Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0d5ff21a618356abb060301bcbbce6fbd78622031888fd76603738b13513beee
+oid sha256:6ee1cd5fb163518bc5bf041636e287b0b5edac46272b8473408c6263b6e2535e
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:17fc0ba6b4fd81fe21eb6a67c0af343e1b870998333ae77d9d84e273c0489f57
+oid sha256:51a1e7257585eda453d51ce550e63e1c45166689f9ac772944c51e69d0d77873
 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": 1.699485421180725,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.003440919413667332,
+  "best_metric": 1.6785205602645874,
+  "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": 114.508,
       "eval_steps_per_second": 14.317,
       "step": 25
+    },
+    {
+      "epoch": 0.003578556190214025,
+      "grad_norm": 1.8210140466690063,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 1.5769,
+      "step": 26
+    },
+    {
+      "epoch": 0.0037161929667607185,
+      "grad_norm": 1.803637981414795,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 1.4474,
+      "step": 27
+    },
+    {
+      "epoch": 0.0038538297433074117,
+      "grad_norm": 1.8251798152923584,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 1.5875,
+      "step": 28
+    },
+    {
+      "epoch": 0.003991466519854105,
+      "grad_norm": 1.932847499847412,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 1.5869,
+      "step": 29
+    },
+    {
+      "epoch": 0.004129103296400798,
+      "grad_norm": 2.0150198936462402,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 1.8076,
+      "step": 30
+    },
+    {
+      "epoch": 0.0042667400729474916,
+      "grad_norm": 2.0604617595672607,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 1.7204,
+      "step": 31
+    },
+    {
+      "epoch": 0.004404376849494185,
+      "grad_norm": 1.9407871961593628,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 1.7125,
+      "step": 32
+    },
+    {
+      "epoch": 0.004542013626040878,
+      "grad_norm": 2.1350440979003906,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 1.7457,
+      "step": 33
+    },
+    {
+      "epoch": 0.004679650402587571,
+      "grad_norm": 1.9392979145050049,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 1.6631,
+      "step": 34
+    },
+    {
+      "epoch": 0.004817287179134265,
+      "grad_norm": 1.967930555343628,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.6614,
+      "step": 35
+    },
+    {
+      "epoch": 0.004954923955680958,
+      "grad_norm": 2.1190671920776367,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.6438,
+      "step": 36
+    },
+    {
+      "epoch": 0.005092560732227651,
+      "grad_norm": 2.027472496032715,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.8127,
+      "step": 37
+    },
+    {
+      "epoch": 0.0052301975087743445,
+      "grad_norm": 1.9992049932479858,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.6343,
+      "step": 38
+    },
+    {
+      "epoch": 0.005367834285321038,
+      "grad_norm": 2.1239211559295654,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8371,
+      "step": 39
+    },
+    {
+      "epoch": 0.005505471061867731,
+      "grad_norm": 2.310203790664673,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.8977,
+      "step": 40
+    },
+    {
+      "epoch": 0.005643107838414424,
+      "grad_norm": 2.299560070037842,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.6689,
+      "step": 41
+    },
+    {
+      "epoch": 0.005780744614961118,
+      "grad_norm": 2.2246201038360596,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7129,
+      "step": 42
+    },
+    {
+      "epoch": 0.005918381391507811,
+      "grad_norm": 2.226691484451294,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7453,
+      "step": 43
+    },
+    {
+      "epoch": 0.006056018168054504,
+      "grad_norm": 2.3118553161621094,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.9296,
+      "step": 44
+    },
+    {
+      "epoch": 0.0061936549446011974,
+      "grad_norm": 2.4144370555877686,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8286,
+      "step": 45
+    },
+    {
+      "epoch": 0.006331291721147891,
+      "grad_norm": 2.6773507595062256,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0211,
+      "step": 46
+    },
+    {
+      "epoch": 0.006468928497694584,
+      "grad_norm": 3.043905019760132,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0154,
+      "step": 47
+    },
+    {
+      "epoch": 0.006606565274241277,
+      "grad_norm": 3.406757116317749,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2506,
+      "step": 48
+    },
+    {
+      "epoch": 0.0067442020507879705,
+      "grad_norm": 3.9268417358398438,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.3643,
+      "step": 49
+    },
+    {
+      "epoch": 0.006881838827334664,
+      "grad_norm": 7.131216526031494,
+      "learning_rate": 0.0,
+      "loss": 3.1503,
+      "step": 50
+    },
+    {
+      "epoch": 0.006881838827334664,
+      "eval_loss": 1.6785205602645874,
+      "eval_runtime": 106.9957,
+      "eval_samples_per_second": 114.369,
+      "eval_steps_per_second": 14.3,
+      "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