Training in progress, step 95, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b9e6029b8e20ffea46f0a63f305f8a19b4b8d4c222505c00dd1756a2c05e327
+oid sha256:719fcb5c9db18237bd1dc22a5c30e434288dbf398d2e0596edeace2933d22427
 size 237402

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c5ac99cd1c2daa03a4004e768b1475426edc7b4b4d2c5f4eaebb8ae60fbdc45c
+oid sha256:0eb5b2c377a3c356f094f68d42270bee4cc35d70c7af5b5d48e4f8c53670c64b
 size 222294

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd119cfb8d5f79126ee024c0402e15266cdde51590656c9bfff6d4c1906f5f2
+oid sha256:d1198b041f02130d25891e82e3bfff2efce248c2f44a5246eec91fc96c7a38f9
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bcdfaa06a050154a02b7db40937ce5ed5fadd7e1cdcda101cef6fda76cd4aa3b
+oid sha256:9021567b3ca7affc6bb82b67aa17648ec2ce8c44a9b4c1f5f01d2dacf89c9b13
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f1dce42a6c12395909ff288b85ec6528b48ce766f999f9454df6e9b03a18ef1d
+oid sha256:6d3b5b6efd5f70e44b3ddc68874b355dd85d3e12fa484eab5e8800b612717e68
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05d6bba347f596d22ebf95e8935e06faf3787342cd6c72879bba6c7d46f04e1a
+oid sha256:5b6783182f0ea3ea6ac751b0318d93d4953b4ecbb0e620c4e3ce3ecebfdcde32
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
+oid sha256:1fd9769bcb04586b7ead175b588f12a0bbbeba72d5f308b868ba8f36b77aa801
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 6.879824638366699,
   "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.03702104029123218,
+  "epoch": 0.04689331770222743,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 95,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,146 @@
       "eval_samples_per_second": 663.996,
       "eval_steps_per_second": 172.639,
       "step": 75
+    },
+    {
+      "epoch": 0.03751465416178194,
+      "grad_norm": 0.12949536740779877,
+      "learning_rate": 1.91437699862843e-05,
+      "loss": 6.8888,
+      "step": 76
+    },
+    {
+      "epoch": 0.03800826803233171,
+      "grad_norm": 0.122923344373703,
+      "learning_rate": 1.8236354814530112e-05,
+      "loss": 6.8853,
+      "step": 77
+    },
+    {
+      "epoch": 0.03850188190288147,
+      "grad_norm": 0.1295005977153778,
+      "learning_rate": 1.7371804408538024e-05,
+      "loss": 6.8858,
+      "step": 78
+    },
+    {
+      "epoch": 0.038995495773431234,
+      "grad_norm": 0.11691726744174957,
+      "learning_rate": 1.6551126795408016e-05,
+      "loss": 6.8864,
+      "step": 79
+    },
+    {
+      "epoch": 0.039489109643980995,
+      "grad_norm": 0.1165173351764679,
+      "learning_rate": 1.577527884852619e-05,
+      "loss": 6.8828,
+      "step": 80
+    },
+    {
+      "epoch": 0.039982723514530756,
+      "grad_norm": 0.1302141696214676,
+      "learning_rate": 1.5045165171893116e-05,
+      "loss": 6.8843,
+      "step": 81
+    },
+    {
+      "epoch": 0.040476337385080524,
+      "grad_norm": 0.12200380116701126,
+      "learning_rate": 1.4361637045396029e-05,
+      "loss": 6.8813,
+      "step": 82
+    },
+    {
+      "epoch": 0.040969951255630285,
+      "grad_norm": 0.12973135709762573,
+      "learning_rate": 1.3725491432254624e-05,
+      "loss": 6.8809,
+      "step": 83
+    },
+    {
+      "epoch": 0.041463565126180046,
+      "grad_norm": 0.12173114717006683,
+      "learning_rate": 1.313747004979751e-05,
+      "loss": 6.8837,
+      "step": 84
+    },
+    {
+      "epoch": 0.04195717899672981,
+      "grad_norm": 0.10662299394607544,
+      "learning_rate": 1.2598258504653081e-05,
+      "loss": 6.8864,
+      "step": 85
+    },
+    {
+      "epoch": 0.04245079286727957,
+      "grad_norm": 0.11969508230686188,
+      "learning_rate": 1.2108485493362765e-05,
+      "loss": 6.8813,
+      "step": 86
+    },
+    {
+      "epoch": 0.04294440673782933,
+      "grad_norm": 0.11755706369876862,
+      "learning_rate": 1.1668722069349041e-05,
+      "loss": 6.8826,
+      "step": 87
+    },
+    {
+      "epoch": 0.0434380206083791,
+      "grad_norm": 0.11743596196174622,
+      "learning_rate": 1.1279480977092635e-05,
+      "loss": 6.8882,
+      "step": 88
+    },
+    {
+      "epoch": 0.04393163447892886,
+      "grad_norm": 0.11842235922813416,
+      "learning_rate": 1.094121605429547e-05,
+      "loss": 6.8884,
+      "step": 89
+    },
+    {
+      "epoch": 0.04442524834947862,
+      "grad_norm": 0.1109689399600029,
+      "learning_rate": 1.0654321702726141e-05,
+      "loss": 6.8836,
+      "step": 90
+    },
+    {
+      "epoch": 0.04491886222002838,
+      "grad_norm": 0.10875685513019562,
+      "learning_rate": 1.0419132428365116e-05,
+      "loss": 6.8867,
+      "step": 91
+    },
+    {
+      "epoch": 0.04541247609057814,
+      "grad_norm": 0.11175169795751572,
+      "learning_rate": 1.0235922451385733e-05,
+      "loss": 6.8833,
+      "step": 92
+    },
+    {
+      "epoch": 0.04590608996112791,
+      "grad_norm": 0.10757743567228317,
+      "learning_rate": 1.0104905386425733e-05,
+      "loss": 6.8826,
+      "step": 93
+    },
+    {
+      "epoch": 0.04639970383167767,
+      "grad_norm": 0.10695550590753555,
+      "learning_rate": 1.002623399352217e-05,
+      "loss": 6.8832,
+      "step": 94
+    },
+    {
+      "epoch": 0.04689331770222743,
+      "grad_norm": 0.1099054366350174,
+      "learning_rate": 1e-05,
+      "loss": 6.8866,
+      "step": 95
     }
   ],
   "logging_steps": 1,
@@ -587,12 +727,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8558936064000.0,
+  "total_flos": 10841319014400.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null