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:b378e29efc042d5ddaaef7909dab405fc409b7cd819cfbc9294e4a54c8bc7513
+oid sha256:53b7798714601573c3957641a63bbef95504956022ff0f556283aa471fde4c58
 size 247944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:404efc730053c821740b4a5229b943cf872c74c1a947a6521d1af449d0077436
+oid sha256:d484ec5d9e282a63bbaf56a21f93d40ce8175a3630f49f2f6b6df672714f3aed
 size 263088

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7f7262fbb517a61859b768df28934f5dbab8ec521b3d9a7b305b2dfcdcb1fb
+oid sha256:6c222ad0cf61ebdc285135fab3352b1133b31d7bc7f1b59f0d93017fc1c8df82
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6676fe28230ae15b45fb334c871c6fdf1a7984a935952b9f8650896c37a8c106
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0001366321807042569,
+  "epoch": 0.0002732643614085138,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,49 @@
       "eval_samples_per_second": 35.679,
       "eval_steps_per_second": 35.679,
       "step": 25
+    },
+    {
+      "epoch": 0.0001639586168451083,
+      "grad_norm": 2.305196762084961,
+      "learning_rate": 5e-05,
+      "loss": 11.0493,
+      "step": 30
+    },
+    {
+      "epoch": 0.00019128505298595966,
+      "grad_norm": 2.923957586288452,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 11.0813,
+      "step": 35
+    },
+    {
+      "epoch": 0.00021861148912681106,
+      "grad_norm": 3.5035717487335205,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 10.901,
+      "step": 40
+    },
+    {
+      "epoch": 0.00024593792526766246,
+      "grad_norm": 3.045618772506714,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 10.987,
+      "step": 45
+    },
+    {
+      "epoch": 0.0002732643614085138,
+      "grad_norm": 2.9671630859375,
+      "learning_rate": 0.0,
+      "loss": 10.9988,
+      "step": 50
+    },
+    {
+      "epoch": 0.0002732643614085138,
+      "eval_loss": 11.035735130310059,
+      "eval_runtime": 569.5957,
+      "eval_samples_per_second": 35.694,
+      "eval_steps_per_second": 35.694,
+      "step": 50
     }
   ],
   "logging_steps": 5,
@@ -72,12 +115,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 129997209600.0,
+  "total_flos": 259994419200.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null