Training in progress, step 1000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5db93d5bbd8ee27e2c605f26462c67689729477710806611d40989d1ddbb37ce
+oid sha256:79e2574ceb1e47f09e9d94af457fc609f2c413e78f5e145a26a3989b86caee9b
 size 1987250795

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11df0d0c28ede32fdd87d0e229340412effcbdcc37f4f2fdafd317639cb64c01
+oid sha256:e34238f0fcbf478a47d0c3cbc8202b1324526156425444a8e5bbb1e0600b7397
 size 996026489

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5af12890d72958474f59e2a6e38aefa8b12d58cc605376a65f0760cdf419671
+oid sha256:abbaf7bb5d4b6e1adc859aa780e92889e11df327b3419e8ae89360d9806fa799
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7708e7360ae5d9dfbc21f14bae0f24f4e0ee89da5d58b4c05796253aac585a
+oid sha256:5477cf1aa2d17968d104d1bcb25665280e729d92cb7a986c7fb18a35fab276e8
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025d4a6a1771d5d78df663db14260a7e4dac96d458cc7cf3490ace1f7cc857e7
+oid sha256:cf87ddda7572b37a559a6d8c1e13c8d6c7fdccde84c44b7bca91dc3f42335c54
 size 627

last-checkpoint/trainer_state.json

@@ -1,124 +1,52 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.92307692307692,
-  "global_step": 3000,
+  "epoch": 25.641025641025642,
+  "global_step": 1000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
   "log_history": [
     {
-      "epoch": 25.0,
+      "epoch": 12.82,
       "learning_rate": 1.2375000000000001e-05,
-      "loss": 4.997,
+      "loss": 5.1115,
       "step": 500
     },
     {
-      "epoch": 25.0,
-      "eval_bleu": 55.7784,
+      "epoch": 12.82,
+      "eval_bleu": 55.8418,
       "eval_em": 0.0,
-      "eval_gen_len": 83.1007,
-      "eval_loss": 1.7169510126113892,
+      "eval_gen_len": 78.6043,
+      "eval_loss": 1.7833343744277954,
       "eval_rm": 0.0,
-      "eval_runtime": 251.4041,
-      "eval_samples_per_second": 1.659,
-      "eval_steps_per_second": 0.211,
+      "eval_runtime": 216.1632,
+      "eval_samples_per_second": 1.929,
+      "eval_steps_per_second": 0.245,
       "step": 500
     },
     {
-      "epoch": 50.0,
+      "epoch": 25.64,
       "learning_rate": 2.4875e-05,
-      "loss": 0.8348,
+      "loss": 0.8877,
       "step": 1000
     },
     {
-      "epoch": 50.0,
-      "eval_bleu": 92.3851,
-      "eval_em": 0.2086,
-      "eval_gen_len": 79.1127,
-      "eval_loss": 0.2999931573867798,
-      "eval_rm": 0.2182,
-      "eval_runtime": 201.8913,
-      "eval_samples_per_second": 2.065,
-      "eval_steps_per_second": 0.263,
+      "epoch": 25.64,
+      "eval_bleu": 88.9639,
+      "eval_em": 0.2062,
+      "eval_gen_len": 77.9976,
+      "eval_loss": 0.3478254973888397,
+      "eval_rm": 0.2158,
+      "eval_runtime": 173.1336,
+      "eval_samples_per_second": 2.409,
+      "eval_steps_per_second": 0.306,
       "step": 1000
-    },
-    {
-      "epoch": 38.46,
-      "learning_rate": 3.737500000000001e-05,
-      "loss": 0.0966,
-      "step": 1500
-    },
-    {
-      "epoch": 38.46,
-      "eval_bleu": 95.4441,
-      "eval_em": 0.3669,
-      "eval_gen_len": 81.6475,
-      "eval_loss": 0.21956025063991547,
-      "eval_rm": 0.4484,
-      "eval_runtime": 168.3123,
-      "eval_samples_per_second": 2.478,
-      "eval_steps_per_second": 0.315,
-      "step": 1500
-    },
-    {
-      "epoch": 51.28,
-      "learning_rate": 4.9875000000000006e-05,
-      "loss": 0.0406,
-      "step": 2000
-    },
-    {
-      "epoch": 51.28,
-      "eval_bleu": 96.0687,
-      "eval_em": 0.5108,
-      "eval_gen_len": 80.777,
-      "eval_loss": 0.21358482539653778,
-      "eval_rm": 0.5947,
-      "eval_runtime": 167.4281,
-      "eval_samples_per_second": 2.491,
-      "eval_steps_per_second": 0.317,
-      "step": 2000
-    },
-    {
-      "epoch": 64.1,
-      "learning_rate": 4.7448453608247423e-05,
-      "loss": 0.0266,
-      "step": 2500
-    },
-    {
-      "epoch": 64.1,
-      "eval_bleu": 96.1601,
-      "eval_em": 0.5516,
-      "eval_gen_len": 80.3981,
-      "eval_loss": 0.21729224920272827,
-      "eval_rm": 0.6211,
-      "eval_runtime": 165.3475,
-      "eval_samples_per_second": 2.522,
-      "eval_steps_per_second": 0.321,
-      "step": 2500
-    },
-    {
-      "epoch": 76.92,
-      "learning_rate": 4.487113402061856e-05,
-      "loss": 0.0191,
-      "step": 3000
-    },
-    {
-      "epoch": 76.92,
-      "eval_bleu": 96.1309,
-      "eval_em": 0.5444,
-      "eval_gen_len": 81.693,
-      "eval_loss": 0.22468438744544983,
-      "eval_rm": 0.6427,
-      "eval_runtime": 164.8881,
-      "eval_samples_per_second": 2.529,
-      "eval_steps_per_second": 0.321,
-      "step": 3000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 3282494931353088.0,
+  "total_flos": 797954568947712.0,
   "trial_name": null,
   "trial_params": null
 }

last-checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb7cbf69764be856cace1d69d8021e6c2300e10ccc26fbc78c609f8368570b4
+oid sha256:16b1498745616fbf0a4cd4c1b6cf32468b15b936a8b11b56029767534510acd1
 size 4155

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:11df0d0c28ede32fdd87d0e229340412effcbdcc37f4f2fdafd317639cb64c01
+oid sha256:e34238f0fcbf478a47d0c3cbc8202b1324526156425444a8e5bbb1e0600b7397
 size 996026489

runs/May25_07-14-58_27b5c1724d9c/1684999636.9758022/events.out.tfevents.1684999636.27b5c1724d9c.3103.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa3ffb36e6fe621d6d1e0eb8045396f42daa6775c1179dc8e481fbc23b703553
+size 6253

runs/May25_07-14-58_27b5c1724d9c/events.out.tfevents.1684999636.27b5c1724d9c.3103.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2f970e17ae6a60954fd8227a20af3157dc7af8494257e8e6a72addb9a4c985e
+size 9799

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bb7cbf69764be856cace1d69d8021e6c2300e10ccc26fbc78c609f8368570b4
+oid sha256:16b1498745616fbf0a4cd4c1b6cf32468b15b936a8b11b56029767534510acd1
 size 4155