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:fac543db80284db183008621b2805d772e91b61385765eeafde175dd0e12c9f3
+oid sha256:4e13a0e2ae508cedf1b8ed32383da4f09bef3653dec02a29686e14082bdb0f1e
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3ae8a1de89805f5ec8c41ab59fb28054e8babb15a30b0ba0d6834ae8798141a
+oid sha256:ed3c4ab884196b40596967ca167c41f3ded3c58692d1c6f0b73eca81637275a3
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:23eabadc316fcb4b7ace4f7417db2ceb8fc167af667166d434363c0811477327
+oid sha256:26739fd615a64b3e653015dc0faa9f5d5cba9b577ffbabf30277e45f9819cd60
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e02abf5f069e2dc4a8b2e4b8b6b0f5fd591dee8708b159258ae1ac268d75079d
+oid sha256:dae65c945cd225192d787283629e7fbdceacfc9089f9bb525ae1dc1a4f5c4070
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0bef1d8dc3d01fa27dc93a481a6d4899467c7a35c2db71c493ed1e568e0efb
+oid sha256:0683d0c3795d34174ff7ea703bd4e0f26e66c7bd27b05a729caabf24c9b998fa
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b83ddab9a7eed8bfcae91b6dc6cc36eee2c55e9de6fb96b1ae2ca687ebde22d1
+oid sha256:485d51ca3effef4393f9de31815a03a3640ef184d84a00294772c482651b2d5e
 size 15024

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37b2aa490ccb1598b01e14cda36e9081f7ce646deab4d3c2d03de0d2169a755
+oid sha256:b1df0528620c07325b8faa7567e59b0c1e86a1f1ee6af1245a69c6c0463fe4e2
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
-  "best_metric": 0.7933292388916016,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.06325110689437065,
+  "best_metric": 0.7669674754142761,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1265022137887413,
   "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": 14.91,
       "eval_steps_per_second": 1.864,
       "step": 25
+    },
+    {
+      "epoch": 0.06578115117014548,
+      "grad_norm": 0.3085412085056305,
+      "learning_rate": 5e-05,
+      "loss": 0.5028,
+      "step": 26
+    },
+    {
+      "epoch": 0.0683111954459203,
+      "grad_norm": 0.4568122923374176,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.709,
+      "step": 27
+    },
+    {
+      "epoch": 0.07084123972169513,
+      "grad_norm": 0.4451022148132324,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.7108,
+      "step": 28
+    },
+    {
+      "epoch": 0.07337128399746995,
+      "grad_norm": 0.44292229413986206,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.7233,
+      "step": 29
+    },
+    {
+      "epoch": 0.07590132827324478,
+      "grad_norm": 0.5089272856712341,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7952,
+      "step": 30
+    },
+    {
+      "epoch": 0.0784313725490196,
+      "grad_norm": 0.4563312828540802,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.7415,
+      "step": 31
+    },
+    {
+      "epoch": 0.08096141682479444,
+      "grad_norm": 0.4483792185783386,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.7205,
+      "step": 32
+    },
+    {
+      "epoch": 0.08349146110056926,
+      "grad_norm": 0.48972287774086,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.7487,
+      "step": 33
+    },
+    {
+      "epoch": 0.08602150537634409,
+      "grad_norm": 0.5764914751052856,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.8205,
+      "step": 34
+    },
+    {
+      "epoch": 0.08855154965211891,
+      "grad_norm": 0.710080087184906,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.7891,
+      "step": 35
+    },
+    {
+      "epoch": 0.09108159392789374,
+      "grad_norm": 0.8010451197624207,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.8268,
+      "step": 36
+    },
+    {
+      "epoch": 0.09361163820366857,
+      "grad_norm": 1.0116633176803589,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.8728,
+      "step": 37
+    },
+    {
+      "epoch": 0.0961416824794434,
+      "grad_norm": 0.4091106057167053,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.5207,
+      "step": 38
+    },
+    {
+      "epoch": 0.09867172675521822,
+      "grad_norm": 0.2687011957168579,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.5985,
+      "step": 39
+    },
+    {
+      "epoch": 0.10120177103099304,
+      "grad_norm": 0.30941206216812134,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6427,
+      "step": 40
+    },
+    {
+      "epoch": 0.10373181530676787,
+      "grad_norm": 0.3291284441947937,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.6819,
+      "step": 41
+    },
+    {
+      "epoch": 0.1062618595825427,
+      "grad_norm": 0.3654635548591614,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.7387,
+      "step": 42
+    },
+    {
+      "epoch": 0.10879190385831752,
+      "grad_norm": 0.37484773993492126,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.7585,
+      "step": 43
+    },
+    {
+      "epoch": 0.11132194813409235,
+      "grad_norm": 0.39777594804763794,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.7547,
+      "step": 44
+    },
+    {
+      "epoch": 0.11385199240986717,
+      "grad_norm": 0.4498005509376526,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.7332,
+      "step": 45
+    },
+    {
+      "epoch": 0.116382036685642,
+      "grad_norm": 0.4953252077102661,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.7556,
+      "step": 46
+    },
+    {
+      "epoch": 0.11891208096141682,
+      "grad_norm": 0.5951145887374878,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.7668,
+      "step": 47
+    },
+    {
+      "epoch": 0.12144212523719165,
+      "grad_norm": 0.7458454966545105,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.828,
+      "step": 48
+    },
+    {
+      "epoch": 0.12397216951296648,
+      "grad_norm": 0.9640898704528809,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.9184,
+      "step": 49
+    },
+    {
+      "epoch": 0.1265022137887413,
+      "grad_norm": 1.3981536626815796,
+      "learning_rate": 0.0,
+      "loss": 1.0085,
+      "step": 50
+    },
+    {
+      "epoch": 0.1265022137887413,
+      "eval_loss": 0.7669674754142761,
+      "eval_runtime": 176.9953,
+      "eval_samples_per_second": 15.046,
+      "eval_steps_per_second": 1.881,
+      "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": 2.9139466216852685e+17,
+  "total_flos": 5.833339884672123e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null