Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fb0a3c61238f482a44c0a673f9f0b0110cd8448a7d94b6e15ad6c70f67d9fcc
+oid sha256:b1734e6fe4f45ed343b344a4d3f6739da2bf57ca32659d8ac4c53a3b4512428e
 size 478211024

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7060b27188f45ab811ba96e1245c9d46f1f34ea33a8a06353ca00847e566ee4
+oid sha256:b8924d9e50a7c51c2f888cdcdb19f0a4f4b2c9a8d79a2d938fc208138009302c
 size 243337876

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:07e868a5d42bcd1d26cd76590186501281c910a664f356e55285bd3a1ffe4f40
+oid sha256:25e5b9a0137c194c01e917af99d0bcb47e3a75c925c52847ce42a564e2873e37
 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": 1.1481987237930298,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.016909029421711193,
+  "best_metric": 1.1276743412017822,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.033818058843422386,
   "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": 39.025,
       "eval_steps_per_second": 4.89,
       "step": 25
+    },
+    {
+      "epoch": 0.01758539059857964,
+      "grad_norm": 1.4804654121398926,
+      "learning_rate": 5.522642316338268e-05,
+      "loss": 4.6336,
+      "step": 26
+    },
+    {
+      "epoch": 0.01826175177544809,
+      "grad_norm": 1.5661972761154175,
+      "learning_rate": 5.174497483512506e-05,
+      "loss": 4.7698,
+      "step": 27
+    },
+    {
+      "epoch": 0.018938112952316538,
+      "grad_norm": 1.5047603845596313,
+      "learning_rate": 4.825502516487497e-05,
+      "loss": 4.4571,
+      "step": 28
+    },
+    {
+      "epoch": 0.019614474129184985,
+      "grad_norm": 1.5553841590881348,
+      "learning_rate": 4.477357683661734e-05,
+      "loss": 4.4778,
+      "step": 29
+    },
+    {
+      "epoch": 0.020290835306053433,
+      "grad_norm": 1.5995780229568481,
+      "learning_rate": 4.131759111665349e-05,
+      "loss": 4.6735,
+      "step": 30
+    },
+    {
+      "epoch": 0.02096719648292188,
+      "grad_norm": 1.5220364332199097,
+      "learning_rate": 3.790390522001662e-05,
+      "loss": 4.7163,
+      "step": 31
+    },
+    {
+      "epoch": 0.021643557659790327,
+      "grad_norm": 1.4890873432159424,
+      "learning_rate": 3.4549150281252636e-05,
+      "loss": 4.2718,
+      "step": 32
+    },
+    {
+      "epoch": 0.022319918836658775,
+      "grad_norm": 1.648818016052246,
+      "learning_rate": 3.12696703292044e-05,
+      "loss": 4.6693,
+      "step": 33
+    },
+    {
+      "epoch": 0.022996280013527222,
+      "grad_norm": 1.5415022373199463,
+      "learning_rate": 2.8081442660546125e-05,
+      "loss": 4.3453,
+      "step": 34
+    },
+    {
+      "epoch": 0.023672641190395673,
+      "grad_norm": 1.60922372341156,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 4.606,
+      "step": 35
+    },
+    {
+      "epoch": 0.02434900236726412,
+      "grad_norm": 1.661799430847168,
+      "learning_rate": 2.2040354826462668e-05,
+      "loss": 4.7403,
+      "step": 36
+    },
+    {
+      "epoch": 0.025025363544132567,
+      "grad_norm": 1.6511698961257935,
+      "learning_rate": 1.9216926233717085e-05,
+      "loss": 4.7336,
+      "step": 37
+    },
+    {
+      "epoch": 0.025701724721001015,
+      "grad_norm": 1.5974169969558716,
+      "learning_rate": 1.6543469682057106e-05,
+      "loss": 4.6502,
+      "step": 38
+    },
+    {
+      "epoch": 0.026378085897869462,
+      "grad_norm": 1.7044310569763184,
+      "learning_rate": 1.4033009983067452e-05,
+      "loss": 4.6695,
+      "step": 39
+    },
+    {
+      "epoch": 0.02705444707473791,
+      "grad_norm": 1.5518771409988403,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 4.4624,
+      "step": 40
+    },
+    {
+      "epoch": 0.027730808251606356,
+      "grad_norm": 1.8471145629882812,
+      "learning_rate": 9.549150281252633e-06,
+      "loss": 4.6761,
+      "step": 41
+    },
+    {
+      "epoch": 0.028407169428474807,
+      "grad_norm": 1.697399377822876,
+      "learning_rate": 7.597595192178702e-06,
+      "loss": 4.5145,
+      "step": 42
+    },
+    {
+      "epoch": 0.029083530605343254,
+      "grad_norm": 1.636686086654663,
+      "learning_rate": 5.852620357053651e-06,
+      "loss": 4.4332,
+      "step": 43
+    },
+    {
+      "epoch": 0.029759891782211702,
+      "grad_norm": 1.6814813613891602,
+      "learning_rate": 4.322727117869951e-06,
+      "loss": 4.6082,
+      "step": 44
+    },
+    {
+      "epoch": 0.03043625295908015,
+      "grad_norm": 1.770627498626709,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 4.5782,
+      "step": 45
+    },
+    {
+      "epoch": 0.031112614135948596,
+      "grad_norm": 1.9010318517684937,
+      "learning_rate": 1.9369152030840556e-06,
+      "loss": 4.5493,
+      "step": 46
+    },
+    {
+      "epoch": 0.03178897531281705,
+      "grad_norm": 1.9612586498260498,
+      "learning_rate": 1.0926199633097157e-06,
+      "loss": 4.6045,
+      "step": 47
+    },
+    {
+      "epoch": 0.03246533648968549,
+      "grad_norm": 1.9514307975769043,
+      "learning_rate": 4.865965629214819e-07,
+      "loss": 4.4648,
+      "step": 48
+    },
+    {
+      "epoch": 0.03314169766655394,
+      "grad_norm": 2.2790310382843018,
+      "learning_rate": 1.2179748700879012e-07,
+      "loss": 4.7822,
+      "step": 49
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "grad_norm": 3.5149526596069336,
+      "learning_rate": 0.0,
+      "loss": 5.4604,
+      "step": 50
+    },
+    {
+      "epoch": 0.033818058843422386,
+      "eval_loss": 1.1276743412017822,
+      "eval_runtime": 63.8973,
+      "eval_samples_per_second": 38.969,
+      "eval_steps_per_second": 4.883,
+      "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": 9914505064611840.0,
+  "total_flos": 1.935689084043264e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null