Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:49580437d5a45a419edc4e79f0c27d54e5bf90d83e09895f5ca1a41396c0aaef
+oid sha256:a6a5ba8f9b5fbca3499435897bdc700e1e5963e4eec4efe413f9153bd2d98acb
 size 166182480

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc8ffba8484f6bbd067452eb18f5e577f15650a50b4027175f41a9a95ad5e359
+oid sha256:b983ff6bab6ad35d2c215c954c93689b7b625e78627baa00dc545a474e86d772
 size 332574358

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:40e83082cedc5ac7c69f21b438802d105848abfa7f6a53d3e01662798b7208c2
+oid sha256:f3829a38cd5e220a3a0cca3ad47f3eba3204cbc2a1f2484428bddf314994d5dc
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7adebb8f7186b2f0583fbc6e3def9adb1255f2859cee821fb08613a8e673847d
+oid sha256:bfe04e06da5f7b4bfcd93b0d52cb95a6683f6189615948e1b2893be090644e3f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8dca689fc14670da943761ed7485923bdda914d5cfd82f95f1653e02aefb9ce7
+oid sha256:0d8b6019a4d19c309f5a404270cf6051488f484ab521431635ec2b37fb638bb1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e28207640e52511642546c88adfffc9ef80828051520e8d3e8d79f6222a85b68
+oid sha256:0528420e533b76139c53640be57570ec87d06c8f84e5be0568eb4e35c46bf379
 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": 1.244596004486084,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.039615727443795185,
+  "best_metric": 1.2211970090866089,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.07923145488759037,
   "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": 49.28,
       "eval_steps_per_second": 6.166,
       "step": 25
+    },
+    {
+      "epoch": 0.041200356541546995,
+      "grad_norm": 0.69757080078125,
+      "learning_rate": 5e-05,
+      "loss": 1.1166,
+      "step": 26
+    },
+    {
+      "epoch": 0.0427849856392988,
+      "grad_norm": 0.7477506399154663,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.1383,
+      "step": 27
+    },
+    {
+      "epoch": 0.04436961473705061,
+      "grad_norm": 0.8282836675643921,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3684,
+      "step": 28
+    },
+    {
+      "epoch": 0.045954243834802413,
+      "grad_norm": 0.7872549891471863,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.2038,
+      "step": 29
+    },
+    {
+      "epoch": 0.047538872932554224,
+      "grad_norm": 0.848495602607727,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2335,
+      "step": 30
+    },
+    {
+      "epoch": 0.049123502030306035,
+      "grad_norm": 0.8855195045471191,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2782,
+      "step": 31
+    },
+    {
+      "epoch": 0.05070813112805784,
+      "grad_norm": 0.9403620362281799,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3107,
+      "step": 32
+    },
+    {
+      "epoch": 0.05229276022580965,
+      "grad_norm": 0.9452459812164307,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2787,
+      "step": 33
+    },
+    {
+      "epoch": 0.05387738932356145,
+      "grad_norm": 1.062166452407837,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3067,
+      "step": 34
+    },
+    {
+      "epoch": 0.055462018421313264,
+      "grad_norm": 1.1450388431549072,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3326,
+      "step": 35
+    },
+    {
+      "epoch": 0.05704664751906507,
+      "grad_norm": 1.1706715822219849,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3093,
+      "step": 36
+    },
+    {
+      "epoch": 0.05863127661681688,
+      "grad_norm": 1.3499324321746826,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.4092,
+      "step": 37
+    },
+    {
+      "epoch": 0.06021590571456868,
+      "grad_norm": 0.7645833492279053,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1249,
+      "step": 38
+    },
+    {
+      "epoch": 0.06180053481232049,
+      "grad_norm": 0.7073479294776917,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2296,
+      "step": 39
+    },
+    {
+      "epoch": 0.0633851639100723,
+      "grad_norm": 0.7113702893257141,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.1356,
+      "step": 40
+    },
+    {
+      "epoch": 0.0649697930078241,
+      "grad_norm": 0.7894446849822998,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.2843,
+      "step": 41
+    },
+    {
+      "epoch": 0.06655442210557591,
+      "grad_norm": 0.767471432685852,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1519,
+      "step": 42
+    },
+    {
+      "epoch": 0.06813905120332772,
+      "grad_norm": 0.9337680339813232,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.3667,
+      "step": 43
+    },
+    {
+      "epoch": 0.06972368030107953,
+      "grad_norm": 0.8977687358856201,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2943,
+      "step": 44
+    },
+    {
+      "epoch": 0.07130830939883133,
+      "grad_norm": 0.8998286128044128,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.171,
+      "step": 45
+    },
+    {
+      "epoch": 0.07289293849658314,
+      "grad_norm": 0.9295518398284912,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1533,
+      "step": 46
+    },
+    {
+      "epoch": 0.07447756759433495,
+      "grad_norm": 1.0339083671569824,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3036,
+      "step": 47
+    },
+    {
+      "epoch": 0.07606219669208676,
+      "grad_norm": 1.183160424232483,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.3415,
+      "step": 48
+    },
+    {
+      "epoch": 0.07764682578983857,
+      "grad_norm": 1.2279109954833984,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2925,
+      "step": 49
+    },
+    {
+      "epoch": 0.07923145488759037,
+      "grad_norm": 1.5355768203735352,
+      "learning_rate": 0.0,
+      "loss": 1.2531,
+      "step": 50
+    },
+    {
+      "epoch": 0.07923145488759037,
+      "eval_loss": 1.2211970090866089,
+      "eval_runtime": 86.1186,
+      "eval_samples_per_second": 49.374,
+      "eval_steps_per_second": 6.178,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -221,12 +404,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.1240447254528e+16,
+  "total_flos": 1.62480894509056e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null