Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c06229bc6fd3db9913129f2caac1687d8c8d4a1320540c6c052387a4cf1589a
+oid sha256:f4646d665cc3b8a18921b451990977727076442ada94836cccb72d854b780632
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1bac203ecba8c08b095adf5fb9cacb0f51500c65d63bd8b111208d6f2b7638c
+oid sha256:8fcc406ce3163d4d65f0b2af64e18aee40d4664419f4a9da6ec109891a7c1c30
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d5557e73cf47fea7e6e91b9332fcf0de6697fd421d6c8eb1f56a6cf1a9e6e16
+oid sha256:c83e9c6cffe56906fb96ccc931c4ff7c8b1f2c456963bf71ddeb0bfdec5ea259
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e7ce3b51bc003b51fe6bcdc786d9e3f055758523291c74799b3d849dc9e1a4fa
+oid sha256:71840f8f7bc3fccb54dbb4fb4d2ea3e9d129e4f0641547c4caa35a359579569c
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:81515458257392be11098b823e7f92de34f9a6f16f228a3ea914333eea074fd9
+oid sha256:bd0d9ca789ef68048d61d945bf9781223b77e731b891dc6083382d31cb5230f9
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b5ff328fb3660cf3bf5af8f770c949ac6091f2492e16e58a58c1b17403631d
+oid sha256:6f788ca2e8552811d4d77376235a5ae4932cb455a198476098be6dbb00a40113
 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": 0.5549858212471008,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010689756540794784,
+  "best_metric": 0.53879714012146,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.021379513081589568,
   "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": 10.51,
       "eval_steps_per_second": 2.732,
       "step": 25
+    },
+    {
+      "epoch": 0.011117346802426575,
+      "grad_norm": 6.102064609527588,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 5.7123,
+      "step": 26
+    },
+    {
+      "epoch": 0.011544937064058366,
+      "grad_norm": 7.0178656578063965,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 7.5794,
+      "step": 27
+    },
+    {
+      "epoch": 0.011972527325690157,
+      "grad_norm": 6.182474136352539,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 7.5756,
+      "step": 28
+    },
+    {
+      "epoch": 0.012400117587321948,
+      "grad_norm": 5.909448146820068,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 7.8836,
+      "step": 29
+    },
+    {
+      "epoch": 0.01282770784895374,
+      "grad_norm": 6.4864726066589355,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 8.2802,
+      "step": 30
+    },
+    {
+      "epoch": 0.01325529811058553,
+      "grad_norm": 6.8360443115234375,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 8.946,
+      "step": 31
+    },
+    {
+      "epoch": 0.013682888372217322,
+      "grad_norm": 6.480278491973877,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 8.9649,
+      "step": 32
+    },
+    {
+      "epoch": 0.014110478633849115,
+      "grad_norm": 6.515498161315918,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 8.7772,
+      "step": 33
+    },
+    {
+      "epoch": 0.014538068895480906,
+      "grad_norm": 6.456510066986084,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 9.118,
+      "step": 34
+    },
+    {
+      "epoch": 0.014965659157112697,
+      "grad_norm": 6.677673816680908,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 9.3821,
+      "step": 35
+    },
+    {
+      "epoch": 0.015393249418744488,
+      "grad_norm": 7.584144592285156,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 9.8773,
+      "step": 36
+    },
+    {
+      "epoch": 0.01582083968037628,
+      "grad_norm": 7.644411087036133,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 10.0979,
+      "step": 37
+    },
+    {
+      "epoch": 0.01624842994200807,
+      "grad_norm": 6.097660064697266,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 7.3581,
+      "step": 38
+    },
+    {
+      "epoch": 0.01667602020363986,
+      "grad_norm": 5.650531768798828,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 6.9252,
+      "step": 39
+    },
+    {
+      "epoch": 0.017103610465271653,
+      "grad_norm": 6.409210205078125,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 7.6358,
+      "step": 40
+    },
+    {
+      "epoch": 0.017531200726903444,
+      "grad_norm": 6.688713073730469,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 8.1115,
+      "step": 41
+    },
+    {
+      "epoch": 0.017958790988535235,
+      "grad_norm": 6.200973033905029,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 8.2123,
+      "step": 42
+    },
+    {
+      "epoch": 0.018386381250167026,
+      "grad_norm": 6.261044025421143,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 8.687,
+      "step": 43
+    },
+    {
+      "epoch": 0.018813971511798817,
+      "grad_norm": 5.8840179443359375,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 8.2914,
+      "step": 44
+    },
+    {
+      "epoch": 0.01924156177343061,
+      "grad_norm": 6.317307472229004,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 8.8269,
+      "step": 45
+    },
+    {
+      "epoch": 0.019669152035062403,
+      "grad_norm": 6.801748275756836,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 9.2658,
+      "step": 46
+    },
+    {
+      "epoch": 0.020096742296694194,
+      "grad_norm": 6.915708065032959,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 9.0082,
+      "step": 47
+    },
+    {
+      "epoch": 0.020524332558325985,
+      "grad_norm": 6.995912551879883,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 9.375,
+      "step": 48
+    },
+    {
+      "epoch": 0.020951922819957777,
+      "grad_norm": 8.353010177612305,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 10.1514,
+      "step": 49
+    },
+    {
+      "epoch": 0.021379513081589568,
+      "grad_norm": 9.611238479614258,
+      "learning_rate": 1e-05,
+      "loss": 10.2421,
+      "step": 50
+    },
+    {
+      "epoch": 0.021379513081589568,
+      "eval_loss": 0.53879714012146,
+      "eval_runtime": 4.7618,
+      "eval_samples_per_second": 10.5,
+      "eval_steps_per_second": 2.73,
+      "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": 2.8749820985553715e+17,
+  "total_flos": 5.7570367304944845e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null