Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a3e94103d02278633f6b4e094a5de7ce3a8b05cccde2b4256127ae1572d341
+oid sha256:381e181b47539195849da6bd546423763a8c67449363e028abcce3905b73a83b
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9bee4922f8da42bd4b53d8d341a5871cb0eb8c576da4eaeb2cb86c8eafc2c2ec
+oid sha256:c5e56d1a40d6f80592fd7e0a0bc0ec3f996fff03d91828a49222355815e635cf
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda9b9cfba7ebccbe7f22098e3ea4dc2a60c1239bd16d9992beb270a41ca5c07
+oid sha256:ae3cf8fba773ae49de6db000b1538728d0e854db03fb09cddc0278785522de6f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0a19f6f131d24c3d813edad26f713e58221b4a57371fdb0444078f19c74c832
+oid sha256:9af91622282ee3a2e06a03577ad16318b9ff1a3f19b2c57a7e67f4241ae0d1ea
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90c7a2f24961f083e0ee6b16547573ac18741e4d980c69a6f8935523f613abb0
+oid sha256:12220246a173b554b199379f317eacaf5033ec15605f7ce34d500e113bd5cdc2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:90be222c4ddf8ca74fda75a1bd0d3788a6bf7042f64f28a73038524c192657fc
+oid sha256:7a335a686936310a8e23bbce16c79f77c50645a7268a61317cb3ce2e44809d22
 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": 7.021544933319092,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0839278220730172,
+  "best_metric": 6.8306074142456055,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1678556441460344,
   "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": 65.364,
       "eval_steps_per_second": 16.995,
       "step": 25
+    },
+    {
+      "epoch": 0.08728493495593789,
+      "grad_norm": 1.2115647792816162,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 7.3506,
+      "step": 26
+    },
+    {
+      "epoch": 0.09064204783885858,
+      "grad_norm": 1.0654467344284058,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 7.0821,
+      "step": 27
+    },
+    {
+      "epoch": 0.09399916072177927,
+      "grad_norm": 1.0704606771469116,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.9776,
+      "step": 28
+    },
+    {
+      "epoch": 0.09735627360469996,
+      "grad_norm": 1.156465768814087,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 6.8104,
+      "step": 29
+    },
+    {
+      "epoch": 0.10071338648762064,
+      "grad_norm": 1.1990591287612915,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8855,
+      "step": 30
+    },
+    {
+      "epoch": 0.10407049937054133,
+      "grad_norm": 1.2621642351150513,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 6.7606,
+      "step": 31
+    },
+    {
+      "epoch": 0.10742761225346202,
+      "grad_norm": 1.326280951499939,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.9083,
+      "step": 32
+    },
+    {
+      "epoch": 0.11078472513638271,
+      "grad_norm": 1.5722599029541016,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 6.7573,
+      "step": 33
+    },
+    {
+      "epoch": 0.1141418380193034,
+      "grad_norm": 1.8806253671646118,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 6.8356,
+      "step": 34
+    },
+    {
+      "epoch": 0.11749895090222409,
+      "grad_norm": 2.3613550662994385,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 6.5832,
+      "step": 35
+    },
+    {
+      "epoch": 0.12085606378514478,
+      "grad_norm": 3.0503711700439453,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 6.4064,
+      "step": 36
+    },
+    {
+      "epoch": 0.12421317666806546,
+      "grad_norm": 4.733037948608398,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 6.5771,
+      "step": 37
+    },
+    {
+      "epoch": 0.12757028955098615,
+      "grad_norm": 1.1526490449905396,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 7.3537,
+      "step": 38
+    },
+    {
+      "epoch": 0.13092740243390685,
+      "grad_norm": 0.9709998369216919,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 7.0119,
+      "step": 39
+    },
+    {
+      "epoch": 0.13428451531682753,
+      "grad_norm": 0.9723122715950012,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 6.9824,
+      "step": 40
+    },
+    {
+      "epoch": 0.1376416281997482,
+      "grad_norm": 0.9486874341964722,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 6.9058,
+      "step": 41
+    },
+    {
+      "epoch": 0.1409987410826689,
+      "grad_norm": 1.069161057472229,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.7611,
+      "step": 42
+    },
+    {
+      "epoch": 0.1443558539655896,
+      "grad_norm": 1.207305669784546,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.7608,
+      "step": 43
+    },
+    {
+      "epoch": 0.1477129668485103,
+      "grad_norm": 1.2742780447006226,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 6.8111,
+      "step": 44
+    },
+    {
+      "epoch": 0.15107007973143097,
+      "grad_norm": 1.5717660188674927,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 6.5346,
+      "step": 45
+    },
+    {
+      "epoch": 0.15442719261435164,
+      "grad_norm": 1.710330605506897,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 6.7916,
+      "step": 46
+    },
+    {
+      "epoch": 0.15778430549727235,
+      "grad_norm": 2.0946614742279053,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 6.8355,
+      "step": 47
+    },
+    {
+      "epoch": 0.16114141838019302,
+      "grad_norm": 2.7978506088256836,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 6.66,
+      "step": 48
+    },
+    {
+      "epoch": 0.16449853126311373,
+      "grad_norm": 3.859832525253296,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 6.4211,
+      "step": 49
+    },
+    {
+      "epoch": 0.1678556441460344,
+      "grad_norm": 6.498544692993164,
+      "learning_rate": 1e-05,
+      "loss": 6.8038,
+      "step": 50
+    },
+    {
+      "epoch": 0.1678556441460344,
+      "eval_loss": 6.8306074142456055,
+      "eval_runtime": 0.7255,
+      "eval_samples_per_second": 68.913,
+      "eval_steps_per_second": 17.917,
+      "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": 116006898892800.0,
+  "total_flos": 232013797785600.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null