Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2350f6510b0999619a90a4e0b1392859687f755b69628c520ac49b75ab8ffeec
+oid sha256:f2284009b9bf1ee7af61ccc870b5a3da923f5d735dfabb354510812673974b86
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e4c4864a340841afa36aa4f3ce395a74e1730efbd863505bebe8cc667ab2850
+oid sha256:3ff424b3f74b8135a2e0519cb8d28990aded965b4fa0fb50bf46600df8a43fb3
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d758c7155e7221b725d6d927e4facacebdeb579dcb9fca15d0a8fb375672ddf1
+oid sha256:52d687f2290abf6a3c03da45fc431d7e94b763bb7bb57edd8b466963213dccfa
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a55e0f8d4a7022bf2c35470cd15c07444eaf857232d37481aff173844b4f84fe
+oid sha256:51e6d7ae2c82366dc80b2cd9405e3bc805bf8c4ce97dd8ba16b7380d535b6451
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a56085612c4edc3d936f0d194d5cf1e07717891fd886adcb73040e6afa2cda3
+oid sha256:f11e2f84da910f103339058111775ae16818233777f386f4bfb3bf8065577830
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a73cd39e8d28373b02f4ad62db879c70e21777186151f2acdb1a61cce32deb9
+oid sha256:881fb7df38556c40519eb45f5970fd3ad815eae8d0dbc5984f5a657b221c7295
 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": 1.5221261978149414,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.3029315960912053,
+  "best_metric": 1.5111960172653198,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.6058631921824107,
   "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": 84.228,
       "eval_steps_per_second": 11.014,
       "step": 25
+    },
+    {
+      "epoch": 1.3550488599348534,
+      "grad_norm": 0.1639164388179779,
+      "learning_rate": 5e-05,
+      "loss": 1.4846,
+      "step": 26
+    },
+    {
+      "epoch": 1.4071661237785016,
+      "grad_norm": 0.18915408849716187,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5516,
+      "step": 27
+    },
+    {
+      "epoch": 1.4592833876221498,
+      "grad_norm": 0.21086834371089935,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.5759,
+      "step": 28
+    },
+    {
+      "epoch": 1.511400651465798,
+      "grad_norm": 0.15464426577091217,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.303,
+      "step": 29
+    },
+    {
+      "epoch": 1.5635179153094463,
+      "grad_norm": 0.16771115362644196,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.6029,
+      "step": 30
+    },
+    {
+      "epoch": 1.6156351791530945,
+      "grad_norm": 0.16686154901981354,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4701,
+      "step": 31
+    },
+    {
+      "epoch": 1.6677524429967425,
+      "grad_norm": 0.19988751411437988,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.545,
+      "step": 32
+    },
+    {
+      "epoch": 1.7198697068403908,
+      "grad_norm": 0.23184122145175934,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.5683,
+      "step": 33
+    },
+    {
+      "epoch": 1.771986970684039,
+      "grad_norm": 0.15493892133235931,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3687,
+      "step": 34
+    },
+    {
+      "epoch": 1.8241042345276872,
+      "grad_norm": 0.16259148716926575,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.5158,
+      "step": 35
+    },
+    {
+      "epoch": 1.8762214983713354,
+      "grad_norm": 0.17531201243400574,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.4868,
+      "step": 36
+    },
+    {
+      "epoch": 1.9283387622149837,
+      "grad_norm": 0.19777899980545044,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.5352,
+      "step": 37
+    },
+    {
+      "epoch": 1.980456026058632,
+      "grad_norm": 0.2821734547615051,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.5323,
+      "step": 38
+    },
+    {
+      "epoch": 2.03257328990228,
+      "grad_norm": 0.37536874413490295,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 2.6423,
+      "step": 39
+    },
+    {
+      "epoch": 2.0846905537459284,
+      "grad_norm": 0.1467260718345642,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3896,
+      "step": 40
+    },
+    {
+      "epoch": 2.1368078175895766,
+      "grad_norm": 0.16421370208263397,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4957,
+      "step": 41
+    },
+    {
+      "epoch": 2.188925081433225,
+      "grad_norm": 0.19313547015190125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4973,
+      "step": 42
+    },
+    {
+      "epoch": 2.241042345276873,
+      "grad_norm": 0.19032856822013855,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.0895,
+      "step": 43
+    },
+    {
+      "epoch": 2.2931596091205213,
+      "grad_norm": 0.20216412842273712,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.87,
+      "step": 44
+    },
+    {
+      "epoch": 2.3452768729641695,
+      "grad_norm": 0.15414832532405853,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.4545,
+      "step": 45
+    },
+    {
+      "epoch": 2.3973941368078178,
+      "grad_norm": 0.17168298363685608,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.4898,
+      "step": 46
+    },
+    {
+      "epoch": 2.449511400651466,
+      "grad_norm": 0.20633788406848907,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.5513,
+      "step": 47
+    },
+    {
+      "epoch": 2.5016286644951142,
+      "grad_norm": 0.17030811309814453,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.0551,
+      "step": 48
+    },
+    {
+      "epoch": 2.5537459283387625,
+      "grad_norm": 0.1883995532989502,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.8285,
+      "step": 49
+    },
+    {
+      "epoch": 2.6058631921824107,
+      "grad_norm": 0.1657257378101349,
+      "learning_rate": 0.0,
+      "loss": 1.4567,
+      "step": 50
+    },
+    {
+      "epoch": 2.6058631921824107,
+      "eval_loss": 1.5111960172653198,
+      "eval_runtime": 1.5423,
+      "eval_samples_per_second": 84.287,
+      "eval_steps_per_second": 11.022,
+      "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