Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ee7c8006164d3a4385e66423ad18128caf10a05564e28b4eff5ddb0625e2b4f
+oid sha256:5537fe6e0741ec92626c587e5cdd4c9aabc223734dedcd6ec4d20a8cbd5455b5
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36c1b996e3198d0ab932da5ad13f425139a43839574003ca0a77315bc749edf8
+oid sha256:670f0d05e4ec1536a318ece726df426dac69231edd17e5f4b794b3f6a6493780
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b906ccb491c9982ecf6287775feed5da1183434d9295a049626e95185db5a79f
+oid sha256:c857fbd2bf8fa8ae79a5adf48b0102498f9428bd76fce6ebde0ae182b4594071
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a63a5be4cc55b371414fd64e71797c694106f7888a35a41dc0e5c9b993903318
+oid sha256:0020df83ccb6d3cdf671346b0d7d49c94d5e70eb8385dcb4451a13a428951855
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:141cd6a76272c69610226643938b991ca095b8a3777123fbb8c80702c1bb1f21
+oid sha256:b89e9bb79a0267aa9a1a85ed5c77eb11cec5b1363ec89a6eb11519515250217c
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5ee22711bd8cadf36e4fcf9084a124fd052c6c71dfd2ae4cb8b58b2827822c6
+oid sha256:125d993e196abf0321c975ed699bc4befd55501e6ef9a97f5044ab47a2d5029c
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d271cdb95f63cd655315f063ca2e25c78dc5ae4275523c5d4f80f367586b3351
+oid sha256:5607f6de446164d9d9adb8b91c44cec55b14aa391e24ba5637c08b834eedda2a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.18398380279541,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.004948198546466677,
+  "best_metric": 0.369827538728714,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.009896397092933353,
   "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": 16.572,
       "eval_steps_per_second": 4.309,
       "step": 25
+    },
+    {
+      "epoch": 0.005146126488325344,
+      "grad_norm": 59.69435119628906,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 2.2896,
+      "step": 26
+    },
+    {
+      "epoch": 0.005344054430184011,
+      "grad_norm": 38.86437225341797,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 1.779,
+      "step": 27
+    },
+    {
+      "epoch": 0.005541982372042678,
+      "grad_norm": 18.590524673461914,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 1.2249,
+      "step": 28
+    },
+    {
+      "epoch": 0.005739910313901345,
+      "grad_norm": 10.571396827697754,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 0.8503,
+      "step": 29
+    },
+    {
+      "epoch": 0.005937838255760012,
+      "grad_norm": 4.663567543029785,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 0.6435,
+      "step": 30
+    },
+    {
+      "epoch": 0.006135766197618679,
+      "grad_norm": 2.635765314102173,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 0.5362,
+      "step": 31
+    },
+    {
+      "epoch": 0.006333694139477346,
+      "grad_norm": 2.034586191177368,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 0.5163,
+      "step": 32
+    },
+    {
+      "epoch": 0.006531622081336013,
+      "grad_norm": 1.348783016204834,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 0.4927,
+      "step": 33
+    },
+    {
+      "epoch": 0.0067295500231946805,
+      "grad_norm": 1.3473753929138184,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 0.4985,
+      "step": 34
+    },
+    {
+      "epoch": 0.006927477965053348,
+      "grad_norm": 1.6605085134506226,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 0.5119,
+      "step": 35
+    },
+    {
+      "epoch": 0.007125405906912015,
+      "grad_norm": 2.3796026706695557,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 0.5092,
+      "step": 36
+    },
+    {
+      "epoch": 0.007323333848770682,
+      "grad_norm": 4.877535343170166,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 0.7055,
+      "step": 37
+    },
+    {
+      "epoch": 0.007521261790629349,
+      "grad_norm": 3.616194486618042,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.386,
+      "step": 38
+    },
+    {
+      "epoch": 0.007719189732488016,
+      "grad_norm": 3.2030487060546875,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 0.3744,
+      "step": 39
+    },
+    {
+      "epoch": 0.007917117674346684,
+      "grad_norm": 1.7222741842269897,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 0.4175,
+      "step": 40
+    },
+    {
+      "epoch": 0.00811504561620535,
+      "grad_norm": 1.1066466569900513,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 0.395,
+      "step": 41
+    },
+    {
+      "epoch": 0.008312973558064018,
+      "grad_norm": 0.585119366645813,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.4375,
+      "step": 42
+    },
+    {
+      "epoch": 0.008510901499922684,
+      "grad_norm": 0.4170882999897003,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.3857,
+      "step": 43
+    },
+    {
+      "epoch": 0.00870882944178135,
+      "grad_norm": 0.5387073755264282,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.3985,
+      "step": 44
+    },
+    {
+      "epoch": 0.008906757383640019,
+      "grad_norm": 0.6630279421806335,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.3758,
+      "step": 45
+    },
+    {
+      "epoch": 0.009104685325498685,
+      "grad_norm": 0.8859663605690002,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 0.4147,
+      "step": 46
+    },
+    {
+      "epoch": 0.009302613267357353,
+      "grad_norm": 1.1143105030059814,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.4396,
+      "step": 47
+    },
+    {
+      "epoch": 0.009500541209216019,
+      "grad_norm": 1.7111051082611084,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.4743,
+      "step": 48
+    },
+    {
+      "epoch": 0.009698469151074687,
+      "grad_norm": 2.983445644378662,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.6497,
+      "step": 49
+    },
+    {
+      "epoch": 0.009896397092933353,
+      "grad_norm": 7.340808868408203,
+      "learning_rate": 1e-05,
+      "loss": 0.9425,
+      "step": 50
+    },
+    {
+      "epoch": 0.009896397092933353,
+      "eval_loss": 0.369827538728714,
+      "eval_runtime": 3.0255,
+      "eval_samples_per_second": 16.526,
+      "eval_steps_per_second": 4.297,
+      "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": 2.9859068337822106e+17,
+  "total_flos": 5.969948642440643e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null