Training in progress, step 1000, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b4e881e510e1359daaa5a0a6a1ec4d6e4e00c53ed58158e593a28a015b3a55d
+oid sha256:872dafd4f7a04e803d7c539219fc84f71fe6a69c1babbc798b79455dc4e1cc48
 size 1583480280

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d4b02def5ec83ca784589121daf22c2c0116c6536bbf66b50f8878f10fece4
+oid sha256:d9ad0354ec70f7cee4872b10ddc2b723a017a3711c3e9c5a25eba5b7823716aa
 size 3166958572

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f45cb09598ea281c4e6aac3c96e3028c200ee8a6a0ca5be3350a9bea5cb821a
+oid sha256:7ef1ee026e99fb5f8e5a5e72bb4657b4cedd8651ee5b752f5c314d3a89fd9ad7
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82c7fe1f31968d4a08ce97e5b567d82fa63c9eed763f8746018c0f588eae06e4
+oid sha256:14ae2a2128444abab378aa06c09a61a84665f758fcc19fc46f5789b0bc1b5665
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3119686f5b86680b00f771de05ac750cb0f59d3c7c26fcf6c714283782911200
+oid sha256:68aec417c91400a5fbe9c98d7447dabd74ed3b0812272a5f21d640985e919bad
 size 1465

