Training in progress, step 450, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c152cb6a91e6eb19cce5696bb5aab7af49b1436d63206846d7950a059f6829cc
+oid sha256:c78a77e2e0ca36266d090a929ee8a692bca004e435b6c4d5e4b51cc2d0eae970
 size 550593184

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f1d7db0293fb74147f7fe567624adc37460bac20ea378baaff44290172671e
+oid sha256:f88592b407317f11a87a94f4acb3da3defcda2175025edfcb11e8f2968dac586
 size 280342100

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30497404fbe87652d1676a91ddfb5d898aa726c54fd96fe0a00ea56154a09678
+oid sha256:5b1841640495b824fc5eb1d6b671ac4d502c008aa677d26e420739054f18e87a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cd6612e1be5fc1a945d1a2e93ec2df274cca4c095f65d292f5fd095af43ba016
+oid sha256:c9636ae38b683f4b5b714bdf172e563b0c593e0efe94f07eea78547963bfbfae
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.2922627031803131,
-  "best_model_checkpoint": "miner_id_24/checkpoint-300",
-  "epoch": 0.09203159751514686,
+  "best_metric": 0.29087916016578674,
+  "best_model_checkpoint": "miner_id_24/checkpoint-450",
+  "epoch": 0.1380473962727203,
   "eval_steps": 50,
-  "global_step": 300,
+  "global_step": 450,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -273,6 +273,135 @@
       "eval_samples_per_second": 7.163,
       "eval_steps_per_second": 1.791,
       "step": 300
+    },
+    {
+      "epoch": 0.09509931743231843,
+      "grad_norm": 0.0941392332315445,
+      "learning_rate": 2.296795912722014e-05,
+      "loss": 0.275,
+      "step": 310
+    },
+    {
+      "epoch": 0.09816703734948999,
+      "grad_norm": 0.11052852123975754,
+      "learning_rate": 2.0036116674432654e-05,
+      "loss": 0.3692,
+      "step": 320
+    },
+    {
+      "epoch": 0.10123475726666155,
+      "grad_norm": 0.10507681220769882,
+      "learning_rate": 1.725696330273575e-05,
+      "loss": 0.3476,
+      "step": 330
+    },
+    {
+      "epoch": 0.10430247718383312,
+      "grad_norm": 0.10875732451677322,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.2607,
+      "step": 340
+    },
+    {
+      "epoch": 0.10737019710100468,
+      "grad_norm": 0.23030522465705872,
+      "learning_rate": 1.2212521282287092e-05,
+      "loss": 0.1934,
+      "step": 350
+    },
+    {
+      "epoch": 0.10737019710100468,
+      "eval_loss": 0.29142311215400696,
+      "eval_runtime": 765.9528,
+      "eval_samples_per_second": 7.168,
+      "eval_steps_per_second": 1.793,
+      "step": 350
+    },
+    {
+      "epoch": 0.11043791701817623,
+      "grad_norm": 0.10388277471065521,
+      "learning_rate": 9.972937953781986e-06,
+      "loss": 0.2745,
+      "step": 360
+    },
+    {
+      "epoch": 0.1135056369353478,
+      "grad_norm": 0.10279553383588791,
+      "learning_rate": 7.937323358440935e-06,
+      "loss": 0.3599,
+      "step": 370
+    },
+    {
+      "epoch": 0.11657335685251936,
+      "grad_norm": 0.10545451194047928,
+      "learning_rate": 6.116050521637218e-06,
+      "loss": 0.3421,
+      "step": 380
+    },
+    {
+      "epoch": 0.11964107676969092,
+      "grad_norm": 0.11335179954767227,
+      "learning_rate": 4.5184002322740785e-06,
+      "loss": 0.2616,
+      "step": 390
+    },
+    {
+      "epoch": 0.12270879668686249,
+      "grad_norm": 0.22902686893939972,
+      "learning_rate": 3.1525137500119207e-06,
+      "loss": 0.1961,
+      "step": 400
+    },
+    {
+      "epoch": 0.12270879668686249,
+      "eval_loss": 0.29096364974975586,
+      "eval_runtime": 767.6702,
+      "eval_samples_per_second": 7.152,
+      "eval_steps_per_second": 1.789,
+      "step": 400
+    },
+    {
+      "epoch": 0.12577651660403405,
+      "grad_norm": 0.09514732658863068,
+      "learning_rate": 2.0253513192751373e-06,
+      "loss": 0.2589,
+      "step": 410
+    },
+    {
+      "epoch": 0.1288442365212056,
+      "grad_norm": 0.10798075050115585,
+      "learning_rate": 1.1426567014420297e-06,
+      "loss": 0.3551,
+      "step": 420
+    },
+    {
+      "epoch": 0.13191195643837716,
+      "grad_norm": 0.10427014529705048,
+      "learning_rate": 5.089279059533658e-07,
+      "loss": 0.3446,
+      "step": 430
+    },
+    {
+      "epoch": 0.13497967635554875,
+      "grad_norm": 0.1093059629201889,
+      "learning_rate": 1.2739426948732424e-07,
+      "loss": 0.2696,
+      "step": 440
+    },
+    {
+      "epoch": 0.1380473962727203,
+      "grad_norm": 0.2530665993690491,
+      "learning_rate": 0.0,
+      "loss": 0.1993,
+      "step": 450
+    },
+    {
+      "epoch": 0.1380473962727203,
+      "eval_loss": 0.29087916016578674,
+      "eval_runtime": 766.9955,
+      "eval_samples_per_second": 7.158,
+      "eval_steps_per_second": 1.79,
+      "step": 450
     }
   ],
   "logging_steps": 10,
@@ -296,12 +425,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 8.56285344058835e+17,
+  "total_flos": 1.2833863064239473e+18,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null