Training in progress, step 133, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d9443d3806b3f524104e7410b3e7a5e0e8f8deae600b21085beb3ac0c347fe7
+oid sha256:d12be65f7e8dd5ac27291117edd1522ed1581db54bb6a06a934a5bd27b67433f
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883ac1d2d58af98f5c15e8c1f68fa35b3c5825ab049535194ee9b5e9923331e5
+oid sha256:311f36c5d5948b26d4bcd744cf495abfea0b2c2b47bbdcbd5358442b98ab6940
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea7479aa993184fae8582a8ac09e7b54fd0c69e1659e2cd0f651a189fcfe7ab3
+oid sha256:053a19bf6ddaa7bbad68aedb481b6fbae1f1ede7b8789c2659555b2f7468d4c2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7827a0766373e30cb2e50db528dff06a73ccc5e29be7188061afef7b5fe7b104
+oid sha256:d723020e200376885e5ac296b9cba37ed8d9cf413b9b76c448ebc21c950b5a77
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06031019adc9147ff97b6a7795fcebe13ec08027167ebbf684d7b589e62e1a23
+oid sha256:996b5e0855b39aa6eafe4b88cbd8f3449cf57c2b9ab8bd497eea241d840fb88c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddce3cd2ce73700e2934bb3f599ad484193bf9109c3b6e0a907e0ff72008c987
+oid sha256:22498a1c9b3f72e3686290a05844b34240bb18597ef646fc6b0c3b651699e0ff
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2d2e9486a02a9d276f7ca10792a086dd994b16cb3a60458cafba5cc010d9e3
+oid sha256:349b16c1d49b7fd568cd7193488ce7ffb223618fe2fd7726cd63b343cdf98e43
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.3449122905731201,
   "best_model_checkpoint": "miner_id_24/checkpoint-100",
-  "epoch": 0.8609093354856067,
+  "epoch": 1.1450094161958568,
   "eval_steps": 25,
-  "global_step": 100,
+  "global_step": 133,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -747,6 +747,245 @@
       "eval_samples_per_second": 39.295,
       "eval_steps_per_second": 10.217,
       "step": 100
+    },
+    {
+      "epoch": 0.8695184288404627,
+      "grad_norm": 0.3012229800224304,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.176,
+      "step": 101
+    },
+    {
+      "epoch": 0.8781275221953188,
+      "grad_norm": 0.4754287004470825,
+      "learning_rate": 2.2408881267183997e-05,
+      "loss": 1.1958,
+      "step": 102
+    },
+    {
+      "epoch": 0.8867366155501749,
+      "grad_norm": 0.43265655636787415,
+      "learning_rate": 2.165719935902685e-05,
+      "loss": 1.3262,
+      "step": 103
+    },
+    {
+      "epoch": 0.895345708905031,
+      "grad_norm": 0.5260616540908813,
+      "learning_rate": 2.09256019072082e-05,
+      "loss": 1.3721,
+      "step": 104
+    },
+    {
+      "epoch": 0.903954802259887,
+      "grad_norm": 0.5602609515190125,
+      "learning_rate": 2.0214529598676836e-05,
+      "loss": 1.401,
+      "step": 105
+    },
+    {
+      "epoch": 0.912563895614743,
+      "grad_norm": 0.29336562752723694,
+      "learning_rate": 1.952441075680272e-05,
+      "loss": 1.6924,
+      "step": 106
+    },
+    {
+      "epoch": 0.9211729889695991,
+      "grad_norm": 0.9488304853439331,
+      "learning_rate": 1.8855661083370986e-05,
+      "loss": 1.8012,
+      "step": 107
+    },
+    {
+      "epoch": 0.9297820823244553,
+      "grad_norm": 0.3932758867740631,
+      "learning_rate": 1.820868340817874e-05,
+      "loss": 1.6428,
+      "step": 108
+    },
+    {
+      "epoch": 0.9383911756793113,
+      "grad_norm": 0.3379191756248474,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.3678,
+      "step": 109
+    },
+    {
+      "epoch": 0.9470002690341673,
+      "grad_norm": 0.5376018285751343,
+      "learning_rate": 1.698158956376318e-05,
+      "loss": 1.6057,
+      "step": 110
+    },
+    {
+      "epoch": 0.9556093623890234,
+      "grad_norm": 0.6705049872398376,
+      "learning_rate": 1.6402212549987762e-05,
+      "loss": 1.5497,
+      "step": 111
+    },
+    {
+      "epoch": 0.9642184557438794,
+      "grad_norm": 1.5708343982696533,
+      "learning_rate": 1.584608540010799e-05,
+      "loss": 1.4589,
+      "step": 112
+    },
+    {
+      "epoch": 0.9728275490987356,
+      "grad_norm": 2.8929443359375,
+      "learning_rate": 1.531354310432403e-05,
