Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9ba0ffb27c3ee97c16157432056f7b224669b1b7dac23f66fbad27ead115bb1
+oid sha256:c93e50e08c01575207d3df1824da9fafba7229987c7c42d0309e4b5a03447af5
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afcba4ad9183b29a2f1f9361f36e62c2841eba5c1d167237e6ec926b19fd761c
+oid sha256:aeab663ef89814eaa94787d4d966ff62528ba4552632a08745b4d6fef73e84e8
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e38f4863187cee4f4946335561242e6304b4d97bc3ea28e117ef62897dd2360
+oid sha256:db0ed6aa900dcd74a06c1c728a6d3b4129c2c024e67dd7a690b7ee047a7a97cc
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd3b6d61a4bd82d4236b02dc65c20a512b7c28117f6748d5943a301ef6d463c7
+oid sha256:749b0300fd68753158e63d740b0709b1c99e84525c6667c54b93f69d5c04e6c8
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0854b62d67d8a5f83079ff08e2b33cfe019b7eb9bbf830699132abf51f1d0923
+oid sha256:2b0f1dec1ee0c0ad8989683a6968ada651879e714271bf20ad4050a09bbd3bc7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82176713d3a23af93357b0b9e4a6a944f50fad91c947f6995b0415301bdd20ec
+oid sha256:1ab9ac6a716e1187fb599551ad9748d175e54ba09f059fed69a8036c0dcc5e25
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.3901463747024536,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10045203415369161,
+  "best_metric": 0.3419298231601715,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.20090406830738322,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,189 @@
       "eval_samples_per_second": 28.557,
       "eval_steps_per_second": 7.425,
       "step": 25
+    },
+    {
+      "epoch": 0.10447011551983927,
+      "grad_norm": 173.174072265625,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 14.3707,
+      "step": 26
+    },
+    {
+      "epoch": 0.10848819688598695,
+      "grad_norm": 147.3890380859375,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 11.0976,
+      "step": 27
+    },
+    {
+      "epoch": 0.1125062782521346,
+      "grad_norm": 114.66434478759766,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 9.7754,
+      "step": 28
+    },
+    {
+      "epoch": 0.11652435961828227,
+      "grad_norm": 78.83654022216797,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 5.5902,
+      "step": 29
+    },
+    {
+      "epoch": 0.12054244098442994,
+      "grad_norm": 31.42974090576172,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.6766,
+      "step": 30
+    },
+    {
+      "epoch": 0.1245605223505776,
+      "grad_norm": 38.81559371948242,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.143,
+      "step": 31
+    },
+    {
+      "epoch": 0.12857860371672528,
+      "grad_norm": 60.23033142089844,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.8414,
+      "step": 32
+    },
+    {
+      "epoch": 0.13259668508287292,
+      "grad_norm": 35.685691833496094,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.1602,
+      "step": 33
+    },
+    {
+      "epoch": 0.1366147664490206,
+      "grad_norm": 34.83101272583008,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.1482,
+      "step": 34
+    },
+    {
+      "epoch": 0.14063284781516824,
+      "grad_norm": 14.176968574523926,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.5788,
+      "step": 35
+    },
+    {
+      "epoch": 0.14465092918131592,
+      "grad_norm": 25.032855987548828,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.0398,
+      "step": 36
+    },
+    {
+      "epoch": 0.1486690105474636,
+      "grad_norm": 12.065668106079102,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.62,
+      "step": 37
+    },
+    {
+      "epoch": 0.15268709191361124,
+      "grad_norm": 44.62394714355469,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.2944,
+      "step": 38
+    },
+    {
+      "epoch": 0.1567051732797589,
+      "grad_norm": 71.64360809326172,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.0688,
+      "step": 39
+    },
+    {
+      "epoch": 0.1607232546459066,
+      "grad_norm": 58.64244079589844,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.0727,
+      "step": 40
+    },
+    {
+      "epoch": 0.16474133601205423,
+      "grad_norm": 92.85259246826172,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.1197,
+      "step": 41
+    },
+    {
+      "epoch": 0.1687594173782019,
+      "grad_norm": 80.76541137695312,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 5.2377,
+      "step": 42
+    },
+    {
+      "epoch": 0.17277749874434958,
+      "grad_norm": 63.15403747558594,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.6449,
+      "step": 43
+    },
+    {
+      "epoch": 0.17679558011049723,
+      "grad_norm": 66.09992980957031,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.4156,
+      "step": 44
+    },
+    {
+      "epoch": 0.1808136614766449,
+      "grad_norm": 36.22022247314453,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.6311,
+      "step": 45
+    },
+    {
+      "epoch": 0.18483174284279258,
+      "grad_norm": 56.1572265625,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.4557,
+      "step": 46
+    },
+    {
+      "epoch": 0.18884982420894023,
+      "grad_norm": 35.4969482421875,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.9909,
+      "step": 47
+    },
+    {
+      "epoch": 0.1928679055750879,
+      "grad_norm": 28.917226791381836,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.7636,
+      "step": 48
+    },
+    {
+      "epoch": 0.19688598694123555,
+      "grad_norm": 49.72064971923828,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.4829,
+      "step": 49
+    },
+    {
+      "epoch": 0.20090406830738322,
+      "grad_norm": 85.38445281982422,
+      "learning_rate": 1e-05,
+      "loss": 3.6811,
+      "step": 50
+    },
+    {
+      "epoch": 0.20090406830738322,
+      "eval_loss": 0.3419298231601715,
+      "eval_runtime": 1.7502,
+      "eval_samples_per_second": 28.569,
+      "eval_steps_per_second": 7.428,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null