Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2041148be33294e0cd4d30c62cf415e53f85df89d7ef8e5b32e3223c7c38f35a
+oid sha256:d84049039d9bea61e91bc3a1eb22e33ec91d13f1b2a6814ee094f82c78bdceb7
 size 140815952

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0eaa697c57f5b5efb8ae6e09c459ab2ac7d4185a41fe985c29d8c03afc5ce83
+oid sha256:cd7fa10451ac86058c37b5766800e300587583894ae3fe726c50458116ac7f4e
 size 71878612

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:334d877cb53b63f40feaf798ed2d27d51fa607b0b40673b82657ea0addb7517c
+oid sha256:8a9dc045b9bc5a565e6dfde3fdb06b0d620422165417c90d17c180980214fd9c
 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": 0.37230128049850464,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.01886080724254998,
+  "best_metric": 0.34391269087791443,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03772161448509996,
   "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": 109.406,
       "eval_steps_per_second": 13.719,
       "step": 25
+    },
+    {
+      "epoch": 0.01961523953225198,
+      "grad_norm": 0.7963305115699768,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 0.3521,
+      "step": 26
+    },
+    {
+      "epoch": 0.02036967182195398,
+      "grad_norm": 0.8047768473625183,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 0.2861,
+      "step": 27
+    },
+    {
+      "epoch": 0.021124104111655977,
+      "grad_norm": 0.8749202489852905,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 0.3615,
+      "step": 28
+    },
+    {
+      "epoch": 0.02187853640135798,
+      "grad_norm": 0.9675726890563965,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 0.3973,
+      "step": 29
+    },
+    {
+      "epoch": 0.022632968691059976,
+      "grad_norm": 0.8586735129356384,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 0.2973,
+      "step": 30
+    },
+    {
+      "epoch": 0.023387400980761978,
+      "grad_norm": 0.7812412977218628,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 0.3003,
+      "step": 31
+    },
+    {
+      "epoch": 0.024141833270463976,
+      "grad_norm": 0.6331107020378113,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 0.2103,
+      "step": 32
+    },
+    {
+      "epoch": 0.024896265560165973,
+      "grad_norm": 0.9905163645744324,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 0.3044,
+      "step": 33
+    },
+    {
+      "epoch": 0.025650697849867975,
+      "grad_norm": 0.7896565198898315,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 0.327,
+      "step": 34
+    },
+    {
+      "epoch": 0.026405130139569973,
+      "grad_norm": 0.713309109210968,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2048,
+      "step": 35
+    },
+    {
+      "epoch": 0.027159562429271974,
+      "grad_norm": 0.8383902907371521,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 0.3208,
+      "step": 36
+    },
+    {
+      "epoch": 0.02791399471897397,
+      "grad_norm": 0.8634557723999023,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 0.2882,
+      "step": 37
+    },
+    {
+      "epoch": 0.028668427008675973,
+      "grad_norm": 1.0824906826019287,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 0.4171,
+      "step": 38
+    },
+    {
+      "epoch": 0.02942285929837797,
+      "grad_norm": 0.9223806262016296,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 0.3,
+      "step": 39
+    },
+    {
+      "epoch": 0.03017729158807997,
+      "grad_norm": 0.8734697103500366,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 0.3141,
+      "step": 40
+    },
+    {
+      "epoch": 0.03093172387778197,
+      "grad_norm": 0.8941064476966858,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 0.2985,
+      "step": 41
+    },
+    {
+      "epoch": 0.03168615616748397,
+      "grad_norm": 1.1077510118484497,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 0.3071,
+      "step": 42
+    },
+    {
+      "epoch": 0.03244058845718597,
+      "grad_norm": 0.9423010349273682,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 0.3249,
+      "step": 43
+    },
+    {
+      "epoch": 0.03319502074688797,
+      "grad_norm": 1.1726397275924683,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 0.3669,
+      "step": 44
+    },
+    {
+      "epoch": 0.033949453036589965,
+      "grad_norm": 1.0002593994140625,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 0.2912,
+      "step": 45
+    },
+    {
+      "epoch": 0.03470388532629196,
+      "grad_norm": 1.1142090559005737,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 0.3569,
+      "step": 46
+    },
+    {
+      "epoch": 0.03545831761599397,
+      "grad_norm": 1.3756223917007446,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 0.4046,
+      "step": 47
+    },
+    {
+      "epoch": 0.036212749905695965,
+      "grad_norm": 1.5654147863388062,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 0.4228,
+      "step": 48
+    },
+    {
+      "epoch": 0.03696718219539796,
+      "grad_norm": 1.8884528875350952,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 0.3177,
+      "step": 49
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "grad_norm": 3.2178640365600586,
+      "learning_rate": 0.0,
+      "loss": 0.59,
+      "step": 50
+    },
+    {
+      "epoch": 0.03772161448509996,
+      "eval_loss": 0.34391269087791443,
+      "eval_runtime": 20.4132,
+      "eval_samples_per_second": 109.39,
+      "eval_steps_per_second": 13.717,
+      "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": 1033684525252608.0,
+  "total_flos": 1999744829227008.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null