Training in progress, step 600, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5f8d3299712b376660cccc0cffd2618f027545216af1ecd01649bf6d9a1cf253
-size 2751039840
+oid sha256:cd57c13abaf0d174c02290aa0f78a71d70c5476a554ad8bad73849b8ff61800d
+size 2751040864

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4384d18af5225ec354e46813b7536ed97a28d9cad198dd893f182076e87130ff
+oid sha256:38ba27f5af6a9d724d4d82ace5f1a728dba288ac250dd2f2b1aa561b035f112e
 size 5000078781

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d9bc066b662b746b93f37c74c802ca86ec4755884dba15455cdc38281a3dffe
+oid sha256:edf81f2e392254cad5d0bdd1d3ad2fea57b5121e77d0f300dca574c9f8b116af
 size 482838574

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9348b8c9a65159f1ce6d48a8b8d958aa47f54a0eed2af1fa60d866a416126f
+oid sha256:28d6e030bac5bb05861de097616fc28c5de259971c7b9cffa30d3bf2f2cab125
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae45884e25f64d4c500190492a746910f03faaad4ecb5fc5bf3c74366978017d
+oid sha256:68ef6cfe9e27fdf12c0645118ae1508ca53b1d473f965478e80079844fa9a98e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.39197173714637756,
-  "best_model_checkpoint": "../KevinKibe/nllb-200-distilled-1.3B-finetuned-finetuned-finetuned/checkpoint-200",
-  "epoch": 200.0,
+  "best_metric": 0.37990298867225647,
+  "best_model_checkpoint": "../KevinKibe/nllb-200-distilled-1.3B-finetuned-finetuned-finetuned/checkpoint-600",
+  "epoch": 600.0,
   "eval_steps": 200,
-  "global_step": 200,
+  "global_step": 600,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24,6 +24,40 @@
       "eval_samples_per_second": 0.2,
       "eval_steps_per_second": 0.1,
       "step": 200
+    },
+    {
+      "epoch": 400.0,
+      "grad_norm": 0.08469633013010025,
+      "learning_rate": 1.6000000000000003e-05,
+      "loss": 0.0069,
+      "step": 400
+    },
+    {
+      "epoch": 400.0,
+      "eval_gen_len": 17.5,
+      "eval_loss": 0.3805849552154541,
+      "eval_rouge": 0.1364,
+      "eval_runtime": 1.1672,
+      "eval_samples_per_second": 1.713,
+      "eval_steps_per_second": 0.857,
+      "step": 400
+    },
+    {
+      "epoch": 600.0,
+      "grad_norm": 0.05082901939749718,
+      "learning_rate": 1.4e-05,
+      "loss": 0.0034,
+      "step": 600
+    },
+    {
+      "epoch": 600.0,
+      "eval_gen_len": 17.5,
+      "eval_loss": 0.37990298867225647,
+      "eval_rouge": 0.1364,
+      "eval_runtime": 1.2177,
+      "eval_samples_per_second": 1.642,
+      "eval_steps_per_second": 0.821,
+      "step": 600
     }
   ],
   "logging_steps": 200,
@@ -31,7 +65,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2000,
   "save_steps": 200,
-  "total_flos": 585173630976000.0,
+  "total_flos": 1755520892928000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null