Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37fd059798f64487c5b166b4914102222b92e387e1fd60638d7813bcda2904de
+oid sha256:30c1b8a72deb693daddb3174f3479145e46e0cfa2fcac2a35803b7cab3cac085
 size 201361312

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:293ff0f0d1b5f415ffeadbae4b8e886f1b695875242d0e11d7f802f2aa0e4bb8
+oid sha256:15ff3f0ea8e3d4bd1b691868640645b8cfd76b1ffa5c74c82b5c3af84f4d60d4
 size 402868986

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c41f5af5170600cfeb4335419031a82134691cb057b2360433d700e659e2e71
+oid sha256:9dcd78e83dc86bcf72eae5ea7e1b6791594f5a32bc0a1616c401d20dd15bd544
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3520a244f7baf9726c2f5f6eef799637299b7b2ea853b0e87cbe06e56c631520
+oid sha256:d2ef293d39b571e93afcfe022f30ed2be489adfdd0ba08f5e346af457b75c540
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:155acb34b388bfea8d886b958d15ca842ae492a2a318603a2b5872992599c20d
+oid sha256:3623b2473d382f5e1204000cca61768f51378ce748af6a4137862ff57991fb60
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef9986efb000c0dd544b136c23e2ad18d73cc267ebb28a1e94de491bc4fc620e
+oid sha256:d7db39dc0566681d1a88e6455ddaea6b17042b8ed008f74d7dd0f77112d1b80f
 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": 2.003164768218994,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.6111535523300229,
+  "best_metric": 1.8708174228668213,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.2307104660045836,
   "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": 24.208,
       "eval_steps_per_second": 6.294,
       "step": 25
+    },
+    {
+      "epoch": 0.6355996944232238,
+      "grad_norm": 18.929536819458008,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 64.7618,
+      "step": 26
+    },
+    {
+      "epoch": 0.6600458365164248,
+      "grad_norm": 21.448637008666992,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 64.5529,
+      "step": 27
+    },
+    {
+      "epoch": 0.6844919786096256,
+      "grad_norm": 33.85430908203125,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 63.4589,
+      "step": 28
+    },
+    {
+      "epoch": 0.7089381207028266,
+      "grad_norm": 40.63993453979492,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 68.7545,
+      "step": 29
+    },
+    {
+      "epoch": 0.7333842627960275,
+      "grad_norm": 82.17156219482422,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 87.5419,
+      "step": 30
+    },
+    {
+      "epoch": 0.7578304048892284,
+      "grad_norm": 13.374621391296387,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 59.8912,
+      "step": 31
+    },
+    {
+      "epoch": 0.7822765469824293,
+      "grad_norm": 13.585383415222168,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 63.3713,
+      "step": 32
+    },
+    {
+      "epoch": 0.8067226890756303,
+      "grad_norm": 13.443493843078613,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 64.0963,
+      "step": 33
+    },
+    {
+      "epoch": 0.8311688311688312,
+      "grad_norm": 14.117866516113281,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 67.4577,
+      "step": 34
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 14.199562072753906,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 64.4722,
+      "step": 35
+    },
+    {
+      "epoch": 0.880061115355233,
+      "grad_norm": 15.438693046569824,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 62.3811,
+      "step": 36
+    },
+    {
+      "epoch": 0.904507257448434,
+      "grad_norm": 19.638364791870117,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 61.1175,
+      "step": 37
+    },
+    {
+      "epoch": 0.9289533995416348,
+      "grad_norm": 24.781003952026367,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 63.7251,
+      "step": 38
+    },
+    {
+      "epoch": 0.9533995416348358,
+      "grad_norm": 39.62467575073242,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 69.1405,
+      "step": 39
+    },
+    {
+      "epoch": 0.9778456837280367,
+      "grad_norm": 81.1537857055664,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 80.104,
+      "step": 40
+    },
+    {
+      "epoch": 1.0106951871657754,
+      "grad_norm": 10.694902420043945,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 61.8659,
+      "step": 41
+    },
+    {
+      "epoch": 1.0351413292589764,
+      "grad_norm": 13.224225044250488,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 61.0651,
+      "step": 42
+    },
+    {
+      "epoch": 1.0595874713521773,
+      "grad_norm": 11.33064079284668,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 62.6553,
+      "step": 43
+    },
+    {
+      "epoch": 1.084033613445378,
+      "grad_norm": 11.749734878540039,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 62.2971,
+      "step": 44
+    },
+    {
+      "epoch": 1.108479755538579,
+      "grad_norm": 11.777039527893066,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 65.4289,
+      "step": 45
+    },
+    {
+      "epoch": 1.13292589763178,
+      "grad_norm": 12.874588012695312,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 62.4115,
+      "step": 46
+    },
+    {
+      "epoch": 1.157372039724981,
+      "grad_norm": 14.659823417663574,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 57.853,
+      "step": 47
+    },
+    {
+      "epoch": 1.1818181818181819,
+      "grad_norm": 21.78965187072754,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 58.6357,
+      "step": 48
+    },
+    {
+      "epoch": 1.2062643239113828,
+      "grad_norm": 30.539003372192383,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 60.2393,
+      "step": 49
+    },
+    {
+      "epoch": 1.2307104660045836,
+      "grad_norm": 42.250736236572266,
+      "learning_rate": 1e-05,
+      "loss": 68.542,
+      "step": 50
+    },
+    {
+      "epoch": 1.2307104660045836,
+      "eval_loss": 1.8708174228668213,
+      "eval_runtime": 2.0588,
+      "eval_samples_per_second": 24.286,
+      "eval_steps_per_second": 6.314,
+      "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": 1.483568811343872e+17,
+  "total_flos": 2.967137622687744e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null