Training in progress, step 1000, checkpoint

last-checkpoint/model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4725f7683f2b8dc2c37be3613593f25b041ac5cfee2a86d851142562e03f31e2
+oid sha256:06d13d73b349e73c3ad309343c997321f1de4a6b22c8a70a801cd8f62c755053
 size 4995335576

last-checkpoint/model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe054c5b7dbc4504491e8399e4c3dd2f601a8021e18628ca1a900249c2072e44
+oid sha256:6be83e77d182a6edb613bbe5055e77f0fe1ed630c996228e078d57f9ca78dcea
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4483c56b3458c6f88b40364283839fd954d028d7abdcc22bb698f9239fe76b79
+oid sha256:51e78de1db2a14bce4185840a9dceb67098b6b349ac4a43a01da0d38a059fef0
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:645b71843375baf4cc10bc75a2f0f04e91b8e3f8e8929f518a87022898b3bc20
+oid sha256:f7286dee9a5da5b96232ccd668e3561a460616ec53ea433806da321343af8636
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a288ddd8ddfd7759ce5e03ca2b9f4240d1938c54de141af3734f632c4e8a713b
+oid sha256:bb16655f4370357d3b852c8ea67d9f0fc3c635151884c4092645d050bc5ecdd4
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.05933791380387258,
+  "epoch": 0.06246096189881324,
   "eval_steps": 50,
-  "global_step": 950,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -833,6 +833,49 @@
       "eval_samples_per_second": 15.989,
       "eval_steps_per_second": 15.989,
       "step": 950
+    },
+    {
+      "epoch": 0.059962523422860715,
+      "grad_norm": 40.5,
+      "learning_rate": 0.00021129750238107204,
+      "loss": 6.8338,
+      "step": 960
+    },
+    {
+      "epoch": 0.060587133041848845,
+      "grad_norm": 268.0,
+      "learning_rate": 0.00012086832304096795,
+      "loss": 7.0505,
+      "step": 970
+    },
+    {
+      "epoch": 0.061211742660836975,
+      "grad_norm": 76.5,
+      "learning_rate": 5.54903203858731e-05,
+      "loss": 7.9223,
+      "step": 980
+    },
+    {
+      "epoch": 0.06183635227982511,
+      "grad_norm": 108.0,
+      "learning_rate": 1.5229324522605948e-05,
+      "loss": 7.8772,
+      "step": 990
+    },
+    {
+      "epoch": 0.06246096189881324,
+      "grad_norm": 516.0,
+      "learning_rate": 1.2587486122317416e-07,
+      "loss": 7.4005,
+      "step": 1000
+    },
+    {
+      "epoch": 0.06246096189881324,
+      "eval_loss": 7.635000705718994,
+      "eval_runtime": 52.4898,
+      "eval_samples_per_second": 16.06,
+      "eval_steps_per_second": 16.06,
+      "step": 1000
     }
   ],
   "logging_steps": 10,
@@ -847,7 +890,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 19
+        "early_stopping_patience_counter": 20
       }
     },
     "TrainerControl": {
@@ -856,12 +899,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.880390557696e+16,
+  "total_flos": 4.08462163968e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null