Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ffef11321aeb40c36498a7b0243b13c9ad66a1ed4042e5d2cff5f22aa66c152
+oid sha256:7b5d75064e1de3d8ff277b65fcf6be1c1090b9aa0c075611010076863e88d7b8
 size 639691872

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:026b4e4a3e304f00ef68b648ee773062cfc432c6ebbdb19dfa9f21385d9c478c
+oid sha256:5782a505c8412a3595c8dedfc9058ff5a4f9ac462a9a7b5953722813b0b69d8a
 size 325339796

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fbbf97b3a5982769328e6c17bbd721d4db29f3a90af2964997b842ff0b7c627
+oid sha256:0cd2ea5148b786104b5d03d654aea02a4ebb7861ef328097d86ab87744dfcb97
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55dae8430b90d80adef1c03a4f3a616fcfecb52c15727db0573d3903a58c7433
+oid sha256:3d723739a6fa4ea30945a34ff1af162c2bb89c5992ef1094b5c521b7694bd2c4
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2a53637177b916508a2faa86ffb825e8aec1da6f32f04559dcc4f209969d4ad
+oid sha256:e459198448be978969fedceb3360c51e8cf0313cac6ae433ec53e0762d4e3e6d
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7624a009fbd55b74eabae40d34cae21bdea5444998c9b54d71b3dce9371f4b09
+oid sha256:853ef45badcd2e2c9ae1e5c4cb439d1b75e9390885aca05053c68a331042cbf5
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf945fd2a3d32a022238b4fa2cccd83f027cee749881f4a3cd330deb0fbba67d
+oid sha256:a908a57dd84dbfde0b01a60979b6b18d2cdac3c8d0bed90e087eae9f71c94d21
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b39cc4938391c9cb93ced3ff4ba63e53d75aec591735c4893f30bd34c1bf2cdb
+oid sha256:720c8196507c1925e2431dd97b1cda7a8f76810603dd724b1502d76c5183720e
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fca866cd199952053cad89fe8ee47fd054f317b68d9a842774a6ed014c7755b5
+oid sha256:a1ebe7a215439b5b9725e621fcb738a0eb88896276c25aa27e4aefcf4c177061
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6006c96ab3ed3fd9a76884eb4947385722e38fb97c03a068a95364ce3f2f031
+oid sha256:e24b69780e11768bbf28d91bd178cf09c839ff734fef597cd839a55a3a3ec0a8
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d606eeb1aa97b417de3c30d0a970be83ac979e2c7cc0fa41135c63d459909e5
+oid sha256:ba4af3b1b4fa156d60adeec70df709d1741ac2f3147c676ab2805007313fc707
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5667701959609985,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.9404388714733543,
+  "best_metric": 1.5487430095672607,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 1.2539184952978055,
   "eval_steps": 50,
-  "global_step": 150,
+  "global_step": 200,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -1089,6 +1089,364 @@
       "eval_samples_per_second": 95.791,
       "eval_steps_per_second": 3.031,
       "step": 150
+    },
+    {
+      "epoch": 0.9467084639498433,
+      "grad_norm": 0.19177977740764618,
+      "learning_rate": 2.6047368421052634e-05,
+      "loss": 1.1268,
+      "step": 151
+    },
+    {
+      "epoch": 0.9529780564263323,
+      "grad_norm": 0.22979336977005005,
+      "learning_rate": 2.5515789473684213e-05,
+      "loss": 1.547,
+      "step": 152
+    },
+    {
+      "epoch": 0.9592476489028213,
+      "grad_norm": 0.25756391882896423,
+      "learning_rate": 2.4984210526315788e-05,
+      "loss": 1.557,
+      "step": 153
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 0.28064021468162537,
+      "learning_rate": 2.445263157894737e-05,
+      "loss": 1.6312,
+      "step": 154
+    },
+    {
+      "epoch": 0.9717868338557993,
+      "grad_norm": 0.26792532205581665,
+      "learning_rate": 2.3921052631578946e-05,
+      "loss": 1.6238,
+      "step": 155
+    },
+    {
+      "epoch": 0.9780564263322884,
+      "grad_norm": 0.39074593782424927,
+      "learning_rate": 2.3389473684210528e-05,
+      "loss": 1.7098,
+      "step": 156
+    },
+    {
+      "epoch": 0.9843260188087775,
+      "grad_norm": 0.18297022581100464,
+      "learning_rate": 2.2857894736842106e-05,
+      "loss": 1.3357,
+      "step": 157
+    },
+    {
+      "epoch": 0.9905956112852664,
+      "grad_norm": 0.25956788659095764,
