Training in progress, step 49, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aa2a517ff3e9d377f0eeaa601f09ea191bf212ac861b9d7354bb8cc156455a0
+oid sha256:a391150701be4aed32dc47f7deaf8c7fc4a3e47f8768f92908c603028a988d6e
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5a17648c864a3207e599902fd6cfb64c17a2d26d12f2eef1b8307dc0b0cc37f
+oid sha256:4d3234deda7640bc12807e3712ee73bcd6a89dfc58af9ce112928b41b0c0aadc
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ba7af0ebc055e755eec7a0ab7cdd2873369c12154336c83e8af5b04c367741f
+oid sha256:dee3880f73947473f81cbac59354bceb5a3de54750083dfa6736a5595ebed1ad
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:faf14c981feadff0b2e8b87dc2785eb216aac5d387ab302c09f2af13733dfa3f
+oid sha256:90a7301de989dc531e6f5af523d05f830b5c1f4b3a53567fd77f2b459c2ef9f5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7843d84ed4fd497fe14180ddd3335c81592a5f4ed9a04fc44db0107049af9198
+oid sha256:52d6115dd145d35ff8c079eff3691e6f0115627abe797fe28ec82bf56914d08f
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:352a67a7165bd4b15bae7a5f1709a05bbf7a3d662dfbca20eca738f95733d1ac
+oid sha256:2dc9100dc6f31a55b6fbfc1203305c3f974d6b04aae890fecc67f0ca636cbe72
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:840657c72d1644d32902ed3baed4169f8fa8749780cabcde307874a07544bcbd
+oid sha256:25704ee5478cd4521ee5db3e9e14050e9c72edebe1088acf05e49ba2bb8ed7fb
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 0.5065415501594543,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.556420233463035,
+  "epoch": 3.0505836575875485,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 49,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,174 @@
       "eval_samples_per_second": 23.328,
       "eval_steps_per_second": 3.024,
       "step": 25
+    },
+    {
+      "epoch": 1.6186770428015564,
+      "grad_norm": 0.7603065371513367,
+      "learning_rate": 4.832925114961629e-05,
+      "loss": 7.9956,
+      "step": 26
+    },
+    {
+      "epoch": 1.6809338521400778,
+      "grad_norm": 0.7943618893623352,
+      "learning_rate": 4.4995215418795085e-05,
+      "loss": 7.7549,
+      "step": 27
+    },
+    {
+      "epoch": 1.7431906614785992,
+      "grad_norm": 0.967389702796936,
+      "learning_rate": 4.1683532270843504e-05,
+      "loss": 7.6843,
+      "step": 28
+    },
+    {
+      "epoch": 1.8054474708171206,
+      "grad_norm": 0.7394790053367615,
+      "learning_rate": 3.840899248662358e-05,
+      "loss": 8.0537,
+      "step": 29
+    },
+    {
+      "epoch": 1.867704280155642,
+      "grad_norm": 0.7868384718894958,
+      "learning_rate": 3.5186220955718306e-05,
+      "loss": 7.7551,
+      "step": 30
+    },
+    {
+      "epoch": 1.9299610894941635,
+      "grad_norm": 1.0688693523406982,
+      "learning_rate": 3.202961135812437e-05,
+      "loss": 8.1714,
+      "step": 31
+    },
+    {
+      "epoch": 1.9922178988326849,
+      "grad_norm": 0.8963145017623901,
+      "learning_rate": 2.895326187858326e-05,
+      "loss": 7.9336,
+      "step": 32
+    },
+    {
+      "epoch": 2.054474708171206,
+      "grad_norm": 0.7154244184494019,
+      "learning_rate": 2.5970912240665813e-05,
+      "loss": 7.4189,
+      "step": 33
+    },
+    {
+      "epoch": 2.1167315175097277,
+      "grad_norm": 1.0934628248214722,
+      "learning_rate": 2.3095882341831372e-05,
+      "loss": 7.9469,
+      "step": 34
+    },
+    {
+      "epoch": 2.178988326848249,
+      "grad_norm": 0.7415445446968079,
+      "learning_rate": 2.0341012763532243e-05,
+      "loss": 7.5521,
+      "step": 35
+    },
+    {
+      "epoch": 2.2412451361867705,
+      "grad_norm": 0.7995844483375549,
+      "learning_rate": 1.771860742205988e-05,
+      "loss": 7.5147,
+      "step": 36
+    },
+    {
+      "epoch": 2.3035019455252916,
+      "grad_norm": 1.1787042617797852,
+      "learning_rate": 1.5240378616267886e-05,
+      "loss": 7.7859,
+      "step": 37
+    },
+    {
+      "epoch": 2.3657587548638133,
+      "grad_norm": 0.7349408864974976,
+      "learning_rate": 1.2917394717602121e-05,
+      "loss": 7.8634,
+      "step": 38
+    },
+    {
+      "epoch": 2.4280155642023344,
+      "grad_norm": 0.8099451065063477,
+      "learning_rate": 1.0760030736066951e-05,
+      "loss": 8.0651,
+      "step": 39
+    },
+    {
+      "epoch": 2.490272373540856,
+      "grad_norm": 0.8851613402366638,
+      "learning_rate": 8.777921982911996e-06,
+      "loss": 7.5255,
+      "step": 40
+    },
+    {
+      "epoch": 2.5525291828793772,
+      "grad_norm": 0.8391734957695007,
+      "learning_rate": 6.979921036993042e-06,
+      "loss": 8.0917,
+      "step": 41
+    },
+    {
+      "epoch": 2.614785992217899,
+      "grad_norm": 1.488593339920044,
+      "learning_rate": 5.374058207005944e-06,
+      "loss": 7.9092,
+      "step": 42
+    },
+    {
+      "epoch": 2.6770428015564205,
+      "grad_norm": 1.0373982191085815,
+      "learning_rate": 3.967505666178556e-06,
+      "loss": 8.0546,
+      "step": 43
+    },
+    {
+      "epoch": 2.7392996108949417,
+      "grad_norm": 0.8613387942314148,
+      "learning_rate": 2.7665454196040664e-06,
+      "loss": 7.4587,
+      "step": 44
+    },
+    {
+      "epoch": 2.801556420233463,
+      "grad_norm": 0.8068078756332397,
+      "learning_rate": 1.7765412472811771e-06,
+      "loss": 7.8842,
+      "step": 45
+    },
+    {
+      "epoch": 2.8638132295719845,
+      "grad_norm": 0.713803231716156,
+      "learning_rate": 1.0019147481706625e-06,
+      "loss": 7.6852,
+      "step": 46
+    },
+    {
+      "epoch": 2.926070038910506,
+      "grad_norm": 0.7315906286239624,
+      "learning_rate": 4.461255922609986e-07,
+      "loss": 7.5289,
+      "step": 47
+    },
+    {
+      "epoch": 2.9883268482490273,
+      "grad_norm": 0.807794451713562,
+      "learning_rate": 1.1165606884234181e-07,
+      "loss": 7.7788,
+      "step": 48
+    },
+    {
+      "epoch": 3.0505836575875485,
+      "grad_norm": 0.7264207005500793,
+      "learning_rate": 0.0,
+      "loss": 7.7754,
+      "step": 49
     }
   ],
   "logging_steps": 1,
@@ -221,12 +389,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.5037572799266816e+17,
+  "total_flos": 1.0781614054771261e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null