Training in progress, step 1000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87eafb69887e6bd01f939e477bcb1265c335411126086cb1b96404a24624ea6e
+oid sha256:70b8be01b75a83e3a49f7e9a34c3bbfa87afc53dc23a9ded96bdfb6a4a84d350
 size 6710771584

last-checkpoint/pytorch_model-00001-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc2500c01fb5d4dc75525131491fc2017f41b93897d5a615d458c20340892066
+oid sha256:e05884733762cfe4e5832856f6fad8b084157a43eef53720b7b634ae9e95db2c
 size 4986145435

last-checkpoint/pytorch_model-00002-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9f224c0c53ed0e1a0351e725936d6594b2e4c249be60a79d9a102bb423e153
+oid sha256:7821894ab9ece20964b8ee7081c71441ddc6d59f9cf0117065eb236f6a5a6057
 size 4985796040

last-checkpoint/pytorch_model-00003-of-00003.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cac4b2da289ebf6d0e02375c9b816467efe40597ffeb270e0537bae49e59a4cb
+oid sha256:ccf434a439f08e70ea44ff46dbd41b4a05aff545e4d2c05122231977ece0a9e5
 size 3407874846

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e081734a57494d4fe14ed26d46cbbdb085dfea894c363c22066d693eb92a923
+oid sha256:4003b01b87ceeb9499c79d58de35776b6f016af4e88e9c2106f8f5ae0a97b5a1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a44141ca904c51387fc0d64514a0a117260422f3a980a9526327c16e040f02
+oid sha256:7264f2fa31a81df845774e38b4b38010e57af573916d13425253b1815c7271f0
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.901174306869507,
-  "best_model_checkpoint": "../facebook/nllb-200-3.3B-finetuned/checkpoint-500",
-  "epoch": 500.0,
+  "best_metric": 1.1881097555160522,
+  "best_model_checkpoint": "../facebook/nllb-200-3.3B-finetuned/checkpoint-1000",
+  "epoch": 1000.0,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -24,6 +24,23 @@
       "eval_samples_per_second": 0.284,
       "eval_steps_per_second": 0.142,
       "step": 500
+    },
+    {
+      "epoch": 1000.0,
+      "grad_norm": 0.9894864559173584,
+      "learning_rate": 9.050617527877911e-06,
+      "loss": 0.609,
+      "step": 1000
+    },
+    {
+      "epoch": 1000.0,
+      "eval_gen_len": 26.0,
+      "eval_loss": 1.1881097555160522,
+      "eval_rouge": 0.098,
+      "eval_runtime": 1.1556,
+      "eval_samples_per_second": 1.731,
+      "eval_steps_per_second": 0.865,
+      "step": 1000
     }
   ],
   "logging_steps": 500,
@@ -31,7 +48,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5000,
   "save_steps": 500,
-  "total_flos": 3181132972032000.0,
+  "total_flos": 6362265944064000.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null