Training in progress, epoch 5, checkpoint

last-checkpoint/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a580f8931d3c0b73a4622991aa6cb3b40337ac5190443f4d57543128a06debd
+oid sha256:f94034709b397975548cb9fbe3a07aad5648c6a4a432299e1011979d35fd8920
 size 2460354912

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c445f2be47afa8fe35e10ccfbab01c2115861a34c88c68d4f9a2329b3c655bf
+oid sha256:3ddb21a7614a291f781d08059c7d74bb4d34d15bbd3bbabd7058de72e6e59ba2
 size 4921023445

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c8a2de6fd3300223d2a2c6022b35cc0aae70c2ee044eca6760de0d2de20cf17
+oid sha256:5dfc59386df7407a0fc45116f54b32e769582aa411c1cba47cc07dc2aeebc682
 size 14244

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:41216328ab75de937007afb04d76156949bedb908461001a451c8991c2ba8cca
+oid sha256:061929cf33bbb1db778e3f3bba75a30feaf7aa9ae494505513aa8b545044f0b4
 size 988

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a11a75238b320f6122b6a3754c879f05bf15124609a375c0697fe088d06519c3
+oid sha256:f82ec84100546c47a76f63e10c051f300392ef520458425efd0cbf0afe3718ce
 size 1064

last-checkpoint/trainer_state.json

@@ -1,10 +1,10 @@
 {
-  "best_global_step": 3750,
-  "best_metric": 59.30988278861181,
-  "best_model_checkpoint": "nllb-200-600M-dzo-eng-checkpoints/checkpoint-3750",
-  "epoch": 4.0,
+  "best_global_step": 6250,
+  "best_metric": 59.5126771383472,
+  "best_model_checkpoint": "nllb-200-600M-dzo-eng-checkpoints/checkpoint-6250",
+  "epoch": 5.0,
   "eval_steps": 500,
-  "global_step": 5000,
+  "global_step": 6250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -114,6 +114,29 @@
       "eval_samples_per_second": 5.951,
       "eval_steps_per_second": 1.488,
       "step": 5000
+    },
+    {
+      "epoch": 4.4,
+      "grad_norm": 0.17317089438438416,
+      "learning_rate": 3.6048e-06,
+      "loss": 0.0337,
+      "step": 5500
+    },
+    {
+      "epoch": 4.8,
+      "grad_norm": 0.32834669947624207,
+      "learning_rate": 1.2048e-06,
+      "loss": 0.033,
+      "step": 6000
+    },
+    {
+      "epoch": 5.0,
+      "eval_bleu": 59.5126771383472,
+      "eval_loss": 0.07744310051202774,
+      "eval_runtime": 168.6113,
+      "eval_samples_per_second": 5.931,
+      "eval_steps_per_second": 1.483,
+      "step": 6250
     }
   ],
   "logging_steps": 500,
@@ -128,12 +151,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.083552301056e+16,
+  "total_flos": 1.35444037632e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null