Training in progress, step 4500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3eb29474e73931dfcd91c2e79d9d8a79eabb6944e3d84da49f7f90f18979f71
+oid sha256:ffe7afe5c070fab96ca43ba7d40ffa5a5697d168401423ad6c0ad6e75a43f93b
 size 6710771584

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3667ce09a5903ad6e193c00d0ddb89daaea8db351add98c814da23dbafea530d
+oid sha256:34683cb4007c3b92110f7840142f7ce353dc35fa8c47d3906f2a8292351af604
 size 4986145435

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a11d04976761ef8277f44a0f7c0e228b3cac969b10ee5c6b4de7b171c800cc9
+oid sha256:7892cbbcf16ff8490e2d0a329d8594e2218d984e8584083ac3da0573e6d508dd
 size 4985796040

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a4a2096581fc9ebadb506824fa7258859cda3d3274ad32362d499c3cb4e45b7
+oid sha256:4e4147dc29ced8cfe98d7c7047558106240377827105c3d76a5ee8d8e17d7754
 size 3407874846

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0592b22bbf2c12a8a47cfcd0fc1dc3c2494837461af5f07d2b2ae6a9fe0dfde8
+oid sha256:e4fbdd49ae32378de0eb7b581f65e4edbef5eb7583e3157a829c62678554ea54
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78d61582d761df7115a63fb89688f5937274cf5adaaf644e15aaa05c94e6b14d
+oid sha256:47132a874ad4fda1d1f651cb8d7cf3a21ccb1e85b7d1f0c122a2dcf69a4af0ac
 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": 4000.0,
+  "epoch": 4500.0,
   "eval_steps": 500,
-  "global_step": 4000,
+  "global_step": 4500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -143,6 +143,23 @@
       "eval_samples_per_second": 0.288,
       "eval_steps_per_second": 0.144,
       "step": 4000
+    },
+    {
+      "epoch": 4500.0,
+      "grad_norm": 0.029812365770339966,
+      "learning_rate": 2.4763828125157654e-07,
+      "loss": 0.0016,
+      "step": 4500
+    },
+    {
+      "epoch": 4500.0,
+      "eval_gen_len": 24.5,
+      "eval_loss": 1.4486483335494995,
+      "eval_rouge": 0.0357,
+      "eval_runtime": 6.9642,
+      "eval_samples_per_second": 0.287,
+      "eval_steps_per_second": 0.144,
+      "step": 4500
     }
   ],
   "logging_steps": 500,
@@ -150,7 +167,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5000,
   "save_steps": 500,
-  "total_flos": 2.5449063776256e+16,
+  "total_flos": 2.8630196748288e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null