Training in progress, step 39, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a700b65d128f3b1e20c3095a54c2f9d85655519e101ff7588ab1befe88d83165
+oid sha256:3672a928e63f40bdaddaf2aa1e28dac494a53e1da04929a17b04aa035f52abe2
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e95bf84b2dfa2e9ec7aa80a380bdc7401012143be5935c305f79a52366a9fba6
+oid sha256:ad9cb39bfcebb327d5c5c2cfead1ad4d59d489aabccf15be29a52fa3811051b4
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e810995368afe1167633ee5494f290aa6c7eca9da3c0da6ebbb42b066addb46
+oid sha256:9f112ba0059e1e2747e6aaf6607bd2437d044c87110017bd2a6ba7d362ca7d07
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edc7eb997c4eb95725f327b37b6789ff1e532f4a96b0e99982736b781ac5ce3e
+oid sha256:b9c71761f916949d10444dde27b35ed626cd707568999b387243f471c081a7b0
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1ac0d902d43d2a3732de76d0bc067491cae6ba4322146fce57d81571ef0b8a3
+oid sha256:3cba05e3cb3b7ab2c061fae15850e3a6bad8411d48d62400a743709bbcab103a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28473748d2b42cb01c4bd78a80f1949df1bf07ecdbf043712f6ae511ed43e3f2
+oid sha256:6b456269d7a65b5f70953ed5162490c37fd66823d3b8dfaf1d06eb15b90cb5d6
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b53322a9e0770f1aa889f3dc8eda417cbde627f634c75503b1e43849ff496ab
+oid sha256:d50872ebe2ae52bfb0e335aaa2e28a3dac724479a77b01ce7ef36e8156017c85
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.2940391302108765,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 2.0291970802919708,
+  "epoch": 3.1605839416058394,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 39,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,104 @@
       "eval_samples_per_second": 51.505,
       "eval_steps_per_second": 13.391,
       "step": 25
+    },
+    {
+      "epoch": 2.1070559610705595,
+      "grad_norm": 0.4368249177932739,
+      "learning_rate": 3.474083148320469e-05,
+      "loss": 1.0774,
+      "step": 26
+    },
+    {
+      "epoch": 2.1849148418491486,
+      "grad_norm": 0.6278235912322998,
+      "learning_rate": 3.1406172239924584e-05,
+      "loss": 1.1516,
+      "step": 27
+    },
+    {
+      "epoch": 2.2627737226277373,
+      "grad_norm": 0.5482242703437805,
+      "learning_rate": 2.8241507066307104e-05,
+      "loss": 1.0975,
+      "step": 28
+    },
+    {
+      "epoch": 2.340632603406326,
+      "grad_norm": 0.45156601071357727,
+      "learning_rate": 2.5269637447446348e-05,
+      "loss": 1.0717,
+      "step": 29
+    },
+    {
+      "epoch": 2.4184914841849148,
+      "grad_norm": 0.5456267595291138,
+      "learning_rate": 2.2511975772046403e-05,
+      "loss": 1.1172,
+      "step": 30
+    },
+    {
+      "epoch": 2.4963503649635035,
+      "grad_norm": 0.5466234683990479,
+      "learning_rate": 1.9988391055670233e-05,
+      "loss": 1.1527,
+      "step": 31
+    },
+    {
+      "epoch": 2.574209245742092,
+      "grad_norm": 0.4269847571849823,
+      "learning_rate": 1.771706578402711e-05,
+      "loss": 1.0926,
+      "step": 32
+    },
+    {
+      "epoch": 2.6520681265206814,
+      "grad_norm": 0.5346320867538452,
+      "learning_rate": 1.5714364907746536e-05,
+      "loss": 1.0923,
+      "step": 33
+    },
+    {
+      "epoch": 2.72992700729927,
+      "grad_norm": 0.5671536326408386,
+      "learning_rate": 1.3994717932533891e-05,
+      "loss": 1.1694,
+      "step": 34
+    },
+    {
+      "epoch": 2.807785888077859,
+      "grad_norm": 0.4398534297943115,
+      "learning_rate": 1.257051495425121e-05,
+      "loss": 1.1125,
+      "step": 35
+    },
+    {
+      "epoch": 2.885644768856448,
+      "grad_norm": 0.560420572757721,
+      "learning_rate": 1.1452017387992552e-05,
+      "loss": 1.1148,
+      "step": 36
+    },
+    {
+      "epoch": 3.004866180048662,
+      "grad_norm": 0.9056612253189087,
+      "learning_rate": 1.064728403435312e-05,
+      "loss": 1.7632,
+      "step": 37
+    },
+    {
+      "epoch": 3.0827250608272507,
+      "grad_norm": 0.3938903212547302,
+      "learning_rate": 1.0162113015586309e-05,
+      "loss": 1.144,
+      "step": 38
+    },
+    {
+      "epoch": 3.1605839416058394,
+      "grad_norm": 0.48829081654548645,
+      "learning_rate": 1e-05,
+      "loss": 1.045,
+      "step": 39
     }
   ],
   "logging_steps": 1,
@@ -221,12 +319,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.114626154561536e+17,
+  "total_flos": 1.738816801115996e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null