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 sha256:61114c6a92e58ce464f00de9c099e8f03dc4230c177b928f5956c816d7725990
+oid sha256:12cbcb4d8d1e5e3990fda1cbd9f75d6cfdf1ff56d4f653915bdb7624e8c6fdce
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fbbf4da0f14a88e52ba3a2a4073b4aaa1c19709f107ca0ea0f7d394e7b8943e5
+oid sha256:be939951feabd06b46a93a0abcfba5a4269029f30ffb7249421c644e3dba5734
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42dcce8c9a2d0c024270cf90f873168e73cdade4af51b5e3849a0fd68c66911
+oid sha256:65270ff2f8bcc913fe29d5507ae214db12cbae4df19fd8d81b8711e8b93bdc82
 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": 14.97,
       "eval_steps_per_second": 14.97,
       "step": 300
+    },
+    {
+      "epoch": 0.019362898188632106,
+      "grad_norm": 42.75,
+      "learning_rate": 0.03956597249065126,
+      "loss": 9.9067,
+      "step": 310
+    },
+    {
+      "epoch": 0.019987507807620236,
+      "grad_norm": 200.0,
+      "learning_rate": 0.0389139821485336,
+      "loss": 7.9326,
+      "step": 320
+    },
+    {
+      "epoch": 0.02061211742660837,
+      "grad_norm": 458.0,
+      "learning_rate": 0.03824798160583012,
+      "loss": 12.0065,
+      "step": 330
+    },
+    {
+      "epoch": 0.021236727045596503,
+      "grad_norm": 684.0,
+      "learning_rate": 0.037568641468632896,
+      "loss": 15.9906,
+      "step": 340
+    },
+    {
+      "epoch": 0.021861336664584636,
+      "grad_norm": 2160.0,
+      "learning_rate": 0.03687664577487488,
+      "loss": 15.0601,
+      "step": 350
+    },
+    {
+      "epoch": 0.021861336664584636,
+      "eval_loss": 12.592202186584473,
+      "eval_runtime": 52.3897,
+      "eval_samples_per_second": 16.091,
+      "eval_steps_per_second": 16.091,
+      "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