Training in progress, step 350, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8184d250b7999dee69332883ea324c78ec4c7f4598ad2667207642efe3aaeca
+oid sha256:b5bcbdfc06087516d9708916d354a3173888201f08b33e1cb2b73cf8aeb1cbae
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6319531c096fbc443a5808f5c7fda0178e30925ef23e76c2b4b0ff1e5dee0da
+oid sha256:ab2c886b5878736a4a0379e3b5b673f880ba7fd9c522040e8849419c1c0ab576
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c62165be0f53737e55f3e75f021e8f584796137fe98feeca985918f86f5097e3
+oid sha256:fed445c7bf9de67fe20adad94605eaf6ed2caf6143450f9b77271543f58bcce9
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2768285b45b2a0c05f6f50bbb8c0287fca6f62a8cde6d1b1f02151ac72ee8dc
+oid sha256:f9a6944c405a002fce05f295d08ea6650e2e2ad6dbf5d6da1e9053f7bf7f5827
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5948dcd3223dd0e3f4d6f300a2e7a88ae966cce604338b85ff6032bc67f692
+oid sha256:7236ba56a19cd6992ceb8886669075220921c5f0657e2c01dfabd97116fc7832
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.018738288569643973,
+  "epoch": 0.021861336664584636,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 350,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -274,6 +274,49 @@
       "eval_samples_per_second": 16.045,
       "eval_steps_per_second": 16.045,
       "step": 300
+    },
+    {
+      "epoch": 0.019362898188632106,
+      "grad_norm": 15.8125,
+      "learning_rate": 0.03956597249065126,
+      "loss": 8.3444,
+      "step": 310
+    },
+    {
+      "epoch": 0.019987507807620236,
+      "grad_norm": 26.25,
+      "learning_rate": 0.0389139821485336,
+      "loss": 8.1302,
+      "step": 320
+    },
+    {
+      "epoch": 0.02061211742660837,
+      "grad_norm": 32.25,
+      "learning_rate": 0.03824798160583012,
+      "loss": 8.5943,
+      "step": 330
+    },
+    {
+      "epoch": 0.021236727045596503,
+      "grad_norm": 22.375,
+      "learning_rate": 0.037568641468632896,
+      "loss": 8.2872,
+      "step": 340
+    },
+    {
+      "epoch": 0.021861336664584636,
+      "grad_norm": 35.5,
+      "learning_rate": 0.03687664577487488,
+      "loss": 9.0739,
+      "step": 350
+    },
+    {
+      "epoch": 0.021861336664584636,
+      "eval_loss": 10.262110710144043,
+      "eval_runtime": 53.54,
+      "eval_samples_per_second": 15.745,
+      "eval_steps_per_second": 15.745,
+      "step": 350
     }
   ],
   "logging_steps": 10,
@@ -288,7 +331,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 6
+        "early_stopping_patience_counter": 7
       }
     },
     "TrainerControl": {
@@ -302,7 +345,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.225386491904e+16,
+  "total_flos": 1.429617573888e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null