Training in progress, step 100, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab20c364e42310ed437faf8460c3206ecba82fce9b1aeb3364f58c170d4c2049
+oid sha256:824c8f0a712e9b94ca78c3b8b93a4b432f686d358a24c2f9734d9dea27416b80
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8c372ddb5011b8a7d2405d81cc5d7e44d59303ae53d8f7f052c10cd44f30f56a
+oid sha256:c5d658f08afa308bf4bdcf48725ea083ff2b4b408de3db51d17ca92db3cb380f
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a12635441debf73fea86223e7939f3057cc0ac942a12eb1b3c97fb835087ec1
+oid sha256:66bac0f112277a7420ffe12b93ec7ccfa1371db0442fb7970007d50eac079697
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a8d5f446d81df8b8e6d5d3423a874831fec3d08bffbe4980db71b54ceb3e7bd4
+oid sha256:49d60a69e2379be2053e816cbaff31e6c931b5922dd86c71c9eaf473299cbf62
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.0642553567886353,
-  "best_model_checkpoint": "miner_id_24/checkpoint-75",
-  "epoch": 0.05799342741156002,
+  "best_metric": 1.06106698513031,
+  "best_model_checkpoint": "miner_id_24/checkpoint-100",
+  "epoch": 0.07732456988208003,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -564,6 +564,189 @@
       "eval_samples_per_second": 1.548,
       "eval_steps_per_second": 0.775,
       "step": 75
+    },
+    {
+      "epoch": 0.05876667311038082,
+      "grad_norm": 7.514301776885986,
+      "learning_rate": 1.4938160786375572e-05,
+      "loss": 3.9285,
+      "step": 76
+    },
+    {
+      "epoch": 0.05953991880920163,
+      "grad_norm": 11.112171173095703,
+      "learning_rate": 1.3778739760445552e-05,
+      "loss": 4.9558,
+      "step": 77
+    },
+    {
+      "epoch": 0.060313164508022425,
+      "grad_norm": 7.495338439941406,
+      "learning_rate": 1.2658926150792322e-05,
+      "loss": 3.9271,
+      "step": 78
+    },
+    {
+      "epoch": 0.061086410206843224,
+      "grad_norm": 9.140981674194336,
+      "learning_rate": 1.157994445715706e-05,
+      "loss": 3.571,
+      "step": 79
+    },
+    {
+      "epoch": 0.06185965590566402,
+      "grad_norm": 9.3052978515625,
+      "learning_rate": 1.0542974530180327e-05,
+      "loss": 4.5799,
+      "step": 80
+    },
+    {
+      "epoch": 0.06263290160448483,
+      "grad_norm": 8.143803596496582,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 3.5652,
+      "step": 81
+    },
+    {
+      "epoch": 0.06340614730330563,
+      "grad_norm": 10.234214782714844,
+      "learning_rate": 8.599558442598998e-06,
+      "loss": 4.2623,
+      "step": 82
+    },
+    {
+      "epoch": 0.06417939300212643,
+      "grad_norm": 8.836921691894531,
+      "learning_rate": 7.695237378953223e-06,
+      "loss": 3.5661,
+      "step": 83
+    },
+    {
+      "epoch": 0.06495263870094722,
+      "grad_norm": 10.0997953414917,
+      "learning_rate": 6.837175952121306e-06,
+      "loss": 4.2513,
+      "step": 84
+    },
+    {
+      "epoch": 0.06572588439976802,
+      "grad_norm": 9.577383995056152,
+      "learning_rate": 6.026312439675552e-06,
+      "loss": 4.6833,
+      "step": 85
+    },
+    {
+      "epoch": 0.06649913009858882,
+      "grad_norm": 10.211189270019531,
+      "learning_rate": 5.263533508961827e-06,
+      "loss": 4.5139,
+      "step": 86
+    },
+    {
+      "epoch": 0.06727237579740963,
+      "grad_norm": 9.4320068359375,
+      "learning_rate": 4.549673247541875e-06,
+      "loss": 4.1881,
+      "step": 87
+    },
+    {
+      "epoch": 0.06804562149623043,
+      "grad_norm": 9.295085906982422,
+      "learning_rate": 3.885512251130763e-06,
+      "loss": 4.5596,
+      "step": 88
+    },
+    {
+      "epoch": 0.06881886719505123,
+      "grad_norm": 7.192505836486816,
+      "learning_rate": 3.271776770026963e-06,
+      "loss": 3.1656,
+      "step": 89
+    },
+    {
+      "epoch": 0.06959211289387203,
+      "grad_norm": 8.369428634643555,
+      "learning_rate": 2.7091379149682685e-06,
+      "loss": 4.5796,
+      "step": 90
+    },
+    {
+      "epoch": 0.07036535859269283,
+      "grad_norm": 7.142214298248291,
+      "learning_rate": 2.1982109232821178e-06,
+      "loss": 3.4252,
+      "step": 91
+    },
+    {
+      "epoch": 0.07113860429151363,
+      "grad_norm": 9.0031099319458,
+      "learning_rate": 1.7395544861325718e-06,
+      "loss": 4.4111,
+      "step": 92
+    },
+    {
+      "epoch": 0.07191184999033443,
+      "grad_norm": 8.895259857177734,
+      "learning_rate": 1.333670137599713e-06,
+      "loss": 3.6634,
+      "step": 93
+    },
+    {
+      "epoch": 0.07268509568915522,
+      "grad_norm": 8.90333080291748,
+      "learning_rate": 9.810017062595322e-07,
+      "loss": 4.1098,
+      "step": 94
+    },
+    {
+      "epoch": 0.07345834138797602,
+      "grad_norm": 10.424738883972168,
+      "learning_rate": 6.819348298638839e-07,
+      "loss": 4.9226,
+      "step": 95
+    },
+    {
+      "epoch": 0.07423158708679684,
+      "grad_norm": 10.640342712402344,
+      "learning_rate": 4.367965336512403e-07,
+      "loss": 4.4209,
+      "step": 96
+    },
+    {
+      "epoch": 0.07500483278561763,
+      "grad_norm": 11.282198905944824,
+      "learning_rate": 2.458548727494292e-07,
+      "loss": 4.0654,
+      "step": 97
+    },
+    {
+      "epoch": 0.07577807848443843,
+      "grad_norm": 9.29175853729248,
+      "learning_rate": 1.0931863906127327e-07,
+      "loss": 4.4543,
+      "step": 98
+    },
+    {
+      "epoch": 0.07655132418325923,
+      "grad_norm": 9.734441757202148,
+      "learning_rate": 2.7337132953697554e-08,
+      "loss": 3.6864,
+      "step": 99
+    },
+    {
+      "epoch": 0.07732456988208003,
+      "grad_norm": 9.622171401977539,
+      "learning_rate": 0.0,
+      "loss": 3.4783,
+      "step": 100
+    },
+    {
+      "epoch": 0.07732456988208003,
+      "eval_loss": 1.06106698513031,
+      "eval_runtime": 351.8934,
+      "eval_samples_per_second": 1.549,
+      "eval_steps_per_second": 0.776,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -587,12 +770,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.054694248022016e+17,
+  "total_flos": 1.406258997362688e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null