Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:85e0b16f9249504a49c7043b1de758136469c537c38a7c531fd96363eb427f20
+oid sha256:2ace6d69f732dbd4acc3c6ac7507945c08ff6543cf01287856a30f53a9b31880
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4d139d8bc75b32d1d95761b66b57e3b34ec501d2c6116517d9c5f3789728f5e3
+oid sha256:894133359bcc6edde7210a05e7080f9de1820c7ee2aac66c60613a116d8e6d9d
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d1427efbce5c6fbe9778837685c76ac26952aabd6520427d3c27d7d104bfa9
+oid sha256:c801cfe09e122b66f44061139227d1a92813ea205a79f325f6a0ae0703482cd7
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6d6e8bfaf30c539c4ca62ef13ad1943d5668c39873988868d8c8ecc4125821c
+oid sha256:b14e607ce7929e2aa6f64eafb6eb76d0248a1529a0d5dc9e1d2d77b79ec25bba
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05bcd12cc135d4ca9ff8459d0c8cd585ec8701ea961aa2951fa5190fb943b761
+oid sha256:1c1b6290612b59161cec881dd9859925d5bcdf4813b297b060759dc15332f39a
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba9c6a39bfe7c70806acea320f793e271b52dc48e29c8e5c044e356f4769d63
+oid sha256:8c06141a47ff35dd388ecab3b161650aa7aed2f274c8b4bc3477729b30425cad
 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": 0.3628028333187103,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.05813953488372093,
+  "best_metric": 0.23411691188812256,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.11627906976744186,
   "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": 34.109,
       "eval_steps_per_second": 4.274,
       "step": 25
+    },
+    {
+      "epoch": 0.06046511627906977,
+      "grad_norm": 88.96664428710938,
+      "learning_rate": 5e-05,
+      "loss": 0.396,
+      "step": 26
+    },
+    {
+      "epoch": 0.06279069767441861,
+      "grad_norm": 82.79183197021484,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 0.3057,
+      "step": 27
+    },
+    {
+      "epoch": 0.06511627906976744,
+      "grad_norm": 61.08711242675781,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 0.2818,
+      "step": 28
+    },
+    {
+      "epoch": 0.06744186046511629,
+      "grad_norm": 70.03043365478516,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 0.2947,
+      "step": 29
+    },
+    {
+      "epoch": 0.06976744186046512,
+      "grad_norm": 64.4678955078125,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 0.2746,
+      "step": 30
+    },
+    {
+      "epoch": 0.07209302325581396,
+      "grad_norm": 58.500099182128906,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 0.2671,
+      "step": 31
+    },
+    {
+      "epoch": 0.07441860465116279,
+      "grad_norm": 59.845664978027344,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 0.2728,
+      "step": 32
+    },
+    {
+      "epoch": 0.07674418604651163,
+      "grad_norm": 56.12503433227539,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 0.3234,
+      "step": 33
+    },
+    {
+      "epoch": 0.07906976744186046,
+      "grad_norm": 58.79863357543945,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 0.2889,
+      "step": 34
+    },
+    {
+      "epoch": 0.08139534883720931,
+      "grad_norm": 59.2402229309082,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 0.328,
+      "step": 35
+    },
+    {
+      "epoch": 0.08372093023255814,
+      "grad_norm": 46.734561920166016,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 0.3102,
+      "step": 36
+    },
+    {
+      "epoch": 0.08604651162790698,
+      "grad_norm": 48.9833869934082,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 0.2495,
+      "step": 37
+    },
+    {
+      "epoch": 0.08837209302325581,
+      "grad_norm": 49.06808853149414,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 0.3149,
+      "step": 38
+    },
+    {
+      "epoch": 0.09069767441860466,
+      "grad_norm": 66.39009094238281,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 0.2584,
+      "step": 39
+    },
+    {
+      "epoch": 0.09302325581395349,
+      "grad_norm": 46.767024993896484,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.2119,
+      "step": 40
+    },
+    {
+      "epoch": 0.09534883720930233,
+      "grad_norm": 43.55037307739258,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 0.2359,
+      "step": 41
+    },
+    {
+      "epoch": 0.09767441860465116,
+      "grad_norm": 51.920928955078125,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 0.2567,
+      "step": 42
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 51.2324333190918,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 0.3273,
+      "step": 43
+    },
+    {
+      "epoch": 0.10232558139534884,
+      "grad_norm": 41.81425094604492,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 0.2583,
+      "step": 44
+    },
+    {
+      "epoch": 0.10465116279069768,
+      "grad_norm": 35.66553497314453,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 0.1697,
+      "step": 45
+    },
+    {
+      "epoch": 0.10697674418604651,
+      "grad_norm": 47.469024658203125,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 0.2617,
+      "step": 46
+    },
+    {
+      "epoch": 0.10930232558139535,
+      "grad_norm": 52.34221649169922,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 0.3625,
+      "step": 47
+    },
+    {
+      "epoch": 0.11162790697674418,
+      "grad_norm": 40.48112869262695,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 0.2194,
+      "step": 48
+    },
+    {
+      "epoch": 0.11395348837209303,
+      "grad_norm": 44.73693084716797,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 0.2252,
+      "step": 49
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "grad_norm": 57.12425994873047,
+      "learning_rate": 0.0,
+      "loss": 0.2006,
+      "step": 50
+    },
+    {
+      "epoch": 0.11627906976744186,
+      "eval_loss": 0.23411691188812256,
+      "eval_runtime": 84.9204,
+      "eval_samples_per_second": 34.114,
+      "eval_steps_per_second": 4.275,
+      "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": 2.829013890367488e+17,
+  "total_flos": 5.658027780734976e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null