Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a398e94268eeda71e4f6096eb44351cc73ea70481caa944ddf56fa2df68d61c
+oid sha256:eee06b40900da216685c7c59d347f7c4908db76b2a4159fea2fc495a49eed55c
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea80eba8fc7ca3cbdb97b115fc8862646e5fbef50ea4c6f7482844b100857613
+oid sha256:aee10073a68718f0de7553581be4169e4a02cdf2294f1b4523c3ff544d53f30f
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1989bc216f8ca3a286db99f5b2c575594e6dd212b2d10add3e346c236a3407dd
+oid sha256:09db57a58ea518e0f2294f8b5ef2e8e7c39da7e7a2058d1673f0fbf149d1d76b
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fc800b9f6646e104091528c5516e418587d913e67c356e93a07d74b0615ac91
+oid sha256:e08380848499664892c68a83cb93f7d549fee2c50eb31a1f7fbc4bad182dd86f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dea0680dbca982ecb815d7bcdac3f7336691ae517071283591c4b2db783b1d0f
+oid sha256:5c52ec4730a6740e87229ad52e26ad09d2aba152d627b3c7021b3cf8a55668d0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f8eaa1dd70365586ec5f94cd381f56c64ccba86f98a003eaefb284bf9660e3ea
+oid sha256:d94a218c754fec0d34c3dd1f3eff14c6e667c79c95b3a110b02a8e3e7a85cda2
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05636978579481398,
+  "epoch": 0.11273957158962795,
   "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": 14.81,
       "eval_steps_per_second": 1.854,
       "step": 25
+    },
+    {
+      "epoch": 0.058624577226606536,
+      "grad_norm": 0.0,
+      "learning_rate": 5e-05,
+      "loss": 0.0,
+      "step": 26
+    },
+    {
+      "epoch": 0.060879368658399095,
+      "grad_norm": 0.0,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0,
+      "step": 27
+    },
+    {
+      "epoch": 0.06313416009019165,
+      "grad_norm": 2.1285784244537354,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0987,
+      "step": 28
+    },
+    {
+      "epoch": 0.06538895152198422,
+      "grad_norm": 0.0,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0,
+      "step": 29
+    },
+    {
+      "epoch": 0.06764374295377677,
+      "grad_norm": 8.128816604614258,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.0764,
+      "step": 30
+    },
+    {
+      "epoch": 0.06989853438556934,
+      "grad_norm": 8.919053077697754,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.7324,
+      "step": 31
+    },
+    {
+      "epoch": 0.07215332581736189,
+      "grad_norm": 10.01648998260498,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 2.172,
+      "step": 32
+    },
+    {
+      "epoch": 0.07440811724915446,
+      "grad_norm": 6.418951988220215,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.0659,
+      "step": 33
+    },
+    {
+      "epoch": 0.07666290868094701,
+      "grad_norm": 4.666852951049805,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.2771,
+      "step": 34
+    },
+    {
+      "epoch": 0.07891770011273957,
+      "grad_norm": 3.2862226963043213,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.1777,
+      "step": 35
+    },
+    {
+      "epoch": 0.08117249154453213,
+      "grad_norm": 2.7737483978271484,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.9861,
+      "step": 36
+    },
+    {
+      "epoch": 0.0834272829763247,
+      "grad_norm": 3.1474602222442627,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.9087,
+      "step": 37
+    },
+    {
+      "epoch": 0.08568207440811725,
+      "grad_norm": 4.241426467895508,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.1816,
+      "step": 38
+    },
+    {
+      "epoch": 0.08793686583990981,
+      "grad_norm": 0.0,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0,
+      "step": 39
+    },
+    {
+      "epoch": 0.09019165727170236,
+      "grad_norm": 0.0,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.09244644870349493,
+      "grad_norm": 0.0,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0,
+      "step": 41
+    },
+    {
+      "epoch": 0.09470124013528748,
+      "grad_norm": 0.0,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0,
+      "step": 42
+    },
+    {
+      "epoch": 0.09695603156708005,
+      "grad_norm": 4.324437618255615,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6584,
+      "step": 43
+    },
+    {
+      "epoch": 0.0992108229988726,
+      "grad_norm": 5.493435859680176,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8257,
+      "step": 44
+    },
+    {
+      "epoch": 0.10146561443066517,
+      "grad_norm": 6.390080451965332,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.1197,
+      "step": 45
+    },
+    {
+      "epoch": 0.10372040586245772,
+      "grad_norm": 3.0929791927337646,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.0103,
+      "step": 46
+    },
+    {
+      "epoch": 0.10597519729425028,
+      "grad_norm": 2.387812376022339,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7846,
+      "step": 47
+    },
+    {
+      "epoch": 0.10822998872604284,
+      "grad_norm": 2.138292074203491,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.9271,
+      "step": 48
+    },
+    {
+      "epoch": 0.1104847801578354,
+      "grad_norm": 2.3450963497161865,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.51,
+      "step": 49
+    },
+    {
+      "epoch": 0.11273957158962795,
+      "grad_norm": 2.4274940490722656,
+      "learning_rate": 0.0,
+      "loss": 1.7368,
+      "step": 50
+    },
+    {
+      "epoch": 0.11273957158962795,
+      "eval_loss": NaN,
+      "eval_runtime": 201.7805,
+      "eval_samples_per_second": 14.808,
+      "eval_steps_per_second": 1.853,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -212,7 +395,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null