Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7dbdfc4bd3c24e18897e94a179ba79a4fa854765624d3f1864fa92b1b6719b59
+oid sha256:31fa4cc3b61079e987f0fbff93f96c1bba07a05ee9a4d32a238a9759f970f474
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3e36793e0faed1def690355178eee50e0aa54bb19231413b758003fed12c41c
+oid sha256:0f87b47845552c8f845ba41130d6252db2bb6936eb3f8ba0abb92c873764db37
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e6e5cf7322001d3afc8ba3860a079c111718b9bf971a8b2ff6a48fa53b10c497
+oid sha256:d452aa6fceb59a5bf6301cce0e16a327b8ff9853dd95385dfa7c875ce49348aa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d083a6d8e8ddc3ef2f63dd4813ab1461a3d40fa4a10071753a9616997642cf6
+oid sha256:e897464048de439567641425f84cd56d36a8d4fc23915750434e867194243fbe
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed9af755cd9c41842cb14aaa22143bfd9b5b68bb969ad27fc9e58846777f2ed4
+oid sha256:88bc856310e89db4156830f89a4788452266e0b8fc6e6c5ae126a1d50d8b3d68
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c41fb047f886595b39750a3f573ee622291ad10ba4039165a727a75dde8d4ef3
+oid sha256:9069763201acfccd253412cfdf72c7e969625e688bf63270a5198405ecc8d6e0
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6489320397377014,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.26999662504218697,
+  "best_metric": 0.64404296875,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.5399932500843739,
   "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": 22.935,
       "eval_steps_per_second": 5.963,
       "step": 25
+    },
+    {
+      "epoch": 0.28079649004387447,
+      "grad_norm": 0.08643216639757156,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 0.509,
+      "step": 26
+    },
+    {
+      "epoch": 0.2915963550455619,
+      "grad_norm": 0.11556915938854218,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 0.5407,
+      "step": 27
+    },
+    {
+      "epoch": 0.3023962200472494,
+      "grad_norm": 0.13107015192508698,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 0.6307,
+      "step": 28
+    },
+    {
+      "epoch": 0.31319608504893687,
+      "grad_norm": 0.14084775745868683,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.5932,
+      "step": 29
+    },
+    {
+      "epoch": 0.32399595005062437,
+      "grad_norm": 0.1543428748846054,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.629,
+      "step": 30
+    },
+    {
+      "epoch": 0.3347958150523119,
+      "grad_norm": 0.15614484250545502,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.6655,
+      "step": 31
+    },
+    {
+      "epoch": 0.3455956800539993,
+      "grad_norm": 0.17313002049922943,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.6806,
+      "step": 32
+    },
+    {
+      "epoch": 0.3563955450556868,
+      "grad_norm": 0.19408182799816132,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.7165,
+      "step": 33
+    },
+    {
+      "epoch": 0.36719541005737427,
+      "grad_norm": 0.16677334904670715,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.6582,
+      "step": 34
+    },
+    {
+      "epoch": 0.3779952750590618,
+      "grad_norm": 0.18193095922470093,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.6302,
+      "step": 35
+    },
+    {
+      "epoch": 0.3887951400607492,
+      "grad_norm": 0.20297932624816895,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.66,
+      "step": 36
+    },
+    {
+      "epoch": 0.3995950050624367,
+      "grad_norm": 0.23466193675994873,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.649,
+      "step": 37
+    },
+    {
+      "epoch": 0.4103948700641242,
+      "grad_norm": 0.09354816377162933,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.5787,
+      "step": 38
+    },
+    {
+      "epoch": 0.4211947350658117,
+      "grad_norm": 0.08726412057876587,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.5915,
+      "step": 39
+    },
+    {
+      "epoch": 0.4319946000674992,
+      "grad_norm": 0.10443510860204697,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.616,
+      "step": 40
+    },
+    {
+      "epoch": 0.4427944650691866,
+      "grad_norm": 0.123623326420784,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.5388,
+      "step": 41
+    },
+    {
+      "epoch": 0.45359433007087413,
+      "grad_norm": 0.12465845048427582,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.6571,
+      "step": 42
+    },
+    {
+      "epoch": 0.4643941950725616,
+      "grad_norm": 0.12447262555360794,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.6103,
+      "step": 43
+    },
+    {
+      "epoch": 0.4751940600742491,
+      "grad_norm": 0.13273553550243378,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.6815,
+      "step": 44
+    },
+    {
+      "epoch": 0.48599392507593653,
+      "grad_norm": 0.13501819968223572,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.6672,
+      "step": 45
+    },
+    {
+      "epoch": 0.49679379007762403,
+      "grad_norm": 0.159222811460495,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.6671,
+      "step": 46
+    },
+    {
+      "epoch": 0.5075936550793115,
+      "grad_norm": 0.1639116108417511,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.6808,
+      "step": 47
+    },
+    {
+      "epoch": 0.518393520080999,
+      "grad_norm": 0.18950490653514862,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.7195,
+      "step": 48
+    },
+    {
+      "epoch": 0.5291933850826864,
+      "grad_norm": 0.20681390166282654,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6118,
+      "step": 49
+    },
+    {
+      "epoch": 0.5399932500843739,
+      "grad_norm": 0.30206191539764404,
+      "learning_rate": 1e-05,
+      "loss": 0.5832,
+      "step": 50
+    },
+    {
+      "epoch": 0.5399932500843739,
+      "eval_loss": 0.64404296875,
+      "eval_runtime": 2.1858,
+      "eval_samples_per_second": 22.875,
+      "eval_steps_per_second": 5.948,
+      "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": 5.302648335394406e+16,
+  "total_flos": 1.0601985626813235e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null