Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e7d7a7a8daf6554e34ef9b66bb466fe187bdc0169a30786636e380f8feeb49a
+oid sha256:9d9b0420cba6c99ae77670d3fd8cfda46767ca289eb8fc9d0b52b4c1b1b7149b
 size 25192496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82db042a0b3b1dd429fe946ac01b740594b666e41698f2283bef51f6370f4c2a
+oid sha256:f819c5030faa673e626d229db9ae54990c9101bc80e737a0f34f48fb876656f2
 size 13005178

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75caa14d0693086c5957e78bfabc5e03e26e0a02e3ebab6e9c7167f2b79dbe10
+oid sha256:54000a22ed1e03e617e8ef255fb82f30282946acb9d4f185597661be658960f2
 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": 0.0021315260906991677,
+  "epoch": 0.0027327257573066255,
   "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": 8.1588,
       "step": 35
+    },
+    {
+      "epoch": 0.0021861806058453004,
+      "grad_norm": 6.613674640655518,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 7.6758,
+      "step": 40
+    },
+    {
+      "epoch": 0.0021861806058453004,
+      "eval_loss": 2.015115261077881,
+      "eval_runtime": 694.743,
+      "eval_samples_per_second": 11.089,
+      "eval_steps_per_second": 5.544,
+      "step": 40
+    },
+    {
+      "epoch": 0.002459453181575963,
+      "grad_norm": 12.226581573486328,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 8.2919,
+      "step": 45
+    },
+    {
+      "epoch": 0.0027327257573066255,
+      "grad_norm": 6.518136501312256,
+      "learning_rate": 0.0,
+      "loss": 7.7789,
+      "step": 50
+    },
+    {
+      "epoch": 0.0027327257573066255,
+      "eval_loss": 2.0047683715820312,
+      "eval_runtime": 695.4843,
+      "eval_samples_per_second": 11.077,
+      "eval_steps_per_second": 5.539,
+      "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": 2328864478986240.0,
+  "total_flos": 2985723691008000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null