Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:493f524fecc919ddd30e79d89a08d8988f5524eb72a8a69f42ef5db13e723ca6
+oid sha256:8f7a52ebf4cc2c68c6f703f2473317d52da89783dbde121bc1f703a99257c64f
 size 400084608

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12a32f489b0dc640d554e08b52963a8a44e4d6ccc5bbab9e8f931e63610f4da0
+oid sha256:270cbf42f9599efe5475961ed16edd72c9bd9a430ec2c8123654591a0d0ab106
 size 800394282

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c3cfca9a007051f9d6f00a8b62250ce903c89e7486bdc5570cb422dc8e36a05
+oid sha256:c88866fcd06fccd0f75dc78b461b73338ae96e82ee70833ffbb5926e07e1d762
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7cee5c293f60ff5bb84c96e8a96153cfd02479afd718c836e5d9e2eac0ebed61
+oid sha256:3f6c8b25bc556d72b249d4a69054bcb8cc09b1727e62ccab781bbaff6a71e55a
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4bc47360cf9d5051ee1e6f5a6d9a730f22aa0e9842c5053170a534746b0fece0
+oid sha256:c6c57dd9affa753556d5a46ea924c0f168bbb4a0785a6f0f7ae912d22a418b58
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:befeb03f30579dcc8ae7fd4c25c16e8e5dd3217ef8dcd164afafefcaf14038be
+oid sha256:4ca87a2349a7003903d88c727b233d71455c55f438f734ab7b33d903eafaf6f8
 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": 1.5664660930633545,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22573363431151242,
+  "best_metric": 1.4240585565567017,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45146726862302483,
   "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": 30.133,
       "eval_steps_per_second": 3.792,
       "step": 25
+    },
+    {
+      "epoch": 0.23476297968397292,
+      "grad_norm": 4.827845096588135,
+      "learning_rate": 5e-05,
+      "loss": 1.6863,
+      "step": 26
+    },
+    {
+      "epoch": 0.24379232505643342,
+      "grad_norm": 3.786040782928467,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.4784,
+      "step": 27
+    },
+    {
+      "epoch": 0.2528216704288939,
+      "grad_norm": 4.99733829498291,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.5557,
+      "step": 28
+    },
+    {
+      "epoch": 0.2618510158013544,
+      "grad_norm": 3.477863073348999,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.4737,
+      "step": 29
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 3.390841245651245,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.479,
+      "step": 30
+    },
+    {
+      "epoch": 0.2799097065462754,
+      "grad_norm": 3.5737245082855225,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4372,
+      "step": 31
+    },
+    {
+      "epoch": 0.28893905191873587,
+      "grad_norm": 3.6658477783203125,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3752,
+      "step": 32
+    },
+    {
+      "epoch": 0.2979683972911964,
+      "grad_norm": 3.751608371734619,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3446,
+      "step": 33
+    },
+    {
+      "epoch": 0.30699774266365687,
+      "grad_norm": 4.204435348510742,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.4559,
+      "step": 34
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 3.454246997833252,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2622,
+      "step": 35
+    },
+    {
+      "epoch": 0.32505643340857787,
+      "grad_norm": 3.807039737701416,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.1839,
+      "step": 36
+    },
+    {
+      "epoch": 0.3340857787810384,
+      "grad_norm": 3.116135597229004,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.0593,
+      "step": 37
+    },
+    {
+      "epoch": 0.3431151241534989,
+      "grad_norm": 3.280864953994751,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.2688,
+      "step": 38
+    },
+    {
+      "epoch": 0.35214446952595935,
+      "grad_norm": 3.6423065662384033,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.5025,
+      "step": 39
+    },
+    {
+      "epoch": 0.3611738148984199,
+      "grad_norm": 4.164337158203125,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.4415,
+      "step": 40
+    },
+    {
+      "epoch": 0.37020316027088035,
+      "grad_norm": 3.5268914699554443,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.5199,
+      "step": 41
+    },
+    {
+      "epoch": 0.3792325056433409,
+      "grad_norm": 3.11435866355896,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.4073,
+      "step": 42
+    },
+    {
+      "epoch": 0.38826185101580135,
+      "grad_norm": 3.4523799419403076,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2832,
+      "step": 43
+    },
+    {
+      "epoch": 0.3972911963882618,
+      "grad_norm": 3.1517751216888428,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.4045,
+      "step": 44
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 3.2089760303497314,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3794,
+      "step": 45
+    },
+    {
+      "epoch": 0.4153498871331828,
+      "grad_norm": 3.2101340293884277,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2995,
+      "step": 46
+    },
+    {
+      "epoch": 0.42437923250564336,
+      "grad_norm": 3.4631175994873047,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4122,
+      "step": 47
+    },
+    {
+      "epoch": 0.43340857787810383,
+      "grad_norm": 3.2164947986602783,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1155,
+      "step": 48
+    },
+    {
+      "epoch": 0.44243792325056436,
+      "grad_norm": 3.03357195854187,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.0593,
+      "step": 49
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 3.364856004714966,
+      "learning_rate": 0.0,
+      "loss": 1.016,
+      "step": 50
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "eval_loss": 1.4240585565567017,
+      "eval_runtime": 24.8043,
+      "eval_samples_per_second": 30.116,
+      "eval_steps_per_second": 3.79,
+      "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": 2,
   "trial_name": null,
   "trial_params": null