+      "learning_rate": 2.2326315789473685e-05,
+      "loss": 1.5917,
+      "step": 158
+    },
+    {
+      "epoch": 0.9968652037617555,
+      "grad_norm": 0.2860299050807953,
+      "learning_rate": 2.1794736842105264e-05,
+      "loss": 1.614,
+      "step": 159
+    },
+    {
+      "epoch": 1.0031347962382444,
+      "grad_norm": 0.7106801271438599,
+      "learning_rate": 2.1263157894736842e-05,
+      "loss": 2.2942,
+      "step": 160
+    },
+    {
+      "epoch": 1.0094043887147335,
+      "grad_norm": 0.18997180461883545,
+      "learning_rate": 2.073157894736842e-05,
+      "loss": 1.2174,
+      "step": 161
+    },
+    {
+      "epoch": 1.0156739811912225,
+      "grad_norm": 0.23358674347400665,
+      "learning_rate": 2.0200000000000003e-05,
+      "loss": 1.5371,
+      "step": 162
+    },
+    {
+      "epoch": 1.0219435736677116,
+      "grad_norm": 0.2865792512893677,
+      "learning_rate": 1.966842105263158e-05,
+      "loss": 1.4463,
+      "step": 163
+    },
+    {
+      "epoch": 1.0282131661442007,
+      "grad_norm": 0.2753351926803589,
+      "learning_rate": 1.913684210526316e-05,
+      "loss": 1.5938,
+      "step": 164
+    },
+    {
+      "epoch": 1.0344827586206897,
+      "grad_norm": 0.3426651954650879,
+      "learning_rate": 1.8605263157894736e-05,
+      "loss": 1.6158,
+      "step": 165
+    },
+    {
+      "epoch": 1.0407523510971788,
+      "grad_norm": 0.3205581605434418,
+      "learning_rate": 1.8073684210526318e-05,
+      "loss": 1.0132,
+      "step": 166
+    },
+    {
+      "epoch": 1.0470219435736676,
+      "grad_norm": 0.2695804238319397,
+      "learning_rate": 1.7542105263157897e-05,
+      "loss": 1.4809,
+      "step": 167
+    },
+    {
+      "epoch": 1.0532915360501567,
+      "grad_norm": 0.282909095287323,
+      "learning_rate": 1.7010526315789475e-05,
+      "loss": 1.4876,
+      "step": 168
+    },
+    {
+      "epoch": 1.0595611285266457,
+      "grad_norm": 0.3307754099369049,
+      "learning_rate": 1.6478947368421054e-05,
+      "loss": 1.6473,
+      "step": 169
+    },
+    {
+      "epoch": 1.0658307210031348,
+      "grad_norm": 0.2856920659542084,
+      "learning_rate": 1.5947368421052633e-05,
+      "loss": 1.4577,
+      "step": 170
+    },
+    {
+      "epoch": 1.0721003134796239,
+      "grad_norm": 0.3223838806152344,
+      "learning_rate": 1.541578947368421e-05,
+      "loss": 1.5373,
+      "step": 171
+    },
+    {
+      "epoch": 1.078369905956113,
+      "grad_norm": 0.3112918734550476,
+      "learning_rate": 1.4884210526315788e-05,
+      "loss": 0.7563,
+      "step": 172
+    },
+    {
+      "epoch": 1.084639498432602,
+      "grad_norm": 0.23498904705047607,
+      "learning_rate": 1.4352631578947369e-05,
+      "loss": 1.7513,
+      "step": 173
+    },
+    {
+      "epoch": 1.0909090909090908,
+      "grad_norm": 0.2094041258096695,
+      "learning_rate": 1.3821052631578949e-05,
+      "loss": 1.4246,
+      "step": 174
+    },
+    {
+      "epoch": 1.09717868338558,
+      "grad_norm": 0.26500001549720764,
+      "learning_rate": 1.3289473684210526e-05,
+      "loss": 1.5089,
+      "step": 175
+    },
+    {
+      "epoch": 1.103448275862069,
+      "grad_norm": 0.279803991317749,
+      "learning_rate": 1.2757894736842106e-05,
+      "loss": 1.5255,
+      "step": 176
+    },
+    {
+      "epoch": 1.109717868338558,
+      "grad_norm": 0.3192012310028076,
+      "learning_rate": 1.2226315789473685e-05,
+      "loss": 1.5016,
+      "step": 177
+    },
+    {
+      "epoch": 1.115987460815047,
+      "grad_norm": 0.24994367361068726,
+      "learning_rate": 1.1694736842105264e-05,
+      "loss": 0.8325,
+      "step": 178
+    },
+    {
+      "epoch": 1.1222570532915361,
+      "grad_norm": 0.2624943256378174,
+      "learning_rate": 1.1163157894736842e-05,
+      "loss": 1.6258,
+      "step": 179
+    },
+    {
+      "epoch": 1.1285266457680252,
+      "grad_norm": 0.21942251920700073,
+      "learning_rate": 1.0631578947368421e-05,
+      "loss": 1.3844,
+      "step": 180
