Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a87421e3a8f20612521e71c423b544bda9fcc2c6ee20a4d4377f5414bfcee9c
+oid sha256:2710e49ab186e12adc38d5a571b4c81d388ad08b23ee41e93dfbb257220a4baa
 size 2460359008

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f6174299f560006cde8a99fa3a1b8ce5a5a9e1e4c9fde7e935c38eca1925783
+oid sha256:052fd2e692143b8247ad886aaebff809e046faf15974ab05bae4c1abc579c079
 size 4921031637

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d10ef6f507f8ebfde960deac8bce9425cf6a51cacda5ba79a18f18b45f0b37e
+oid sha256:4c2af3241d86ddcbf6a06ccbb1b7fa7c7608795360426cc94893fe3d8ccbb4f1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cec5952bdc21c397c50099196b21c11fa80846c74cee21ea9ac6f9c9105df231
+oid sha256:79e6bf62780eeafb7c159ed5da3c5b870152c515e473817f8771beda25bc35f6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 3.0,
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 7317,
+  "global_step": 12195,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -135,6 +135,96 @@
       "eval_samples_per_second": 16.496,
       "eval_steps_per_second": 2.063,
       "step": 7317
+    },
+    {
+      "epoch": 3.075030750307503,
+      "grad_norm": 0.5503592491149902,
+      "learning_rate": 1.925789257892579e-05,
+      "loss": 0.3721,
+      "step": 7500
+    },
+    {
+      "epoch": 3.2800328003280033,
+      "grad_norm": 0.8528617024421692,
+      "learning_rate": 1.7207872078720788e-05,
+      "loss": 0.3503,
+      "step": 8000
+    },
+    {
+      "epoch": 3.4850348503485034,
+      "grad_norm": 0.572259247303009,
+      "learning_rate": 1.5157851578515787e-05,
+      "loss": 0.3509,
+      "step": 8500
+    },
+    {
+      "epoch": 3.6900369003690034,
+      "grad_norm": 0.5713686347007751,
+      "learning_rate": 1.3107831078310784e-05,
+      "loss": 0.3466,
+      "step": 9000
+    },
+    {
+      "epoch": 3.895038950389504,
+      "grad_norm": 0.6144512295722961,
+      "learning_rate": 1.1061910619106192e-05,
+      "loss": 0.3515,
+      "step": 9500
+    },
+    {
+      "epoch": 4.0,
+      "eval_bleu_eng_Latn-swh_Latn": 75.36340129440856,
+      "eval_bleu_swh_Latn-eng_Latn": 61.44137797667521,
+      "eval_loss": 0.45032787322998047,
+      "eval_runtime": 852.2592,
+      "eval_samples_per_second": 16.335,
+      "eval_steps_per_second": 2.043,
+      "step": 9756
+    },
+    {
+      "epoch": 4.1000410004100045,
+      "grad_norm": 0.5769449472427368,
+      "learning_rate": 9.01189011890119e-06,
+      "loss": 0.3366,
+      "step": 10000
+    },
+    {
+      "epoch": 4.305043050430505,
+      "grad_norm": 0.5665178298950195,
+      "learning_rate": 6.961869618696187e-06,
+      "loss": 0.3251,
+      "step": 10500
+    },
+    {
+      "epoch": 4.510045100451005,
+      "grad_norm": 0.5888523459434509,
+      "learning_rate": 4.911849118491185e-06,
+      "loss": 0.3253,
+      "step": 11000
+    },
+    {
+      "epoch": 4.715047150471505,
+      "grad_norm": 0.6570137739181519,
+      "learning_rate": 2.861828618286183e-06,
+      "loss": 0.3245,
+      "step": 11500
+    },
+    {
+      "epoch": 4.920049200492005,
+      "grad_norm": 0.5004702806472778,
+      "learning_rate": 8.118081180811808e-07,
+      "loss": 0.3254,
+      "step": 12000
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu_eng_Latn-swh_Latn": 75.63347176884412,
+      "eval_bleu_swh_Latn-eng_Latn": 61.57218466545877,
+      "eval_loss": 0.4516850709915161,
+      "eval_runtime": 856.3842,
+      "eval_samples_per_second": 16.257,
+      "eval_steps_per_second": 2.033,
+      "step": 12195
     }
   ],
   "logging_steps": 500,
@@ -149,12 +239,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.253311606305587e+16,
+  "total_flos": 5.421408335993242e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null