Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10ecf4ff652dcb75951cc56093394910cf3dee7f93ce7bf6ba928235ebbd6e4a
+oid sha256:ab8ac08a8319cab6d6f5164f16a4dd90519ab85c58926051637339d63ecc6541
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f96c4352fce54318f65ea791e79f8da56d15961515d54b77845be6c4ce18c911
+oid sha256:f04a0e237f0de10741484261ffd0c128cd3f147184b5c75bb7e02d36a15e3cd8
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ea0fd4134ca2b113ff0f7853896435e75cba09dcf5847bb12c3a1998eede251
+oid sha256:f3a38e803cddfcb65a22d6c32b3c7be0572a618c7be3afd456661a0b850ce7ee
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6f6cec45da7c5ef34e53d18575ae48457ffa907b401d827bc1b728805c485976
+oid sha256:958478fcb22de245a848705e48ad3424f3e9f7c2fcc50e73e2730ddcc4a50eab
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a99416942100c430c2b558f31f587ee93d7335963fe6233f462a34314b875b
+oid sha256:73dd9c8d6f2b2b6d09f233bc5b72177382975b43192cb661bc64aab8823a94a1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d253bb6c567f7f3bc849406f19e725053de00816f0a7c00f5df8f043c891838
+oid sha256:9cef2b64d01182d2f4ea9e26bc6e45d1b47a46583e2af261fd0507383dd05a56
 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": 0.6032811403274536,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5347593582887701,
+  "best_metric": 0.44243600964546204,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.0695187165775402,
   "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": 24.212,
       "eval_steps_per_second": 3.075,
       "step": 25
+    },
+    {
+      "epoch": 0.5561497326203209,
+      "grad_norm": 2.761204481124878,
+      "learning_rate": 5e-05,
+      "loss": 0.4991,
+      "step": 26
+    },
+    {
+      "epoch": 0.5775401069518716,
+      "grad_norm": 2.248439073562622,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4998,
+      "step": 27
+    },
+    {
+      "epoch": 0.5989304812834224,
+      "grad_norm": 8.887104034423828,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6861,
+      "step": 28
+    },
+    {
+      "epoch": 0.6203208556149733,
+      "grad_norm": 12.968907356262207,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.9096,
+      "step": 29
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 11.061800956726074,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.806,
+      "step": 30
+    },
+    {
+      "epoch": 0.6631016042780749,
+      "grad_norm": 5.628628730773926,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5288,
+      "step": 31
+    },
+    {
+      "epoch": 0.6844919786096256,
+      "grad_norm": 4.9715166091918945,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4373,
+      "step": 32
+    },
+    {
+      "epoch": 0.7058823529411765,
+      "grad_norm": 4.011041164398193,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4285,
+      "step": 33
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 3.736095666885376,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4914,
+      "step": 34
+    },
+    {
+      "epoch": 0.7486631016042781,
+      "grad_norm": 6.084108352661133,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6763,
+      "step": 35
+    },
+    {
+      "epoch": 0.7700534759358288,
+      "grad_norm": 1.327826738357544,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.437,
+      "step": 36
+    },
+    {
+      "epoch": 0.7914438502673797,
+      "grad_norm": 2.1312787532806396,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4217,
+      "step": 37
+    },
+    {
+      "epoch": 0.8128342245989305,
+      "grad_norm": 4.005236625671387,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4557,
+      "step": 38
+    },
+    {
+      "epoch": 0.8342245989304813,
+      "grad_norm": 1.245957612991333,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4159,
+      "step": 39
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 4.751588821411133,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5018,
+      "step": 40
+    },
+    {
+      "epoch": 0.8770053475935828,
+      "grad_norm": 6.285404682159424,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.519,
+      "step": 41
+    },
+    {
+      "epoch": 0.8983957219251337,
+      "grad_norm": 5.302483558654785,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5138,
+      "step": 42
+    },
+    {
+      "epoch": 0.9197860962566845,
+      "grad_norm": 2.5284996032714844,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4295,
+      "step": 43
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 7.028666019439697,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4705,
+      "step": 44
+    },
+    {
+      "epoch": 0.9625668449197861,
+      "grad_norm": 4.487104892730713,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4287,
+      "step": 45
+    },
+    {
+      "epoch": 0.983957219251337,
+      "grad_norm": 2.946838140487671,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4318,
+      "step": 46
+    },
+    {
+      "epoch": 1.0053475935828877,
+      "grad_norm": 2.243734836578369,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.5529,
+      "step": 47
+    },
+    {
+      "epoch": 1.0267379679144386,
+      "grad_norm": 2.9415969848632812,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4532,
+      "step": 48
+    },
+    {
+      "epoch": 1.0481283422459893,
+      "grad_norm": 1.878656029701233,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4325,
+      "step": 49
+    },
+    {
+      "epoch": 1.0695187165775402,
+      "grad_norm": 2.0214691162109375,
+      "learning_rate": 0.0,
+      "loss": 0.3916,
+      "step": 50
+    },
+    {
+      "epoch": 1.0695187165775402,
+      "eval_loss": 0.44243600964546204,
+      "eval_runtime": 12.9999,
+      "eval_samples_per_second": 24.231,
+      "eval_steps_per_second": 3.077,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null