Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d86f28566aaa7be3922310867b747184b4fe3e5bcceee0ad42c2257bff7a2e0
+oid sha256:8d59a711a550dc918f7088a0c0ea4609b0e928e91704ab8b5e58d881c84aee9d
 size 119801528

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4228c27dcc05eb15310729130f1c0313c46c4c6562fbf8311c5ffc405e8756
+oid sha256:59a79519d0257a10927631120e36edef73bd21d48d000dc6ec93f64a0fa4f985
 size 239892858

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72328fe9f5226bdbab508eef41f5524d19f4cd740dfebb05663b93830536b06c
+oid sha256:99bcb9c489ef86e45e6b5b44f91483615ae6ed4f3e5f9e16d519b7c6349d3524
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ea7ff16b0c30a914eb0d145e3fb06ff9027c6cd2408e766ce8a09accab89a4d
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 1.1469987630844116,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.006671559143371806,
+  "best_metric": 1.1243497133255005,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.013343118286743613,
   "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": 4.848,
       "eval_steps_per_second": 2.424,
       "step": 25
+    },
+    {
+      "epoch": 0.006938421509106678,
+      "grad_norm": 0.6408900022506714,
+      "learning_rate": 0.0001,
+      "loss": 1.3754,
+      "step": 26
+    },
+    {
+      "epoch": 0.007205283874841551,
+      "grad_norm": 0.9624432921409607,
+      "learning_rate": 9.345968707698569e-05,
+      "loss": 1.3455,
+      "step": 27
+    },
+    {
+      "epoch": 0.007472146240576422,
+      "grad_norm": 0.6052916646003723,
+      "learning_rate": 8.694738077799488e-05,
+      "loss": 1.3871,
+      "step": 28
+    },
+    {
+      "epoch": 0.007739008606311295,
+      "grad_norm": 0.5944576859474182,
+      "learning_rate": 8.049096779838719e-05,
+      "loss": 1.1906,
+      "step": 29
+    },
+    {
+      "epoch": 0.008005870972046168,
+      "grad_norm": 0.66631680727005,
+      "learning_rate": 7.411809548974792e-05,
+      "loss": 1.3954,
+      "step": 30
+    },
+    {
+      "epoch": 0.00827273333778104,
+      "grad_norm": 0.6512559056282043,
+      "learning_rate": 6.785605346968386e-05,
+      "loss": 1.5238,
+      "step": 31
+    },
+    {
+      "epoch": 0.008539595703515911,
+      "grad_norm": 0.6266358494758606,
+      "learning_rate": 6.173165676349103e-05,
+      "loss": 1.2382,
+      "step": 32
+    },
+    {
+      "epoch": 0.008806458069250784,
+      "grad_norm": 0.6132543087005615,
+      "learning_rate": 5.577113097809989e-05,
+      "loss": 1.053,
+      "step": 33
+    },
+    {
+      "epoch": 0.009073320434985656,
+      "grad_norm": 0.6559033989906311,
+      "learning_rate": 5.000000000000002e-05,
+      "loss": 1.5881,
+      "step": 34
+    },
+    {
+      "epoch": 0.009340182800720529,
+      "grad_norm": 0.6847499012947083,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 1.5597,
+      "step": 35
+    },
+    {
+      "epoch": 0.009607045166455401,
+      "grad_norm": 0.6695072650909424,
+      "learning_rate": 3.9123857099127936e-05,
+      "loss": 1.464,
+      "step": 36
+    },
+    {
+      "epoch": 0.009873907532190272,
+      "grad_norm": 0.6664255261421204,
+      "learning_rate": 3.406541848999312e-05,
+      "loss": 1.4036,
+      "step": 37
+    },
+    {
+      "epoch": 0.010140769897925145,
+      "grad_norm": 0.7430691719055176,
+      "learning_rate": 2.9289321881345254e-05,
+      "loss": 1.0536,
+      "step": 38
+    },
+    {
+      "epoch": 0.010407632263660017,
+      "grad_norm": 0.7103254795074463,
+      "learning_rate": 2.4816019252102273e-05,
+      "loss": 1.5054,
+      "step": 39
+    },
+    {
+      "epoch": 0.01067449462939489,
+      "grad_norm": 0.6650035381317139,
+      "learning_rate": 2.0664665970876496e-05,
+      "loss": 1.6155,
+      "step": 40
+    },
+    {
+      "epoch": 0.010941356995129763,
+      "grad_norm": 0.702969491481781,
+      "learning_rate": 1.6853038769745467e-05,
+      "loss": 1.3914,
+      "step": 41
+    },
+    {
+      "epoch": 0.011208219360864633,
+      "grad_norm": 0.8632053732872009,
+      "learning_rate": 1.339745962155613e-05,
+      "loss": 1.4575,
+      "step": 42
+    },
+    {
+      "epoch": 0.011475081726599506,
+      "grad_norm": 0.757703959941864,
+      "learning_rate": 1.0312725846731175e-05,
+      "loss": 1.3532,
+      "step": 43
+    },
+    {
+      "epoch": 0.011741944092334379,
+      "grad_norm": 0.7126505970954895,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 1.3034,
+      "step": 44
+    },
+    {
+      "epoch": 0.012008806458069251,
+      "grad_norm": 0.8105053901672363,
+      "learning_rate": 5.306987050489442e-06,
+      "loss": 1.6154,
+      "step": 45
+    },
+    {
+      "epoch": 0.012275668823804124,
+      "grad_norm": 0.7980390787124634,
+      "learning_rate": 3.40741737109318e-06,
+      "loss": 1.1972,
+      "step": 46
+    },
+    {
+      "epoch": 0.012542531189538995,
+      "grad_norm": 0.8466772437095642,
+      "learning_rate": 1.921471959676957e-06,
+      "loss": 1.8855,
+      "step": 47
+    },
+    {
+      "epoch": 0.012809393555273867,
+      "grad_norm": 1.5893186330795288,
+      "learning_rate": 8.555138626189618e-07,
+      "loss": 1.6354,
+      "step": 48
+    },
+    {
+      "epoch": 0.01307625592100874,
+      "grad_norm": 1.0377373695373535,
+      "learning_rate": 2.141076761396521e-07,
+      "loss": 1.8772,
+      "step": 49
+    },
+    {
+      "epoch": 0.013343118286743613,
+      "grad_norm": 1.9227272272109985,
+      "learning_rate": 0.0,
+      "loss": 1.7072,
+      "step": 50
+    },
+    {
+      "epoch": 0.013343118286743613,
+      "eval_loss": 1.1243497133255005,
+      "eval_runtime": 325.4715,
+      "eval_samples_per_second": 4.848,
+      "eval_steps_per_second": 2.424,
+      "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": 1.37856974585856e+16,
+  "total_flos": 2.75713949171712e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null