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:bac9f32d996df640d3e91b30d574d47b1dd861f6d258f1db6ec4894a644caa2f
+oid sha256:66f8aa96fc46a747e1984bbaed681c09a75127b3866d79b638ead6ce537dea5d
 size 524363632

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c87316a966812e2b18f24f866592762738d5bf0f5a4c178f266f20089b8278f
+oid sha256:41eeccf15904333330c2603008c450af2233d7e71ed10cd8ffdc353fad28b57d
 size 1049049122

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c22df12f8c5fd29f23892226452f0ba73e412286107a36314e98553ed252a818
+oid sha256:5237d54593dbd9aea6d3ca20b086aff5c3f36f9e96856f083bd37ae64d057ebd
 size 15024

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:616bdd674dfdcd2e80a7974d470b13a0d1b81b06af1ca31ab6863c1b4342fc38
+oid sha256:4b6d3af1f4da4a0515590224a88536533f082fbab8962bdb2f2c77262ed75518
 size 15024

last-checkpoint/rng_state_2.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1258d2256f26127a475c9c66eb043d25c20405094089e15a8b9d112708b746
+oid sha256:fb0ada03f0387c3c6fcbd96c77671b143e905ff508cec9bb039f31a1f76d3b36
 size 15024

last-checkpoint/rng_state_3.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f37207610e1058d777b4ee489fa15dbf44d020573b5c67fe96e532e402d17cd8
+oid sha256:3b5822bb8b3d1e15ee34ad9ae3f16c34967208d4e88ef11b46628ebf720056f5
 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": 1.4412074089050293,
-  "best_model_checkpoint": "miner_id_24/checkpoint-25",
-  "epoch": 0.7920792079207921,
+  "best_metric": 1.396116852760315,
+  "best_model_checkpoint": "miner_id_24/checkpoint-50",
+  "epoch": 1.5841584158415842,
   "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": 21.35,
       "eval_steps_per_second": 1.353,
       "step": 25
+    },
+    {
+      "epoch": 0.8237623762376237,
+      "grad_norm": 5.965777397155762,
+      "learning_rate": 5e-05,
+      "loss": 1.3469,
+      "step": 26
+    },
+    {
+      "epoch": 0.8554455445544554,
+      "grad_norm": 4.295379161834717,
+      "learning_rate": 4.6729843538492847e-05,
+      "loss": 1.319,
+      "step": 27
+    },
+    {
+      "epoch": 0.8871287128712871,
+      "grad_norm": 4.880377292633057,
+      "learning_rate": 4.347369038899744e-05,
+      "loss": 1.2994,
+      "step": 28
+    },
+    {
+      "epoch": 0.9188118811881189,
+      "grad_norm": 4.994838237762451,
+      "learning_rate": 4.0245483899193595e-05,
+      "loss": 1.3067,
+      "step": 29
+    },
+    {
+      "epoch": 0.9504950495049505,
+      "grad_norm": 5.390483379364014,
+      "learning_rate": 3.705904774487396e-05,
+      "loss": 1.3938,
+      "step": 30
+    },
+    {
+      "epoch": 0.9821782178217822,
+      "grad_norm": 9.734456062316895,
+      "learning_rate": 3.392802673484193e-05,
+      "loss": 1.4057,
+      "step": 31
+    },
+    {
+      "epoch": 1.0138613861386139,
+      "grad_norm": 6.865916728973389,
+      "learning_rate": 3.086582838174551e-05,
+      "loss": 1.4327,
+      "step": 32
+    },
+    {
+      "epoch": 1.0455445544554456,
+      "grad_norm": 8.426886558532715,
+      "learning_rate": 2.7885565489049946e-05,
+      "loss": 1.528,
+      "step": 33
+    },
+    {
+      "epoch": 1.0772277227722773,
+      "grad_norm": 6.466370105743408,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 1.3748,
+      "step": 34
+    },
+    {
+      "epoch": 1.108910891089109,
+      "grad_norm": 6.0085601806640625,
+      "learning_rate": 2.2221488349019903e-05,
+      "loss": 1.2561,
+      "step": 35
+    },
+    {
+      "epoch": 1.1405940594059407,
+      "grad_norm": 5.070044040679932,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 1.2524,
+      "step": 36
+    },
+    {
+      "epoch": 1.1722772277227722,
+      "grad_norm": 5.348262310028076,
+      "learning_rate": 1.703270924499656e-05,
+      "loss": 1.297,
+      "step": 37
+    },
+    {
+      "epoch": 1.203960396039604,
+      "grad_norm": 6.561531066894531,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 1.3092,
+      "step": 38
+    },
+    {
+      "epoch": 1.2356435643564356,
+      "grad_norm": 8.211418151855469,
+      "learning_rate": 1.2408009626051137e-05,
+      "loss": 1.3696,
+      "step": 39
+    },
+    {
+      "epoch": 1.2673267326732673,
+      "grad_norm": 7.698812961578369,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 1.47,
+      "step": 40
+    },
+    {
+      "epoch": 1.299009900990099,
+      "grad_norm": 7.947728157043457,
+      "learning_rate": 8.426519384872733e-06,
+      "loss": 1.4385,
+      "step": 41
+    },
+    {
+      "epoch": 1.3306930693069308,
+      "grad_norm": 6.462954044342041,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 1.2735,
+      "step": 42
+    },
+    {
+      "epoch": 1.3623762376237623,
+      "grad_norm": 5.012844562530518,
+      "learning_rate": 5.156362923365588e-06,
+      "loss": 1.2215,
+      "step": 43
+    },
+    {
+      "epoch": 1.394059405940594,
+      "grad_norm": 5.397099494934082,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 1.3073,
+      "step": 44
+    },
+    {
+      "epoch": 1.4257425742574257,
+      "grad_norm": 5.290295124053955,
+      "learning_rate": 2.653493525244721e-06,
+      "loss": 1.2953,
+      "step": 45
+    },
+    {
+      "epoch": 1.4574257425742574,
+      "grad_norm": 6.2458319664001465,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 1.2694,
+      "step": 46
+    },
+    {
+      "epoch": 1.489108910891089,
+      "grad_norm": 10.212119102478027,
+      "learning_rate": 9.607359798384785e-07,
+      "loss": 1.4039,
+      "step": 47
+    },
+    {
+      "epoch": 1.5207920792079208,
+      "grad_norm": 10.062838554382324,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 1.5661,
+      "step": 48
+    },
+    {
+      "epoch": 1.5524752475247525,
+      "grad_norm": 6.744816780090332,
+      "learning_rate": 1.0705383806982606e-07,
+      "loss": 1.4388,
+      "step": 49
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "grad_norm": 6.674411296844482,
+      "learning_rate": 0.0,
+      "loss": 1.2739,
+      "step": 50
+    },
+    {
+      "epoch": 1.5841584158415842,
+      "eval_loss": 1.396116852760315,
+      "eval_runtime": 19.9429,
+      "eval_samples_per_second": 21.361,
+      "eval_steps_per_second": 1.354,
+      "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": 1.0952750720352256e+18,
+  "total_flos": 2.1905501440704512e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null