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:e3b2c0c35225f8f186410a08947cc4fa1e7b408220dcd47266153820f9a3f502
+oid sha256:e0ed4a17daba5bb754b8ab74cfcdf674498036606842c014c06f75fe1260c2e2
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:acc676a6ad1355fc6d9582e66458620cfd5641a1066ed66026fef770d25e126b
+oid sha256:c1ed351e53555ac11b1e863e9d68392303040bdb2b56169d5ca8ef85fe341272
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1bf89ccea77326b181cbad424305b1db93ee09e1bf0a1f99f1faf1e7047c5669
+oid sha256:d5cfbf46ad24da6970b82fa80d09a19aaa200ccc4ad5af984435a80b89b3bb5d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5da1f63959678ae2e7a62a3bcc912f2ed123a9f438caf5c6d1a3040d8054d46
+oid sha256:898d6a48fd055ec05a4982de168a1cff438aee2ba9a2d23f65f4337177d9a7be
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e02afb35fec1c397493f4a75878f5446d5096064a3d541318796c544af4fb8b
+oid sha256:0c96cf09c8d6c442573495b20f32187d53265dda61cf53d0a97d72f81620600e
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fc6265092f8fc798478fd39f1154de993e4c7bfb49d78e7d1a23cec4120545b4
+oid sha256:c5ab75e5c2ba3a489960232058060556506b99d88edce24053e711f18ed7d53c
 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": 0.6941483616828918,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.3421727972626176,
+  "best_metric": 0.5393621325492859,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.6843455945252352,
   "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": 146.473,
       "eval_steps_per_second": 18.421,
       "step": 25
+    },
+    {
+      "epoch": 0.3558597091531223,
+      "grad_norm": 1.6155089139938354,
+      "learning_rate": 5e-05,
+      "loss": 0.6285,
+      "step": 26
+    },
+    {
+      "epoch": 0.369546621043627,
+      "grad_norm": 1.031862497329712,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.5529,
+      "step": 27
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "grad_norm": 1.5417953729629517,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.388,
+      "step": 28
+    },
+    {
+      "epoch": 0.39692044482463645,
+      "grad_norm": 1.5241392850875854,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.444,
+      "step": 29
+    },
+    {
+      "epoch": 0.41060735671514115,
+      "grad_norm": 1.4948774576187134,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4667,
+      "step": 30
+    },
+    {
+      "epoch": 0.42429426860564584,
+      "grad_norm": 2.6010279655456543,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.5152,
+      "step": 31
+    },
+    {
+      "epoch": 0.43798118049615054,
+      "grad_norm": 3.134805202484131,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4711,
+      "step": 32
+    },
+    {
+      "epoch": 0.4516680923866553,
+      "grad_norm": 2.2566981315612793,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.9955,
+      "step": 33
+    },
+    {
+      "epoch": 0.46535500427716,
+      "grad_norm": 1.405287265777588,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7662,
+      "step": 34
+    },
+    {
+      "epoch": 0.47904191616766467,
+      "grad_norm": 1.2101404666900635,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6766,
+      "step": 35
+    },
+    {
+      "epoch": 0.49272882805816937,
+      "grad_norm": 1.462323546409607,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.7952,
+      "step": 36
+    },
+    {
+      "epoch": 0.5064157399486741,
+      "grad_norm": 1.990311861038208,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0486,
+      "step": 37
+    },
+    {
+      "epoch": 0.5201026518391788,
+      "grad_norm": 1.2818390130996704,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5182,
+      "step": 38
+    },
+    {
+      "epoch": 0.5337895637296834,
+      "grad_norm": 0.8473722338676453,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5777,
+      "step": 39
+    },
+    {
+      "epoch": 0.5474764756201882,
+      "grad_norm": 1.3635905981063843,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4073,
+      "step": 40
+    },
+    {
+      "epoch": 0.561163387510693,
+      "grad_norm": 1.370269536972046,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3791,
+      "step": 41
+    },
+    {
+      "epoch": 0.5748502994011976,
+      "grad_norm": 1.566010594367981,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4403,
+      "step": 42
+    },
+    {
+      "epoch": 0.5885372112917023,
+      "grad_norm": 1.6927084922790527,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4468,
+      "step": 43
+    },
+    {
+      "epoch": 0.602224123182207,
+      "grad_norm": 1.8676680326461792,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.3234,
+      "step": 44
+    },
+    {
+      "epoch": 0.6159110350727117,
+      "grad_norm": 1.352358102798462,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6321,
+      "step": 45
+    },
+    {
+      "epoch": 0.6295979469632165,
+      "grad_norm": 1.2584972381591797,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.907,
+      "step": 46
+    },
+    {
+      "epoch": 0.6432848588537211,
+      "grad_norm": 1.0651510953903198,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.6019,
+      "step": 47
+    },
+    {
+      "epoch": 0.6569717707442259,
+      "grad_norm": 1.1571849584579468,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.605,
+      "step": 48
+    },
+    {
+      "epoch": 0.6706586826347305,
+      "grad_norm": 1.4067716598510742,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.7436,
+      "step": 49
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "grad_norm": 2.812145709991455,
+      "learning_rate": 0.0,
+      "loss": 1.1729,
+      "step": 50
+    },
+    {
+      "epoch": 0.6843455945252352,
+      "eval_loss": 0.5393621325492859,
+      "eval_runtime": 3.3647,
+      "eval_samples_per_second": 146.522,
+      "eval_steps_per_second": 18.427,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null