Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:270be49c45c05d0c92a29f3d8201cc2b1f3c44dd0be402732afb2f73cd333d4d
+oid sha256:56dc5ec53a835b67ee63f07145017576ad617e6cf7865aa14bdf4b2c85a18169
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e894e8b79f90429d9bbfa4fe2cca965293f336c73d6183179d940646b09e6d90
+oid sha256:0fd9f08f1addfeb80ecfa836d0e192f65c3bd02faa61006543281c488c70bd51
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:21d5e699df91824d2cc21cd6fca6ae5534fe06dfbe2e002eb2ee89373822274c
+oid sha256:8a47d81feac90379fa90bc7badbfc0a8b6242a876e1b6c9392c16e813811c019
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d5cc00b4ba6ce7df9fd5cdc856eb7aa4309bdf5e3da1c08ab5730bbed675f827
+oid sha256:d75464829baeaca9bf7f38f17a234bf7d54fc5c63f679b86e4676250d2270a38
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa67446d02bb158f746de30b32d55732057e4a1a25c7d3234058b2196103e39f
+oid sha256:25708a205aa44c195b2e306f559223c9cd9720b10a579b9fb98d9c97e2e81fa8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:edffadb8afd1ffc6f8c00939b54bdf18aa525da99bdd2d00e0bc6544b9df129e
+oid sha256:8e54654ce899520db9a2531e25d8931be923e7205199f957ee1fcc5b2a7e546c
 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": 2.2345645427703857,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7155635062611807,
+  "best_metric": 2.0475499629974365,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.4373881932021466,
   "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": 23.014,
       "eval_steps_per_second": 5.984,
       "step": 25
+    },
+    {
+      "epoch": 0.7441860465116279,
+      "grad_norm": 2.2192697525024414,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 1.9938,
+      "step": 26
+    },
+    {
+      "epoch": 0.7728085867620751,
+      "grad_norm": 2.8937413692474365,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.2059,
+      "step": 27
+    },
+    {
+      "epoch": 0.8014311270125224,
+      "grad_norm": 2.5368123054504395,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.0859,
+      "step": 28
+    },
+    {
+      "epoch": 0.8300536672629696,
+      "grad_norm": 1.9519373178482056,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.0092,
+      "step": 29
+    },
+    {
+      "epoch": 0.8586762075134168,
+      "grad_norm": 1.957302212715149,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 1.954,
+      "step": 30
+    },
+    {
+      "epoch": 0.8872987477638641,
+      "grad_norm": 3.078779697418213,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 1.9646,
+      "step": 31
+    },
+    {
+      "epoch": 0.9159212880143113,
+      "grad_norm": 2.7473530769348145,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 1.9372,
+      "step": 32
+    },
+    {
+      "epoch": 0.9445438282647585,
+      "grad_norm": 2.635892152786255,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.2733,
+      "step": 33
+    },
+    {
+      "epoch": 0.9731663685152058,
+      "grad_norm": 2.5369815826416016,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 2.3486,
+      "step": 34
+    },
+    {
+      "epoch": 1.0080500894454383,
+      "grad_norm": 2.8737504482269287,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 2.4615,
+      "step": 35
+    },
+    {
+      "epoch": 1.0366726296958855,
+      "grad_norm": 1.9721633195877075,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.9552,
+      "step": 36
+    },
+    {
+      "epoch": 1.0652951699463327,
+      "grad_norm": 1.634428858757019,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.8953,
+      "step": 37
+    },
+    {
+      "epoch": 1.0939177101967799,
+      "grad_norm": 1.4716153144836426,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.9606,
+      "step": 38
+    },
+    {
+      "epoch": 1.1225402504472273,
+      "grad_norm": 1.6855412721633911,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 1.8368,
+      "step": 39
+    },
+    {
+      "epoch": 1.1511627906976745,
+      "grad_norm": 2.3863978385925293,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.8061,
+      "step": 40
+    },
+    {
+      "epoch": 1.1797853309481217,
+      "grad_norm": 2.4788835048675537,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.805,
+      "step": 41
+    },
+    {
+      "epoch": 1.2084078711985689,
+      "grad_norm": 1.9841209650039673,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.1931,
+      "step": 42
+    },
+    {
+      "epoch": 1.237030411449016,
+      "grad_norm": 1.788836121559143,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 2.2587,
+      "step": 43
+    },
+    {
+      "epoch": 1.2656529516994635,
+      "grad_norm": 2.320674180984497,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.9501,
+      "step": 44
+    },
+    {
+      "epoch": 1.2942754919499104,
+      "grad_norm": 2.0197575092315674,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 1.8906,
+      "step": 45
+    },
+    {
+      "epoch": 1.3228980322003578,
+      "grad_norm": 2.010979175567627,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.8234,
+      "step": 46
+    },
+    {
+      "epoch": 1.351520572450805,
+      "grad_norm": 1.6593760251998901,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 1.8833,
+      "step": 47
+    },
+    {
+      "epoch": 1.3801431127012522,
+      "grad_norm": 1.9684267044067383,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.6469,
+      "step": 48
+    },
+    {
+      "epoch": 1.4087656529516994,
+      "grad_norm": 2.6509218215942383,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 1.6708,
+      "step": 49
+    },
+    {
+      "epoch": 1.4373881932021466,
+      "grad_norm": 2.042696952819824,
+      "learning_rate": 1e-05,
+      "loss": 1.7957,
+      "step": 50
+    },
+    {
+      "epoch": 1.4373881932021466,
+      "eval_loss": 2.0475499629974365,
+      "eval_runtime": 2.0907,
+      "eval_samples_per_second": 23.916,
+      "eval_steps_per_second": 6.218,
+      "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": 2.4703766989111296e+16,
+  "total_flos": 5.002120628745011e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null