Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c146dcb4dbcd27192913d855125baef0205539afb3ce5f5ec9b342d434e616a
+oid sha256:3015283d753c00d3f613c3f12215a3584bb83f569bcb8a322f211176617bb171
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dbee6fbc1be17863983c6af83b751c0bce1d803910dac553da8e8cd11967554
+oid sha256:f14cf3ad8ea0358ea9e9d3aeeb05815f1887257da58e2d77178618a679a108dd
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20035373a0d585855462071b0b7debb0973bb539d5a7aede39de586e30746199
+oid sha256:65d5e64de19bd837807e080f9bec38d17c418a4373319ed137725a270fa026db
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03208084372619,
+  "epoch": 0.06416168745238,
   "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": 7.935,
       "eval_steps_per_second": 7.935,
       "step": 25
+    },
+    {
+      "epoch": 0.038497012471428,
+      "grad_norm": 3.7447290420532227,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4539,
+      "step": 30
+    },
+    {
+      "epoch": 0.044913181216666,
+      "grad_norm": 3.3202221393585205,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.4218,
+      "step": 35
+    },
+    {
+      "epoch": 0.051329349961904,
+      "grad_norm": 3.2296829223632812,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4064,
+      "step": 40
+    },
+    {
+      "epoch": 0.057745518707142,
+      "grad_norm": 2.998584270477295,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.405,
+      "step": 45
+    },
+    {
+      "epoch": 0.06416168745238,
+      "grad_norm": 3.7719151973724365,
+      "learning_rate": 0.0,
+      "loss": 1.3559,
+      "step": 50
+    },
+    {
+      "epoch": 0.06416168745238,
+      "eval_loss": 1.4145891666412354,
+      "eval_runtime": 349.8696,
+      "eval_samples_per_second": 7.92,
+      "eval_steps_per_second": 7.92,
+      "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": 9677225695641600.0,
+  "total_flos": 1.93544513912832e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null