Training in progress, step 1400, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d83de31581fe6cb4059f3158472dbdf40e6af6b2dcbd3b0137f30cef84e4e683
+oid sha256:f2a303e416b8e87e82b0a9e76a5d7a78b1fc5109468b48fe4e63f33e9c3bd855
 size 2751040864

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4d24ec5c1660898a3119af80d0941f0b3fbcbeb38dfff835b840fb8dcc3a325
+oid sha256:ac654860a07162e4c0f37a59df869b9b1b80e34174d1a714bd957e4f32abd2d1
 size 5000078781

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2be09685823f96c2f8b284e862351bab4f3ab64664fbba473bff89df0c1bbca
+oid sha256:354c2aa6152650ba3dfa40e3f219ee3e964aac74b46fa672914384b3af535e9b
 size 482838574

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d41c4f210ed64e3b4ca1d599f52e022995a72814fdf542be888368b7322823b2
+oid sha256:a364d71973980816c47dc3b9dabc9ae54ad71e3b4a66da0300314d8bb9a5a804
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81817a053d50e28a36bf282b57fddce1e0b3bf7730474081347b6457fc1bd5e8
+oid sha256:1a051f2b7b66e1d1bb2f8dad5db282e6521639d1f5915c20f67b57d63e76b058
 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": 1000.0,
+  "epoch": 1400.0,
   "eval_steps": 200,
-  "global_step": 1000,
+  "global_step": 1400,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,40 @@
       "eval_samples_per_second": 0.19,
       "eval_steps_per_second": 0.095,
       "step": 1000
+    },
+    {
+      "epoch": 1200.0,
+      "grad_norm": 0.02252182736992836,
+      "learning_rate": 8.000000000000001e-06,
+      "loss": 0.0013,
+      "step": 1200
+    },
+    {
+      "epoch": 1200.0,
+      "eval_gen_len": 13.5,
+      "eval_loss": 0.39042866230010986,
+      "eval_rouge": 0.1765,
+      "eval_runtime": 10.4367,
+      "eval_samples_per_second": 0.192,
+      "eval_steps_per_second": 0.096,
+      "step": 1200
+    },
+    {
+      "epoch": 1400.0,
+      "grad_norm": 0.019408540800213814,
+      "learning_rate": 6e-06,
+      "loss": 0.0011,
+      "step": 1400
+    },
+    {
+      "epoch": 1400.0,
+      "eval_gen_len": 13.5,
+      "eval_loss": 0.3919622004032135,
+      "eval_rouge": 0.1765,
+      "eval_runtime": 9.8993,
+      "eval_samples_per_second": 0.202,
+      "eval_steps_per_second": 0.101,
+      "step": 1400
     }
   ],
   "logging_steps": 200,
@@ -99,7 +133,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2000,
   "save_steps": 200,
-  "total_flos": 2925868154880000.0,
+  "total_flos": 4096215416832000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null