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:cd6dea59c6cabdc52eb2d3ce31ea3334fada60c2409a7f49a0cbdb618707a9bc
+oid sha256:2a888403dc43350b096279f8f3bf67da10ded3a4c991577ff59fd42dfc7f5c1f
 size 435773944

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a71cc800d0a75604f981c829c289cc6284c2dd47fd14c23961f7c610b8c976e
+oid sha256:92f005c9c14836e7f3073b81e42102b8e0dfc7dafaa60cebbc614cc25c1f5b75
 size 871934770

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cdea1e1ee1ddd7728039798e1585945c06e56f8be2bc6555d12c5720c2e70d2
+oid sha256:258804e72e7a596f66525b722cb94c0764729c1c1ac404ffdeb3d1729c239b7a
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df9d6c3a21c86f30a200a49f3f872d2dac70f2fd2ed5fe762ba410cac08dcda4
+oid sha256:66f0669ffb55efc04a732b0cbae1d92bb2be3d93f9122a0492b1f9b8a03da0f7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06babb6221e24dcd9ca8dc45ffb0f4c4a85073befabc229f226b8e2ee773a432
+oid sha256:7c1edb94aeb9e43a9bbbcc066c5a36d0d3eae5182f8ccc071c4a1a5cd8b5ecde
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22572491986c6fe32c9be90648a518d055a51cfe7c3448feb6aca13a19ac607
+oid sha256:e47016cc230544d626be7bc36827384ea20eeb36f655d530328350244ecfce79
 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": 4.228944778442383,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.4184397163120568,
+  "best_metric": 3.743145704269409,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.8368794326241136,
   "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": 11.459,
       "eval_steps_per_second": 2.979,
       "step": 25
+    },
+    {
+      "epoch": 1.475177304964539,
+      "grad_norm": 7.520847320556641,
+      "learning_rate": 5.500000000000001e-05,
+      "loss": 3.2305,
+      "step": 26
+    },
+    {
+      "epoch": 1.5319148936170213,
+      "grad_norm": 6.371490001678467,
+      "learning_rate": 5.205685918464356e-05,
+      "loss": 2.9182,
+      "step": 27
+    },
+    {
+      "epoch": 1.5886524822695036,
+      "grad_norm": 3.166982412338257,
+      "learning_rate": 4.912632135009769e-05,
+      "loss": 2.331,
+      "step": 28
+    },
+    {
+      "epoch": 1.645390070921986,
+      "grad_norm": 4.1069016456604,
+      "learning_rate": 4.6220935509274235e-05,
+      "loss": 2.9918,
+      "step": 29
+    },
+    {
+      "epoch": 1.702127659574468,
+      "grad_norm": 5.494497299194336,
+      "learning_rate": 4.3353142970386564e-05,
+      "loss": 3.0673,
+      "step": 30
+    },
+    {
+      "epoch": 1.7588652482269502,
+      "grad_norm": 9.687826156616211,
+      "learning_rate": 4.053522406135775e-05,
+      "loss": 2.9902,
+      "step": 31
+    },
+    {
+      "epoch": 1.8156028368794326,
+      "grad_norm": 3.650472402572632,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 2.2526,
+      "step": 32
+    },
+    {
+      "epoch": 1.872340425531915,
+      "grad_norm": 4.139589309692383,
+      "learning_rate": 3.509700894014496e-05,
+      "loss": 2.7633,
+      "step": 33
+    },
+    {
+      "epoch": 1.9290780141843973,
+      "grad_norm": 7.082653045654297,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 3.8162,
+      "step": 34
+    },
+    {
+      "epoch": 1.9858156028368794,
+      "grad_norm": 21.436193466186523,
+      "learning_rate": 2.9999339514117912e-05,
+      "loss": 5.175,
+      "step": 35
+    },
+    {
+      "epoch": 2.0425531914893615,
+      "grad_norm": 3.4575095176696777,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 2.1421,
+      "step": 36
+    },
+    {
+      "epoch": 2.099290780141844,
+      "grad_norm": 3.1642634868621826,
+      "learning_rate": 2.53294383204969e-05,
+      "loss": 1.9559,
+      "step": 37
+    },
+    {
+      "epoch": 2.1560283687943262,
+      "grad_norm": 3.7310965061187744,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 2.442,
+      "step": 38
+    },
+    {
+      "epoch": 2.2127659574468086,
+      "grad_norm": 6.142940998077393,
+      "learning_rate": 2.1167208663446025e-05,
+      "loss": 3.7213,
+      "step": 39
+    },
+    {
+      "epoch": 2.269503546099291,
+      "grad_norm": 9.058276176452637,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 2.5916,
+      "step": 40
+    },
+    {
+      "epoch": 2.326241134751773,
+      "grad_norm": 2.9689388275146484,
+      "learning_rate": 1.758386744638546e-05,
+      "loss": 1.9181,
+      "step": 41
+    },
+    {
+      "epoch": 2.382978723404255,
+      "grad_norm": 3.1938860416412354,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 2.3449,
+      "step": 42
+    },
+    {
+      "epoch": 2.4397163120567376,
+      "grad_norm": 5.2489752769470215,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 3.3714,
+      "step": 43
+    },
+    {
+      "epoch": 2.49645390070922,
+      "grad_norm": 10.633807182312012,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 2.5432,
+      "step": 44
+    },
+    {
+      "epoch": 2.5531914893617023,
+      "grad_norm": 3.7500996589660645,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 2.0958,
+      "step": 45
+    },
+    {
+      "epoch": 2.6099290780141846,
+      "grad_norm": 3.7776594161987305,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 2.2518,
+      "step": 46
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 4.717670440673828,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 2.848,
+      "step": 47
+    },
+    {
+      "epoch": 2.723404255319149,
+      "grad_norm": 15.359528541564941,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 2.6212,
+      "step": 48
+    },
+    {
+      "epoch": 2.780141843971631,
+      "grad_norm": 4.678123950958252,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 2.3551,
+      "step": 49
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "grad_norm": 3.875638723373413,
+      "learning_rate": 1e-05,
+      "loss": 2.1527,
+      "step": 50
+    },
+    {
+      "epoch": 2.8368794326241136,
+      "eval_loss": 3.743145704269409,
+      "eval_runtime": 4.3478,
+      "eval_samples_per_second": 11.5,
+      "eval_steps_per_second": 2.99,
+      "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": 3.411614392909824e+17,
+  "total_flos": 6.823228785819648e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null