Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c5d8593d69148eb494dc77ca580ec98f49119f9bc89a3d65f0fe9d8e95a526c
+oid sha256:0a4dc31756b1ec3279719e01e3fe8b32bd098aeca78651343cca78c1dc7c7b34
 size 167832240

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a08d33bb93770faf13188e9a5b166057b14b2c7e1649589f4153f1f8e2d7478
+oid sha256:623b8a4121cff716dbbe9b77901594b53c5fc70885a1ba76f17fac1f3c9d20e4
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:def1acb4323a2a87efbbbea33a58fb741dac2455f7dd3541d57bea8067e0e097
+oid sha256:7d602f002ceb4f1394ef501a72438705f77760c4d95a2f2377ec6a53bc6d1ce7
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.12636807560920715,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04478280340349306,
+  "best_metric": 0.10715995728969574,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.08956560680698612,
   "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": 7.057,
       "eval_steps_per_second": 3.544,
       "step": 25
+    },
+    {
+      "epoch": 0.04657411553963278,
+      "grad_norm": 2.4748008251190186,
+      "learning_rate": 5e-05,
+      "loss": 0.2563,
+      "step": 26
+    },
+    {
+      "epoch": 0.0483654276757725,
+      "grad_norm": 4.218332290649414,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4993,
+      "step": 27
+    },
+    {
+      "epoch": 0.050156739811912224,
+      "grad_norm": 2.3692610263824463,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.235,
+      "step": 28
+    },
+    {
+      "epoch": 0.05194805194805195,
+      "grad_norm": 3.3568317890167236,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.3957,
+      "step": 29
+    },
+    {
+      "epoch": 0.05373936408419167,
+      "grad_norm": 4.579010009765625,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.4771,
+      "step": 30
+    },
+    {
+      "epoch": 0.05553067622033139,
+      "grad_norm": 3.82382869720459,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2925,
+      "step": 31
+    },
+    {
+      "epoch": 0.057321988356471114,
+      "grad_norm": 2.7304625511169434,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2957,
+      "step": 32
+    },
+    {
+      "epoch": 0.059113300492610835,
+      "grad_norm": 4.2830352783203125,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4469,
+      "step": 33
+    },
+    {
+      "epoch": 0.06090461262875056,
+      "grad_norm": 2.769845724105835,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.4208,
+      "step": 34
+    },
+    {
+      "epoch": 0.06269592476489028,
+      "grad_norm": 2.1712167263031006,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.1889,
+      "step": 35
+    },
+    {
+      "epoch": 0.06448723690103,
+      "grad_norm": 3.581455707550049,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3311,
+      "step": 36
+    },
+    {
+      "epoch": 0.06627854903716973,
+      "grad_norm": 4.364194393157959,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5934,
+      "step": 37
+    },
+    {
+      "epoch": 0.06806986117330945,
+      "grad_norm": 2.803682565689087,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3943,
+      "step": 38
+    },
+    {
+      "epoch": 0.06986117330944917,
+      "grad_norm": 3.7528460025787354,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4517,
+      "step": 39
+    },
+    {
+      "epoch": 0.07165248544558889,
+      "grad_norm": 3.5302984714508057,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.5168,
+      "step": 40
+    },
+    {
+      "epoch": 0.07344379758172861,
+      "grad_norm": 5.849757194519043,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6599,
+      "step": 41
+    },
+    {
+      "epoch": 0.07523510971786834,
+      "grad_norm": 4.0423760414123535,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.5821,
+      "step": 42
+    },
+    {
+      "epoch": 0.07702642185400806,
+      "grad_norm": 4.6589484214782715,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.6031,
+      "step": 43
+    },
+    {
+      "epoch": 0.07881773399014778,
+      "grad_norm": 3.569039821624756,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5059,
+      "step": 44
+    },
+    {
+      "epoch": 0.08060904612628751,
+      "grad_norm": 5.747331619262695,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.8897,
+      "step": 45
+    },
+    {
+      "epoch": 0.08240035826242723,
+      "grad_norm": 5.7729363441467285,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.8777,
+      "step": 46
+    },
+    {
+      "epoch": 0.08419167039856695,
+      "grad_norm": 5.641356945037842,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.9093,
+      "step": 47
+    },
+    {
+      "epoch": 0.08598298253470667,
+      "grad_norm": 4.868679523468018,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.7942,
+      "step": 48
+    },
+    {
+      "epoch": 0.0877742946708464,
+      "grad_norm": 6.637969493865967,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.746,
+      "step": 49
+    },
+    {
+      "epoch": 0.08956560680698612,
+      "grad_norm": 4.852217197418213,
+      "learning_rate": 0.0,
+      "loss": 0.4853,
+      "step": 50
+    },
+    {
+      "epoch": 0.08956560680698612,
+      "eval_loss": 0.10715995728969574,
+      "eval_runtime": 33.3425,
+      "eval_samples_per_second": 7.048,
+      "eval_steps_per_second": 3.539,
+      "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": 1.75782374670336e+16,
+  "total_flos": 3.51564749340672e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null