Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:691194c7702a6c06b06ce960dc11bd8dafe0aea60866bca96d4fcf4a3de28318
+oid sha256:2533609106166abc62bfbb23c42f0f6b95e42b747606435f681bc01fc37478fd
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:452fbab98c61833cf2c5e960653d03553f2410b4098b06b20e66fb0d5b19de6b
+oid sha256:dd658f77e8c87b7cda1abdef507edcbf5c932973712ae954f0c89b879d046d87
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b46eb6d4afb11fd61fda074a29a1afa78f9d878d31471db1b53889547e4af176
+oid sha256:54089c163b5f94cbb2be38781cb8cc0a37dee060f6762a3d970d915203f9b4ab
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b87a612dd35dfb995cbebd173e5aaca7f2922765c96e911cdeaad2a11c0e52d
+oid sha256:c5c6c84d79d3b2a4c0c50b8b0dfaa178dae91112908a56fce0ce60a2e545a7dc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cfdee1f2f68a2aa9ac502a0ce6f09ffa311a5da77b659482eddc43e01646f0b
+oid sha256:e2ea67b68c3365c1d75f2a603b9f38c2ba5a8d5d34431b5b5a3cfdc1a5b67397
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ccd75c83cd182b0d27cb65bcbf254724bbdcb8e9d2c0607364dc94968c7d5d43
+oid sha256:fe657cdffc8ff974cca234f8dc6ab30969639b256ee9f114d42d529ca64426cf
 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": 2.1845593452453613,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.043936731107205626,
+  "best_metric": 2.117478132247925,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08787346221441125,
   "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": 14.854,
       "eval_steps_per_second": 3.862,
       "step": 25
+    },
+    {
+      "epoch": 0.04569420035149385,
+      "grad_norm": 6.5634565353393555,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 35.1202,
+      "step": 26
+    },
+    {
+      "epoch": 0.04745166959578207,
+      "grad_norm": 5.575784206390381,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 34.9999,
+      "step": 27
+    },
+    {
+      "epoch": 0.0492091388400703,
+      "grad_norm": 5.333949089050293,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 34.6598,
+      "step": 28
+    },
+    {
+      "epoch": 0.050966608084358524,
+      "grad_norm": 5.233462810516357,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 35.3394,
+      "step": 29
+    },
+    {
+      "epoch": 0.05272407732864675,
+      "grad_norm": 4.848039627075195,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 34.6306,
+      "step": 30
+    },
+    {
+      "epoch": 0.054481546572934976,
+      "grad_norm": 4.672798156738281,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 34.26,
+      "step": 31
+    },
+    {
+      "epoch": 0.056239015817223195,
+      "grad_norm": 5.004295825958252,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 35.2661,
+      "step": 32
+    },
+    {
+      "epoch": 0.05799648506151142,
+      "grad_norm": 4.774494647979736,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 34.3399,
+      "step": 33
+    },
+    {
+      "epoch": 0.05975395430579965,
+      "grad_norm": 5.3914713859558105,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 33.8915,
+      "step": 34
+    },
+    {
+      "epoch": 0.061511423550087874,
+      "grad_norm": 5.224306583404541,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 34.217,
+      "step": 35
+    },
+    {
+      "epoch": 0.0632688927943761,
+      "grad_norm": 5.110523700714111,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 34.3804,
+      "step": 36
+    },
+    {
+      "epoch": 0.06502636203866433,
+      "grad_norm": 6.0106201171875,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 34.0626,
+      "step": 37
+    },
+    {
+      "epoch": 0.06678383128295255,
+      "grad_norm": 6.163959980010986,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 34.2085,
+      "step": 38
+    },
+    {
+      "epoch": 0.06854130052724078,
+      "grad_norm": 5.352950572967529,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 34.3615,
+      "step": 39
+    },
+    {
+      "epoch": 0.070298769771529,
+      "grad_norm": 5.185631275177002,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 33.6859,
+      "step": 40
+    },
+    {
+      "epoch": 0.07205623901581722,
+      "grad_norm": 4.927276134490967,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 34.1852,
+      "step": 41
+    },
+    {
+      "epoch": 0.07381370826010544,
+      "grad_norm": 4.6272172927856445,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 33.955,
+      "step": 42
+    },
+    {
+      "epoch": 0.07557117750439367,
+      "grad_norm": 4.516628265380859,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 34.2475,
+      "step": 43
+    },
+    {
+      "epoch": 0.0773286467486819,
+      "grad_norm": 4.3881731033325195,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 34.2023,
+      "step": 44
+    },
+    {
+      "epoch": 0.07908611599297012,
+      "grad_norm": 4.675719738006592,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 34.3724,
+      "step": 45
+    },
+    {
+      "epoch": 0.08084358523725835,
+      "grad_norm": 4.657413005828857,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 33.9527,
+      "step": 46
+    },
+    {
+      "epoch": 0.08260105448154657,
+      "grad_norm": 5.37712287902832,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 34.4192,
+      "step": 47
+    },
+    {
+      "epoch": 0.0843585237258348,
+      "grad_norm": 5.268314361572266,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 34.3434,
+      "step": 48
+    },
+    {
+      "epoch": 0.08611599297012303,
+      "grad_norm": 5.414996147155762,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 33.6508,
+      "step": 49
+    },
+    {
+      "epoch": 0.08787346221441125,
+      "grad_norm": 7.697075366973877,
+      "learning_rate": 1e-05,
+      "loss": 33.6944,
+      "step": 50
+    },
+    {
+      "epoch": 0.08787346221441125,
+      "eval_loss": 2.117478132247925,
+      "eval_runtime": 3.3457,
+      "eval_samples_per_second": 14.945,
+      "eval_steps_per_second": 3.886,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null