Training in progress, step 47, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49f0c05ffffc02a951d07fccabfd90c7c8e73142c7127ce688a420a9431c0d84
+oid sha256:a1c08849e362b1d282ca53c8281b901939e0edb23ea1f28a6b2d70b1eac8e7bf
 size 478528978

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef51191c6606c1f0969bbb13366a160c1a0d9d8e0eff567627c3108d804a0563
+oid sha256:704821269782b402bb653005eb9ccb266686cd23f608b2944fbb637e5287da64
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea931368d0e77445ed59ef67db514d328b4a2efd70f23f857f9a58364168abb5
+oid sha256:62bf17a35cb6e5dacab0d9c9ed5d52702a16b48ad95791e62c0f4a56b05ae6a5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bd97c860dedc4403280c178486ce9a92d0dd85f3683ae1396c200bcda87e02b
+oid sha256:b68255f54d9670a52c2161626f2cb21f3ebe202049ecc5c1d736aac09de48740
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb6c0abd1048971e0da5fb8d74654492657b7d58f790fe62b17239239c11dc98
+oid sha256:19840a58a8ba0b2b8873b5499612ebc723330bed7ef07e600fcf9f721bfd3c9d
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a25230216c7a49e9024a60f6b2ba44b71176046374fb4d551a7f778d26456d
+oid sha256:0450ceb846581ea6cc2effaa1b64a4cf3fc14799532fcc3c887a5695b8adb55d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.6161616161616161,
+  "epoch": 3.0383838383838384,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 47,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,160 @@
       "eval_samples_per_second": 16.258,
       "eval_steps_per_second": 4.227,
       "step": 25
+    },
+    {
+      "epoch": 1.680808080808081,
+      "grad_norm": NaN,
+      "learning_rate": 5.0296219152955604e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 1.7454545454545456,
+      "grad_norm": NaN,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 1.8101010101010102,
+      "grad_norm": NaN,
+      "learning_rate": 4.411351469801496e-05,
+      "loss": 0.0,
+      "step": 28
+    },
+    {
+      "epoch": 1.8747474747474748,
+      "grad_norm": NaN,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": NaN,
+      "learning_rate": 3.814270329628396e-05,
+      "loss": 0.0,
+      "step": 30
+    },
+    {
+      "epoch": 2.004040404040404,
+      "grad_norm": NaN,
+      "learning_rate": 3.5273298394491515e-05,
+      "loss": 0.0,
+      "step": 31
+    },
+    {
+      "epoch": 2.0686868686868687,
+      "grad_norm": NaN,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0,
+      "step": 32
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": NaN,
+      "learning_rate": 2.98363193438164e-05,
+      "loss": 0.0,
+      "step": 33
+    },
+    {
+      "epoch": 2.197979797979798,
+      "grad_norm": NaN,
+      "learning_rate": 2.729523361034538e-05,
+      "loss": 0.0,
+      "step": 34
+    },
+    {
+      "epoch": 2.2626262626262625,
+      "grad_norm": NaN,
+      "learning_rate": 2.4889122713851394e-05,
+      "loss": 0.0,
+      "step": 35
+    },
+    {
+      "epoch": 2.327272727272727,
+      "grad_norm": NaN,
+      "learning_rate": 2.2629708984760708e-05,
+      "loss": 0.0,
+      "step": 36
+    },
+    {
+      "epoch": 2.391919191919192,
+      "grad_norm": NaN,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 0.0,
+      "step": 37
+    },
+    {
+      "epoch": 2.4565656565656564,
+      "grad_norm": NaN,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 0.0,
+      "step": 38
+    },
+    {
+      "epoch": 2.5212121212121215,
+      "grad_norm": NaN,
+      "learning_rate": 1.6837835672960835e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 2.5858585858585856,
+      "grad_norm": NaN,
+      "learning_rate": 1.526735832134829e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 2.6505050505050507,
+      "grad_norm": NaN,
+      "learning_rate": 1.389045440608296e-05,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 2.7151515151515153,
+      "grad_norm": NaN,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 2.77979797979798,
+      "grad_norm": NaN,
+      "learning_rate": 1.174322368277565e-05,
+      "loss": 0.0,
+      "step": 43
+    },
+    {
+      "epoch": 2.8444444444444446,
+      "grad_norm": NaN,
+      "learning_rate": 1.0983357966978745e-05,
+      "loss": 0.0,
+      "step": 44
+    },
+    {
+      "epoch": 2.909090909090909,
+      "grad_norm": NaN,
+      "learning_rate": 1.0437936906629336e-05,
+      "loss": 0.0,
+      "step": 45
+    },
+    {
+      "epoch": 2.973737373737374,
+      "grad_norm": NaN,
+      "learning_rate": 1.0109617738307912e-05,
+      "loss": 0.0,
+      "step": 46
+    },
+    {
+      "epoch": 3.0383838383838384,
+      "grad_norm": NaN,
+      "learning_rate": 1e-05,
+      "loss": 0.0,
+      "step": 47
     }
   ],
   "logging_steps": 1,
@@ -221,12 +375,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.487279663087616e+17,
+  "total_flos": 2.796085766604718e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null