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:ff58896f86dbc180db3b614b823cf1c2b4c17c18bab82a71ab520d9afbbf4207
+oid sha256:40710fd1d4afea3017e2d681c990e25edf154e4468ebb63d19ba5931903a4cdc
 size 289452128

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4ab71442599bb8da7023a712c968990c8ec218041b01ac4deb40e93fd61e0183
+oid sha256:ed1efb021694d6b93f56a5577ade51f745691dcb024550690358b64d9ff487a7
 size 147359892

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84337a0b5baecd930c964daa54054e5734ed5e51c3d921251b77b2277716e16c
+oid sha256:17fdeb77d06dcedbaefd3bb0d7470406b3d6cbc5bb7b22f3c7cb407555ab75a4
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb15fdd4c0ab874f4afa0ea95fae119cbc74554df5fbe92ab825fe27063eaa04
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 2.1998445987701416,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.017593244194229415,
+  "best_metric": 2.1071135997772217,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.03518648838845883,
   "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": 63.522,
       "eval_steps_per_second": 7.96,
       "step": 25
+    },
+    {
+      "epoch": 0.018296973961998593,
+      "grad_norm": 0.8111019134521484,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 2.1868,
+      "step": 26
+    },
+    {
+      "epoch": 0.019000703729767768,
+      "grad_norm": 0.6819187998771667,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 2.1773,
+      "step": 27
+    },
+    {
+      "epoch": 0.019704433497536946,
+      "grad_norm": 0.7138143181800842,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 2.2268,
+      "step": 28
+    },
+    {
+      "epoch": 0.02040816326530612,
+      "grad_norm": 1.2253530025482178,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 2.4231,
+      "step": 29
+    },
+    {
+      "epoch": 0.0211118930330753,
+      "grad_norm": 0.7903726100921631,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 2.0236,
+      "step": 30
+    },
+    {
+      "epoch": 0.021815622800844477,
+      "grad_norm": 0.6488191485404968,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 2.0918,
+      "step": 31
+    },
+    {
+      "epoch": 0.022519352568613652,
+      "grad_norm": 0.7203357219696045,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 2.1305,
+      "step": 32
+    },
+    {
+      "epoch": 0.02322308233638283,
+      "grad_norm": 0.7722885608673096,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 2.2269,
+      "step": 33
+    },
+    {
+      "epoch": 0.023926812104152005,
+      "grad_norm": 0.6173502802848816,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 2.0185,
+      "step": 34
+    },
+    {
+      "epoch": 0.024630541871921183,
+      "grad_norm": 0.8969466090202332,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.4426,
+      "step": 35
+    },
+    {
+      "epoch": 0.025334271639690358,
+      "grad_norm": 0.7939102053642273,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 2.0875,
+      "step": 36
+    },
+    {
+      "epoch": 0.026038001407459536,
+      "grad_norm": 0.6162180304527283,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 1.9491,
+      "step": 37
+    },
+    {
+      "epoch": 0.02674173117522871,
+      "grad_norm": 0.6837140321731567,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 1.8046,
+      "step": 38
+    },
+    {
+      "epoch": 0.02744546094299789,
+      "grad_norm": 0.6838858127593994,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 1.8489,
+      "step": 39
+    },
+    {
+      "epoch": 0.028149190710767064,
+      "grad_norm": 0.9752803444862366,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 1.9773,
+      "step": 40
+    },
+    {
+      "epoch": 0.028852920478536243,
+      "grad_norm": 0.8087269067764282,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 1.7675,
+      "step": 41
+    },
+    {
+      "epoch": 0.029556650246305417,
+      "grad_norm": 0.8337047696113586,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 1.7071,
+      "step": 42
+    },
+    {
+      "epoch": 0.030260380014074596,
+      "grad_norm": 1.047497272491455,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 1.7507,
+      "step": 43
+    },
+    {
+      "epoch": 0.03096410978184377,
+      "grad_norm": 1.00037682056427,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 1.84,
+      "step": 44
+    },
+    {
+      "epoch": 0.03166783954961295,
+      "grad_norm": 1.0732063055038452,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 1.7851,
+      "step": 45
+    },
+    {
+      "epoch": 0.03237156931738212,
+      "grad_norm": 1.073845386505127,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 2.0417,
+      "step": 46
+    },
+    {
+      "epoch": 0.033075299085151305,
+      "grad_norm": 1.1644452810287476,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 2.0671,
+      "step": 47
+    },
+    {
+      "epoch": 0.03377902885292048,
+      "grad_norm": 1.675778865814209,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 2.2341,
+      "step": 48
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 2.151191234588623,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 2.0903,
+      "step": 49
+    },
+    {
+      "epoch": 0.03518648838845883,
+      "grad_norm": 3.5507590770721436,
+      "learning_rate": 0.0,
+      "loss": 2.834,
+      "step": 50
+    },
+    {
+      "epoch": 0.03518648838845883,
+      "eval_loss": 2.1071135997772217,
+      "eval_runtime": 37.6494,
+      "eval_samples_per_second": 63.587,
+      "eval_steps_per_second": 7.968,
+      "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": 4384478138990592.0,
+  "total_flos": 8520778270113792.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null