Training in progress, step 3500, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5c89bdf301f739fbb033533166f882246f7313b189b8b208d7dc50cc875f753e
+oid sha256:5c3f58047ad6c40a78585613022f4ed80be220bf6ec21185d07d2c8a498c4d81
 size 6710771584

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:046346897019761b666da0e193401e2706ade13eb57fc5f3dea142ab495aac0c
+oid sha256:c82a2e7c8ec4e63cb1fe1265398cbd375ba2db2c8e3306d8c4f71b7aee6a9650
 size 4986145435

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d8c5b7c86adbfb248596d040800d0034668272b3ec643c486e162fe23a939f6
+oid sha256:1ffc65c9f1d6f86ab21566e966a8ee5f99bb6514bc9a833ae54f735ad7480417
 size 4985796040

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28b779e190a7dc5c23d2e4a3ba37cbe019e51b16d256aff63888445449974407
+oid sha256:23ce7fd3a2949f3878635d26b1caf6c1559d0813d1ebd24edc72fb58c2187e58
 size 3407874846

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:714bd7fa9e5617bc8a7da8037713bc3378304787976fdb32a6face2699bee68d
+oid sha256:1b5bfe987daf29ca780f6f0f48d581306ba9822c23e7ac806d164694cc658fe0
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70249393eecaa461148d94aed4aee9bdae2594c3e9983709826d58e41ede6ec9
+oid sha256:a8d3846c8c4611a93d268239a3a849d9aeb15e0e658fb1d1fc10fa99b8483e00
 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": 3000.0,
+  "epoch": 3500.0,
   "eval_steps": 500,
-  "global_step": 3000,
+  "global_step": 3500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -109,6 +109,23 @@
       "eval_samples_per_second": 0.288,
       "eval_steps_per_second": 0.144,
       "step": 3000
+    },
+    {
+      "epoch": 3500.0,
+      "grad_norm": 0.03480682149529457,
+      "learning_rate": 2.0687037606464554e-06,
+      "loss": 0.002,
+      "step": 3500
+    },
+    {
+      "epoch": 3500.0,
+      "eval_gen_len": 33.5,
+      "eval_loss": 1.5625765323638916,
+      "eval_rouge": 0.125,
+      "eval_runtime": 6.9229,
+      "eval_samples_per_second": 0.289,
+      "eval_steps_per_second": 0.144,
+      "step": 3500
     }
   ],
   "logging_steps": 500,
@@ -116,7 +133,7 @@
   "num_input_tokens_seen": 0,
   "num_train_epochs": 5000,
   "save_steps": 500,
-  "total_flos": 1.9086797832192e+16,
+  "total_flos": 2.2267930804224e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null