Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:917666bbc0e63271ca7d03583877a37b49adf91f9f9ef310c5761b8501d660d9
+oid sha256:51378d3e2684381c9cb2704d5c4c136ecffed2be2d034dd5c3f197f6eb44fd9d
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c6b0630459e45035c726307659ab548ffa02c41139a8a8382f8a87b59353298f
+oid sha256:94fe690b9ce658ab5a5a8d5b1b92efc172a911d0690257de045f1705735a272e
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8833a862c5781d29c88e006dcada0d20be7e65f74e5dc133884c63164563c62d
+oid sha256:228f19647dc65bf2f1c05f626620b9d851a4e73b631923847d3316e4ff80bafb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:27f538c872515ae9950a96e1d2835bb478ceedc52481d43252a7838818c00d56
+oid sha256:814aa8142d1ec3f548e91ff05498d50e765817e2f57fd4bfde1e51544d77bc91
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46700bcaacbc8e1a46cd4290cfc02cd8a13af9bb755c08bb509987ac9c23eff9
+oid sha256:42102009a1411e0e3f29d3d1b2452814c98aa0272fa7bb3f64547792809f8688
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26865edbb08573afbe90652802596d58696f671f1a4e84edd7602222afd85d6b
+oid sha256:8402d955a963217afc4a6754bb487db2a0673705e3714d11c94060899aab5036
 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": 1.1515358686447144,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01992081476132374,
+  "best_metric": 1.1095232963562012,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03984162952264748,
   "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": 9.404,
       "eval_steps_per_second": 2.445,
       "step": 25
+    },
+    {
+      "epoch": 0.020717647351776686,
+      "grad_norm": 0.1238275095820427,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.7318,
+      "step": 26
+    },
+    {
+      "epoch": 0.021514479942229638,
+      "grad_norm": 0.12721899151802063,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.7337,
+      "step": 27
+    },
+    {
+      "epoch": 0.022311312532682585,
+      "grad_norm": 0.12318814545869827,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.7866,
+      "step": 28
+    },
+    {
+      "epoch": 0.023108145123135537,
+      "grad_norm": 0.14742588996887207,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.7804,
+      "step": 29
+    },
+    {
+      "epoch": 0.023904977713588484,
+      "grad_norm": 0.23791754245758057,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.0907,
+      "step": 30
+    },
+    {
+      "epoch": 0.024701810304041436,
+      "grad_norm": 0.29251614212989807,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.1775,
+      "step": 31
+    },
+    {
+      "epoch": 0.025498642894494383,
+      "grad_norm": 0.29965853691101074,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.2387,
+      "step": 32
+    },
+    {
+      "epoch": 0.026295475484947334,
+      "grad_norm": 0.3010103404521942,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.2586,
+      "step": 33
+    },
+    {
+      "epoch": 0.027092308075400282,
+      "grad_norm": 0.2877664268016815,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.2567,
+      "step": 34
+    },
+    {
+      "epoch": 0.027889140665853233,
+      "grad_norm": 0.2702466547489166,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2134,
+      "step": 35
+    },
+    {
+      "epoch": 0.028685973256306185,
+      "grad_norm": 0.3501109778881073,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2461,
+      "step": 36
+    },
+    {
+      "epoch": 0.029482805846759132,
+      "grad_norm": 0.8502271175384521,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.38,
+      "step": 37
+    },
+    {
+      "epoch": 0.030279638437212084,
+      "grad_norm": 0.10287067294120789,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.7774,
+      "step": 38
+    },
+    {
+      "epoch": 0.03107647102766503,
+      "grad_norm": 0.09060327708721161,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.7215,
+      "step": 39
+    },
+    {
+      "epoch": 0.03187330361811798,
+      "grad_norm": 0.09810002893209457,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.7485,
+      "step": 40
+    },
+    {
+      "epoch": 0.032670136208570934,
+      "grad_norm": 0.11357197165489197,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.7505,
+      "step": 41
+    },
+    {
+      "epoch": 0.03346696879902388,
+      "grad_norm": 0.12801313400268555,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.8528,
+      "step": 42
+    },
+    {
+      "epoch": 0.03426380138947683,
+      "grad_norm": 0.17026148736476898,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.1343,
+      "step": 43
+    },
+    {
+      "epoch": 0.03506063397992978,
+      "grad_norm": 0.2460681051015854,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2216,
+      "step": 44
+    },
+    {
+      "epoch": 0.03585746657038273,
+      "grad_norm": 0.19261527061462402,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1919,
+      "step": 45
+    },
+    {
+      "epoch": 0.03665429916083568,
+      "grad_norm": 0.213339164853096,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.2428,
+      "step": 46
+    },
+    {
+      "epoch": 0.03745113175128863,
+      "grad_norm": 0.23940491676330566,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.1661,
+      "step": 47
+    },
+    {
+      "epoch": 0.038247964341741575,
+      "grad_norm": 0.31757083535194397,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.2426,
+      "step": 48
+    },
+    {
+      "epoch": 0.03904479693219453,
+      "grad_norm": 0.6811033487319946,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.3631,
+      "step": 49
+    },
+    {
+      "epoch": 0.03984162952264748,
+      "grad_norm": 2.329777956008911,
+      "learning_rate": 1e-05,
+      "loss": 1.6394,
+      "step": 50
+    },
+    {
+      "epoch": 0.03984162952264748,
+      "eval_loss": 1.1095232963562012,
+      "eval_runtime": 5.3407,
+      "eval_samples_per_second": 9.362,
+      "eval_steps_per_second": 2.434,
+      "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": 1.327074698592256e+17,
+  "total_flos": 2.654149397184512e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null