Training in progress, step 8000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:291c82bc6232ac6f51e80188b84cd77a983a313d92bf22a7c53a64d81426b292
+oid sha256:dc98c7c2bc0c4206028dfacf943fe417a45fd1a4921f341f0b750bb0a800eb46
 size 1987250795

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f777049e5ab871b3886db48c6ebffe144558eff92682787173cc85ccbcf8ea13
+oid sha256:8699dfd5b9111daab2cd89fef363e56d68c96ca130d5424f6241698596430836
 size 996026489

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc17c4fc2b1e504e186ec9e5442cdf1fde30c77358b52f4d0224428846a45f14
+oid sha256:cda6569db1bc2d3d0435133aaa63d6f8465fafb2497de735ccd7d68f26426942
 size 14575

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e200bbfaad357e2ba09051b2fdad3d1bd26148492ab99f88e577528dd01de4a
+oid sha256:daae6f8fb25a77228382add9166586e74f66ba572bb14f90a533805d7d13d5a9
 size 557

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f201e9a0306165f72a8a1832852e4b1425307f8fb7530da45bd5907be85b3689
+oid sha256:cc1a99d87e2c39ac247735b2acf3b937a77d263374455fdfc4d46375e8f8af01
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 179.48717948717947,
-  "global_step": 7000,
+  "epoch": 205.12820512820514,
+  "global_step": 8000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -258,11 +258,47 @@
       "eval_samples_per_second": 2.501,
       "eval_steps_per_second": 0.318,
       "step": 7000
+    },
+    {
+      "epoch": 192.31,
+      "learning_rate": 2.1675257731958766e-05,
+      "loss": 0.0036,
+      "step": 7500
+    },
+    {
+      "epoch": 192.31,
+      "eval_bleu": 96.5899,
+      "eval_em": 0.6163,
+      "eval_gen_len": 80.7794,
+      "eval_loss": 0.2510390877723694,
+      "eval_rm": 0.7314,
+      "eval_runtime": 173.7032,
+      "eval_samples_per_second": 2.401,
+      "eval_steps_per_second": 0.305,
+      "step": 7500
+    },
+    {
+      "epoch": 205.13,
+      "learning_rate": 1.9097938144329897e-05,
+      "loss": 0.0034,
+      "step": 8000
+    },
+    {
+      "epoch": 205.13,
+      "eval_bleu": 96.4759,
+      "eval_em": 0.6331,
+      "eval_gen_len": 81.7578,
+      "eval_loss": 0.2551712095737457,
+      "eval_rm": 0.7434,
+      "eval_runtime": 170.3668,
+      "eval_samples_per_second": 2.448,
+      "eval_steps_per_second": 0.311,
+      "step": 8000
     }
   ],
   "max_steps": 11700,
   "num_train_epochs": 300,
-  "total_flos": 5576000859788544.0,
+  "total_flos": 6373629529551360.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f777049e5ab871b3886db48c6ebffe144558eff92682787173cc85ccbcf8ea13
+oid sha256:8699dfd5b9111daab2cd89fef363e56d68c96ca130d5424f6241698596430836
 size 996026489

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

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd741fca70a1d7bafcf18e68ed6c2d410f12211f78f2a6e167c6a8696c44faff
-size 17227
+oid sha256:83a0c0976b343685aea77955cc06b9e04bc75d95b3dd3fab3c2ac650bd511676
+size 18465