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:a39e2547274e93044a55f8fb94894d64ed55f427ff32c8c62e8e93d108ab4172
+oid sha256:9446bd8c5faeb76cd8dec0d8b5ce4ff04b379d0e8a9389193606f36cef04d250
 size 1521616

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4f5a9d402d18bedc1332867ac8493f937895878cb6db293bb3bafe6b2de3d73a
+oid sha256:733bd4f75355bee326788cdb90af278a83f16ee7cd962c7eaffba859c7bf7bad
 size 3108666

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a29c4332cdbc3bbb423b1470891e32d0f8a997d8fb9a160441a35de7b045f830
+oid sha256:fa008a4be23558a50880bc63e17f5669b469ca29e27c6cf3cefb7a528b449f48
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4d1fddf588bcbe79c762e474a1bd303b53ece48e913f30f951673155ff0120a
+oid sha256:79475b4c75c2433139d5dbc56469509af1ea9e7cde892de33e8b508a0f145e3d
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9119547080356b12d22e6037e7bead13f85824f14afad9564f65b59b4387dc58
+oid sha256:d37a2d5076e93e3093698a2c0b91f162fbc60151a710332c748297496d2c886d
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:947f17a0b59a09da01c1edab7a1ae846b14c75f6e35ee44bdabfbf0c635674c8
+oid sha256:2d39c93f1e283522d34142b2b6d519696f7eb4b96fbcaf580fdc4638967adf81
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5eda964d5b06109c7ff637060199d72e397eeb7027b50e10972a323edbe81312
+oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 6.543909072875977,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0622568093385214,
+  "best_metric": 6.405816078186035,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1245136186770428,
   "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": 104.926,
       "eval_steps_per_second": 27.281,
       "step": 25
+    },
+    {
+      "epoch": 0.06474708171206225,
+      "grad_norm": 3.1084837913513184,
+      "learning_rate": 7.917848237560709e-05,
+      "loss": 6.6169,
+      "step": 26
+    },
+    {
+      "epoch": 0.06723735408560311,
+      "grad_norm": 1.2209361791610718,
+      "learning_rate": 7.75e-05,
+      "loss": 6.7791,
+      "step": 27
+    },
+    {
+      "epoch": 0.06972762645914397,
+      "grad_norm": 1.1099854707717896,
+      "learning_rate": 7.577868759557654e-05,
+      "loss": 6.936,
+      "step": 28
+    },
+    {
+      "epoch": 0.07221789883268483,
+      "grad_norm": 1.0699315071105957,
+      "learning_rate": 7.401782177833148e-05,
+      "loss": 6.8154,
+      "step": 29
+    },
+    {
+      "epoch": 0.07470817120622568,
+      "grad_norm": 0.9406839609146118,
+      "learning_rate": 7.222075445642904e-05,
+      "loss": 6.988,
+      "step": 30
+    },
+    {
+      "epoch": 0.07719844357976653,
+      "grad_norm": 0.9526640176773071,
+      "learning_rate": 7.03909064496551e-05,
+      "loss": 6.7899,
+      "step": 31
+    },
+    {
+      "epoch": 0.0796887159533074,
+      "grad_norm": 0.8295072913169861,
+      "learning_rate": 6.853176097769229e-05,
+      "loss": 6.7357,
+      "step": 32
+    },
+    {
+      "epoch": 0.08217898832684825,
+      "grad_norm": 0.9567013382911682,
+      "learning_rate": 6.664685702961344e-05,
+      "loss": 6.797,
+      "step": 33
+    },
+    {
+      "epoch": 0.0846692607003891,
+      "grad_norm": 1.071341872215271,
+      "learning_rate": 6.473978262721463e-05,
+      "loss": 6.6351,
+      "step": 34
+    },
+    {
+      "epoch": 0.08715953307392996,
+      "grad_norm": 1.3368276357650757,
+      "learning_rate": 6.281416799501188e-05,
+      "loss": 6.6517,
+      "step": 35
+    },
+    {
+      "epoch": 0.08964980544747082,
+      "grad_norm": 1.7732629776000977,
+      "learning_rate": 6.087367864990233e-05,
+      "loss": 6.4047,
+      "step": 36
+    },
+    {
+      "epoch": 0.09214007782101168,
+      "grad_norm": 2.385563850402832,
+      "learning_rate": 5.8922008423644624e-05,
+      "loss": 6.4936,
+      "step": 37
+    },
+    {
+      "epoch": 0.09463035019455253,
+      "grad_norm": 2.034431219100952,
+      "learning_rate": 5.696287243144013e-05,
+      "loss": 7.0241,
+      "step": 38
+    },
+    {
+      "epoch": 0.09712062256809338,
+      "grad_norm": 0.9206064343452454,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 6.7179,
+      "step": 39
+    },
+    {
+      "epoch": 0.09961089494163425,
+      "grad_norm": 0.995243489742279,
+      "learning_rate": 5.303712756855988e-05,
+      "loss": 6.8535,
+      "step": 40
+    },
+    {
+      "epoch": 0.1021011673151751,
+      "grad_norm": 0.9085476994514465,
+      "learning_rate": 5.107799157635538e-05,
+      "loss": 6.7739,
+      "step": 41
+    },
+    {
+      "epoch": 0.10459143968871595,
+      "grad_norm": 0.8075990080833435,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 6.8463,
+      "step": 42
+    },
+    {
+      "epoch": 0.1070817120622568,
+      "grad_norm": 0.7797780632972717,
+      "learning_rate": 4.718583200498814e-05,
+      "loss": 6.7627,
+      "step": 43
+    },
+    {
+      "epoch": 0.10957198443579766,
+      "grad_norm": 0.7625030279159546,
+      "learning_rate": 4.526021737278538e-05,
+      "loss": 6.7574,
+      "step": 44
+    },
+    {
+      "epoch": 0.11206225680933853,
+      "grad_norm": 0.788215160369873,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 6.653,
+      "step": 45
+    },
+    {
+      "epoch": 0.11455252918287938,
+      "grad_norm": 1.022986888885498,
+      "learning_rate": 4.146823902230772e-05,
+      "loss": 6.7437,
+      "step": 46
+    },
+    {
+      "epoch": 0.11704280155642023,
+      "grad_norm": 1.1553353071212769,
+      "learning_rate": 3.960909355034491e-05,
+      "loss": 6.5571,
+      "step": 47
+    },
+    {
+      "epoch": 0.11953307392996108,
+      "grad_norm": 1.4759111404418945,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 6.4163,
+      "step": 48
+    },
+    {
+      "epoch": 0.12202334630350195,
+      "grad_norm": 1.8967125415802002,
+      "learning_rate": 3.598217822166854e-05,
+      "loss": 6.7076,
+      "step": 49
+    },
+    {
+      "epoch": 0.1245136186770428,
+      "grad_norm": 2.9591472148895264,
+      "learning_rate": 3.422131240442349e-05,
+      "loss": 6.5811,
+      "step": 50
+    },
+    {
+      "epoch": 0.1245136186770428,
+      "eval_loss": 6.405816078186035,
+      "eval_runtime": 0.4887,
+      "eval_samples_per_second": 102.322,
+      "eval_steps_per_second": 26.604,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -226,7 +409,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 116043151310848.0,
+  "total_flos": 232050050203648.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null