Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5b336babce88b9734ac9a329c85b5aa61f02937aa8399e161faf1aed4a5251d1
+oid sha256:3eef859a0bd7c0c42743d0bf56c2756ff95a2ff2e062a7b476419d6c5052e9fc
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dacb0b4a6b2a22ecece29a8ee1235311c71dcaaafb3394e1206a927eb0bd51d7
+oid sha256:fd48a15c40f44f2903b63ae37a75c6234430d87e2cf192b98a92aaa7167490c8
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3305013ad0062918e6de875c136f29ff31fc26aded2ead91a97403155550973f
+oid sha256:72fb4f236274676f927494d500fc685fa9d257a9cdc17e3ea811ac75245519d3
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:62737b6b5714426bad2ea771fa7a7ea754d3f11ee605bfe37b1c5dbabb614a31
+oid sha256:578ff54130c59a29840d32a9dde1b96572b9bf5c4f49548a43f2f198e565b7d3
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:89888a90cbe4317ac0c782401073a693e12f0680ff224a5f1fed7dca4259c168
+oid sha256:505f086a6fadac78c549aa3c5fcf9b8daf29bf320c61abaa93ac3904db7cbc58
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0fac1efcec7948392e8c0a818539ad8be82dc59311b997ffd444dfd4ee173675
+oid sha256:1217cfc08932d033d21dbc467d3e932289415562661809f51572c5d1477cfd9f
 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": 1.1771202087402344,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.14738393515106854,
+  "best_metric": 1.1518352031707764,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.2947678703021371,
   "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": 84.755,
       "eval_steps_per_second": 10.604,
       "step": 25
+    },
+    {
+      "epoch": 0.15327929255711129,
+      "grad_norm": 0.41432493925094604,
+      "learning_rate": 5e-05,
+      "loss": 1.3968,
+      "step": 26
+    },
+    {
+      "epoch": 0.159174649963154,
+      "grad_norm": 0.4302958548069,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.3309,
+      "step": 27
+    },
+    {
+      "epoch": 0.16507000736919675,
+      "grad_norm": 0.4882798492908478,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4163,
+      "step": 28
+    },
+    {
+      "epoch": 0.1709653647752395,
+      "grad_norm": 0.5064733624458313,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.335,
+      "step": 29
+    },
+    {
+      "epoch": 0.17686072218128224,
+      "grad_norm": 0.4844876229763031,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2396,
+      "step": 30
+    },
+    {
+      "epoch": 0.18275607958732498,
+      "grad_norm": 0.47237423062324524,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.1634,
+      "step": 31
+    },
+    {
+      "epoch": 0.18865143699336773,
+      "grad_norm": 0.5116559863090515,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.15,
+      "step": 32
+    },
+    {
+      "epoch": 0.19454679439941047,
+      "grad_norm": 0.33985745906829834,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.0385,
+      "step": 33
+    },
+    {
+      "epoch": 0.20044215180545322,
+      "grad_norm": 0.3580736815929413,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.0018,
+      "step": 34
+    },
+    {
+      "epoch": 0.20633750921149593,
+      "grad_norm": 0.3772769868373871,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.0042,
+      "step": 35
+    },
+    {
+      "epoch": 0.21223286661753868,
+      "grad_norm": 0.3896821141242981,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.9262,
+      "step": 36
+    },
+    {
+      "epoch": 0.21812822402358142,
+      "grad_norm": 0.38928064703941345,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.9422,
+      "step": 37
+    },
+    {
+      "epoch": 0.22402358142962417,
+      "grad_norm": 0.3280961513519287,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2344,
+      "step": 38
+    },
+    {
+      "epoch": 0.22991893883566691,
+      "grad_norm": 0.32811683416366577,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3309,
+      "step": 39
+    },
+    {
+      "epoch": 0.23581429624170966,
+      "grad_norm": 0.32886970043182373,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3533,
+      "step": 40
+    },
+    {
+      "epoch": 0.2417096536477524,
+      "grad_norm": 0.34771019220352173,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1761,
+      "step": 41
+    },
+    {
+      "epoch": 0.24760501105379515,
+      "grad_norm": 0.38889893889427185,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2497,
+      "step": 42
+    },
+    {
+      "epoch": 0.25350036845983787,
+      "grad_norm": 0.42282721400260925,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.1889,
+      "step": 43
+    },
+    {
+      "epoch": 0.2593957258658806,
+      "grad_norm": 0.3826811909675598,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.0699,
+      "step": 44
+    },
+    {
+      "epoch": 0.26529108327192336,
+      "grad_norm": 0.32068920135498047,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.9982,
+      "step": 45
+    },
+    {
+      "epoch": 0.2711864406779661,
+      "grad_norm": 0.3361916244029999,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.0015,
+      "step": 46
+    },
+    {
+      "epoch": 0.27708179808400885,
+      "grad_norm": 0.332919716835022,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9339,
+      "step": 47
+    },
+    {
+      "epoch": 0.2829771554900516,
+      "grad_norm": 0.3428276479244232,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.9266,
+      "step": 48
+    },
+    {
+      "epoch": 0.28887251289609434,
+      "grad_norm": 0.3674064874649048,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9696,
+      "step": 49
+    },
+    {
+      "epoch": 0.2947678703021371,
+      "grad_norm": 0.42665550112724304,
+      "learning_rate": 0.0,
+      "loss": 0.9495,
+      "step": 50
+    },
+    {
+      "epoch": 0.2947678703021371,
+      "eval_loss": 1.1518352031707764,
+      "eval_runtime": 13.463,
+      "eval_samples_per_second": 84.899,
+      "eval_steps_per_second": 10.622,
+      "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": 2.2913505166360576e+16,
+  "total_flos": 4.556862208029491e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null