Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93079a914a552d1da0d97db6a3d97778ec02090573f57cca45c162dc6ab59cb4
+oid sha256:ad3982c3f922c3ac1096f6391bdd48ad03398311ec1fe07cd9206484ed13b9a4
 size 399632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0da1e1dc46b967c2bcd7844dff8a988454a440342fe4d2a2fc2ea03919b67ae
+oid sha256:ce987260cf8f4885e5bb308d766c4e63fe88d78ef85af6d5fa58e80f01064192
 size 531130

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2e7cc7fd1ad3a5b4df9187d5af175a5d99ef934d2b94a7b779fe5e296e29170
+oid sha256:f81d347aec1ec4099d4e5d6e81e0d42dc863a348af162789cc585e814e29b32c
 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": 0.0677671589921807,
+  "epoch": 0.08688097306689835,
   "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": 25.3217,
       "step": 35
+    },
+    {
+      "epoch": 0.06950477845351868,
+      "grad_norm": 3242.72119140625,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 25.3607,
+      "step": 40
+    },
+    {
+      "epoch": 0.06950477845351868,
+      "eval_loss": 6.420129776000977,
+      "eval_runtime": 1.6872,
+      "eval_samples_per_second": 144.022,
+      "eval_steps_per_second": 72.307,
+      "step": 40
+    },
+    {
+      "epoch": 0.07819287576020852,
+      "grad_norm": 3691.49462890625,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 25.7192,
+      "step": 45
+    },
+    {
+      "epoch": 0.08688097306689835,
+      "grad_norm": 4117.0908203125,
+      "learning_rate": 0.0,
+      "loss": 25.7918,
+      "step": 50
+    },
+    {
+      "epoch": 0.08688097306689835,
+      "eval_loss": 6.41416072845459,
+      "eval_runtime": 1.7003,
+      "eval_samples_per_second": 142.919,
+      "eval_steps_per_second": 71.753,
+      "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": 8782935490560.0,
+  "total_flos": 11014275858432.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null