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:de2f393ba7d3307f8201765e52ce0a815d5c2a1308f1d79b80c8b0a10eaf7505
+oid sha256:b066c354d221ec658c8920e84419e5a65b614e324aeeaef176ad7f441ab11fbb
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:355747ebcb892880883f348859a1427ce13bd528006f22bf5e453e46e5c1bf38
+oid sha256:1292b6c6b358d51a5b74b66bfca636531923b8076619b51fc9cbb83ca3e2a8eb
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87ed465b8131ade14ccc40a75420ec5291bdb48b0617b0af2e06cae9f1980e34
+oid sha256:0f35da35ed0bb49acf5be02710549a92543862db93f14e40705c11d3732e0a25
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:937b3c763de285bf8e7976c73ee06ad859d8bffcb0e083004bb3c438d6bf5d1c
+oid sha256:5e60df284b0a11c8f65370907b6a7b160fafff9e7ba8373a356ecb9705fd8324
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f23b5c8be9c199811b18b21da2310d649f6bb783653318cb5d79b5bdb05a3478
+oid sha256:c31087bd6adea4e30384bef3af3c959d0c6d6b00619701b0fc87b81f9c46a7f0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2a6911123be9d1d2e369e6d11060a86b30a5641e6b182922c97d232b2ff96e
+oid sha256:ba462f1372089baf6421b357f4a674524ce5c1f88053de520147667b05857bd0
 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": 2.192530632019043,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.008794494646351384,
+  "best_metric": 2.1861934661865234,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.017588989292702768,
   "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": 11.974,
       "eval_steps_per_second": 1.497,
       "step": 25
+    },
+    {
+      "epoch": 0.00914627443220544,
+      "grad_norm": 3.850252389907837,
+      "learning_rate": 5e-05,
+      "loss": 32.5252,
+      "step": 26
+    },
+    {
+      "epoch": 0.009498054218059495,
+      "grad_norm": 3.9339077472686768,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 31.5305,
+      "step": 27
+    },
+    {
+      "epoch": 0.00984983400391355,
+      "grad_norm": 4.544314384460449,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 32.7912,
+      "step": 28
+    },
+    {
+      "epoch": 0.010201613789767605,
+      "grad_norm": 5.1566386222839355,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 33.4204,
+      "step": 29
+    },
+    {
+      "epoch": 0.010553393575621661,
+      "grad_norm": 5.830033302307129,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 31.9166,
+      "step": 30
+    },
+    {
+      "epoch": 0.010905173361475716,
+      "grad_norm": 7.928355693817139,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 32.5998,
+      "step": 31
+    },
+    {
+      "epoch": 0.011256953147329772,
+      "grad_norm": 7.931662082672119,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 33.5552,
+      "step": 32
+    },
+    {
+      "epoch": 0.011608732933183827,
+      "grad_norm": 8.679764747619629,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 35.0329,
+      "step": 33
+    },
+    {
+      "epoch": 0.011960512719037883,
+      "grad_norm": 10.883329391479492,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 35.1929,
+      "step": 34
+    },
+    {
+      "epoch": 0.012312292504891938,
+      "grad_norm": 11.988004684448242,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 36.985,
+      "step": 35
+    },
+    {
+      "epoch": 0.012664072290745993,
+      "grad_norm": 14.921319961547852,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 38.2092,
+      "step": 36
+    },
+    {
+      "epoch": 0.013015852076600049,
+      "grad_norm": 17.755186080932617,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 39.6091,
+      "step": 37
+    },
+    {
+      "epoch": 0.013367631862454104,
+      "grad_norm": 22.678396224975586,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 39.4044,
+      "step": 38
+    },
+    {
+      "epoch": 0.01371941164830816,
+      "grad_norm": 3.5891330242156982,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 33.0391,
+      "step": 39
+    },
+    {
+      "epoch": 0.014071191434162215,
+      "grad_norm": 8.799407958984375,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 33.2429,
+      "step": 40
+    },
+    {
+      "epoch": 0.01442297122001627,
+      "grad_norm": 4.962418556213379,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 33.156,
+      "step": 41
+    },
+    {
+      "epoch": 0.014774751005870326,
+      "grad_norm": 5.748550891876221,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 31.7608,
+      "step": 42
+    },
+    {
+      "epoch": 0.015126530791724381,
+      "grad_norm": 6.102511405944824,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 32.0973,
+      "step": 43
+    },
+    {
+      "epoch": 0.015478310577578435,
+      "grad_norm": 6.81181526184082,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 34.2612,
+      "step": 44
+    },
+    {
+      "epoch": 0.01583009036343249,
+      "grad_norm": 7.937811374664307,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 33.158,
+      "step": 45
+    },
+    {
+      "epoch": 0.016181870149286546,
+      "grad_norm": 8.875764846801758,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 34.1222,
+      "step": 46
+    },
+    {
+      "epoch": 0.0165336499351406,
+      "grad_norm": 10.221689224243164,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 35.9223,
+      "step": 47
+    },
+    {
+      "epoch": 0.016885429720994657,
+      "grad_norm": 11.83366870880127,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 37.0314,
+      "step": 48
+    },
+    {
+      "epoch": 0.017237209506848712,
+      "grad_norm": 14.52757740020752,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 38.5339,
+      "step": 49
+    },
+    {
+      "epoch": 0.017588989292702768,
+      "grad_norm": 21.84239387512207,
+      "learning_rate": 0.0,
+      "loss": 45.6407,
+      "step": 50
+    },
+    {
+      "epoch": 0.017588989292702768,
+      "eval_loss": 2.1861934661865234,
+      "eval_runtime": 1604.544,
+      "eval_samples_per_second": 11.935,
+      "eval_steps_per_second": 1.492,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null