Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:395197e8a11c6ecb392ec1f438d8cc1dfa4d281d26ceb351f3fb3418b6cc9052
+oid sha256:9d80a6e98eda4ca4d9f9db23987f6ce6c79ea19ab61271a6dc6859cc1f197788
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:387c00b5acb837f204a8c0e90f4dc00cb5b3d8a38eccfd5c177c4a14a473faaa
+oid sha256:7797462ec399b552c2e14f711b24626e5047a84608ead61a392d4b891d0552d0
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a817696e3e030e9e334bc528014336ec49bc00a48bf738686d25918d5489ca36
+oid sha256:774e33b15e94d5e64fc6ce7060a54e786b410c4aeb3e06d7298de21e9a85bbd1
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a4fa4b91f15160ac6c4439efe323a978b3efa6861920b1e195d5f4591beb48
+oid sha256:2e2d74456691a658bf2c30bf4ecd4be778c6a42ef883fd5b5789b5b6eab4f16c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996d8dcfb55b9529987cab2bb72a1b7252bc5bca54d2a3d8ad7666bcc23ffe64
+oid sha256:dff8c125d686e292f7d1b2a015c9b2d4e77990224ab3fd6cf1d48fc2cd1d56e2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bfad5ff6f814349ff9984c036533a2506563be218f839f2433fe2e38e2b2dad9
+oid sha256:b1c515a82cac1c4a3c1a6a5f73d00a5c984cae0a039b57fc31515934d13b6aa9
 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": 1.1993739604949951,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006404560046753288,
+  "best_metric": 1.1387065649032593,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012809120093506576,
   "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": 37.954,
       "eval_steps_per_second": 9.868,
       "step": 25
+    },
+    {
+      "epoch": 0.0066607424486234195,
+      "grad_norm": 0.6878185272216797,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.7723,
+      "step": 26
+    },
+    {
+      "epoch": 0.006916924850493551,
+      "grad_norm": 1.156850814819336,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.0832,
+      "step": 27
+    },
+    {
+      "epoch": 0.007173107252363683,
+      "grad_norm": 1.2199252843856812,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.6599,
+      "step": 28
+    },
+    {
+      "epoch": 0.007429289654233814,
+      "grad_norm": 1.1851943731307983,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.2332,
+      "step": 29
+    },
+    {
+      "epoch": 0.007685472056103946,
+      "grad_norm": 1.0575395822525024,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.1859,
+      "step": 30
+    },
+    {
+      "epoch": 0.007941654457974078,
+      "grad_norm": 0.8781502842903137,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1534,
+      "step": 31
+    },
+    {
+      "epoch": 0.00819783685984421,
+      "grad_norm": 0.7835288643836975,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.0699,
+      "step": 32
+    },
+    {
+      "epoch": 0.008454019261714341,
+      "grad_norm": 0.7258645296096802,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.006,
+      "step": 33
+    },
+    {
+      "epoch": 0.008710201663584473,
+      "grad_norm": 0.5958614945411682,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.9268,
+      "step": 34
+    },
+    {
+      "epoch": 0.008966384065454604,
+      "grad_norm": 0.6093451380729675,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.8199,
+      "step": 35
+    },
+    {
+      "epoch": 0.009222566467324736,
+      "grad_norm": 0.5917091369628906,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.7703,
+      "step": 36
+    },
+    {
+      "epoch": 0.009478748869194868,
+      "grad_norm": 1.675472617149353,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.0259,
+      "step": 37
+    },
+    {
+      "epoch": 0.009734931271064999,
+      "grad_norm": 0.5305991768836975,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.6949,
+      "step": 38
+    },
+    {
+      "epoch": 0.00999111367293513,
+      "grad_norm": 0.7452951669692993,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.2857,
+      "step": 39
+    },
+    {
+      "epoch": 0.010247296074805262,
+      "grad_norm": 0.8421163558959961,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.8188,
+      "step": 40
+    },
+    {
+      "epoch": 0.010503478476675394,
+      "grad_norm": 0.8257361650466919,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3073,
+      "step": 41
+    },
+    {
+      "epoch": 0.010759660878545525,
+      "grad_norm": 0.7207552790641785,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.138,
+      "step": 42
+    },
+    {
+      "epoch": 0.011015843280415655,
+      "grad_norm": 0.6140944957733154,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1504,
+      "step": 43
+    },
+    {
+      "epoch": 0.011272025682285787,
+      "grad_norm": 0.5321956276893616,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.0165,
+      "step": 44
+    },
+    {
+      "epoch": 0.011528208084155918,
+      "grad_norm": 0.41653451323509216,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.9307,
+      "step": 45
+    },
+    {
+      "epoch": 0.01178439048602605,
+      "grad_norm": 0.396756112575531,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.9256,
+      "step": 46
+    },
+    {
+      "epoch": 0.012040572887896181,
+      "grad_norm": 0.4138922691345215,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8874,
+      "step": 47
+    },
+    {
+      "epoch": 0.012296755289766313,
+      "grad_norm": 0.45892012119293213,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.8118,
+      "step": 48
+    },
+    {
+      "epoch": 0.012552937691636444,
+      "grad_norm": 0.7600415945053101,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9194,
+      "step": 49
+    },
+    {
+      "epoch": 0.012809120093506576,
+      "grad_norm": 1.6304396390914917,
+      "learning_rate": 1e-05,
+      "loss": 0.9984,
+      "step": 50
+    },
+    {
+      "epoch": 0.012809120093506576,
+      "eval_loss": 1.1387065649032593,
+      "eval_runtime": 1.3363,
+      "eval_samples_per_second": 37.416,
+      "eval_steps_per_second": 9.728,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null