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:ce4d71db0d4a285d9875beec68878094975e41018d052926b5b00f579d7945b7
+oid sha256:fafd78a8ba817e29946c3efff5b37f4dde5e2e15ea5469e4eef192b3a5905e25
 size 80792096

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a581b4ede5f48a0dc9b656644863c36de18bced218b59b319408fcf22f4f6cb
+oid sha256:e05ce5e531708ff1aa6b3f8af3e0d8dc88c8d49e1a1898b06028342d2a931ece
 size 41459700

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63f420b9e7de84bbc3c5a80fdd9facfc42c1cda1e04aef6966e66fbe6f161f1
+oid sha256:8cdf07a28c1a078875b0a906ff6d3e3202e38624eb24ec7d2f3280a07f5c40e3
 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": 0.0497131931166348,
+  "epoch": 0.06373486297004462,
   "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": 3.5493,
       "step": 35
+    },
+    {
+      "epoch": 0.05098789037603569,
+      "grad_norm": 1.5180522203445435,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.204,
+      "step": 40
+    },
+    {
+      "epoch": 0.05098789037603569,
+      "eval_loss": 3.3309152126312256,
+      "eval_runtime": 20.7667,
+      "eval_samples_per_second": 15.939,
+      "eval_steps_per_second": 7.994,
+      "step": 40
+    },
+    {
+      "epoch": 0.05736137667304015,
+      "grad_norm": 1.5108928680419922,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.1994,
+      "step": 45
+    },
+    {
+      "epoch": 0.06373486297004462,
+      "grad_norm": 1.4551308155059814,
+      "learning_rate": 0.0,
+      "loss": 3.3705,
+      "step": 50
+    },
+    {
+      "epoch": 0.06373486297004462,
+      "eval_loss": 3.3083887100219727,
+      "eval_runtime": 20.8234,
+      "eval_samples_per_second": 15.896,
+      "eval_steps_per_second": 7.972,
+      "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": 6796280579751936.0,
+  "total_flos": 8713180230451200.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null