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:d12c9ecc4f3c63d1f79716704df4bc09f7e37406841f930ac73d4966c17170de
+oid sha256:35eb778b986caa859e687812959ae08f9dbf75216295a7dcbda141fac6ce985a
 size 203456160

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cf3b7dbe961de5db76832f326810eafbeb9ea98a5242f399555d4a743bbccb0
+oid sha256:5793764aaa8ce9a690b547afc658221c35a0c6dc4e9341e77b4c05e5a61cd9c3
 size 407121750

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:411a05201088fddfe6513ebb90b9270310cf41bc1a9c86184c4553bd46aafbb1
+oid sha256:64bf932cbb2433952b5fc789cfa29c0f9d9c2cda1260a59e75bb879bf8081c35
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:58b6a26382703e17f462a4948e7caf707e5c52547bc9678ea971625237ac495a
+oid sha256:685c932da790878bdaf790bdb8689fd8a3507e3cc0fd68166199b58f63c97bab
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a8453a6222913d082350a11a9917532017531244c90a7b7d4683279b6025535
+oid sha256:ab0cfd1f4e28c0a639c9a3b574c3faf9ce6b12a11858a723c3a6712443af6d46
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:807bf872d1eea5b5a4ef239df16fd49933621d2e0cd2c3ade8536bc1a5747232
+oid sha256:054ba1ee7fed9d03f1678dd1fc5afcde8853667cda1d7572cccc5108b6e1482d
 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": 0.707122802734375,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 1.2121212121212122,
+  "best_metric": 0.6839619874954224,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 2.4242424242424243,
   "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": 42.104,
       "eval_steps_per_second": 5.452,
       "step": 25
+    },
+    {
+      "epoch": 1.2606060606060607,
+      "grad_norm": 0.8380623459815979,
+      "learning_rate": 5e-05,
+      "loss": 0.639,
+      "step": 26
+    },
+    {
+      "epoch": 1.309090909090909,
+      "grad_norm": 0.732282817363739,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.6241,
+      "step": 27
+    },
+    {
+      "epoch": 1.3575757575757577,
+      "grad_norm": 0.7353828549385071,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.6116,
+      "step": 28
+    },
+    {
+      "epoch": 1.406060606060606,
+      "grad_norm": 0.8748971819877625,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.6333,
+      "step": 29
+    },
+    {
+      "epoch": 1.4545454545454546,
+      "grad_norm": 1.0290173292160034,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.7567,
+      "step": 30
+    },
+    {
+      "epoch": 1.503030303030303,
+      "grad_norm": 0.7504650354385376,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.641,
+      "step": 31
+    },
+    {
+      "epoch": 1.5515151515151515,
+      "grad_norm": 0.6707954406738281,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.5967,
+      "step": 32
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.8035198450088501,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.6397,
+      "step": 33
+    },
+    {
+      "epoch": 1.6484848484848484,
+      "grad_norm": 1.0750758647918701,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.7201,
+      "step": 34
+    },
+    {
+      "epoch": 1.696969696969697,
+      "grad_norm": 0.8901678919792175,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.6931,
+      "step": 35
+    },
+    {
+      "epoch": 1.7454545454545456,
+      "grad_norm": 0.808151364326477,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.6304,
+      "step": 36
+    },
+    {
+      "epoch": 1.793939393939394,
+      "grad_norm": 0.800571858882904,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.6342,
+      "step": 37
+    },
+    {
+      "epoch": 1.8424242424242423,
+      "grad_norm": 0.732184112071991,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.6579,
+      "step": 38
+    },
+    {
+      "epoch": 1.8909090909090909,
+      "grad_norm": 0.8361778855323792,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.6471,
+      "step": 39
+    },
+    {
+      "epoch": 1.9393939393939394,
+      "grad_norm": 1.0458678007125854,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.6809,
+      "step": 40
+    },
+    {
+      "epoch": 1.9878787878787878,
+      "grad_norm": 1.5578941106796265,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.7013,
+      "step": 41
+    },
+    {
+      "epoch": 2.036363636363636,
+      "grad_norm": 0.7779700756072998,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.6391,
+      "step": 42
+    },
+    {
+      "epoch": 2.084848484848485,
+      "grad_norm": 0.8941618204116821,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.5834,
+      "step": 43
+    },
+    {
+      "epoch": 2.1333333333333333,
+      "grad_norm": 0.9314845204353333,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.5874,
+      "step": 44
+    },
+    {
+      "epoch": 2.1818181818181817,
+      "grad_norm": 1.1137163639068604,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.6653,
+      "step": 45
+    },
+    {
+      "epoch": 2.2303030303030305,
+      "grad_norm": 1.257054090499878,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.5913,
+      "step": 46
+    },
+    {
+      "epoch": 2.278787878787879,
+      "grad_norm": 0.7937349677085876,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4917,
+      "step": 47
+    },
+    {
+      "epoch": 2.327272727272727,
+      "grad_norm": 0.9872217774391174,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.6183,
+      "step": 48
+    },
+    {
+      "epoch": 2.375757575757576,
+      "grad_norm": 0.9808546304702759,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.5957,
+      "step": 49
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "grad_norm": 1.1789116859436035,
+      "learning_rate": 0.0,
+      "loss": 0.6563,
+      "step": 50
+    },
+    {
+      "epoch": 2.4242424242424243,
+      "eval_loss": 0.6839619874954224,
+      "eval_runtime": 3.3023,
+      "eval_samples_per_second": 42.092,
+      "eval_steps_per_second": 5.451,
+      "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": 1.327074698592256e+17,
+  "total_flos": 2.654149397184512e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null