Training in progress, step 8000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:546cd4e7ec947305a665edaa2e582e225d7b8301eaa78f72956ea9b0b6882be6
+oid sha256:e43f071cc4836a60597cf222c8478e4cd1e1111165dfb21cf6697b97c233180f
 size 2000137067

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938f724c0f91c737457d75986a81bb14510b0f67d394e6715914ee6427257f11
+oid sha256:df36a6fbb124fad805fa0396d55c0b39c87ddb96291e2ba989cc66d6b6934b19
 size 1002469625

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db097afe89ed3c3eb23a6fe209105077506d8139157678f90acd89f98273927d
+oid sha256:26de261b54d4d4f3a241740bf2341a65cfa642b817cbd9e14d3e07fd77f01229
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ace18575c64fb9061a4bdb4187294f04e31e9a65a2e4da680ca78aeef9f963e2
+oid sha256:58fe3c6aa062ab01fcab2b20e4eaf1d3d1ce48b9ce3761ac8c445680169e65ca
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 4.1928721174004195,
-  "global_step": 6000,
+  "epoch": 5.590496156533892,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -399,11 +399,142 @@
       "eval_samples_per_second": 2.847,
       "eval_steps_per_second": 0.357,
       "step": 6000
+    },
+    {
+      "epoch": 4.26,
+      "learning_rate": 2.9883772910147524e-05,
+      "loss": 1.5968,
+      "step": 6100
+    },
+    {
+      "epoch": 4.33,
+      "learning_rate": 2.9324988824318283e-05,
+      "loss": 1.5813,
+      "step": 6200
+    },
+    {
+      "epoch": 4.4,
+      "learning_rate": 2.876620473848905e-05,
+      "loss": 1.5421,
+      "step": 6300
+    },
+    {
+      "epoch": 4.47,
+      "learning_rate": 2.8207420652659816e-05,
+      "loss": 1.4852,
+      "step": 6400
+    },
+    {
+      "epoch": 4.54,
+      "learning_rate": 2.7648636566830576e-05,
+      "loss": 1.5027,
+      "step": 6500
+    },
+    {
+      "epoch": 4.61,
+      "learning_rate": 2.7089852481001342e-05,
+      "loss": 1.4951,
+      "step": 6600
+    },
+    {
+      "epoch": 4.68,
+      "learning_rate": 2.653106839517211e-05,
+      "loss": 1.4803,
+      "step": 6700
+    },
+    {
+      "epoch": 4.75,
+      "learning_rate": 2.597228430934287e-05,
+      "loss": 1.4127,
+      "step": 6800
+    },
+    {
+      "epoch": 4.82,
+      "learning_rate": 2.5413500223513638e-05,
+      "loss": 1.3896,
+      "step": 6900
+    },
+    {
+      "epoch": 4.89,
+      "learning_rate": 2.48547161376844e-05,
+      "loss": 1.3656,
+      "step": 7000
+    },
+    {
+      "epoch": 4.96,
+      "learning_rate": 2.4295932051855164e-05,
+      "loss": 1.3432,
+      "step": 7100
+    },
+    {
+      "epoch": 5.03,
+      "learning_rate": 2.373714796602593e-05,
+      "loss": 1.2224,
+      "step": 7200
+    },
+    {
+      "epoch": 5.1,
+      "learning_rate": 2.3178363880196693e-05,
+      "loss": 1.1396,
+      "step": 7300
+    },
+    {
+      "epoch": 5.17,
+      "learning_rate": 2.2619579794367456e-05,
+      "loss": 1.1475,
+      "step": 7400
+    },
+    {
+      "epoch": 5.24,
+      "learning_rate": 2.206079570853822e-05,
+      "loss": 1.0669,
+      "step": 7500
+    },
+    {
+      "epoch": 5.31,
+      "learning_rate": 2.1502011622708985e-05,
+      "loss": 1.1356,
+      "step": 7600
+    },
+    {
+      "epoch": 5.38,
+      "learning_rate": 2.0943227536879752e-05,
+      "loss": 1.0965,
+      "step": 7700
+    },
+    {
+      "epoch": 5.45,
+      "learning_rate": 2.0384443451050515e-05,
+      "loss": 1.1086,
+      "step": 7800
+    },
+    {
+      "epoch": 5.52,
+      "learning_rate": 1.982565936522128e-05,
+      "loss": 1.0642,
+      "step": 7900
+    },
+    {
+      "epoch": 5.59,
+      "learning_rate": 1.9266875279392044e-05,
+      "loss": 1.0717,
+      "step": 8000
+    },
+    {
+      "epoch": 5.59,
+      "eval_bleu": 69.9606,
+      "eval_em": 0.0199,
+      "eval_gen_len": 46.0722,
+      "eval_loss": 1.26251220703125,
+      "eval_runtime": 355.6397,
+      "eval_samples_per_second": 3.388,
+      "eval_steps_per_second": 0.425,
+      "step": 8000
     }
   ],
   "max_steps": 11448,
   "num_train_epochs": 8,
-  "total_flos": 3958404255138432.0,
+  "total_flos": 5257694441864832.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:938f724c0f91c737457d75986a81bb14510b0f67d394e6715914ee6427257f11
+oid sha256:df36a6fbb124fad805fa0396d55c0b39c87ddb96291e2ba989cc66d6b6934b19
 size 1002469625

runs/Jun05_10-45-59_0a95bf9de5ac/events.out.tfevents.1685962630.0a95bf9de5ac.3272.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a959ff46eca4f3545c8c05e80af7a2fe5e478b7b3102f1f41ccc3cfcf54b040
-size 19210
+oid sha256:0edc726214577185b7f744ad847d5a0a4a05b3fab28bad4d6a50d38bc569dd95
+size 22766