Training in progress, step 400, checkpoint

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12cbcb4d8d1e5e3990fda1cbd9f75d6cfdf1ff56d4f653915bdb7624e8c6fdce
+oid sha256:adc647644987060ae788ca19e928c440ad55bcac6442997ef3e26e80f31130cc
 size 4995335576

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be939951feabd06b46a93a0abcfba5a4269029f30ffb7249421c644e3dba5734
+oid sha256:6222017bf3353d20065920e1530537277482aa38eba1e8fa57d14461898fbe2f
 size 1857639032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65270ff2f8bcc913fe29d5507ae214db12cbae4df19fd8d81b8711e8b93bdc82
+oid sha256:a8fba833c93e476cc06978c7d577a70193eb7633ffb7234e665bdc3ca981815f
 size 13706103974

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a6944c405a002fce05f295d08ea6650e2e2ad6dbf5d6da1e9053f7bf7f5827
+oid sha256:4b11a10749bfb1630d95eef94125f4590e8610c579d217d1f158e71ce518d72b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7236ba56a19cd6992ceb8886669075220921c5f0657e2c01dfabd97116fc7832
+oid sha256:97d77772d015237116c653131e7ea932ab54323cc0a66e7c4895f90aecb97a1a
 size 1064

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 1,
   "best_metric": 1.4945952892303467,
   "best_model_checkpoint": null,
-  "epoch": 0.021861336664584636,
+  "epoch": 0.024984384759525295,
   "eval_steps": 50,
-  "global_step": 350,
+  "global_step": 400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -317,6 +317,49 @@
       "eval_samples_per_second": 16.091,
       "eval_steps_per_second": 16.091,
       "step": 350
+    },
+    {
+      "epoch": 0.022485946283572766,
+      "grad_norm": 8384.0,
+      "learning_rate": 0.03617269130556171,
+      "loss": 13.996,
+      "step": 360
+    },
+    {
+      "epoch": 0.0231105559025609,
+      "grad_norm": 438.0,
+      "learning_rate": 0.035457486883172316,
+      "loss": 10.1482,
+      "step": 370
+    },
+    {
+      "epoch": 0.023735165521549032,
+      "grad_norm": 6464.0,
+      "learning_rate": 0.03473175265793479,
+      "loss": 9.1758,
+      "step": 380
+    },
+    {
+      "epoch": 0.024359775140537165,
+      "grad_norm": 596.0,
+      "learning_rate": 0.033996219382696063,
+      "loss": 8.7717,
+      "step": 390
+    },
+    {
+      "epoch": 0.024984384759525295,
+      "grad_norm": 44288.0,
+      "learning_rate": 0.033251627677115835,
+      "loss": 10.1332,
+      "step": 400
+    },
+    {
+      "epoch": 0.024984384759525295,
+      "eval_loss": 9.592761993408203,
+      "eval_runtime": 56.6259,
+      "eval_samples_per_second": 14.887,
+      "eval_steps_per_second": 14.887,
+      "step": 400
     }
   ],
   "logging_steps": 10,
@@ -331,7 +374,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 7
+        "early_stopping_patience_counter": 8
       }
     },
     "TrainerControl": {
@@ -345,7 +388,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.429617573888e+16,
+  "total_flos": 1.633848655872e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null