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:c1baf1bd7e24d723de0c445b489ffaa35a3a3cc616f8b9032917c5e66084bc10
+oid sha256:3726687cf7e6e2a5c6c0b646743102f5ad7b34a7d6c3607a40b868b6b36fef7b
 size 239536272

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06f0e17ec207739d29399bd99750a2b602afefaf0296dcc9bd505c3e1ad709f6
+oid sha256:edb36434b1455bacb11c7d6a4fbaeb9bcfd842e44cc3aea24f30ac4a36f7d729
 size 479362682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6aec09a74f0f91557b74deae91a0776cac05f4fdb8b08e9ebf8184ad7cf164d6
+oid sha256:89c19a08b9cef6b66e015dd43e9e84ec9dde230de0901dd3a8959d3724169716
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:97cd21b942e705e5dac06c3f9635509867e087ef57bf28803ee3263486f7d574
+oid sha256:408a6d5101f49a02ca32f1b9608f7b8f09d34dd3e7c774497185a175cb2ddfe5
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31f9c76feeac012b484e47b12157c3579b8e1e97d463d79e326b70580af59444
+oid sha256:1b5b065adac20fb989deae5d818c6368363d1e62578d1697edfd318ffa59113a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7caf908051c4d9b084ec4ebe11162429da2981833ac01fb4c1b489e96d28e51f
+oid sha256:2830742ba2ee715f7b7c50c74592291cfdd70224f60017995aea6bf4f5c45a29
 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": 1.3445146083831787,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.1299435028248588,
+  "best_metric": 1.3316872119903564,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.2598870056497176,
   "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": 56.518,
       "eval_steps_per_second": 7.159,
       "step": 25
+    },
+    {
+      "epoch": 1.1751412429378532,
+      "grad_norm": 0.2728276550769806,
+      "learning_rate": 5e-05,
+      "loss": 1.307,
+      "step": 26
+    },
+    {
+      "epoch": 1.2203389830508475,
+      "grad_norm": 0.3243846893310547,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.2456,
+      "step": 27
+    },
+    {
+      "epoch": 1.2655367231638417,
+      "grad_norm": 0.19411033391952515,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2509,
+      "step": 28
+    },
+    {
+      "epoch": 1.310734463276836,
+      "grad_norm": 0.1757993847131729,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.5307,
+      "step": 29
+    },
+    {
+      "epoch": 1.3559322033898304,
+      "grad_norm": 0.21353618800640106,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3326,
+      "step": 30
+    },
+    {
+      "epoch": 1.4011299435028248,
+      "grad_norm": 0.2679908871650696,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.3144,
+      "step": 31
+    },
+    {
+      "epoch": 1.4463276836158192,
+      "grad_norm": 0.31348928809165955,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.2523,
+      "step": 32
+    },
+    {
+      "epoch": 1.4915254237288136,
+      "grad_norm": 0.2946011424064636,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.2485,
+      "step": 33
+    },
+    {
+      "epoch": 1.536723163841808,
+      "grad_norm": 0.15832407772541046,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3634,
+      "step": 34
+    },
+    {
+      "epoch": 1.5819209039548023,
+      "grad_norm": 0.17590704560279846,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.3351,
+      "step": 35
+    },
+    {
+      "epoch": 1.6271186440677967,
+      "grad_norm": 0.2035454660654068,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.3247,
+      "step": 36
+    },
+    {
+      "epoch": 1.672316384180791,
+      "grad_norm": 0.2129197120666504,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.2981,
+      "step": 37
+    },
+    {
+      "epoch": 1.7175141242937855,
+      "grad_norm": 0.29245874285697937,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2265,
+      "step": 38
+    },
+    {
+      "epoch": 1.7627118644067796,
+      "grad_norm": 0.17280784249305725,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2161,
+      "step": 39
+    },
+    {
+      "epoch": 1.807909604519774,
+      "grad_norm": 0.15356288850307465,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.5015,
+      "step": 40
+    },
+    {
+      "epoch": 1.8531073446327684,
+      "grad_norm": 0.1719873696565628,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.3178,
+      "step": 41
+    },
+    {
+      "epoch": 1.8983050847457628,
+      "grad_norm": 0.19485509395599365,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.303,
+      "step": 42
+    },
+    {
+      "epoch": 1.943502824858757,
+      "grad_norm": 0.25505155324935913,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2617,
+      "step": 43
+    },
+    {
+      "epoch": 1.9887005649717513,
+      "grad_norm": 0.36434733867645264,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.2443,
+      "step": 44
+    },
+    {
+      "epoch": 2.0338983050847457,
+      "grad_norm": 0.4829481542110443,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.5418,
+      "step": 45
+    },
+    {
+      "epoch": 2.07909604519774,
+      "grad_norm": 0.14236965775489807,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.333,
+      "step": 46
+    },
+    {
+      "epoch": 2.1242937853107344,
+      "grad_norm": 0.17663514614105225,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.3061,
+      "step": 47
+    },
+    {
+      "epoch": 2.169491525423729,
+      "grad_norm": 0.20408064126968384,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2736,
+      "step": 48
+    },
+    {
+      "epoch": 2.214689265536723,
+      "grad_norm": 0.2776390314102173,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.2458,
+      "step": 49
+    },
+    {
+      "epoch": 2.2598870056497176,
+      "grad_norm": 0.1917027235031128,
+      "learning_rate": 0.0,
+      "loss": 1.0958,
+      "step": 50
+    },
+    {
+      "epoch": 2.2598870056497176,
+      "eval_loss": 1.3316872119903564,
+      "eval_runtime": 2.6518,
+      "eval_samples_per_second": 56.565,
+      "eval_steps_per_second": 7.165,
+      "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": 1.114626154561536e+17,
+  "total_flos": 2.229252309123072e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null