Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:76de05868119282f294c4308e929d8fa397ec95c43bc7f58c1ae41679447a18c
+oid sha256:3ab8e1026b6d9b19a38ede103038c39b0bf2de5340598a3e4f8d33a92be0660f
 size 70430032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5ab42fb37e0f6cb0b7d3950ebd7defaf7f347e00dee828de8975012f6a8142a5
+oid sha256:3a4a35e84099827f3c89ce8ce7a069cab440163a46df8ba580862650d31f6a58
 size 141053442

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f0faae5b8b22e50797059a1efc3f7990b8022a1909ecb1793699dd2e91bcba
+oid sha256:46342187f4dc75c9e6c39a7b1878f43e0ec716b87dd40a756912014fb7ab4fe0
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6f7d3c581dec20c2d3cf2e53a92b7aac68e8d7e6f0e6bbe328ef5cfb93d519b
+oid sha256:465716345b10469c5253861a2558865d7131ff7c526453a498941870d32e3baa
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c536cb67fa848be4a5a4f4c90ef69a306a2e02d2e814a55ce472c5c40f87bacc
+oid sha256:8647dbf034b9ef56d9c9724cba9f0dc9efe2ec86060c11c290af874fcb737722
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4588c484fddacc3a16dba0daaa2ff946e376af439352880a42cf840893baf7d6
+oid sha256:2528df0f1c0d578da727283d5c1a0808f95ecc1dbeefb25dcf5ab37d8b6f0256
 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": 3.268176555633545,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.09918175055789735,
+  "best_metric": 3.2202842235565186,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.1983635011157947,
   "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": 147.024,
       "eval_steps_per_second": 18.432,
       "step": 25
+    },
+    {
+      "epoch": 0.10314902058021325,
+      "grad_norm": 0.9733558893203735,
+      "learning_rate": 5e-05,
+      "loss": 3.2624,
+      "step": 26
+    },
+    {
+      "epoch": 0.10711629060252914,
+      "grad_norm": 1.166012167930603,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.1748,
+      "step": 27
+    },
+    {
+      "epoch": 0.11108356062484503,
+      "grad_norm": 1.3410450220108032,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.2613,
+      "step": 28
+    },
+    {
+      "epoch": 0.11505083064716093,
+      "grad_norm": 1.3012003898620605,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.2793,
+      "step": 29
+    },
+    {
+      "epoch": 0.11901810066947682,
+      "grad_norm": 1.0508790016174316,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.2646,
+      "step": 30
+    },
+    {
+      "epoch": 0.12298537069179272,
+      "grad_norm": 0.9772084355354309,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.2421,
+      "step": 31
+    },
+    {
+      "epoch": 0.1269526407141086,
+      "grad_norm": 0.8641189932823181,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.2449,
+      "step": 32
+    },
+    {
+      "epoch": 0.1309199107364245,
+      "grad_norm": 0.8817277550697327,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.3813,
+      "step": 33
+    },
+    {
+      "epoch": 0.1348871807587404,
+      "grad_norm": 0.8557921648025513,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.2187,
+      "step": 34
+    },
+    {
+      "epoch": 0.1388544507810563,
+      "grad_norm": 0.9797968864440918,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.2734,
+      "step": 35
+    },
+    {
+      "epoch": 0.1428217208033722,
+      "grad_norm": 0.9896147847175598,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 3.2438,
+      "step": 36
+    },
+    {
+      "epoch": 0.14678899082568808,
+      "grad_norm": 1.0835036039352417,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 3.3002,
+      "step": 37
+    },
+    {
+      "epoch": 0.15075626084800398,
+      "grad_norm": 0.842976987361908,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.2495,
+      "step": 38
+    },
+    {
+      "epoch": 0.15472353087031987,
+      "grad_norm": 0.6773706078529358,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.2503,
+      "step": 39
+    },
+    {
+      "epoch": 0.15869080089263576,
+      "grad_norm": 0.5887467861175537,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.2258,
+      "step": 40
+    },
+    {
+      "epoch": 0.16265807091495166,
+      "grad_norm": 0.5568850040435791,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.1648,
+      "step": 41
+    },
+    {
+      "epoch": 0.16662534093726755,
+      "grad_norm": 0.5692043900489807,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.2207,
+      "step": 42
+    },
+    {
+      "epoch": 0.17059261095958345,
+      "grad_norm": 0.6383813619613647,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.2575,
+      "step": 43
+    },
+    {
+      "epoch": 0.17455988098189934,
+      "grad_norm": 0.6307452917098999,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.2423,
+      "step": 44
+    },
+    {
+      "epoch": 0.17852715100421523,
+      "grad_norm": 0.7243000268936157,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.2007,
+      "step": 45
+    },
+    {
+      "epoch": 0.18249442102653113,
+      "grad_norm": 0.846513032913208,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.2938,
+      "step": 46
+    },
+    {
+      "epoch": 0.18646169104884702,
+      "grad_norm": 0.951248824596405,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.3001,
+      "step": 47
+    },
+    {
+      "epoch": 0.19042896107116292,
+      "grad_norm": 0.9839473962783813,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.1855,
+      "step": 48
+    },
+    {
+      "epoch": 0.1943962310934788,
+      "grad_norm": 1.0755198001861572,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 3.1702,
+      "step": 49
+    },
+    {
+      "epoch": 0.1983635011157947,
+      "grad_norm": 1.5319169759750366,
+      "learning_rate": 0.0,
+      "loss": 3.2793,
+      "step": 50
+    },
+    {
+      "epoch": 0.1983635011157947,
+      "eval_loss": 3.2202842235565186,
+      "eval_runtime": 11.5549,
+      "eval_samples_per_second": 147.037,
+      "eval_steps_per_second": 18.434,
+      "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": 1.47650456322048e+16,
+  "total_flos": 2.95300912644096e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null