Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0391b4ca31e5ccd66fe788336bc179c62138daed9231711ce870e5ccaa695ef7
+oid sha256:2d63b96280aa2d81b676b5af078e3abc510c8161c41af8fe68a8e48ab91577ba
 size 78207176

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8181a98e5be0cca56925ca030f66fec5c74a39c20b63badc71dc798fc46129fe
+oid sha256:b89aed508c6217af01cb5381e8b22ab75b4c8ef6300bcfa51f00140648417b94
 size 40177764

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:08dc2b0f1adbdb7ca8f772cce658a8cd971deee100923e812dfb479420a928b7
+oid sha256:386890c0e190211f6e54ca46bb1be0c55b30a7fa022651a97669d10ab4b2ce38
 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": 2.4427363872528076,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.17825311942959002,
+  "best_metric": 2.0915205478668213,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.35650623885918004,
   "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": 149.028,
       "eval_steps_per_second": 18.944,
       "step": 25
+    },
+    {
+      "epoch": 0.18538324420677363,
+      "grad_norm": 1.5658035278320312,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.5442,
+      "step": 26
+    },
+    {
+      "epoch": 0.1925133689839572,
+      "grad_norm": 1.6989140510559082,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.6993,
+      "step": 27
+    },
+    {
+      "epoch": 0.19964349376114082,
+      "grad_norm": 2.7406604290008545,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 3.7101,
+      "step": 28
+    },
+    {
+      "epoch": 0.20677361853832443,
+      "grad_norm": 2.6439878940582275,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 3.4467,
+      "step": 29
+    },
+    {
+      "epoch": 0.21390374331550802,
+      "grad_norm": 3.644503593444824,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 3.9153,
+      "step": 30
+    },
+    {
+      "epoch": 0.22103386809269163,
+      "grad_norm": 2.4745495319366455,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 3.6534,
+      "step": 31
+    },
+    {
+      "epoch": 0.2281639928698752,
+      "grad_norm": 4.7882866859436035,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 3.7345,
+      "step": 32
+    },
+    {
+      "epoch": 0.23529411764705882,
+      "grad_norm": 2.7473108768463135,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 3.8752,
+      "step": 33
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 3.205869674682617,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.8759,
+      "step": 34
+    },
+    {
+      "epoch": 0.24955436720142601,
+      "grad_norm": 3.5639467239379883,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.4342,
+      "step": 35
+    },
+    {
+      "epoch": 0.25668449197860965,
+      "grad_norm": 2.509160041809082,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 1.9873,
+      "step": 36
+    },
+    {
+      "epoch": 0.2638146167557932,
+      "grad_norm": 2.184943914413452,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.9518,
+      "step": 37
+    },
+    {
+      "epoch": 0.2709447415329768,
+      "grad_norm": 1.8048384189605713,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.8759,
+      "step": 38
+    },
+    {
+      "epoch": 0.27807486631016043,
+      "grad_norm": 2.1149380207061768,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8156,
+      "step": 39
+    },
+    {
+      "epoch": 0.28520499108734404,
+      "grad_norm": 1.9589015245437622,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.7161,
+      "step": 40
+    },
+    {
+      "epoch": 0.29233511586452765,
+      "grad_norm": 2.062096357345581,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.4362,
+      "step": 41
+    },
+    {
+      "epoch": 0.2994652406417112,
+      "grad_norm": 2.128787040710449,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7625,
+      "step": 42
+    },
+    {
+      "epoch": 0.3065953654188948,
+      "grad_norm": 2.045071840286255,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.68,
+      "step": 43
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 1.7764232158660889,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.8457,
+      "step": 44
+    },
+    {
+      "epoch": 0.32085561497326204,
+      "grad_norm": 1.7600865364074707,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.8762,
+      "step": 45
+    },
+    {
+      "epoch": 0.32798573975044565,
+      "grad_norm": 1.417314887046814,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 1.478,
+      "step": 46
+    },
+    {
+      "epoch": 0.33511586452762926,
+      "grad_norm": 2.077120065689087,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0639,
+      "step": 47
+    },
+    {
+      "epoch": 0.3422459893048128,
+      "grad_norm": 1.3124065399169922,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 1.8697,
+      "step": 48
+    },
+    {
+      "epoch": 0.3493761140819964,
+      "grad_norm": 1.1877974271774292,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 1.7146,
+      "step": 49
+    },
+    {
+      "epoch": 0.35650623885918004,
+      "grad_norm": 1.3717702627182007,
+      "learning_rate": 0.0,
+      "loss": 1.8756,
+      "step": 50
+    },
+    {
+      "epoch": 0.35650623885918004,
+      "eval_loss": 2.0915205478668213,
+      "eval_runtime": 1.5783,
+      "eval_samples_per_second": 149.529,
+      "eval_steps_per_second": 19.008,
+      "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": 309022005657600.0,
+  "total_flos": 618044011315200.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null