Training in progress, step 80, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8b7abe2f22382f3999a654747949c5f04cd7b50f2076f7d08dc4cde28c3ff8c3
+oid sha256:1c1c9190f08199ff0609b272bf4812d872ecf6af7ddaae2ad14d54a949f937f8
 size 45118424

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86a525396334785dec46ba6a050a54b56d171785887e5e54d90bce2652d22331
+oid sha256:b3ab265eb30355919991822e0cc6c38dc53b6b2d245118f01060a4abbff6110b
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31543a07fbd48036322e55fc875b941e5f56b48a74d8818ee4618f3aa994756b
+oid sha256:9d863956ee027610692953e2f8b517eb62237dedd2129c265b5b8401104a9871
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:50b80d146b8b37f82a1962ba385b8329fd6c2c35ba5116c53e131bb661ab681b
+oid sha256:ed29baad6d6611c736eccf18bdd7afdc5d6f3612cde61e7bfa83472d3e2068d2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7785296440124512,
-  "best_model_checkpoint": "miner_id_besimray/checkpoint-60",
-  "epoch": 0.7717041800643086,
+  "best_metric": 0.7697538137435913,
+  "best_model_checkpoint": "miner_id_besimray/checkpoint-80",
+  "epoch": 1.0289389067524115,
   "eval_steps": 20,
-  "global_step": 60,
+  "global_step": 80,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -459,6 +459,154 @@
       "eval_samples_per_second": 23.185,
       "eval_steps_per_second": 2.403,
       "step": 60
+    },
+    {
+      "epoch": 0.7845659163987139,
+      "grad_norm": 0.23432762920856476,
+      "learning_rate": 0.00014135585049665207,
+      "loss": 0.8121,
+      "step": 61
+    },
+    {
+      "epoch": 0.797427652733119,
+      "grad_norm": 0.22978775203227997,
+      "learning_rate": 0.00013930250316539238,
+      "loss": 0.8141,
+      "step": 62
+    },
+    {
+      "epoch": 0.8102893890675241,
+      "grad_norm": 0.22213302552700043,
+      "learning_rate": 0.00013722936584019453,
+      "loss": 0.7882,
+      "step": 63
+    },
+    {
+      "epoch": 0.8231511254019293,
+      "grad_norm": 0.22720932960510254,
+      "learning_rate": 0.0001351374824081343,
+      "loss": 0.7198,
+      "step": 64
+    },
+    {
+      "epoch": 0.8360128617363344,
+      "grad_norm": 0.2271229773759842,
+      "learning_rate": 0.00013302790619551674,
+      "loss": 0.7625,
+      "step": 65
+    },
+    {
+      "epoch": 0.8488745980707395,
+      "grad_norm": 0.2052968144416809,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.7236,
+      "step": 66
+    },
+    {
+      "epoch": 0.8617363344051447,
+      "grad_norm": 0.23866061866283417,
+      "learning_rate": 0.00012875993274320173,
+      "loss": 0.7611,
+      "step": 67
+    },
+    {
+      "epoch": 0.8745980707395499,
+      "grad_norm": 0.2304213047027588,
+      "learning_rate": 0.00012660368455666752,
+      "loss": 0.7257,
+      "step": 68
+    },
+    {
+      "epoch": 0.887459807073955,
+      "grad_norm": 0.2596646249294281,
+      "learning_rate": 0.0001244340406137894,
+      "loss": 0.8118,
+      "step": 69
+    },
+    {
+      "epoch": 0.9003215434083601,
+      "grad_norm": 0.2256776988506317,
+      "learning_rate": 0.00012225209339563145,
+      "loss": 0.8183,
+      "step": 70
+    },
+    {
+      "epoch": 0.9131832797427653,
+      "grad_norm": 0.24038884043693542,
+      "learning_rate": 0.00012005894157832729,
+      "loss": 0.8463,
+      "step": 71
+    },
+    {
+      "epoch": 0.9260450160771704,
+      "grad_norm": 0.2232024073600769,
+      "learning_rate": 0.00011785568947986367,
+      "loss": 0.7718,
+      "step": 72
+    },
+    {
+      "epoch": 0.9389067524115756,
+      "grad_norm": 0.23251061141490936,
+      "learning_rate": 0.0001156434465040231,
+      "loss": 0.801,
+      "step": 73
+    },
+    {
+      "epoch": 0.9517684887459807,
+      "grad_norm": 0.2278710901737213,
+      "learning_rate": 0.00011342332658176555,
+      "loss": 0.696,
+      "step": 74
+    },
+    {
+      "epoch": 0.9646302250803859,
+      "grad_norm": 0.1985187828540802,
+      "learning_rate": 0.00011119644761033078,
+      "loss": 0.7299,
+      "step": 75
+    },
+    {
+      "epoch": 0.977491961414791,
+      "grad_norm": 0.24016259610652924,
+      "learning_rate": 0.00010896393089034336,
+      "loss": 0.8603,
+      "step": 76
+    },
+    {
+      "epoch": 0.9903536977491961,
+      "grad_norm": 0.2583943009376526,
+      "learning_rate": 0.00010672690056120399,
+      "loss": 0.7946,
+      "step": 77
+    },
+    {
+      "epoch": 1.0032154340836013,
+      "grad_norm": 0.37707868218421936,
+      "learning_rate": 0.00010448648303505151,
+      "loss": 0.6729,
+      "step": 78
+    },
+    {
+      "epoch": 1.0160771704180065,
+      "grad_norm": 0.20697161555290222,
+      "learning_rate": 0.00010224380642958052,
+      "loss": 0.6831,
+      "step": 79
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "grad_norm": 0.24280855059623718,
+      "learning_rate": 0.0001,
+      "loss": 0.8127,
+      "step": 80
+    },
+    {
+      "epoch": 1.0289389067524115,
+      "eval_loss": 0.7697538137435913,
+      "eval_runtime": 6.764,
+      "eval_samples_per_second": 24.246,
+      "eval_steps_per_second": 2.513,
+      "step": 80
     }
   ],
   "logging_steps": 1,
@@ -487,7 +635,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.446291621543936e+16,
+  "total_flos": 1.911441083203584e+16,
   "train_batch_size": 10,
   "trial_name": null,
   "trial_params": null