Training in progress, step 42, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5cf0f4719e09d41585e0ca4b9e873db4a886f77f1a58eaf1ab6796d1bbd34555
+oid sha256:dc902b1435ecbed19fb941165ea7403dfadb658a12cf41c6f237be2800768ccc
 size 97728

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce01bd3bff7f994f2533ac6a7689965d207f8aa1496d2a68521fddbc031fa9bc
+oid sha256:9ab51ba9f954ebdf59b6c93aed477b8c435131a47a6863a7d942a718fca8caa7
 size 212298

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f065c124f0f424314d1145042e8ee05c5da580710257b761da9284a5fb29c40e
+oid sha256:6fca460bcc06210167d624f4fc154234904288e03912641e076ab5b97621bbaf
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2ae2f3ad7053acd50c7e7d409ad77adf67cf2e41d60f862d993e95c5cd4432e
+oid sha256:fbdda021e46d7f1c2cf552418e85f97ff825cb7c9ed8a919986b027acdf2518b
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cdbae47ee0008be500ee81524891615859684f85d753648f64c68cc8aae01ba0
+oid sha256:edf5c9d2954cc04bff3e70ee522cdc62696360f93cf0870debc116ccc1bd67d8
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:53a78f5b2f2204e30e695d94c2f9dc90d3894600717151ae306b7112087d47cb
+oid sha256:86c8ed61d069d261f1a1b63b19eed784ab5b1d376985a32ce10ce7e4ad608070
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8f5af44da266da277e7531f687942d737458dea336c0a84bf03af6d775c87ac
+oid sha256:dde78f0152770b6d9ff9d100a4e49fd7ae2ec975980251062a46af49a9f251c7
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": NaN,
   "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.8018018018018018,
+  "epoch": 3.027027027027027,
   "eval_steps": 25,
-  "global_step": 25,
+  "global_step": 42,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -198,6 +198,125 @@
       "eval_samples_per_second": 428.002,
       "eval_steps_per_second": 111.28,
       "step": 25
+    },
+    {
+      "epoch": 1.8738738738738738,
+      "grad_norm": 0.5108070373535156,
+      "learning_rate": 4.109423525312738e-05,
+      "loss": 11.2485,
+      "step": 26
+    },
+    {
+      "epoch": 1.945945945945946,
+      "grad_norm": 0.5605173110961914,
+      "learning_rate": 3.777924554357096e-05,
+      "loss": 10.3144,
+      "step": 27
+    },
+    {
+      "epoch": 2.018018018018018,
+      "grad_norm": 0.4780227541923523,
+      "learning_rate": 3.45704275117204e-05,
+      "loss": 11.2554,
+      "step": 28
+    },
+    {
+      "epoch": 2.09009009009009,
+      "grad_norm": 0.3900972306728363,
+      "learning_rate": 3.1487564587782306e-05,
+      "loss": 10.069,
+      "step": 29
+    },
+    {
+      "epoch": 2.1621621621621623,
+      "grad_norm": 0.4860075116157532,
+      "learning_rate": 2.854966364683872e-05,
+      "loss": 11.2109,
+      "step": 30
+    },
+    {
+      "epoch": 2.234234234234234,
+      "grad_norm": 0.4599916636943817,
+      "learning_rate": 2.577483782514174e-05,
+      "loss": 8.562,
+      "step": 31
+    },
+    {
+      "epoch": 2.3063063063063063,
+      "grad_norm": 0.3811488151550293,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 10.8037,
+      "step": 32
+    },
+    {
+      "epoch": 2.3783783783783785,
+      "grad_norm": 0.5661867260932922,
+      "learning_rate": 2.0781731547998614e-05,
+      "loss": 12.446,
+      "step": 33
+    },
+    {
+      "epoch": 2.4504504504504503,
+      "grad_norm": 0.5369315147399902,
+      "learning_rate": 1.8594235253127375e-05,
+      "loss": 9.2962,
+      "step": 34
+    },
+    {
+      "epoch": 2.5225225225225225,
+      "grad_norm": 0.41405609250068665,
+      "learning_rate": 1.6631192604065855e-05,
+      "loss": 10.2131,
+      "step": 35
+    },
+    {
+      "epoch": 2.5945945945945947,
+      "grad_norm": 0.43550166487693787,
+      "learning_rate": 1.490470641152345e-05,
+      "loss": 10.1199,
+      "step": 36
+    },
+    {
+      "epoch": 2.6666666666666665,
+      "grad_norm": 0.5510601997375488,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 10.9105,
+      "step": 37
+    },
+    {
+      "epoch": 2.7387387387387387,
+      "grad_norm": 0.44297927618026733,
+      "learning_rate": 1.2202456766718093e-05,
+      "loss": 10.5097,
+      "step": 38
+    },
+    {
+      "epoch": 2.810810810810811,
+      "grad_norm": 0.4119100868701935,
+      "learning_rate": 1.1243353582104556e-05,
+      "loss": 9.4872,
+      "step": 39
+    },
+    {
+      "epoch": 2.8828828828828827,
+      "grad_norm": 0.5762305855751038,
+      "learning_rate": 1.0554024673218807e-05,
+      "loss": 11.9048,
+      "step": 40
+    },
+    {
+      "epoch": 2.954954954954955,
+      "grad_norm": 0.524325966835022,
+      "learning_rate": 1.0138719982009242e-05,
+      "loss": 10.0337,
+      "step": 41
+    },
+    {
+      "epoch": 3.027027027027027,
+      "grad_norm": 0.5072345733642578,
+      "learning_rate": 1e-05,
+      "loss": 10.4668,
+      "step": 42
     }
   ],
   "logging_steps": 1,
@@ -221,12 +340,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 21384029798400.0,
+  "total_flos": 35925170061312.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null