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:ede6add8bb19725d2e19626b4524d534b1ae78f18320bad36446166771ae2ba3
+oid sha256:64b361d8d499db02fba35bf97383c087aa72260aee60e48415d2e20496b5ab54
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dad8edd3d3bb71fa9a38d80123379aeba09d67cb7f0a674025e75907ffdc1d2b
+oid sha256:c14fc2378cb80f45fe15d78583fc094b5a80fcc1cf98ce4175c431bdcac29dd1
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:94f39912007c1faca694fe79493c3d6acd9f4feb838da034b2027dff8210f7f6
+oid sha256:5751fa2f5de37dcdc04130fc8284486189113f8850da3644b3e29c675ee39e88
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:641c33ea3eb2b6d40499515b60777c9191b1b453a6d33594334c83d1ec68b257
+oid sha256:236c64266a2188ec414600e4b833db04ceeb9f24d05f2365425aad31a6472342
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ab8e9136e1010481c8071c4df01e10e7976e0c29fed504b66c58004e5df73e2
+oid sha256:e7300b764106974e714c33a7c1c55a3d43413833ba3e3745aa36fe7998aa79c0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15d0c1f287184b06f0512e946c89f61cecfe798461024f058c8bf1cd9af3828b
+oid sha256:e05513729ad8ebae1c123e62f00377c72813b84af97503b18e0b9f6f987aea90
 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": 0.22786331176757812,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.012324377618930245,
+  "best_metric": 0.18751490116119385,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02464875523786049,
   "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": 11.47,
       "eval_steps_per_second": 2.982,
       "step": 25
+    },
+    {
+      "epoch": 0.012817352723687454,
+      "grad_norm": 10.412202835083008,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 20.6695,
+      "step": 26
+    },
+    {
+      "epoch": 0.013310327828444664,
+      "grad_norm": 11.937228202819824,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 14.0204,
+      "step": 27
+    },
+    {
+      "epoch": 0.013803302933201873,
+      "grad_norm": 11.14134407043457,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 8.6804,
+      "step": 28
+    },
+    {
+      "epoch": 0.014296278037959083,
+      "grad_norm": 8.361931800842285,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 7.9653,
+      "step": 29
+    },
+    {
+      "epoch": 0.014789253142716292,
+      "grad_norm": 6.868744850158691,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.8276,
+      "step": 30
+    },
+    {
+      "epoch": 0.015282228247473502,
+      "grad_norm": 6.664088726043701,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 5.96,
+      "step": 31
+    },
+    {
+      "epoch": 0.01577520335223071,
+      "grad_norm": 5.193835258483887,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 5.2211,
+      "step": 32
+    },
+    {
+      "epoch": 0.01626817845698792,
+      "grad_norm": 4.7439727783203125,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 4.364,
+      "step": 33
+    },
+    {
+      "epoch": 0.01676115356174513,
+      "grad_norm": 4.816511631011963,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 4.0719,
+      "step": 34
+    },
+    {
+      "epoch": 0.01725412866650234,
+      "grad_norm": 4.376865386962891,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 4.1279,
+      "step": 35
+    },
+    {
+      "epoch": 0.017747103771259553,
+      "grad_norm": 6.949431419372559,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 5.7129,
+      "step": 36
+    },
+    {
+      "epoch": 0.018240078876016762,
+      "grad_norm": 7.87053108215332,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 4.8771,
+      "step": 37
+    },
+    {
+      "epoch": 0.018733053980773972,
+      "grad_norm": 8.47607707977295,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 15.1602,
+      "step": 38
+    },
+    {
+      "epoch": 0.01922602908553118,
+      "grad_norm": 9.229384422302246,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 14.3306,
+      "step": 39
+    },
+    {
+      "epoch": 0.01971900419028839,
+      "grad_norm": 6.947218418121338,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 8.4309,
+      "step": 40
+    },
+    {
+      "epoch": 0.0202119792950456,
+      "grad_norm": 11.459609985351562,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 7.1616,
+      "step": 41
+    },
+    {
+      "epoch": 0.02070495439980281,
+      "grad_norm": 6.800018310546875,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 6.6803,
+      "step": 42
+    },
+    {
+      "epoch": 0.02119792950456002,
+      "grad_norm": 5.521302700042725,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 6.2856,
+      "step": 43
+    },
+    {
+      "epoch": 0.02169090460931723,
+      "grad_norm": 5.030599594116211,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 4.4336,
+      "step": 44
+    },
+    {
+      "epoch": 0.02218387971407444,
+      "grad_norm": 5.067933559417725,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 4.1782,
+      "step": 45
+    },
+    {
+      "epoch": 0.022676854818831648,
+      "grad_norm": 4.571890354156494,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 4.1419,
+      "step": 46
+    },
+    {
+      "epoch": 0.023169829923588858,
+      "grad_norm": 4.118577003479004,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.6094,
+      "step": 47
+    },
+    {
+      "epoch": 0.023662805028346067,
+      "grad_norm": 5.174846172332764,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 4.5297,
+      "step": 48
+    },
+    {
+      "epoch": 0.024155780133103277,
+      "grad_norm": 5.817050933837891,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 4.8852,
+      "step": 49
+    },
+    {
+      "epoch": 0.02464875523786049,
+      "grad_norm": 8.24295425415039,
+      "learning_rate": 1e-05,
+      "loss": 3.8796,
+      "step": 50
+    },
+    {
+      "epoch": 0.02464875523786049,
+      "eval_loss": 0.18751490116119385,
+      "eval_runtime": 4.3097,
+      "eval_samples_per_second": 11.602,
+      "eval_steps_per_second": 3.016,
+      "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": 1.4868141154762752e+17,
+  "total_flos": 2.972701001200435e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null