Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bbf174f5cd0088ee22e2323b0b3b9b0ccea2b5e8fe70d2f82cd4ee02bdf2ba0
+oid sha256:6be5269003b2f15647552613cf5d218e87dd40776823d3cf2d7a823acfe4b3f8
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5165673114daaab7fd5df3125b9ea4cca600bf1f35300adb73aec2096313b9c
+oid sha256:998e782a0ac031857b3baeaf48194c147eddc151b641493700331456b6292244
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b20243bef39a25aaba6f55738bea533875c5efdb9af55a0a7d590e2bb5f9726c
+oid sha256:fa27b0a9ea0a95aafd9b0a3b354774650fdfcd071db982d4a1e431a3cf046ffc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4378ba8c884590808e0e8bc628931de57f648d664b1a32df45558837fbde482
+oid sha256:6ca912ce3e8653b5502e54c50a0ab0aa75c1b476675011a48cc63fab76469672
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b28221c2c14a776a4080131a59077a1de3e9b24786e4fb1d485df3befa89d4ef
+oid sha256:a1a9a7d8d7a144c2ef80a066557e7f9c756c6c19ae44ea9e17f551f10e39ef07
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d3591502c4c4ba6f5cb04939f337fb40266b89401fb485c2e189f9c547a36be
+oid sha256:32df919ea4e6f6ce5e1e6b9ad3ea8b364e65bbad6eede2f82a4255fdb9969840
 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": 1.4964512586593628,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.039647140449995046,
+  "best_metric": 1.4766654968261719,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07929428089999009,
   "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": 14.654,
       "eval_steps_per_second": 3.81,
       "step": 25
+    },
+    {
+      "epoch": 0.041233026067994845,
+      "grad_norm": 0.40284931659698486,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5774,
+      "step": 26
+    },
+    {
+      "epoch": 0.042818911685994644,
+      "grad_norm": 0.38245460391044617,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.6014,
+      "step": 27
+    },
+    {
+      "epoch": 0.04440479730399445,
+      "grad_norm": 0.4388914108276367,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.597,
+      "step": 28
+    },
+    {
+      "epoch": 0.04599068292199425,
+      "grad_norm": 0.42553648352622986,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.5929,
+      "step": 29
+    },
+    {
+      "epoch": 0.047576568539994056,
+      "grad_norm": 0.4502233862876892,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.6029,
+      "step": 30
+    },
+    {
+      "epoch": 0.049162454157993855,
+      "grad_norm": 0.4477775990962982,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.6697,
+      "step": 31
+    },
+    {
+      "epoch": 0.050748339775993655,
+      "grad_norm": 0.47372493147850037,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.6562,
+      "step": 32
+    },
+    {
+      "epoch": 0.05233422539399346,
+      "grad_norm": 0.46918997168540955,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.6332,
+      "step": 33
+    },
+    {
+      "epoch": 0.05392011101199326,
+      "grad_norm": 0.4643358290195465,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.6086,
+      "step": 34
+    },
+    {
+      "epoch": 0.05550599662999306,
+      "grad_norm": 0.4862658679485321,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.6013,
+      "step": 35
+    },
+    {
+      "epoch": 0.057091882247992866,
+      "grad_norm": 0.506260871887207,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6465,
+      "step": 36
+    },
+    {
+      "epoch": 0.058677767865992665,
+      "grad_norm": 0.594947099685669,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.5712,
+      "step": 37
+    },
+    {
+      "epoch": 0.060263653483992465,
+      "grad_norm": 0.5527778267860413,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4738,
+      "step": 38
+    },
+    {
+      "epoch": 0.06184953910199227,
+      "grad_norm": 0.33043065667152405,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.5579,
+      "step": 39
+    },
+    {
+      "epoch": 0.06343542471999207,
+      "grad_norm": 0.374056875705719,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.5702,
+      "step": 40
+    },
+    {
+      "epoch": 0.06502131033799187,
+      "grad_norm": 0.36577755212783813,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.6545,
+      "step": 41
+    },
+    {
+      "epoch": 0.06660719595599167,
+      "grad_norm": 0.33573096990585327,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.6232,
+      "step": 42
+    },
+    {
+      "epoch": 0.06819308157399148,
+      "grad_norm": 0.364795058965683,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.5976,
+      "step": 43
+    },
+    {
+      "epoch": 0.06977896719199128,
+      "grad_norm": 0.40120968222618103,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.6431,
+      "step": 44
+    },
+    {
+      "epoch": 0.07136485280999108,
+      "grad_norm": 0.4092036783695221,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.6469,
+      "step": 45
+    },
+    {
+      "epoch": 0.07295073842799088,
+      "grad_norm": 0.420834481716156,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.6295,
+      "step": 46
+    },
+    {
+      "epoch": 0.07453662404599068,
+      "grad_norm": 0.4343208372592926,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.6405,
+      "step": 47
+    },
+    {
+      "epoch": 0.07612250966399048,
+      "grad_norm": 0.4775432050228119,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6059,
+      "step": 48
+    },
+    {
+      "epoch": 0.07770839528199029,
+      "grad_norm": 0.5238398313522339,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5927,
+      "step": 49
+    },
+    {
+      "epoch": 0.07929428089999009,
+      "grad_norm": 0.7994441390037537,
+      "learning_rate": 1e-05,
+      "loss": 1.4393,
+      "step": 50
+    },
+    {
+      "epoch": 0.07929428089999009,
+      "eval_loss": 1.4766654968261719,
+      "eval_runtime": 3.4247,
+      "eval_samples_per_second": 14.6,
+      "eval_steps_per_second": 3.796,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null