Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88bfb3ebc2a0a8193913920d8a6ce33bc55fc9e6b0152b9f43b59099a4f2d35a
+oid sha256:da23a2b435007538e65fa4fcabf9a2035f17fcd175ac9292d967e03fd3ab7145
 size 2436967616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01c313f8c0eac026d9858e47f211775461defc0d54c19bc0684bcb39d7a8d8cd
+oid sha256:15857b0a03f5603b8cc2b289c15a86e499a891c33595d66e736c9c46a26f44b3
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d85c13420b6d30e05846bbe22764a7889bd9486ccf06064adf83080b7a2f62d
+oid sha256:1769c9faf492b0198f5342faaa44873580364c51dbd8f57c9ad6e267b9fda96a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fd9995bfa9a6183dc2ffa6a8ac43bc591583df50c0a22b52e8ab18989a3a87d
+oid sha256:234656f8bd8a7454d20ba2b4b8b3fb5225dd2130e84125c1ba779f5a8d08c437
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ada4ceab2c4a36188e52ba0d75550b4fb6d2fb21b35f8862af293c4f15d12463
+oid sha256:d95a4b18111b2fd52c397bc5ac520c8f2fbc1aa91ffca0ad3e51daba6ecea7f7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70b63afd93d505f47f09dfce1e60c55156c91aa2d285423f9fb4240cbc01a9a9
+oid sha256:760648db164ce809c771a5b8dfefb9356fe8916322d91e9ec799be3defe97433
 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": 0.4663977026939392,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.5296367112810707,
+  "best_metric": 0.45020294189453125,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 3.0592734225621414,
   "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": 13.053,
       "eval_steps_per_second": 3.394,
       "step": 25
+    },
+    {
+      "epoch": 1.5908221797323137,
+      "grad_norm": 0.1691490262746811,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.4589,
+      "step": 26
+    },
+    {
+      "epoch": 1.6520076481835564,
+      "grad_norm": 0.15722176432609558,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.3106,
+      "step": 27
+    },
+    {
+      "epoch": 1.7131931166347991,
+      "grad_norm": 0.2748729884624481,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.5667,
+      "step": 28
+    },
+    {
+      "epoch": 1.774378585086042,
+      "grad_norm": 0.20471762120723724,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.8172,
+      "step": 29
+    },
+    {
+      "epoch": 1.835564053537285,
+      "grad_norm": 0.12656819820404053,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.4779,
+      "step": 30
+    },
+    {
+      "epoch": 1.8967495219885278,
+      "grad_norm": 0.1545308381319046,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.3229,
+      "step": 31
+    },
+    {
+      "epoch": 1.9579349904397705,
+      "grad_norm": 0.28750380873680115,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6275,
+      "step": 32
+    },
+    {
+      "epoch": 2.019120458891013,
+      "grad_norm": 0.33765679597854614,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.1463,
+      "step": 33
+    },
+    {
+      "epoch": 2.0803059273422564,
+      "grad_norm": 0.13991977274417877,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.6376,
+      "step": 34
+    },
+    {
+      "epoch": 2.141491395793499,
+      "grad_norm": 0.13830013573169708,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.3475,
+      "step": 35
+    },
+    {
+      "epoch": 2.202676864244742,
+      "grad_norm": 0.19515806436538696,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.4098,
+      "step": 36
+    },
+    {
+      "epoch": 2.2638623326959846,
+      "grad_norm": 0.22438541054725647,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.6891,
+      "step": 37
+    },
+    {
+      "epoch": 2.3250478011472273,
+      "grad_norm": 0.13861946761608124,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6306,
+      "step": 38
+    },
+    {
+      "epoch": 2.3862332695984705,
+      "grad_norm": 0.15394841134548187,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.4031,
+      "step": 39
+    },
+    {
+      "epoch": 2.447418738049713,
+      "grad_norm": 0.1811305582523346,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4764,
+      "step": 40
+    },
+    {
+      "epoch": 2.508604206500956,
+      "grad_norm": 0.20983630418777466,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7532,
+      "step": 41
+    },
+    {
+      "epoch": 2.569789674952199,
+      "grad_norm": 0.13580162823200226,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6098,
+      "step": 42
+    },
+    {
+      "epoch": 2.6309751434034414,
+      "grad_norm": 0.13629181683063507,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3037,
+      "step": 43
+    },
+    {
+      "epoch": 2.6921606118546846,
+      "grad_norm": 0.1759355366230011,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.4198,
+      "step": 44
+    },
+    {
+      "epoch": 2.7533460803059273,
+      "grad_norm": 0.20882584154605865,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7149,
+      "step": 45
+    },
+    {
+      "epoch": 2.81453154875717,
+      "grad_norm": 0.13564932346343994,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6719,
+      "step": 46
+    },
+    {
+      "epoch": 2.875717017208413,
+      "grad_norm": 0.12577201426029205,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.3369,
+      "step": 47
+    },
+    {
+      "epoch": 2.936902485659656,
+      "grad_norm": 0.18013103306293488,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4247,
+      "step": 48
+    },
+    {
+      "epoch": 2.9980879541108987,
+      "grad_norm": 0.3251934349536896,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.9791,
+      "step": 49
+    },
+    {
+      "epoch": 3.0592734225621414,
+      "grad_norm": 0.14723213016986847,
+      "learning_rate": 1e-05,
+      "loss": 0.7412,
+      "step": 50
+    },
+    {
+      "epoch": 3.0592734225621414,
+      "eval_loss": 0.45020294189453125,
+      "eval_runtime": 3.8089,
+      "eval_samples_per_second": 13.127,
+      "eval_steps_per_second": 3.413,
+      "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": 2.989638494642504e+17,
+  "total_flos": 5.981142014408786e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null