Training in progress, step 2500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a807a85f754badd8c9efd649e3bbf2166996fe5e3ec9c11eaae85c9dda679932
+oid sha256:1deebaafa1b70cdd1c9d15999c2a57939ea7aa4e7e67ebf6416bf58ca007a215
 size 6710771584

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3aa3609d1b8a48a05066b7cc714f71556636ee0e47045d9a44d8ec81d0cd6180
+oid sha256:90f7b03f32a17be7878bad823c9fc9641df111cbb59878e6341dbb3f5f09447c
 size 4986145435

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e0e9574d2b72bdb7076b81bc5bcd7b440fe9f2455942410d80ca6ac072da517
+oid sha256:d9732c698870d30036287d93533e194169410d34fc775850790dd041877ad668
 size 4985796040

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ebe618324c892dc8f285f90d25cf405d891b10e738ec50fc52102cf4bd10239d
+oid sha256:0a2e66e0ca3756e27d5d9a81e7dc69845faab10c0ac5dd5952704590e8a2691a
 size 3407874846

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:295251b092aed1296d3d74e502859b3c44bbbb2d464be8b37cda12c62cc041ef
+oid sha256:63e6e16bff0ec180144dd98dc6380e7255e231f7afab88faed35990fbd12abca
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5f968c3af98b2806782b37880f7c223858e5c193ce3abef2c9dc55a7138fce6
+oid sha256:bc039a0907d33dafb6ae078bb0b9d8ad6e476d3ee6969607ecf1648c7ec43f6a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1881097555160522,
   "best_model_checkpoint": "../facebook/nllb-200-3.3B-finetuned/checkpoint-1000",
-  "epoch": 2000.0,
+  "epoch": 2500.0,
   "eval_steps": 500,
-  "global_step": 2000,
+  "global_step": 2500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -75,6 +75,23 @@
       "eval_samples_per_second": 0.288,
       "eval_steps_per_second": 0.144,
       "step": 2000
+    },
+    {
+      "epoch": 2500.0,
+      "grad_norm": 0.05517512932419777,
+      "learning_rate": 5.0094247723796405e-06,
+      "loss": 0.0036,
+      "step": 2500
+    },
+    {
+      "epoch": 2500.0,
+      "eval_gen_len": 33.5,
+      "eval_loss": 1.5625241994857788,
+      "eval_rouge": 0.125,
+      "eval_runtime": 6.9319,
+      "eval_samples_per_second": 0.289,
+      "eval_steps_per_second": 0.144,
+      "step": 2500
     }
   ],
   "logging_steps": 500,
@@ -82,7 +99,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5000,
   "save_steps": 500,
-  "total_flos": 1.2724531888128e+16,
+  "total_flos": 1.590566486016e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null