Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60637391729df9e656b156a241dec7c1e925bbe14b079ec990ae769c77461a01
+oid sha256:2d81ce0e3f7c690bb5e131d223c13dca73e6fc35af7e8903c113ea72ca9e5928
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23bfc74d86c2bbd6fc7e41e1a3182ab7b4a9a29e66c4794d0be48e2f065cd811
+oid sha256:be5db312adefb0461c16303c0209aa18f0f46de6b1b46cddaff68c5c6313fbb2
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba40e84e991758419f82ccf5f7a8e9bbb6a30417ff7897a5638663d5a7264007
+oid sha256:9a5a95c508fa50079dcadcfb59f158454af0c6300fcea69bab53427f29aeb45f
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5aa365110780f12edfe54751fa123785ae60819def704e87e3c35ec31663f554
+oid sha256:7291dcb5832a08cd9c27582a7b5ea164a1e31d6449fb8e3b7829230f0d2bab11
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2f23a7eb8010a262826dd3f54f5e41025aae2374c9a7273de5fb4db8b8948d20
+oid sha256:4b85ef2149e444fc7f413561622e36dd0727d96cd37198f64db93d0c8bbbdbe1
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75bec37b27a29ce04cc68bbfd89a8339927f93b8cf9c91c52bcd30fb9e9e5fe0
+oid sha256:6fd04b4b1969db711240a94cc4e6a6e98112145b606e891bba595c58689935e3
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb0ce41087f0939d63a9a6eb297660d82f62bda022868309a8c97328e5da41a5
+oid sha256:0b823f3900a3c8aa20bff7ce05b4e552f6bc019793f00b0bb20027204b5c704a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.5857478380203247,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.6218422075398368,
+  "best_metric": 1.4757866859436035,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.9327633113097551,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 11.182,
       "eval_steps_per_second": 2.907,
       "step": 50
+    },
+    {
+      "epoch": 0.6342790516906335,
+      "grad_norm": 1.9586689472198486,
+      "learning_rate": 3.250000000000001e-05,
+      "loss": 1.9342,
+      "step": 51
+    },
+    {
+      "epoch": 0.6467158958414302,
+      "grad_norm": 1.7377395629882812,
+      "learning_rate": 3.082151762439293e-05,
+      "loss": 1.9846,
+      "step": 52
+    },
+    {
+      "epoch": 0.659152739992227,
+      "grad_norm": 1.4514222145080566,
+      "learning_rate": 2.9189060364202943e-05,
+      "loss": 1.6922,
+      "step": 53
+    },
+    {
+      "epoch": 0.6715895841430237,
+      "grad_norm": 1.5051312446594238,
+      "learning_rate": 2.760573569460757e-05,
+      "loss": 1.872,
+      "step": 54
+    },
+    {
+      "epoch": 0.6840264282938204,
+      "grad_norm": 1.3607957363128662,
+      "learning_rate": 2.6074557564105727e-05,
+      "loss": 1.563,
+      "step": 55
+    },
+    {
+      "epoch": 0.6964632724446171,
+      "grad_norm": 1.4457933902740479,
+      "learning_rate": 2.459844065729529e-05,
+      "loss": 1.5738,
+      "step": 56
+    },
+    {
+      "epoch": 0.708900116595414,
+      "grad_norm": 1.5340603590011597,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 1.4182,
+      "step": 57
+    },
+    {
+      "epoch": 0.7213369607462107,
+      "grad_norm": 1.8126493692398071,
+      "learning_rate": 2.1822519843544424e-05,
+      "loss": 1.4997,
+      "step": 58
+    },
+    {
+      "epoch": 0.7337738048970074,
+      "grad_norm": 1.8174535036087036,
+      "learning_rate": 2.0528000059645997e-05,
+      "loss": 1.4925,
+      "step": 59
+    },
+    {
+      "epoch": 0.7462106490478041,
+      "grad_norm": 1.6950277090072632,
+      "learning_rate": 1.9299099686894423e-05,
+      "loss": 1.3651,
+      "step": 60
+    },
+    {
+      "epoch": 0.7586474931986008,
+      "grad_norm": 1.7184079885482788,
+      "learning_rate": 1.8138158006995364e-05,
+      "loss": 1.258,
+      "step": 61
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "grad_norm": 2.286306142807007,
+      "learning_rate": 1.7047384938420154e-05,
+      "loss": 0.9343,
+      "step": 62
+    },
+    {
+      "epoch": 0.7835211815001943,
+      "grad_norm": 1.4997891187667847,
+      "learning_rate": 1.602885682970026e-05,
+      "loss": 1.5661,
+      "step": 63
+    },
+    {
+      "epoch": 0.795958025650991,
+      "grad_norm": 1.3938400745391846,
+      "learning_rate": 1.5084512506980026e-05,
+      "loss": 1.7878,
+      "step": 64
+    },
+    {
+      "epoch": 0.8083948698017878,
+      "grad_norm": 1.4616719484329224,
+      "learning_rate": 1.4216149583350754e-05,
+      "loss": 1.7966,
+      "step": 65
+    },
+    {
+      "epoch": 0.8208317139525846,
+      "grad_norm": 1.3521653413772583,
+      "learning_rate": 1.3425421036992098e-05,
+      "loss": 1.7621,
+      "step": 66
+    },
+    {
+      "epoch": 0.8332685581033813,
+      "grad_norm": 1.436239242553711,
+      "learning_rate": 1.2713832064634126e-05,
+      "loss": 1.4504,
+      "step": 67
+    },
+    {
+      "epoch": 0.845705402254178,
+      "grad_norm": 1.5169296264648438,
+      "learning_rate": 1.2082737216329794e-05,
+      "loss": 1.5677,
+      "step": 68
+    },
+    {
+      "epoch": 0.8581422464049747,
+      "grad_norm": 1.4382579326629639,
+      "learning_rate": 1.1533337816991932e-05,
+      "loss": 1.5528,
+      "step": 69
+    },
+    {
+      "epoch": 0.8705790905557714,
+      "grad_norm": 1.535103440284729,
+      "learning_rate": 1.1066679679603e-05,
+      "loss": 1.5379,
+      "step": 70
+    },
+    {
+      "epoch": 0.8830159347065683,
+      "grad_norm": 1.5666173696517944,
+      "learning_rate": 1.0683651114450641e-05,
+      "loss": 1.4208,
+      "step": 71
+    },
+    {
+      "epoch": 0.895452778857365,
+      "grad_norm": 1.581671953201294,
+      "learning_rate": 1.0384981238178534e-05,
+      "loss": 1.3917,
+      "step": 72
+    },
+    {
+      "epoch": 0.9078896230081617,
+      "grad_norm": 1.4792799949645996,
+      "learning_rate": 1.017123858587145e-05,
+      "loss": 1.1024,
+      "step": 73
+    },
+    {
+      "epoch": 0.9203264671589584,
+      "grad_norm": 1.4445815086364746,
+      "learning_rate": 1.00428300288164e-05,
+      "loss": 0.9231,
+      "step": 74
+    },
+    {
+      "epoch": 0.9327633113097551,
+      "grad_norm": 1.419348120689392,
+      "learning_rate": 1e-05,
+      "loss": 0.3999,
+      "step": 75
+    },
+    {
+      "epoch": 0.9327633113097551,
+      "eval_loss": 1.4757866859436035,
+      "eval_runtime": 4.3684,
+      "eval_samples_per_second": 11.446,
+      "eval_steps_per_second": 2.976,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -404,12 +587,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 5.968083617316864e+17,
+  "total_flos": 8.952125425975296e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null