Training in progress, step 4000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:95248b59e7dac0d789b6b077fbe09ce5175324e63b5e9cdd37a3a30c2cde9027
+oid sha256:4f8804038bfc8c4fff09781205b46f28d914f21115e30a8813fb451cdb64ad17
 size 2000137067

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4238518d766751ead10635c197669c039a8c46869571a7f8fc96716f256600df
+oid sha256:6ccb2c6910f34be7a138f85235698d8f0ec58283fab1416ef6a153c170b333ed
 size 1002469625

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda8e14cf65113c4145f87b0ecbda755c0d32ab5bbb56548e3c45d7ecd14a2c9
+oid sha256:047a205ba65d4143fae2458ea498dbf8e5a685cd3e2e670c6951c8a299de8ae5
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c68e8f52d353c005549c69e33b5a29ace5f59d7300d7ea3a17b4a529d455d0
+oid sha256:5789a0b7645be9b850d95a6b32fdc2dd662d33e25aea9a3e9fcb4a7309e592af
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.397624039133473,
-  "global_step": 2000,
+  "epoch": 2.795248078266946,
+  "global_step": 4000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -137,11 +137,142 @@
       "eval_samples_per_second": 0.751,
       "eval_steps_per_second": 0.094,
       "step": 2000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 4.2e-05,
+      "loss": 6.2524,
+      "step": 2100
+    },
+    {
+      "epoch": 1.54,
+      "learning_rate": 4.4000000000000006e-05,
+      "loss": 5.8029,
+      "step": 2200
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 4.600000000000001e-05,
+      "loss": 5.606,
+      "step": 2300
+    },
+    {
+      "epoch": 1.68,
+      "learning_rate": 4.8e-05,
+      "loss": 5.3757,
+      "step": 2400
+    },
+    {
+      "epoch": 1.75,
+      "learning_rate": 5e-05,
+      "loss": 5.1043,
+      "step": 2500
+    },
+    {
+      "epoch": 1.82,
+      "learning_rate": 4.944121591417077e-05,
+      "loss": 4.9414,
+      "step": 2600
+    },
+    {
+      "epoch": 1.89,
+      "learning_rate": 4.888243182834153e-05,
+      "loss": 4.7381,
+      "step": 2700
+    },
+    {
+      "epoch": 1.96,
+      "learning_rate": 4.8323647742512295e-05,
+      "loss": 4.6214,
+      "step": 2800
+    },
+    {
+      "epoch": 2.03,
+      "learning_rate": 4.776486365668306e-05,
+      "loss": 4.2971,
+      "step": 2900
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 4.720607957085382e-05,
+      "loss": 4.1602,
+      "step": 3000
+    },
+    {
+      "epoch": 2.17,
+      "learning_rate": 4.664729548502459e-05,
+      "loss": 4.0391,
+      "step": 3100
+    },
+    {
+      "epoch": 2.24,
+      "learning_rate": 4.6088511399195353e-05,
+      "loss": 3.9211,
+      "step": 3200
+    },
+    {
+      "epoch": 2.31,
+      "learning_rate": 4.552972731336611e-05,
+      "loss": 3.7642,
+      "step": 3300
+    },
+    {
+      "epoch": 2.38,
+      "learning_rate": 4.497094322753688e-05,
+      "loss": 3.6698,
+      "step": 3400
+    },
+    {
+      "epoch": 2.45,
+      "learning_rate": 4.4412159141707646e-05,
+      "loss": 3.5409,
+      "step": 3500
+    },
+    {
+      "epoch": 2.52,
+      "learning_rate": 4.385337505587841e-05,
+      "loss": 3.4016,
+      "step": 3600
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.329459097004918e-05,
+      "loss": 3.2761,
+      "step": 3700
+    },
+    {
+      "epoch": 2.66,
+      "learning_rate": 4.2735806884219945e-05,
+      "loss": 3.1708,
+      "step": 3800
+    },
+    {
+      "epoch": 2.73,
+      "learning_rate": 4.2177022798390704e-05,
+      "loss": 3.0849,
+      "step": 3900
+    },
+    {
+      "epoch": 2.8,
+      "learning_rate": 4.161823871256147e-05,
+      "loss": 3.0222,
+      "step": 4000
+    },
+    {
+      "epoch": 2.8,
+      "eval_bleu": 27.8543,
+      "eval_em": 0.0,
+      "eval_gen_len": 36.8,
+      "eval_loss": 2.8796441555023193,
+      "eval_runtime": 501.7382,
+      "eval_samples_per_second": 2.402,
+      "eval_steps_per_second": 0.301,
+      "step": 4000
     }
   ],
   "max_steps": 11448,
   "num_train_epochs": 8,
-  "total_flos": 1328908826910720.0,
+  "total_flos": 2632028349156096.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4238518d766751ead10635c197669c039a8c46869571a7f8fc96716f256600df
+oid sha256:6ccb2c6910f34be7a138f85235698d8f0ec58283fab1416ef6a153c170b333ed
 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 sha256:098e0e6b4e1c013ebd1598cfcedd0c3450868df3bf0b760afd29eede229bcb12
-size 12098
+oid sha256:bbc2bf10f2e8697285e6c7d205571262251279a84d779b5e1565cd93e4f856da
+size 15654