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:cc3baf7fcaa3f440f9faeebe75dde4cb192d1c7a256356fd6d3e98bddfc052b9
+oid sha256:e460b20799bd816f49437a79902738cd70e6dff2bcd8be6f5b29b8b1976be4aa
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7089953fce7d068f562736982133175f347e87d2adc73a762ca0ec61312b87e
+oid sha256:f9c0eb215aed21633f1e90167af44fd40cf20dba81a2c8cc26f009bfa26979b4
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d09a54888afea9c63dad1293e36c0fa1c4ed48d89d7635b800fb6375c121d21f
+oid sha256:274db1549de07216725b115e88f1de82fb7c6b9ef5c82cd28989976c6eb473f5
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed99f85ca5c5cd84f276a478186c18a0f74be406952a6b6c3aee2a3c65ca16e2
+oid sha256:c2015623df4d3a64797f5163dea0ff105cce15d043352ef4a75054d05f891795
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1c77367d898bedf399ef26a0e4628e291b6ad30472060287c26a207fc2b191ba
+oid sha256:ab74da2466efbe212b2291cf3215e9d5fb6fc22515e3974c8d840a69d7d19a7d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a0b47a3c09e43e8de2080a5713aaa652f5dc315d5579030c6e1a36c51061ba9
+oid sha256:476f0454d0a195fc84931032c9aad384756c0ecec235eb3e210cb6f928bf08a9
 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": 0.1036100909113884,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.18298261665141813,
+  "best_metric": 0.03854666277766228,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.36596523330283626,
   "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": 14.742,
       "eval_steps_per_second": 1.857,
       "step": 25
+    },
+    {
+      "epoch": 0.19030192131747484,
+      "grad_norm": 3.6858677864074707,
+      "learning_rate": 5e-05,
+      "loss": 0.3231,
+      "step": 26
+    },
+    {
+      "epoch": 0.19762122598353157,
+      "grad_norm": 2.9305121898651123,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2424,
+      "step": 27
+    },
+    {
+      "epoch": 0.20494053064958828,
+      "grad_norm": 1.5549768209457397,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1292,
+      "step": 28
+    },
+    {
+      "epoch": 0.21225983531564502,
+      "grad_norm": 0.6307731866836548,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0656,
+      "step": 29
+    },
+    {
+      "epoch": 0.21957913998170173,
+      "grad_norm": 0.11370497941970825,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0027,
+      "step": 30
+    },
+    {
+      "epoch": 0.22689844464775846,
+      "grad_norm": 0.23623719811439514,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.0066,
+      "step": 31
+    },
+    {
+      "epoch": 0.2342177493138152,
+      "grad_norm": 0.4721357822418213,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.033,
+      "step": 32
+    },
+    {
+      "epoch": 0.2415370539798719,
+      "grad_norm": 0.13088849186897278,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0035,
+      "step": 33
+    },
+    {
+      "epoch": 0.24885635864592864,
+      "grad_norm": 0.09359122067689896,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.002,
+      "step": 34
+    },
+    {
+      "epoch": 0.2561756633119854,
+      "grad_norm": 0.16688086092472076,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0045,
+      "step": 35
+    },
+    {
+      "epoch": 0.26349496797804206,
+      "grad_norm": 0.024983542039990425,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0008,
+      "step": 36
+    },
+    {
+      "epoch": 0.2708142726440988,
+      "grad_norm": 0.19985878467559814,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0033,
+      "step": 37
+    },
+    {
+      "epoch": 0.27813357731015553,
+      "grad_norm": 2.7440826892852783,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2057,
+      "step": 38
+    },
+    {
+      "epoch": 0.28545288197621227,
+      "grad_norm": 3.220916271209717,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3132,
+      "step": 39
+    },
+    {
+      "epoch": 0.292772186642269,
+      "grad_norm": 2.932844877243042,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2462,
+      "step": 40
+    },
+    {
+      "epoch": 0.3000914913083257,
+      "grad_norm": 2.592712879180908,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2169,
+      "step": 41
+    },
+    {
+      "epoch": 0.3074107959743824,
+      "grad_norm": 0.9707460999488831,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0715,
+      "step": 42
+    },
+    {
+      "epoch": 0.31473010064043916,
+      "grad_norm": 0.14762447774410248,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0051,
+      "step": 43
+    },
+    {
+      "epoch": 0.3220494053064959,
+      "grad_norm": 0.18460015952587128,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.006,
+      "step": 44
+    },
+    {
+      "epoch": 0.32936870997255263,
+      "grad_norm": 0.04780831187963486,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0018,
+      "step": 45
+    },
+    {
+      "epoch": 0.3366880146386093,
+      "grad_norm": 0.04981381073594093,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.002,
+      "step": 46
+    },
+    {
+      "epoch": 0.34400731930466605,
+      "grad_norm": 0.020230049267411232,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.0006,
+      "step": 47
+    },
+    {
+      "epoch": 0.3513266239707228,
+      "grad_norm": 0.013130583800375462,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0005,
+      "step": 48
+    },
+    {
+      "epoch": 0.3586459286367795,
+      "grad_norm": 0.012524500489234924,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0006,
+      "step": 49
+    },
+    {
+      "epoch": 0.36596523330283626,
+      "grad_norm": 1.1961338520050049,
+      "learning_rate": 0.0,
+      "loss": 0.0142,
+      "step": 50
+    },
+    {
+      "epoch": 0.36596523330283626,
+      "eval_loss": 0.03854666277766228,
+      "eval_runtime": 62.4179,
+      "eval_samples_per_second": 14.755,
+      "eval_steps_per_second": 1.858,
+      "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": 2.822877455843328e+17,
+  "total_flos": 5.645754911686656e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null