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:b279bb4f687ba9c3036b5809f8349f562ddabd31f4e3ef399f4a1f8a1dc51072
+oid sha256:9b3f159d6e399590782f4c47c76f04d82cac32f54491176e98923f648e9a8c57
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dbb542d07010bfad99e56ce6097ec2f71c71ebc53c9f8032ac829c41bc8d2296
+oid sha256:41563507f6cf589b5a04900e63dc1a178da1f89dff54f3c83ad39bb74d0a12ac
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58a2434d9ba8434a212424f651387de433a6453cbeb2bab1493b39b7036fe174
+oid sha256:1fc3938e94bb9593ede3ac4bc61deb8cf1abf1f091350e4a7c4f31e581316a40
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0f56738954a93628713c79b08cdcbbe4839cc66395dec8f03c74cd23c4ba371f
+oid sha256:8580cf1ff2bab9f0ee79c29f227a00bb6e340ff1929624aec67d53a6d2879786
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8fe4ffde8c01346da3e697bbfd6dd14af6ee031f014f8802e46fb7e2356b84f4
+oid sha256:73c812a96176f270fe252e30b1432d0f887841e83d4d5fde2e830ebd8e15f031
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:82028d06a4c86cd7962a233611a52304d63cc3b9a071a972ee0afdff108db7cb
+oid sha256:ab2d2d14e25cf3a3c23eb7f7de2a59f364cbc175043016606077e10ee4011135
 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": 3.763901472091675,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.10244589576130106,
+  "best_metric": 3.6524410247802734,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.20489179152260212,
   "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": 10.34,
       "eval_steps_per_second": 2.688,
       "step": 25
+    },
+    {
+      "epoch": 0.10654373159175311,
+      "grad_norm": 1.9079407453536987,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.8517,
+      "step": 26
+    },
+    {
+      "epoch": 0.11064156742220514,
+      "grad_norm": 1.4432978630065918,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 3.8022,
+      "step": 27
+    },
+    {
+      "epoch": 0.11473940325265719,
+      "grad_norm": 1.3254631757736206,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 3.7132,
+      "step": 28
+    },
+    {
+      "epoch": 0.11883723908310924,
+      "grad_norm": 1.2801110744476318,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 3.7882,
+      "step": 29
+    },
+    {
+      "epoch": 0.12293507491356127,
+      "grad_norm": 0.9412828087806702,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.632,
+      "step": 30
+    },
+    {
+      "epoch": 0.12703291074401332,
+      "grad_norm": 1.3773285150527954,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 3.6076,
+      "step": 31
+    },
+    {
+      "epoch": 0.13113074657446536,
+      "grad_norm": 1.1964783668518066,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 3.638,
+      "step": 32
+    },
+    {
+      "epoch": 0.1352285824049174,
+      "grad_norm": 0.9496121406555176,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 3.7015,
+      "step": 33
+    },
+    {
+      "epoch": 0.13932641823536945,
+      "grad_norm": 1.2388590574264526,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.6222,
+      "step": 34
+    },
+    {
+      "epoch": 0.1434242540658215,
+      "grad_norm": 1.1453251838684082,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 3.6447,
+      "step": 35
+    },
+    {
+      "epoch": 0.14752208989627352,
+      "grad_norm": 1.0861890316009521,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 3.6983,
+      "step": 36
+    },
+    {
+      "epoch": 0.15161992572672559,
+      "grad_norm": 1.466780424118042,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 3.874,
+      "step": 37
+    },
+    {
+      "epoch": 0.15571776155717762,
+      "grad_norm": 1.2210124731063843,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 3.7076,
+      "step": 38
+    },
+    {
+      "epoch": 0.15981559738762965,
+      "grad_norm": 1.3490753173828125,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.6633,
+      "step": 39
+    },
+    {
+      "epoch": 0.1639134332180817,
+      "grad_norm": 0.9062822461128235,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 3.7274,
+      "step": 40
+    },
+    {
+      "epoch": 0.16801126904853375,
+      "grad_norm": 0.9520427584648132,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 3.6353,
+      "step": 41
+    },
+    {
+      "epoch": 0.17210910487898579,
+      "grad_norm": 1.2778575420379639,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 3.6745,
+      "step": 42
+    },
+    {
+      "epoch": 0.17620694070943782,
+      "grad_norm": 1.169716477394104,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.6648,
+      "step": 43
+    },
+    {
+      "epoch": 0.18030477653988988,
+      "grad_norm": 0.8360440731048584,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 3.6354,
+      "step": 44
+    },
+    {
+      "epoch": 0.18440261237034192,
+      "grad_norm": 0.8596037030220032,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 3.621,
+      "step": 45
+    },
+    {
+      "epoch": 0.18850044820079395,
+      "grad_norm": 0.8236773014068604,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 3.5638,
+      "step": 46
+    },
+    {
+      "epoch": 0.192598284031246,
+      "grad_norm": 1.0101842880249023,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 3.6251,
+      "step": 47
+    },
+    {
+      "epoch": 0.19669611986169805,
+      "grad_norm": 1.1143778562545776,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 3.6001,
+      "step": 48
+    },
+    {
+      "epoch": 0.20079395569215008,
+      "grad_norm": 1.1271101236343384,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 3.6615,
+      "step": 49
+    },
+    {
+      "epoch": 0.20489179152260212,
+      "grad_norm": 1.5570321083068848,
+      "learning_rate": 1e-05,
+      "loss": 3.8948,
+      "step": 50
+    },
+    {
+      "epoch": 0.20489179152260212,
+      "eval_loss": 3.6524410247802734,
+      "eval_runtime": 4.841,
+      "eval_samples_per_second": 10.328,
+      "eval_steps_per_second": 2.685,
+      "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": 3.087239672233984e+17,
+  "total_flos": 6.174479344467968e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null