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:a6772bc5312a0b2967b2e45ac6386040915b340362d0408d7ccb27fc35e160f1
+oid sha256:c4087b4ebfe0a66dd5dd5c4ef5e42c769f3f92022ccc6fe4cd5b1049abf390ee
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37433d14e51cc2db595658f941a0c3f69fb44a3c8090b322935eb63df2a2fc4c
+oid sha256:b506c830402e841bd190d4fb7b5765694209306689bcda91e9be0e7dde7b5096
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa15a5cf05cdc8ab8ea4e475d09c4cd702e8add9efd40d74e05db142c973fc9c
+oid sha256:0f95a238797f03033fb1be9bbaeaf046824d52445110fbbfacb63aa2c1b64ac0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6334d05862679f958d588ef8f07e43167c072911928035e6391b3a28b430514
+oid sha256:d487b8691d0fc8a88da0c277ce1ae72a639986863644d0fffa80f5e90902b16b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df04356cb410fcc66fada0d6d306990e98d9fcfe8b1ae689099013b6c85d3851
+oid sha256:b1e5c6f0f894d25d0d01406b9fae23ae3f9de6e2761e9fdc268265858fbf1504
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0d722dc82dff4b5f58431e1ab5641ce1d710801af1b3117384aa3957ac74cae
+oid sha256:7be9c25fc5290e146259493158478d50f5115654cc4eb9b4cb1a1fc701cd10f0
 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": 0.07134973257780075,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.0526315789473684,
+  "best_metric": 0.0032391464337706566,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.1052631578947367,
   "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": 16.535,
       "eval_steps_per_second": 4.299,
       "step": 25
+    },
+    {
+      "epoch": 1.0947368421052632,
+      "grad_norm": 0.2849907875061035,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.0064,
+      "step": 26
+    },
+    {
+      "epoch": 1.1368421052631579,
+      "grad_norm": 1.011404275894165,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.0255,
+      "step": 27
+    },
+    {
+      "epoch": 1.1789473684210527,
+      "grad_norm": 2.2019524574279785,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.0276,
+      "step": 28
+    },
+    {
+      "epoch": 1.2210526315789474,
+      "grad_norm": 0.5445430278778076,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.0445,
+      "step": 29
+    },
+    {
+      "epoch": 1.263157894736842,
+      "grad_norm": 3.8727214336395264,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.0576,
+      "step": 30
+    },
+    {
+      "epoch": 1.305263157894737,
+      "grad_norm": 0.2200043797492981,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.0027,
+      "step": 31
+    },
+    {
+      "epoch": 1.3473684210526315,
+      "grad_norm": 0.5764152407646179,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.0121,
+      "step": 32
+    },
+    {
+      "epoch": 1.3894736842105262,
+      "grad_norm": 0.3320938050746918,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.0102,
+      "step": 33
+    },
+    {
+      "epoch": 1.431578947368421,
+      "grad_norm": 0.5339176654815674,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.0041,
+      "step": 34
+    },
+    {
+      "epoch": 1.4736842105263157,
+      "grad_norm": 0.9797345995903015,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.0105,
+      "step": 35
+    },
+    {
+      "epoch": 1.5157894736842106,
+      "grad_norm": 0.7296271324157715,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.0068,
+      "step": 36
+    },
+    {
+      "epoch": 1.5578947368421052,
+      "grad_norm": 0.605354368686676,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.0074,
+      "step": 37
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.6698538661003113,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.012,
+      "step": 38
+    },
+    {
+      "epoch": 1.6421052631578947,
+      "grad_norm": 5.393788814544678,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.0142,
+      "step": 39
+    },
+    {
+      "epoch": 1.6842105263157894,
+      "grad_norm": 1.3299963474273682,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.0109,
+      "step": 40
+    },
+    {
+      "epoch": 1.7263157894736842,
+      "grad_norm": 0.04660975560545921,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.0008,
+      "step": 41
+    },
+    {
+      "epoch": 1.768421052631579,
+      "grad_norm": 0.1902923732995987,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.0011,
+      "step": 42
+    },
+    {
+      "epoch": 1.8105263157894735,
+      "grad_norm": 1.5841089487075806,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.012,
+      "step": 43
+    },
+    {
+      "epoch": 1.8526315789473684,
+      "grad_norm": 3.1886465549468994,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.0083,
+      "step": 44
+    },
+    {
+      "epoch": 1.8947368421052633,
+      "grad_norm": 0.28632158041000366,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.0005,
+      "step": 45
+    },
+    {
+      "epoch": 1.936842105263158,
+      "grad_norm": 0.23157168924808502,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.002,
+      "step": 46
+    },
+    {
+      "epoch": 1.9789473684210526,
+      "grad_norm": 0.08383818715810776,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.0012,
+      "step": 47
+    },
+    {
+      "epoch": 2.0210526315789474,
+      "grad_norm": 0.062229812145233154,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.0006,
+      "step": 48
+    },
+    {
+      "epoch": 2.0631578947368423,
+      "grad_norm": 0.14913830161094666,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.001,
+      "step": 49
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "grad_norm": 0.00795549713075161,
+      "learning_rate": 1e-05,
+      "loss": 0.0002,
+      "step": 50
+    },
+    {
+      "epoch": 2.1052631578947367,
+      "eval_loss": 0.0032391464337706566,
+      "eval_runtime": 2.9882,
+      "eval_samples_per_second": 16.732,
+      "eval_steps_per_second": 4.35,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null