Training in progress, step 6000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae77720e1818a27b6a9d1bf027bb69d7b2e7f500fbf351920139668fa47ffb64
+oid sha256:7dc14a418d59224cba58e564b6d6eef9aa9100a97c4b5e0ac5c3cbc885eaf925
 size 1987250795

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8aa78251192c63956f122fee22f86d3fe3bdeda45f4ee2f11eac1a80940a4f
+oid sha256:bcb324ae10c9946ff9ef4af6f63f22b2dd06013b12fa4e88d3618c532cbf3f06
 size 996026489

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:442af02c48ce7f9c1cc09c783e67ec45c7ceeceeaadc16593b03427291d80a41
+oid sha256:8236b1efeea9a0cb188d1516c456991f957b0cd275f7723797fadddb72ce7a7a
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b7708e7360ae5d9dfbc21f14bae0f24f4e0ee89da5d58b4c05796253aac585a
+oid sha256:9ca778e3dad5cb50f422990d67ea86870f277935e7ee0e0941e09a709f60546d
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fde6704b17d2f8f73cbac6618d35712dcd4a3a65703f80f1300df08d82a783f6
+oid sha256:92153a01a9bc6795849b819ba557c141c4265ba3ff9cfeb2e9038a64ec17c505
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 150.0,
-  "global_step": 3000,
+  "epoch": 300.0,
+  "global_step": 6000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,11 +60,65 @@
       "eval_samples_per_second": 3.668,
       "eval_steps_per_second": 0.237,
       "step": 3000
+    },
+    {
+      "epoch": 200.0,
+      "learning_rate": 2.50625e-05,
+      "loss": 0.0086,
+      "step": 4000
+    },
+    {
+      "epoch": 200.0,
+      "eval_bleu": 95.5885,
+      "eval_em": 0.5803,
+      "eval_gen_len": 80.6978,
+      "eval_loss": 0.40772923827171326,
+      "eval_rm": 0.6283,
+      "eval_runtime": 118.0147,
+      "eval_samples_per_second": 3.533,
+      "eval_steps_per_second": 0.229,
+      "step": 4000
+    },
+    {
+      "epoch": 250.0,
+      "learning_rate": 1.2562499999999999e-05,
+      "loss": 0.0051,
+      "step": 5000
+    },
+    {
+      "epoch": 250.0,
+      "eval_bleu": 95.5923,
+      "eval_em": 0.6019,
+      "eval_gen_len": 80.6523,
+      "eval_loss": 0.41692906618118286,
+      "eval_rm": 0.6523,
+      "eval_runtime": 120.2437,
+      "eval_samples_per_second": 3.468,
+      "eval_steps_per_second": 0.225,
+      "step": 5000
+    },
+    {
+      "epoch": 300.0,
+      "learning_rate": 6.250000000000001e-08,
+      "loss": 0.0038,
+      "step": 6000
+    },
+    {
+      "epoch": 300.0,
+      "eval_bleu": 95.481,
+      "eval_em": 0.6019,
+      "eval_gen_len": 80.4676,
+      "eval_loss": 0.42530182003974915,
+      "eval_rm": 0.6547,
+      "eval_runtime": 133.449,
+      "eval_samples_per_second": 3.125,
+      "eval_steps_per_second": 0.202,
+      "step": 6000
     }
   ],
   "max_steps": 6000,
   "num_train_epochs": 300,
-  "total_flos": 5067042185682432.0,
+  "total_flos": 1.014399554069376e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6d8aa78251192c63956f122fee22f86d3fe3bdeda45f4ee2f11eac1a80940a4f
+oid sha256:bcb324ae10c9946ff9ef4af6f63f22b2dd06013b12fa4e88d3618c532cbf3f06
 size 996026489

runs/May24_08-16-03_555aebd6415b/events.out.tfevents.1684916185.555aebd6415b.20495.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9c66795b241c4e02cad73b3534d69dc437dc71b61058db346aee1fcac8f8009
-size 10421
+oid sha256:f2a18636c33728d779873fe4ff60ce1d282acf6f14be5b3378c3077e3bc8ff02
+size 12278