Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef66fa0edaabe6b133ed7bbdac01ff37ffd9694167d0b37e9b187db31434cff
+oid sha256:4065ad4840c2f4297bbf405464d9a61b34fb088f0a621f46c280f24c72dd4829
 size 14696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:603df5dc029fe4e4d1c13cded338af81bc6f14a58ec3db0ca435d476aa3f349e
+oid sha256:d66b066f9fb8c5fdccd09fee3eb6d8b51cdc7501ed42f53e658d50ba15ba943e
 size 39398

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48d41985628b63b1f03308534e42f5f4fade1dc9f1a7ca147144af3b829d1153
+oid sha256:52c1e8dd4ba9ace9e6fcca937683862f29cfd6bf4fb3642d8d44c9c9a4359dc1
 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": 0.011917494270435447,
+  "epoch": 0.015278838808250574,
   "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": 11.9352,
       "step": 35
+    },
+    {
+      "epoch": 0.012223071046600458,
+      "grad_norm": 0.018195880576968193,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9315,
+      "step": 40
+    },
+    {
+      "epoch": 0.012223071046600458,
+      "eval_loss": 11.932579040527344,
+      "eval_runtime": 12.7987,
+      "eval_samples_per_second": 107.667,
+      "eval_steps_per_second": 53.833,
+      "step": 40
+    },
+    {
+      "epoch": 0.013750954927425516,
+      "grad_norm": 0.03546914830803871,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.934,
+      "step": 45
+    },
+    {
+      "epoch": 0.015278838808250574,
+      "grad_norm": 0.013694709166884422,
+      "learning_rate": 0.0,
+      "loss": 11.9332,
+      "step": 50
+    },
+    {
+      "epoch": 0.015278838808250574,
+      "eval_loss": 11.932577133178711,
+      "eval_runtime": 12.6629,
+      "eval_samples_per_second": 108.822,
+      "eval_steps_per_second": 54.411,
+      "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": 4637835264.0,
+  "total_flos": 6026231808.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null