Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b3991eeb59a26890e760682b1a9cc78ac4bbbeb923cbf8a23ae7708dd6c0e98
+oid sha256:13a5bbebae36e534476fc580dce6ec5ca2bedfebe7b41da7295fedfa5080a1fa
 size 500770656

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d02e9718b5327674c51f2a60ce7a287c2c33c9ce02587fc93a1a70c1ead12b70
+oid sha256:c8e4f89fc14d059f6e469d2f60a93e6f32270b2382c189b145a66eaa6ecf591c
 size 1001863522

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3a7ba6b8db111c442ac23ff3e3afd18a2e9d95ad1e206b6598772eaf7a6d4fe
+oid sha256:c76eef7682cda480d971b5d837dcda56407b3b54d52e39104d9b875bfd7a12b2
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4748eb6c1596b908714456376ec4974b9573930424f511b150e030991a9276bf
+oid sha256:20e4c98c21aebf9b4ca06f8f460b327d996fc8edea43f99987b7a378499dd676
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52e3fd05945f059fb3d6d938689e9b970d807816d0e4b4649dcf99f10d99e692
+oid sha256:18e495527d36e1031034ee45b1c63569e86d60cdff4447cd4f63a2526f3e661c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df70424674bd3dfb26616ca43a96b5f496453dddaf1efa35937bdf5e94995616
+oid sha256:abe55f06d3845a919e31a7007b71c67dcf7cb09fa8a1774ca43f515d8d8fb012
 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": 1.124017596244812,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01113368775572689,
+  "best_metric": 0.9899536967277527,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02226737551145378,
   "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": 21.034,
       "eval_steps_per_second": 2.629,
       "step": 25
+    },
+    {
+      "epoch": 0.011579035265955967,
+      "grad_norm": 1.7371728420257568,
+      "learning_rate": 5e-05,
+      "loss": 1.3708,
+      "step": 26
+    },
+    {
+      "epoch": 0.012024382776185042,
+      "grad_norm": 1.6122159957885742,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3295,
+      "step": 27
+    },
+    {
+      "epoch": 0.012469730286414118,
+      "grad_norm": 1.6537405252456665,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.0579,
+      "step": 28
+    },
+    {
+      "epoch": 0.012915077796643193,
+      "grad_norm": 1.7590739727020264,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9833,
+      "step": 29
+    },
+    {
+      "epoch": 0.01336042530687227,
+      "grad_norm": 1.4219406843185425,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.9743,
+      "step": 30
+    },
+    {
+      "epoch": 0.013805772817101344,
+      "grad_norm": 1.4464205503463745,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.8225,
+      "step": 31
+    },
+    {
+      "epoch": 0.01425112032733042,
+      "grad_norm": 1.3641613721847534,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.8066,
+      "step": 32
+    },
+    {
+      "epoch": 0.014696467837559495,
+      "grad_norm": 1.4936997890472412,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9581,
+      "step": 33
+    },
+    {
+      "epoch": 0.015141815347788572,
+      "grad_norm": 1.404656171798706,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7723,
+      "step": 34
+    },
+    {
+      "epoch": 0.015587162858017646,
+      "grad_norm": 2.1803853511810303,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.9384,
+      "step": 35
+    },
+    {
+      "epoch": 0.01603251036824672,
+      "grad_norm": 2.4153835773468018,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.0157,
+      "step": 36
+    },
+    {
+      "epoch": 0.016477857878475798,
+      "grad_norm": 1.6833958625793457,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9205,
+      "step": 37
+    },
+    {
+      "epoch": 0.016923205388704874,
+      "grad_norm": 1.9868228435516357,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.1589,
+      "step": 38
+    },
+    {
+      "epoch": 0.01736855289893395,
+      "grad_norm": 1.3428561687469482,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.0347,
+      "step": 39
+    },
+    {
+      "epoch": 0.017813900409163023,
+      "grad_norm": 1.3924375772476196,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9026,
+      "step": 40
+    },
+    {
+      "epoch": 0.0182592479193921,
+      "grad_norm": 1.322308897972107,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.94,
+      "step": 41
+    },
+    {
+      "epoch": 0.018704595429621176,
+      "grad_norm": 1.5756248235702515,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7711,
+      "step": 42
+    },
+    {
+      "epoch": 0.019149942939850253,
+      "grad_norm": 1.912229299545288,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0106,
+      "step": 43
+    },
+    {
+      "epoch": 0.019595290450079326,
+      "grad_norm": 1.682334065437317,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.8101,
+      "step": 44
+    },
+    {
+      "epoch": 0.020040637960308402,
+      "grad_norm": 1.701161503791809,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9,
+      "step": 45
+    },
+    {
+      "epoch": 0.02048598547053748,
+      "grad_norm": 1.8976212739944458,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0663,
+      "step": 46
+    },
+    {
+      "epoch": 0.020931332980766555,
+      "grad_norm": 1.8541693687438965,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9436,
+      "step": 47
+    },
+    {
+      "epoch": 0.02137668049099563,
+      "grad_norm": 2.434173822402954,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2097,
+      "step": 48
+    },
+    {
+      "epoch": 0.021822028001224705,
+      "grad_norm": 2.1513125896453857,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9393,
+      "step": 49
+    },
+    {
+      "epoch": 0.02226737551145378,
+      "grad_norm": 2.3237390518188477,
+      "learning_rate": 0.0,
+      "loss": 1.2021,
+      "step": 50
+    },
+    {
+      "epoch": 0.02226737551145378,
+      "eval_loss": 0.9899536967277527,
+      "eval_runtime": 719.3135,
+      "eval_samples_per_second": 21.031,
+      "eval_steps_per_second": 2.629,
+      "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": 5.114180768104448e+17,
+  "total_flos": 1.0228361536208896e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null