Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4645a70192715fd91375d98af95fa96e17d1afbbfaf6addd7b157e91189bac11
+oid sha256:6c3a110ea343f7a6dd5d29544f26907c9421e3633fa1e954df0d2d86b83c4d42
 size 319876032

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:883f06aff4f98c0cc5bafbeb93fc16547ca5347cee29d305ab49078a26ff86ff
+oid sha256:c7c1a5ab4baed7fbdd10e8da582ce330ee6948c30b2501b379ce0300f0de13b2
 size 640009682

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e2396be98c86caa758e4c49be9224643a471958a324f026d8c113232e4d7d087
+oid sha256:89e692ce16d84166344cd49d0257383aedf8dee1163462903cb1e8014fbaa830
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f1278791f9eefeb7e32b2e40be5f8d6758449faf2dacc78b1df82de8a08a92
+oid sha256:fa8f1f9b7a4922e25d1076ec01ee5af3c55a794014d8136572727d92b374a454
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bc24ba966eb73b37f23b1de3b17d4cb338c4f7001354e1323aaa492a1e424fa9
+oid sha256:b203d0ba838d26fba2f460724682e614b4d34076bc8ad17cb9d55d46a0795a90
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:420949172d577bf3cb3d6e299557be63f256def87b3acdc7194406e457ade773
+oid sha256:881e8fe7aace17e9356447b697c1bd4066404ae598974dc60d24ddf3920d9355
 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": 0.0004589141171891242,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05942653394740752,
+  "best_metric": 0.00014307092351373285,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11885306789481503,
   "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": 41.721,
       "eval_steps_per_second": 5.226,
       "step": 25
+    },
+    {
+      "epoch": 0.06180359530530382,
+      "grad_norm": 0.5359752178192139,
+      "learning_rate": 5e-05,
+      "loss": 0.0032,
+      "step": 26
+    },
+    {
+      "epoch": 0.06418065666320012,
+      "grad_norm": 0.013400775380432606,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.0005,
+      "step": 27
+    },
+    {
+      "epoch": 0.06655771802109642,
+      "grad_norm": 0.19051715731620789,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.0026,
+      "step": 28
+    },
+    {
+      "epoch": 0.06893477937899271,
+      "grad_norm": 0.01478293351829052,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.0006,
+      "step": 29
+    },
+    {
+      "epoch": 0.07131184073688902,
+      "grad_norm": 0.016781041398644447,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.0007,
+      "step": 30
+    },
+    {
+      "epoch": 0.07368890209478532,
+      "grad_norm": 0.8415308594703674,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.005,
+      "step": 31
+    },
+    {
+      "epoch": 0.07606596345268163,
+      "grad_norm": 0.009778022766113281,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.0004,
+      "step": 32
+    },
+    {
+      "epoch": 0.07844302481057792,
+      "grad_norm": 0.013184771873056889,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.0004,
+      "step": 33
+    },
+    {
+      "epoch": 0.08082008616847422,
+      "grad_norm": 0.011009763926267624,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.0004,
+      "step": 34
+    },
+    {
+      "epoch": 0.08319714752637053,
+      "grad_norm": 0.015330126509070396,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.0006,
+      "step": 35
+    },
+    {
+      "epoch": 0.08557420888426683,
+      "grad_norm": 0.015668345615267754,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.0005,
+      "step": 36
+    },
+    {
+      "epoch": 0.08795127024216312,
+      "grad_norm": 0.0042808507569134235,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.0003,
+      "step": 37
+    },
+    {
+      "epoch": 0.09032833160005943,
+      "grad_norm": 0.07753123342990875,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.0009,
+      "step": 38
+    },
+    {
+      "epoch": 0.09270539295795573,
+      "grad_norm": 0.010145001113414764,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.0006,
+      "step": 39
+    },
+    {
+      "epoch": 0.09508245431585202,
+      "grad_norm": 16.53394889831543,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.0323,
+      "step": 40
+    },
+    {
+      "epoch": 0.09745951567374833,
+      "grad_norm": 0.01686001382768154,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.0005,
+      "step": 41
+    },
+    {
+      "epoch": 0.09983657703164463,
+      "grad_norm": 0.028522521257400513,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.0007,
+      "step": 42
+    },
+    {
+      "epoch": 0.10221363838954094,
+      "grad_norm": 0.03315084055066109,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.0005,
+      "step": 43
+    },
+    {
+      "epoch": 0.10459069974743723,
+      "grad_norm": 0.019801389425992966,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.0006,
+      "step": 44
+    },
+    {
+      "epoch": 0.10696776110533353,
+      "grad_norm": 0.06491321325302124,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.0006,
+      "step": 45
+    },
+    {
+      "epoch": 0.10934482246322984,
+      "grad_norm": 0.006896046455949545,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.0003,
+      "step": 46
+    },
+    {
+      "epoch": 0.11172188382112613,
+      "grad_norm": 1.4069654941558838,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.017,
+      "step": 47
+    },
+    {
+      "epoch": 0.11409894517902243,
+      "grad_norm": 0.004831578582525253,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.0004,
+      "step": 48
+    },
+    {
+      "epoch": 0.11647600653691874,
+      "grad_norm": 0.0032711592502892017,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.0003,
+      "step": 49
+    },
+    {
+      "epoch": 0.11885306789481503,
+      "grad_norm": 0.004975167568773031,
+      "learning_rate": 0.0,
+      "loss": 0.0003,
+      "step": 50
+    },
+    {
+      "epoch": 0.11885306789481503,
+      "eval_loss": 0.00014307092351373285,
+      "eval_runtime": 67.8913,
+      "eval_samples_per_second": 41.743,
+      "eval_steps_per_second": 5.229,
+      "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": 2.629578157719552e+17,
+  "total_flos": 5.259156315439104e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null