Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e30ab7e04461699fbed29b5aed89c6cd4c5e95e23df8ead9cb8bc83097317b0
+oid sha256:e4ebabee034b2d74570680b62008abdceeec0a1e9db2d84bc338d285bed4a7cb
 size 83945296

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd1a20bf64256624cf44f3dcd3c6c61054c5c87753771fdbdc9aace73cf2c7ae
+oid sha256:d2a7a7b5e97af7b1b2648e6cbba4778674ea473a8d2dda528e94c13d72e2e435
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab423bf67e2c5e85eb32f5af0f6128c31e26227abaf51e1b653a551268fea34f
+oid sha256:ddbe3ac20620b9f6414488482ee62d821b51a843109ce3326131d41ac1f469f9
 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": 0.029345372460496615,
+  "epoch": 0.03762227238525207,
   "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": 2.8201,
       "step": 35
+    },
+    {
+      "epoch": 0.030097817908201655,
+      "grad_norm": 0.9662715792655945,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.6426,
+      "step": 40
+    },
+    {
+      "epoch": 0.030097817908201655,
+      "eval_loss": 2.9788880348205566,
+      "eval_runtime": 42.6832,
+      "eval_samples_per_second": 13.12,
+      "eval_steps_per_second": 6.56,
+      "step": 40
+    },
+    {
+      "epoch": 0.033860045146726865,
+      "grad_norm": 1.2202461957931519,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.9604,
+      "step": 45
+    },
+    {
+      "epoch": 0.03762227238525207,
+      "grad_norm": 1.2100179195404053,
+      "learning_rate": 0.0,
+      "loss": 2.7795,
+      "step": 50
+    },
+    {
+      "epoch": 0.03762227238525207,
+      "eval_loss": 2.973825693130493,
+      "eval_runtime": 42.5859,
+      "eval_samples_per_second": 13.15,
+      "eval_steps_per_second": 6.575,
+      "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": 7953126267027456.0,
+  "total_flos": 1.017260336480256e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null