Training in progress, step 30000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec7b974441388e888eea61e7fc83f2d3e64adf3ed37f00d4fb6d4a12ace19f6a
+oid sha256:d4afd9e96e30c55033c81d663e123112d0e4b940b7f531817870755548ffc840
 size 768843213

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd8a34ddf7e38c5080236a7687e8e63c25b944dd9f3f12d8b4325f57006b1cd
+oid sha256:3f4a64d6d78c9e8abfcc625bc8b4d39d5db180f7cd080685979599555a6e56ae
 size 384848389

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1a48af60df70a0fc5925076ff66d31b72fa2e72742c28160990b6bda9ee1664
-size 14567
+oid sha256:5623ef7e3da407c88d16106413c2f65b14dd4d4f8687ed1b55a66b25ce1d7ead
+size 14503

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0242c88e90c1ded6be60df7d6726df86d88437c186b98d9835e9f7ca644d21
+oid sha256:76cc3bd636dff666d4435d9a1314227eb29c1052699611f59040a24a461e1e87
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f185139787c577b5818236290c3f10307b8aa66ac5cf8699f48ca0065a085bfb
+oid sha256:9a35f16b3d3457db09b7df4283c2d03aee6146b79859cc29b3b18a6fd7d571b9
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 1.786511835640911,
-  "global_step": 20000,
+  "epoch": 2.6797677534613666,
+  "global_step": 30000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -266,11 +266,141 @@
       "eval_samples_per_second": 15.432,
       "eval_steps_per_second": 0.966,
       "step": 20000
+    },
+    {
+      "epoch": 1.83,
+      "learning_rate": 6.339855266684536e-05,
+      "loss": 0.7469,
+      "step": 20500
+    },
+    {
+      "epoch": 1.88,
+      "learning_rate": 6.250692397033861e-05,
+      "loss": 0.7497,
+      "step": 21000
+    },
+    {
+      "epoch": 1.92,
+      "learning_rate": 6.161350844277674e-05,
+      "loss": 0.7361,
+      "step": 21500
+    },
+    {
+      "epoch": 1.97,
+      "learning_rate": 6.0720092915214864e-05,
+      "loss": 0.7278,
+      "step": 22000
+    },
+    {
+      "epoch": 2.01,
+      "learning_rate": 5.9826677387652995e-05,
+      "loss": 0.7232,
+      "step": 22500
+    },
+    {
+      "epoch": 2.05,
+      "learning_rate": 5.8933261860091126e-05,
+      "loss": 0.6626,
+      "step": 23000
+    },
+    {
+      "epoch": 2.1,
+      "learning_rate": 5.8041633163584383e-05,
+      "loss": 0.672,
+      "step": 23500
+    },
+    {
+      "epoch": 2.14,
+      "learning_rate": 5.7148217636022514e-05,
+      "loss": 0.6616,
+      "step": 24000
+    },
+    {
+      "epoch": 2.19,
+      "learning_rate": 5.6254802108460645e-05,
+      "loss": 0.6631,
+      "step": 24500
+    },
+    {
+      "epoch": 2.23,
+      "learning_rate": 5.5361386580898776e-05,
+      "loss": 0.6686,
+      "step": 25000
+    },
+    {
+      "epoch": 2.28,
+      "learning_rate": 5.446797105333691e-05,
+      "loss": 0.6583,
+      "step": 25500
+    },
+    {
+      "epoch": 2.32,
+      "learning_rate": 5.3576342356830165e-05,
+      "loss": 0.6431,
+      "step": 26000
+    },
+    {
+      "epoch": 2.37,
+      "learning_rate": 5.2682926829268296e-05,
+      "loss": 0.6527,
+      "step": 26500
+    },
+    {
+      "epoch": 2.41,
+      "learning_rate": 5.178951130170643e-05,
+      "loss": 0.6501,
+      "step": 27000
+    },
+    {
+      "epoch": 2.46,
+      "learning_rate": 5.089609577414456e-05,
+      "loss": 0.6493,
+      "step": 27500
+    },
+    {
+      "epoch": 2.5,
+      "learning_rate": 5.000446707763781e-05,
+      "loss": 0.6406,
+      "step": 28000
+    },
+    {
+      "epoch": 2.55,
+      "learning_rate": 4.911105155007594e-05,
+      "loss": 0.6358,
+      "step": 28500
+    },
+    {
+      "epoch": 2.59,
+      "learning_rate": 4.821763602251407e-05,
+      "loss": 0.649,
+      "step": 29000
+    },
+    {
+      "epoch": 2.64,
+      "learning_rate": 4.73242204949522e-05,
+      "loss": 0.6325,
+      "step": 29500
+    },
+    {
+      "epoch": 2.68,
+      "learning_rate": 4.643080496739033e-05,
+      "loss": 0.6385,
+      "step": 30000
+    },
+    {
+      "epoch": 2.68,
+      "eval_bleu": 25.9878,
+      "eval_gen_len": 43.5751,
+      "eval_loss": 0.7514618635177612,
+      "eval_runtime": 558.5823,
+      "eval_samples_per_second": 15.987,
+      "eval_steps_per_second": 1.001,
+      "step": 30000
     }
   ],
   "max_steps": 55975,
   "num_train_epochs": 5,
-  "total_flos": 2.1694343383351296e+16,
+  "total_flos": 3.254120998974259e+16,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd8a34ddf7e38c5080236a7687e8e63c25b944dd9f3f12d8b4325f57006b1cd
+oid sha256:3f4a64d6d78c9e8abfcc625bc8b4d39d5db180f7cd080685979599555a6e56ae
 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:f8aee400640f7abb63237ec03c78a54989a6e18f43aa762814fde4984193e3b0
-size 11226
+oid sha256:48e3d31ad4549eee77407d5cc929647b4822156841d65e92f5b1d81339bf4a79
+size 14803