+    },
+    {
+      "epoch": 1.134796238244514,
+      "grad_norm": 0.30005061626434326,
+      "learning_rate": 1.0100000000000002e-05,
+      "loss": 1.5267,
+      "step": 181
+    },
+    {
+      "epoch": 1.141065830721003,
+      "grad_norm": 0.2847813367843628,
+      "learning_rate": 9.56842105263158e-06,
+      "loss": 1.4495,
+      "step": 182
+    },
+    {
+      "epoch": 1.1473354231974922,
+      "grad_norm": 0.31018346548080444,
+      "learning_rate": 9.036842105263159e-06,
+      "loss": 1.5836,
+      "step": 183
+    },
+    {
+      "epoch": 1.1536050156739812,
+      "grad_norm": 0.5289681553840637,
+      "learning_rate": 8.505263157894738e-06,
+      "loss": 1.6493,
+      "step": 184
+    },
+    {
+      "epoch": 1.1598746081504703,
+      "grad_norm": 0.43757107853889465,
+      "learning_rate": 7.973684210526316e-06,
+      "loss": 1.1491,
+      "step": 185
+    },
+    {
+      "epoch": 1.1661442006269593,
+      "grad_norm": 0.21726253628730774,
+      "learning_rate": 7.442105263157894e-06,
+      "loss": 1.2735,
+      "step": 186
+    },
+    {
+      "epoch": 1.1724137931034484,
+      "grad_norm": 0.2704596221446991,
+      "learning_rate": 6.9105263157894745e-06,
+      "loss": 1.4476,
+      "step": 187
+    },
+    {
+      "epoch": 1.1786833855799372,
+      "grad_norm": 0.3226219713687897,
+      "learning_rate": 6.378947368421053e-06,
+      "loss": 1.5664,
+      "step": 188
+    },
+    {
+      "epoch": 1.1849529780564263,
+      "grad_norm": 0.28913891315460205,
+      "learning_rate": 5.847368421052632e-06,
+      "loss": 1.5248,
+      "step": 189
+    },
+    {
+      "epoch": 1.1912225705329154,
+      "grad_norm": 0.36767032742500305,
+      "learning_rate": 5.315789473684211e-06,
+      "loss": 1.5853,
+      "step": 190
+    },
+    {
+      "epoch": 1.1974921630094044,
+      "grad_norm": 0.3359694182872772,
+      "learning_rate": 4.78421052631579e-06,
+      "loss": 1.0707,
+      "step": 191
+    },
+    {
+      "epoch": 1.2037617554858935,
+      "grad_norm": 0.22743798792362213,
+      "learning_rate": 4.252631578947369e-06,
+      "loss": 1.4596,
+      "step": 192
+    },
+    {
+      "epoch": 1.2100313479623825,
+      "grad_norm": 0.25363078713417053,
+      "learning_rate": 3.721052631578947e-06,
+      "loss": 1.4679,
+      "step": 193
+    },
+    {
+      "epoch": 1.2163009404388714,
+      "grad_norm": 0.2995630204677582,
+      "learning_rate": 3.1894736842105266e-06,
+      "loss": 1.4777,
+      "step": 194
+    },
+    {
+      "epoch": 1.2225705329153604,
+      "grad_norm": 0.29661110043525696,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 1.491,
+      "step": 195
+    },
+    {
+      "epoch": 1.2288401253918495,
+      "grad_norm": 0.34250086545944214,
+      "learning_rate": 2.1263157894736844e-06,
+      "loss": 1.6321,
+      "step": 196
+    },
+    {
+      "epoch": 1.2351097178683386,
+      "grad_norm": 0.27531641721725464,
+      "learning_rate": 1.5947368421052633e-06,
+      "loss": 0.7624,
+      "step": 197
+    },
+    {
+      "epoch": 1.2413793103448276,
+      "grad_norm": 0.2552913725376129,
+      "learning_rate": 1.0631578947368422e-06,
+      "loss": 1.7947,
+      "step": 198
+    },
+    {
+      "epoch": 1.2476489028213167,
+      "grad_norm": 0.2434651106595993,
+      "learning_rate": 5.315789473684211e-07,
+      "loss": 1.4614,
+      "step": 199
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "grad_norm": 0.31214702129364014,
+      "learning_rate": 0.0,
+      "loss": 1.4839,
+      "step": 200
+    },
+    {
+      "epoch": 1.2539184952978055,
+      "eval_loss": 1.5487430095672607,
+      "eval_runtime": 21.4416,
+      "eval_samples_per_second": 100.226,
+      "eval_steps_per_second": 3.171,
+      "step": 200
     }
   ],
   "logging_steps": 1,
@@ -1112,12 +1470,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.6208921818772275e+18,
+  "total_flos": 2.1634070899998065e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null