Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f22496712fc5efb0a400a83d4c23ed289b3555ef1f8e8c69c8a9cff79f3cf658
+oid sha256:cc57595a8bbefe39c4fd7d58f66ddb5d6e9ac21d62fa02085fc062deee4ed5fa
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:005371babdabb9018bea3fe11e98c0b3c83641a65e16a91405a4569608982d6d
+oid sha256:423af9dbdf46867c566521d47af2f9623d35cae1f70982c4b08775f32d4c9a45
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83dcff0a16765769a48a7747da189d563c55af010b7a78d9bcb5b0e5ff2cfef8
+oid sha256:a39c0e74b807d279589e955892d45b77b0d5724a1fec9c8b2f99c2362d712d54
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:776fd5cb7ccdc8f9f8192eb3b96c529049ae49b8a7dcf9d127b5de47954ef5fb
+oid sha256:3061a8a95789ebdcd80feb9608794594df99627b54597f9d58af0df174ca2544
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:78de5a81f027f75bc277d68d3e9125ef909afdb1951bb0ceab4adbe2ecd7a878
+oid sha256:f0588bf34645d26f6e8c08f4a580782a5d4563cdeb5d1e1b24b44813709cbce7
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7238e77cfb3adb05bd2aa4ecf9e15dd956e20f7c57a862cebf274e47b32e5856
+oid sha256:732a48f706fdd94d1435d60e75f2cfafc3dbe48fa457c175d401e569639c114a
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df19ed1a9610a5422497073697cbf4575f80de47fbb46ef0cdd2779386b031fa
+oid sha256:a5b53655d80c3ade692dacae57cafa4aff84c325b5cb8d0fba89d01b50d41566
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.6646984219551086,
-  "best_model_checkpoint": "miner_id_24/checkpoint-50",
-  "epoch": 0.061597690086621755,
+  "best_metric": 0.617424488067627,
+  "best_model_checkpoint": "miner_id_24/checkpoint-75",
+  "epoch": 0.09239653512993262,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 14.235,
       "eval_steps_per_second": 3.701,
       "step": 50
+    },
+    {
+      "epoch": 0.06282964388835419,
+      "grad_norm": 0.8724278807640076,
+      "learning_rate": 5.192909139858981e-05,
+      "loss": 0.69,
+      "step": 51
+    },
+    {
+      "epoch": 0.06406159769008662,
+      "grad_norm": 0.9073512554168701,
+      "learning_rate": 5.0398113297608465e-05,
+      "loss": 0.6701,
+      "step": 52
+    },
+    {
+      "epoch": 0.06529355149181906,
+      "grad_norm": 0.8863846659660339,
+      "learning_rate": 4.887250079066892e-05,
+      "loss": 0.6345,
+      "step": 53
+    },
+    {
+      "epoch": 0.06652550529355149,
+      "grad_norm": 0.8188042044639587,
+      "learning_rate": 4.7354032673710005e-05,
+      "loss": 0.6611,
+      "step": 54
+    },
+    {
+      "epoch": 0.06775745909528393,
+      "grad_norm": 0.7507838606834412,
+      "learning_rate": 4.584447941263149e-05,
+      "loss": 0.6475,
+      "step": 55
+    },
+    {
+      "epoch": 0.06898941289701636,
+      "grad_norm": 0.7349779605865479,
+      "learning_rate": 4.43456010790099e-05,
+      "loss": 0.6515,
+      "step": 56
+    },
+    {
+      "epoch": 0.0702213666987488,
+      "grad_norm": 0.7216666340827942,
+      "learning_rate": 4.285914529793391e-05,
+      "loss": 0.64,
+      "step": 57
+    },
+    {
+      "epoch": 0.07145332050048123,
+      "grad_norm": 0.8082278966903687,
+      "learning_rate": 4.13868452103516e-05,
+      "loss": 0.664,
+      "step": 58
+    },
+    {
+      "epoch": 0.07268527430221366,
+      "grad_norm": 0.80323326587677,
+      "learning_rate": 3.9930417452305626e-05,
