Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ab28428d918ba12ef087a59f0a3d72b44f5917730f8689f6e65d2e35232a32
+oid sha256:91e81117879118d2f5bd2935d8cf8df9654fae581518f40ce6cce612cad9c568
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd73452e34b1efce03f3dbffdb4d88fd9b48c7201a83a0336e786010f4ecc3b4
+oid sha256:bda297494bb93fa1a53ad7bf9507ca0b8f95ada2742041b7e4684de3f487700e
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5558c648f0de26466009e6ea9ff1034c989f4e0343628321b9d1ffe8eb05a140
+oid sha256:4a21c0fe9251ecdeeb288db9cb145281e8aa41eee773066ad4566dfc18cacc8c
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ee47acb4d148495c1321de4b53b0e178be017e58b78207e9f3c694c403dab2b
+oid sha256:9a5efe44c573db041ab71ea85c9de3c4deecac96723f107b6e4a1d69962ba6a6
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:24700e807be2ecda3ed62d7fa57ae6648fc3ab6747c2f3726af09ec184ebdcaa
+oid sha256:037cd4cc973ed0b70410aa74539c53523403e359c8acf5b379edc0466b9ee7b0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37d6ad1c01445ecb7dcabe077d287f388e05583554338198610b6bb34a32635f
+oid sha256:bfebbf1e69eb3abd278a06c6b8f6a1b0c56dafaf22d37d1245874296c2a30c43
 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": 1.5183314085006714,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.029708853238265002,
+  "best_metric": 1.1910210847854614,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.059417706476530004,
   "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": 33.906,
       "eval_steps_per_second": 4.241,
       "step": 25
+    },
+    {
+      "epoch": 0.030897207367795602,
+      "grad_norm": 274.412841796875,
+      "learning_rate": 5e-05,
+      "loss": 1.7169,
+      "step": 26
+    },
+    {
+      "epoch": 0.03208556149732621,
+      "grad_norm": 149.68296813964844,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5095,
+      "step": 27
+    },
+    {
+      "epoch": 0.033273915626856804,
+      "grad_norm": 25.888473510742188,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.3772,
+      "step": 28
+    },
+    {
+      "epoch": 0.0344622697563874,
+      "grad_norm": 14.580528259277344,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3296,
+      "step": 29
+    },
+    {
+      "epoch": 0.035650623885918005,
+      "grad_norm": 12.936845779418945,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2996,
+      "step": 30
+    },
+    {
+      "epoch": 0.0368389780154486,
+      "grad_norm": 11.484175682067871,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.2468,
+      "step": 31
+    },
+    {
+      "epoch": 0.038027332144979206,
+      "grad_norm": 11.391379356384277,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2111,
+      "step": 32
+    },
+    {
+      "epoch": 0.0392156862745098,
+      "grad_norm": 12.249479293823242,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.1536,
+      "step": 33
+    },
+    {
+      "epoch": 0.04040404040404041,
+      "grad_norm": 17.404399871826172,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2524,
+      "step": 34
+    },
+    {
+      "epoch": 0.041592394533571005,
+      "grad_norm": 23.930089950561523,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.209,
+      "step": 35
+    },
+    {
+      "epoch": 0.0427807486631016,
+      "grad_norm": 35.380741119384766,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0254,
+      "step": 36
+    },
+    {
+      "epoch": 0.043969102792632206,
+      "grad_norm": 44.73492431640625,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9604,
+      "step": 37
+    },
+    {
+      "epoch": 0.0451574569221628,
+      "grad_norm": 32.5949821472168,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2433,
+      "step": 38
+    },
+    {
+      "epoch": 0.04634581105169341,
+      "grad_norm": 12.151544570922852,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3159,
+      "step": 39
+    },
+    {
+      "epoch": 0.047534165181224004,
+      "grad_norm": 13.319056510925293,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.333,
+      "step": 40
+    },
+    {
+      "epoch": 0.0487225193107546,
+      "grad_norm": 12.818878173828125,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3444,
+      "step": 41
+    },
+    {
+      "epoch": 0.049910873440285206,
+      "grad_norm": 12.929219245910645,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3271,
+      "step": 42
+    },
+    {
+      "epoch": 0.0510992275698158,
+      "grad_norm": 12.480031967163086,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.254,
+      "step": 43
+    },
+    {
+      "epoch": 0.05228758169934641,
+      "grad_norm": 13.18757152557373,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2245,
+      "step": 44
+    },
+    {
+      "epoch": 0.053475935828877004,
+      "grad_norm": 16.51483917236328,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.1654,
+      "step": 45
+    },
+    {
+      "epoch": 0.05466428995840761,
+      "grad_norm": 17.32997703552246,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.1569,
+      "step": 46
+    },
+    {
+      "epoch": 0.055852644087938205,
+      "grad_norm": 17.273448944091797,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3149,
+      "step": 47
+    },
+    {
+      "epoch": 0.0570409982174688,
+      "grad_norm": 19.1171932220459,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0405,
+      "step": 48
+    },
+    {
+      "epoch": 0.058229352346999406,
+      "grad_norm": 22.05423355102539,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9513,
+      "step": 49
+    },
+    {
+      "epoch": 0.059417706476530004,
+      "grad_norm": 28.549123764038086,
+      "learning_rate": 0.0,
+      "loss": 0.9478,
+      "step": 50
+    },
+    {
+      "epoch": 0.059417706476530004,
+      "eval_loss": 1.1910210847854614,
+      "eval_runtime": 166.9658,
+      "eval_samples_per_second": 33.953,
+      "eval_steps_per_second": 4.246,
+      "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": 2.8307820210290688e+17,
+  "total_flos": 5.6633321727197184e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null