Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:34098dbd9bd3b07b19cadc8990fbe10f509aa8a16a45bdc061bb46aab913f891
+oid sha256:ffff28bd2336dfaccc6f1d07a3514776389650d13da63d36db431354f8f0cb5e
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6bae3b8dd371e1ff8d54704d71a492d42ddaa29fc17f2d9cbb9bc2e1522186a9
+oid sha256:d8152ef662deff49456399a2cb6327dad4b286217eefa56b179acce4766d062c
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:925c099bfc1781cba5e127e54f3c37203d0c5a44642f86ffecad65ccc71ea8ea
+oid sha256:9268e5123d0790c11295477aab1c135d6f02f8ea8107c895677ad6361966ff03
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df007af7f74a154ba6a2cf795d203cd54dfd0f2834aa782669a0c21f83495390
+oid sha256:8130d11b6bc113ca41b1320af37c2a991b8d3f3538d7481db06e48d89c792ebb
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0edeb080c5229c6b7a8c70c54df849a0a89ea3a9f7af2eed759fcc8ea5e7a934
+oid sha256:977e6950c88bcf9ff6299db55dae71d314f72c3582ac08cad105e0b8445c6d32
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30dd81f1a7c96ceb9c3bc97d1f2c3f5df995a0e2a0e6ed564c6fdd061152c685
+oid sha256:8bd8ef9cd904e147b95d951959d0cc04cc34755065faf2f257e15afc5d96040b
 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": 10.323739051818848,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5128205128205128,
+  "best_metric": 10.302132606506348,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0256410256410255,
   "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": 523.14,
       "eval_steps_per_second": 136.016,
       "step": 25
+    },
+    {
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.3629811704158783,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3643,
+      "step": 26
+    },
+    {
+      "epoch": 0.5538461538461539,
+      "grad_norm": 0.38693100214004517,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3506,
+      "step": 27
+    },
+    {
+      "epoch": 0.5743589743589743,
+      "grad_norm": 0.3990083932876587,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3487,
+      "step": 28
+    },
+    {
+      "epoch": 0.5948717948717949,
+      "grad_norm": 0.4057125151157379,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3388,
+      "step": 29
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.4252845346927643,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3212,
+      "step": 30
+    },
+    {
+      "epoch": 0.6358974358974359,
+      "grad_norm": 0.4381605386734009,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3197,
+      "step": 31
+    },
+    {
+      "epoch": 0.6564102564102564,
+      "grad_norm": 0.4398859441280365,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3138,
+      "step": 32
+    },
+    {
+      "epoch": 0.676923076923077,
+      "grad_norm": 0.48066049814224243,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3216,
+      "step": 33
+    },
+    {
+      "epoch": 0.6974358974358974,
+      "grad_norm": 0.48158058524131775,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3172,
+      "step": 34
+    },
+    {
+      "epoch": 0.717948717948718,
+      "grad_norm": 0.492822527885437,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3043,
+      "step": 35
+    },
+    {
+      "epoch": 0.7384615384615385,
+      "grad_norm": 0.5400839447975159,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3198,
+      "step": 36
+    },
+    {
+      "epoch": 0.7589743589743589,
+      "grad_norm": 0.4561348855495453,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3269,
+      "step": 37
+    },
+    {
+      "epoch": 0.7794871794871795,
+      "grad_norm": 0.4233783185482025,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3418,
+      "step": 38
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 0.45299649238586426,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.3455,
+      "step": 39
+    },
+    {
+      "epoch": 0.8205128205128205,
+      "grad_norm": 0.4731706976890564,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3285,
+      "step": 40
+    },
+    {
+      "epoch": 0.841025641025641,
+      "grad_norm": 0.46432170271873474,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.318,
+      "step": 41
+    },
+    {
+      "epoch": 0.8615384615384616,
+      "grad_norm": 0.4683786630630493,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3266,
+      "step": 42
+    },
+    {
+      "epoch": 0.882051282051282,
+      "grad_norm": 0.4873765707015991,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3033,
+      "step": 43
+    },
+    {
+      "epoch": 0.9025641025641026,
+      "grad_norm": 0.5106824636459351,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3023,
+      "step": 44
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.546622633934021,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.2991,
+      "step": 45
+    },
+    {
+      "epoch": 0.9435897435897436,
+      "grad_norm": 0.5175260901451111,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.2922,
+      "step": 46
+    },
+    {
+      "epoch": 0.9641025641025641,
+      "grad_norm": 0.5443073511123657,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.2989,
+      "step": 47
+    },
+    {
+      "epoch": 0.9846153846153847,
+      "grad_norm": 0.5688486099243164,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3112,
+      "step": 48
+    },
+    {
+      "epoch": 1.005128205128205,
+      "grad_norm": 0.6074473857879639,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 12.8749,
+      "step": 49
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "grad_norm": 0.48072201013565063,
+      "learning_rate": 1e-05,
+      "loss": 10.1882,
+      "step": 50
+    },
+    {
+      "epoch": 1.0256410256410255,
+      "eval_loss": 10.302132606506348,
+      "eval_runtime": 0.1235,
+      "eval_samples_per_second": 404.986,
+      "eval_steps_per_second": 105.296,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null