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:e3857b703d635ad73e0d3e0f236ef4127ac83f129fdb25e9244696189587ad42
+oid sha256:4e3bc2cb4edc9ad628d5766cdfef0ac0906d9583a55392f4e9f9b0d603618aa3
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7bc37663437f4e48c400d3093a6157b6cc6a9abe4a999e8a92ed88c0c0e465d3
+oid sha256:472a162654435990d72955e0d55752df4e5ec1d18de5f8d03d0108a890f62445
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ca11e4c51e511f5acc0358d5b3001af0b5c75dbc1da9661940648baea0a9038
+oid sha256:91a3240c35f52202e508ce28e9f63e13e21fd02136bf5ee0a3e8d3040ff966da
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a4970237d6885d5de64cb868dd24bad0b86bd89af1b2bacc45ce04df821239b
+oid sha256:46c4ab7e74327a838a32830332ca6c2678b695231ec7447fa57bb466da58606f
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b4d68a5b84a10d393a6509025a9c854cc74b0e58f66aebc93097413cc1c5fac8
+oid sha256:93487d57fc6dd258f77ae0d3c893540a510b5c26d284f0b34e4fe13b0b64f4e4
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4c93cad948a75d382a259939de454957972a5553dcaae1507958728eebd150e
+oid sha256:045dd3055e3e4c76480d694f9d29966c8972305c3298b337027d4e4b63bda3be
 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": 0.45366477966308594,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.011250492209034145,
+  "best_metric": 0.44486159086227417,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.02250098441806829,
   "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": 32.788,
       "eval_steps_per_second": 4.1,
       "step": 25
+    },
+    {
+      "epoch": 0.01170051189739551,
+      "grad_norm": 3.5797367095947266,
+      "learning_rate": 5e-05,
+      "loss": 0.3567,
+      "step": 26
+    },
+    {
+      "epoch": 0.012150531585756876,
+      "grad_norm": 4.528767108917236,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.4475,
+      "step": 27
+    },
+    {
+      "epoch": 0.012600551274118243,
+      "grad_norm": 4.389427661895752,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4494,
+      "step": 28
+    },
+    {
+      "epoch": 0.013050570962479609,
+      "grad_norm": 4.565876007080078,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4593,
+      "step": 29
+    },
+    {
+      "epoch": 0.013500590650840975,
+      "grad_norm": 4.244178771972656,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.433,
+      "step": 30
+    },
+    {
+      "epoch": 0.01395061033920234,
+      "grad_norm": 4.859099388122559,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4386,
+      "step": 31
+    },
+    {
+      "epoch": 0.014400630027563706,
+      "grad_norm": 4.869718551635742,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.472,
+      "step": 32
+    },
+    {
+      "epoch": 0.014850649715925071,
+      "grad_norm": 5.395300388336182,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4698,
+      "step": 33
+    },
+    {
+      "epoch": 0.015300669404286437,
+      "grad_norm": 6.101658344268799,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.443,
+      "step": 34
+    },
+    {
+      "epoch": 0.015750689092647804,
+      "grad_norm": 5.844554901123047,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4324,
+      "step": 35
+    },
+    {
+      "epoch": 0.016200708781009168,
+      "grad_norm": 6.385544300079346,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4312,
+      "step": 36
+    },
+    {
+      "epoch": 0.016650728469370536,
+      "grad_norm": 7.2580461502075195,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4674,
+      "step": 37
+    },
+    {
+      "epoch": 0.0171007481577319,
+      "grad_norm": 6.991725444793701,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.4949,
+      "step": 38
+    },
+    {
+      "epoch": 0.017550767846093267,
+      "grad_norm": 3.6845273971557617,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.4213,
+      "step": 39
+    },
+    {
+      "epoch": 0.018000787534454634,
+      "grad_norm": 4.191789627075195,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4935,
+      "step": 40
+    },
+    {
+      "epoch": 0.018450807222815998,
+      "grad_norm": 5.070094108581543,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.4547,
+      "step": 41
+    },
+    {
+      "epoch": 0.018900826911177365,
+      "grad_norm": 4.569336414337158,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4384,
+      "step": 42
+    },
+    {
+      "epoch": 0.01935084659953873,
+      "grad_norm": 4.306663513183594,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.4513,
+      "step": 43
+    },
+    {
+      "epoch": 0.019800866287900096,
+      "grad_norm": 4.363531589508057,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4405,
+      "step": 44
+    },
+    {
+      "epoch": 0.02025088597626146,
+      "grad_norm": 4.676458358764648,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4528,
+      "step": 45
+    },
+    {
+      "epoch": 0.020700905664622828,
+      "grad_norm": 4.858545780181885,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4823,
+      "step": 46
+    },
+    {
+      "epoch": 0.02115092535298419,
+      "grad_norm": 5.037557125091553,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4299,
+      "step": 47
+    },
+    {
+      "epoch": 0.02160094504134556,
+      "grad_norm": 5.234649658203125,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.4471,
+      "step": 48
+    },
+    {
+      "epoch": 0.022050964729706926,
+      "grad_norm": 5.939426422119141,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4684,
+      "step": 49
+    },
+    {
+      "epoch": 0.02250098441806829,
+      "grad_norm": 7.509469509124756,
+      "learning_rate": 0.0,
+      "loss": 0.5282,
+      "step": 50
+    },
+    {
+      "epoch": 0.02250098441806829,
+      "eval_loss": 0.44486159086227417,
+      "eval_runtime": 459.9762,
+      "eval_samples_per_second": 32.545,
+      "eval_steps_per_second": 4.07,
+      "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": 2.8443988497688166e+17,
+  "total_flos": 5.6941044108047155e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null