Training in progress, step 44, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:340b2b10c22e3995a9b132c6f57c1465c35e2ff07055d0400e58880a63cd1d11
+oid sha256:d6052209711a9243be66ea7b0d917a4daf3e51c35359e6160239b491762afa1c
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:122e1a6acbc93d423a7bc332e8bb3fb110862f67e4a15d622dccf471a8b0d722
+oid sha256:763c7de0af5d693ecd7cddbd5c310f0b87d0043cfcb1fc1278628bebf6747ef4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a4944bab1f5943276d3cf1017e47d2fb167e6b7d5b5dea3d433ee04e45cc4b
+oid sha256:0dd0b3896279d68111a5822eb5a6f7141e66013dd54ae562835b4a9cf52d3969
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69a75fe6f36911ad471534effdd12f2fdabf964f3752ba50726c39a5af55d76f
+oid sha256:84d611e29cf65aa06a958fbddc8c682964d345609422c92cf6c12455e06a8be9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9024cb3b2751112ca8a017ce216bd38dfd6b001366e375907d3b845a68681cd2
+oid sha256:469bedeab97fe5ea2d97b11c4f0c2157961302f0ff0122b425d6ad2be85a6430
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1229ee494750fdca01199e7b17f6407ce48ff55604d2cd9d7a7582776cffc192
+oid sha256:eba890d5c37511d983154de0f89f465e597822376430ed595af6f919e721806d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.7278617710583153,
+  "epoch": 3.041036717062635,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 44,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,139 @@
       "eval_samples_per_second": 24.973,
       "eval_steps_per_second": 6.493,
       "step": 25
+    },
+    {
+      "epoch": 1.7969762419006479,
+      "grad_norm": NaN,
+      "learning_rate": 4.498655797196586e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.8660907127429804,
+      "grad_norm": NaN,
+      "learning_rate": 4.173601715150931e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.935205183585313,
+      "grad_norm": NaN,
+      "learning_rate": 3.8559653903512224e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 2.0043196544276456,
+      "grad_norm": NaN,
+      "learning_rate": 3.547523173970989e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 2.0734341252699786,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.142548596112311,
+      "grad_norm": NaN,
+      "learning_rate": 2.9650597387137014e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.2116630669546438,
+      "grad_norm": NaN,
+      "learning_rate": 2.6942958916356998e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.2807775377969763,
+      "grad_norm": NaN,
+      "learning_rate": 2.4392226800308622e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.349892008639309,
+      "grad_norm": NaN,
+      "learning_rate": 2.2012665767657826e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.4190064794816415,
+      "grad_norm": NaN,
+      "learning_rate": 1.981758328893866e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.488120950323974,
+      "grad_norm": NaN,
+      "learning_rate": 1.781925515578024e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.5572354211663066,
+      "grad_norm": NaN,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.626349892008639,
+      "grad_norm": NaN,
+      "learning_rate": 1.4456400944391146e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.695464362850972,
+      "grad_norm": NaN,
+      "learning_rate": 1.3110681311010814e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.7645788336933044,
+      "grad_norm": NaN,
+      "learning_rate": 1.1999223739623667e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.833693304535637,
+      "grad_norm": NaN,
+      "learning_rate": 1.1128243951817937e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.90280777537797,
+      "grad_norm": NaN,
+      "learning_rate": 1.0502612819869217e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.971922246220302,
+      "grad_norm": NaN,
+      "learning_rate": 1.0125829126846895e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 3.041036717062635,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 44
     }
   ],
   "logging_steps": 1,
@@ -221,12 +354,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.29768176943104e+16,
+  "total_flos": 9.32391991419863e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null