Training in progress, step 74, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28c80fabba16dc0d7e036f5ae552235fc143ef01162865bc26d99027e726421b
+oid sha256:424858a895f2a90f8f28e9d7ed3f3fce59d16625f079ed50fd05a9e3bce873b3
 size 402688040

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a53cce6e2bc5ec7677fbb8519558f4d7b2a5243877618148af0fde97cfb70fb
+oid sha256:f5b712189bca3b983faff78c85f33cda5a85aaae3a5787a7dc718844ca8af34e
 size 204773716

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c04b784607ecfebf2f8907cd8551c4fff661eeec6d7725d9cb07ae92a91a882d
+oid sha256:5b44d4076e0e7faa8598105a6ac2bf1d1cc7a099a32a53df9176c59ce4827def
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dfdd42b3078aa2721ae65762bacf3e311ccf189e9060581e232d41dfc610dfff
+oid sha256:7105a509bdfde59e6e4d893f7ae8de5118e3beb17226743671d553509dc9662b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.1070915460586548,
   "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 2.061224489795918,
+  "epoch": 3.0510204081632653,
   "eval_steps": 50,
-  "global_step": 50,
+  "global_step": 74,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -373,6 +373,174 @@
       "eval_samples_per_second": 20.797,
       "eval_steps_per_second": 5.447,
       "step": 50
+    },
+    {
+      "epoch": 2.1020408163265305,
+      "grad_norm": 2.2608895301818848,
+      "learning_rate": 2.8622245328485907e-05,
+      "loss": 3.3243,
+      "step": 51
+    },
+    {
+      "epoch": 2.142857142857143,
+      "grad_norm": 5.559860706329346,
+      "learning_rate": 2.6430163158700115e-05,
+      "loss": 3.5716,
+      "step": 52
+    },
+    {
+      "epoch": 2.183673469387755,
+      "grad_norm": 2.4335508346557617,
+      "learning_rate": 2.4294862790338917e-05,
+      "loss": 3.1162,
+      "step": 53
+    },
+    {
+      "epoch": 2.2244897959183674,
+      "grad_norm": 2.707456350326538,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 4.0959,
+      "step": 54
+    },
+    {
+      "epoch": 2.2653061224489797,
+      "grad_norm": 2.8806371688842773,
+      "learning_rate": 2.0215034775378332e-05,
+      "loss": 3.0917,
+      "step": 55
+    },
+    {
+      "epoch": 2.306122448979592,
+      "grad_norm": 2.399998664855957,
+      "learning_rate": 1.8280335791817733e-05,
+      "loss": 2.7012,
+      "step": 56
+    },
+    {
+      "epoch": 2.3469387755102042,
+      "grad_norm": 2.528128147125244,
+      "learning_rate": 1.6422052257649078e-05,
+      "loss": 3.2158,
+      "step": 57
+    },
+    {
+      "epoch": 2.387755102040816,
+      "grad_norm": 2.2674336433410645,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2289,
+      "step": 58
+    },
+    {
+      "epoch": 2.4285714285714284,
+      "grad_norm": 2.6586036682128906,
+      "learning_rate": 1.2952443732252057e-05,
+      "loss": 3.2352,
+      "step": 59
+    },
+    {
+      "epoch": 2.4693877551020407,
+      "grad_norm": 3.082754373550415,
+      "learning_rate": 1.134947733186315e-05,
+      "loss": 3.1058,
+      "step": 60
+    },
+    {
+      "epoch": 2.510204081632653,
+      "grad_norm": 2.3137409687042236,
+      "learning_rate": 9.83962342596776e-06,
+      "loss": 3.1489,
+      "step": 61
+    },
+    {
+      "epoch": 2.5510204081632653,
+      "grad_norm": 3.146894693374634,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.7389,
+      "step": 62
+    },
+    {
+      "epoch": 2.5918367346938775,
+      "grad_norm": 2.5860869884490967,
+      "learning_rate": 7.1135694999864e-06,
+      "loss": 2.8921,
+      "step": 63
+    },
+    {
+      "epoch": 2.63265306122449,
+      "grad_norm": 2.651083469390869,
+      "learning_rate": 5.903936782582253e-06,
+      "loss": 3.3957,
+      "step": 64
+    },
+    {
+      "epoch": 2.673469387755102,
+      "grad_norm": 2.846827507019043,
+      "learning_rate": 4.800535343827833e-06,
+      "loss": 2.759,
+      "step": 65
+    },
+    {
+      "epoch": 2.7142857142857144,
+      "grad_norm": 3.2200374603271484,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.8369,
+      "step": 66
+    },
+    {
+      "epoch": 2.7551020408163263,
+      "grad_norm": 3.225104808807373,
+      "learning_rate": 2.9227967408489653e-06,
+      "loss": 3.5187,
+      "step": 67
+    },
+    {
+      "epoch": 2.795918367346939,
+      "grad_norm": 2.8337438106536865,
+      "learning_rate": 2.152983213389559e-06,
+      "loss": 2.9697,
+      "step": 68
+    },
+    {
+      "epoch": 2.836734693877551,
+      "grad_norm": 2.468045949935913,
+      "learning_rate": 1.4984373402728014e-06,
+      "loss": 2.9315,
+      "step": 69
+    },
+    {
+      "epoch": 2.877551020408163,
+      "grad_norm": 3.3334028720855713,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.4555,
+      "step": 70
+    },
+    {
+      "epoch": 2.9183673469387754,
+      "grad_norm": 3.127939224243164,
+      "learning_rate": 5.411745017609493e-07,
+      "loss": 3.4373,
+      "step": 71
+    },
+    {
+      "epoch": 2.9591836734693877,
+      "grad_norm": 3.0887768268585205,
+      "learning_rate": 2.407636663901591e-07,
+      "loss": 2.9134,
+      "step": 72
+    },
+    {
+      "epoch": 3.010204081632653,
+      "grad_norm": 2.975400924682617,
+      "learning_rate": 6.022718974137975e-08,
+      "loss": 3.4059,
+      "step": 73
+    },
+    {
+      "epoch": 3.0510204081632653,
+      "grad_norm": 2.2996485233306885,
+      "learning_rate": 0.0,
+      "loss": 3.0027,
+      "step": 74
     }
   ],
   "logging_steps": 1,
@@ -396,12 +564,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 3.7584000516096e+16,
+  "total_flos": 5.562432076382208e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null