Training in progress, step 50, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6529576854130ef0755a365a94b882e3e967fe4128b4e9bd4b4bd49921295b6b
+oid sha256:cb23bdae31a074c4df5490c0dc8845aa108168dfd8d89576c66d9cda15e1575b
 size 323014168

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ba4bdde01bfae49074218917dfababaa883546ae51a7edc02ce32aa19100ba2
+oid sha256:b545f7418047f6ac84caa3e5b7c68e9146e9ac9b9013c29fe4c88d56f85074ba
 size 646253418

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c28d727c1dd9a7aab839ba7f6fd15bfc5564683a12ae132915b2eb6acea855fe
+oid sha256:ec35926f0b9f0d5a284720b8ec8b3df0f9ffcce4dc51b85865f29893cdb88e4d
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f118cb0c78cd7f9db5b9a4fa0127dc8d59371fd558815d19520118cbc6aac471
+oid sha256:934d222648ce0f7d4935b979ece431b0816a2e4dc7b4aa49133c2b2c722c21a9
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e760f20834aa779802c230d4d8e71dcf1a125a929ebc6a27c850f58c10ca00c
+oid sha256:cb0a58d702b273ed06823ecec73bc6327d347f9c1c3297816d99e849b4ff3d08
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2b0b86ccc1e71d45a54700bd85d64284da8dc95beb70c5cc0644e665addbfc37
+oid sha256:6825b601193f86811fe9d0b8d3b977097d3e6bc50cb9e88915caeafbc6a484a8
 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": 2.611330509185791,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.010865136493277196,
+  "best_metric": 1.8663398027420044,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.021730272986554392,
   "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": 16.52,
       "eval_steps_per_second": 2.065,
       "step": 25
+    },
+    {
+      "epoch": 0.011299741953008285,
+      "grad_norm": 4.896826267242432,
+      "learning_rate": 5e-05,
+      "loss": 1.9688,
+      "step": 26
+    },
+    {
+      "epoch": 0.011734347412739373,
+      "grad_norm": 5.283179759979248,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.6019,
+      "step": 27
+    },
+    {
+      "epoch": 0.01216895287247046,
+      "grad_norm": 4.623892784118652,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2992,
+      "step": 28
+    },
+    {
+      "epoch": 0.012603558332201548,
+      "grad_norm": 3.667201519012451,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.601,
+      "step": 29
+    },
+    {
+      "epoch": 0.013038163791932636,
+      "grad_norm": 2.6739249229431152,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.7889,
+      "step": 30
+    },
+    {
+      "epoch": 0.013472769251663724,
+      "grad_norm": 2.9542391300201416,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 2.5814,
+      "step": 31
+    },
+    {
+      "epoch": 0.013907374711394811,
+      "grad_norm": 3.9561479091644287,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 3.0254,
+      "step": 32
+    },
+    {
+      "epoch": 0.0143419801711259,
+      "grad_norm": 6.196057319641113,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 2.8031,
+      "step": 33
+    },
+    {
+      "epoch": 0.014776585630856988,
+      "grad_norm": 5.7320876121521,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 3.0618,
+      "step": 34
+    },
+    {
+      "epoch": 0.015211191090588076,
+      "grad_norm": 7.060523986816406,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 2.7292,
+      "step": 35
+    },
+    {
+      "epoch": 0.015645796550319162,
+      "grad_norm": 7.061924934387207,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.3804,
+      "step": 36
+    },
+    {
+      "epoch": 0.016080402010050253,
+      "grad_norm": 8.16179084777832,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 2.4146,
+      "step": 37
+    },
+    {
+      "epoch": 0.01651500746978134,
+      "grad_norm": 3.796286106109619,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.2274,
+      "step": 38
+    },
+    {
+      "epoch": 0.016949612929512428,
+      "grad_norm": 3.4712982177734375,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.2515,
+      "step": 39
+    },
+    {
+      "epoch": 0.017384218389243516,
+      "grad_norm": 3.254138946533203,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 0.9577,
+      "step": 40
+    },
+    {
+      "epoch": 0.017818823848974603,
+      "grad_norm": 3.0390448570251465,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.1358,
+      "step": 41
+    },
+    {
+      "epoch": 0.01825342930870569,
+      "grad_norm": 2.8244662284851074,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.1089,
+      "step": 42
+    },
+    {
+      "epoch": 0.01868803476843678,
+      "grad_norm": 2.83131742477417,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.5349,
+      "step": 43
+    },
+    {
+      "epoch": 0.019122640228167866,
+      "grad_norm": 3.1617980003356934,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.025,
+      "step": 44
+    },
+    {
+      "epoch": 0.019557245687898954,
+      "grad_norm": 3.827831268310547,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 2.6416,
+      "step": 45
+    },
+    {
+      "epoch": 0.01999185114763004,
+      "grad_norm": 3.7935428619384766,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.6091,
+      "step": 46
+    },
+    {
+      "epoch": 0.02042645660736113,
+      "grad_norm": 3.7722864151000977,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 2.6035,
+      "step": 47
+    },
+    {
+      "epoch": 0.020861062067092217,
+      "grad_norm": 3.868345022201538,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.4314,
+      "step": 48
+    },
+    {
+      "epoch": 0.021295667526823304,
+      "grad_norm": 5.436539173126221,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 2.1646,
+      "step": 49
+    },
+    {
+      "epoch": 0.021730272986554392,
+      "grad_norm": 6.8189239501953125,
+      "learning_rate": 0.0,
+      "loss": 2.1201,
+      "step": 50
+    },
+    {
+      "epoch": 0.021730272986554392,
+      "eval_loss": 1.8663398027420044,
+      "eval_runtime": 697.6266,
+      "eval_samples_per_second": 22.22,
+      "eval_steps_per_second": 2.778,
+      "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": 2.812028905324544e+17,
+  "total_flos": 5.624057810649088e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null