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:ea4c8563191a407eed5ba48e6245f31e918144d2246681a777bea8f0c5b94436
+oid sha256:57b6fc028ea237b5f9fb14bcb83c1c2c8099412e29e388838c604984c403bb83
 size 432223744

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ae10118dfb54c5066ff0935589d9b87a514845e702886e6856038af41ada85ea
+oid sha256:128e8008e7121d3c8f1197066f901fc62caa803e3f17f2e395ece839c775f433
 size 864785974

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:879f53e1dd037996cf122f02b9d426a4c155a37782e3d2c9a22631e93288ba6f
+oid sha256:03a5ae381d0a498feb79cb5da2c8a16919c69135ee2fde70ce70fa810429d97d
 size 14960

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f138a5263bd4ef87f3af1905d738e7da74e6de05398f6bab42b03c8439603c0c
+oid sha256:97f29ae4a69199ea22d1b3aaf93e42965c37f9a920f67d29c043d36416cd14a1
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:578419735b3f5108273166c930377b3279ff2b5286b609ff37fa4fda8c2c8be6
+oid sha256:a76a0521823a8dd43fe1c74d657a4776a6d0647e2da0d528738af956727fd4c0
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:228f7ffa2fe2c22bbce58dec6bdc5912805310588bbbc5b59bae49f7bec21f8c
+oid sha256:493327b3019f64bf765b77dc81a9681eecebd1f09456940b0b1c24fcc6e26e5e
 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": 3.9213130474090576,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0064196183536888735,
+  "best_metric": 3.8060593605041504,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.012839236707377747,
   "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": 9.769,
       "eval_steps_per_second": 1.221,
       "step": 25
+    },
+    {
+      "epoch": 0.006676403087836428,
+      "grad_norm": 1.3409721851348877,
+      "learning_rate": 5e-05,
+      "loss": 3.4359,
+      "step": 26
+    },
+    {
+      "epoch": 0.006933187821983983,
+      "grad_norm": 1.558974027633667,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 3.5878,
+      "step": 27
+    },
+    {
+      "epoch": 0.007189972556131538,
+      "grad_norm": 1.5054473876953125,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 3.6143,
+      "step": 28
+    },
+    {
+      "epoch": 0.007446757290279093,
+      "grad_norm": 1.3647345304489136,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 3.7567,
+      "step": 29
+    },
+    {
+      "epoch": 0.007703542024426648,
+      "grad_norm": 1.1692473888397217,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 3.772,
+      "step": 30
+    },
+    {
+      "epoch": 0.007960326758574202,
+      "grad_norm": 0.9748162031173706,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 3.7938,
+      "step": 31
+    },
+    {
+      "epoch": 0.008217111492721758,
+      "grad_norm": 0.8939160108566284,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.9191,
+      "step": 32
+    },
+    {
+      "epoch": 0.008473896226869313,
+      "grad_norm": 0.808001697063446,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 3.9843,
+      "step": 33
+    },
+    {
+      "epoch": 0.008730680961016868,
+      "grad_norm": 0.8469786047935486,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.9302,
+      "step": 34
+    },
+    {
+      "epoch": 0.008987465695164423,
+      "grad_norm": 0.9428398609161377,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 3.9169,
+      "step": 35
+    },
+    {
+      "epoch": 0.009244250429311977,
+      "grad_norm": 1.1682770252227783,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 4.044,
+      "step": 36
+    },
+    {
+      "epoch": 0.009501035163459532,
+      "grad_norm": 1.7911386489868164,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 4.1906,
+      "step": 37
+    },
+    {
+      "epoch": 0.009757819897607087,
+      "grad_norm": 0.841162919998169,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 3.4853,
+      "step": 38
+    },
+    {
+      "epoch": 0.010014604631754642,
+      "grad_norm": 0.656592071056366,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 3.4707,
+      "step": 39
+    },
+    {
+      "epoch": 0.010271389365902196,
+      "grad_norm": 0.6998878717422485,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 3.5523,
+      "step": 40
+    },
+    {
+      "epoch": 0.010528174100049753,
+      "grad_norm": 0.6899571418762207,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 3.6552,
+      "step": 41
+    },
+    {
+      "epoch": 0.010784958834197307,
+      "grad_norm": 0.6952070593833923,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 3.6545,
+      "step": 42
+    },
+    {
+      "epoch": 0.011041743568344862,
+      "grad_norm": 0.7949510216712952,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 3.8045,
+      "step": 43
+    },
+    {
+      "epoch": 0.011298528302492417,
+      "grad_norm": 0.7673659324645996,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 3.8022,
+      "step": 44
+    },
+    {
+      "epoch": 0.011555313036639972,
+      "grad_norm": 0.7975015640258789,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 3.8132,
+      "step": 45
+    },
+    {
+      "epoch": 0.011812097770787526,
+      "grad_norm": 0.8527703285217285,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 3.921,
+      "step": 46
+    },
+    {
+      "epoch": 0.012068882504935081,
+      "grad_norm": 0.9256014227867126,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 3.9535,
+      "step": 47
+    },
+    {
+      "epoch": 0.012325667239082636,
+      "grad_norm": 1.11979079246521,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 3.8955,
+      "step": 48
+    },
+    {
+      "epoch": 0.012582451973230192,
+      "grad_norm": 1.5714532136917114,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 4.1461,
+      "step": 49
+    },
+    {
+      "epoch": 0.012839236707377747,
+      "grad_norm": 2.802791118621826,
+      "learning_rate": 0.0,
+      "loss": 4.5027,
+      "step": 50
+    },
+    {
+      "epoch": 0.012839236707377747,
+      "eval_loss": 3.8060593605041504,
+      "eval_runtime": 2685.47,
+      "eval_samples_per_second": 9.77,
+      "eval_steps_per_second": 1.221,
+      "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": 3.315690861756416e+17,
+  "total_flos": 6.631381723512832e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null