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:b3369f662ea8b9cde7ba43585bb038c09fadc76cd96aad665904faf62a871aaf
+oid sha256:1fbc5b7196206be31003ff8ad819e65b2a0b492ac925cc2b66f6a290dacd5ef3
 size 125048

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c11eba46137c6b5d633519a1396ccf35cbf7cba6a9f074fe4f3b0980f304d94
+oid sha256:17d22a1a3c97e8dd34ee09ceed23de4285a3e4a35bb8f4b63658227e7f72a8f8
 size 259694

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52f96a78c4166da7c373a1d5ab990165ab522ea23dcdd4192badee9a064a2c57
+oid sha256:ae8bdf706ba5da0eff0a21cfad0c422bdc4cc48a1bac9256174c76dac50cf7dd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06570376c7695e2f0d7ea4a85faddc0d42045c7535b59bed2e07998cbface370
+oid sha256:6b065fcf2ddb061845192afa993afb1833cfb9d82dcc185372e53f7f861afaf2
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c461f8f3f90457d13df2fcce3bef1fca269877f594a0e6c96cc7b97b65db176
+oid sha256:728e9af9bb099176c29b40917c8df32783ffe30666da7e26032e95e177fee85b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1d6fca73405ab4ae6773bd77d66c3450e65cfab9fa83dd957f4a4e43ceaf9ed2
+oid sha256:e2506f3fb61ec682d848bca408a3a9ba2214315b4cb2a80d0c2b69eb12c1fe4e
 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": 11.05729866027832,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06212144742972511,
+  "best_metric": 11.050471305847168,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.12424289485945023,
   "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": 742.749,
       "eval_steps_per_second": 193.115,
       "step": 25
+    },
+    {
+      "epoch": 0.06460630532691412,
+      "grad_norm": 2.363105535507202,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 176.9951,
+      "step": 26
+    },
+    {
+      "epoch": 0.06709116322410312,
+      "grad_norm": 2.308183431625366,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 177.0155,
+      "step": 27
+    },
+    {
+      "epoch": 0.06957602112129213,
+      "grad_norm": 2.374415636062622,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 176.9725,
+      "step": 28
+    },
+    {
+      "epoch": 0.07206087901848113,
+      "grad_norm": 2.332383632659912,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 176.9675,
+      "step": 29
+    },
+    {
+      "epoch": 0.07454573691567014,
+      "grad_norm": 2.3888845443725586,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 176.9647,
+      "step": 30
+    },
+    {
+      "epoch": 0.07703059481285914,
+      "grad_norm": 2.154043674468994,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 176.9708,
+      "step": 31
+    },
+    {
+      "epoch": 0.07951545271004815,
+      "grad_norm": 2.187833309173584,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 177.0012,
+      "step": 32
+    },
+    {
+      "epoch": 0.08200031060723714,
+      "grad_norm": 2.254279136657715,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 177.0057,
+      "step": 33
+    },
+    {
+      "epoch": 0.08448516850442615,
+      "grad_norm": 2.4378998279571533,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 177.0279,
+      "step": 34
+    },
+    {
+      "epoch": 0.08697002640161516,
+      "grad_norm": 2.5491225719451904,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 177.0323,
+      "step": 35
+    },
+    {
+      "epoch": 0.08945488429880416,
+      "grad_norm": 2.9381349086761475,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 177.0188,
+      "step": 36
+    },
+    {
+      "epoch": 0.09193974219599317,
+      "grad_norm": 4.217606544494629,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 176.96,
+      "step": 37
+    },
+    {
+      "epoch": 0.09442460009318217,
+      "grad_norm": 3.7434186935424805,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 176.9411,
+      "step": 38
+    },
+    {
+      "epoch": 0.09690945799037118,
+      "grad_norm": 2.4249818325042725,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 176.918,
+      "step": 39
+    },
+    {
+      "epoch": 0.09939431588756018,
+      "grad_norm": 2.454371213912964,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 176.9138,
+      "step": 40
+    },
+    {
+      "epoch": 0.10187917378474919,
+      "grad_norm": 2.4155266284942627,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 176.8716,
+      "step": 41
+    },
+    {
+      "epoch": 0.10436403168193818,
+      "grad_norm": 2.3778913021087646,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 176.8662,
+      "step": 42
+    },
+    {
+      "epoch": 0.1068488895791272,
+      "grad_norm": 2.3316171169281006,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 176.8941,
+      "step": 43
+    },
+    {
+      "epoch": 0.1093337474763162,
+      "grad_norm": 2.3049378395080566,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 176.915,
+      "step": 44
+    },
+    {
+      "epoch": 0.1118186053735052,
+      "grad_norm": 2.311338186264038,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 176.923,
+      "step": 45
+    },
+    {
+      "epoch": 0.11430346327069421,
+      "grad_norm": 2.349407911300659,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 177.0067,
+      "step": 46
+    },
+    {
+      "epoch": 0.11678832116788321,
+      "grad_norm": 2.390659809112549,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 177.0241,
+      "step": 47
+    },
+    {
+      "epoch": 0.11927317906507222,
+      "grad_norm": 2.6497437953948975,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 176.9568,
+      "step": 48
+    },
+    {
+      "epoch": 0.12175803696226122,
+      "grad_norm": 3.6108851432800293,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 176.9483,
+      "step": 49
+    },
+    {
+      "epoch": 0.12424289485945023,
+      "grad_norm": 6.112040996551514,
+      "learning_rate": 1e-05,
+      "loss": 176.8994,
+      "step": 50
+    },
+    {
+      "epoch": 0.12424289485945023,
+      "eval_loss": 11.050471305847168,
+      "eval_runtime": 0.0674,
+      "eval_samples_per_second": 742.347,
+      "eval_steps_per_second": 193.01,
+      "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": 2101346304000.0,
+  "total_flos": 4202692608000.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null