Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49bb3232a31cd1c41758fc01fad17dbc2d759c2274dabb109c7c26fbd82f1727
+oid sha256:9677a86f4bf1962c1a66d8f042ba3439bd9b986b558d8951b36f6309bebf83c7
 size 50899792

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:886954a974a16bef13474deae6bae46e89d8f319160c3ce301a7a144a8738228
+oid sha256:3483a0d4b4307ef8115daa2f67cf2d12f1d601df69098568645a505bfbb0ebc1
 size 26231300

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46a7d77f7c0c53177105db9c32667c7a911c1f05b401fbd9c12e4068544cba16
+oid sha256:079c57ab58cc0d7acfaf7a2a6075235723faa08c9b7d0205fed0c4ab7c433466
 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": 0.024864520242269685,
+  "epoch": 0.031877590054191905,
   "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": 0.7404,
       "step": 35
+    },
+    {
+      "epoch": 0.025502072043353523,
+      "grad_norm": 2.994288682937622,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6233,
+      "step": 40
+    },
+    {
+      "epoch": 0.025502072043353523,
+      "eval_loss": 0.5640355348587036,
+      "eval_runtime": 28.5895,
+      "eval_samples_per_second": 23.12,
+      "eval_steps_per_second": 11.578,
+      "step": 40
+    },
+    {
+      "epoch": 0.028689831048772714,
+      "grad_norm": 2.964512348175049,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.505,
+      "step": 45
+    },
+    {
+      "epoch": 0.031877590054191905,
+      "grad_norm": 2.4485843181610107,
+      "learning_rate": 0.0,
+      "loss": 0.6592,
+      "step": 50
+    },
+    {
+      "epoch": 0.031877590054191905,
+      "eval_loss": 0.5352591872215271,
+      "eval_runtime": 28.3212,
+      "eval_samples_per_second": 23.339,
+      "eval_steps_per_second": 11.687,
+      "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": 3895231158681600.0,
+  "total_flos": 4858788340039680.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null