Training in progress, step 20000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a36b8300d1efed86c6cc8fb68ca4b8652d3bf07567b89b6c33af4b5f60f5304
+oid sha256:ec7b974441388e888eea61e7fc83f2d3e64adf3ed37f00d4fb6d4a12ace19f6a
 size 768843213

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667fc042b1654ba63be98142339f82e2d9ced5a682e237a00651e87d9529cdde
+oid sha256:0cd8a34ddf7e38c5080236a7687e8e63c25b944dd9f3f12d8b4325f57006b1cd
 size 384848389

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:04fd57acfc1796a4a73b883b65812353a1d9ef39b1a9eca84abd70bc2800b465
-size 14503
+oid sha256:d1a48af60df70a0fc5925076ff66d31b72fa2e72742c28160990b6bda9ee1664
+size 14567

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7edce77d6edc3d0cefec8d66d191dbe596742f200664a33c2d45656329643a47
+oid sha256:2b0242c88e90c1ded6be60df7d6726df86d88437c186b98d9835e9f7ca644d21
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f07aaae1ee1a8d1345b09c237d52be9808364382f9ab7825d7d6baa44aac78
+oid sha256:f185139787c577b5818236290c3f10307b8aa66ac5cf8699f48ca0065a085bfb
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.8932559178204555,
-  "global_step": 10000,
+  "epoch": 1.786511835640911,
+  "global_step": 20000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -136,11 +136,141 @@
       "eval_samples_per_second": 13.043,
       "eval_steps_per_second": 0.816,
       "step": 10000
+    },
+    {
+      "epoch": 0.94,
+      "learning_rate": 8.126328955597249e-05,
+      "loss": 0.9619,
+      "step": 10500
+    },
+    {
+      "epoch": 0.98,
+      "learning_rate": 8.036987402841062e-05,
+      "loss": 0.9549,
+      "step": 11000
+    },
+    {
+      "epoch": 1.03,
+      "learning_rate": 7.947645850084875e-05,
+      "loss": 0.9069,
+      "step": 11500
+    },
+    {
+      "epoch": 1.07,
+      "learning_rate": 7.858304297328688e-05,
+      "loss": 0.8864,
+      "step": 12000
+    },
+    {
+      "epoch": 1.12,
+      "learning_rate": 7.768962744572501e-05,
+      "loss": 0.8692,
+      "step": 12500
+    },
+    {
+      "epoch": 1.16,
+      "learning_rate": 7.679799874921827e-05,
+      "loss": 0.8603,
+      "step": 13000
+    },
+    {
+      "epoch": 1.21,
+      "learning_rate": 7.59045832216564e-05,
+      "loss": 0.8496,
+      "step": 13500
+    },
+    {
+      "epoch": 1.25,
+      "learning_rate": 7.501116769409454e-05,
+      "loss": 0.8412,
+      "step": 14000
+    },
+    {
+      "epoch": 1.3,
+      "learning_rate": 7.411775216653267e-05,
+      "loss": 0.8436,
+      "step": 14500
+    },
+    {
+      "epoch": 1.34,
+      "learning_rate": 7.32243366389708e-05,
+      "loss": 0.8297,
+      "step": 15000
+    },
+    {
+      "epoch": 1.38,
+      "learning_rate": 7.233092111140893e-05,
+      "loss": 0.811,
+      "step": 15500
+    },
+    {
+      "epoch": 1.43,
+      "learning_rate": 7.143750558384706e-05,
+      "loss": 0.8057,
+      "step": 16000
+    },
+    {
+      "epoch": 1.47,
+      "learning_rate": 7.05458768873403e-05,
+      "loss": 0.8113,
+      "step": 16500
+    },
+    {
+      "epoch": 1.52,
+      "learning_rate": 6.965246135977843e-05,
+      "loss": 0.8007,
+      "step": 17000
+    },
+    {
+      "epoch": 1.56,
+      "learning_rate": 6.875904583221656e-05,
+      "loss": 0.7831,
+      "step": 17500
+    },
+    {
+      "epoch": 1.61,
+      "learning_rate": 6.786563030465469e-05,
+      "loss": 0.7916,
+      "step": 18000
+    },
+    {
+      "epoch": 1.65,
+      "learning_rate": 6.697221477709283e-05,
+      "loss": 0.7687,
+      "step": 18500
+    },
+    {
+      "epoch": 1.7,
+      "learning_rate": 6.607879924953097e-05,
+      "loss": 0.7655,
+      "step": 19000
+    },
+    {
+      "epoch": 1.74,
+      "learning_rate": 6.51853837219691e-05,
+      "loss": 0.7576,
+      "step": 19500
+    },
+    {
+      "epoch": 1.79,
+      "learning_rate": 6.429196819440723e-05,
+      "loss": 0.7576,
+      "step": 20000
+    },
+    {
+      "epoch": 1.79,
+      "eval_bleu": 22.8022,
+      "eval_gen_len": 43.8515,
+      "eval_loss": 0.833698570728302,
+      "eval_runtime": 578.6578,
+      "eval_samples_per_second": 15.432,
+      "eval_steps_per_second": 0.966,
+      "step": 20000
     }
   ],
   "max_steps": 55975,
   "num_train_epochs": 5,
-  "total_flos": 1.084747677696e+16,
+  "total_flos": 2.1694343383351296e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:667fc042b1654ba63be98142339f82e2d9ced5a682e237a00651e87d9529cdde
+oid sha256:0cd8a34ddf7e38c5080236a7687e8e63c25b944dd9f3f12d8b4325f57006b1cd
 size 384848389

runs/Apr02_22-09-40_2ea1649bbc44/events.out.tfevents.1680473399.2ea1649bbc44.981.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2443cae59216eaf5f4a0e87e066b8f9a5fccbfa06c2217efd71f4a53e8022ca
-size 7685
+oid sha256:f8aee400640f7abb63237ec03c78a54989a6e18f43aa762814fde4984193e3b0
+size 11226