Training in progress, step 43, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:742d7d6b09eceb8a893ef3294602a4da77806a229682af265a781d9889815994
+oid sha256:d7d5ff2a0d108e41ae85e53bbf492ec1fae97e2b7e8e4ead0320e0d738b36e65
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10626401a31dec3e14bcbec406942c4f7b506ba67eb2ed0a4abc533114931afb
+oid sha256:919984c149033f3f00c4e7765967ca6787445a434a522bdab8bc47faa1f48c07
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b79c9f62aea0cf629f8045d2ec1a2d01646c5e4a8b0908a6b0230435ea8cf8
+oid sha256:bf8b7fffbae8ddeeceeb24ca45900b2468ade00de804cb61c0d28fe65d3de100
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7682ca2e5172d8443dd41ac87652ff2e14caa222295c3d44aa3192d0183719a
+oid sha256:7de0e239cdfab35316002647ca38cea559a5c0ab464720a0f6b6173aa85b646e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:48055993f57d3e0e6f0ce1e486d1dc607aea07277d45b3084121da639c38928e
+oid sha256:bfd1d4c853ff82e3146ea73034c6bdc040f0852d09f4abbd792782509cc17861
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1f73e6deadf3f08547d8bef9e9b3d87995c0c2ef87d51b8801270b8b2d32ac55
+oid sha256:d9ca16dc5125aa616f8880e7477dabd4029e096d950b1e4b31474d314c00eace
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7660044150110377,
+  "epoch": 3.0375275938189845,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 43,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,132 @@
       "eval_samples_per_second": 13.815,
       "eval_steps_per_second": 3.592,
       "step": 25
+    },
+    {
+      "epoch": 1.836644591611479,
+      "grad_norm": NaN,
+      "learning_rate": 4.307583240115024e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.9072847682119205,
+      "grad_norm": NaN,
+      "learning_rate": 3.9789240471617385e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.977924944812362,
+      "grad_norm": NaN,
+      "learning_rate": 3.659191132728971e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.0485651214128033,
+      "grad_norm": NaN,
+      "learning_rate": 3.350260816694816e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.119205298013245,
+      "grad_norm": NaN,
+      "learning_rate": 3.0539460249945056e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.1898454746136866,
+      "grad_norm": NaN,
+      "learning_rate": 2.7719856506501306e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.260485651214128,
+      "grad_norm": NaN,
+      "learning_rate": 2.5060343492549566e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.3311258278145695,
+      "grad_norm": NaN,
+      "learning_rate": 2.257652828796459e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.401766004415011,
+      "grad_norm": NaN,
+      "learning_rate": 2.0282986908012567e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.4724061810154527,
+      "grad_norm": NaN,
+      "learning_rate": 1.819317876549771e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.543046357615894,
+      "grad_norm": NaN,
+      "learning_rate": 1.631936768557596e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.6136865342163356,
+      "grad_norm": NaN,
+      "learning_rate": 1.4672549936752506e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.684326710816777,
+      "grad_norm": NaN,
+      "learning_rate": 1.3262389700405744e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.7549668874172184,
+      "grad_norm": NaN,
+      "learning_rate": 1.2097162357528127e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.8256070640176603,
+      "grad_norm": NaN,
+      "learning_rate": 1.1183705925499948e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.8962472406181017,
+      "grad_norm": NaN,
+      "learning_rate": 1.0527380929884324e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.966887417218543,
+      "grad_norm": NaN,
+      "learning_rate": 1.013203894673168e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 3.0375275938189845,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 43
     }
   ],
   "logging_steps": 1,
@@ -221,12 +347,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.066827840159744e+17,
+  "total_flos": 5.2513569876895334e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null