Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:555e4717f728e5200b380745b3e30a6e2ae69ad064193584da04678506b777b1
+oid sha256:b6bd4091960458194e393882e198f53ed049c4d05ac5beff364a982c97ba2139
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:374dc1b4fe66227557e6b5585931822513a82dbd6065c36cbfe40a1deaa68569
+oid sha256:9b999c066791f6790786cc737fa703278fbe4972be5e9ab81ee704036e5c66b6
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5d7125d59fde157735c97a5fe74a209c1eed0f1c65ae19339f3601d500f7108
+oid sha256:6ae6e44d7807882362f48e0a78973a3df08725ccff54846f5b0bb82594f73149
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:65ec78008f1e718b7b3fca657d76fcebc5307a6087003b7bc8c5a94f8dfc7698
+oid sha256:29eb020784270465a476a2acfc580006891a65014de7c32214c1d7e8a52cb94f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9985da4a0a7153067bf8765587acc55b2aaee6a36bfa7dcef5bf62be853b155
+oid sha256:89be29f3302d77b7bddb53a2a4a2cfa8fa10350e6701c8a053ba695af7a6477d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:613e322c384f9b0dbdaad5dd1d9ee1641447c972d2c9b4c9bb945b83457ef939
+oid sha256:1e57566ee20135b27695eea9481a0ad2f7d7fc6bd0a3358c76e7622dfe51a1d8
 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": 0.33662736415863037,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016092370204976565,
+  "best_metric": 0.32603439688682556,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03218474040995313,
   "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": 33.039,
       "eval_steps_per_second": 4.131,
       "step": 25
+    },
+    {
+      "epoch": 0.01673606501317563,
+      "grad_norm": 0.1330234706401825,
+      "learning_rate": 5e-05,
+      "loss": 0.2149,
+      "step": 26
+    },
+    {
+      "epoch": 0.017379759821374692,
+      "grad_norm": 0.18368133902549744,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2541,
+      "step": 27
+    },
+    {
+      "epoch": 0.018023454629573752,
+      "grad_norm": 0.1871601641178131,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2284,
+      "step": 28
+    },
+    {
+      "epoch": 0.018667149437772815,
+      "grad_norm": 0.25672218203544617,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2669,
+      "step": 29
+    },
+    {
+      "epoch": 0.01931084424597188,
+      "grad_norm": 0.22058886289596558,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2587,
+      "step": 30
+    },
+    {
+      "epoch": 0.019954539054170942,
+      "grad_norm": 0.21751423180103302,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2583,
+      "step": 31
+    },
+    {
+      "epoch": 0.020598233862370002,
+      "grad_norm": 0.24312442541122437,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2602,
+      "step": 32
+    },
+    {
+      "epoch": 0.021241928670569066,
+      "grad_norm": 0.28104859590530396,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.2916,
+      "step": 33
+    },
+    {
+      "epoch": 0.02188562347876813,
+      "grad_norm": 0.26052653789520264,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.287,
+      "step": 34
+    },
+    {
+      "epoch": 0.022529318286967193,
+      "grad_norm": 0.28748980164527893,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.2935,
+      "step": 35
+    },
+    {
+      "epoch": 0.023173013095166253,
+      "grad_norm": 0.33002161979675293,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.333,
+      "step": 36
+    },
+    {
+      "epoch": 0.023816707903365316,
+      "grad_norm": 0.4679362177848816,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.3874,
+      "step": 37
+    },
+    {
+      "epoch": 0.02446040271156438,
+      "grad_norm": 0.16794776916503906,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2197,
+      "step": 38
+    },
+    {
+      "epoch": 0.025104097519763443,
+      "grad_norm": 0.17064571380615234,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2548,
+      "step": 39
+    },
+    {
+      "epoch": 0.025747792327962506,
+      "grad_norm": 0.15181192755699158,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2173,
+      "step": 40
+    },
+    {
+      "epoch": 0.026391487136161566,
+      "grad_norm": 0.1739838421344757,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2321,
+      "step": 41
+    },
+    {
+      "epoch": 0.02703518194436063,
+      "grad_norm": 0.1635858714580536,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2087,
+      "step": 42
+    },
+    {
+      "epoch": 0.027678876752559693,
+      "grad_norm": 0.20415830612182617,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.2588,
+      "step": 43
+    },
+    {
+      "epoch": 0.028322571560758757,
+      "grad_norm": 0.21352346241474152,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2543,
+      "step": 44
+    },
+    {
+      "epoch": 0.028966266368957817,
+      "grad_norm": 0.2400074601173401,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.2767,
+      "step": 45
+    },
+    {
+      "epoch": 0.02960996117715688,
+      "grad_norm": 0.22325584292411804,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2616,
+      "step": 46
+    },
+    {
+      "epoch": 0.030253655985355943,
+      "grad_norm": 0.22152790427207947,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.2494,
+      "step": 47
+    },
+    {
+      "epoch": 0.030897350793555007,
+      "grad_norm": 0.2652023732662201,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2918,
+      "step": 48
+    },
+    {
+      "epoch": 0.03154104560175407,
+      "grad_norm": 0.41260552406311035,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.3789,
+      "step": 49
+    },
+    {
+      "epoch": 0.03218474040995313,
+      "grad_norm": 0.4374171793460846,
+      "learning_rate": 0.0,
+      "loss": 0.4499,
+      "step": 50
+    },
+    {
+      "epoch": 0.03218474040995313,
+      "eval_loss": 0.32603439688682556,
+      "eval_runtime": 633.9912,
+      "eval_samples_per_second": 33.016,
+      "eval_steps_per_second": 4.128,
+      "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": 5.9736786926882e+17,
+  "total_flos": 1.1949222410500178e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null