Training in progress, step 700, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db740509f5a95eecba7872e2a1e17b037034a23a73f00bb1d1061af31b9b5e44
+oid sha256:67fb82930389b24ba0208a7a08b33f2abbd2323860716962cf881cf5a16bc6ed
 size 2751040864

last-checkpoint/pytorch_model-00001-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:398cfd12e51c24f5864a31c205e44db9a404ab7717a0075a6d153b914fcef1f0
+oid sha256:c84f8cc0dcd4bb5980ea5c4e462292f7fdcfa76bf833ecfba7b6e2fcdd96d3c0
 size 5000078781

last-checkpoint/pytorch_model-00002-of-00002.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1606b9f5785865abbc70c805039dc367e7a957d7c8b8bdc7b28a1ae2899b5d75
+oid sha256:13a55fd318dc6a5d1963163df52119c23c1dac0f939b79c076170d494afe47c8
 size 482838574

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae687f4500411ca2e1ef17be88ce145b3ea9cb18005002027164c0c3ab6645d9
+oid sha256:ac1b10d6f7dd9cdf9b5b89778eacbed4b4a8f31412820b85b64a56b3a491d825
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50f0e1d62e75d3dedce865615f4c070df947c2befbd956dcb7172fce5c716479
+oid sha256:a573157b5af49c7fd752beb625308fa4d3184af6323528856e81787deb4e252b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.453127384185791,
-  "best_model_checkpoint": "../KevinKibe/nllb-200-distilled-1.3B-finetuned-finetuned/checkpoint-400",
-  "epoch": 400.0,
+  "best_metric": 0.8545865416526794,
+  "best_model_checkpoint": "../KevinKibe/nllb-200-distilled-1.3B-finetuned-finetuned/checkpoint-700",
+  "epoch": 700.0,
   "eval_steps": 100,
-  "global_step": 400,
+  "global_step": 700,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,57 @@
       "eval_samples_per_second": 1.224,
       "eval_steps_per_second": 0.612,
       "step": 400
+    },
+    {
+      "epoch": 500.0,
+      "grad_norm": 11.111770629882812,
+      "learning_rate": 1.006e-05,
+      "loss": 1.4112,
+      "step": 500
+    },
+    {
+      "epoch": 500.0,
+      "eval_gen_len": 70.0,
+      "eval_loss": 1.6681925058364868,
+      "eval_rouge": 0.1899,
+      "eval_runtime": 6.0247,
+      "eval_samples_per_second": 0.332,
+      "eval_steps_per_second": 0.166,
+      "step": 500
+    },
+    {
+      "epoch": 600.0,
+      "grad_norm": 6.4994120597839355,
+      "learning_rate": 8.06e-06,
+      "loss": 0.6738,
+      "step": 600
+    },
+    {
+      "epoch": 600.0,
+      "eval_gen_len": 68.0,
+      "eval_loss": 1.1857625246047974,
+      "eval_rouge": 0.1907,
+      "eval_runtime": 6.0626,
+      "eval_samples_per_second": 0.33,
+      "eval_steps_per_second": 0.165,
+      "step": 600
+    },
+    {
+      "epoch": 700.0,
+      "grad_norm": 3.2670979499816895,
+      "learning_rate": 6.0600000000000004e-06,
+      "loss": 0.2921,
+      "step": 700
+    },
+    {
+      "epoch": 700.0,
+      "eval_gen_len": 28.0,
+      "eval_loss": 0.8545865416526794,
+      "eval_rouge": 0.2776,
+      "eval_runtime": 1.6454,
+      "eval_samples_per_second": 1.215,
+      "eval_steps_per_second": 0.608,
+      "step": 700
     }
   ],
   "logging_steps": 100,
@@ -82,7 +133,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 1000,
   "save_steps": 100,
-  "total_flos": 1000114932940800.0,
+  "total_flos": 1750201132646400.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null