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:fe2eb4e145fa8221ea048e4f522e9acecfd5c66ea3be77bca14673d57cd152c1
+oid sha256:cfa2a5b3eece0dd704079be9d6c710598cef478551b8fd77530d199dfef63945
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:735d47667d28e94dd281497b6179a1358544b5d737a96ff03abfa9b9cd98a6b2
+oid sha256:c6838c4fc40a332b6300631d038fdae611bebcc90852b3d55c468d6a352f88f9
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a34c47eb333704b3847869f21df7b73675d47415b83f3a5c0a7346fde67ac586
+oid sha256:a02bce9736e66f5d30bbf3e76627fa9d1df027ded14eebf6738594a6efd8379b
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a37c8b3174e20f81cf03ee7a64d3223df39e58383e28f02e7d27684982ccd76c
+oid sha256:7e14d6b6e7f248a6f1185d1bb0aceab636abf269559a04cd62d616ec8f5df7dc
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fba971a1814bd31bf5d580c2f0e4035ae01cb4a2940c1774b3535173e39affa9
+oid sha256:27613f7985ca15bedf09522283eb35c2e2191533dcbeb80901e3aa5e43690bc3
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eee7932315201a0c23ac7580f4372d0042d34d6e65e0c974f259dcf76d1ed2d3
+oid sha256:40cfb1d738b734633790aa6258c4931bbe4ab9b3313e5dfdd712e4aeced04979
 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": 0.1733342856168747,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.02914602156805596,
+  "best_metric": 0.12431660294532776,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.05829204313611192,
   "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": 32.955,
       "eval_steps_per_second": 4.123,
       "step": 25
+    },
+    {
+      "epoch": 0.0303118624307782,
+      "grad_norm": 5.865137100219727,
+      "learning_rate": 5e-05,
+      "loss": 0.2452,
+      "step": 26
+    },
+    {
+      "epoch": 0.031477703293500435,
+      "grad_norm": 3.4867568016052246,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.2191,
+      "step": 27
+    },
+    {
+      "epoch": 0.03264354415622268,
+      "grad_norm": 2.2110798358917236,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.1272,
+      "step": 28
+    },
+    {
+      "epoch": 0.03380938501894491,
+      "grad_norm": 1.080565094947815,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.1427,
+      "step": 29
+    },
+    {
+      "epoch": 0.034975225881667155,
+      "grad_norm": 2.4473915100097656,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.1414,
+      "step": 30
+    },
+    {
+      "epoch": 0.03614106674438939,
+      "grad_norm": 1.6242526769638062,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.1169,
+      "step": 31
+    },
+    {
+      "epoch": 0.03730690760711163,
+      "grad_norm": 0.48892101645469666,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.099,
+      "step": 32
+    },
+    {
+      "epoch": 0.03847274846983387,
+      "grad_norm": 1.3659566640853882,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.1268,
+      "step": 33
+    },
+    {
+      "epoch": 0.03963858933255611,
+      "grad_norm": 1.2674806118011475,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.1134,
+      "step": 34
+    },
+    {
+      "epoch": 0.040804430195278345,
+      "grad_norm": 0.8224604725837708,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1139,
+      "step": 35
+    },
+    {
+      "epoch": 0.04197027105800058,
+      "grad_norm": 1.6787289381027222,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.1354,
+      "step": 36
+    },
+    {
+      "epoch": 0.04313611192072282,
+      "grad_norm": 2.8732471466064453,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.1431,
+      "step": 37
+    },
+    {
+      "epoch": 0.04430195278344506,
+      "grad_norm": 0.9703247547149658,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.1333,
+      "step": 38
+    },
+    {
+      "epoch": 0.0454677936461673,
+      "grad_norm": 0.530714213848114,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.1256,
+      "step": 39
+    },
+    {
+      "epoch": 0.046633634508889535,
+      "grad_norm": 0.4804125726222992,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.1302,
+      "step": 40
+    },
+    {
+      "epoch": 0.04779947537161178,
+      "grad_norm": 0.6326729655265808,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.1215,
+      "step": 41
+    },
+    {
+      "epoch": 0.04896531623433401,
+      "grad_norm": 0.6073267459869385,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.1261,
+      "step": 42
+    },
+    {
+      "epoch": 0.050131157097056255,
+      "grad_norm": 0.46726205945014954,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.1253,
+      "step": 43
+    },
+    {
+      "epoch": 0.05129699795977849,
+      "grad_norm": 0.7564307451248169,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.1214,
+      "step": 44
+    },
+    {
+      "epoch": 0.05246283882250073,
+      "grad_norm": 0.7565365433692932,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1425,
+      "step": 45
+    },
+    {
+      "epoch": 0.05362867968522297,
+      "grad_norm": 0.6103953719139099,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.1005,
+      "step": 46
+    },
+    {
+      "epoch": 0.0547945205479452,
+      "grad_norm": 0.5481635332107544,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.112,
+      "step": 47
+    },
+    {
+      "epoch": 0.055960361410667445,
+      "grad_norm": 1.2962995767593384,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.1086,
+      "step": 48
+    },
+    {
+      "epoch": 0.05712620227338968,
+      "grad_norm": 1.229022741317749,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.1553,
+      "step": 49
+    },
+    {
+      "epoch": 0.05829204313611192,
+      "grad_norm": 0.7609378695487976,
+      "learning_rate": 0.0,
+      "loss": 0.1328,
+      "step": 50
+    },
+    {
+      "epoch": 0.05829204313611192,
+      "eval_loss": 0.12431660294532776,
+      "eval_runtime": 175.3436,
+      "eval_samples_per_second": 32.958,
+      "eval_steps_per_second": 4.123,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null