+      "loss": 1.5784,
+      "step": 113
+    },
+    {
+      "epoch": 0.9814366424535916,
+      "grad_norm": 0.3657113313674927,
+      "learning_rate": 1.4804906446201816e-05,
+      "loss": 1.3912,
+      "step": 114
+    },
+    {
+      "epoch": 0.9900457358084477,
+      "grad_norm": 0.3794941306114197,
+      "learning_rate": 1.4320481809445051e-05,
+      "loss": 1.5847,
+      "step": 115
+    },
+    {
+      "epoch": 0.9986548291633037,
+      "grad_norm": 0.7362991571426392,
+      "learning_rate": 1.386056099334112e-05,
+      "loss": 1.399,
+      "step": 116
+    },
+    {
+      "epoch": 1.0072639225181599,
+      "grad_norm": 0.8029009103775024,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.2215,
+      "step": 117
+    },
+    {
+      "epoch": 1.0158730158730158,
+      "grad_norm": 0.5080808997154236,
+      "learning_rate": 1.3015324052436753e-05,
+      "loss": 1.2015,
+      "step": 118
+    },
+    {
+      "epoch": 1.024482109227872,
+      "grad_norm": 0.44496291875839233,
+      "learning_rate": 1.2630517066764069e-05,
+      "loss": 1.2138,
+      "step": 119
+    },
+    {
+      "epoch": 1.033091202582728,
+      "grad_norm": 0.4348479211330414,
+      "learning_rate": 1.227123187331335e-05,
+      "loss": 1.2767,
+      "step": 120
+    },
+    {
+      "epoch": 1.041700295937584,
+      "grad_norm": 0.37992164492607117,
+      "learning_rate": 1.1937684892050604e-05,
+      "loss": 1.5242,
+      "step": 121
+    },
+    {
+      "epoch": 1.0503093892924402,
+      "grad_norm": 0.32971861958503723,
+      "learning_rate": 1.1630077039205209e-05,
+      "loss": 1.5498,
+      "step": 122
+    },
+    {
+      "epoch": 1.0589184826472962,
+      "grad_norm": 0.5224172472953796,
+      "learning_rate": 1.1348593606245522e-05,
+      "loss": 1.6984,
+      "step": 123
+    },
+    {
+      "epoch": 1.0675275760021523,
+      "grad_norm": 0.43070971965789795,
+      "learning_rate": 1.109340414826622e-05,
+      "loss": 1.5932,
+      "step": 124
+    },
+    {
+      "epoch": 1.0761366693570082,
+      "grad_norm": 0.4774491786956787,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.4308,
+      "step": 125
+    },
+    {
+      "epoch": 1.0761366693570082,
+      "eval_loss": 1.3410676717758179,
+      "eval_runtime": 1.2741,
+      "eval_samples_per_second": 39.242,
+      "eval_steps_per_second": 10.203,
+      "step": 125
+    },
+    {
+      "epoch": 1.0847457627118644,
+      "grad_norm": 0.5184400677680969,
+      "learning_rate": 1.0662506092497646e-05,
+      "loss": 1.4641,
+      "step": 126
+    },
+    {
+      "epoch": 1.0933548560667206,
+      "grad_norm": 0.5525245666503906,
+      "learning_rate": 1.0487057051584856e-05,
+      "loss": 1.5545,
+      "step": 127
+    },
+    {
+      "epoch": 1.1019639494215765,
+      "grad_norm": 1.609927773475647,
+      "learning_rate": 1.0338420943058053e-05,
+      "loss": 1.3439,
+      "step": 128
+    },
+    {
+      "epoch": 1.1105730427764327,
+      "grad_norm": 2.2938551902770996,
+      "learning_rate": 1.0216687299751144e-05,
+      "loss": 1.4817,
+      "step": 129
+    },
+    {
+      "epoch": 1.1191821361312886,
+      "grad_norm": 0.45292142033576965,
+      "learning_rate": 1.0121929449458941e-05,
+      "loss": 1.1242,
+      "step": 130
+    },
+    {
+      "epoch": 1.1277912294861447,
+      "grad_norm": 0.4423352777957916,
+      "learning_rate": 1.0054204470767243e-05,
+      "loss": 1.1672,
+      "step": 131
+    },
+    {
+      "epoch": 1.136400322841001,
+      "grad_norm": 0.33851832151412964,
+      "learning_rate": 1.0013553158670811e-05,
+      "loss": 1.2433,
+      "step": 132
+    },
+    {
+      "epoch": 1.1450094161958568,
+      "grad_norm": 0.3434777855873108,
+      "learning_rate": 1e-05,
+      "loss": 1.4094,
+      "step": 133
     }
   ],
   "logging_steps": 1,
@@ -770,12 +1009,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.1243703888707584e+17,
+  "total_flos": 2.8256510115053568e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null