Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:592668e882920d9c1f761f2ba56aa69733200a22ad3f5fc9018c9b676ca15fe7
+oid sha256:fb782d12ac3d4d76b3621da097373b976fb1901b53c9430aac0a3875483a900f
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0a0f860573121c71a9cf6982b517d0db9a3834eba50fa9602c5a9dd61b25c3ec
+oid sha256:a2f70e641f4d4d24771ed150e62287a6548c74e505ae3d784019d100c0553df9
 size 180543866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7ecf97d70428997efc51416d5b74ae0dc007b554d82c8c66bf57d6eb7b32370d
+oid sha256:9c0da6843130971b3a57dd8ffdc640e79c099c3e1d21cebf4537b79ce673abae
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a01a250a153c407e11881852b5dc5e7098f2e327fd6d898a76d14de5c3eae299
+oid sha256:71bbc9e6272609e3c9feb6c6b297524be71a44a1ad007e44dd24febb990bd913
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e0554ddfb4b36f1b2cac14945bacae8c1c0c45b2059bdc7430915ca2636e061
+oid sha256:a297722fa3850c0ceb5b16f58e25cfd578f315986d43943ffd9c906e187f772d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:899ce5f4405500a02279df61d878e69f76bce31cb7b97f4916c1cd4c6640c83a
+oid sha256:378133a322d3424b206f5c264534c1a2fe78b8664265361238e016079613ca7e
 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": 2.1376192569732666,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.024792363951902815,
+  "best_metric": 2.11165714263916,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.04958472790380563,
   "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": 44.466,
       "eval_steps_per_second": 11.561,
       "step": 25
+    },
+    {
+      "epoch": 0.025784058509978926,
+      "grad_norm": 0.6506301164627075,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.1492,
+      "step": 26
+    },
+    {
+      "epoch": 0.02677575306805504,
+      "grad_norm": 0.6272109746932983,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.1375,
+      "step": 27
+    },
+    {
+      "epoch": 0.02776744762613115,
+      "grad_norm": 0.5856204628944397,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0767,
+      "step": 28
+    },
+    {
+      "epoch": 0.028759142184207265,
+      "grad_norm": 0.603814423084259,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.1341,
+      "step": 29
+    },
+    {
+      "epoch": 0.029750836742283376,
+      "grad_norm": 0.6377735137939453,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 2.0204,
+      "step": 30
+    },
+    {
+      "epoch": 0.03074253130035949,
+      "grad_norm": 0.6095825433731079,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0747,
+      "step": 31
+    },
+    {
+      "epoch": 0.031734225858435605,
+      "grad_norm": 0.5862390398979187,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.0728,
+      "step": 32
+    },
+    {
+      "epoch": 0.03272592041651171,
+      "grad_norm": 0.5877420902252197,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.1091,
+      "step": 33
+    },
+    {
+      "epoch": 0.03371761497458783,
+      "grad_norm": 0.5727083683013916,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9683,
+      "step": 34
+    },
+    {
+      "epoch": 0.03470930953266394,
+      "grad_norm": 0.5779207944869995,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.084,
+      "step": 35
+    },
+    {
+      "epoch": 0.03570100409074005,
+      "grad_norm": 0.6393936276435852,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.1341,
+      "step": 36
+    },
+    {
+      "epoch": 0.03669269864881616,
+      "grad_norm": 0.6033120155334473,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 2.0806,
+      "step": 37
+    },
+    {
+      "epoch": 0.03768439320689228,
+      "grad_norm": 0.6125691533088684,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.2096,
+      "step": 38
+    },
+    {
+      "epoch": 0.03867608776496839,
+      "grad_norm": 0.6041589379310608,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.1368,
+      "step": 39
+    },
+    {
+      "epoch": 0.0396677823230445,
+      "grad_norm": 0.601218581199646,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.1579,
+      "step": 40
+    },
+    {
+      "epoch": 0.040659476881120614,
+      "grad_norm": 0.588674008846283,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 2.064,
+      "step": 41
+    },
+    {
+      "epoch": 0.04165117143919673,
+      "grad_norm": 0.5896679162979126,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.0999,
+      "step": 42
+    },
+    {
+      "epoch": 0.04264286599727284,
+      "grad_norm": 0.6175012588500977,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.0315,
+      "step": 43
+    },
+    {
+      "epoch": 0.04363456055534895,
+      "grad_norm": 0.6025582551956177,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.0327,
+      "step": 44
+    },
+    {
+      "epoch": 0.044626255113425065,
+      "grad_norm": 0.5947927236557007,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.0573,
+      "step": 45
+    },
+    {
+      "epoch": 0.04561794967150118,
+      "grad_norm": 0.6009608507156372,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.1075,
+      "step": 46
+    },
+    {
+      "epoch": 0.04660964422957729,
+      "grad_norm": 0.5778355598449707,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.0815,
+      "step": 47
+    },
+    {
+      "epoch": 0.0476013387876534,
+      "grad_norm": 0.6041818857192993,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.1687,
+      "step": 48
+    },
+    {
+      "epoch": 0.048593033345729515,
+      "grad_norm": 0.6211597323417664,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.2201,
+      "step": 49
+    },
+    {
+      "epoch": 0.04958472790380563,
+      "grad_norm": 0.6282414793968201,
+      "learning_rate": 1e-05,
+      "loss": 2.0931,
+      "step": 50
+    },
+    {
+      "epoch": 0.04958472790380563,
+      "eval_loss": 2.11165714263916,
+      "eval_runtime": 1.1461,
+      "eval_samples_per_second": 43.626,
+      "eval_steps_per_second": 11.343,
+      "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": 3.91521434075136e+16,
+  "total_flos": 7.83042868150272e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null