Training in progress, step 3000, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1deebaafa1b70cdd1c9d15999c2a57939ea7aa4e7e67ebf6416bf58ca007a215
+oid sha256:5c89bdf301f739fbb033533166f882246f7313b189b8b208d7dc50cc875f753e
 size 6710771584

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90f7b03f32a17be7878bad823c9fc9641df111cbb59878e6341dbb3f5f09447c
+oid sha256:046346897019761b666da0e193401e2706ade13eb57fc5f3dea142ab495aac0c
 size 4986145435

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d9732c698870d30036287d93533e194169410d34fc775850790dd041877ad668
+oid sha256:8d8c5b7c86adbfb248596d040800d0034668272b3ec643c486e162fe23a939f6
 size 4985796040

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a2e66e0ca3756e27d5d9a81e7dc69845faab10c0ac5dd5952704590e8a2691a
+oid sha256:28b779e190a7dc5c23d2e4a3ba37cbe019e51b16d256aff63888445449974407
 size 3407874846

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:63e6e16bff0ec180144dd98dc6380e7255e231f7afab88faed35990fbd12abca
+oid sha256:714bd7fa9e5617bc8a7da8037713bc3378304787976fdb32a6face2699bee68d
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc039a0907d33dafb6ae078bb0b9d8ad6e476d3ee6969607ecf1648c7ec43f6a
+oid sha256:70249393eecaa461148d94aed4aee9bdae2594c3e9983709826d58e41ede6ec9
 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": 2500.0,
+  "epoch": 3000.0,
   "eval_steps": 500,
-  "global_step": 2500,
+  "global_step": 3000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -92,6 +92,23 @@
       "eval_samples_per_second": 0.289,
       "eval_steps_per_second": 0.144,
       "step": 2500
+    },
+    {
+      "epoch": 3000.0,
+      "grad_norm": 0.04180261120200157,
+      "learning_rate": 3.463881264198645e-06,
+      "loss": 0.0025,
+      "step": 3000
+    },
+    {
+      "epoch": 3000.0,
+      "eval_gen_len": 33.5,
+      "eval_loss": 1.5641270875930786,
+      "eval_rouge": 0.125,
+      "eval_runtime": 6.9474,
+      "eval_samples_per_second": 0.288,
+      "eval_steps_per_second": 0.144,
+      "step": 3000
     }
   ],
   "logging_steps": 500,
@@ -99,7 +116,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5000,
   "save_steps": 500,
-  "total_flos": 1.590566486016e+16,
+  "total_flos": 1.9086797832192e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null