Training in progress, epoch 2, checkpoint

last-checkpoint/README.md

@@ -5,6 +5,5 @@ library_name: peft
 
 ### Framework versions
 
-- PEFT 0.5.0
 
 - PEFT 0.5.0

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d8eece0cb713c5bda8dfaf483fde59a9a8d7586872a7489092df0ad63d26b85
+oid sha256:538342ac688fb0a0d86aaedd7330737ae00e80eb8e093f459c58ce63d811fc33
 size 1256

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8f8922c352ab63d1593bcb944e77d461472df192dcdc1202984e9e08f16a111
+oid sha256:2ba8427ac6eea57ec5734699585fe0dd282eb1503ee998fdc4232e54bb7d6354
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9f352ad8ae767de1cdfeb29fde8f2883bf1769f14e8edca24b5887be36d5a540
+oid sha256:0bc60bce785072809819f1c1fc75a413381f48d7fd0b438c4400860ca72a7129
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 2.2744693756103516,
   "best_model_checkpoint": "dq158/pingusPongus/checkpoint-6323",
-  "epoch": 1.0,
+  "epoch": 2.0,
   "eval_steps": 500,
-  "global_step": 6323,
+  "global_step": 12646,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -98,13 +98,110 @@
       "eval_steps_per_second": 0.895,
       "eval_translation_length": 1439232,
       "step": 6323
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 6.678034646037393e-05,
+      "loss": 2.3216,
+      "step": 6500
+    },
+    {
+      "epoch": 1.11,
+      "learning_rate": 6.343059707231406e-05,
+      "loss": 2.3675,
+      "step": 7000
+    },
+    {
+      "epoch": 1.19,
+      "learning_rate": 5.995319481960425e-05,
+      "loss": 2.3563,
+      "step": 7500
+    },
+    {
+      "epoch": 1.27,
+      "learning_rate": 5.6372224671242366e-05,
+      "loss": 2.4016,
+      "step": 8000
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 5.2712488921797064e-05,
+      "loss": 2.3769,
+      "step": 8500
+    },
+    {
+      "epoch": 1.42,
+      "learning_rate": 4.899933540728503e-05,
+      "loss": 2.3531,
+      "step": 9000
+    },
+    {
+      "epoch": 1.5,
+      "learning_rate": 4.5258481942552583e-05,
+      "loss": 2.3503,
+      "step": 9500
+    },
+    {
+      "epoch": 1.58,
+      "learning_rate": 4.151583819613269e-05,
+      "loss": 2.3508,
+      "step": 10000
+    },
+    {
+      "epoch": 1.66,
+      "learning_rate": 3.779732623629695e-05,
+      "loss": 2.3509,
+      "step": 10500
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 3.412870099122515e-05,
+      "loss": 2.3825,
+      "step": 11000
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 3.0535371866810265e-05,
+      "loss": 2.3884,
+      "step": 11500
+    },
+    {
+      "epoch": 1.9,
+      "learning_rate": 2.704222675759866e-05,
+      "loss": 2.3531,
+      "step": 12000
+    },
+    {
+      "epoch": 1.98,
+      "learning_rate": 2.367345966978985e-05,
+      "loss": 2.3813,
+      "step": 12500
+    },
+    {
+      "epoch": 2.0,
+      "eval_bleu": 1.0,
+      "eval_brevity_penalty": 1.0,
+      "eval_length_ratio": 1.0,
+      "eval_loss": 2.2744693756103516,
+      "eval_precisions": [
+        1.0,
+        1.0,
+        1.0,
+        1.0
+      ],
+      "eval_reference_length": 1439232,
+      "eval_runtime": 1567.8247,
+      "eval_samples_per_second": 1.793,
+      "eval_steps_per_second": 0.897,
+      "eval_translation_length": 1439232,
+      "step": 12646
     }
   ],
   "logging_steps": 500,
   "max_steps": 18969,
   "num_train_epochs": 3,
   "save_steps": 500,
-  "total_flos": 2.1666322696686797e+17,
+  "total_flos": 4.3332645393373594e+17,
   "trial_name": null,
   "trial_params": null
 }