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:a65c595581f0d3a1494caa6f10b9e8d46b41ba2c9d917153ac0c612eacc84a0a
+oid sha256:4121d8d0eacc28e6c94c43289be8dbdc657bef849e5478d09510a1b1c6ce57bf
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98ca22d830f36f278c1f395eed34f115e1d9636308ea4bfbd2b559d313952aaa
+oid sha256:abc1274ec6d6f4ac4ae3604274b1ae01e8bea0244e6cf7baea8f0c4fba358bb9
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca61128a5a0a3f14528f211bf07a9b88b439d88a1d6bdb67f4fdeef73784f0b3
+oid sha256:0fe25d20f7e50f294e573d227ab50c7fa8ecf8efa8628e4f35843f607c9f75bb
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ca869ba7e9d13e59e5ff27a335fe77755d6ef0e20846155b9ad47060142cae4
+oid sha256:a47e9904f04ba420811ef8c9a750aa174cefbe2700dad81b84216ec46031907b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8e41be5ba667c192351ba37feac2a33dd02821b5d8d779a2b1dd45f1bd9225ef
+oid sha256:e7b770d93a313a221075f74ce39546e98544c0a2afce1f81bdc66623c5b39254
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a931e05bdc836c3fbe2ddb7d4cb473a15f4479ea373b93c66ab939a519c95bbd
+oid sha256:e25316dac459baca287ca0329aad4cc789447f30aaee094ffd4e71690c4c5c72
 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": 1.7648794651031494,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1799410029498525,
+  "best_metric": 1.746710181236267,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.359882005899705,
   "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": 39.159,
       "eval_steps_per_second": 4.929,
       "step": 25
+    },
+    {
+      "epoch": 1.2271386430678466,
+      "grad_norm": 1.1068404912948608,
+      "learning_rate": 5e-05,
+      "loss": 1.7302,
+      "step": 26
+    },
+    {
+      "epoch": 1.2743362831858407,
+      "grad_norm": 1.2672423124313354,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.7341,
+      "step": 27
+    },
+    {
+      "epoch": 1.3215339233038348,
+      "grad_norm": 1.0532811880111694,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.6848,
+      "step": 28
+    },
+    {
+      "epoch": 1.368731563421829,
+      "grad_norm": 1.037347674369812,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6998,
+      "step": 29
+    },
+    {
+      "epoch": 1.415929203539823,
+      "grad_norm": 1.1231845617294312,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6996,
+      "step": 30
+    },
+    {
+      "epoch": 1.463126843657817,
+      "grad_norm": 1.1563193798065186,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.655,
+      "step": 31
+    },
+    {
+      "epoch": 1.5103244837758112,
+      "grad_norm": 1.0125848054885864,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5737,
+      "step": 32
+    },
+    {
+      "epoch": 1.5575221238938053,
+      "grad_norm": 1.0071817636489868,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.8132,
+      "step": 33
+    },
+    {
+      "epoch": 1.6047197640117994,
+      "grad_norm": 0.9246135354042053,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6492,
+      "step": 34
+    },
+    {
+      "epoch": 1.6519174041297935,
+      "grad_norm": 1.0794720649719238,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.6322,
+      "step": 35
+    },
+    {
+      "epoch": 1.6991150442477876,
+      "grad_norm": 1.4046562910079956,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.6497,
+      "step": 36
+    },
+    {
+      "epoch": 1.7463126843657817,
+      "grad_norm": 1.0453946590423584,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5673,
+      "step": 37
+    },
+    {
+      "epoch": 1.7935103244837758,
+      "grad_norm": 1.0008294582366943,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8059,
+      "step": 38
+    },
+    {
+      "epoch": 1.8407079646017699,
+      "grad_norm": 0.9396019577980042,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5804,
+      "step": 39
+    },
+    {
+      "epoch": 1.887905604719764,
+      "grad_norm": 1.0129765272140503,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6912,
+      "step": 40
+    },
+    {
+      "epoch": 1.935103244837758,
+      "grad_norm": 1.0260602235794067,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.6417,
+      "step": 41
+    },
+    {
+      "epoch": 1.9823008849557522,
+      "grad_norm": 1.5143276453018188,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.7454,
+      "step": 42
+    },
+    {
+      "epoch": 2.0294985250737465,
+      "grad_norm": 1.6464427709579468,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 2.9107,
+      "step": 43
+    },
+    {
+      "epoch": 2.0766961651917404,
+      "grad_norm": 0.8135335445404053,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.6117,
+      "step": 44
+    },
+    {
+      "epoch": 2.1238938053097347,
+      "grad_norm": 0.8873955011367798,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.6066,
+      "step": 45
+    },
+    {
+      "epoch": 2.1710914454277286,
+      "grad_norm": 1.112796664237976,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.7035,
+      "step": 46
+    },
+    {
+      "epoch": 2.218289085545723,
+      "grad_norm": 1.3752461671829224,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.7328,
+      "step": 47
+    },
+    {
+      "epoch": 2.265486725663717,
+      "grad_norm": 0.9514968395233154,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5891,
+      "step": 48
+    },
+    {
+      "epoch": 2.312684365781711,
+      "grad_norm": 0.9039832353591919,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.6777,
+      "step": 49
+    },
+    {
+      "epoch": 2.359882005899705,
+      "grad_norm": 0.9195019006729126,
+      "learning_rate": 0.0,
+      "loss": 1.6891,
+      "step": 50
+    },
+    {
+      "epoch": 2.359882005899705,
+      "eval_loss": 1.746710181236267,
+      "eval_runtime": 3.624,
+      "eval_samples_per_second": 39.459,
+      "eval_steps_per_second": 4.967,
+      "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": 5.29768176943104e+16,
+  "total_flos": 1.059536353886208e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null