 187.8024,
+      "eval_samples_per_second": 67.273,
+      "eval_steps_per_second": 33.636,
+      "step": 40
+    },
+    {
+      "epoch": 0.0014997375459294623,
+      "grad_norm": 9.646410942077637,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.5253,
+      "step": 45
+    },
+    {
+      "epoch": 0.0016663750510327359,
+      "grad_norm": 8.402804374694824,
+      "learning_rate": 0.0,
+      "loss": 8.8223,
+      "step": 50
+    },
+    {
+      "epoch": 0.0016663750510327359,
+      "eval_loss": 2.22995924949646,
+      "eval_runtime": 188.1478,
+      "eval_samples_per_second": 67.149,
+      "eval_steps_per_second": 33.575,
+      "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": 875032913903616.0,
+  "total_flos": 1121837069107200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null