Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfba5eb6d717f6810a318bb07685c82a93d4e4a9ff4b16f65b812f55595ea15
+oid sha256:a89bded92dc9d04e321f07648da153cb0bf4eb047790c84941726b4e5caa3a6e
 size 604317736

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c3cbaa45904f07c54c39c9b38a89675615335f6270a56dc39cf9be79ef58a76
+oid sha256:63cc8be02a6d51b2f1bb7b75c695337f5d74c5a3d77911d3c55daa3185685ffd
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d04c72ba41fa997c16944b8df1cb883fd987f479bf7cf1aaafc8d595f88172c
+oid sha256:0179f6364b3a13bc8e52bd0d3c375aad43463a96547d9d2021d336ef6f53a9a0
 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": 0.0008318669012957927,
+  "epoch": 0.0010664960273022983,
   "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": 0.4426,
       "step": 35
+    },
+    {
+      "epoch": 0.0008531968218418387,
+      "grad_norm": 0.4009244740009308,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4028,
+      "step": 40
+    },
+    {
+      "epoch": 0.0008531968218418387,
+      "eval_loss": 0.42813223600387573,
+      "eval_runtime": 1223.674,
+      "eval_samples_per_second": 16.132,
+      "eval_steps_per_second": 8.066,
+      "step": 40
+    },
+    {
+      "epoch": 0.0009598464245720685,
+      "grad_norm": 0.39128080010414124,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4453,
+      "step": 45
+    },
+    {
+      "epoch": 0.0010664960273022983,
+      "grad_norm": 0.39831650257110596,
+      "learning_rate": 0.0,
+      "loss": 0.4352,
+      "step": 50
+    },
+    {
+      "epoch": 0.0010664960273022983,
+      "eval_loss": 0.42544740438461304,
+      "eval_runtime": 1223.1167,
+      "eval_samples_per_second": 16.139,
+      "eval_steps_per_second": 8.07,
+      "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": 6799965045129216.0,
+  "total_flos": 8713727662620672.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null