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:ca16999ebf997a0d6861070c27dc1ce0fced68ee6066eb495ad38c4c3af3d796
+oid sha256:d0fe1054b542bac42599f05ab2a702ea850b93f713465eb2f9f0e9caf77fee1a
 size 327040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb36ce80f769c8d8a7cb616b9db51969f14e6ef743acdb2e549a28decf4b8917
+oid sha256:5bceb64a0d0ff994e4e8c3965deebd69eaf3d547ac44b8becef25f5c2d267140
 size 739258

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97c7af0c928fdcc0d5052f7ecd28b407f46c40c36dcaf7ab51bd8ba421ff3920
+oid sha256:844fbd3d467f0640ba6a8563e377765306846b3d1e3b996e57d44fe34907b25f
 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": 0.0010918788014530388,
+  "epoch": 0.0013998446172474855,
   "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": 11.9316,
       "step": 35
+    },
+    {
+      "epoch": 0.0011198756937979885,
+      "grad_norm": 0.13800644874572754,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 11.9286,
+      "step": 40
+    },
+    {
+      "epoch": 0.0011198756937979885,
+      "eval_loss": 11.928312301635742,
+      "eval_runtime": 362.9081,
+      "eval_samples_per_second": 41.443,
+      "eval_steps_per_second": 20.721,
+      "step": 40
+    },
+    {
+      "epoch": 0.001259860155522737,
+      "grad_norm": 0.1399076133966446,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 11.9251,
+      "step": 45
+    },
+    {
+      "epoch": 0.0013998446172474855,
+      "grad_norm": 0.1719651073217392,
+      "learning_rate": 0.0,
+      "loss": 11.9275,
+      "step": 50
+    },
+    {
+      "epoch": 0.0013998446172474855,
+      "eval_loss": 11.928133010864258,
+      "eval_runtime": 359.7369,
+      "eval_samples_per_second": 41.808,
+      "eval_steps_per_second": 20.904,
+      "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": 4881081434112.0,
+  "total_flos": 6257796710400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null