Training in progress, step 750, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8dd9e129246dcbcb02aa668d99467d2eb7fc0c79fe6b5f3e0fd04b2fecb753e
+oid sha256:d425e498e6ea5e98cfd459b2b2df78bf5605bd551cc2b2f19d2ed0d145ae61dc
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bf7d3dc3e85ba0080213a7282bb8dd0adc5dd21f3b2d56df884de89efa389ab
+oid sha256:e76be76af91f29063bfcebef649f23fc116d070cd4e8c608c922d67c1dcaa32d
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6c0e3d3c6a08247a17a374ba94859dad3af4488cdbf7337e335e08f647f522b
+oid sha256:ad29f8cf4ebaa4c54604266e6a8a1d5d0769f2cc214c8d151ac79b0bbc731b0a
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cfe3540f24c66f9bc38a546448a9e5d9989705fafc8d4b37aa5dafd0c7460f2
+oid sha256:f83fe17529e572dff2734bb21512b28dd7cf5d20ef0e84688f5068ffbf24e765
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d00596a2a77c6d3c29d66ae8e723565a357207bb2e5d1c235f7357b00a4b32b7
+oid sha256:1144fac8f856c755e44dc152ccdb65401daaed44242a933fe7be5d965bad4096
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.04372267332916927,
+  "epoch": 0.046845721424109935,
   "eval_steps": 50,
-  "global_step": 700,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -618,6 +618,49 @@
       "eval_samples_per_second": 12.55,
       "eval_steps_per_second": 12.55,
       "step": 700
+    },
+    {
+      "epoch": 0.0443472829481574,
+      "grad_norm": 1304.0,
+      "learning_rate": 0.009922964238362761,
+      "loss": 8.057,
+      "step": 710
+    },
+    {
+      "epoch": 0.04497189256714553,
+      "grad_norm": 187.0,
+      "learning_rate": 0.009297836732454564,
+      "loss": 7.3939,
+      "step": 720
+    },
+    {
+      "epoch": 0.04559650218613367,
+      "grad_norm": 744.0,
+      "learning_rate": 0.0086885199739414,
+      "loss": 7.4594,
+      "step": 730
+    },
+    {
+      "epoch": 0.0462211118051218,
+      "grad_norm": 35.0,
+      "learning_rate": 0.00809562749314952,
+      "loss": 7.2934,
+      "step": 740
+    },
+    {
+      "epoch": 0.046845721424109935,
+      "grad_norm": 65024.0,
+      "learning_rate": 0.0075197562825497334,
+      "loss": 7.937,
+      "step": 750
+    },
+    {
+      "epoch": 0.046845721424109935,
+      "eval_loss": 8.636336326599121,
+      "eval_runtime": 52.4038,
+      "eval_samples_per_second": 16.087,
+      "eval_steps_per_second": 16.087,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -632,7 +675,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 14
+        "early_stopping_patience_counter": 15
       }
     },
     "TrainerControl": {
@@ -646,7 +689,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.859235147776e+16,
+  "total_flos": 3.06346622976e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null