Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0e243ddc6f4bbd6e923872df814abd3af107c8fec1a4a109a5378f83386917a3
+oid sha256:ff70a3eea48d76f99e10e87aa93ecd96a9b7034e055a0e218a3d22f8780b3eab
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea27c55c6926cde825051053ce37c49d21cbb86eb30ed3d62d908da6aad076d
+oid sha256:6ebacebc62d8be4474e97b9f16484cc388503aefcb006f6a07512c74685f72b4
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8e2c70d5a759d65afc03096684553b6e6fda2d71a3bc3fc259b29ff9b55f61d
+oid sha256:4a14823d0f023fa51eaf33dec6516ebff0dd70b88adb2e6dfb875973e628d821
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c1b3dbe50fdab8c889eebf9a4db677f95c86baf35f92d712d54851cb582e49b8
+oid sha256:51e976a9fd2fe4d43df151822a863605486e237484ec611839bac2b6db90b1af
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fb921076bb24f50b9b2240c6c32e237cc4d1b7fa91599ea22d771e7c496e64e
+oid sha256:0fa17af4073a4b66dcdd1b7a682b66feb9ab175aa18b21cbb2874c714c83db2a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e5767311e5bf7263e82bac4a7a5e7ea11fe26aee6866c7e63b0b056d63285c5
+oid sha256:6a075c88c0f33a8ad46743a18c333cc8fc0ce0f2ddedd0dfd6b4974f5491b017
 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": 10.363873481750488,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.059497248252268334,
+  "best_metric": 10.357853889465332,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11899449650453667,
   "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": 612.812,
       "eval_steps_per_second": 159.331,
       "step": 25
+    },
+    {
+      "epoch": 0.061877138182359064,
+      "grad_norm": 0.06834245473146439,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 10.3747,
+      "step": 26
+    },
+    {
+      "epoch": 0.0642570281124498,
+      "grad_norm": 0.07222069799900055,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 10.3685,
+      "step": 27
+    },
+    {
+      "epoch": 0.06663691804254053,
+      "grad_norm": 0.10398434102535248,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 10.3603,
+      "step": 28
+    },
+    {
+      "epoch": 0.06901680797263127,
+      "grad_norm": 0.1319500207901001,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 10.3593,
+      "step": 29
+    },
+    {
+      "epoch": 0.071396697902722,
+      "grad_norm": 0.13767267763614655,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 10.3598,
+      "step": 30
+    },
+    {
+      "epoch": 0.07377658783281273,
+      "grad_norm": 0.1553162932395935,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 10.3605,
+      "step": 31
+    },
+    {
+      "epoch": 0.07615647776290346,
+      "grad_norm": 0.16494451463222504,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3616,
+      "step": 32
+    },
+    {
+      "epoch": 0.0785363676929942,
+      "grad_norm": 0.17596690356731415,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 10.3608,
+      "step": 33
+    },
+    {
+      "epoch": 0.08091625762308494,
+      "grad_norm": 0.1648629605770111,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 10.3584,
+      "step": 34
+    },
+    {
+      "epoch": 0.08329614755317566,
+      "grad_norm": 0.16102421283721924,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 10.3577,
+      "step": 35
+    },
+    {
+      "epoch": 0.0856760374832664,
+      "grad_norm": 0.15746867656707764,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 10.3566,
+      "step": 36
+    },
+    {
+      "epoch": 0.08805592741335713,
+      "grad_norm": 0.18058502674102783,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.3559,
+      "step": 37
+    },
+    {
+      "epoch": 0.09043581734344787,
+      "grad_norm": 0.08370359987020493,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.3671,
+      "step": 38
+    },
+    {
+      "epoch": 0.0928157072735386,
+      "grad_norm": 0.06642691045999527,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 10.375,
+      "step": 39
+    },
+    {
+      "epoch": 0.09519559720362933,
+      "grad_norm": 0.10110778361558914,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 10.3617,
+      "step": 40
+    },
+    {
+      "epoch": 0.09757548713372007,
+      "grad_norm": 0.12056875973939896,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 10.3613,
+      "step": 41
+    },
+    {
+      "epoch": 0.0999553770638108,
+      "grad_norm": 0.14950105547904968,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 10.3561,
+      "step": 42
+    },
+    {
+      "epoch": 0.10233526699390154,
+      "grad_norm": 0.18000173568725586,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 10.3575,
+      "step": 43
+    },
+    {
+      "epoch": 0.10471515692399226,
+      "grad_norm": 0.18226058781147003,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.3569,
+      "step": 44
+    },
+    {
+      "epoch": 0.107095046854083,
+      "grad_norm": 0.1937638521194458,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 10.3542,
+      "step": 45
+    },
+    {
+      "epoch": 0.10947493678417373,
+      "grad_norm": 0.18526925146579742,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 10.3531,
+      "step": 46
+    },
+    {
+      "epoch": 0.11185482671426447,
+      "grad_norm": 0.2028881460428238,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 10.3568,
+      "step": 47
+    },
+    {
+      "epoch": 0.1142347166443552,
+      "grad_norm": 0.18155358731746674,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 10.3561,
+      "step": 48
+    },
+    {
+      "epoch": 0.11661460657444593,
+      "grad_norm": 0.17677204310894012,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.3552,
+      "step": 49
+    },
+    {
+      "epoch": 0.11899449650453667,
+      "grad_norm": 0.1765909194946289,
+      "learning_rate": 1e-05,
+      "loss": 10.3561,
+      "step": 50
+    },
+    {
+      "epoch": 0.11899449650453667,
+      "eval_loss": 10.357853889465332,
+      "eval_runtime": 0.0832,
+      "eval_samples_per_second": 601.218,
+      "eval_steps_per_second": 156.317,
+      "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": 21384029798400.0,
+  "total_flos": 42768059596800.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null