Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd57c13abaf0d174c02290aa0f78a71d70c5476a554ad8bad73849b8ff61800d
+oid sha256:d83de31581fe6cb4059f3158472dbdf40e6af6b2dcbd3b0137f30cef84e4e683
 size 2751040864

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:38ba27f5af6a9d724d4d82ace5f1a728dba288ac250dd2f2b1aa561b035f112e
+oid sha256:f4d24ec5c1660898a3119af80d0941f0b3fbcbeb38dfff835b840fb8dcc3a325
 size 5000078781

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edf81f2e392254cad5d0bdd1d3ad2fea57b5121e77d0f300dca574c9f8b116af
+oid sha256:c2be09685823f96c2f8b284e862351bab4f3ab64664fbba473bff89df0c1bbca
 size 482838574

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28d6e030bac5bb05861de097616fc28c5de259971c7b9cffa30d3bf2f2cab125
+oid sha256:d41c4f210ed64e3b4ca1d599f52e022995a72814fdf542be888368b7322823b2
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68ef6cfe9e27fdf12c0645118ae1508ca53b1d473f965478e80079844fa9a98e
+oid sha256:81817a053d50e28a36bf282b57fddce1e0b3bf7730474081347b6457fc1bd5e8
 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": 600.0,
+  "epoch": 1000.0,
   "eval_steps": 200,
-  "global_step": 600,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,40 @@
       "eval_samples_per_second": 1.642,
       "eval_steps_per_second": 0.821,
       "step": 600
+    },
+    {
+      "epoch": 800.0,
+      "grad_norm": 0.03562492877244949,
+      "learning_rate": 1.2e-05,
+      "loss": 0.0022,
+      "step": 800
+    },
+    {
+      "epoch": 800.0,
+      "eval_gen_len": 109.0,
+      "eval_loss": 0.39079928398132324,
+      "eval_rouge": 0.1364,
+      "eval_runtime": 10.1532,
+      "eval_samples_per_second": 0.197,
+      "eval_steps_per_second": 0.098,
+      "step": 800
+    },
+    {
+      "epoch": 1000.0,
+      "grad_norm": 0.027455538511276245,
+      "learning_rate": 1e-05,
+      "loss": 0.0016,
+      "step": 1000
+    },
+    {
+      "epoch": 1000.0,
+      "eval_gen_len": 13.5,
+      "eval_loss": 0.3873954713344574,
+      "eval_rouge": 0.1765,
+      "eval_runtime": 10.52,
+      "eval_samples_per_second": 0.19,
+      "eval_steps_per_second": 0.095,
+      "step": 1000
     }
   ],
   "logging_steps": 200,
@@ -65,7 +99,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 2000,
   "save_steps": 200,
-  "total_flos": 1755520892928000.0,
+  "total_flos": 2925868154880000.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null