Training in progress, step 1800, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f2a303e416b8e87e82b0a9e76a5d7a78b1fc5109468b48fe4e63f33e9c3bd855
+oid sha256:154db639e0c4ba9f6504e3bc183c200891d38beb003b68908f789f57a627f526
 size 2751040864

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac654860a07162e4c0f37a59df869b9b1b80e34174d1a714bd957e4f32abd2d1
+oid sha256:b0b6a7d1c35bcaf448b673f7238dbaa4f3b2476f98073c29e5a13312bd140b2e
 size 5000078781

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:354c2aa6152650ba3dfa40e3f219ee3e964aac74b46fa672914384b3af535e9b
+oid sha256:ada2d1395c61c9e04cf436684e7df9d0a968a075accb14ef27dcecd1c9e7c17a
 size 482838574

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a364d71973980816c47dc3b9dabc9ae54ad71e3b4a66da0300314d8bb9a5a804
+oid sha256:ae25b7f14655f414d57bbcaef4e73e78779f0fbb79aca93ea240474900642c9c
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a051f2b7b66e1d1bb2f8dad5db282e6521639d1f5915c20f67b57d63e76b058
+oid sha256:f1ef1b747498f408ff85e0a019461da14a74df62497d8e7b903379927c997b6e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.37990298867225647,
   "best_model_checkpoint": "../KevinKibe/nllb-200-distilled-1.3B-finetuned-finetuned-finetuned/checkpoint-600",
-  "epoch": 1400.0,
+  "epoch": 1800.0,
   "eval_steps": 200,
-  "global_step": 1400,
+  "global_step": 1800,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -126,6 +126,40 @@
       "eval_samples_per_second": 0.202,
       "eval_steps_per_second": 0.101,
       "step": 1400
+    },
+    {
+      "epoch": 1600.0,
+      "grad_norm": 0.017478974536061287,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.001,
+      "step": 1600
+    },
+    {
+      "epoch": 1600.0,
+      "eval_gen_len": 13.5,
+      "eval_loss": 0.3930334746837616,
+      "eval_rouge": 0.1765,
+      "eval_runtime": 10.2296,
+      "eval_samples_per_second": 0.196,
+      "eval_steps_per_second": 0.098,
+      "step": 1600
+    },
+    {
+      "epoch": 1800.0,
+      "grad_norm": 0.01638863794505596,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.0009,
+      "step": 1800
+    },
+    {
+      "epoch": 1800.0,
+      "eval_gen_len": 13.5,
+      "eval_loss": 0.3938616216182709,
+      "eval_rouge": 0.1765,
+      "eval_runtime": 9.7251,
+      "eval_samples_per_second": 0.206,
+      "eval_steps_per_second": 0.103,
+      "step": 1800
     }
   ],
   "logging_steps": 200,
@@ -133,7 +167,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2000,
   "save_steps": 200,
-  "total_flos": 4096215416832000.0,
+  "total_flos": 5266562678784000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null