Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9b455b642237093deb0a3cfa4bc22f8eec0ab1d4270ca0139bc9ad33e98af1eb
+oid sha256:e3f8a79d8e6811d620490758c799460a5dc790fab815caebaa28ea2fa3ac2038
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39b0c13f45f1e6cf7e6c251a171222cb7ecd1eac5b314a15d74039b6e7e2b302
+oid sha256:7223968394fa63e242196d34696690010aabc75e400c3b8a735ef01c8778d527
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c67bbae85891c3abdff708d110af864f53d01345b17dd294d1e625bad92cd1d4
+oid sha256:7674c2a5d96b7dd8617baf0ef4975eba2c266c0750292f6c60e107b6976f9929
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a72921ae91111ec6af6de54dadcceefdf32ba5503b8e8e85fc1e92517f90d611
+oid sha256:1379181e1c83c62ad2b5506363f1da74f0b64a838bf6df989f0a54e998c60a17
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e529c18453435be7df68f063171e955c5bfa48f4e99681c6125346c202dcc934
+oid sha256:cac8761e57a0871241834772015cc8a59e69fcd564a7d8a5fd4c5b2b7c85e707
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c99231f94cd3f5bd61d44d92a1f0adedd4e336a373b136fa3c6cfe9357387da4
+oid sha256:98b61e878afccaf9caea692f838043444693aa5a7550b7e00def46e61acfa071
 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": 1.238913655281067,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.00549111126364198,
+  "best_metric": 1.1364797353744507,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.01098222252728396,
   "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": 30.115,
       "eval_steps_per_second": 3.764,
       "step": 25
+    },
+    {
+      "epoch": 0.005710755714187658,
+      "grad_norm": 38.344783782958984,
+      "learning_rate": 5e-05,
+      "loss": 19.6379,
+      "step": 26
+    },
+    {
+      "epoch": 0.005930400164733338,
+      "grad_norm": 32.68745422363281,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 18.0308,
+      "step": 27
+    },
+    {
+      "epoch": 0.006150044615279017,
+      "grad_norm": 29.66469955444336,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 17.3707,
+      "step": 28
+    },
+    {
+      "epoch": 0.006369689065824696,
+      "grad_norm": 26.52182388305664,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 15.5194,
+      "step": 29
+    },
+    {
+      "epoch": 0.0065893335163703754,
+      "grad_norm": 28.181365966796875,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 14.7521,
+      "step": 30
+    },
+    {
+      "epoch": 0.006808977966916055,
+      "grad_norm": 25.07322120666504,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 15.3409,
+      "step": 31
+    },
+    {
+      "epoch": 0.007028622417461734,
+      "grad_norm": 31.03534507751465,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 22.3768,
+      "step": 32
+    },
+    {
+      "epoch": 0.007248266868007413,
+      "grad_norm": 32.72694396972656,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 22.6606,
+      "step": 33
+    },
+    {
+      "epoch": 0.007467911318553093,
+      "grad_norm": 29.681062698364258,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 23.0873,
+      "step": 34
+    },
+    {
+      "epoch": 0.007687555769098771,
+      "grad_norm": 30.46506118774414,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 22.9483,
+      "step": 35
+    },
+    {
+      "epoch": 0.00790720021964445,
+      "grad_norm": 29.355850219726562,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 20.3716,
+      "step": 36
+    },
+    {
+      "epoch": 0.00812684467019013,
+      "grad_norm": 28.247610092163086,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 19.0221,
+      "step": 37
+    },
+    {
+      "epoch": 0.008346489120735809,
+      "grad_norm": 27.88100814819336,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 16.6165,
+      "step": 38
+    },
+    {
+      "epoch": 0.008566133571281487,
+      "grad_norm": 25.673690795898438,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 17.2327,
+      "step": 39
+    },
+    {
+      "epoch": 0.008785778021827168,
+      "grad_norm": 25.04754638671875,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 16.4663,
+      "step": 40
+    },
+    {
+      "epoch": 0.009005422472372846,
+      "grad_norm": 25.1225528717041,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 15.2518,
+      "step": 41
+    },
+    {
+      "epoch": 0.009225066922918525,
+      "grad_norm": 24.92913246154785,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 15.0262,
+      "step": 42
+    },
+    {
+      "epoch": 0.009444711373464205,
+      "grad_norm": 24.988466262817383,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 12.7022,
+      "step": 43
+    },
+    {
+      "epoch": 0.009664355824009884,
+      "grad_norm": 26.765302658081055,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 18.6385,
+      "step": 44
+    },
+    {
+      "epoch": 0.009884000274555563,
+      "grad_norm": 26.349815368652344,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 22.6444,
+      "step": 45
+    },
+    {
+      "epoch": 0.010103644725101243,
+      "grad_norm": 28.357736587524414,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 23.0244,
+      "step": 46
+    },
+    {
+      "epoch": 0.010323289175646922,
+      "grad_norm": 28.125967025756836,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 20.9472,
+      "step": 47
+    },
+    {
+      "epoch": 0.0105429336261926,
+      "grad_norm": 27.11406707763672,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 19.9431,
+      "step": 48
+    },
+    {
+      "epoch": 0.01076257807673828,
+      "grad_norm": 31.245771408081055,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 21.9699,
+      "step": 49
+    },
+    {
+      "epoch": 0.01098222252728396,
+      "grad_norm": 28.27548599243164,
+      "learning_rate": 0.0,
+      "loss": 17.7171,
+      "step": 50
+    },
+    {
+      "epoch": 0.01098222252728396,
+      "eval_loss": 1.1364797353744507,
+      "eval_runtime": 1003.4143,
+      "eval_samples_per_second": 30.568,
+      "eval_steps_per_second": 3.821,
+      "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": 2.9561017256955085e+17,
+  "total_flos": 5.896147371137434e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null