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:a551626f5eabecd06c5791301739011fc13bca4d6ed5ed4fab05b14b7df153ae
+oid sha256:9a3c2ec4a4b786d682196abdcdbdcbebcbc1a31733cbc7797384a77aca468d28
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b9a6a53f0b1fac788dc6c5d6c19e8e92aa8c3c42c64b74de1a7671c784684c4c
+oid sha256:44316396d34f45592819eec57ea7b04d36b643e5e0699ad373243283e6471d01
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5404d668cba383cf2f08b4464c5679cd746fe16ecb0e3b1bb7046f53e3bcf57e
+oid sha256:f76f29d524b085b543d9a52a9675384ce38c9cf0abf91d43afd1a64a0f3b8be7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3037474aff2ca3c49dd4e94c24d101efa1ee7c0a81af2db4878d382c7619f781
+oid sha256:53ec46509a6e08f0535c2fa1d95afe7ab164f02b3e5d22180649fc3a818a699e
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:117c45337d1c86473ebb3bca43cc2cd3f16957ec506f68b52588cf553187bbaf
+oid sha256:a1a9ff02d70d62c377030a7b7602e45b6cf03744fc1cc9f1b65afdeb54e6c1c2
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f398f6c1aabac0f6a077a9e9f849fafebc6750c9249b1abbcdf56ae64ba35fe3
+oid sha256:c6743151550d73442b447ab0e37d9125c0b049cf3565a606bafaef497bd556f1
 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": 1.3367341756820679,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.35650623885918004,
+  "best_metric": 1.2739750146865845,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.7130124777183601,
   "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": 34.391,
       "eval_steps_per_second": 4.362,
       "step": 25
+    },
+    {
+      "epoch": 0.37076648841354726,
+      "grad_norm": 0.8801906704902649,
+      "learning_rate": 5e-05,
+      "loss": 1.5095,
+      "step": 26
+    },
+    {
+      "epoch": 0.3850267379679144,
+      "grad_norm": 0.9089639186859131,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.5273,
+      "step": 27
+    },
+    {
+      "epoch": 0.39928698752228164,
+      "grad_norm": 0.7997736930847168,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4282,
+      "step": 28
+    },
+    {
+      "epoch": 0.41354723707664887,
+      "grad_norm": 0.7313483953475952,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3141,
+      "step": 29
+    },
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": 0.647161602973938,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.2967,
+      "step": 30
+    },
+    {
+      "epoch": 0.44206773618538325,
+      "grad_norm": 0.634042501449585,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.295,
+      "step": 31
+    },
+    {
+      "epoch": 0.4563279857397504,
+      "grad_norm": 0.6881169080734253,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.3276,
+      "step": 32
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.7702770233154297,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.323,
+      "step": 33
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.8563191890716553,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.2778,
+      "step": 34
+    },
+    {
+      "epoch": 0.49910873440285203,
+      "grad_norm": 0.9157997965812683,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2706,
+      "step": 35
+    },
+    {
+      "epoch": 0.5133689839572193,
+      "grad_norm": 0.9603651165962219,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.273,
+      "step": 36
+    },
+    {
+      "epoch": 0.5276292335115864,
+      "grad_norm": 1.0942834615707397,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.1878,
+      "step": 37
+    },
+    {
+      "epoch": 0.5418894830659536,
+      "grad_norm": 0.7016259431838989,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.4631,
+      "step": 38
+    },
+    {
+      "epoch": 0.5561497326203209,
+      "grad_norm": 0.6480449438095093,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4078,
+      "step": 39
+    },
+    {
+      "epoch": 0.5704099821746881,
+      "grad_norm": 0.6285794377326965,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.3957,
+      "step": 40
+    },
+    {
+      "epoch": 0.5846702317290553,
+      "grad_norm": 0.6484659910202026,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.338,
+      "step": 41
+    },
+    {
+      "epoch": 0.5989304812834224,
+      "grad_norm": 0.6326348781585693,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.3341,
+      "step": 42
+    },
+    {
+      "epoch": 0.6131907308377896,
+      "grad_norm": 0.6208999156951904,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2645,
+      "step": 43
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 0.6368456482887268,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.248,
+      "step": 44
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 0.6965120434761047,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.3331,
+      "step": 45
+    },
+    {
+      "epoch": 0.6559714795008913,
+      "grad_norm": 0.6685178875923157,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2342,
+      "step": 46
+    },
+    {
+      "epoch": 0.6702317290552585,
+      "grad_norm": 0.718367874622345,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.265,
+      "step": 47
+    },
+    {
+      "epoch": 0.6844919786096256,
+      "grad_norm": 0.7094207406044006,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.2124,
+      "step": 48
+    },
+    {
+      "epoch": 0.6987522281639929,
+      "grad_norm": 0.8180119395256042,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.1806,
+      "step": 49
+    },
+    {
+      "epoch": 0.7130124777183601,
+      "grad_norm": 1.0620092153549194,
+      "learning_rate": 0.0,
+      "loss": 1.1791,
+      "step": 50
+    },
+    {
+      "epoch": 0.7130124777183601,
+      "eval_loss": 1.2739750146865845,
+      "eval_runtime": 13.738,
+      "eval_samples_per_second": 34.43,
+      "eval_steps_per_second": 4.367,
+      "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": 2.984041808658432e+17,
+  "total_flos": 5.968083617316864e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null