Training in progress, step 600, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5effaa531506fd6c094304a0d4fbf50e4689c0c91e34799a678ff3cc9aec82c0
+oid sha256:ad832a709ceb64a88d98817dcb75ad708bfacf1a4f40055fae54bcea8244ed97
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c05b3e597eb203363767c34935766da9cb2fb043cc0009221d70ea49f93ee318
+oid sha256:6af8410d351904bb32739cb663c37b7698ec1f70ff79e91a4a8d02f23e66cc06
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:043188c965bea5abf083a00c8e41c7840c397481f18153d4c25fcaffb631a510
+oid sha256:d5332c2221b81d3206827e2f3bda349a3e32e62b283b472331914261c4f8bf7d
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0b8a6e3878f9402461193b241d8f1ee8546c6ad03f43e5b9dab8f4fc8c4d065
+oid sha256:ad578a43d11126d2531a957d968233fceac13bb258b4a43a2e2c3ad855ce9084
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3372cb7b685e225287edc953534a919d443ed17283851ec6045c9673db22615
+oid sha256:a471a6ec9e3c58f40e439496906fe4d5cf4f1a004883d461acf006d0c949a038
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.034353529044347283,
+  "epoch": 0.037476577139287946,
   "eval_steps": 50,
-  "global_step": 550,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -489,6 +489,49 @@
       "eval_samples_per_second": 15.692,
       "eval_steps_per_second": 15.692,
       "step": 550
+    },
+    {
+      "epoch": 0.03497813866333541,
+      "grad_norm": 1072.0,
+      "learning_rate": 0.020736945184184407,
+      "loss": 9.5244,
+      "step": 560
+    },
+    {
+      "epoch": 0.03560274828232355,
+      "grad_norm": 2352.0,
+      "learning_rate": 0.019957510427206296,
+      "loss": 8.832,
+      "step": 570
+    },
+    {
+      "epoch": 0.03622735790131168,
+      "grad_norm": 540.0,
+      "learning_rate": 0.01918315302979444,
+      "loss": 10.0747,
+      "step": 580
+    },
+    {
+      "epoch": 0.03685196752029981,
+      "grad_norm": 600.0,
+      "learning_rate": 0.018414652704208584,
+      "loss": 8.9236,
+      "step": 590
+    },
+    {
+      "epoch": 0.037476577139287946,
+      "grad_norm": 644.0,
+      "learning_rate": 0.017652783265133608,
+      "loss": 8.524,
+      "step": 600
+    },
+    {
+      "epoch": 0.037476577139287946,
+      "eval_loss": 8.281222343444824,
+      "eval_runtime": 52.4549,
+      "eval_samples_per_second": 16.071,
+      "eval_steps_per_second": 16.071,
+      "step": 600
     }
   ],
   "logging_steps": 10,
@@ -503,7 +546,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 11
+        "early_stopping_patience_counter": 12
       }
     },
     "TrainerControl": {
@@ -517,7 +560,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.246541901824e+16,
+  "total_flos": 2.450772983808e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null