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:d731f516be704ce63bec73cf763113e9cfc8ecaaa04907ccd14b3aa6b7ba68a5
+oid sha256:246f2850985f39770f3cfdbe1a1bfd59739a5739733074370c530a250276198b
 size 188794608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffdc7764e734386f1dac1ed1decc897edcccf5b8f6e2bfeeeb6aaab6d7ab3e96
+oid sha256:bb87a1cab9361faf81f73b0c89fd6fbc9a0296009787580d21ed73445e6acb68
 size 377811346

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cebfcbb74a2191589fcf61fafc34cbbfccab57752d5b9827d6c4492be4789623
+oid sha256:78beb1a3694ca258c5d9e3a2d48a3c58f7ed20ce33e1dcdfe31d9f7bbb95ef09
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f5d22e35b31c6a4ac2c95febb21c24e94f2b9ccdb9635e90c412d737a093bc7
+oid sha256:c440f226ee8de60f8f9e229d8323fdf393a709a978d987c9c9fd834a662ec48a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d7045aa3a923fd90fa4e43929d580e9a2feb265c8c07d703728377c1ad7f3a09
+oid sha256:05e34fcaace1e40aac64f5c0fa9cde654d5d7aa59e25d0a35185b2ac8c0d914f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5411597fec8438b6ed5ab030dd43f59448bb87a397c592838a5b3469d564df95
+oid sha256:2180f709507df01ab60ec58ec8217cc85afec3a23a5fb97e51b4f12b785f91dd
 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": 1.2877497673034668,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.9478672985781991,
+  "best_metric": 1.1550209522247314,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.8957345971563981,
   "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": 17.905,
       "eval_steps_per_second": 4.655,
       "step": 25
+    },
+    {
+      "epoch": 0.985781990521327,
+      "grad_norm": 3.641972780227661,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.3063,
+      "step": 26
+    },
+    {
+      "epoch": 1.0236966824644549,
+      "grad_norm": 6.575774192810059,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.2342,
+      "step": 27
+    },
+    {
+      "epoch": 1.061611374407583,
+      "grad_norm": 2.9681127071380615,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.1676,
+      "step": 28
+    },
+    {
+      "epoch": 1.099526066350711,
+      "grad_norm": 3.215055465698242,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 1.3389,
+      "step": 29
+    },
+    {
+      "epoch": 1.1374407582938388,
+      "grad_norm": 3.5927894115448,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.3118,
+      "step": 30
+    },
+    {
+      "epoch": 1.1753554502369667,
+      "grad_norm": 3.6256959438323975,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.2951,
+      "step": 31
+    },
+    {
+      "epoch": 1.2132701421800949,
+      "grad_norm": 4.082485675811768,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.3665,
+      "step": 32
+    },
+    {
+      "epoch": 1.2511848341232228,
+      "grad_norm": 3.8541548252105713,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 1.2832,
+      "step": 33
+    },
+    {
+      "epoch": 1.2890995260663507,
+      "grad_norm": 3.3070080280303955,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.4977,
+      "step": 34
+    },
+    {
+      "epoch": 1.3270142180094786,
+      "grad_norm": 2.957866668701172,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 1.2518,
+      "step": 35
+    },
+    {
+      "epoch": 1.3649289099526065,
+      "grad_norm": 3.1968929767608643,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.2103,
+      "step": 36
+    },
+    {
+      "epoch": 1.4028436018957346,
+      "grad_norm": 3.788357973098755,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.2678,
+      "step": 37
+    },
+    {
+      "epoch": 1.4407582938388626,
+      "grad_norm": 3.5773918628692627,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.2282,
+      "step": 38
+    },
+    {
+      "epoch": 1.4786729857819905,
+      "grad_norm": 5.209697723388672,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.2627,
+      "step": 39
+    },
+    {
+      "epoch": 1.5165876777251186,
+      "grad_norm": 3.6985459327697754,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.3944,
+      "step": 40
+    },
+    {
+      "epoch": 1.5545023696682465,
+      "grad_norm": 3.104992151260376,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.1069,
+      "step": 41
+    },
+    {
+      "epoch": 1.5924170616113744,
+      "grad_norm": 3.5081048011779785,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.2404,
+      "step": 42
+    },
+    {
+      "epoch": 1.6303317535545023,
+      "grad_norm": 4.174959659576416,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 1.2726,
+      "step": 43
+    },
+    {
+      "epoch": 1.6682464454976302,
+      "grad_norm": 3.9129672050476074,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.235,
+      "step": 44
+    },
+    {
+      "epoch": 1.7061611374407581,
+      "grad_norm": 3.7290847301483154,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.1971,
+      "step": 45
+    },
+    {
+      "epoch": 1.7440758293838863,
+      "grad_norm": 4.0499725341796875,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.1738,
+      "step": 46
+    },
+    {
+      "epoch": 1.7819905213270142,
+      "grad_norm": 4.013765335083008,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4398,
+      "step": 47
+    },
+    {
+      "epoch": 1.8199052132701423,
+      "grad_norm": 3.703307628631592,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.2168,
+      "step": 48
+    },
+    {
+      "epoch": 1.8578199052132702,
+      "grad_norm": 3.162926197052002,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.2299,
+      "step": 49
+    },
+    {
+      "epoch": 1.8957345971563981,
+      "grad_norm": 3.2073774337768555,
+      "learning_rate": 1e-05,
+      "loss": 1.1804,
+      "step": 50
+    },
+    {
+      "epoch": 1.8957345971563981,
+      "eval_loss": 1.1550209522247314,
+      "eval_runtime": 2.8058,
+      "eval_samples_per_second": 17.82,
+      "eval_steps_per_second": 4.633,
+      "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": 1.06003081199616e+17,
+  "total_flos": 2.12006162399232e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null