Training in progress, step 5376, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b30a18281b22182316747cceddd8d6c37353221bc3f8fb5d02c882c5629422d
+oid sha256:ff920e5ccc2d2a405fd728410318b5d77a58a46344ae8542bb3adc83fa0b5aa5
 size 903834408

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb114aa5f0332140b4eec1de73af442aa382ec1878556383d86000d2acf516d8
+oid sha256:dc711544bbc463382370e087fb56a499145af6b3d8d135d3d2ad1e1612e329ff
 size 1807824186

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:56b9ce523794195d6fe6eaf298487c89289b615fed50c7eecdaaf4b487304fb9
+oid sha256:efc2f5216a7387c189c9349463d3b40a111802d247e9267a1c2d9b8f7b01f222
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9637751fdfaaf8a45d6222ffb7baf0bbdacedfccacc03a39d139d6c493b9ec1d
+oid sha256:6a2cc71334cc40bd202de7bb17936da773f888ad3b66367935ef5b0e0f47c791
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.3465050505050505,
+  "epoch": 0.3475393939393939,
   "eval_steps": 16,
-  "global_step": 5360,
+  "global_step": 5376,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -40542,6 +40542,127 @@
       "eval_samples_per_second": 11.555,
       "eval_steps_per_second": 1.444,
       "step": 5360
+    },
+    {
+      "epoch": 0.34656969696969697,
+      "grad_norm": 0.0666361004114151,
+      "learning_rate": 0.00019445821927260975,
+      "loss": 0.0985,
+      "step": 5361
+    },
+    {
+      "epoch": 0.34663434343434346,
+      "grad_norm": 0.0619664341211319,
+      "learning_rate": 0.0001944559741044043,
+      "loss": 0.0795,
+      "step": 5362
+    },
+    {
+      "epoch": 0.3466989898989899,
+      "grad_norm": 0.07481850683689117,
+      "learning_rate": 0.0001944537284944595,
+      "loss": 0.0889,
+      "step": 5363
+    },
+    {
+      "epoch": 0.3467636363636364,
+      "grad_norm": 0.10630080848932266,
+      "learning_rate": 0.00019445148244278586,
+      "loss": 0.1363,
+      "step": 5364
+    },
+    {
+      "epoch": 0.3468282828282828,
+      "grad_norm": 0.06847912818193436,
+      "learning_rate": 0.00019444923594939386,
+      "loss": 0.0961,
+      "step": 5365
+    },
+    {
+      "epoch": 0.3468929292929293,
+      "grad_norm": 0.06266526877880096,
+      "learning_rate": 0.00019444698901429397,
+      "loss": 0.0847,
+      "step": 5366
+    },
+    {
+      "epoch": 0.34695757575757574,
+      "grad_norm": 0.058274924755096436,
+      "learning_rate": 0.00019444474163749677,
+      "loss": 0.0782,
+      "step": 5367
+    },
+    {
+      "epoch": 0.34702222222222223,
+      "grad_norm": 0.06570993363857269,
+      "learning_rate": 0.00019444249381901272,
+      "loss": 0.093,
+      "step": 5368
+    },
+    {
+      "epoch": 0.34708686868686867,
+      "grad_norm": 0.06814686208963394,
+      "learning_rate": 0.00019444024555885237,
+      "loss": 0.0896,
+      "step": 5369
+    },
+    {
+      "epoch": 0.34715151515151516,
+      "grad_norm": 0.06851497292518616,
+      "learning_rate": 0.0001944379968570262,
+      "loss": 0.1058,
+      "step": 5370
+    },
+    {
+      "epoch": 0.3472161616161616,
+      "grad_norm": 0.058960504829883575,
+      "learning_rate": 0.00019443574771354474,
+      "loss": 0.0793,
+      "step": 5371
+    },
+    {
+      "epoch": 0.3472808080808081,
+      "grad_norm": 0.06058274954557419,
+      "learning_rate": 0.0001944334981284185,
+      "loss": 0.0858,
+      "step": 5372
+    },
+    {
+      "epoch": 0.34734545454545457,
+      "grad_norm": 0.06411627680063248,
+      "learning_rate": 0.00019443124810165802,
+      "loss": 0.0831,
+      "step": 5373
+    },
+    {
+      "epoch": 0.347410101010101,
+      "grad_norm": 0.06605079025030136,
+      "learning_rate": 0.00019442899763327378,
+      "loss": 0.0885,
+      "step": 5374
+    },
+    {
+      "epoch": 0.3474747474747475,
+      "grad_norm": 0.058634303510189056,
+      "learning_rate": 0.00019442674672327638,
+      "loss": 0.0788,
+      "step": 5375
+    },
+    {
+      "epoch": 0.3475393939393939,
+      "grad_norm": 0.06674228608608246,
+      "learning_rate": 0.00019442449537167628,
+      "loss": 0.1054,
+      "step": 5376
+    },
+    {
+      "epoch": 0.3475393939393939,
+      "eval_bleu": 15.692248886076214,
+      "eval_loss": 0.09231525659561157,
+      "eval_runtime": 2.8228,
+      "eval_samples_per_second": 11.336,
+      "eval_steps_per_second": 1.417,
+      "step": 5376
     }
   ],
   "logging_steps": 1,
@@ -40561,7 +40682,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.044484573888512e+17,
+  "total_flos": 1.0476024382881792e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null