Training in progress, step 200, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:824f09925e06dade0980b7b6f2673ad9313a1860d3955d0f6ec2c24b8d19dac8
+oid sha256:652a576a3e82b1634213820a1aea0edb84bd2d71efa1ae2be11d1a87b6714d03
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0385716b1e421bc04c934b8f7557055a72735142692c3a1dba5e7471da2b24ea
+oid sha256:282f7d1441a515d81fa7c0deb938fe42c0cc64293fa807b99874adb6156a3d1c
 size 71878612

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254216cd1bfa077aac79ddf3aa991dd86be3d924b5693193fb57c269a3229fc5
+oid sha256:b4bd11b79962093f63166c032f33c6677ca9cbceb16acc1461698f1032b38edd
 size 15984

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98e93359c59ca311edbe89f16d5f0231bbab585603f1b0be35494b54b91a1828
+oid sha256:fc4e63c06c47cb43dde79e4b3b024990c15702f1c7eb21b8675d83e7fcdcdcc2
 size 15984

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4653009b10dd48c6a46766f75f0f4c3beaaf299dba0329a995450677bc18ca49
+oid sha256:2d247ae4f3cdb291a56293b5328221d2c7e727c51548f1d2997d5f4944ebe665
 size 15984

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5415a05b9817c8d92f7f2ef1613eb04335e657362fb7e72f840691f4ab31dc13
+oid sha256:f424cff57f9dd9fb41d7c1299f5d4913f6d638fe40cbd7332bc1709bed82fc7d
 size 15984

last-checkpoint/rng_state_4.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfa835537978680c561926622f8191526b11e7115b2608526fb7b423c2761adb
+oid sha256:a0926c04d60517b6000c6be2bddbbb896cbf28c3a6d36bd54d59dffb988bc8bd
 size 15984

last-checkpoint/rng_state_5.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d99df497585478105a47995bca143a42ccb608ae08ea70b6fa51f3ac15d28c3
+oid sha256:c45cf1b097f53f89a6635f6ee0fd8a1f0bca642c10e89bb54428d8aa25ae35f2
 size 15984

last-checkpoint/rng_state_6.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:975a341ff81520c4a9e0bf9eb1d42a63cc63f204e2529f8679b8c5258e9f3765
+oid sha256:39e1f3c1f1958874e2d94af61c32f582608983ece6d656adbdf83fcbde6094f3
 size 15984

last-checkpoint/rng_state_7.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:168986a5fc9ca577afbaa24ced94bae1c6aeb7a2e5577615a8f9fb71b2478a65
+oid sha256:8af9db006550ee2e28f87d97b3a9b7eb99a19c3a830617d306435c3f433d7277
 size 15984

