Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24f277894086c4abe781e72f14c16384b0cdd1f9eab2c4ba7e9e8f244f25caeb
+oid sha256:7350810184c26c3ff202a0d3f1fefb6e11ab5a22805095547e80a20351c2f484
 size 80013120

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9f03293fd35654d39b714a8dc71a10c3f48683c1df48f438f467634c77c0759
+oid sha256:3a72ae2529e5c712457b2466ae8a0635e3fcd56b7a32beaa48afa729dc5c8746
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fcac41dbd9142df5390346c9aeb20da7424d647bb3d8dc6eede3f489ba85d01
+oid sha256:962cea57a3c1e89f2fd0c22e1029508e8a1b3408e2754bc6141dcc71b84d7289
 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": 0.0022946238140766346,
+  "epoch": 0.002941825402662352,
   "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": 0.8626,
       "step": 35
+    },
+    {
+      "epoch": 0.0023534603221298817,
+      "grad_norm": 0.4122065603733063,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.9215,
+      "step": 40
+    },
+    {
+      "epoch": 0.0023534603221298817,
+      "eval_loss": 0.9009389877319336,
+      "eval_runtime": 655.9569,
+      "eval_samples_per_second": 10.911,
+      "eval_steps_per_second": 5.456,
+      "step": 40
+    },
+    {
+      "epoch": 0.0026476428623961167,
+      "grad_norm": 0.370616614818573,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8667,
+      "step": 45
+    },
+    {
+      "epoch": 0.002941825402662352,
+      "grad_norm": 0.3705947995185852,
+      "learning_rate": 0.0,
+      "loss": 0.8787,
+      "step": 50
+    },
+    {
+      "epoch": 0.002941825402662352,
+      "eval_loss": 0.8991426825523376,
+      "eval_runtime": 657.0507,
+      "eval_samples_per_second": 10.893,
+      "eval_steps_per_second": 5.447,
+      "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": 1.047517194092544e+16,
+  "total_flos": 1.3391788442124288e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null