Training in progress, step 10000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e43f071cc4836a60597cf222c8478e4cd1e1111165dfb21cf6697b97c233180f
+oid sha256:0d4a84163d9e3f58c2ca6d7ae1232f180bd2352a5dd7f211bb9ecff86446527b
 size 2000137067

last-checkpoint/pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df36a6fbb124fad805fa0396d55c0b39c87ddb96291e2ba989cc66d6b6934b19
+oid sha256:d0f5499abb66ce84c1a439abb41338b00f823616fdcd09cd0b02ac791cb90e7d
 size 1002469625

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26de261b54d4d4f3a241740bf2341a65cfa642b817cbd9e14d3e07fd77f01229
+oid sha256:027bacb9a66f7124054acdc9881eec1028c531e19ceae1a2fb05ecf19f4335f1
 size 14575

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58fe3c6aa062ab01fcab2b20e4eaf1d3d1ce48b9ce3761ac8c445680169e65ca
+oid sha256:c1ae23ef329f4306e7c601317d8e62a0d9cdc03945f103aed1e4405fe8f53be5
 size 627

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 5.590496156533892,
-  "global_step": 8000,
+  "epoch": 6.988120195667365,
+  "global_step": 10000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -530,11 +530,142 @@
       "eval_samples_per_second": 3.388,
       "eval_steps_per_second": 0.425,
       "step": 8000
+    },
+    {
+      "epoch": 5.66,
+      "learning_rate": 1.8708091193562807e-05,
+      "loss": 1.0546,
+      "step": 8100
+    },
+    {
+      "epoch": 5.73,
+      "learning_rate": 1.8149307107733573e-05,
+      "loss": 1.0579,
+      "step": 8200
+    },
+    {
+      "epoch": 5.8,
+      "learning_rate": 1.7590523021904336e-05,
+      "loss": 1.0204,
+      "step": 8300
+    },
+    {
+      "epoch": 5.87,
+      "learning_rate": 1.70317389360751e-05,
+      "loss": 1.0398,
+      "step": 8400
+    },
+    {
+      "epoch": 5.94,
+      "learning_rate": 1.6472954850245866e-05,
+      "loss": 0.9992,
+      "step": 8500
+    },
+    {
+      "epoch": 6.01,
+      "learning_rate": 1.5914170764416632e-05,
+      "loss": 0.9756,
+      "step": 8600
+    },
+    {
+      "epoch": 6.08,
+      "learning_rate": 1.5355386678587395e-05,
+      "loss": 0.8385,
+      "step": 8700
+    },
+    {
+      "epoch": 6.15,
+      "learning_rate": 1.479660259275816e-05,
+      "loss": 0.8815,
+      "step": 8800
+    },
+    {
+      "epoch": 6.22,
+      "learning_rate": 1.4237818506928924e-05,
+      "loss": 0.8447,
+      "step": 8900
+    },
+    {
+      "epoch": 6.29,
+      "learning_rate": 1.3679034421099687e-05,
+      "loss": 0.8553,
+      "step": 9000
+    },
+    {
+      "epoch": 6.36,
+      "learning_rate": 1.312025033527045e-05,
+      "loss": 0.8188,
+      "step": 9100
+    },
+    {
+      "epoch": 6.43,
+      "learning_rate": 1.2561466249441217e-05,
+      "loss": 0.8241,
+      "step": 9200
+    },
+    {
+      "epoch": 6.5,
+      "learning_rate": 1.2002682163611981e-05,
+      "loss": 0.8118,
+      "step": 9300
+    },
+    {
+      "epoch": 6.57,
+      "learning_rate": 1.1443898077782746e-05,
+      "loss": 0.8357,
+      "step": 9400
+    },
+    {
+      "epoch": 6.64,
+      "learning_rate": 1.0885113991953509e-05,
+      "loss": 0.8063,
+      "step": 9500
+    },
+    {
+      "epoch": 6.71,
+      "learning_rate": 1.0326329906124274e-05,
+      "loss": 0.8263,
+      "step": 9600
+    },
+    {
+      "epoch": 6.78,
+      "learning_rate": 9.767545820295038e-06,
+      "loss": 0.8064,
+      "step": 9700
+    },
+    {
+      "epoch": 6.85,
+      "learning_rate": 9.208761734465803e-06,
+      "loss": 0.7858,
+      "step": 9800
+    },
+    {
+      "epoch": 6.92,
+      "learning_rate": 8.649977648636568e-06,
+      "loss": 0.7854,
+      "step": 9900
+    },
+    {
+      "epoch": 6.99,
+      "learning_rate": 8.09119356280733e-06,
+      "loss": 0.7765,
+      "step": 10000
+    },
+    {
+      "epoch": 6.99,
+      "eval_bleu": 74.7723,
+      "eval_em": 0.0349,
+      "eval_gen_len": 46.1685,
+      "eval_loss": 1.0809996128082275,
+      "eval_runtime": 352.8566,
+      "eval_samples_per_second": 3.415,
+      "eval_steps_per_second": 0.428,
+      "step": 10000
     }
   ],
   "max_steps": 11448,
   "num_train_epochs": 8,
-  "total_flos": 5257694441864832.0,
+  "total_flos": 6573454605451008.0,
   "trial_name": null,
   "trial_params": null
 }

pytorch_model.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df36a6fbb124fad805fa0396d55c0b39c87ddb96291e2ba989cc66d6b6934b19
+oid sha256:d0f5499abb66ce84c1a439abb41338b00f823616fdcd09cd0b02ac791cb90e7d
 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 sha256:0edc726214577185b7f744ad847d5a0a4a05b3fab28bad4d6a50d38bc569dd95
-size 22766
+oid sha256:49a5d5b48ed4e7070ca4651c54a1acddc9ff99d8b562927254692e8f85dac97b
+size 26322