Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c0c501585fde058a002480888e32d1c3d21692836c3a94add3f70405a431bcd
+oid sha256:6b3ac0be360ec3a4734430daf21bebd3136f2f61ce5129dd12c035c6f784d34a
 size 147770496

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fcbdc0a3a32dfad0445de6c4137e5e67acd447ba3e85fb8a40d5fdea5cd95123
+oid sha256:459403051f759bd59cb63d5473e566647ade73493e7f5f106fd679177726a58e
 size 295765866

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4b343f6d1257c38df0118b0095b0a64d1ab76fcb60a235e3fa6dbff60a4bf416
+oid sha256:600ef0a699d177eba12b0d0a3d45bd1b59f3c786ffc3e2d6bba825af42b34906
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4932059fd7ed3f4264de4bd7b5cdd404f77b433cfd122b736793fbe3f4a127a3
+oid sha256:a5226a12cc9880cdd7b570b6ea5afa4c30d7647128d9c1836619056a7cdbffb7
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:960e82eb249553544674d59109b2c15873391b022e468a167d8ad71da9e8bff0
+oid sha256:2bae30b2eb90ea317e16b013a8f96f62874ca7092d7f01e78b868bffbcb7a094
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c2a3c75e943301dfd2218a6556f9c425795154256a175bae4cfcda5886e29686
+oid sha256:f54a2144b58a8a9f4ce3d0191673726af4f45c596764fddd2cc1e09c955f4726
 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": 1.1319423913955688,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.22573363431151242,
+  "best_metric": 1.1211003065109253,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.45146726862302483,
   "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": 37.061,
       "eval_steps_per_second": 4.67,
       "step": 25
+    },
+    {
+      "epoch": 0.23476297968397292,
+      "grad_norm": 0.3029966354370117,
+      "learning_rate": 5e-05,
+      "loss": 1.5864,
+      "step": 26
+    },
+    {
+      "epoch": 0.24379232505643342,
+      "grad_norm": 0.3005797266960144,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6568,
+      "step": 27
+    },
+    {
+      "epoch": 0.2528216704288939,
+      "grad_norm": 0.24547135829925537,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.4648,
+      "step": 28
+    },
+    {
+      "epoch": 0.2618510158013544,
+      "grad_norm": 0.19365021586418152,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.6744,
+      "step": 29
+    },
+    {
+      "epoch": 0.2708803611738149,
+      "grad_norm": 0.19894447922706604,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.4961,
+      "step": 30
+    },
+    {
+      "epoch": 0.2799097065462754,
+      "grad_norm": 0.2252543866634369,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.6705,
+      "step": 31
+    },
+    {
+      "epoch": 0.28893905191873587,
+      "grad_norm": 0.25827154517173767,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.5442,
+      "step": 32
+    },
+    {
+      "epoch": 0.2979683972911964,
+      "grad_norm": 0.2601383328437805,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.3812,
+      "step": 33
+    },
+    {
+      "epoch": 0.30699774266365687,
+      "grad_norm": 0.2715680003166199,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.1781,
+      "step": 34
+    },
+    {
+      "epoch": 0.3160270880361174,
+      "grad_norm": 0.3026103377342224,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.1607,
+      "step": 35
+    },
+    {
+      "epoch": 0.32505643340857787,
+      "grad_norm": 0.42034703493118286,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.784,
+      "step": 36
+    },
+    {
+      "epoch": 0.3340857787810384,
+      "grad_norm": 0.37357938289642334,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.5649,
+      "step": 37
+    },
+    {
+      "epoch": 0.3431151241534989,
+      "grad_norm": 0.15997634828090668,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.6707,
+      "step": 38
+    },
+    {
+      "epoch": 0.35214446952595935,
+      "grad_norm": 0.15511050820350647,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.4331,
+      "step": 39
+    },
+    {
+      "epoch": 0.3611738148984199,
+      "grad_norm": 0.1680152416229248,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.6783,
+      "step": 40
+    },
+    {
+      "epoch": 0.37020316027088035,
+      "grad_norm": 0.19817280769348145,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4853,
+      "step": 41
+    },
+    {
+      "epoch": 0.3792325056433409,
+      "grad_norm": 0.19002708792686462,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.5314,
+      "step": 42
+    },
+    {
+      "epoch": 0.38826185101580135,
+      "grad_norm": 0.20888566970825195,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5721,
+      "step": 43
+    },
+    {
+      "epoch": 0.3972911963882618,
+      "grad_norm": 0.1991356760263443,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.5912,
+      "step": 44
+    },
+    {
+      "epoch": 0.40632054176072235,
+      "grad_norm": 0.21265777945518494,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.5148,
+      "step": 45
+    },
+    {
+      "epoch": 0.4153498871331828,
+      "grad_norm": 0.21502944827079773,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2986,
+      "step": 46
+    },
+    {
+      "epoch": 0.42437923250564336,
+      "grad_norm": 0.23923197388648987,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.1442,
+      "step": 47
+    },
+    {
+      "epoch": 0.43340857787810383,
+      "grad_norm": 0.26049110293388367,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.1479,
+      "step": 48
+    },
+    {
+      "epoch": 0.44243792325056436,
+      "grad_norm": 0.35071879625320435,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.6991,
+      "step": 49
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "grad_norm": 0.3658585250377655,
+      "learning_rate": 0.0,
+      "loss": 0.4838,
+      "step": 50
+    },
+    {
+      "epoch": 0.45146726862302483,
+      "eval_loss": 1.1211003065109253,
+      "eval_runtime": 20.125,
+      "eval_samples_per_second": 37.068,
+      "eval_steps_per_second": 4.671,
+      "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": 5.310925972176896e+16,
+  "total_flos": 1.0621851944353792e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null