Training in progress, step 150, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea533a8edad2e186e6dc13f37d10ba5327defb69716ff7f37454c2c9954abe3f
+oid sha256:00d88933608eb6905d568ca7e9e85d5016a989ef2014842f3da6aaf3411552e2
 size 100966336

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb3381d078e6ecf2406b957a967c8c5d95ac8267beaa4a55a8e9c935dfd2eeff
+oid sha256:58efcef6024e2351c63d9176d72130f5574c9e6e2792d34dad1f4a33a8d1b940
 size 202110330

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9261c4c40220670a7edbad71de1a08039e483f33679a9a176dd7c228765ebefc
+oid sha256:a3aff36c16222d0061df677990f58f3f7934e0ed42dca0e491f8288649395c91
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03e9c3cb452fe294f65c78c2fab42ae3065f3d6551c282a3495643221b60a78e
+oid sha256:4824b9f06a716c63dffd9ca6415f87a30db97b053916125c867d13e365c901dd
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae3a13368de0b5e74afa25a40a37cee212e56b0c5b7a164138e75a700fd2b788
+oid sha256:14c0078cd168d28d770993976fadecd807c036306bdcbd167c303a3fa0ce1be5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d8c96a8b4c96ff6dff384e25b5c7953b2640eef5b3d7b930c5356c47c63a2e
+oid sha256:33cd93429d6fe703ae69413cc707f400665a1c9e7e51b17b9003485acc16345e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72e23a2d1e485599a7b5fae1501ffcbc43db47e90bf1e1f6de6ac821e4368041
+oid sha256:eff6fb7d68f4fba752f9a34c10ead544a122d6bff4d10f27de692e046608ac1c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.8382258415222168,
-  "best_model_checkpoint": "miner_id_24/checkpoint-125",
-  "epoch": 0.8017638805371818,
+  "best_metric": 0.8291622996330261,
+  "best_model_checkpoint": "miner_id_24/checkpoint-150",
+  "epoch": 0.9621166566446182,
   "eval_steps": 25,
-  "global_step": 125,
+  "global_step": 150,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -930,6 +930,189 @@
       "eval_samples_per_second": 49.116,
       "eval_steps_per_second": 12.77,
       "step": 125
+    },
+    {
+      "epoch": 0.8081779915814793,
+      "grad_norm": 0.31197455525398254,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 0.9636,
+      "step": 126
+    },
+    {
+      "epoch": 0.8145921026257767,
+      "grad_norm": 0.3908165693283081,
+      "learning_rate": 1.5547295993162156e-05,
+      "loss": 0.95,
+      "step": 127
+    },
+    {
+      "epoch": 0.8210062136700742,
+      "grad_norm": 0.3665495812892914,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 0.8052,
+      "step": 128
+    },
+    {
+      "epoch": 0.8274203247143717,
+      "grad_norm": 0.37569713592529297,
+      "learning_rate": 1.464072663102903e-05,
+      "loss": 0.8625,
+      "step": 129
+    },
+    {
+      "epoch": 0.8338344357586691,
+      "grad_norm": 0.40901851654052734,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 0.7515,
+      "step": 130
+    },
+    {
+      "epoch": 0.8402485468029666,
+      "grad_norm": 0.42621657252311707,
+      "learning_rate": 1.3810983439624881e-05,
+      "loss": 0.7998,
+      "step": 131
+    },
+    {
+      "epoch": 0.846662657847264,
+      "grad_norm": 0.44142094254493713,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 0.7929,
+      "step": 132
+    },
+    {
+      "epoch": 0.8530767688915615,
+      "grad_norm": 0.43068927526474,
+      "learning_rate": 1.305964588227407e-05,
+      "loss": 0.7788,
+      "step": 133
+    },
+    {
+      "epoch": 0.8594908799358589,
+      "grad_norm": 0.4872435927391052,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 0.8294,
+      "step": 134
+    },
+    {
+      "epoch": 0.8659049909801564,
+      "grad_norm": 0.4502367675304413,
+      "learning_rate": 1.2388144172720251e-05,
+      "loss": 0.7533,
+      "step": 135
+    },
+    {
+      "epoch": 0.8723191020244538,
+      "grad_norm": 0.4974122941493988,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 0.7485,
+      "step": 136
+    },
+    {
+      "epoch": 0.8787332130687513,
+      "grad_norm": 0.5290459394454956,
+      "learning_rate": 1.1797756552633215e-05,
+      "loss": 0.8153,
+      "step": 137
+    },
+    {
+      "epoch": 0.8851473241130488,
+      "grad_norm": 0.37030237913131714,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.0218,
+      "step": 138
+    },
+    {
+      "epoch": 0.8915614351573462,
+      "grad_norm": 0.34467270970344543,
+      "learning_rate": 1.1289606858403237e-05,
+      "loss": 0.9029,
+      "step": 139
+    },
+    {
+      "epoch": 0.8979755462016437,
+      "grad_norm": 0.36066851019859314,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 0.8987,
+      "step": 140
+    },
+    {
+      "epoch": 0.9043896572459411,
+      "grad_norm": 0.3829849362373352,
+      "learning_rate": 1.0864662381854632e-05,
+      "loss": 0.8635,
+      "step": 141
+    },
+    {
+      "epoch": 0.9108037682902386,
+      "grad_norm": 0.3921374976634979,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 0.842,
+      "step": 142
+    },
+    {
+      "epoch": 0.917217879334536,
+      "grad_norm": 0.41558754444122314,
+      "learning_rate": 1.0523732028950771e-05,
+      "loss": 0.7996,
+      "step": 143
+    },
+    {
+      "epoch": 0.9236319903788335,
+      "grad_norm": 0.4474291205406189,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 0.7812,
+      "step": 144
+    },
+    {
+      "epoch": 0.9300461014231309,
+      "grad_norm": 0.4382871687412262,
+      "learning_rate": 1.0267464779995617e-05,
+      "loss": 0.7382,
+      "step": 145
+    },
+    {
+      "epoch": 0.9364602124674284,
+      "grad_norm": 0.43462201952934265,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 0.7305,
+      "step": 146
+    },
+    {
+      "epoch": 0.9428743235117258,
+      "grad_norm": 0.43509241938591003,
+      "learning_rate": 1.0096348454262845e-05,
+      "loss": 0.693,
+      "step": 147
+    },
+    {
+      "epoch": 0.9492884345560233,
+      "grad_norm": 0.4872788190841675,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.8178,
+      "step": 148
+    },
+    {
+      "epoch": 0.9557025456003208,
+      "grad_norm": 0.5364053845405579,
+      "learning_rate": 1.001070878140409e-05,
+      "loss": 0.7784,
+      "step": 149
+    },
+    {
+      "epoch": 0.9621166566446182,
+      "grad_norm": 0.6880702972412109,
+      "learning_rate": 1e-05,
+      "loss": 0.8225,
+      "step": 150
+    },
+    {
+      "epoch": 0.9621166566446182,
+      "eval_loss": 0.8291622996330261,
+      "eval_runtime": 1.0213,
+      "eval_samples_per_second": 48.958,
+      "eval_steps_per_second": 12.729,
+      "step": 150
     }
   ],
   "logging_steps": 1,
@@ -953,12 +1136,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.08367120092758e+17,
+  "total_flos": 2.500379396968284e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null