Training in progress, step 2000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72bc55befc8debe91950431873d0e15da2f255a016894eb1e97161ec38db3919
+oid sha256:a807a85f754badd8c9efd649e3bbf2166996fe5e3ec9c11eaae85c9dda679932
 size 6710771584

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d64fb89da44600a3a0ffe05a99b210c965449cf763ddd42e2164f729fdebfe0
+oid sha256:3aa3609d1b8a48a05066b7cc714f71556636ee0e47045d9a44d8ec81d0cd6180
 size 4986145435

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88ec66d25ed5d85f5968d17ac7ac4b263f11ed3af11e33343203bdcd1c4a23f3
+oid sha256:7e0e9574d2b72bdb7076b81bc5bcd7b440fe9f2455942410d80ca6ac072da517
 size 4985796040

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b91529b816ee6997bb83cf347f1efb55ee3dd1ec88043e685afc90a3323c0330
+oid sha256:ebe618324c892dc8f285f90d25cf405d891b10e738ec50fc52102cf4bd10239d
 size 3407874846

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b399b3571ee5890490d5200d8835e940a3ae42b45b41b3a1ef49cec071e88795
+oid sha256:295251b092aed1296d3d74e502859b3c44bbbb2d464be8b37cda12c62cc041ef
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f6efdda7b4c17f1006bd7ce353017288d59224f22c57bbd4ad998564b561ec8
+oid sha256:c5f968c3af98b2806782b37880f7c223858e5c193ce3abef2c9dc55a7138fce6
 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": 1500.0,
+  "epoch": 2000.0,
   "eval_steps": 500,
-  "global_step": 1500,
+  "global_step": 2000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -58,6 +58,23 @@
       "eval_samples_per_second": 0.288,
       "eval_steps_per_second": 0.144,
       "step": 1500
+    },
+    {
+      "epoch": 2000.0,
+      "grad_norm": 0.08364015817642212,
+      "learning_rate": 6.554045718173867e-06,
+      "loss": 0.0061,
+      "step": 2000
+    },
+    {
+      "epoch": 2000.0,
+      "eval_gen_len": 33.5,
+      "eval_loss": 1.5447587966918945,
+      "eval_rouge": 0.125,
+      "eval_runtime": 6.9455,
+      "eval_samples_per_second": 0.288,
+      "eval_steps_per_second": 0.144,
+      "step": 2000
     }
   ],
   "logging_steps": 500,
@@ -65,7 +82,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5000,
   "save_steps": 500,
-  "total_flos": 9543398916096000.0,
+  "total_flos": 1.2724531888128e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null