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4a1d4966bbb3ac4136a17b84f52768cf52a77159d3c183b2a8af35a019ee542b
+oid sha256:561a6b9ecae5b6527dce41502ac783b23e6868cde355bb5233897b623a71ea0d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.138585329055786,
-  "best_model_checkpoint": "miner_id_24/checkpoint-150",
-  "epoch": 0.05185825410544512,
+  "best_metric": 2.1342074871063232,
+  "best_model_checkpoint": "miner_id_24/checkpoint-200",
+  "epoch": 0.06914433880726016,
   "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": 301.878,
       "eval_steps_per_second": 9.434,
       "step": 150
+    },
+    {
+      "epoch": 0.05220397579948142,
+      "grad_norm": 0.21927562355995178,
+      "learning_rate": 1.5842976134953143e-05,
+      "loss": 1.4091,
+      "step": 151
+    },
+    {
+      "epoch": 0.05254969749351772,
+      "grad_norm": 0.30813464522361755,
+      "learning_rate": 1.5236924002103082e-05,
+      "loss": 1.6268,
+      "step": 152
+    },
+    {
+      "epoch": 0.05289541918755402,
+      "grad_norm": 0.42510512471199036,
+      "learning_rate": 1.4640649137138753e-05,
+      "loss": 2.0049,
+      "step": 153
+    },
+    {
+      "epoch": 0.05324114088159032,
+      "grad_norm": 0.5293447971343994,
+      "learning_rate": 1.4054314555654462e-05,
+      "loss": 2.2239,
+      "step": 154
+    },
+    {
+      "epoch": 0.05358686257562662,
+      "grad_norm": 0.7817128300666809,
+      "learning_rate": 1.3478080555670289e-05,
+      "loss": 2.3194,
+      "step": 155
+    },
+    {
+      "epoch": 0.05393258426966292,
+      "grad_norm": 2.0287394523620605,
+      "learning_rate": 1.2912104673808168e-05,
+      "loss": 2.6797,
+      "step": 156
+    },
+    {
+      "epoch": 0.054278305963699224,
+      "grad_norm": 0.24206052720546722,
+      "learning_rate": 1.2356541642222938e-05,
+      "loss": 1.331,
+      "step": 157
+    },
+    {
+      "epoch": 0.054624027657735524,
+      "grad_norm": 0.2946099042892456,
+      "learning_rate": 1.1811543346300201e-05,
+      "loss": 1.5435,
+      "step": 158
+    },
+    {
+      "epoch": 0.054969749351771825,
+      "grad_norm": 0.43680340051651,
+      "learning_rate": 1.1277258783132271e-05,
+      "loss": 2.0719,
+      "step": 159
+    },
+    {
+      "epoch": 0.055315471045808126,
+      "grad_norm": 0.5616028904914856,
+      "learning_rate": 1.0753834020783934e-05,
+      "loss": 2.2293,
+      "step": 160
+    },
+    {
+      "epoch": 0.05566119273984443,
+      "grad_norm": 0.7067009210586548,
+      "learning_rate": 1.024141215835884e-05,
+      "loss": 2.2842,
+      "step": 161
+    },
+    {
+      "epoch": 0.05600691443388073,
+      "grad_norm": 1.4020217657089233,
+      "learning_rate": 9.740133286877686e-06,
+      "loss": 2.5166,
+      "step": 162
+    },
+    {
+      "epoch": 0.05635263612791703,
+      "grad_norm": 0.2626679837703705,
+      "learning_rate": 9.25013445097869e-06,
+      "loss": 1.3913,
+      "step": 163
+    },
+    {
+      "epoch": 0.05669835782195333,
+      "grad_norm": 0.27605897188186646,
+      "learning_rate": 8.771549611450978e-06,
+      "loss": 1.5436,
+      "step": 164
+    },
+    {
+      "epoch": 0.05704407951598963,
+      "grad_norm": 0.39887532591819763,
+      "learning_rate": 8.304509608611044e-06,
+      "loss": 2.0188,
+      "step": 165
+    },
+    {
+      "epoch": 0.05738980121002593,
+      "grad_norm": 0.548843502998352,
+      "learning_rate": 7.849142126532288e-06,
+      "loss": 2.2028,
+      "step": 166
+    },
+    {
+      "epoch": 0.05773552290406223,
+      "grad_norm": 0.6388208270072937,
+      "learning_rate": 7.405571658137504e-06,
+      "loss": 2.1768,
+      "step": 167
+    },
+    {
+      "epoch": 0.05808124459809853,
+      "grad_norm": 1.2126517295837402,
+      "learning_rate": 6.973919471163731e-06,
+      "loss": 2.4696,
+      "step": 168
+    },
+    {
+      "epoch": 0.058426966292134834,
+      "grad_norm": 0.3545350730419159,
+      "learning_rate": 6.554303575008853e-06,
+      "loss": 1.3924,
+      "step": 169
+    },
+    {
+      "epoch": 0.058772687986171135,
+      "grad_norm": 0.2450939565896988,
+      "learning_rate": 6.146838688469063e-06,
+      "loss": 1.4214,
+      "step": 170
+    },
+    {
+      "epoch": 0.059118409680207436,
+      "grad_norm": 0.35611891746520996,
+      "learning_rate": 5.751636208375797e-06,
+      "loss": 1.8901,
+      "step": 171
+    },
+    {
+      "epoch": 0.05946413137424374,
+      "grad_norm": 0.49131643772125244,
+      "learning_rate": 5.3688041791410625e-06,
+      "loss": 2.2007,
+      "step": 172
+    },
+    {
+      "epoch": 0.05980985306828004,
+      "grad_norm": 0.6172560453414917,
+      "learning_rate": 4.998447263219096e-06,
+      "loss": 2.346,
+      "step": 173
+    },
+    {
+      "epoch": 0.06015557476231634,
+      "grad_norm": 1.04538893699646,
+      "learning_rate": 4.640666712492712e-06,
+      "loss": 2.4448,
+      "step": 174
+    },
+    {
+      "epoch": 0.06050129645635264,
