Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:804c7a491dd4129a03c87a0e64554a3c80bc6afebabdbce127e8299f3b692899
+oid sha256:8eaf8b33bd3236becab8b3c18da31589cef1bd8d5fb7c1f063e637c8cd7f51be
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edeabb9b909e3e62e87d83d17d5873a9140a069e1cd77babb101fc6693672764
+oid sha256:f44184e0bc3f00618a5cf577cf99cea35579185c575802c420126b3713b3d878
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4690a3509cc5659a8c207fe43097546e6998e994c0c79817eff9769ffd796dac
+oid sha256:1702b52f6aa6d94640c418f804cceb8dc8d9b9323179797c13c604eae3f09272
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21a04b880c83e07b3ee3f3174ea4669be3454922aad2219e6839dcd55d24be2e
+oid sha256:2874886b376d27153b0e056cd5028cd1ccdc684f5e69127e1324f628ea19b9a4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fedd98af41e4021c4205eb58c11a700589e089a86fe19c11c4a45aca10585bb8
+oid sha256:d39bc9f5bc62a3f8a1ac1967dfe2f26fd5f014b7982b4077911cd89526cb90fc
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10b006ff0a5d3df787b439dfb6bda01f1676e713627d50d8bb3ee8005b2fe825
+oid sha256:1a5e34473aadf99460dcdbeec4ae87778faafdcd3ab5e54b50b31109213d7c4d
 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": 1.3627617359161377,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.5730659025787965,
+  "best_metric": 1.312924861907959,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.1475644699140402,
   "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": 10.551,
       "eval_steps_per_second": 2.743,
       "step": 25
+    },
+    {
+      "epoch": 0.5959885386819485,
+      "grad_norm": 27.527820587158203,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 23.6761,
+      "step": 26
+    },
+    {
+      "epoch": 0.6189111747851003,
+      "grad_norm": 27.30636215209961,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 22.9558,
+      "step": 27
+    },
+    {
+      "epoch": 0.6418338108882522,
+      "grad_norm": 29.87013053894043,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 23.2196,
+      "step": 28
+    },
+    {
+      "epoch": 0.664756446991404,
+      "grad_norm": 29.727075576782227,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 21.3986,
+      "step": 29
+    },
+    {
+      "epoch": 0.6876790830945558,
+      "grad_norm": 29.525386810302734,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 21.6861,
+      "step": 30
+    },
+    {
+      "epoch": 0.7106017191977078,
+      "grad_norm": 29.010095596313477,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 22.7758,
+      "step": 31
+    },
+    {
+      "epoch": 0.7335243553008596,
+      "grad_norm": 32.525333404541016,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 19.9094,
+      "step": 32
+    },
+    {
+      "epoch": 0.7564469914040115,
+      "grad_norm": 35.969703674316406,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 21.9237,
+      "step": 33
+    },
+    {
+      "epoch": 0.7793696275071633,
+      "grad_norm": 24.25885009765625,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 23.5966,
+      "step": 34
+    },
+    {
+      "epoch": 0.8022922636103151,
+      "grad_norm": 24.96795082092285,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 22.0095,
+      "step": 35
+    },
+    {
+      "epoch": 0.8252148997134671,
+      "grad_norm": 24.220693588256836,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 22.4496,
+      "step": 36
+    },
+    {
+      "epoch": 0.8481375358166189,
+      "grad_norm": 23.359615325927734,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 20.1796,
+      "step": 37
+    },
+    {
+      "epoch": 0.8710601719197708,
+      "grad_norm": 24.08407211303711,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 21.778,
+      "step": 38
+    },
+    {
+      "epoch": 0.8939828080229226,
+      "grad_norm": 27.159765243530273,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 22.5282,
+      "step": 39
+    },
+    {
+      "epoch": 0.9169054441260746,
+      "grad_norm": 25.686376571655273,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 20.8734,
+      "step": 40
+    },
+    {
+      "epoch": 0.9398280802292264,
+      "grad_norm": 27.449390411376953,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 21.2547,
+      "step": 41
+    },
+    {
+      "epoch": 0.9627507163323782,
+      "grad_norm": 30.158475875854492,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 20.4989,
+      "step": 42
+    },
+    {
+      "epoch": 0.9856733524355301,
+      "grad_norm": 33.0136604309082,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 20.1556,
+      "step": 43
+    },
+    {
+      "epoch": 1.010028653295129,
+      "grad_norm": 21.4853572845459,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 21.4587,
+      "step": 44
+    },
+    {
+      "epoch": 1.0329512893982808,
+      "grad_norm": 19.242902755737305,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 20.5628,
+      "step": 45
+    },
+    {
+      "epoch": 1.0558739255014327,
+      "grad_norm": 19.76910400390625,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 19.7431,
+      "step": 46
+    },
+    {
+      "epoch": 1.0787965616045845,
+      "grad_norm": 20.58301544189453,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 20.1779,
+      "step": 47
+    },
+    {
+      "epoch": 1.1017191977077363,
+      "grad_norm": 21.95994758605957,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 19.1627,
+      "step": 48
+    },
+    {
+      "epoch": 1.1246418338108883,
+      "grad_norm": 22.073286056518555,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 17.5031,
+      "step": 49
+    },
+    {
+      "epoch": 1.1475644699140402,
+      "grad_norm": 21.839536666870117,
+      "learning_rate": 1e-05,
+      "loss": 18.7401,
+      "step": 50
+    },
+    {
+      "epoch": 1.1475644699140402,
+      "eval_loss": 1.312924861907959,
+      "eval_runtime": 4.7394,
+      "eval_samples_per_second": 10.55,
+      "eval_steps_per_second": 2.743,
+      "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": 2.829010669142016e+17,
+  "total_flos": 5.658021338284032e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null