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 3000,
-  "best_metric": 1.5201951265335083,
-  "best_model_checkpoint": "hieptt/vietnamese-correction-finetuning/checkpoint-3000",
-  "epoch": 0.08058667096462245,
+  "best_global_step": 1000,
+  "best_metric": 1.550229787826538,
+  "best_model_checkpoint": "hieptt/vietnamese-correction-finetuning/checkpoint-1000",
+  "epoch": 0.02686222365487415,
   "eval_steps": 1000,
-  "global_step": 3000,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -82,169 +82,11 @@
     {
       "epoch": 0.02686222365487415,
       "eval_loss": 1.550229787826538,
-      "eval_runtime": 3482.8166,
+      "eval_runtime": 3677.195,
       "eval_sacrebleu": 96.21455916515954,
-      "eval_samples_per_second": 76.009,
-      "eval_steps_per_second": 0.594,
+      "eval_samples_per_second": 71.991,
+      "eval_steps_per_second": 0.563,
       "step": 1000
-    },
-    {
-      "epoch": 0.029548446020361566,
-      "grad_norm": 0.43504711985588074,
-      "learning_rate": 4.999949639906304e-05,
-      "loss": 1.5642,
-      "step": 1100
-    },
-    {
-      "epoch": 0.03223466838584898,
-      "grad_norm": 0.5235740542411804,
-      "learning_rate": 4.999796521812822e-05,
-      "loss": 1.5535,
-      "step": 1200
-    },
-    {
-      "epoch": 0.0349208907513364,
-      "grad_norm": 0.40589195489883423,
-      "learning_rate": 4.999540646875361e-05,
-      "loss": 1.5474,
-      "step": 1300
-    },
-    {
-      "epoch": 0.03760711311682381,
-      "grad_norm": 0.47619858384132385,
-      "learning_rate": 4.9991820256119385e-05,
-      "loss": 1.5467,
-      "step": 1400
-    },
-    {
-      "epoch": 0.040293335482311225,
-      "grad_norm": 0.5160552263259888,
-      "learning_rate": 4.9987206727640703e-05,
-      "loss": 1.5404,
-      "step": 1500
-    },
-    {
-      "epoch": 0.04297955784779864,
-      "grad_norm": 0.7639428973197937,
-      "learning_rate": 4.998156607296163e-05,
-      "loss": 1.5391,
-      "step": 1600
-    },
-    {
-      "epoch": 0.04566578021328606,
-      "grad_norm": Infinity,
-      "learning_rate": 4.997489852394741e-05,
-      "loss": 1.5411,
-      "step": 1700
-    },
-    {
-      "epoch": 0.04835200257877347,
-      "grad_norm": 11.356963157653809,
-      "learning_rate": 4.996720435467485e-05,
-      "loss": 3.6358,
-      "step": 1800
-    },
-    {
-      "epoch": 0.051038224944260885,
-      "grad_norm": 0.5683807730674744,
-      "learning_rate": 4.995848388142112e-05,
-      "loss": 5.6818,
-      "step": 1900
-    },
-    {
-      "epoch": 0.0537244473097483,
-      "grad_norm": 0.47999536991119385,
-      "learning_rate": 4.994873746265073e-05,
-      "loss": 1.8588,
-      "step": 2000
-    },
-    {
-      "epoch": 0.0537244473097483,
-      "eval_loss": 1.5401405096054077,
-      "eval_runtime": 3744.0666,
-      "eval_sacrebleu": 96.05509046827605,
-      "eval_samples_per_second": 70.705,
-      "eval_steps_per_second": 0.553,
-      "step": 2000
-    },
-    {
-      "epoch": 0.05641066967523572,
-      "grad_norm": 0.4521150290966034,
-      "learning_rate": 4.993796549900076e-05,
-      "loss": 1.5427,
-      "step": 2100
-    },
-    {
-      "epoch": 0.05909689204072313,
-      "grad_norm": 0.4296003580093384,
-      "learning_rate": 4.992616843326446e-05,
-      "loss": 1.5634,
-      "step": 2200
-    },
-    {
-      "epoch": 0.061783114406210544,
-      "grad_norm": 0.6067550182342529,
-      "learning_rate": 4.991334675037299e-05,
-      "loss": 1.534,
-      "step": 2300
-    },
-    {
-      "epoch": 0.06446933677169796,
-      "grad_norm": 0.5774173140525818,
-      "learning_rate": 4.989950097737552e-05,
-      "loss": 1.542,
-      "step": 2400
-    },
-    {
-      "epoch": 0.06715555913718538,
-      "grad_norm": 0.40837734937667847,
-      "learning_rate": 4.988463168341755e-05,
-      "loss": 1.5252,
-      "step": 2500
-    },
-    {
-      "epoch": 0.0698417815026728,
-      "grad_norm": 0.5584208965301514,
-      "learning_rate": 4.986873947971751e-05,
-      "loss": 1.5311,
-      "step": 2600
-    },
-    {
-      "epoch": 0.0725280038681602,
-      "grad_norm": 0.430813193321228,
-      "learning_rate": 4.9851825019541644e-05,
-      "loss": 1.5247,
-      "step": 2700
-    },
-    {
-      "epoch": 0.07521422623364762,
-      "grad_norm": 0.3637406826019287,
-      "learning_rate": 4.9833888998177165e-05,
-      "loss": 1.5221,
-      "step": 2800
-    },
-    {
-      "epoch": 0.07790044859913503,
-      "grad_norm": 0.530950129032135,
-      "learning_rate": 4.981493215290366e-05,
-      "loss": 1.5233,
-      "step": 2900
-    },
-    {
-      "epoch": 0.08058667096462245,
-      "grad_norm": 1.674155831336975,
-      "learning_rate": 4.979495526296279e-05,
-      "loss": 1.5204,
-      "step": 3000
-    },
-    {
-      "epoch": 0.08058667096462245,
-      "eval_loss": 1.5201951265335083,
-      "eval_runtime": 3522.0591,
-      "eval_sacrebleu": 96.36598044790144,
-      "eval_samples_per_second": 75.162,
-      "eval_steps_per_second": 0.587,
-      "step": 3000
     }
   ],
   "logging_steps": 100,
@@ -273,7 +115,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 4.981147771600896e+16,
+  "total_flos": 1.6604548281925632e+16,
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": null

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c179acc21123cb85cf576463327f9e9fa5b106f6eec15b612cc17cf046140506
+oid sha256:ce0cdcde6ce6ad61a433903430eaa7d57da2bdffd8fa9982262860bcf6d0b1b1
 size 6033