+      "grad_norm": 3.5751025676727295,
+      "learning_rate": 4.295560340592067e-06,
+      "loss": 2.6621,
+      "step": 175
+    },
+    {
+      "epoch": 0.06084701815038894,
+      "grad_norm": 0.22359122335910797,
+      "learning_rate": 3.963222496153378e-06,
+      "loss": 1.4161,
+      "step": 176
+    },
+    {
+      "epoch": 0.06119273984442524,
+      "grad_norm": 0.3183920085430145,
+      "learning_rate": 3.6437440370249446e-06,
+      "loss": 1.698,
+      "step": 177
+    },
+    {
+      "epoch": 0.06153846153846154,
+      "grad_norm": 0.4430980086326599,
+      "learning_rate": 3.3372123054275022e-06,
+      "loss": 2.1287,
+      "step": 178
+    },
+    {
+      "epoch": 0.061884183232497836,
+      "grad_norm": 0.5623943209648132,
+      "learning_rate": 3.0437111040757805e-06,
+      "loss": 2.2807,
+      "step": 179
+    },
+    {
+      "epoch": 0.06222990492653414,
+      "grad_norm": 0.8057716488838196,
+      "learning_rate": 2.7633206732676334e-06,
+      "loss": 2.3764,
+      "step": 180
+    },
+    {
+      "epoch": 0.06257562662057044,
+      "grad_norm": 2.1826820373535156,
+      "learning_rate": 2.49611766894717e-06,
+      "loss": 2.7555,
+      "step": 181
+    },
+    {
+      "epoch": 0.06292134831460675,
+      "grad_norm": 0.23808926343917847,
+      "learning_rate": 2.24217514174776e-06,
+      "loss": 1.401,
+      "step": 182
+    },
+    {
+      "epoch": 0.06326707000864304,
+      "grad_norm": 0.28936347365379333,
+      "learning_rate": 2.0015625170207446e-06,
+      "loss": 1.6276,
+      "step": 183
+    },
+    {
+      "epoch": 0.06361279170267935,
+      "grad_norm": 0.422021746635437,
+      "learning_rate": 1.7743455758552233e-06,
+      "loss": 2.1177,
+      "step": 184
+    },
+    {
+      "epoch": 0.06395851339671564,
+      "grad_norm": 0.523854672908783,
+      "learning_rate": 1.5605864370941509e-06,
+      "loss": 2.0992,
+      "step": 185
+    },
+    {
+      "epoch": 0.06430423509075195,
+      "grad_norm": 0.6923096179962158,
+      "learning_rate": 1.360343540351707e-06,
+      "loss": 2.1482,
+      "step": 186
+    },
+    {
+      "epoch": 0.06464995678478824,
+      "grad_norm": 1.487024188041687,
+      "learning_rate": 1.1736716300364373e-06,
+      "loss": 2.6114,
+      "step": 187
+    },
+    {
+      "epoch": 0.06499567847882455,
+      "grad_norm": 0.2701355516910553,
+      "learning_rate": 1.0006217403847229e-06,
+      "loss": 1.4045,
+      "step": 188
+    },
+    {
+      "epoch": 0.06534140017286084,
+      "grad_norm": 0.2602534294128418,
+      "learning_rate": 8.412411815084993e-07,
+      "loss": 1.4839,
+      "step": 189
+    },
+    {
+      "epoch": 0.06568712186689715,
+      "grad_norm": 0.37865686416625977,
+      "learning_rate": 6.955735264611615e-07,
+      "loss": 1.9496,
+      "step": 190
+    },
+    {
+      "epoch": 0.06603284356093345,
+      "grad_norm": 0.49220287799835205,
+      "learning_rate": 5.636585993251069e-07,
+      "loss": 2.2272,
+      "step": 191
+    },
+    {
+      "epoch": 0.06637856525496975,
+      "grad_norm": 0.6344109177589417,
+      "learning_rate": 4.4553246432426505e-07,
+      "loss": 2.2781,
+      "step": 192
+    },
+    {
+      "epoch": 0.06672428694900605,
+      "grad_norm": 1.2186602354049683,
+      "learning_rate": 3.4122741596445473e-07,
+      "loss": 2.4822,
+      "step": 193
+    },
+    {
+      "epoch": 0.06707000864304236,
+      "grad_norm": 0.3830315172672272,
+      "learning_rate": 2.5077197020441776e-07,
+      "loss": 1.3769,
+      "step": 194
+    },
+    {
+      "epoch": 0.06741573033707865,
+      "grad_norm": 0.2576148211956024,
+      "learning_rate": 1.741908566598378e-07,
+      "loss": 1.4397,
+      "step": 195
+    },
+    {
+      "epoch": 0.06776145203111496,
+      "grad_norm": 0.3489200174808502,
+      "learning_rate": 1.1150501184249872e-07,
+      "loss": 1.8016,
+      "step": 196
+    },
+    {
+      "epoch": 0.06810717372515125,
+      "grad_norm": 0.47421106696128845,
+      "learning_rate": 6.27315734364584e-08,
+      "loss": 2.2056,
+      "step": 197
+    },
+    {
+      "epoch": 0.06845289541918756,
+      "grad_norm": 0.6165635585784912,
+      "learning_rate": 2.7883875612771503e-08,
+      "loss": 2.1757,
+      "step": 198
+    },
+    {
+      "epoch": 0.06879861711322385,
+      "grad_norm": 0.9678878784179688,
+      "learning_rate": 6.971445384080788e-09,
+      "loss": 2.3874,
+      "step": 199
+    },
+    {
+      "epoch": 0.06914433880726016,
+      "grad_norm": 3.845649242401123,
+      "learning_rate": 0.0,
+      "loss": 2.7224,
+      "step": 200
+    },
+    {
+      "epoch": 0.06914433880726016,
+      "eval_loss": 2.1342074871063232,
+      "eval_runtime": 128.6644,
+      "eval_samples_per_second": 302.904,
+      "eval_steps_per_second": 9.466,
+      "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": 9.515693955350528e+16,
+  "total_flos": 1.2688235979761254e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null