Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:88647d44eb35c095c5f98c1cf7456e59e85c9106f330bf1573b2d86f0f6329a5
+oid sha256:afe107455ad362e3fe94b17076eb8779d0d8357e9e7bf8bc30ed5ac297d59b6a
 size 156926880

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f97274c8dd9720f9ac8399b7f9c26c5798fe5f56144af3c6a1512e9f08b391ff
+oid sha256:1b5e5b7f1b82eee2db7187b0a6e29a9cfdfaa48994e8f75bc2f95bc730bcb6c9
 size 313998650

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d99c0eda8f3907cbbd3196c8c80418d2d514672c8326299f8a98eaf1a29e44e9
+oid sha256:618ab8cc56aa5f1d1f35a159bcd373057d46cd37ac1249c292d632876a61b6d6
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:eb4f92a4145894887a41a51654bb769e844a55fe25ebd24d77ed338ba33b00ee
+oid sha256:f58bfecd14f5e2eaaf61eb7a2be3930f5066ac94ff179eb9592082e108daf1e4
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d867e7619c218ffbfe9165d15d630f4de5eb76ba48c1a68a2f12196d7c9526
+oid sha256:2239b6defd803861fed09f3d5192857b778b531a0f80a5553c6b287368acd01b
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c93a8a2433d6fe04a39ec65d925e786380e5207eaadff2ef63fd6bc5b2eadc74
+oid sha256:8c06e4574100cc04c4eee9b3fd205f62d6f6b2ac1cb4224afdb24fad8656ce77
 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": 0.4249492883682251,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.04515182300485382,
+  "best_metric": 0.41177281737327576,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.09030364600970764,
   "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": 41.237,
       "eval_steps_per_second": 5.163,
       "step": 25
+    },
+    {
+      "epoch": 0.046957895925047975,
+      "grad_norm": 0.20495416224002838,
+      "learning_rate": 5e-05,
+      "loss": 0.3645,
+      "step": 26
+    },
+    {
+      "epoch": 0.048763968845242124,
+      "grad_norm": 0.24285714328289032,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3556,
+      "step": 27
+    },
+    {
+      "epoch": 0.05057004176543628,
+      "grad_norm": 0.25440144538879395,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.4104,
+      "step": 28
+    },
+    {
+      "epoch": 0.052376114685630436,
+      "grad_norm": 0.2471897006034851,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.4108,
+      "step": 29
+    },
+    {
+      "epoch": 0.054182187605824585,
+      "grad_norm": 0.26587310433387756,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.422,
+      "step": 30
+    },
+    {
+      "epoch": 0.05598826052601874,
+      "grad_norm": 0.2613593339920044,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.4146,
+      "step": 31
+    },
+    {
+      "epoch": 0.05779433344621289,
+      "grad_norm": 0.2861674427986145,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.4656,
+      "step": 32
+    },
+    {
+      "epoch": 0.059600406366407045,
+      "grad_norm": 0.2913093864917755,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.4247,
+      "step": 33
+    },
+    {
+      "epoch": 0.061406479286601194,
+      "grad_norm": 0.3075777292251587,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.438,
+      "step": 34
+    },
+    {
+      "epoch": 0.06321255220679535,
+      "grad_norm": 0.32408568263053894,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.4746,
+      "step": 35
+    },
+    {
+      "epoch": 0.0650186251269895,
+      "grad_norm": 0.34247300028800964,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.4418,
+      "step": 36
+    },
+    {
+      "epoch": 0.06682469804718366,
+      "grad_norm": 0.3859308362007141,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.4453,
+      "step": 37
+    },
+    {
+      "epoch": 0.06863077096737781,
+      "grad_norm": 0.2347421646118164,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.353,
+      "step": 38
+    },
+    {
+      "epoch": 0.07043684388757196,
+      "grad_norm": 0.21311472356319427,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.3831,
+      "step": 39
+    },
+    {
+      "epoch": 0.07224291680776611,
+      "grad_norm": 0.22881631553173065,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.4234,
+      "step": 40
+    },
+    {
+      "epoch": 0.07404898972796027,
+      "grad_norm": 0.2297966629266739,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.3825,
+      "step": 41
+    },
+    {
+      "epoch": 0.07585506264815442,
+      "grad_norm": 0.2609304189682007,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.4715,
+      "step": 42
+    },
+    {
+      "epoch": 0.07766113556834857,
+      "grad_norm": 0.25210073590278625,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.41,
+      "step": 43
+    },
+    {
+      "epoch": 0.07946720848854273,
+      "grad_norm": 0.2684996724128723,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.4345,
+      "step": 44
+    },
+    {
+      "epoch": 0.08127328140873688,
+      "grad_norm": 0.27470850944519043,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.4293,
+      "step": 45
+    },
+    {
+      "epoch": 0.08307935432893103,
+      "grad_norm": 0.27928435802459717,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.4149,
+      "step": 46
+    },
+    {
+      "epoch": 0.08488542724912518,
+      "grad_norm": 0.28541573882102966,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.4271,
+      "step": 47
+    },
+    {
+      "epoch": 0.08669150016931934,
+      "grad_norm": 0.30577269196510315,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.453,
+      "step": 48
+    },
+    {
+      "epoch": 0.08849757308951349,
+      "grad_norm": 0.3629637658596039,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.4461,
+      "step": 49
+    },
+    {
+      "epoch": 0.09030364600970764,
+      "grad_norm": 0.3974674344062805,
+      "learning_rate": 0.0,
+      "loss": 0.4008,
+      "step": 50
+    },
+    {
+      "epoch": 0.09030364600970764,
+      "eval_loss": 0.41177281737327576,
+      "eval_runtime": 90.5093,
+      "eval_samples_per_second": 41.211,
+      "eval_steps_per_second": 5.16,
+      "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": 7.952285976808653e+16,
+  "total_flos": 1.5899604877626573e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null