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:ecb65415b98403d2137f96cc8d322a5bef8eb10a7141cee87034fc911ac27935
+oid sha256:409583193766c9ce089aeaddab16aa566e7b44979d8ca8bcd723ca733ccbc013
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be6622ae88a661430f7e82080f79febd80b7e60908e721669c16191354fd5ccc
+oid sha256:49effa0d477cd4ee320f47e88adf1fd0f48eb7a3bbd30f32e5d8d4c2d53587bc
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4454a5dc6f4d0e0c5ed8a56d320d38614d9df5049e347ecad7fb074c8d036f
+oid sha256:215705b831ef00b0daf0627f5cb6347d808c62aa6fab8f4aaabd7912af383ee4
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f966d2db0226a4a727cbb853af54ecf82b3d132bb26c483ca71f875a007827d1
+oid sha256:72c238e814f4d6087f52333c4fa1852e369c5cf1b950dc262220796bef0518f2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30a3c6c72055ef8ac691ad058649b2ade8e51650e307a53a7a459c56c0c9dd87
+oid sha256:4a7938bb4b2862e74651436d3d35a93abcac23c24fd9624048168fd43e21e013
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c0eae0bab78602ffbbc100cee7170defccc56243a5fb8936470b9fdf5b40f3d0
+oid sha256:8f4441c6869802c83292f990c09653e7ef71b02a4130694d915161f6e0d3d81c
 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": 3.6986312866210938,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0035167153878277687,
+  "best_metric": 3.585186243057251,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.007033430775655537,
   "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": 11.568,
       "eval_steps_per_second": 3.008,
       "step": 25
+    },
+    {
+      "epoch": 0.0036573840033408797,
+      "grad_norm": 0.6881301403045654,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.8389,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037980526188539903,
+      "grad_norm": 0.792911171913147,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.5026,
+      "step": 27
+    },
+    {
+      "epoch": 0.003938721234367101,
+      "grad_norm": 0.8642730116844177,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.9211,
+      "step": 28
+    },
+    {
+      "epoch": 0.0040793898498802115,
+      "grad_norm": 1.2017244100570679,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.4445,
+      "step": 29
+    },
+    {
+      "epoch": 0.0042200584653933225,
+      "grad_norm": 1.1826562881469727,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.6573,
+      "step": 30
+    },
+    {
+      "epoch": 0.0043607270809064335,
+      "grad_norm": 1.3540639877319336,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.7198,
+      "step": 31
+    },
+    {
+      "epoch": 0.0045013956964195445,
+      "grad_norm": 1.3807733058929443,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.6719,
+      "step": 32
+    },
+    {
+      "epoch": 0.004642064311932655,
+      "grad_norm": 1.3128817081451416,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.7725,
+      "step": 33
+    },
+    {
+      "epoch": 0.004782732927445766,
+      "grad_norm": 1.4953864812850952,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.7893,
+      "step": 34
+    },
+    {
+      "epoch": 0.004923401542958877,
+      "grad_norm": 1.6556501388549805,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.9066,
+      "step": 35
+    },
+    {
+      "epoch": 0.005064070158471987,
+      "grad_norm": 1.7631824016571045,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 4.0591,
+      "step": 36
+    },
+    {
+      "epoch": 0.005204738773985098,
+      "grad_norm": 2.5257699489593506,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.4642,
+      "step": 37
+    },
+    {
+      "epoch": 0.005345407389498209,
+      "grad_norm": 0.6542789936065674,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.8916,
+      "step": 38
+    },
+    {
+      "epoch": 0.00548607600501132,
+      "grad_norm": 0.5933400392532349,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 2.3769,
+      "step": 39
+    },
+    {
+      "epoch": 0.00562674462052443,
+      "grad_norm": 0.7565528154373169,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.7812,
+      "step": 40
+    },
+    {
+      "epoch": 0.005767413236037541,
+      "grad_norm": 0.8536903858184814,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.0485,
+      "step": 41
+    },
+    {
+      "epoch": 0.005908081851550652,
+      "grad_norm": 0.993644654750824,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.5119,
+      "step": 42
+    },
+    {
+      "epoch": 0.006048750467063762,
+      "grad_norm": 1.0827058553695679,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.5816,
+      "step": 43
+    },
+    {
+      "epoch": 0.006189419082576873,
+      "grad_norm": 1.3338035345077515,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.7165,
+      "step": 44
+    },
+    {
+      "epoch": 0.006330087698089984,
+      "grad_norm": 1.4324630498886108,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.7711,
+      "step": 45
+    },
+    {
+      "epoch": 0.006470756313603095,
+      "grad_norm": 1.5651832818984985,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.6286,
+      "step": 46
+    },
+    {
+      "epoch": 0.006611424929116205,
+      "grad_norm": 1.6895540952682495,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.5996,
+      "step": 47
+    },
+    {
+      "epoch": 0.006752093544629316,
+      "grad_norm": 2.1800448894500732,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.9122,
+      "step": 48
+    },
+    {
+      "epoch": 0.006892762160142427,
+      "grad_norm": 2.110852003097534,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.0356,
+      "step": 49
+    },
+    {
+      "epoch": 0.007033430775655537,
+      "grad_norm": 3.81133770942688,
+      "learning_rate": 1e-05,
+      "loss": 4.6192,
+      "step": 50
+    },
+    {
+      "epoch": 0.007033430775655537,
+      "eval_loss": 3.585186243057251,
+      "eval_runtime": 4.3231,
+      "eval_samples_per_second": 11.566,
+      "eval_steps_per_second": 3.007,
+      "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