Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27fee307162b88dd9045f2c6f15a8ae8e9091dd8f7aae47c8d8541014d2adbe9
+oid sha256:628a94cfd8920982c63035d58a0935865e89736c8c510d088885c32dd3950035
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1163420f5533d2213e0f6f8be9c1b4a0aa1e3914c96b6f72860f2511f1dcb3d
+oid sha256:5a53ef18ce4705c5cf1193c9eb67dd3e9ca8ea1edc3dbbe9342d1976328985e2
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0446f0394966b68ab4d5574aa8aa3120b11b41d89f003b6d9b183f34b912c211
+oid sha256:19f8ccd66454f2d1deccec9ec94b37f1d2515adb8ec5668b61828473ab50c52b
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e980a369392718f51199736b56e2d29554893d52b054e338a4fdcee23d5ae318
+oid sha256:9e3fddc36e661f28d706dec7084e9b54aa1e9b5805428664bab711a349d41fbc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:011739a207ed52accb6616c62a223bce11c6881edd4e1e8312a99e39cbc3bcaf
+oid sha256:83082907f8fd340708884daedabbd38e5fea3d67daed1eb3b394ef90a463d98d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eea9112c218a725a5f2f6026d5e8eef81e238ff1dd0c64e4a7bbbd050455efc4
+oid sha256:ae25accc62e6aef6fb5caebadc03c016d8136dcac03fe2bb076992fa3c8b3d02
 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": 1.8580714464187622,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22271714922049,
+  "best_metric": 1.7249575853347778,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.44543429844098,
   "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": 37.135,
       "eval_steps_per_second": 9.655,
       "step": 25
+    },
+    {
+      "epoch": 0.23162583518930957,
+      "grad_norm": 0.41025131940841675,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.5984,
+      "step": 26
+    },
+    {
+      "epoch": 0.24053452115812918,
+      "grad_norm": 0.8294768333435059,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.694,
+      "step": 27
+    },
+    {
+      "epoch": 0.24944320712694878,
+      "grad_norm": 0.9431820511817932,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.9993,
+      "step": 28
+    },
+    {
+      "epoch": 0.2583518930957684,
+      "grad_norm": 1.1680399179458618,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.8814,
+      "step": 29
+    },
+    {
+      "epoch": 0.267260579064588,
+      "grad_norm": 0.865944504737854,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.9858,
+      "step": 30
+    },
+    {
+      "epoch": 0.27616926503340755,
+      "grad_norm": 0.6460347771644592,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.0091,
+      "step": 31
+    },
+    {
+      "epoch": 0.28507795100222716,
+      "grad_norm": 0.4979117810726166,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9771,
+      "step": 32
+    },
+    {
+      "epoch": 0.29398663697104677,
+      "grad_norm": 0.4473193883895874,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.7974,
+      "step": 33
+    },
+    {
+      "epoch": 0.3028953229398664,
+      "grad_norm": 0.6420344114303589,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.8387,
+      "step": 34
+    },
+    {
+      "epoch": 0.311804008908686,
+      "grad_norm": 0.9772244095802307,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.7613,
+      "step": 35
+    },
+    {
+      "epoch": 0.3207126948775056,
+      "grad_norm": 1.5189650058746338,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.6827,
+      "step": 36
+    },
+    {
+      "epoch": 0.32962138084632514,
+      "grad_norm": 3.2754437923431396,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.6556,
+      "step": 37
+    },
+    {
+      "epoch": 0.33853006681514475,
+      "grad_norm": 0.333280473947525,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.6686,
+      "step": 38
+    },
+    {
+      "epoch": 0.34743875278396436,
+      "grad_norm": 0.24920018017292023,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.4806,
+      "step": 39
+    },
+    {
+      "epoch": 0.35634743875278396,
+      "grad_norm": 0.320494681596756,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.7333,
+      "step": 40
+    },
+    {
+      "epoch": 0.36525612472160357,
+      "grad_norm": 0.31181883811950684,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.7869,
+      "step": 41
+    },
+    {
+      "epoch": 0.3741648106904232,
+      "grad_norm": 0.2530730068683624,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.9439,
+      "step": 42
+    },
+    {
+      "epoch": 0.3830734966592428,
+      "grad_norm": 0.29116693139076233,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.8799,
+      "step": 43
+    },
+    {
+      "epoch": 0.39198218262806234,
+      "grad_norm": 0.3935719132423401,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.9294,
+      "step": 44
+    },
+    {
+      "epoch": 0.40089086859688194,
+      "grad_norm": 0.3431456983089447,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8817,
+      "step": 45
+    },
+    {
+      "epoch": 0.40979955456570155,
+      "grad_norm": 0.42623868584632874,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8161,
+      "step": 46
+    },
+    {
+      "epoch": 0.41870824053452116,
+      "grad_norm": 0.48873162269592285,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.7659,
+      "step": 47
+    },
+    {
+      "epoch": 0.42761692650334077,
+      "grad_norm": 0.7280839085578918,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.8101,
+      "step": 48
+    },
+    {
+      "epoch": 0.4365256124721604,
+      "grad_norm": 1.710809350013733,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.5907,
+      "step": 49
+    },
+    {
+      "epoch": 0.44543429844098,
+      "grad_norm": 4.463897228240967,
+      "learning_rate": 1e-05,
+      "loss": 2.065,
+      "step": 50
+    },
+    {
+      "epoch": 0.44543429844098,
+      "eval_loss": 1.7249575853347778,
+      "eval_runtime": 1.3575,
+      "eval_samples_per_second": 36.832,
+      "eval_steps_per_second": 9.576,
+      "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": 5.314237029574246e+16,
+  "total_flos": 1.0621851957775565e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null