+      "loss": 0.6373,
+      "step": 59
+    },
+    {
+      "epoch": 0.0739172281039461,
+      "grad_norm": 0.9069752097129822,
+      "learning_rate": 3.8491560153412466e-05,
+      "loss": 0.6496,
+      "step": 60
+    },
+    {
+      "epoch": 0.07514918190567854,
+      "grad_norm": 0.8475314378738403,
+      "learning_rate": 3.707195095691913e-05,
+      "loss": 0.6553,
+      "step": 61
+    },
+    {
+      "epoch": 0.07638113570741097,
+      "grad_norm": 0.9898352026939392,
+      "learning_rate": 3.567324506364632e-05,
+      "loss": 0.7292,
+      "step": 62
+    },
+    {
+      "epoch": 0.0776130895091434,
+      "grad_norm": 0.7595363259315491,
+      "learning_rate": 3.4297073302098156e-05,
+      "loss": 0.6807,
+      "step": 63
+    },
+    {
+      "epoch": 0.07884504331087584,
+      "grad_norm": 0.781152069568634,
+      "learning_rate": 3.2945040226989244e-05,
+      "loss": 0.5905,
+      "step": 64
+    },
+    {
+      "epoch": 0.08007699711260828,
+      "grad_norm": 0.7119630575180054,
+      "learning_rate": 3.16187222484055e-05,
+      "loss": 0.6144,
+      "step": 65
+    },
+    {
+      "epoch": 0.08130895091434072,
+      "grad_norm": 0.7199792861938477,
+      "learning_rate": 3.0319665793780648e-05,
+      "loss": 0.6314,
+      "step": 66
+    },
+    {
+      "epoch": 0.08254090471607314,
+      "grad_norm": 0.8011656999588013,
+      "learning_rate": 2.9049385504830985e-05,
+      "loss": 0.5818,
+      "step": 67
+    },
+    {
+      "epoch": 0.08377285851780558,
+      "grad_norm": 0.7348117232322693,
+      "learning_rate": 2.7809362471550748e-05,
+      "loss": 0.6245,
+      "step": 68
+    },
+    {
+      "epoch": 0.08500481231953802,
+      "grad_norm": 0.7128881812095642,
+      "learning_rate": 2.660104250532764e-05,
+      "loss": 0.6185,
+      "step": 69
+    },
+    {
+      "epoch": 0.08623676612127046,
+      "grad_norm": 0.7044535875320435,
+      "learning_rate": 2.5425834453191232e-05,
+      "loss": 0.6437,
+      "step": 70
+    },
+    {
+      "epoch": 0.08746871992300288,
+      "grad_norm": 0.7829747200012207,
+      "learning_rate": 2.4285108555160577e-05,
+      "loss": 0.6293,
+      "step": 71
+    },
+    {
+      "epoch": 0.08870067372473532,
+      "grad_norm": 0.746275007724762,
+      "learning_rate": 2.3180194846605367e-05,
+      "loss": 0.6268,
+      "step": 72
+    },
+    {
+      "epoch": 0.08993262752646776,
+      "grad_norm": 0.7758780717849731,
+      "learning_rate": 2.2112381607484417e-05,
+      "loss": 0.636,
+      "step": 73
+    },
+    {
+      "epoch": 0.0911645813282002,
+      "grad_norm": 0.7950238585472107,
+      "learning_rate": 2.1082913860268765e-05,
+      "loss": 0.647,
+      "step": 74
+    },
+    {
+      "epoch": 0.09239653512993262,
+      "grad_norm": 0.9090643525123596,
+      "learning_rate": 2.0092991918301108e-05,
+      "loss": 0.665,
+      "step": 75
+    },
+    {
+      "epoch": 0.09239653512993262,
+      "eval_loss": 0.617424488067627,
+      "eval_runtime": 3.5324,
+      "eval_samples_per_second": 14.155,
+      "eval_steps_per_second": 3.68,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -409,7 +592,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.968083617316864e+17,
+  "total_flos": 8.952125425975296e+17,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null