Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a4f5035ac237e59a8363aa43117a6a7547b77f0791255c6c286e8f3165c6f3
+oid sha256:6366997465e8ea89c68cdaf61ce4cc26c9871954fad8749fa7dec6113ae4f1ce
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:adbb6044de9612956d66b4f2975f79a215c59aebcd8228e3ca075b8baadb6177
+oid sha256:47b3e2c8a749dabb59fe8419d936cfe13c34e501eeae78d0b310edb6c8781550
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9af7e277fe0103e10d6cf1e1ebfff00ba2b616f2c041a959aea1b699ea34f672
+oid sha256:a5bd54eee130c17cd2a8fff7c374419f95111469057f1131bdf469dc930b821f
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.70032799243927,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003440919413667332,
+  "best_metric": 1.6801203489303589,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.006881838827334664,
   "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": 114.547,
       "eval_steps_per_second": 14.322,
       "step": 25
+    },
+    {
+      "epoch": 0.003578556190214025,
+      "grad_norm": 1.8355437517166138,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.579,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037161929667607185,
+      "grad_norm": 1.7906683683395386,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.4476,
+      "step": 27
+    },
+    {
+      "epoch": 0.0038538297433074117,
+      "grad_norm": 1.82988703250885,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.5864,
+      "step": 28
+    },
+    {
+      "epoch": 0.003991466519854105,
+      "grad_norm": 1.955890417098999,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.5891,
+      "step": 29
+    },
+    {
+      "epoch": 0.004129103296400798,
+      "grad_norm": 2.021894931793213,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.8077,
+      "step": 30
+    },
+    {
+      "epoch": 0.0042667400729474916,
+      "grad_norm": 2.075988531112671,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7214,
+      "step": 31
+    },
+    {
+      "epoch": 0.004404376849494185,
+      "grad_norm": 1.942689061164856,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7103,
+      "step": 32
+    },
+    {
+      "epoch": 0.004542013626040878,
+      "grad_norm": 2.155029058456421,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.7459,
+      "step": 33
+    },
+    {
+      "epoch": 0.004679650402587571,
+      "grad_norm": 1.9637714624404907,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6637,
+      "step": 34
+    },
+    {
+      "epoch": 0.004817287179134265,
+      "grad_norm": 1.9927000999450684,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6629,
+      "step": 35
+    },
+    {
+      "epoch": 0.004954923955680958,
+      "grad_norm": 2.146827459335327,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.6425,
+      "step": 36
+    },
+    {
+      "epoch": 0.005092560732227651,
+      "grad_norm": 2.037449836730957,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.8133,
+      "step": 37
+    },
+    {
+      "epoch": 0.0052301975087743445,
+      "grad_norm": 2.0150561332702637,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.636,
+      "step": 38
+    },
+    {
+      "epoch": 0.005367834285321038,
+      "grad_norm": 2.134779691696167,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8358,
+      "step": 39
+    },
+    {
+      "epoch": 0.005505471061867731,
+      "grad_norm": 2.3213002681732178,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8923,
+      "step": 40
+    },
+    {
+      "epoch": 0.005643107838414424,
+      "grad_norm": 2.3136813640594482,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6691,
+      "step": 41
+    },
+    {
+      "epoch": 0.005780744614961118,
+      "grad_norm": 2.2391891479492188,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7149,
+      "step": 42
+    },
+    {
+      "epoch": 0.005918381391507811,
+      "grad_norm": 2.2326366901397705,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7424,
+      "step": 43
+    },
+    {
+      "epoch": 0.006056018168054504,
+      "grad_norm": 2.3350918292999268,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9315,
+      "step": 44
+    },
+    {
+      "epoch": 0.0061936549446011974,
+      "grad_norm": 2.414999485015869,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8257,
+      "step": 45
+    },
+    {
+      "epoch": 0.006331291721147891,
+      "grad_norm": 2.6851768493652344,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0204,
+      "step": 46
+    },
+    {
+      "epoch": 0.006468928497694584,
+      "grad_norm": 3.064577579498291,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0167,
+      "step": 47
+    },
+    {
+      "epoch": 0.006606565274241277,
+      "grad_norm": 3.4269301891326904,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2436,
+      "step": 48
+    },
+    {
+      "epoch": 0.0067442020507879705,
+      "grad_norm": 3.9567739963531494,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.3654,
+      "step": 49
+    },
+    {
+      "epoch": 0.006881838827334664,
+      "grad_norm": 7.154803276062012,
+      "learning_rate": 0.0,
+      "loss": 3.1455,
+      "step": 50
+    },
+    {
+      "epoch": 0.006881838827334664,
+      "eval_loss": 1.6801203489303589,
+      "eval_runtime": 106.7627,
+      "eval_samples_per_second": 114.619,
+      "eval_steps_per_second": 14.331,
+      "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": 975720907014144.0,
+  "total_flos": 1941781210988544.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null