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:bfc1e769c48de955155738cdf9a81ee5e9f9eccf5677b5c034cc6a5f4c382b69
+oid sha256:eb4fb957253340adfe55f18e2b31ac37569688e6670656609e63fa361dc2ae5d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:92e798b704e72935e74e0a98d31a439b1a0ffd78657f11326502823b8e44339b
+oid sha256:942d2693a634db6713525d02741fd58a004eaff0f1be906a13133ddbc2623163
 size 671466706

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb8891d2a694a5493b418d519e40014388a24d8c95ac195f2a82857be6d22925
+oid sha256:6bb2d4521ffc775ebad6150610ef94661141b793fb894d8235ba11ae200a6f88
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffd484f7930081bc4f7f474982eb7d2a1f95c7f25d97cdfa168ad9f3086cbf0c
+oid sha256:ae986ca85f899c861f76bc3cc8277524c9d00efb29cba4870ffccea7df5aa3af
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3926eb51214d91d64dad56d1d8f570cf05e2986663050f347e566df223d3ceac
+oid sha256:2091a22600c4609e27530d8cea06eac4e4bee0f19268d6fe1068571890ce6ac5
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79beb9627b559e951d8f19cc5cdc6e660834b51a1f2d972acaf2bdc25029538a
+oid sha256:bfe29b7abe971989e61da1cfda3e7151b5e54150585f127348d1ab60930a18dc
 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": 1.894762635231018,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.0377643504531722,
+  "best_metric": 1.8761990070343018,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 0.0755287009063444,
   "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": 24.246,
       "eval_steps_per_second": 3.031,
       "step": 25
+    },
+    {
+      "epoch": 0.03927492447129909,
+      "grad_norm": 13.991535186767578,
+      "learning_rate": 5e-05,
+      "loss": 1.9516,
+      "step": 26
+    },
+    {
+      "epoch": 0.04078549848942598,
+      "grad_norm": 12.654444694519043,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.9724,
+      "step": 27
+    },
+    {
+      "epoch": 0.04229607250755287,
+      "grad_norm": 9.985688209533691,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.9129,
+      "step": 28
+    },
+    {
+      "epoch": 0.04380664652567976,
+      "grad_norm": 8.882885932922363,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.9091,
+      "step": 29
+    },
+    {
+      "epoch": 0.045317220543806644,
+      "grad_norm": 8.36329460144043,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.9237,
+      "step": 30
+    },
+    {
+      "epoch": 0.04682779456193353,
+      "grad_norm": 8.64007568359375,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.886,
+      "step": 31
+    },
+    {
+      "epoch": 0.04833836858006042,
+      "grad_norm": 9.498104095458984,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.9173,
+      "step": 32
+    },
+    {
+      "epoch": 0.04984894259818731,
+      "grad_norm": 9.14793586730957,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.9047,
+      "step": 33
+    },
+    {
+      "epoch": 0.0513595166163142,
+      "grad_norm": 9.84379768371582,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.8504,
+      "step": 34
+    },
+    {
+      "epoch": 0.052870090634441085,
+      "grad_norm": 10.553916931152344,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.8816,
+      "step": 35
+    },
+    {
+      "epoch": 0.054380664652567974,
+      "grad_norm": 11.11711311340332,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.852,
+      "step": 36
+    },
+    {
+      "epoch": 0.055891238670694864,
+      "grad_norm": 12.357012748718262,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.8347,
+      "step": 37
+    },
+    {
+      "epoch": 0.05740181268882175,
+      "grad_norm": 10.349846839904785,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.8391,
+      "step": 38
+    },
+    {
+      "epoch": 0.05891238670694864,
+      "grad_norm": 7.760517597198486,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.9363,
+      "step": 39
+    },
+    {
+      "epoch": 0.06042296072507553,
+      "grad_norm": 8.133441925048828,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.9542,
+      "step": 40
+    },
+    {
+      "epoch": 0.061933534743202415,
+      "grad_norm": 7.650514125823975,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.927,
+      "step": 41
+    },
+    {
+      "epoch": 0.0634441087613293,
+      "grad_norm": 7.582345008850098,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.9362,
+      "step": 42
+    },
+    {
+      "epoch": 0.0649546827794562,
+      "grad_norm": 8.583966255187988,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.9035,
+      "step": 43
+    },
+    {
+      "epoch": 0.06646525679758308,
+      "grad_norm": 8.344738960266113,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.8908,
+      "step": 44
+    },
+    {
+      "epoch": 0.06797583081570997,
+      "grad_norm": 7.929678440093994,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.871,
+      "step": 45
+    },
+    {
+      "epoch": 0.06948640483383686,
+      "grad_norm": 7.730828285217285,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.8825,
+      "step": 46
+    },
+    {
+      "epoch": 0.07099697885196375,
+      "grad_norm": 8.460161209106445,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.8743,
+      "step": 47
+    },
+    {
+      "epoch": 0.07250755287009064,
+      "grad_norm": 8.845512390136719,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.8665,
+      "step": 48
+    },
+    {
+      "epoch": 0.07401812688821752,
+      "grad_norm": 9.84435749053955,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.8485,
+      "step": 49
+    },
+    {
+      "epoch": 0.0755287009063444,
+      "grad_norm": 12.877066612243652,
+      "learning_rate": 0.0,
+      "loss": 1.7575,
+      "step": 50
+    },
+    {
+      "epoch": 0.0755287009063444,
+      "eval_loss": 1.8761990070343018,
+      "eval_runtime": 367.8841,
+      "eval_samples_per_second": 24.247,
+      "eval_steps_per_second": 3.031,
+      "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": 5.658021338284032e+17,
+  "total_flos": 1.1316042676568064e+18,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null